diff --git a/libpcre/AUTHORS b/libpcre/AUTHORS index adb4fc401..36e4aafbd 100644 --- a/libpcre/AUTHORS +++ b/libpcre/AUTHORS @@ -6,9 +6,9 @@ Email local part: ph10 Email domain: cam.ac.uk University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. +Cambridge, England. -Copyright (c) 1997-2006 University of Cambridge +Copyright (c) 1997-2007 University of Cambridge All rights reserved @@ -17,7 +17,7 @@ THE C++ WRAPPER LIBRARY Written by: Google Inc. -Copyright (c) 2006 Google Inc +Copyright (c) 2007 Google Inc All rights reserved #### diff --git a/libpcre/COPYING b/libpcre/COPYING deleted file mode 100644 index daea2e48a..000000000 --- a/libpcre/COPYING +++ /dev/null @@ -1,68 +0,0 @@ -PCRE LICENCE ------------- - -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Release 6 of PCRE is distributed under the terms of the "BSD" licence, as -specified below. The documentation for PCRE, supplied in the "doc" -directory, is distributed under the same terms as the software itself. - -The basic library functions are written in C and are freestanding. Also -included in the distribution is a set of C++ wrapper functions. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. - -Copyright (c) 1997-2006 University of Cambridge -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2006, Google Inc. -All rights reserved. - - -THE "BSD" LICENCE ------------------ - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the name of Google - Inc. nor the names of their contributors may be used to endorse or - promote products derived from this software without specific prior - written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. - -End diff --git a/libpcre/INSTALL b/libpcre/INSTALL index 08802812d..5458714e1 100644 --- a/libpcre/INSTALL +++ b/libpcre/INSTALL @@ -1,41 +1,54 @@ +Installation Instructions +************************* + +Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002, 2004, 2005, +2006 Free Software Foundation, Inc. + +This file is free documentation; the Free Software Foundation gives +unlimited permission to copy, distribute and modify it. + Basic Installation ================== - These are generic installation instructions that apply to systems that -can run the `configure' shell script - Unix systems and any that imitate -it. They are not specific to PCRE. There are PCRE-specific instructions -for non-Unix systems in the file NON-UNIX-USE. +Briefly, the shell commands `./configure; make; make install' should +configure, build, and install this package. The following +more-detailed instructions are generic; see the `README' file for +instructions specific to this package. The `configure' shell script attempts to guess correct values for various system-dependent variables used during compilation. It uses those values to create a `Makefile' in each directory of the package. It may also create one or more `.h' files containing system-dependent definitions. Finally, it creates a shell script `config.status' that -you can run in the future to recreate the current configuration, a file -`config.cache' that saves the results of its tests to speed up -reconfiguring, and a file `config.log' containing compiler output -(useful mainly for debugging `configure'). +you can run in the future to recreate the current configuration, and a +file `config.log' containing compiler output (useful mainly for +debugging `configure'). + + It can also use an optional file (typically called `config.cache' +and enabled with `--cache-file=config.cache' or simply `-C') that saves +the results of its tests to speed up reconfiguring. Caching is +disabled by default to prevent problems with accidental use of stale +cache files. If you need to do unusual things to compile the package, please try to figure out how `configure' could check whether to do them, and mail diffs or instructions to the address given in the `README' so they can -be considered for the next release. If at some point `config.cache' -contains results you don't want to keep, you may remove or edit it. +be considered for the next release. If you are using the cache, and at +some point `config.cache' contains results you don't want to keep, you +may remove or edit it. - The file `configure.in' is used to create `configure' by a program -called `autoconf'. You only need `configure.in' if you want to change -it or regenerate `configure' using a newer version of `autoconf'. + The file `configure.ac' (or `configure.in') is used to create +`configure' by a program called `autoconf'. You need `configure.ac' if +you want to change it or regenerate `configure' using a newer version +of `autoconf'. The simplest way to compile this package is: 1. `cd' to the directory containing the package's source code and type - `./configure' to configure the package for your system. If you're - using `csh' on an old version of System V, you might need to type - `sh ./configure' instead to prevent `csh' from trying to execute - `configure' itself. + `./configure' to configure the package for your system. - Running `configure' takes awhile. While running, it prints some - messages telling which features it is checking for. + Running `configure' might take a while. While running, it prints + some messages telling which features it is checking for. 2. Type `make' to compile the package. @@ -57,49 +70,49 @@ The simplest way to compile this package is: Compilers and Options ===================== - Some systems require unusual options for compilation or linking that -the `configure' script does not know about. You can give `configure' -initial values for variables by setting them in the environment. Using -a Bourne-compatible shell, you can do that on the command line like -this: - CC=c89 CFLAGS=-O2 LIBS=-lposix ./configure +Some systems require unusual options for compilation or linking that the +`configure' script does not know about. Run `./configure --help' for +details on some of the pertinent environment variables. -Or on systems that have the `env' program, you can do it like this: - env CPPFLAGS=-I/usr/local/include LDFLAGS=-s ./configure + You can give `configure' initial values for configuration parameters +by setting variables in the command line or in the environment. Here +is an example: + + ./configure CC=c99 CFLAGS=-g LIBS=-lposix + + *Note Defining Variables::, for more details. Compiling For Multiple Architectures ==================================== - You can compile the package for more than one kind of computer at the +You can compile the package for more than one kind of computer at the same time, by placing the object files for each architecture in their -own directory. To do this, you must use a version of `make' that -supports the `VPATH' variable, such as GNU `make'. `cd' to the +own directory. To do this, you can use GNU `make'. `cd' to the directory where you want the object files and executables to go and run the `configure' script. `configure' automatically checks for the source code in the directory that `configure' is in and in `..'. - If you have to use a `make' that does not supports the `VPATH' -variable, you have to compile the package for one architecture at a time -in the source code directory. After you have installed the package for -one architecture, use `make distclean' before reconfiguring for another -architecture. + With a non-GNU `make', it is safer to compile the package for one +architecture at a time in the source code directory. After you have +installed the package for one architecture, use `make distclean' before +reconfiguring for another architecture. Installation Names ================== - By default, `make install' will install the package's files in -`/usr/local/bin', `/usr/local/man', etc. You can specify an -installation prefix other than `/usr/local' by giving `configure' the -option `--prefix=PATH'. +By default, `make install' installs the package's commands under +`/usr/local/bin', include files under `/usr/local/include', etc. You +can specify an installation prefix other than `/usr/local' by giving +`configure' the option `--prefix=PREFIX'. You can specify separate installation prefixes for architecture-specific files and architecture-independent files. If you -give `configure' the option `--exec-prefix=PATH', the package will use -PATH as the prefix for installing programs and libraries. -Documentation and other data files will still use the regular prefix. +pass the option `--exec-prefix=PREFIX' to `configure', the package uses +PREFIX as the prefix for installing programs and libraries. +Documentation and other data files still use the regular prefix. In addition, if you use an unusual directory layout you can give -options like `--bindir=PATH' to specify different values for particular +options like `--bindir=DIR' to specify different values for particular kinds of files. Run `configure --help' for a list of the directories you can set and what kinds of files go in them. @@ -110,7 +123,7 @@ option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. Optional Features ================= - Some packages pay attention to `--enable-FEATURE' options to +Some packages pay attention to `--enable-FEATURE' options to `configure', where FEATURE indicates an optional part of the package. They may also pay attention to `--with-PACKAGE' options, where PACKAGE is something like `gnu-as' or `x' (for the X Window System). The @@ -125,48 +138,86 @@ you can use the `configure' options `--x-includes=DIR' and Specifying the System Type ========================== - There may be some features `configure' can not figure out -automatically, but needs to determine by the type of host the package -will run on. Usually `configure' can figure that out, but if it prints -a message saying it can not guess the host type, give it the -`--host=TYPE' option. TYPE can either be a short name for the system -type, such as `sun4', or a canonical name with three fields: +There may be some features `configure' cannot figure out automatically, +but needs to determine by the type of machine the package will run on. +Usually, assuming the package is built to be run on the _same_ +architectures, `configure' can figure that out, but if it prints a +message saying it cannot guess the machine type, give it the +`--build=TYPE' option. TYPE can either be a short name for the system +type, such as `sun4', or a canonical name which has the form: + CPU-COMPANY-SYSTEM -See the file `config.sub' for the possible values of each field. If -`config.sub' isn't included in this package, then this package doesn't -need to know the host type. +where SYSTEM can have one of these forms: - If you are building compiler tools for cross-compiling, you can also -use the `--target=TYPE' option to select the type of system they will -produce code for and the `--build=TYPE' option to select the type of -system on which you are compiling the package. + OS KERNEL-OS + + See the file `config.sub' for the possible values of each field. If +`config.sub' isn't included in this package, then this package doesn't +need to know the machine type. + + If you are _building_ compiler tools for cross-compiling, you should +use the option `--target=TYPE' to select the type of system they will +produce code for. + + If you want to _use_ a cross compiler, that generates code for a +platform different from the build platform, you should specify the +"host" platform (i.e., that on which the generated programs will +eventually be run) with `--host=TYPE'. Sharing Defaults ================ - If you want to set default values for `configure' scripts to share, -you can create a site shell script called `config.site' that gives -default values for variables like `CC', `cache_file', and `prefix'. +If you want to set default values for `configure' scripts to share, you +can create a site shell script called `config.site' that gives default +values for variables like `CC', `cache_file', and `prefix'. `configure' looks for `PREFIX/share/config.site' if it exists, then `PREFIX/etc/config.site' if it exists. Or, you can set the `CONFIG_SITE' environment variable to the location of the site script. A warning: not all `configure' scripts look for a site script. -Operation Controls +Defining Variables ================== - `configure' recognizes the following options to control how it -operates. +Variables not defined in a site shell script can be set in the +environment passed to `configure'. However, some packages may run +configure again during the build, and the customized values of these +variables may be lost. In order to avoid this problem, you should set +them in the `configure' command line, using `VAR=value'. For example: -`--cache-file=FILE' - Use and save the results of the tests in FILE instead of - `./config.cache'. Set FILE to `/dev/null' to disable caching, for - debugging `configure'. + ./configure CC=/usr/local2/bin/gcc + +causes the specified `gcc' to be used as the C compiler (unless it is +overridden in the site shell script). + +Unfortunately, this technique does not work for `CONFIG_SHELL' due to +an Autoconf bug. Until the bug is fixed you can use this workaround: + + CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash + +`configure' Invocation +====================== + +`configure' recognizes the following options to control how it operates. `--help' +`-h' Print a summary of the options to `configure', and exit. +`--version' +`-V' + Print the version of Autoconf used to generate the `configure' + script, and exit. + +`--cache-file=FILE' + Enable the cache: use and save the results of the tests in FILE, + traditionally `config.cache'. FILE defaults to `/dev/null' to + disable caching. + +`--config-cache' +`-C' + Alias for `--cache-file=config.cache'. + `--quiet' `--silent' `-q' @@ -178,8 +229,6 @@ operates. Look for the package's source code in directory DIR. Usually `configure' can determine that directory automatically. -`--version' - Print the version of Autoconf used to generate the `configure' - script, and exit. +`configure' also accepts some other, not widely useful, options. Run +`configure --help' for more details. -`configure' also accepts some other, not widely useful, options. diff --git a/libpcre/LICENCE b/libpcre/LICENCE index daea2e48a..4baa7d83a 100644 --- a/libpcre/LICENCE +++ b/libpcre/LICENCE @@ -4,7 +4,7 @@ PCRE LICENCE PCRE is a library of functions to support regular expressions whose syntax and semantics are as close as possible to those of the Perl 5 language. -Release 6 of PCRE is distributed under the terms of the "BSD" licence, as +Release 7 of PCRE is distributed under the terms of the "BSD" licence, as specified below. The documentation for PCRE, supplied in the "doc" directory, is distributed under the same terms as the software itself. @@ -20,9 +20,9 @@ Email local part: ph10 Email domain: cam.ac.uk University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. +Cambridge, England. -Copyright (c) 1997-2006 University of Cambridge +Copyright (c) 1997-2007 University of Cambridge All rights reserved. @@ -31,7 +31,7 @@ THE C++ WRAPPER FUNCTIONS Contributed by: Google Inc. -Copyright (c) 2006, Google Inc. +Copyright (c) 2007, Google Inc. All rights reserved. diff --git a/libpcre/Makefile.am b/libpcre/Makefile.am new file mode 100644 index 000000000..b15fe6dcc --- /dev/null +++ b/libpcre/Makefile.am @@ -0,0 +1,85 @@ +## Process this file with automake to produce Makefile.in. + +lib_LIBRARIES = + +# Some of the binaries we make are to be installed, and others are +# (non-user-visible) helper programs needed to build libpcre. +bin_PROGRAMS = +noinst_PROGRAMS = + +# Additional files to delete on 'make clean' and 'make maintainer-clean'. +CLEANFILES = +MAINTAINERCLEANFILES = + +pcre.h.generic: configure.ac + rm -f $@ + cp -p pcre.h $@ + +MAINTAINERCLEANFILES += pcre.h.generic + +# These are the header files we'll install. We do not distribute pcre.h because +# it is generated from pcre.h.in. +nodist_include_HEADERS = pcre.h +include_HEADERS = pcreposix.h + +bin_SCRIPTS = pcre-config + +## --------------------------------------------------------------- +## The dftables program is used to rebuild character tables before compiling +## PCRE, if --enable-rebuild-chartables is specified. It is not a user-visible +## program. The default (when --enable-rebuild-chartables is not specified) is +## to copy a distributed set of tables that are defined for ASCII code. In this +## case, dftables is not needed. + +if WITH_REBUILD_CHARTABLES + +noinst_PROGRAMS += dftables +dftables_SOURCES = dftables.c + +pcre_chartables.c: dftables$(EXEEXT) + ./dftables$(EXEEXT) $@ +else + +pcre_chartables.c: $(srcdir)/pcre_chartables.c.dist + rm -f $@ + $(LN_S) $(srcdir)/pcre_chartables.c.dist $@ + +endif # WITH_REBUILD_CHARTABLES + + +## The main pcre library +lib_LIBRARIES += libpcre.a +libpcre_a_SOURCES = \ + pcre_compile.c \ + pcre_config.c \ + pcre_dfa_exec.c \ + pcre_exec.c \ + pcre_fullinfo.c \ + pcre_get.c \ + pcre_globals.c \ + pcre_info.c \ + pcre_internal.h \ + pcre_maketables.c \ + pcre_newline.c \ + pcre_ord2utf8.c \ + pcre_refcount.c \ + pcre_study.c \ + pcre_tables.c \ + pcre_try_flipped.c \ + pcre_ucp_searchfuncs.c \ + pcre_valid_utf8.c \ + pcre_version.c \ + pcre_xclass.c \ + ucp.h \ + ucpinternal.h \ + ucptable.h + +## This file is generated as part of the building process, so don't distribute. +nodist_libpcre_a_SOURCES = pcre_chartables.c + +CLEANFILES += pcre_chartables.c + +# A compatibility line, the old build system worked with 'make test' +test: check ; + +## end Makefile.am diff --git a/libpcre/Makefile.in b/libpcre/Makefile.in index 6ec7d09d5..787c9b875 100644 --- a/libpcre/Makefile.in +++ b/libpcre/Makefile.in @@ -1,255 +1,789 @@ +# Makefile.in generated by automake 1.10 from Makefile.am. +# @configure_input@ -# Makefile.in for PCRE (Perl-Compatible Regular Expression) library. +# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, +# 2003, 2004, 2005, 2006 Free Software Foundation, Inc. +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ -# Edited substantially by fyodor@insecure.org to remove libtool dependency -# and strip it to just building the library. - -############################################################################# - -# PCRE is developed on a Unix system. I do not use Windows or Macs, and know -# nothing about building software on them. Although the code of PCRE should -# be very portable, the building system in this Makefile is designed for Unix -# systems. However, there are features that have been supplied to me by various -# people that should make it work on MinGW and Cygwin systems. - -# This setting enables Unix-style directory scanning in pcregrep, triggered -# by the -f option. Maybe one day someone will add code for other systems. - -PCREGREP_OSTYPE=-DIS_UNIX - -############################################################################# -# Libtool places .o files in the .libs directory; this can mean that "make" -# thinks is it not up-to-date when in fact it is. This setting helps when -# GNU "make" is being used. It presumably does no harm in other cases. - -VPATH=.libs - - -#---------------------------------------------------------------------------# -# The following lines are modified by "configure" to insert data that it is # -# given in its arguments, or which it finds out for itself. # -#---------------------------------------------------------------------------# - -SHELL = @SHELL@ -prefix = @prefix@ -exec_prefix = @exec_prefix@ -top_srcdir = @top_srcdir@ - -mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs - -# NB: top_builddir is not referred to directly below, but it is used in the -# setting of $(LIBTOOL), so don't remove it! - -top_builddir = . - -# BINDIR is the directory in which the pcregrep, pcretest, and pcre-config -# commands are installed. -# INCDIR is the directory in which the public header files pcre.h and -# pcreposix.h are installed. -# LIBDIR is the directory in which the libraries are installed. -# MANDIR is the directory in which the man pages are installed. - -BINDIR = @bindir@ -LIBDIR = @libdir@ -INCDIR = @includedir@ -MANDIR = @mandir@ - -# EXEEXT is set by configure to the extention of an executable file -# OBJEXT is set by configure to the extention of an object file -# The BUILD_* equivalents are the same but for the host we're building on - -EXEEXT = @EXEEXT@ -OBJEXT = @OBJEXT@ -# Note that these are just here to have a convenient place to look at the -# outcome. -BUILD_EXEEXT = @BUILD_EXEEXT@ -BUILD_OBJEXT = @BUILD_OBJEXT@ - -# POSIX_OBJ and POSIX_LOBJ are either set empty, or to the names of the -# POSIX object files. - -POSIX_OBJ = @POSIX_OBJ@ -POSIX_LOBJ = @POSIX_LOBJ@ - -# The compiler, C flags, preprocessor flags, etc - -CC = @CC@ +VPATH = @srcdir@ +pkgdatadir = $(datadir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +build_triplet = @build@ +host_triplet = @host@ +bin_PROGRAMS = +noinst_PROGRAMS = $(am__EXEEXT_1) +@WITH_REBUILD_CHARTABLES_TRUE@am__append_1 = dftables +subdir = . +DIST_COMMON = README $(am__configure_deps) $(include_HEADERS) \ + $(srcdir)/Makefile.am $(srcdir)/Makefile.in \ + $(srcdir)/config.h.in $(srcdir)/pcre-config.in \ + $(srcdir)/pcre.h.in $(top_srcdir)/configure AUTHORS COPYING \ + ChangeLog INSTALL NEWS config.guess config.sub depcomp \ + install-sh missing +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \ + configure.lineno config.status.lineno +mkinstalldirs = $(install_sh) -d +CONFIG_HEADER = config.h +CONFIG_CLEAN_FILES = pcre-config pcre.h +am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; +am__vpath_adj = case $$p in \ + $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \ + *) f=$$p;; \ + esac; +am__strip_dir = `echo $$p | sed -e 's|^.*/||'`; +am__installdirs = "$(DESTDIR)$(libdir)" "$(DESTDIR)$(bindir)" \ + "$(DESTDIR)$(bindir)" "$(DESTDIR)$(includedir)" \ + "$(DESTDIR)$(includedir)" +libLIBRARIES_INSTALL = $(INSTALL_DATA) +LIBRARIES = $(lib_LIBRARIES) AR = ar -RANLIB = @RANLIB@ -CXX = @CXX@ +ARFLAGS = cru +libpcre_a_AR = $(AR) $(ARFLAGS) +libpcre_a_LIBADD = +am_libpcre_a_OBJECTS = pcre_compile.$(OBJEXT) pcre_config.$(OBJEXT) \ + pcre_dfa_exec.$(OBJEXT) pcre_exec.$(OBJEXT) \ + pcre_fullinfo.$(OBJEXT) pcre_get.$(OBJEXT) \ + pcre_globals.$(OBJEXT) pcre_info.$(OBJEXT) \ + pcre_maketables.$(OBJEXT) pcre_newline.$(OBJEXT) \ + pcre_ord2utf8.$(OBJEXT) pcre_refcount.$(OBJEXT) \ + pcre_study.$(OBJEXT) pcre_tables.$(OBJEXT) \ + pcre_try_flipped.$(OBJEXT) pcre_ucp_searchfuncs.$(OBJEXT) \ + pcre_valid_utf8.$(OBJEXT) pcre_version.$(OBJEXT) \ + pcre_xclass.$(OBJEXT) +nodist_libpcre_a_OBJECTS = pcre_chartables.$(OBJEXT) +libpcre_a_OBJECTS = $(am_libpcre_a_OBJECTS) \ + $(nodist_libpcre_a_OBJECTS) +binPROGRAMS_INSTALL = $(INSTALL_PROGRAM) +@WITH_REBUILD_CHARTABLES_TRUE@am__EXEEXT_1 = dftables$(EXEEXT) +PROGRAMS = $(bin_PROGRAMS) $(noinst_PROGRAMS) +am__dftables_SOURCES_DIST = dftables.c +@WITH_REBUILD_CHARTABLES_TRUE@am_dftables_OBJECTS = \ +@WITH_REBUILD_CHARTABLES_TRUE@ dftables.$(OBJEXT) +dftables_OBJECTS = $(am_dftables_OBJECTS) +dftables_LDADD = $(LDADD) +binSCRIPT_INSTALL = $(INSTALL_SCRIPT) +SCRIPTS = $(bin_SCRIPTS) +DEFAULT_INCLUDES = -I.@am__isrc@ +depcomp = $(SHELL) $(top_srcdir)/depcomp +am__depfiles_maybe = depfiles +COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \ + $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +CCLD = $(CC) +LINK = $(CCLD) $(AM_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) $(LDFLAGS) -o $@ +SOURCES = $(libpcre_a_SOURCES) $(nodist_libpcre_a_SOURCES) \ + $(dftables_SOURCES) +DIST_SOURCES = $(libpcre_a_SOURCES) $(am__dftables_SOURCES_DIST) +includeHEADERS_INSTALL = $(INSTALL_HEADER) +nodist_includeHEADERS_INSTALL = $(INSTALL_HEADER) +HEADERS = $(include_HEADERS) $(nodist_include_HEADERS) +ETAGS = etags +CTAGS = ctags +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +distdir = $(PACKAGE)-$(VERSION) +top_distdir = $(distdir) +am__remove_distdir = \ + { test ! -d $(distdir) \ + || { find $(distdir) -type d ! -perm -200 -exec chmod u+w {} ';' \ + && rm -fr $(distdir); }; } +DIST_ARCHIVES = $(distdir).tar.gz $(distdir).tar.bz2 $(distdir).zip +GZIP_ENV = --best +distuninstallcheck_listfiles = find . -type f -print +distcleancheck_listfiles = find . -type f -print +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CCDEPMODE = @CCDEPMODE@ CFLAGS = @CFLAGS@ -CXXFLAGS = @CXXFLAGS@ -LDFLAGS = @LDFLAGS@ -CXXLDFLAGS = @CXXLDFLAGS@ - -CC_FOR_BUILD = @CC_FOR_BUILD@ -CFLAGS_FOR_BUILD = @CFLAGS_FOR_BUILD@ -CXX_FOR_BUILD = @CXX_FOR_BUILD@ -CXXFLAGS_FOR_BUILD = @CXXFLAGS_FOR_BUILD@ -LDFLAGS_FOR_BUILD = $(LDFLAGS) - -UCP = @UCP@ -NEWLINE = @NEWLINE@ -POSIX_MALLOC_THRESHOLD = @POSIX_MALLOC_THRESHOLD@ -LINK_SIZE = @LINK_SIZE@ -MATCH_LIMIT = @MATCH_LIMIT@ @MATCH_LIMIT_RECURSION@ -NO_RECURSE = @NO_RECURSE@ -EBCDIC = @EBCDIC@ - -INCLS = -I. -I$(top_srcdir) -DEFS = $(NEWLINE) $(LINK_SIZE) $(MATCH_LIMIT) -TARGET=libpcre.a +CPP = @CPP@ +CPPFLAGS = @CPPFLAGS@ +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +EXEEXT = @EXEEXT@ +EXTRA_LIBPCRE_LDFLAGS = @EXTRA_LIBPCRE_LDFLAGS@ +GREP = @GREP@ INSTALL = @INSTALL@ INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LDFLAGS = @LDFLAGS@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LN_S = @LN_S@ +LTLIBOBJS = @LTLIBOBJS@ +MAKEINFO = @MAKEINFO@ +MKDIR_P = @MKDIR_P@ +OBJEXT = @OBJEXT@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +PCRE_DATE = @PCRE_DATE@ +PCRE_MAJOR = @PCRE_MAJOR@ +PCRE_MINOR = @PCRE_MINOR@ +PCRE_PRERELEASE = @PCRE_PRERELEASE@ +RANLIB = @RANLIB@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +STRIP = @STRIP@ +VERSION = @VERSION@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +am__include = @am__include@ +am__leading_dot = @am__leading_dot@ +am__quote = @am__quote@ +am__tar = @am__tar@ +am__untar = @am__untar@ +bindir = @bindir@ +build = @build@ +build_alias = @build_alias@ +build_cpu = @build_cpu@ +build_os = @build_os@ +build_vendor = @build_vendor@ +builddir = @builddir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +host = @host@ +host_alias = @host_alias@ +host_cpu = @host_cpu@ +host_os = @host_os@ +host_vendor = @host_vendor@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libdir = @libdir@ +libexecdir = @libexecdir@ +localedir = @localedir@ +localstatedir = @localstatedir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +oldincludedir = @oldincludedir@ +pcre_have_bits_type_traits = @pcre_have_bits_type_traits@ +pcre_have_long_long = @pcre_have_long_long@ +pcre_have_type_traits = @pcre_have_type_traits@ +pcre_have_ulong_long = @pcre_have_ulong_long@ +pdfdir = @pdfdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +lib_LIBRARIES = libpcre.a -# These are the version numbers for the shared libraries +# Additional files to delete on 'make clean' and 'make maintainer-clean'. +CLEANFILES = pcre_chartables.c +MAINTAINERCLEANFILES = pcre.h.generic -PCRELIBVERSION = @PCRE_LIB_VERSION@ -PCREPOSIXLIBVERSION = @PCRE_POSIXLIB_VERSION@ +# These are the header files we'll install. We do not distribute pcre.h because +# it is generated from pcre.h.in. +nodist_include_HEADERS = pcre.h +include_HEADERS = pcreposix.h +bin_SCRIPTS = pcre-config +@WITH_REBUILD_CHARTABLES_TRUE@dftables_SOURCES = dftables.c +libpcre_a_SOURCES = \ + pcre_compile.c \ + pcre_config.c \ + pcre_dfa_exec.c \ + pcre_exec.c \ + pcre_fullinfo.c \ + pcre_get.c \ + pcre_globals.c \ + pcre_info.c \ + pcre_internal.h \ + pcre_maketables.c \ + pcre_newline.c \ + pcre_ord2utf8.c \ + pcre_refcount.c \ + pcre_study.c \ + pcre_tables.c \ + pcre_try_flipped.c \ + pcre_ucp_searchfuncs.c \ + pcre_valid_utf8.c \ + pcre_version.c \ + pcre_xclass.c \ + ucp.h \ + ucpinternal.h \ + ucptable.h -############################################################################## +nodist_libpcre_a_SOURCES = pcre_chartables.c +all: config.h + $(MAKE) $(AM_MAKEFLAGS) all-am + +.SUFFIXES: +.SUFFIXES: .c .o .obj +am--refresh: + @: +$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + echo ' cd $(srcdir) && $(AUTOMAKE) --gnu '; \ + cd $(srcdir) && $(AUTOMAKE) --gnu \ + && exit 0; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu Makefile'; \ + cd $(top_srcdir) && \ + $(AUTOMAKE) --gnu Makefile +.PRECIOUS: Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + echo ' $(SHELL) ./config.status'; \ + $(SHELL) ./config.status;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $@ $(am__depfiles_maybe)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $@ $(am__depfiles_maybe);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + $(SHELL) ./config.status --recheck + +$(top_srcdir)/configure: $(am__configure_deps) + cd $(srcdir) && $(AUTOCONF) +$(ACLOCAL_M4): $(am__aclocal_m4_deps) + cd $(srcdir) && $(ACLOCAL) $(ACLOCAL_AMFLAGS) + +config.h: stamp-h1 + @if test ! -f $@; then \ + rm -f stamp-h1; \ + $(MAKE) $(AM_MAKEFLAGS) stamp-h1; \ + else :; fi + +stamp-h1: $(srcdir)/config.h.in $(top_builddir)/config.status + @rm -f stamp-h1 + cd $(top_builddir) && $(SHELL) ./config.status config.h +$(srcdir)/config.h.in: $(am__configure_deps) + cd $(top_srcdir) && $(AUTOHEADER) + rm -f stamp-h1 + touch $@ + +distclean-hdr: + -rm -f config.h stamp-h1 +pcre-config: $(top_builddir)/config.status $(srcdir)/pcre-config.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +pcre.h: $(top_builddir)/config.status $(srcdir)/pcre.h.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +install-libLIBRARIES: $(lib_LIBRARIES) + @$(NORMAL_INSTALL) + test -z "$(libdir)" || $(MKDIR_P) "$(DESTDIR)$(libdir)" + @list='$(lib_LIBRARIES)'; for p in $$list; do \ + if test -f $$p; then \ + f=$(am__strip_dir) \ + echo " $(libLIBRARIES_INSTALL) '$$p' '$(DESTDIR)$(libdir)/$$f'"; \ + $(libLIBRARIES_INSTALL) "$$p" "$(DESTDIR)$(libdir)/$$f"; \ + else :; fi; \ + done + @$(POST_INSTALL) + @list='$(lib_LIBRARIES)'; for p in $$list; do \ + if test -f $$p; then \ + p=$(am__strip_dir) \ + echo " $(RANLIB) '$(DESTDIR)$(libdir)/$$p'"; \ + $(RANLIB) "$(DESTDIR)$(libdir)/$$p"; \ + else :; fi; \ + done + +uninstall-libLIBRARIES: + @$(NORMAL_UNINSTALL) + @list='$(lib_LIBRARIES)'; for p in $$list; do \ + p=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(libdir)/$$p'"; \ + rm -f "$(DESTDIR)$(libdir)/$$p"; \ + done + +clean-libLIBRARIES: + -test -z "$(lib_LIBRARIES)" || rm -f $(lib_LIBRARIES) +libpcre.a: $(libpcre_a_OBJECTS) $(libpcre_a_DEPENDENCIES) + -rm -f libpcre.a + $(libpcre_a_AR) libpcre.a $(libpcre_a_OBJECTS) $(libpcre_a_LIBADD) + $(RANLIB) libpcre.a +install-binPROGRAMS: $(bin_PROGRAMS) + @$(NORMAL_INSTALL) + test -z "$(bindir)" || $(MKDIR_P) "$(DESTDIR)$(bindir)" + @list='$(bin_PROGRAMS)'; for p in $$list; do \ + p1=`echo $$p|sed 's/$(EXEEXT)$$//'`; \ + if test -f $$p \ + ; then \ + f=`echo "$$p1" | sed 's,^.*/,,;$(transform);s/$$/$(EXEEXT)/'`; \ + echo " $(INSTALL_PROGRAM_ENV) $(binPROGRAMS_INSTALL) '$$p' '$(DESTDIR)$(bindir)/$$f'"; \ + $(INSTALL_PROGRAM_ENV) $(binPROGRAMS_INSTALL) "$$p" "$(DESTDIR)$(bindir)/$$f" || exit 1; \ + else :; fi; \ + done + +uninstall-binPROGRAMS: + @$(NORMAL_UNINSTALL) + @list='$(bin_PROGRAMS)'; for p in $$list; do \ + f=`echo "$$p" | sed 's,^.*/,,;s/$(EXEEXT)$$//;$(transform);s/$$/$(EXEEXT)/'`; \ + echo " rm -f '$(DESTDIR)$(bindir)/$$f'"; \ + rm -f "$(DESTDIR)$(bindir)/$$f"; \ + done + +clean-binPROGRAMS: + -test -z "$(bin_PROGRAMS)" || rm -f $(bin_PROGRAMS) + +clean-noinstPROGRAMS: + -test -z "$(noinst_PROGRAMS)" || rm -f $(noinst_PROGRAMS) +dftables$(EXEEXT): $(dftables_OBJECTS) $(dftables_DEPENDENCIES) + @rm -f dftables$(EXEEXT) + $(LINK) $(dftables_OBJECTS) $(dftables_LDADD) $(LIBS) +install-binSCRIPTS: $(bin_SCRIPTS) + @$(NORMAL_INSTALL) + test -z "$(bindir)" || $(MKDIR_P) "$(DESTDIR)$(bindir)" + @list='$(bin_SCRIPTS)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + if test -f $$d$$p; then \ + f=`echo "$$p" | sed 's|^.*/||;$(transform)'`; \ + echo " $(binSCRIPT_INSTALL) '$$d$$p' '$(DESTDIR)$(bindir)/$$f'"; \ + $(binSCRIPT_INSTALL) "$$d$$p" "$(DESTDIR)$(bindir)/$$f"; \ + else :; fi; \ + done + +uninstall-binSCRIPTS: + @$(NORMAL_UNINSTALL) + @list='$(bin_SCRIPTS)'; for p in $$list; do \ + f=`echo "$$p" | sed 's|^.*/||;$(transform)'`; \ + echo " rm -f '$(DESTDIR)$(bindir)/$$f'"; \ + rm -f "$(DESTDIR)$(bindir)/$$f"; \ + done + +mostlyclean-compile: + -rm -f *.$(OBJEXT) + +distclean-compile: + -rm -f *.tab.c + +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/dftables.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_chartables.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_compile.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_config.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_dfa_exec.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_exec.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_fullinfo.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_get.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_globals.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_info.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_maketables.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_newline.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_ord2utf8.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_refcount.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_study.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_tables.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_try_flipped.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_ucp_searchfuncs.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_valid_utf8.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_version.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_xclass.Po@am__quote@ + +.c.o: +@am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCC_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(COMPILE) -c $< + +.c.obj: +@am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ `$(CYGPATH_W) '$<'` +@am__fastdepCC_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(COMPILE) -c `$(CYGPATH_W) '$<'` +install-includeHEADERS: $(include_HEADERS) + @$(NORMAL_INSTALL) + test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)" + @list='$(include_HEADERS)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(includeHEADERS_INSTALL) '$$d$$p' '$(DESTDIR)$(includedir)/$$f'"; \ + $(includeHEADERS_INSTALL) "$$d$$p" "$(DESTDIR)$(includedir)/$$f"; \ + done + +uninstall-includeHEADERS: + @$(NORMAL_UNINSTALL) + @list='$(include_HEADERS)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(includedir)/$$f'"; \ + rm -f "$(DESTDIR)$(includedir)/$$f"; \ + done +install-nodist_includeHEADERS: $(nodist_include_HEADERS) + @$(NORMAL_INSTALL) + test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)" + @list='$(nodist_include_HEADERS)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(nodist_includeHEADERS_INSTALL) '$$d$$p' '$(DESTDIR)$(includedir)/$$f'"; \ + $(nodist_includeHEADERS_INSTALL) "$$d$$p" "$(DESTDIR)$(includedir)/$$f"; \ + done + +uninstall-nodist_includeHEADERS: + @$(NORMAL_UNINSTALL) + @list='$(nodist_include_HEADERS)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(includedir)/$$f'"; \ + rm -f "$(DESTDIR)$(includedir)/$$f"; \ + done + +ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES) + list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) ' { files[$$0] = 1; } \ + END { for (i in files) print i; }'`; \ + mkid -fID $$unique +tags: TAGS + +TAGS: $(HEADERS) $(SOURCES) config.h.in $(TAGS_DEPENDENCIES) \ + $(TAGS_FILES) $(LISP) + tags=; \ + here=`pwd`; \ + list='$(SOURCES) $(HEADERS) config.h.in $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) ' { files[$$0] = 1; } \ + END { for (i in files) print i; }'`; \ + if test -z "$(ETAGS_ARGS)$$tags$$unique"; then :; else \ + test -n "$$unique" || unique=$$empty_fix; \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + $$tags $$unique; \ + fi +ctags: CTAGS +CTAGS: $(HEADERS) $(SOURCES) config.h.in $(TAGS_DEPENDENCIES) \ + $(TAGS_FILES) $(LISP) + tags=; \ + here=`pwd`; \ + list='$(SOURCES) $(HEADERS) config.h.in $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) ' { files[$$0] = 1; } \ + END { for (i in files) print i; }'`; \ + test -z "$(CTAGS_ARGS)$$tags$$unique" \ + || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \ + $$tags $$unique + +GTAGS: + here=`$(am__cd) $(top_builddir) && pwd` \ + && cd $(top_srcdir) \ + && gtags -i $(GTAGS_ARGS) $$here + +distclean-tags: + -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags + +distdir: $(DISTFILES) + $(am__remove_distdir) + test -d $(distdir) || mkdir $(distdir) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + list='$(DISTFILES)'; \ + dist_files=`for file in $$list; do echo $$file; done | \ + sed -e "s|^$$srcdirstrip/||;t" \ + -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \ + case $$dist_files in \ + */*) $(MKDIR_P) `echo "$$dist_files" | \ + sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \ + sort -u` ;; \ + esac; \ + for file in $$dist_files; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + if test -d $$d/$$file; then \ + dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \ + fi; \ + cp -pR $$d/$$file $(distdir)$$dir || exit 1; \ + else \ + test -f $(distdir)/$$file \ + || cp -p $$d/$$file $(distdir)/$$file \ + || exit 1; \ + fi; \ + done + -find $(distdir) -type d ! -perm -777 -exec chmod a+rwx {} \; -o \ + ! -type d ! -perm -444 -links 1 -exec chmod a+r {} \; -o \ + ! -type d ! -perm -400 -exec chmod a+r {} \; -o \ + ! -type d ! -perm -444 -exec $(install_sh) -c -m a+r {} {} \; \ + || chmod -R a+r $(distdir) +dist-gzip: distdir + tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz + $(am__remove_distdir) +dist-bzip2: distdir + tardir=$(distdir) && $(am__tar) | bzip2 -9 -c >$(distdir).tar.bz2 + $(am__remove_distdir) + +dist-tarZ: distdir + tardir=$(distdir) && $(am__tar) | compress -c >$(distdir).tar.Z + $(am__remove_distdir) + +dist-shar: distdir + shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz + $(am__remove_distdir) +dist-zip: distdir + -rm -f $(distdir).zip + zip -rq $(distdir).zip $(distdir) + $(am__remove_distdir) + +dist dist-all: distdir + tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz + tardir=$(distdir) && $(am__tar) | bzip2 -9 -c >$(distdir).tar.bz2 + -rm -f $(distdir).zip + zip -rq $(distdir).zip $(distdir) + $(am__remove_distdir) + +# This target untars the dist file and tries a VPATH configuration. Then +# it guarantees that the distribution is self-contained by making another +# tarfile. +distcheck: dist + case '$(DIST_ARCHIVES)' in \ + *.tar.gz*) \ + GZIP=$(GZIP_ENV) gunzip -c $(distdir).tar.gz | $(am__untar) ;;\ + *.tar.bz2*) \ + bunzip2 -c $(distdir).tar.bz2 | $(am__untar) ;;\ + *.tar.Z*) \ + uncompress -c $(distdir).tar.Z | $(am__untar) ;;\ + *.shar.gz*) \ + GZIP=$(GZIP_ENV) gunzip -c $(distdir).shar.gz | unshar ;;\ + *.zip*) \ + unzip $(distdir).zip ;;\ + esac + chmod -R a-w $(distdir); chmod a+w $(distdir) + mkdir $(distdir)/_build + mkdir $(distdir)/_inst + chmod a-w $(distdir) + dc_install_base=`$(am__cd) $(distdir)/_inst && pwd | sed -e 's,^[^:\\/]:[\\/],/,'` \ + && dc_destdir="$${TMPDIR-/tmp}/am-dc-$$$$/" \ + && cd $(distdir)/_build \ + && ../configure --srcdir=.. --prefix="$$dc_install_base" \ + $(DISTCHECK_CONFIGURE_FLAGS) \ + && $(MAKE) $(AM_MAKEFLAGS) \ + && $(MAKE) $(AM_MAKEFLAGS) dvi \ + && $(MAKE) $(AM_MAKEFLAGS) check \ + && $(MAKE) $(AM_MAKEFLAGS) install \ + && $(MAKE) $(AM_MAKEFLAGS) installcheck \ + && $(MAKE) $(AM_MAKEFLAGS) uninstall \ + && $(MAKE) $(AM_MAKEFLAGS) distuninstallcheck_dir="$$dc_install_base" \ + distuninstallcheck \ + && chmod -R a-w "$$dc_install_base" \ + && ({ \ + (cd ../.. && umask 077 && mkdir "$$dc_destdir") \ + && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" install \ + && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" uninstall \ + && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" \ + distuninstallcheck_dir="$$dc_destdir" distuninstallcheck; \ + } || { rm -rf "$$dc_destdir"; exit 1; }) \ + && rm -rf "$$dc_destdir" \ + && $(MAKE) $(AM_MAKEFLAGS) dist \ + && rm -rf $(DIST_ARCHIVES) \ + && $(MAKE) $(AM_MAKEFLAGS) distcleancheck + $(am__remove_distdir) + @(echo "$(distdir) archives ready for distribution: "; \ + list='$(DIST_ARCHIVES)'; for i in $$list; do echo $$i; done) | \ + sed -e 1h -e 1s/./=/g -e 1p -e 1x -e '$$p' -e '$$x' +distuninstallcheck: + @cd $(distuninstallcheck_dir) \ + && test `$(distuninstallcheck_listfiles) | wc -l` -le 1 \ + || { echo "ERROR: files left after uninstall:" ; \ + if test -n "$(DESTDIR)"; then \ + echo " (check DESTDIR support)"; \ + fi ; \ + $(distuninstallcheck_listfiles) ; \ + exit 1; } >&2 +distcleancheck: distclean + @if test '$(srcdir)' = . ; then \ + echo "ERROR: distcleancheck can only run from a VPATH build" ; \ + exit 1 ; \ + fi + @test `$(distcleancheck_listfiles) | wc -l` -eq 0 \ + || { echo "ERROR: files left in build directory after distclean:" ; \ + $(distcleancheck_listfiles) ; \ + exit 1; } >&2 +check-am: all-am +check: check-am +all-am: Makefile $(LIBRARIES) $(PROGRAMS) $(SCRIPTS) $(HEADERS) \ + config.h +installdirs: + for dir in "$(DESTDIR)$(libdir)" "$(DESTDIR)$(bindir)" "$(DESTDIR)$(bindir)" "$(DESTDIR)$(includedir)" "$(DESTDIR)$(includedir)"; do \ + test -z "$$dir" || $(MKDIR_P) "$$dir"; \ + done +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + `test -z '$(STRIP)' || \ + echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install +mostlyclean-generic: + +clean-generic: + -test -z "$(CLEANFILES)" || rm -f $(CLEANFILES) + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." + -test -z "$(MAINTAINERCLEANFILES)" || rm -f $(MAINTAINERCLEANFILES) +clean: clean-am + +clean-am: clean-binPROGRAMS clean-generic clean-libLIBRARIES \ + clean-noinstPROGRAMS mostlyclean-am + +distclean: distclean-am + -rm -f $(am__CONFIG_DISTCLEAN_FILES) + -rm -rf ./$(DEPDIR) + -rm -f Makefile +distclean-am: clean-am distclean-compile distclean-generic \ + distclean-hdr distclean-tags + +dvi: dvi-am + +dvi-am: + +html: html-am + +info: info-am + +info-am: + +install-data-am: install-includeHEADERS install-nodist_includeHEADERS + +install-dvi: install-dvi-am + +install-exec-am: install-binPROGRAMS install-binSCRIPTS \ + install-libLIBRARIES + +install-html: install-html-am + +install-info: install-info-am + +install-man: + +install-pdf: install-pdf-am + +install-ps: install-ps-am + +installcheck-am: + +maintainer-clean: maintainer-clean-am + -rm -f $(am__CONFIG_DISTCLEAN_FILES) + -rm -rf $(top_srcdir)/autom4te.cache + -rm -rf ./$(DEPDIR) + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-compile mostlyclean-generic + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: uninstall-binPROGRAMS uninstall-binSCRIPTS \ + uninstall-includeHEADERS uninstall-libLIBRARIES \ + uninstall-nodist_includeHEADERS + +.MAKE: install-am install-strip + +.PHONY: CTAGS GTAGS all all-am am--refresh check check-am clean \ + clean-binPROGRAMS clean-generic clean-libLIBRARIES \ + clean-noinstPROGRAMS ctags dist dist-all dist-bzip2 dist-gzip \ + dist-shar dist-tarZ dist-zip distcheck distclean \ + distclean-compile distclean-generic distclean-hdr \ + distclean-tags distcleancheck distdir distuninstallcheck dvi \ + dvi-am html html-am info info-am install install-am \ + install-binPROGRAMS install-binSCRIPTS install-data \ + install-data-am install-dvi install-dvi-am install-exec \ + install-exec-am install-html install-html-am \ + install-includeHEADERS install-info install-info-am \ + install-libLIBRARIES install-man install-nodist_includeHEADERS \ + install-pdf install-pdf-am install-ps install-ps-am \ + install-strip installcheck installcheck-am installdirs \ + maintainer-clean maintainer-clean-generic mostlyclean \ + mostlyclean-compile mostlyclean-generic pdf pdf-am ps ps-am \ + tags uninstall uninstall-am uninstall-binPROGRAMS \ + uninstall-binSCRIPTS uninstall-includeHEADERS \ + uninstall-libLIBRARIES uninstall-nodist_includeHEADERS -OBJ = pcre_chartables.@OBJEXT@ \ - pcre_compile.@OBJEXT@ \ - pcre_config.@OBJEXT@ \ - pcre_dfa_exec.@OBJEXT@ \ - pcre_exec.@OBJEXT@ \ - pcre_fullinfo.@OBJEXT@ \ - pcre_get.@OBJEXT@ \ - pcre_globals.@OBJEXT@ \ - pcre_info.@OBJEXT@ \ - pcre_maketables.@OBJEXT@ \ - pcre_refcount.@OBJEXT@ \ - pcre_study.@OBJEXT@ \ - pcre_tables.@OBJEXT@ \ - pcre_try_flipped.@OBJEXT@ \ - pcre_version.@OBJEXT@ \ - pcre_xclass.@OBJEXT@ \ - $(POSIX_OBJ) +pcre.h.generic: configure.ac + rm -f $@ + cp -p pcre.h $@ -all: $(TARGET) +@WITH_REBUILD_CHARTABLES_TRUE@pcre_chartables.c: dftables$(EXEEXT) +@WITH_REBUILD_CHARTABLES_TRUE@ ./dftables$(EXEEXT) $@ -# Note that files generated by ./configure and by dftables are in the current -# directory, not the source directory. +@WITH_REBUILD_CHARTABLES_FALSE@pcre_chartables.c: $(srcdir)/pcre_chartables.c.dist +@WITH_REBUILD_CHARTABLES_FALSE@ rm -f $@ +@WITH_REBUILD_CHARTABLES_FALSE@ $(LN_S) $(srcdir)/pcre_chartables.c.dist $@ -pcre_chartables.@OBJEXT@: pcre_chartables.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) \ - $(POSIX_MALLOC_THRESHOLD) pcre_chartables.c - -pcre_compile.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_compile.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_compile.c - -pcre_config.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_config.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_config.c - -pcre_dfa_exec.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_dfa_exec.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_dfa_exec.c - -pcre_exec.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_exec.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_exec.c - -pcre_fullinfo.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_fullinfo.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_fullinfo.c - -pcre_get.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_get.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_get.c - -pcre_globals.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_globals.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_globals.c - -pcre_info.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_info.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_info.c - -pcre_maketables.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_maketables.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_maketables.c - -pcre_refcount.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_refcount.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_refcount.c - -pcre_study.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_study.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_study.c - -pcre_tables.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_tables.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_tables.c - -pcre_try_flipped.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_try_flipped.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_try_flipped.c - -pcre_version.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_version.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_version.c - -pcre_xclass.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_xclass.c - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_xclass.c - -pcreposix.@OBJEXT@: $(top_srcdir)/pcreposix.c $(top_srcdir)/pcreposix.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre.h config.h Makefile - @$(LTCOMPILE) $(POSIX_MALLOC_THRESHOLD) $(top_srcdir)/pcreposix.c - -$(TARGET): $(OBJ) - -rm -f libpcre.a - $(AR) cr $@ $(OBJ) - $(RANLIB) $@ - -# An auxiliary program makes the default character table source. This is put -# in the current directory, NOT the $top_srcdir directory. - -pcre_chartables.c: dftables@BUILD_EXEEXT@ - ./dftables@BUILD_EXEEXT@ pcre_chartables.c - -dftables.@BUILD_OBJEXT@: $(top_srcdir)/dftables.c \ - $(top_srcdir)/pcre_maketables.c $(top_srcdir)/pcre_internal.h \ - $(top_srcdir)/pcre.h config.h Makefile - $(CC) -c $(CFLAGS) $(INCLS) $(DEFS) -I. $(top_srcdir)/dftables.c - -dftables@BUILD_EXEEXT@: dftables.@BUILD_OBJEXT@ - $(CC) $(CFLAGS) -o dftables dftables.@OBJEXT@ - -# We deliberately omit dftables and pcre_chartables.c from 'make clean'; once -# made pcre_chartables.c shouldn't change, and if people have edited the tables -# by hand, you don't want to throw them away. - -clean:; -rm -rf *.@OBJEXT@ *.lo *.a *.la .libs pcretest@EXEEXT@ pcre_stringpiece_unittest@EXEEXT@ pcrecpp_unittest@EXEEXT@ pcre_scanner_unittest@EXEEXT@ pcregrep@EXEEXT@ testtry - -# But "make distclean" should get back to a virgin distribution - -distclean: clean - -rm -f pcre_chartables.c libtool pcre-config libpcre.pc \ - pcre_stringpiece.h pcrecpparg.h \ - dftables@EXEEXT@ RunGrepTest RunTest \ - Makefile config.h config.status config.log config.cache - -# End +# A compatibility line, the old build system worked with 'make test' +test: check ; +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/libpcre/NMAP_MODIFICATIONS b/libpcre/NMAP_MODIFICATIONS index 58eb28b61..89dc4bc79 100644 --- a/libpcre/NMAP_MODIFICATIONS +++ b/libpcre/NMAP_MODIFICATIONS @@ -1,128 +1,146 @@ -This directory conains a version of LibPCRE 6.7 that has been stripped -down to under half its original uncompressed size. So if you want -docs, tests and such, you should go to the PCRE website at +This directory conains a version of LibPCRE 7.2 that has been stripped +down to less than a third of its original uncompressed size. So if you +want docs, tests and such, you should go to the PCRE website at http://www.pcre.org . Here are the changes for the Nmap version: -o rm -rf doc testdata pcretest.c pcregrep.c pcredemo.c ChangeLog +o Started this NMAP_MODIFICATIONS file -o Renamed configure.in to configure.ac +o Removed these directories: +doc +testdata -o Removed RunGrepTest.in, Runtest.in +o Removed these files: +pcretest.c +pcregrep.c +pcredemo.c +RunGrepTest +RunTest +RunTest.bat +perltest.pl +Detrail +PrepareRelease +libpcre.pc.in +libpcrecpp.pc.in +pcre_printint.src +CMakeLists.txt +config-cmake.h.in +132html +makevp.bat +makevp_c.txt +makevp_l.txt +pcregexp.pas +ltmain.sh +ChangeLog +NEWS +HACKING +COPYING [Look at LICENCE] -o Removed pcretest and pcregrep from the Makefile.in all target: +o Got rid of the C++ wrapper, which included this step: + rm -f *.cc pcrecpparg.h.in pcrecpp.h pcre_scanner.h pcre_stringpiece.h.in ---- Makefile.in.old Sun Jul 20 23:00:56 2003 -+++ Makefile.in Sun Jul 20 23:01:13 2003 -@@ -103,7 +103,7 @@ - OBJ = maketables.@OBJEXT@ get.@OBJEXT@ study.@OBJEXT@ pcre.@OBJEXT@ @POSIX_OBJ@ - LOBJ = maketables.lo get.lo study.lo pcre.lo @POSIX_LOBJ@ - --all: libpcre.la @POSIX_LIB@ pcretest@EXEEXT@ pcregrep@EXEEXT@ @ON_WINDOWS@ winshared -+all: libpcre.la @POSIX_LIB@ @ON_WINDOWS@ winshared - - pcregrep@EXEEXT@: libpcre.la pcregrep.@OBJEXT@ @ON_WINDOWS@ winshared - $(LINK) -o pcregrep@EXEEXT@ pcregrep.@OBJEXT@ -lpcre +o Copied pcre.h.generic to pcre.h and pcre_chartables.c.dist to, you + guessed it, pcre_chartables.c (for Windows). Running ./configure in + UNIX just overwrites them with other ones. -o Stripped down Makefile and configure.ac substantially to remove +o Stripped down Makefile.am and configure.ac substantially to remove libtool dependency (was having trouble on Mac OS X), remove Windows stuff (Nmap uses a custom MS VC project for this), and insure it only worries about building libpcre.a (which is now build in the libpcre - directory rather than in libpcre/.libs ). + directory rather than in libpcre/.libs ). Removed quite a bit of + unneeded things from these files, as well as adding -fno-thread-jumps + when compiling on Mac OS X on Intel (original patch: Kurt Grutzmacher + grutz(a)jingojango.net). [The diff is FAR too large to included here] -o removed libpcre.pc.in +o Comment out some build configuration lines from pcre-internal.h because Nmap + builds a static library: -o Regenerated configure script by running 'aclocal; autoconf' - -o Get rid of C++ wrapper, which included this step: - rm -f pcrecpp.cc pcrecpp_unittest.cc pcre_scanner.cc pcre_scanner_unittest.cc pcre_stringpiece.cc pcre_stringpiece_unittest.cc pcrecpp.h pcrecpp.h.in pcre_scanner.h pcre_stringpiece.h pcre_stringpiece.h.in - -o Removed COPYING file as there is already a LICENSE file with exactly - the same contents. - -o Removed pcre_ucp_findchar.c and ucptable.c - -o Added this NMAP_MODIFICATIONS file - -o Remove some junk that deals with dynamic linking of pcre: ---- pcre.h (revision 2947) -+++ pcre.h (working copy) -@@ -47,19 +47,8 @@ - #define PCRE_DATE 15-Aug-2005 +--- pcre-7.2/pcre_internal.h 2007-06-12 08:39:55.000000000 -0500 ++++ libpcre/pcre_internal.h 2007-08-15 18:56:18.000000000 -0500 +@@ -112,15 +112,19 @@ PCRE_EXP_DATA_DEFN only if they are not - /* Win32 uses DLL by default; it needs special stuff for exported functions. */ -+/* Removed some defines here as I always compile staticly */ - --#ifdef _WIN32 --# ifdef PCRE_DEFINITION --# ifdef DLL_EXPORT --# define PCRE_DATA_SCOPE __declspec(dllexport) --# endif --# else --# ifndef PCRE_STATIC --# define PCRE_DATA_SCOPE extern __declspec(dllimport) --# endif --# endif --#endif -- - /* For other operating systems, we use the standard "extern". */ - - #ifndef PCRE_DATA_SCOPE - - -o Applied this patch from Kurt Grutzmacher (grutz(a)jingojango.net) -which adds the -fno-thread-jumps option when compiled on Mac OS X -intel: - ---- ../nmap-4.02Alpha2.orig/libpcre/configure.ac 2006-03-10 12:48: -34.000000000 -0800 -+++ libpcre/configure.ac 2006-03-10 12:49:33.000000000 -0800 -@@ -169,6 +169,18 @@ - UTF8=-DSUPPORT_UTF8 - fi - -+dnl MacOSX on Intel Hack to remove thread-jumps -+AC_CANONICAL_HOST -+ -+case "$host" in -+ i386-apple-darwin*) -+ macosx=yes -+ AC_DEFINE(MACOSX) -+ needs_cpp_precomp=yes -+ CFLAGS="$CFLAGS -fno-thread-jumps" -+ ;; -+esac -+ - dnl "Export" these variables - - AC_SUBST(BUILD_EXEEXT) -@@ -191,6 +203,7 @@ - AC_SUBST(POSIX_MALLOC_THRESHOLD) - AC_SUBST(UCP) - AC_SUBST(UTF8) -+AC_SUBST(CFLAGS) - - AC_SUBST(POSIX_OBJ) - AC_SUBST(POSIX_LOBJ) - -o rm pcre_printint.src - -o Comment out some build configuration lines from pcre.h because Nmap -builds a static library: ---- pcre.h (revision 4133) -+++ pcre.h (working copy) -@@ -58,8 +58,9 @@ - #define PCRE_DATE 04-Jul-2006 - - /* Win32 uses DLL by default; it needs special stuff for exported functions --when building PCRE. */ -+when building PCRE. -- COMMENTED OUT BECAUSE I COMPILE STATICALLY */ - -+/* - #ifdef _WIN32 - # ifdef PCRE_DEFINITION + #ifndef PCRE_EXP_DECL + # ifdef _WIN32 ++/* COMMENTED OUT AS IT'S COMPILED STATICALLY # ifdef DLL_EXPORT -@@ -71,6 +72,7 @@ + # define PCRE_EXP_DECL extern __declspec(dllexport) + # define PCRE_EXP_DEFN __declspec(dllexport) + # define PCRE_EXP_DATA_DEFN __declspec(dllexport) + # else ++*/ + # define PCRE_EXP_DECL extern + # define PCRE_EXP_DEFN + # define PCRE_EXP_DATA_DEFN ++/* + # endif ++*/ + # + # else + # ifdef __cplusplus + + +...and pcre.h.in/pcre.h.generic/pcre.h: + + +--- pcre-7.2/pcre.h.in 2007-06-04 05:18:02.000000000 -0500 ++++ libpcre/pcre.h.in 2007-08-15 19:24:46.000000000 -0500 +@@ -51,6 +51,7 @@ imported have to be identified as such. + export setting is defined in pcre_internal.h, which includes this file. So we + don't change an existing definition of PCRE_EXP_DECL. */ + ++/* + #ifndef PCRE_EXP_DECL + # ifdef _WIN32 + # ifndef PCRE_STATIC +@@ -58,6 +59,7 @@ don't change an existing definition of P # endif # endif #endif +*/ + + /* By default, we use the standard "extern" declarations. */ + + +..and pcreposix.h: + + +--- pcre-7.2/pcreposix.h 2007-04-04 09:04:40.000000000 -0500 ++++ libpcre/pcreposix.h 2007-08-15 20:31:42.000000000 -0500 +@@ -109,12 +109,14 @@ typedef struct { + imported have to be identified as such. When building PCRE, the appropriate + export settings are needed. */ + ++/* + #ifdef _WIN32 + # ifndef PCREPOSIX_STATIC + # define PCREPOSIX_EXP_DECL extern __declspec(dllimport) + # define PCREPOSIX_EXP_DEFN __declspec(dllimport) + # endif + #endif ++*/ + + /* By default, we use the standard "extern" declarations. */ + + +o Added pcre_winconfig.h, and include it in pcre_internal.h instead of config.h: + +--- pcre-7.2/pcre_internal.h 2007-06-12 08:39:55.000000000 -0500 ++++ libpcre/pcre_internal.h 2007-08-15 20:33:48.000000000 -0500 +@@ -69,7 +69,11 @@ be absolutely sure we get our version. * + + /* Get the definitions provided by running "configure" */ + ++#ifdef WIN32 ++#include "pcre_winconfig.h" ++#else + #include "config.h" ++#endif + + /* Standard C headers plus the external interface definition. The only time + setjmp and stdarg are used is when NO_RECURSE is set. */ + + +o Change the pcre.h #include in pcre_internal.h from to "pcre.h". + This seems to be needed on Windows. + +o Regenerated everything with 'automake; aclocal; autoconf' + diff --git a/libpcre/NON-UNIX-USE b/libpcre/NON-UNIX-USE index 459bdf2b4..a10c7041a 100644 --- a/libpcre/NON-UNIX-USE +++ b/libpcre/NON-UNIX-USE @@ -1,127 +1,121 @@ Compiling PCRE on non-Unix systems ---------------------------------- -See below for comments on Cygwin or MinGW and OpenVMS usage. I (Philip Hazel) -have no knowledge of Windows or VMS sytems and how their libraries work. The -items in the PCRE Makefile that relate to anything other than Unix-like systems -have been contributed by PCRE users. There are some other comments and files in -the Contrib directory on the ftp site that you may find useful. See +This document contains the following sections: + + General + Generic instructions for the PCRE C library + The C++ wrapper functions + Building for virtual Pascal + Comments about Win32 builds + Building under Windows with BCC5.5 + Building PCRE on OpenVMS + + +GENERAL + +I (Philip Hazel) have no knowledge of Windows or VMS sytems and how their +libraries work. The items in the PCRE distribution and Makefile that relate to +anything other than Unix-like systems are untested by me. + +There are some other comments and files in the Contrib directory on the ftp +site that you may find useful. See ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib -If you want to compile PCRE for a non-Unix system (or perhaps, more strictly, -for a system that does not support "configure" and "make" files), note that -the basic PCRE library consists entirely of code written in Standard C, and so -should compile successfully on any system that has a Standard C compiler and -library. The C++ wrapper functions are a separate issue (see below). +If you want to compile PCRE for a non-Unix system (especially for a system that +does not support "configure" and "make" files), note that the basic PCRE +library consists entirely of code written in Standard C, and so should compile +successfully on any system that has a Standard C compiler and library. The C++ +wrapper functions are a separate issue (see below). + +The PCRE distribution contains some experimental support for "cmake", but this +is incomplete and not documented. However if you are a "cmake" user you might +like to try building with "cmake". -GENERIC INSTRUCTIONS FOR THE C LIBRARY +GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY -The following are generic comments about building PCRE. The interspersed -indented commands are suggestions from Mark Tetrode as to which commands you -might use on a Windows system to build a static library. +The following are generic comments about building the PCRE C library "by hand". -(1) Copy or rename the file config.in as config.h, and change the macros that -define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0. -Unfortunately, because of the way Unix autoconf works, the default setting has -to be 0. You may also want to make changes to other macros in config.h. In -particular, if you want to force a specific value for newline, you can define -the NEWLINE macro. The default is to use '\n', thereby using whatever value -your compiler gives to '\n'. +(1) Copy or rename the file config.h.generic as config.h, and edit the macro + settings that it contains to whatever is appropriate for your environment. + In particular, if you want to force a specific value for newline, you can + define the NEWLINE macro. - rem Mark Tetrode's commands - copy config.in config.h - rem Use write, because notepad cannot handle UNIX files. Change values. - write config.h + An alternative approach is not to edit config.h, but to use -D on the + compiler command line to make any changes that you need. -(2) Compile dftables.c as a stand-alone program, and then run it with -the single argument "pcre_chartables.c". This generates a set of standard -character tables and writes them to that file. + NOTE: There have been occasions when the way in which certain parameters in + config.h are used has changed between releases. (In the configure/make + world, this is handled automatically.) When upgrading to a new release, you + are strongly advised to review config.h.generic before re-using what you + had previously. - rem Mark Tetrode's commands - rem Compile & run - cl -DSUPPORT_UTF8 -DSUPPORT_UCP dftables.c - dftables.exe pcre_chartables.c +(2) Copy or rename the file pcre.h.generic as pcre.h. -(3) Compile the following source files: +(3) EITHER: + Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. - pcre_chartables.c - pcre_compile.c - pcre_config.c - pcre_dfa_exec.c - pcre_exec.c - pcre_fullinfo.c - pcre_get.c - pcre_globals.c - pcre_info.c - pcre_maketables.c - pcre_ord2utf8.c - pcre_refcount.c - pcre_study.c - pcre_tables.c - pcre_try_flipped.c - pcre_ucp_searchfuncs.c - pcre_valid_utf8.c - pcre_version.c - pcre_xclass.c + OR: + Compile dftables.c as a stand-alone program, and then run it with the + single argument "pcre_chartables.c". This generates a set of standard + character tables and writes them to that file. The tables are generated + using the default C locale for your system. If you want to use a locale + that is specified by LC_xxx environment variables, add the -L option to + the dftables command. You must use this method if you are building on + a system that uses EBCDIC code. -and link them all together into an object library in whichever form your system -keeps such libraries. This is the pcre C library. If your system has static and -shared libraries, you may have to do this once for each type. + The tables in pcre_chartables.c are defaults. The caller of PCRE can + specify alternative tables at run time. - rem These comments are out-of-date, referring to a previous release which - rem had fewer source files. Replace with the file names from above. - rem Mark Tetrode's commands, for a static library - rem Compile & lib - cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c maketables.c get.c study.c pcre.c - lib /OUT:pcre.lib maketables.obj get.obj study.obj pcre.obj +(4) Compile the following source files: -(4) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix -library. + pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_info.c + pcre_maketables.c + pcre_newline.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_study.c + pcre_tables.c + pcre_try_flipped.c + pcre_ucp_searchfuncs.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c - rem Mark Tetrode's commands, for a static library - rem Compile & lib - cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c pcreposix.c - lib /OUT:pcreposix.lib pcreposix.obj + Now link them all together into an object library in whichever form your + system keeps such libraries. This is the basic PCRE C library. If your + system has static and shared libraries, you may have to do this once for + each type. -(5) Compile the test program pcretest.c. This needs the functions in the -pcre and pcreposix libraries when linking. +(5) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix + library. - rem Mark Tetrode's commands - rem compile & link - cl /F0x400000 pcretest.c pcre.lib pcreposix.lib +(6) Compile the test program pcretest.c. This needs the functions in the + pcre and pcreposix libraries when linking. -(6) Run pcretest on the testinput files in the testdata directory, and check -that the output matches the corresponding testoutput files. You must use the --i option when checking testinput2. Note that the supplied files are in Unix -format, with just LF characters as line terminators. You may need to edit them -to change this if your system uses a different convention. +(7) Run pcretest on the testinput files in the testdata directory, and check + that the output matches the corresponding testoutput files. Note that the + supplied files are in Unix format, with just LF characters as line + terminators. You may need to edit them to change this if your system uses a + different convention. - rem Mark Tetrode's commands - pcretest testdata\testinput1 testdata\myoutput1 - windiff testdata\testoutput1 testdata\myoutput1 - pcretest -i testdata\testinput2 testdata\myoutput2 - windiff testdata\testoutput2 testdata\myoutput2 - pcretest testdata\testinput3 testdata\myoutput3 - windiff testdata\testoutput3 testdata\myoutput3 - pcretest testdata\testinput4 testdata\myoutput4 - windiff testdata\testoutput4 testdata\myoutput4 - pcretest testdata\testinput5 testdata\myoutput5 - windiff testdata\testoutput5 testdata\myoutput5 - pcretest testdata\testinput6 testdata\myoutput6 - windiff testdata\testoutput6 testdata\myoutput6 - -Note that there are now three more tests (7, 8, 9) that did not exist when Mark -wrote those comments. The test the new pcre_dfa_exec() function. - -(7) If you want to use the pcregrep command, compile and link pcregrep.c; it -uses only the basic PCRE library. +(8) If you want to use the pcregrep command, compile and link pcregrep.c; it + uses only the basic PCRE library (it does not need the pcreposix library). THE C++ WRAPPER FUNCTIONS -The PCRE distribution now contains some C++ wrapper functions and tests, +The PCRE distribution also contains some C++ wrapper functions and tests, contributed by Google Inc. On a system that can use "configure" and "make", the functions are automatically built into a library called pcrecpp. It should be straightforward to compile the .cc files manually on other systems. The @@ -129,77 +123,101 @@ files called xxx_unittest.cc are test programs for each of the corresponding xxx.cc files. -FURTHER REMARKS - -If you have a system without "configure" but where you can use a Makefile, edit -Makefile.in to create Makefile, substituting suitable values for the variables -at the head of the file. - -Some help in building a Win32 DLL of PCRE in GnuWin32 environments was -contributed by Paul Sokolovsky. These environments are Mingw32 -(http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and CygWin -(http://sourceware.cygnus.com/cygwin/). Paul comments: - - For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get - pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically - linked pgrep and pcretest. If you have /bin/sh, run RunTest (three - main test go ok, locale not supported). - -Changes to do MinGW with autoconf 2.50 were supplied by Fred Cox -, who comments as follows: - - If you are using the PCRE DLL, the normal Unix style configure && make && - make check && make install should just work[*]. If you want to statically - link against the .a file, you must define PCRE_STATIC before including - pcre.h, otherwise the pcre_malloc and pcre_free exported functions will be - declared __declspec(dllimport), with hilarious results. See the configure.in - and pcretest.c for how it is done for the static test. - - Also, there will only be a libpcre.la, not a libpcreposix.la, as you - would expect from the Unix version. The single DLL includes the pcreposix - interface. - -[*] But note that the supplied test files are in Unix format, with just LF -characters as line terminators. You will have to edit them to change to CR LF -terminators. +BUILDING FOR VIRTUAL PASCAL A script for building PCRE using Borland's C++ compiler for use with VPASCAL -was contributed by Alexander Tokarev. It is called makevp.bat. +was contributed by Alexander Tokarev. Stefan Weber updated the script and added +additional files. The following files in the distribution are for building PCRE +for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. -These are some further comments about Win32 builds from Mark Evans. They -were contributed before Fred Cox's changes were made, so it is possible that -they may no longer be relevant. -"The documentation for Win32 builds is a bit shy. Under MSVC6 I -followed their instructions to the letter, but there were still -some things missing. +COMMENTS ABOUT WIN32 BUILDS -(1) Must #define STATIC for entire project if linking statically. - (I see no reason to use DLLs for code this compact.) This of - course is a project setting in MSVC under Preprocessor. +There are two ways of building PCRE using the "configure, make, make install" +paradigm on Windows systems: using MinGW or using Cygwin. These are not at all +the same thing; they are completely different from each other. There is also +some experimental, undocumented support for building using "cmake", which you +might like to try if you are familiar with "cmake". However, at the present +time, the "cmake" process builds only a static library (not a dll), and the +tests are not automatically run. -(2) Missing some #ifdefs relating to the function pointers - pcre_malloc and pcre_free. See my solution below. (The stubs - may not be mandatory but they made me feel better.)" +The MinGW home page (http://www.mingw.org/) says this: -========================= -#ifdef _WIN32 -#include + MinGW: A collection of freely available and freely distributable Windows + specific header files and import libraries combined with GNU toolsets that + allow one to produce native Windows programs that do not rely on any + 3rd-party C runtime DLLs. -void* malloc_stub(size_t N) -{ return malloc(N); } -void free_stub(void* p) -{ free(p); } -void *(*pcre_malloc)(size_t) = &malloc_stub; -void (*pcre_free)(void *) = &free_stub; +The Cygwin home page (http://www.cygwin.com/) says this: -#else + Cygwin is a Linux-like environment for Windows. It consists of two parts: -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; + . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing + substantial Linux API functionality -#endif -========================= + . A collection of tools which provide Linux look and feel. + + The Cygwin DLL currently works with all recent, commercially released x86 32 + bit and 64 bit versions of Windows, with the exception of Windows CE. + +On both MinGW and Cygwin, PCRE should build correctly using: + + ./configure && make && make install + +This should create two libraries called libpcre and libpcreposix, and, if you +have enabled building the C++ wrapper, a third one called libpcrecpp. These are +independent libraries: when you like with libpcreposix or libpcrecpp you must +also link with libpcre, which contains the basic functions. (Some earlier +releases of PCRE included the basic libpcre functions in libpcreposix. This no +longer happens.) + +If you want to statically link your program against a non-dll .a file, you must +define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and +pcre_free() exported functions will be declared __declspec(dllimport), with +unwanted results. + +Using Cygwin's compiler generates libraries and executables that depend on +cygwin1.dll. If a library that is generated this way is distributed, +cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL +licence, this forces not only PCRE to be under the GPL, but also the entire +application. A distributor who wants to keep their own code proprietary must +purchase an appropriate Cygwin licence. + +MinGW has no such restrictions. The MinGW compiler generates a library or +executable that can run standalone on Windows without any third party dll or +licensing issues. + +But there is more complication: + +If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is +to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a +front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's +gcc and MinGW's gcc). So, a user can: + +. Build native binaries by using MinGW or by getting Cygwin and using + -mno-cygwin. + +. Build binaries that depend on cygwin1.dll by using Cygwin with the normal + compiler flags. + +The test files that are supplied with PCRE are in Unix format, with LF +characters as line terminators. It may be necessary to change the line +terminators in order to get some of the tests to work. We hope to improve +things in this area in future. + + +BUILDING UNDER WINDOWS WITH BCC5.5 + +Michael Roy sent these comments about building PCRE under Windows with BCC5.5: + + Some of the core BCC libraries have a version of PCRE from 1998 built in, + which can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a + version mismatch. I'm including an easy workaround below, if you'd like to + include it in the non-unix instructions: + + When linking a project with BCC5.5, pcre.lib must be included before any of + the libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command + line. BUILDING PCRE ON OPENVMS @@ -266,4 +284,5 @@ $! Locale could not be set to fr $! ========================= +Last Updated: 13 June 2007 **** diff --git a/libpcre/README b/libpcre/README index 24d0b9749..2f4d3c577 100644 --- a/libpcre/README +++ b/libpcre/README @@ -5,51 +5,82 @@ The latest release of PCRE is always available from ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz +There is a mailing list for discussion about the development of PCRE at + + pcre-dev@exim.org + Please read the NEWS file if you are upgrading from a previous release. +The contents of this README file are: + + The PCRE APIs + Documentation for PCRE + Contributions by users of PCRE + Building PCRE on non-Unix systems + Building PCRE on Unix-like systems + Retrieving configuration information on Unix-like systems + Shared libraries on Unix-like systems + Cross-compiling on Unix-like systems + Using HP's ANSI C++ compiler (aCC) + Making new tarballs + Testing PCRE + Character tables + File manifest The PCRE APIs ------------- -PCRE is written in C, and it has its own API. The distribution now includes a -set of C++ wrapper functions, courtesy of Google Inc. (see the pcrecpp man page -for details). +PCRE is written in C, and it has its own API. The distribution also includes a +set of C++ wrapper functions (see the pcrecpp man page for details), courtesy +of Google Inc. -Also included are a set of C wrapper functions that are based on the POSIX -API. These end up in the library called libpcreposix. Note that this just -provides a POSIX calling interface to PCRE: the regular expressions themselves -still follow Perl syntax and semantics. The header file for the POSIX-style -functions is called pcreposix.h. The official POSIX name is regex.h, but I -didn't want to risk possible problems with existing files of that name by -distributing it that way. To use it with an existing program that uses the -POSIX API, it will have to be renamed or pointed at by a link. +In addition, there is a set of C wrapper functions that are based on the POSIX +regular expression API (see the pcreposix man page). These end up in the +library called libpcreposix. Note that this just provides a POSIX calling +interface to PCRE; the regular expressions themselves still follow Perl syntax +and semantics. The POSIX API is restricted, and does not give full access to +all of PCRE's facilities. + +The header file for the POSIX-style functions is called pcreposix.h. The +official POSIX name is regex.h, but I did not want to risk possible problems +with existing files of that name by distributing it that way. To use PCRE with +an existing program that uses the POSIX API, pcreposix.h will have to be +renamed or pointed at by a link. If you are using the POSIX interface to PCRE and there is already a POSIX regex -library installed on your system, you must take care when linking programs to +library installed on your system, as well as worrying about the regex.h header +file (as mentioned above), you must also take care when linking programs to ensure that they link with PCRE's libpcreposix library. Otherwise they may pick -up the "real" POSIX functions of the same name. +up the POSIX functions of the same name from the other library. + +One way of avoiding this confusion is to compile PCRE with the addition of +-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the +compiler flags (CFLAGS if you are using "configure" -- see below). This has the +effect of renaming the functions so that the names no longer clash. Of course, +you have to do the same thing for your applications, or write them using the +new names. Documentation for PCRE ---------------------- -If you install PCRE in the normal way, you will end up with an installed set of -man pages whose names all start with "pcre". The one that is just called "pcre" -lists all the others. In addition to these man pages, the PCRE documentation is -supplied in two other forms; however, as there is no standard place to install -them, they are left in the doc directory of the unpacked source distribution. -These forms are: +If you install PCRE in the normal way on a Unix-like system, you will end up +with a set of man pages whose names all start with "pcre". The one that is just +called "pcre" lists all the others. In addition to these man pages, the PCRE +documentation is supplied in two other forms: - 1. Files called doc/pcre.txt, doc/pcregrep.txt, and doc/pcretest.txt. The - first of these is a concatenation of the text forms of all the section 3 - man pages except those that summarize individual functions. The other two - are the text forms of the section 1 man pages for the pcregrep and - pcretest commands. Text forms are provided for ease of scanning with text - editors or similar tools. + 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and + doc/pcretest.txt in the source distribution. The first of these is a + concatenation of the text forms of all the section 3 man pages except + those that summarize individual functions. The other two are the text + forms of the section 1 man pages for the pcregrep and pcretest commands. + These text forms are provided for ease of scanning with text editors or + similar tools. They are installed in /share/doc/pcre, where + is the installation prefix (defaulting to /usr/local). - 2. A subdirectory called doc/html contains all the documentation in HTML - form, hyperlinked in various ways, and rooted in a file called - doc/index.html. + 2. A set of files containing all the documentation in HTML form, hyperlinked + in various ways, and rooted in a file called index.html, is distributed in + doc/html and installed in /share/doc/pcre/html. Contributions by users of PCRE @@ -59,27 +90,46 @@ You can find contributions from PCRE users in the directory ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib -where there is also a README file giving brief descriptions of what they are. -Several of them provide support for compiling PCRE on various flavours of -Windows systems (I myself do not use Windows). Some are complete in themselves; -others are pointers to URLs containing relevant files. +There is a README file giving brief descriptions of what they are. Some are +complete in themselves; others are pointers to URLs containing relevant files. +Some of this material is likely to be well out-of-date. Several of the earlier +contributions provided support for compiling PCRE on various flavours of +Windows (I myself do not use Windows). Nowadays there is more Windows support +in the standard distribution, so these contibutions have been archived. -Building PCRE on a Unix-like system ------------------------------------ +Building PCRE on non-Unix systems +--------------------------------- + +For a non-Unix system, please read the comments in the file NON-UNIX-USE, +though if your system supports the use of "configure" and "make" you may be +able to build PCRE in the same way as for Unix-like systems. + +PCRE has been compiled on many different operating systems. It should be +straightforward to build PCRE on any system that has a Standard C compiler and +library, because it uses only Standard C functions. + + +Building PCRE on Unix-like systems +---------------------------------- If you are using HP's ANSI C++ compiler (aCC), please see the special note in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. +The following instructions assume the use of the widely used "configure, make, +make install" process. There is also some experimental support for "cmake" in +the PCRE distribution, but it is incomplete and not documented. However, if you +are a "cmake" user, you might want to try it. + To build PCRE on a Unix-like system, first run the "configure" command from the PCRE distribution directory, with your current directory set to the directory where you want the files to be created. This command is a standard GNU "autoconf" configuration script, for which generic instructions are supplied in -INSTALL. +the file INSTALL. Most commonly, people build PCRE within its own distribution directory, and in -this case, on many systems, just running "./configure" is sufficient, but the -usual methods of changing standard defaults are available. For example: +this case, on many systems, just running "./configure" is sufficient. However, +the usual methods of changing standard defaults are available. For example: CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local @@ -103,8 +153,8 @@ library. You can read more about them in the pcrebuild man page. . If you want to suppress the building of the C++ wrapper library, you can add --disable-cpp to the "configure" command. Otherwise, when "configure" is run, - will try to find a C++ compiler and C++ header files, and if it succeeds, it - will try to build the C++ wrapper. + it will try to find a C++ compiler and C++ header files, and if it succeeds, + it will try to build the C++ wrapper. . If you want to make use of the support for UTF-8 character strings in PCRE, you must add --enable-utf8 to the "configure" command. Without it, the code @@ -118,17 +168,25 @@ library. You can read more about them in the pcrebuild man page. property table); only the basic two-letter properties such as Lu are supported. -. You can build PCRE to recognize either CR or LF or the sequence CRLF as - indicating the end of a line. Whatever you specify at build time is the - default; the caller of PCRE can change the selection at run time. The default - newline indicator is a single LF character (the Unix standard). You can - specify the default newline indicator by adding --newline-is-cr or - --newline-is-lf or --newline-is-crlf to the "configure" command, - respectively. +. You can build PCRE to recognize either CR or LF or the sequence CRLF or any + of the preceding, or any of the Unicode newline sequences as indicating the + end of a line. Whatever you specify at build time is the default; the caller + of PCRE can change the selection at run time. The default newline indicator + is a single LF character (the Unix standard). You can specify the default + newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf + or --enable-newline-is-crlf or --enable-newline-is-anycrlf or + --enable-newline-is-any to the "configure" command, respectively. + + If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of + the standard tests will fail, because the lines in the test files end with + LF. Even if the files are edited to change the line endings, there are likely + to be some failures. With --enable-newline-is-anycrlf or + --enable-newline-is-any, many tests should succeed, but there may be some + failures. . When called via the POSIX interface, PCRE uses malloc() to get additional storage for processing capturing parentheses if there are more than 10 of - them. You can increase this threshold by setting, for example, + them in a pattern. You can increase this threshold by setting, for example, --with-posix-malloc-threshold=20 @@ -141,8 +199,8 @@ library. You can read more about them in the pcrebuild man page. --with-match-limit=500000 on the "configure" command. This is just the default; individual calls to - pcre_exec() can supply their own value. There is discussion on the pcreapi - man page. + pcre_exec() can supply their own value. There is more discussion on the + pcreapi man page. . There is a separate counter that limits the depth of recursive function calls during a matching process. This also has a default of ten million, which is @@ -157,37 +215,61 @@ library. You can read more about them in the pcrebuild man page. . The default maximum compiled pattern size is around 64K. You can increase this by adding --with-link-size=3 to the "configure" command. You can increase it even more by setting --with-link-size=4, but this is unlikely - ever to be necessary. If you build PCRE with an increased link size, test 2 - (and 5 if you are using UTF-8) will fail. Part of the output of these tests - is a representation of the compiled pattern, and this changes with the link - size. + ever to be necessary. Increasing the internal link size will reduce + performance. . You can build PCRE so that its internal match() function that is called from - pcre_exec() does not call itself recursively. Instead, it uses blocks of data - from the heap via special functions pcre_stack_malloc() and pcre_stack_free() - to save data that would otherwise be saved on the stack. To build PCRE like - this, use + pcre_exec() does not call itself recursively. Instead, it uses memory blocks + obtained from the heap via the special functions pcre_stack_malloc() and + pcre_stack_free() to save data that would otherwise be saved on the stack. To + build PCRE like this, use --disable-stack-for-recursion on the "configure" command. PCRE runs more slowly in this mode, but it may be necessary in environments with limited stack sizes. This applies only to the pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not - use deeply nested recursion. + use deeply nested recursion. There is a discussion about stack sizes in the + pcrestack man page. -The "configure" script builds eight files for the basic C library: +. For speed, PCRE uses four tables for manipulating and identifying characters + whose code point values are less than 256. By default, it uses a set of + tables for ASCII encoding that is part of the distribution. If you specify + + --enable-rebuild-chartables + + a program called dftables is compiled and run in the default C locale when + you obey "make". It builds a source file called pcre_chartables.c. If you do + not specify this option, pcre_chartables.c is created as a copy of + pcre_chartables.c.dist. See "Character tables" below for further information. + +. It is possible to compile PCRE for use on systems that use EBCDIC as their + default character code (as opposed to ASCII) by specifying + + --enable-ebcdic + + This automatically implies --enable-rebuild-chartables (see above). + +The "configure" script builds the following files for the basic C library: . Makefile is the makefile that builds the library . config.h contains build-time configuration options for the library +. pcre.h is the public PCRE header file . pcre-config is a script that shows the settings of "configure" options . libpcre.pc is data for the pkg-config command . libtool is a script that builds shared and/or static libraries -. RunTest is a script for running tests on the library +. RunTest is a script for running tests on the basic C library . RunGrepTest is a script for running tests on the pcregrep command -In addition, if a C++ compiler is found, the following are also built: +Versions of config.h and pcre.h are distributed in the PCRE tarballs under +the names config.h.generic and pcre.h.generic. These are provided for the +benefit of those who have to built PCRE without the benefit of "configure". If +you use "configure", the .generic versions are not used. -. pcrecpp.h is the header file for programs that call PCRE via the C++ wrapper +If a C++ compiler is found, the following files are also built: + +. libpcrecpp.pc is data for the pkg-config command +. pcrecpparg.h is a header file for programs that call PCRE via the C++ wrapper . pcre_stringpiece.h is the header for the C++ "stringpiece" functions The "configure" script also creates config.status, which is an executable @@ -195,18 +277,65 @@ script that can be run to recreate the configuration, and config.log, which contains compiler output from tests that "configure" runs. Once "configure" has run, you can run "make". It builds two libraries, called -libpcre and libpcreposix, a test program called pcretest, and the pcregrep -command. If a C++ compiler was found on your system, it also builds the C++ -wrapper library, which is called libpcrecpp, and some test programs called -pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest. +libpcre and libpcreposix, a test program called pcretest, a demonstration +program called pcredemo, and the pcregrep command. If a C++ compiler was found +on your system, "make" also builds the C++ wrapper library, which is called +libpcrecpp, and some test programs called pcrecpp_unittest, +pcre_scanner_unittest, and pcre_stringpiece_unittest. Building the C++ wrapper +can be disabled by adding --disable-cpp to the "configure" command. -The command "make test" runs all the appropriate tests. Details of the PCRE -tests are given in a separate section of this document, below. +The command "make check" runs all the appropriate tests. Details of the PCRE +tests are given below in a separate section of this document. -You can use "make install" to copy the libraries, the public header files -pcre.h, pcreposix.h, pcrecpp.h, and pcre_stringpiece.h (the last two only if -the C++ wrapper was built), and the man pages to appropriate live directories -on your system, in the normal way. +You can use "make install" to install PCRE into live directories on your +system. The following are installed (file names are all relative to the + that is set when "configure" is run): + + Commands (bin): + pcretest + pcregrep + pcre-config + + Libraries (lib): + libpcre + libpcreposix + libpcrecpp (if C++ support is enabled) + + Configuration information (lib/pkgconfig): + libpcre.pc + libpcrecpp.pc (if C++ support is enabled) + + Header files (include): + pcre.h + pcreposix.h + pcre_scanner.h ) + pcre_stringpiece.h ) if C++ support is enabled + pcrecpp.h ) + pcrecpparg.h ) + + Man pages (share/man/man{1,3}): + pcregrep.1 + pcretest.1 + pcre.3 + pcre*.3 (lots more pages, all starting "pcre") + + HTML documentation (share/doc/pcre/html): + index.html + *.html (lots more pages, hyperlinked from index.html) + + Text file documentation (share/doc/pcre): + AUTHORS + COPYING + ChangeLog + LICENCE + NEWS + README + pcre.txt (a concatenation of the man(3) pages) + pcretest.txt the pcretest man page + pcregrep.txt the pcregrep man page + +Note that the pcredemo program that is built by "configure" is *not* installed +anywhere. It is a demonstration for programmers wanting to use PCRE. If you want to remove PCRE from your system, you can run "make uninstall". This removes all the files that "make install" installed. However, it does not @@ -216,9 +345,8 @@ remove any directories, because these are often shared with other programs. Retrieving configuration information on Unix-like systems --------------------------------------------------------- -Running "make install" also installs the command pcre-config, which can be used -to recall information about the PCRE configuration and installation. For -example: +Running "make install" installs the command pcre-config, which can be used to +recall information about the PCRE configuration and installation. For example: pcre-config --version @@ -237,7 +365,7 @@ single command is used. For example: pkg-config --cflags pcre The data is held in *.pc files that are installed in a directory called -pkgconfig. +/lib/pkgconfig. Shared libraries on Unix-like systems @@ -254,7 +382,7 @@ built. The programs pcretest and pcregrep are built to use these uninstalled libraries (by means of wrapper scripts in the case of shared libraries). When you use "make install" to install shared libraries, pcregrep and pcretest are automatically re-built to use the newly installed shared libraries before being -installed themselves. However, the versions left in the source directory still +installed themselves. However, the versions left in the build directory still use the uninstalled libraries. To build PCRE using static libraries only you must use --disable-shared when @@ -266,25 +394,33 @@ Then run "make" in the usual way. Similarly, you can use --disable-static to build only shared libraries. -Cross-compiling on a Unix-like system -------------------------------------- +Cross-compiling on Unix-like systems +------------------------------------ You can specify CC and CFLAGS in the normal way to the "configure" command, in -order to cross-compile PCRE for some other host. However, during the building -process, the dftables.c source file is compiled *and run* on the local host, in -order to generate the default character tables (the chartables.c file). It -therefore needs to be compiled with the local compiler, not the cross compiler. -You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD; -there are also CXX_FOR_BUILD and CXXFLAGS_FOR_BUILD for the C++ wrapper) -when calling the "configure" command. If they are not specified, they default -to the values of CC and CFLAGS. +order to cross-compile PCRE for some other host. However, you should NOT +specify --enable-rebuild-chartables, because if you do, the dftables.c source +file is compiled and run on the local host, in order to generate the inbuilt +character tables (the pcre_chartables.c file). This will probably not work, +because dftables.c needs to be compiled with the local compiler, not the cross +compiler. + +When --enable-rebuild-chartables is not specified, pcre_chartables.c is created +by making a copy of pcre_chartables.c.dist, which is a default set of tables +that assumes ASCII code. Cross-compiling with the default tables should not be +a problem. + +If you need to modify the character tables when cross-compiling, you should +move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and +run it on the local host to make a new version of pcre_chartables.c.dist. +Then when you cross-compile PCRE this new version of the tables will be used. Using HP's ANSI C++ compiler (aCC) ---------------------------------- -Unless C++ support is disabled by specifiying the "--disable-cpp" option of the -"configure" script, you *must* include the "-AA" option in the CXXFLAGS +Unless C++ support is disabled by specifying the "--disable-cpp" option of the +"configure" script, you must include the "-AA" option in the CXXFLAGS environment variable in order for the C++ components to compile correctly. Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby @@ -296,49 +432,48 @@ running the "configure" script: CXXLDFLAGS="-lstd_v2 -lCsup_v2" -Building on non-Unix systems ----------------------------- +Making new tarballs +------------------- -For a non-Unix system, read the comments in the file NON-UNIX-USE, though if -the system supports the use of "configure" and "make" you may be able to build -PCRE in the same way as for Unix systems. +The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and +zip formats. The command "make distcheck" does the same, but then does a trial +build of the new distribution to ensure that it works. -PCRE has been compiled on Windows systems and on Macintoshes, but I don't know -the details because I don't use those systems. It should be straightforward to -build PCRE on any system that has a Standard C compiler, because it uses only -Standard C functions. +If you have modified any of the man page sources in the doc directory, you +should first run the PrepareRelease script before making a distribution. This +script creates the .txt and HTML forms of the documentation from the man pages. Testing PCRE ------------ -To test PCRE on a Unix system, run the RunTest script that is created by the -configuring process. There is also a script called RunGrepTest that tests the -options of the pcregrep command. If the C++ wrapper library is build, three -test programs called pcrecpp_unittest, pcre_scanner_unittest, and -pcre_stringpiece_unittest are provided. +To test the basic PCRE library on a Unix system, run the RunTest script that is +created by the configuring process. There is also a script called RunGrepTest +that tests the options of the pcregrep command. If the C++ wrapper library is +built, three test programs called pcrecpp_unittest, pcre_scanner_unittest, and +pcre_stringpiece_unittest are also built. -Both the scripts and all the program tests are run if you obey "make runtest", -"make check", or "make test". For other systems, see the instructions in -NON-UNIX-USE. +Both the scripts and all the program tests are run if you obey "make check" or +"make test". For other systems, see the instructions in NON-UNIX-USE. The RunTest script runs the pcretest test program (which is documented in its -own man page) on each of the testinput files (in the testdata directory) in +own man page) on each of the testinput files in the testdata directory in turn, and compares the output with the contents of the corresponding testoutput -file. A file called testtry is used to hold the main output from pcretest +files. A file called testtry is used to hold the main output from pcretest (testsavedregex is also used as a working file). To run pcretest on just one of the test files, give its number as an argument to RunTest, for example: RunTest 2 -The first file can also be fed directly into the perltest script to check that -Perl gives the same results. The only difference you should see is in the first -few lines, where the Perl version is given instead of the PCRE version. +The first test file can also be fed directly into the perltest.pl script to +check that Perl gives the same results. The only difference you should see is +in the first few lines, where the Perl version is given instead of the PCRE +version. The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(), pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error detection, and run-time flags that are specific to PCRE, as well as the POSIX -wrapper API. It also uses the debugging flag to check some of the internals of +wrapper API. It also uses the debugging flags to check some of the internals of pcre_compile(). If you build PCRE with a locale setting that is not the standard C locale, the @@ -364,6 +499,9 @@ is output to say why. If running this test produces instances of the error in the comparison output, it means that locale is not available on your system, despite being listed by "locale". This does not mean that PCRE is broken. +[If you are trying to run this test on Windows, you may be able to get it to +work by changing "fr_FR" to "french" everywhere it occurs.] + The fourth test checks the UTF-8 support. It is not run automatically unless PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when running "configure". This file can be also fed directly to the perltest script, @@ -373,8 +511,8 @@ commented in the script, can be be used.) The fifth test checks error handling with UTF-8 encoding, and internal UTF-8 features of PCRE that are not relevant to Perl. -The sixth and test checks the support for Unicode character properties. It it -not run automatically unless PCRE is built with Unicode property support. To to +The sixth test checks the support for Unicode character properties. It it not +run automatically unless PCRE is built with Unicode property support. To to this you must set --enable-unicode-properties when running "configure". The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative @@ -386,27 +524,42 @@ automatically unless PCRE is build with the relevant support. Character tables ---------------- -PCRE uses four tables for manipulating and identifying characters whose values -are less than 256. The final argument of the pcre_compile() function is a -pointer to a block of memory containing the concatenated tables. A call to -pcre_maketables() can be used to generate a set of tables in the current -locale. If the final argument for pcre_compile() is passed as NULL, a set of -default tables that is built into the binary is used. +For speed, PCRE uses four tables for manipulating and identifying characters +whose code point values are less than 256. The final argument of the +pcre_compile() function is a pointer to a block of memory containing the +concatenated tables. A call to pcre_maketables() can be used to generate a set +of tables in the current locale. If the final argument for pcre_compile() is +passed as NULL, a set of default tables that is built into the binary is used. -The source file called chartables.c contains the default set of tables. This is -not supplied in the distribution, but is built by the program dftables -(compiled from dftables.c), which uses the ANSI C character handling functions -such as isalnum(), isalpha(), isupper(), islower(), etc. to build the table -sources. This means that the default C locale which is set for your system will -control the contents of these default tables. You can change the default tables -by editing chartables.c and then re-building PCRE. If you do this, you should -probably also edit Makefile to ensure that the file doesn't ever get -re-generated. +The source file called pcre_chartables.c contains the default set of tables. By +default, this is created as a copy of pcre_chartables.c.dist, which contains +tables for ASCII coding. However, if --enable-rebuild-chartables is specified +for ./configure, a different version of pcre_chartables.c is built by the +program dftables (compiled from dftables.c), which uses the ANSI C character +handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to +build the table sources. This means that the default C locale which is set for +your system will control the contents of these default tables. You can change +the default tables by editing pcre_chartables.c and then re-building PCRE. If +you do this, you should take care to ensure that the file does not get +automatically re-generated. The best way to do this is to move +pcre_chartables.c.dist out of the way and replace it with your customized +tables. + +When the dftables program is run as a result of --enable-rebuild-chartables, +it uses the default C locale that is set on your system. It does not pay +attention to the LC_xxx environment variables. In other words, it uses the +system's default locale rather than whatever the compiling user happens to have +set. If you really do want to build a source set of character tables in a +locale that is specified by the LC_xxx variables, you can run the dftables +program by hand with the -L option. For example: + + ./dftables -L pcre_chartables.c.special The first two 256-byte tables provide lower casing and case flipping functions, respectively. The next table consists of three 32-byte bit maps which identify digits, "word" characters, and white space, respectively. These are used when -building 32-byte bit maps that represent character classes. +building 32-byte bit maps that represent character classes for code points less +than 256. The final 256-byte table has bits indicating various character types, as follows: @@ -422,107 +575,143 @@ You should not alter the set of characters that contain the 128 bit, as that will cause PCRE to malfunction. -Manifest --------- +File manifest +------------- The distribution should contain the following files: -(A) The actual source files of the PCRE library functions and their - headers: +(A) Source files of the PCRE library functions and their headers: - dftables.c auxiliary program for building chartables.c + dftables.c auxiliary program for building pcre_chartables.c + when --enable-rebuild-chartables is specified - pcreposix.c ) - pcre_compile.c ) - pcre_config.c ) - pcre_dfa_exec.c ) - pcre_exec.c ) - pcre_fullinfo.c ) - pcre_get.c ) sources for the functions in the library, - pcre_globals.c ) and some internal functions that they use - pcre_info.c ) - pcre_maketables.c ) - pcre_ord2utf8.c ) - pcre_refcount.c ) - pcre_study.c ) - pcre_tables.c ) - pcre_try_flipped.c ) - pcre_ucp_searchfuncs.c) - pcre_valid_utf8.c ) - pcre_version.c ) - pcre_xclass.c ) - ucptable.c ) + pcre_chartables.c.dist a default set of character tables that assume ASCII + coding; used, unless --enable-rebuild-chartables is + specified, by copying to pcre_chartables.c - pcre_printint.src ) debugging function that is #included in pcretest, and - ) can also be #included in pcre_compile() + pcreposix.c ) + pcre_compile.c ) + pcre_config.c ) + pcre_dfa_exec.c ) + pcre_exec.c ) + pcre_fullinfo.c ) + pcre_get.c ) sources for the functions in the library, + pcre_globals.c ) and some internal functions that they use + pcre_info.c ) + pcre_maketables.c ) + pcre_newline.c ) + pcre_ord2utf8.c ) + pcre_refcount.c ) + pcre_study.c ) + pcre_tables.c ) + pcre_try_flipped.c ) + pcre_ucp_searchfuncs.c ) + pcre_valid_utf8.c ) + pcre_version.c ) + pcre_xclass.c ) + pcre_printint.src ) debugging function that is #included in pcretest, + ) and can also be #included in pcre_compile() + pcre.h.in template for pcre.h when built by "configure" + pcreposix.h header for the external POSIX wrapper API + pcre_internal.h header for internal use + ucp.h ) headers concerned with + ucpinternal.h ) Unicode property handling + ucptable.h ) (this one is the data table) - pcre.h the public PCRE header file - pcreposix.h header for the external POSIX wrapper API - pcre_internal.h header for internal use - ucp.h ) headers concerned with - ucpinternal.h ) Unicode property handling - config.in template for config.h, which is built by configure + config.h.in template for config.h, which is built by "configure" - pcrecpp.h the header file for the C++ wrapper - pcrecpparg.h.in "source" for another C++ header file - pcrecpp.cc ) - pcre_scanner.cc ) source for the C++ wrapper library + pcrecpp.h public header file for the C++ wrapper + pcrecpparg.h.in template for another C++ header file + pcre_scanner.h public header file for C++ scanner functions + pcrecpp.cc ) + pcre_scanner.cc ) source for the C++ wrapper library - pcre_stringpiece.h.in "source" for pcre_stringpiece.h, the header for the - C++ stringpiece functions - pcre_stringpiece.cc source for the C++ stringpiece functions + pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the + C++ stringpiece functions + pcre_stringpiece.cc source for the C++ stringpiece functions -(B) Auxiliary files: +(B) Source files for programs that use PCRE: - AUTHORS information about the author of PCRE - ChangeLog log of changes to the code - INSTALL generic installation instructions - LICENCE conditions for the use of PCRE - COPYING the same, using GNU's standard name - Makefile.in template for Unix Makefile, which is built by configure - NEWS important changes in this release - NON-UNIX-USE notes on building PCRE on non-Unix systems - README this file - RunTest.in template for a Unix shell script for running tests - RunGrepTest.in template for a Unix shell script for pcregrep tests - config.guess ) files used by libtool, - config.sub ) used only when building a shared library - config.h.in "source" for the config.h header file - configure a configuring shell script (built by autoconf) - configure.ac the autoconf input used to build configure - doc/Tech.Notes notes on the encoding - doc/*.3 man page sources for the PCRE functions - doc/*.1 man page sources for pcregrep and pcretest - doc/html/* HTML documentation - doc/pcre.txt plain text version of the man pages - doc/pcretest.txt plain text documentation of test program - doc/perltest.txt plain text documentation of Perl test program - install-sh a shell script for installing files - libpcre.pc.in "source" for libpcre.pc for pkg-config - ltmain.sh file used to build a libtool script - mkinstalldirs script for making install directories - pcretest.c comprehensive test program - pcredemo.c simple demonstration of coding calls to PCRE - perltest Perl test program - pcregrep.c source of a grep utility that uses PCRE - pcre-config.in source of script which retains PCRE information - pcrecpp_unittest.c ) - pcre_scanner_unittest.c ) test programs for the C++ wrapper - pcre_stringpiece_unittest.c ) - testdata/testinput* test data for main library tests - testdata/testoutput* expected test results - testdata/grep* input and output for pcregrep tests + pcredemo.c simple demonstration of coding calls to PCRE + pcregrep.c source of a grep utility that uses PCRE + pcretest.c comprehensive test program -(C) Auxiliary files for Win32 DLL +(C) Auxiliary files: - libpcre.def - libpcreposix.def + 132html script to turn "man" pages into HTML + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + CleanTxt script to clean nroff output for txt man pages + Detrail script to remove trailing spaces + HACKING some notes about the internals of PCRE + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in ) template for Unix Makefile, which is built by + ) "configure" + Makefile.am ) the automake input that was used to create + ) Makefile.in + NEWS important changes in this release + NON-UNIX-USE notes on building PCRE on non-Unix systems + PrepareRelease script to make preparations for "make dist" + README this file + RunTest a Unix shell script for running tests + RunGrepTest a Unix shell script for pcregrep tests + aclocal.m4 m4 macros (generated by "aclocal") + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.ac ) the autoconf input that was used to build + ) "configure" and config.h + depcomp ) script to find program dependencies, generated by + ) automake + doc/*.3 man page sources for the PCRE functions + doc/*.1 man page sources for pcregrep and pcretest + doc/index.html.src the base HTML page + doc/html/* HTML documentation + doc/pcre.txt plain text version of the man pages + doc/pcretest.txt plain text documentation of test program + doc/perltest.txt plain text documentation of Perl test program + install-sh a shell script for installing files + libpcre.pc.in template for libpcre.pc for pkg-config + libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config + ltmain.sh file used to build a libtool script + missing ) common stub for a few missing GNU programs while + ) installing, generated by automake + mkinstalldirs script for making install directories + perltest.pl Perl test program + pcre-config.in source of script which retains PCRE information + pcrecpp_unittest.cc ) + pcre_scanner_unittest.cc ) test programs for the C++ wrapper + pcre_stringpiece_unittest.cc ) + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcregrep tests -(D) Auxiliary file for VPASCAL +(D) Auxiliary files for cmake support + + CMakeLists.txt + config-cmake.h.in + +(E) Auxiliary files for VPASCAL makevp.bat + makevp_c.txt + makevp_l.txt + pcregexp.pas + +(F) Auxiliary files for building PCRE "by hand" + + pcre.h.generic ) a version of the public PCRE header file + ) for use in non-"configure" environments + config.h.generic ) a version of config.h for use in non-"configure" + ) environments + +(F) Miscellaneous + + RunTest.bat a script for running tests under Windows Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -June 2006 +Last updated: 24 April 2007 diff --git a/libpcre/aclocal.m4 b/libpcre/aclocal.m4 new file mode 100644 index 000000000..ce67b5778 --- /dev/null +++ b/libpcre/aclocal.m4 @@ -0,0 +1,862 @@ +# generated automatically by aclocal 1.10 -*- Autoconf -*- + +# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, +# 2005, 2006 Free Software Foundation, Inc. +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +m4_if(m4_PACKAGE_VERSION, [2.61],, +[m4_fatal([this file was generated for autoconf 2.61. +You have another version of autoconf. If you want to use that, +you should regenerate the build system entirely.], [63])]) + +# Copyright (C) 2002, 2003, 2005, 2006 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# AM_AUTOMAKE_VERSION(VERSION) +# ---------------------------- +# Automake X.Y traces this macro to ensure aclocal.m4 has been +# generated from the m4 files accompanying Automake X.Y. +# (This private macro should not be called outside this file.) +AC_DEFUN([AM_AUTOMAKE_VERSION], +[am__api_version='1.10' +dnl Some users find AM_AUTOMAKE_VERSION and mistake it for a way to +dnl require some minimum version. Point them to the right macro. +m4_if([$1], [1.10], [], + [AC_FATAL([Do not call $0, use AM_INIT_AUTOMAKE([$1]).])])dnl +]) + +# _AM_AUTOCONF_VERSION(VERSION) +# ----------------------------- +# aclocal traces this macro to find the Autoconf version. +# This is a private macro too. Using m4_define simplifies +# the logic in aclocal, which can simply ignore this definition. +m4_define([_AM_AUTOCONF_VERSION], []) + +# AM_SET_CURRENT_AUTOMAKE_VERSION +# ------------------------------- +# Call AM_AUTOMAKE_VERSION and AM_AUTOMAKE_VERSION so they can be traced. +# This function is AC_REQUIREd by AC_INIT_AUTOMAKE. +AC_DEFUN([AM_SET_CURRENT_AUTOMAKE_VERSION], +[AM_AUTOMAKE_VERSION([1.10])dnl +_AM_AUTOCONF_VERSION(m4_PACKAGE_VERSION)]) + +# AM_AUX_DIR_EXPAND -*- Autoconf -*- + +# Copyright (C) 2001, 2003, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# For projects using AC_CONFIG_AUX_DIR([foo]), Autoconf sets +# $ac_aux_dir to `$srcdir/foo'. In other projects, it is set to +# `$srcdir', `$srcdir/..', or `$srcdir/../..'. +# +# Of course, Automake must honor this variable whenever it calls a +# tool from the auxiliary directory. The problem is that $srcdir (and +# therefore $ac_aux_dir as well) can be either absolute or relative, +# depending on how configure is run. This is pretty annoying, since +# it makes $ac_aux_dir quite unusable in subdirectories: in the top +# source directory, any form will work fine, but in subdirectories a +# relative path needs to be adjusted first. +# +# $ac_aux_dir/missing +# fails when called from a subdirectory if $ac_aux_dir is relative +# $top_srcdir/$ac_aux_dir/missing +# fails if $ac_aux_dir is absolute, +# fails when called from a subdirectory in a VPATH build with +# a relative $ac_aux_dir +# +# The reason of the latter failure is that $top_srcdir and $ac_aux_dir +# are both prefixed by $srcdir. In an in-source build this is usually +# harmless because $srcdir is `.', but things will broke when you +# start a VPATH build or use an absolute $srcdir. +# +# So we could use something similar to $top_srcdir/$ac_aux_dir/missing, +# iff we strip the leading $srcdir from $ac_aux_dir. That would be: +# am_aux_dir='\$(top_srcdir)/'`expr "$ac_aux_dir" : "$srcdir//*\(.*\)"` +# and then we would define $MISSING as +# MISSING="\${SHELL} $am_aux_dir/missing" +# This will work as long as MISSING is not called from configure, because +# unfortunately $(top_srcdir) has no meaning in configure. +# However there are other variables, like CC, which are often used in +# configure, and could therefore not use this "fixed" $ac_aux_dir. +# +# Another solution, used here, is to always expand $ac_aux_dir to an +# absolute PATH. The drawback is that using absolute paths prevent a +# configured tree to be moved without reconfiguration. + +AC_DEFUN([AM_AUX_DIR_EXPAND], +[dnl Rely on autoconf to set up CDPATH properly. +AC_PREREQ([2.50])dnl +# expand $ac_aux_dir to an absolute path +am_aux_dir=`cd $ac_aux_dir && pwd` +]) + +# AM_CONDITIONAL -*- Autoconf -*- + +# Copyright (C) 1997, 2000, 2001, 2003, 2004, 2005, 2006 +# Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 8 + +# AM_CONDITIONAL(NAME, SHELL-CONDITION) +# ------------------------------------- +# Define a conditional. +AC_DEFUN([AM_CONDITIONAL], +[AC_PREREQ(2.52)dnl + ifelse([$1], [TRUE], [AC_FATAL([$0: invalid condition: $1])], + [$1], [FALSE], [AC_FATAL([$0: invalid condition: $1])])dnl +AC_SUBST([$1_TRUE])dnl +AC_SUBST([$1_FALSE])dnl +_AM_SUBST_NOTMAKE([$1_TRUE])dnl +_AM_SUBST_NOTMAKE([$1_FALSE])dnl +if $2; then + $1_TRUE= + $1_FALSE='#' +else + $1_TRUE='#' + $1_FALSE= +fi +AC_CONFIG_COMMANDS_PRE( +[if test -z "${$1_TRUE}" && test -z "${$1_FALSE}"; then + AC_MSG_ERROR([[conditional "$1" was never defined. +Usually this means the macro was only invoked conditionally.]]) +fi])]) + +# Copyright (C) 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006 +# Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 9 + +# There are a few dirty hacks below to avoid letting `AC_PROG_CC' be +# written in clear, in which case automake, when reading aclocal.m4, +# will think it sees a *use*, and therefore will trigger all it's +# C support machinery. Also note that it means that autoscan, seeing +# CC etc. in the Makefile, will ask for an AC_PROG_CC use... + + +# _AM_DEPENDENCIES(NAME) +# ---------------------- +# See how the compiler implements dependency checking. +# NAME is "CC", "CXX", "GCJ", or "OBJC". +# We try a few techniques and use that to set a single cache variable. +# +# We don't AC_REQUIRE the corresponding AC_PROG_CC since the latter was +# modified to invoke _AM_DEPENDENCIES(CC); we would have a circular +# dependency, and given that the user is not expected to run this macro, +# just rely on AC_PROG_CC. +AC_DEFUN([_AM_DEPENDENCIES], +[AC_REQUIRE([AM_SET_DEPDIR])dnl +AC_REQUIRE([AM_OUTPUT_DEPENDENCY_COMMANDS])dnl +AC_REQUIRE([AM_MAKE_INCLUDE])dnl +AC_REQUIRE([AM_DEP_TRACK])dnl + +ifelse([$1], CC, [depcc="$CC" am_compiler_list=], + [$1], CXX, [depcc="$CXX" am_compiler_list=], + [$1], OBJC, [depcc="$OBJC" am_compiler_list='gcc3 gcc'], + [$1], UPC, [depcc="$UPC" am_compiler_list=], + [$1], GCJ, [depcc="$GCJ" am_compiler_list='gcc3 gcc'], + [depcc="$$1" am_compiler_list=]) + +AC_CACHE_CHECK([dependency style of $depcc], + [am_cv_$1_dependencies_compiler_type], +[if test -z "$AMDEP_TRUE" && test -f "$am_depcomp"; then + # We make a subdir and do the tests there. Otherwise we can end up + # making bogus files that we don't know about and never remove. For + # instance it was reported that on HP-UX the gcc test will end up + # making a dummy file named `D' -- because `-MD' means `put the output + # in D'. + mkdir conftest.dir + # Copy depcomp to subdir because otherwise we won't find it if we're + # using a relative directory. + cp "$am_depcomp" conftest.dir + cd conftest.dir + # We will build objects and dependencies in a subdirectory because + # it helps to detect inapplicable dependency modes. For instance + # both Tru64's cc and ICC support -MD to output dependencies as a + # side effect of compilation, but ICC will put the dependencies in + # the current directory while Tru64 will put them in the object + # directory. + mkdir sub + + am_cv_$1_dependencies_compiler_type=none + if test "$am_compiler_list" = ""; then + am_compiler_list=`sed -n ['s/^#*\([a-zA-Z0-9]*\))$/\1/p'] < ./depcomp` + fi + for depmode in $am_compiler_list; do + # Setup a source with many dependencies, because some compilers + # like to wrap large dependency lists on column 80 (with \), and + # we should not choose a depcomp mode which is confused by this. + # + # We need to recreate these files for each test, as the compiler may + # overwrite some of them when testing with obscure command lines. + # This happens at least with the AIX C compiler. + : > sub/conftest.c + for i in 1 2 3 4 5 6; do + echo '#include "conftst'$i'.h"' >> sub/conftest.c + # Using `: > sub/conftst$i.h' creates only sub/conftst1.h with + # Solaris 8's {/usr,}/bin/sh. + touch sub/conftst$i.h + done + echo "${am__include} ${am__quote}sub/conftest.Po${am__quote}" > confmf + + case $depmode in + nosideeffect) + # after this tag, mechanisms are not by side-effect, so they'll + # only be used when explicitly requested + if test "x$enable_dependency_tracking" = xyes; then + continue + else + break + fi + ;; + none) break ;; + esac + # We check with `-c' and `-o' for the sake of the "dashmstdout" + # mode. It turns out that the SunPro C++ compiler does not properly + # handle `-M -o', and we need to detect this. + if depmode=$depmode \ + source=sub/conftest.c object=sub/conftest.${OBJEXT-o} \ + depfile=sub/conftest.Po tmpdepfile=sub/conftest.TPo \ + $SHELL ./depcomp $depcc -c -o sub/conftest.${OBJEXT-o} sub/conftest.c \ + >/dev/null 2>conftest.err && + grep sub/conftst1.h sub/conftest.Po > /dev/null 2>&1 && + grep sub/conftst6.h sub/conftest.Po > /dev/null 2>&1 && + grep sub/conftest.${OBJEXT-o} sub/conftest.Po > /dev/null 2>&1 && + ${MAKE-make} -s -f confmf > /dev/null 2>&1; then + # icc doesn't choke on unknown options, it will just issue warnings + # or remarks (even with -Werror). So we grep stderr for any message + # that says an option was ignored or not supported. + # When given -MP, icc 7.0 and 7.1 complain thusly: + # icc: Command line warning: ignoring option '-M'; no argument required + # The diagnosis changed in icc 8.0: + # icc: Command line remark: option '-MP' not supported + if (grep 'ignoring option' conftest.err || + grep 'not supported' conftest.err) >/dev/null 2>&1; then :; else + am_cv_$1_dependencies_compiler_type=$depmode + break + fi + fi + done + + cd .. + rm -rf conftest.dir +else + am_cv_$1_dependencies_compiler_type=none +fi +]) +AC_SUBST([$1DEPMODE], [depmode=$am_cv_$1_dependencies_compiler_type]) +AM_CONDITIONAL([am__fastdep$1], [ + test "x$enable_dependency_tracking" != xno \ + && test "$am_cv_$1_dependencies_compiler_type" = gcc3]) +]) + + +# AM_SET_DEPDIR +# ------------- +# Choose a directory name for dependency files. +# This macro is AC_REQUIREd in _AM_DEPENDENCIES +AC_DEFUN([AM_SET_DEPDIR], +[AC_REQUIRE([AM_SET_LEADING_DOT])dnl +AC_SUBST([DEPDIR], ["${am__leading_dot}deps"])dnl +]) + + +# AM_DEP_TRACK +# ------------ +AC_DEFUN([AM_DEP_TRACK], +[AC_ARG_ENABLE(dependency-tracking, +[ --disable-dependency-tracking speeds up one-time build + --enable-dependency-tracking do not reject slow dependency extractors]) +if test "x$enable_dependency_tracking" != xno; then + am_depcomp="$ac_aux_dir/depcomp" + AMDEPBACKSLASH='\' +fi +AM_CONDITIONAL([AMDEP], [test "x$enable_dependency_tracking" != xno]) +AC_SUBST([AMDEPBACKSLASH])dnl +_AM_SUBST_NOTMAKE([AMDEPBACKSLASH])dnl +]) + +# Generate code to set up dependency tracking. -*- Autoconf -*- + +# Copyright (C) 1999, 2000, 2001, 2002, 2003, 2004, 2005 +# Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +#serial 3 + +# _AM_OUTPUT_DEPENDENCY_COMMANDS +# ------------------------------ +AC_DEFUN([_AM_OUTPUT_DEPENDENCY_COMMANDS], +[for mf in $CONFIG_FILES; do + # Strip MF so we end up with the name of the file. + mf=`echo "$mf" | sed -e 's/:.*$//'` + # Check whether this is an Automake generated Makefile or not. + # We used to match only the files named `Makefile.in', but + # some people rename them; so instead we look at the file content. + # Grep'ing the first line is not enough: some people post-process + # each Makefile.in and add a new line on top of each file to say so. + # Grep'ing the whole file is not good either: AIX grep has a line + # limit of 2048, but all sed's we know have understand at least 4000. + if sed 10q "$mf" | grep '^#.*generated by automake' > /dev/null 2>&1; then + dirpart=`AS_DIRNAME("$mf")` + else + continue + fi + # Extract the definition of DEPDIR, am__include, and am__quote + # from the Makefile without running `make'. + DEPDIR=`sed -n 's/^DEPDIR = //p' < "$mf"` + test -z "$DEPDIR" && continue + am__include=`sed -n 's/^am__include = //p' < "$mf"` + test -z "am__include" && continue + am__quote=`sed -n 's/^am__quote = //p' < "$mf"` + # When using ansi2knr, U may be empty or an underscore; expand it + U=`sed -n 's/^U = //p' < "$mf"` + # Find all dependency output files, they are included files with + # $(DEPDIR) in their names. We invoke sed twice because it is the + # simplest approach to changing $(DEPDIR) to its actual value in the + # expansion. + for file in `sed -n " + s/^$am__include $am__quote\(.*(DEPDIR).*\)$am__quote"'$/\1/p' <"$mf" | \ + sed -e 's/\$(DEPDIR)/'"$DEPDIR"'/g' -e 's/\$U/'"$U"'/g'`; do + # Make sure the directory exists. + test -f "$dirpart/$file" && continue + fdir=`AS_DIRNAME(["$file"])` + AS_MKDIR_P([$dirpart/$fdir]) + # echo "creating $dirpart/$file" + echo '# dummy' > "$dirpart/$file" + done +done +])# _AM_OUTPUT_DEPENDENCY_COMMANDS + + +# AM_OUTPUT_DEPENDENCY_COMMANDS +# ----------------------------- +# This macro should only be invoked once -- use via AC_REQUIRE. +# +# This code is only required when automatic dependency tracking +# is enabled. FIXME. This creates each `.P' file that we will +# need in order to bootstrap the dependency handling code. +AC_DEFUN([AM_OUTPUT_DEPENDENCY_COMMANDS], +[AC_CONFIG_COMMANDS([depfiles], + [test x"$AMDEP_TRUE" != x"" || _AM_OUTPUT_DEPENDENCY_COMMANDS], + [AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir"]) +]) + +# Do all the work for Automake. -*- Autoconf -*- + +# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, +# 2005, 2006 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 12 + +# This macro actually does too much. Some checks are only needed if +# your package does certain things. But this isn't really a big deal. + +# AM_INIT_AUTOMAKE(PACKAGE, VERSION, [NO-DEFINE]) +# AM_INIT_AUTOMAKE([OPTIONS]) +# ----------------------------------------------- +# The call with PACKAGE and VERSION arguments is the old style +# call (pre autoconf-2.50), which is being phased out. PACKAGE +# and VERSION should now be passed to AC_INIT and removed from +# the call to AM_INIT_AUTOMAKE. +# We support both call styles for the transition. After +# the next Automake release, Autoconf can make the AC_INIT +# arguments mandatory, and then we can depend on a new Autoconf +# release and drop the old call support. +AC_DEFUN([AM_INIT_AUTOMAKE], +[AC_PREREQ([2.60])dnl +dnl Autoconf wants to disallow AM_ names. We explicitly allow +dnl the ones we care about. +m4_pattern_allow([^AM_[A-Z]+FLAGS$])dnl +AC_REQUIRE([AM_SET_CURRENT_AUTOMAKE_VERSION])dnl +AC_REQUIRE([AC_PROG_INSTALL])dnl +if test "`cd $srcdir && pwd`" != "`pwd`"; then + # Use -I$(srcdir) only when $(srcdir) != ., so that make's output + # is not polluted with repeated "-I." + AC_SUBST([am__isrc], [' -I$(srcdir)'])_AM_SUBST_NOTMAKE([am__isrc])dnl + # test to see if srcdir already configured + if test -f $srcdir/config.status; then + AC_MSG_ERROR([source directory already configured; run "make distclean" there first]) + fi +fi + +# test whether we have cygpath +if test -z "$CYGPATH_W"; then + if (cygpath --version) >/dev/null 2>/dev/null; then + CYGPATH_W='cygpath -w' + else + CYGPATH_W=echo + fi +fi +AC_SUBST([CYGPATH_W]) + +# Define the identity of the package. +dnl Distinguish between old-style and new-style calls. +m4_ifval([$2], +[m4_ifval([$3], [_AM_SET_OPTION([no-define])])dnl + AC_SUBST([PACKAGE], [$1])dnl + AC_SUBST([VERSION], [$2])], +[_AM_SET_OPTIONS([$1])dnl +dnl Diagnose old-style AC_INIT with new-style AM_AUTOMAKE_INIT. +m4_if(m4_ifdef([AC_PACKAGE_NAME], 1)m4_ifdef([AC_PACKAGE_VERSION], 1), 11,, + [m4_fatal([AC_INIT should be called with package and version arguments])])dnl + AC_SUBST([PACKAGE], ['AC_PACKAGE_TARNAME'])dnl + AC_SUBST([VERSION], ['AC_PACKAGE_VERSION'])])dnl + +_AM_IF_OPTION([no-define],, +[AC_DEFINE_UNQUOTED(PACKAGE, "$PACKAGE", [Name of package]) + AC_DEFINE_UNQUOTED(VERSION, "$VERSION", [Version number of package])])dnl + +# Some tools Automake needs. +AC_REQUIRE([AM_SANITY_CHECK])dnl +AC_REQUIRE([AC_ARG_PROGRAM])dnl +AM_MISSING_PROG(ACLOCAL, aclocal-${am__api_version}) +AM_MISSING_PROG(AUTOCONF, autoconf) +AM_MISSING_PROG(AUTOMAKE, automake-${am__api_version}) +AM_MISSING_PROG(AUTOHEADER, autoheader) +AM_MISSING_PROG(MAKEINFO, makeinfo) +AM_PROG_INSTALL_SH +AM_PROG_INSTALL_STRIP +AC_REQUIRE([AM_PROG_MKDIR_P])dnl +# We need awk for the "check" target. The system "awk" is bad on +# some platforms. +AC_REQUIRE([AC_PROG_AWK])dnl +AC_REQUIRE([AC_PROG_MAKE_SET])dnl +AC_REQUIRE([AM_SET_LEADING_DOT])dnl +_AM_IF_OPTION([tar-ustar], [_AM_PROG_TAR([ustar])], + [_AM_IF_OPTION([tar-pax], [_AM_PROG_TAR([pax])], + [_AM_PROG_TAR([v7])])]) +_AM_IF_OPTION([no-dependencies],, +[AC_PROVIDE_IFELSE([AC_PROG_CC], + [_AM_DEPENDENCIES(CC)], + [define([AC_PROG_CC], + defn([AC_PROG_CC])[_AM_DEPENDENCIES(CC)])])dnl +AC_PROVIDE_IFELSE([AC_PROG_CXX], + [_AM_DEPENDENCIES(CXX)], + [define([AC_PROG_CXX], + defn([AC_PROG_CXX])[_AM_DEPENDENCIES(CXX)])])dnl +AC_PROVIDE_IFELSE([AC_PROG_OBJC], + [_AM_DEPENDENCIES(OBJC)], + [define([AC_PROG_OBJC], + defn([AC_PROG_OBJC])[_AM_DEPENDENCIES(OBJC)])])dnl +]) +]) + + +# When config.status generates a header, we must update the stamp-h file. +# This file resides in the same directory as the config header +# that is generated. The stamp files are numbered to have different names. + +# Autoconf calls _AC_AM_CONFIG_HEADER_HOOK (when defined) in the +# loop where config.status creates the headers, so we can generate +# our stamp files there. +AC_DEFUN([_AC_AM_CONFIG_HEADER_HOOK], +[# Compute $1's index in $config_headers. +_am_stamp_count=1 +for _am_header in $config_headers :; do + case $_am_header in + $1 | $1:* ) + break ;; + * ) + _am_stamp_count=`expr $_am_stamp_count + 1` ;; + esac +done +echo "timestamp for $1" >`AS_DIRNAME([$1])`/stamp-h[]$_am_stamp_count]) + +# Copyright (C) 2001, 2003, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# AM_PROG_INSTALL_SH +# ------------------ +# Define $install_sh. +AC_DEFUN([AM_PROG_INSTALL_SH], +[AC_REQUIRE([AM_AUX_DIR_EXPAND])dnl +install_sh=${install_sh-"\$(SHELL) $am_aux_dir/install-sh"} +AC_SUBST(install_sh)]) + +# Copyright (C) 2003, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 2 + +# Check whether the underlying file-system supports filenames +# with a leading dot. For instance MS-DOS doesn't. +AC_DEFUN([AM_SET_LEADING_DOT], +[rm -rf .tst 2>/dev/null +mkdir .tst 2>/dev/null +if test -d .tst; then + am__leading_dot=. +else + am__leading_dot=_ +fi +rmdir .tst 2>/dev/null +AC_SUBST([am__leading_dot])]) + +# Check to see how 'make' treats includes. -*- Autoconf -*- + +# Copyright (C) 2001, 2002, 2003, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 3 + +# AM_MAKE_INCLUDE() +# ----------------- +# Check to see how make treats includes. +AC_DEFUN([AM_MAKE_INCLUDE], +[am_make=${MAKE-make} +cat > confinc << 'END' +am__doit: + @echo done +.PHONY: am__doit +END +# If we don't find an include directive, just comment out the code. +AC_MSG_CHECKING([for style of include used by $am_make]) +am__include="#" +am__quote= +_am_result=none +# First try GNU make style include. +echo "include confinc" > confmf +# We grep out `Entering directory' and `Leaving directory' +# messages which can occur if `w' ends up in MAKEFLAGS. +# In particular we don't look at `^make:' because GNU make might +# be invoked under some other name (usually "gmake"), in which +# case it prints its new name instead of `make'. +if test "`$am_make -s -f confmf 2> /dev/null | grep -v 'ing directory'`" = "done"; then + am__include=include + am__quote= + _am_result=GNU +fi +# Now try BSD make style include. +if test "$am__include" = "#"; then + echo '.include "confinc"' > confmf + if test "`$am_make -s -f confmf 2> /dev/null`" = "done"; then + am__include=.include + am__quote="\"" + _am_result=BSD + fi +fi +AC_SUBST([am__include]) +AC_SUBST([am__quote]) +AC_MSG_RESULT([$_am_result]) +rm -f confinc confmf +]) + +# Fake the existence of programs that GNU maintainers use. -*- Autoconf -*- + +# Copyright (C) 1997, 1999, 2000, 2001, 2003, 2004, 2005 +# Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 5 + +# AM_MISSING_PROG(NAME, PROGRAM) +# ------------------------------ +AC_DEFUN([AM_MISSING_PROG], +[AC_REQUIRE([AM_MISSING_HAS_RUN]) +$1=${$1-"${am_missing_run}$2"} +AC_SUBST($1)]) + + +# AM_MISSING_HAS_RUN +# ------------------ +# Define MISSING if not defined so far and test if it supports --run. +# If it does, set am_missing_run to use it, otherwise, to nothing. +AC_DEFUN([AM_MISSING_HAS_RUN], +[AC_REQUIRE([AM_AUX_DIR_EXPAND])dnl +AC_REQUIRE_AUX_FILE([missing])dnl +test x"${MISSING+set}" = xset || MISSING="\${SHELL} $am_aux_dir/missing" +# Use eval to expand $SHELL +if eval "$MISSING --run true"; then + am_missing_run="$MISSING --run " +else + am_missing_run= + AC_MSG_WARN([`missing' script is too old or missing]) +fi +]) + +# Copyright (C) 2003, 2004, 2005, 2006 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# AM_PROG_MKDIR_P +# --------------- +# Check for `mkdir -p'. +AC_DEFUN([AM_PROG_MKDIR_P], +[AC_PREREQ([2.60])dnl +AC_REQUIRE([AC_PROG_MKDIR_P])dnl +dnl Automake 1.8 to 1.9.6 used to define mkdir_p. We now use MKDIR_P, +dnl while keeping a definition of mkdir_p for backward compatibility. +dnl @MKDIR_P@ is magic: AC_OUTPUT adjusts its value for each Makefile. +dnl However we cannot define mkdir_p as $(MKDIR_P) for the sake of +dnl Makefile.ins that do not define MKDIR_P, so we do our own +dnl adjustment using top_builddir (which is defined more often than +dnl MKDIR_P). +AC_SUBST([mkdir_p], ["$MKDIR_P"])dnl +case $mkdir_p in + [[\\/$]]* | ?:[[\\/]]*) ;; + */*) mkdir_p="\$(top_builddir)/$mkdir_p" ;; +esac +]) + +# Helper functions for option handling. -*- Autoconf -*- + +# Copyright (C) 2001, 2002, 2003, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 3 + +# _AM_MANGLE_OPTION(NAME) +# ----------------------- +AC_DEFUN([_AM_MANGLE_OPTION], +[[_AM_OPTION_]m4_bpatsubst($1, [[^a-zA-Z0-9_]], [_])]) + +# _AM_SET_OPTION(NAME) +# ------------------------------ +# Set option NAME. Presently that only means defining a flag for this option. +AC_DEFUN([_AM_SET_OPTION], +[m4_define(_AM_MANGLE_OPTION([$1]), 1)]) + +# _AM_SET_OPTIONS(OPTIONS) +# ---------------------------------- +# OPTIONS is a space-separated list of Automake options. +AC_DEFUN([_AM_SET_OPTIONS], +[AC_FOREACH([_AM_Option], [$1], [_AM_SET_OPTION(_AM_Option)])]) + +# _AM_IF_OPTION(OPTION, IF-SET, [IF-NOT-SET]) +# ------------------------------------------- +# Execute IF-SET if OPTION is set, IF-NOT-SET otherwise. +AC_DEFUN([_AM_IF_OPTION], +[m4_ifset(_AM_MANGLE_OPTION([$1]), [$2], [$3])]) + +# Check to make sure that the build environment is sane. -*- Autoconf -*- + +# Copyright (C) 1996, 1997, 2000, 2001, 2003, 2005 +# Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 4 + +# AM_SANITY_CHECK +# --------------- +AC_DEFUN([AM_SANITY_CHECK], +[AC_MSG_CHECKING([whether build environment is sane]) +# Just in case +sleep 1 +echo timestamp > conftest.file +# Do `set' in a subshell so we don't clobber the current shell's +# arguments. Must try -L first in case configure is actually a +# symlink; some systems play weird games with the mod time of symlinks +# (eg FreeBSD returns the mod time of the symlink's containing +# directory). +if ( + set X `ls -Lt $srcdir/configure conftest.file 2> /dev/null` + if test "$[*]" = "X"; then + # -L didn't work. + set X `ls -t $srcdir/configure conftest.file` + fi + rm -f conftest.file + if test "$[*]" != "X $srcdir/configure conftest.file" \ + && test "$[*]" != "X conftest.file $srcdir/configure"; then + + # If neither matched, then we have a broken ls. This can happen + # if, for instance, CONFIG_SHELL is bash and it inherits a + # broken ls alias from the environment. This has actually + # happened. Such a system could not be considered "sane". + AC_MSG_ERROR([ls -t appears to fail. Make sure there is not a broken +alias in your environment]) + fi + + test "$[2]" = conftest.file + ) +then + # Ok. + : +else + AC_MSG_ERROR([newly created file is older than distributed files! +Check your system clock]) +fi +AC_MSG_RESULT(yes)]) + +# Copyright (C) 2001, 2003, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# AM_PROG_INSTALL_STRIP +# --------------------- +# One issue with vendor `install' (even GNU) is that you can't +# specify the program used to strip binaries. This is especially +# annoying in cross-compiling environments, where the build's strip +# is unlikely to handle the host's binaries. +# Fortunately install-sh will honor a STRIPPROG variable, so we +# always use install-sh in `make install-strip', and initialize +# STRIPPROG with the value of the STRIP variable (set by the user). +AC_DEFUN([AM_PROG_INSTALL_STRIP], +[AC_REQUIRE([AM_PROG_INSTALL_SH])dnl +# Installed binaries are usually stripped using `strip' when the user +# run `make install-strip'. However `strip' might not be the right +# tool to use in cross-compilation environments, therefore Automake +# will honor the `STRIP' environment variable to overrule this program. +dnl Don't test for $cross_compiling = yes, because it might be `maybe'. +if test "$cross_compiling" != no; then + AC_CHECK_TOOL([STRIP], [strip], :) +fi +INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s" +AC_SUBST([INSTALL_STRIP_PROGRAM])]) + +# Copyright (C) 2006 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# _AM_SUBST_NOTMAKE(VARIABLE) +# --------------------------- +# Prevent Automake from outputing VARIABLE = @VARIABLE@ in Makefile.in. +# This macro is traced by Automake. +AC_DEFUN([_AM_SUBST_NOTMAKE]) + +# Check how to create a tarball. -*- Autoconf -*- + +# Copyright (C) 2004, 2005 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# serial 2 + +# _AM_PROG_TAR(FORMAT) +# -------------------- +# Check how to create a tarball in format FORMAT. +# FORMAT should be one of `v7', `ustar', or `pax'. +# +# Substitute a variable $(am__tar) that is a command +# writing to stdout a FORMAT-tarball containing the directory +# $tardir. +# tardir=directory && $(am__tar) > result.tar +# +# Substitute a variable $(am__untar) that extract such +# a tarball read from stdin. +# $(am__untar) < result.tar +AC_DEFUN([_AM_PROG_TAR], +[# Always define AMTAR for backward compatibility. +AM_MISSING_PROG([AMTAR], [tar]) +m4_if([$1], [v7], + [am__tar='${AMTAR} chof - "$$tardir"'; am__untar='${AMTAR} xf -'], + [m4_case([$1], [ustar],, [pax],, + [m4_fatal([Unknown tar format])]) +AC_MSG_CHECKING([how to create a $1 tar archive]) +# Loop over all known methods to create a tar archive until one works. +_am_tools='gnutar m4_if([$1], [ustar], [plaintar]) pax cpio none' +_am_tools=${am_cv_prog_tar_$1-$_am_tools} +# Do not fold the above two line into one, because Tru64 sh and +# Solaris sh will not grok spaces in the rhs of `-'. +for _am_tool in $_am_tools +do + case $_am_tool in + gnutar) + for _am_tar in tar gnutar gtar; + do + AM_RUN_LOG([$_am_tar --version]) && break + done + am__tar="$_am_tar --format=m4_if([$1], [pax], [posix], [$1]) -chf - "'"$$tardir"' + am__tar_="$_am_tar --format=m4_if([$1], [pax], [posix], [$1]) -chf - "'"$tardir"' + am__untar="$_am_tar -xf -" + ;; + plaintar) + # Must skip GNU tar: if it does not support --format= it doesn't create + # ustar tarball either. + (tar --version) >/dev/null 2>&1 && continue + am__tar='tar chf - "$$tardir"' + am__tar_='tar chf - "$tardir"' + am__untar='tar xf -' + ;; + pax) + am__tar='pax -L -x $1 -w "$$tardir"' + am__tar_='pax -L -x $1 -w "$tardir"' + am__untar='pax -r' + ;; + cpio) + am__tar='find "$$tardir" -print | cpio -o -H $1 -L' + am__tar_='find "$tardir" -print | cpio -o -H $1 -L' + am__untar='cpio -i -H $1 -d' + ;; + none) + am__tar=false + am__tar_=false + am__untar=false + ;; + esac + + # If the value was cached, stop now. We just wanted to have am__tar + # and am__untar set. + test -n "${am_cv_prog_tar_$1}" && break + + # tar/untar a dummy directory, and stop if the command works + rm -rf conftest.dir + mkdir conftest.dir + echo GrepMe > conftest.dir/file + AM_RUN_LOG([tardir=conftest.dir && eval $am__tar_ >conftest.tar]) + rm -rf conftest.dir + if test -s conftest.tar; then + AM_RUN_LOG([$am__untar /dev/null 2>&1 && break + fi +done +rm -rf conftest.dir + +AC_CACHE_VAL([am_cv_prog_tar_$1], [am_cv_prog_tar_$1=$_am_tool]) +AC_MSG_RESULT([$am_cv_prog_tar_$1])]) +AC_SUBST([am__tar]) +AC_SUBST([am__untar]) +]) # _AM_PROG_TAR + diff --git a/libpcre/config.guess b/libpcre/config.guess index 10a826017..6960a397a 100755 --- a/libpcre/config.guess +++ b/libpcre/config.guess @@ -1,9 +1,10 @@ #! /bin/sh # Attempt to guess a canonical system name. # Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, -# 2000, 2001, 2002, 2003, 2004, 2005 Free Software Foundation, Inc. +# 2000, 2001, 2002, 2003, 2004, 2005, 2006 Free Software Foundation, +# Inc. -timestamp='2005-12-23' +timestamp='2007-01-15' # This file is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by @@ -106,7 +107,7 @@ set_cc_for_build=' trap "exitcode=\$?; (rm -f \$tmpfiles 2>/dev/null; rmdir \$tmp 2>/dev/null) && exit \$exitcode" 0 ; trap "rm -f \$tmpfiles 2>/dev/null; rmdir \$tmp 2>/dev/null; exit 1" 1 2 13 15 ; : ${TMPDIR=/tmp} ; - { tmp=`(umask 077 && mktemp -d -q "$TMPDIR/cgXXXXXX") 2>/dev/null` && test -n "$tmp" && test -d "$tmp" ; } || + { tmp=`(umask 077 && mktemp -d "$TMPDIR/cgXXXXXX") 2>/dev/null` && test -n "$tmp" && test -d "$tmp" ; } || { test -n "$RANDOM" && tmp=$TMPDIR/cg$$-$RANDOM && (umask 077 && mkdir $tmp) ; } || { tmp=$TMPDIR/cg-$$ && (umask 077 && mkdir $tmp) && echo "Warning: creating insecure temp directory" >&2 ; } || { echo "$me: cannot create a temporary directory in $TMPDIR" >&2 ; exit 1 ; } ; @@ -138,6 +139,23 @@ UNAME_RELEASE=`(uname -r) 2>/dev/null` || UNAME_RELEASE=unknown UNAME_SYSTEM=`(uname -s) 2>/dev/null` || UNAME_SYSTEM=unknown UNAME_VERSION=`(uname -v) 2>/dev/null` || UNAME_VERSION=unknown +if [ "${UNAME_SYSTEM}" = "Linux" ] ; then + eval $set_cc_for_build + cat << EOF > $dummy.c + #include + #ifdef __UCLIBC__ + # ifdef __UCLIBC_CONFIG_VERSION__ + LIBC=uclibc __UCLIBC_CONFIG_VERSION__ + # else + LIBC=uclibc + # endif + #else + LIBC=gnu + #endif +EOF + eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep LIBC= | sed -e 's: ::g'` +fi + # Note: order is significant - the case branches are not exclusive. case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in @@ -160,6 +178,7 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in arm*) machine=arm-unknown ;; sh3el) machine=shl-unknown ;; sh3eb) machine=sh-unknown ;; + sh5el) machine=sh5le-unknown ;; *) machine=${UNAME_MACHINE_ARCH}-unknown ;; esac # The Operating System including object format, if it has switched @@ -206,8 +225,11 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in *:ekkoBSD:*:*) echo ${UNAME_MACHINE}-unknown-ekkobsd${UNAME_RELEASE} exit ;; + *:SolidBSD:*:*) + echo ${UNAME_MACHINE}-unknown-solidbsd${UNAME_RELEASE} + exit ;; macppc:MirBSD:*:*) - echo powerppc-unknown-mirbsd${UNAME_RELEASE} + echo powerpc-unknown-mirbsd${UNAME_RELEASE} exit ;; *:MirBSD:*:*) echo ${UNAME_MACHINE}-unknown-mirbsd${UNAME_RELEASE} @@ -767,6 +789,8 @@ EOF case ${UNAME_MACHINE} in pc98) echo i386-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;; + amd64) + echo x86_64-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;; *) echo ${UNAME_MACHINE}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;; esac @@ -774,7 +798,7 @@ EOF i*:CYGWIN*:*) echo ${UNAME_MACHINE}-pc-cygwin exit ;; - i*:MINGW*:*) + *:MINGW*:*) echo ${UNAME_MACHINE}-pc-mingw32 exit ;; i*:windows32*:*) @@ -784,8 +808,11 @@ EOF i*:PW*:*) echo ${UNAME_MACHINE}-pc-pw32 exit ;; - x86:Interix*:[345]*) - echo i586-pc-interix${UNAME_RELEASE}|sed -e 's/\..*//' + x86:Interix*:[3456]*) + echo i586-pc-interix${UNAME_RELEASE} + exit ;; + EM64T:Interix*:[3456]* | authenticamd:Interix*:[3456]*) + echo x86_64-unknown-interix${UNAME_RELEASE} exit ;; [345]86:Windows_95:* | [345]86:Windows_98:* | [345]86:Windows_NT:*) echo i${UNAME_MACHINE}-pc-mks @@ -820,25 +847,28 @@ EOF echo ${UNAME_MACHINE}-pc-minix exit ;; arm*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + avr32*:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; cris:Linux:*:*) - echo cris-axis-linux-gnu + echo cris-axis-linux-${LIBC} exit ;; crisv32:Linux:*:*) - echo crisv32-axis-linux-gnu + echo crisv32-axis-linux-${LIBC} exit ;; frv:Linux:*:*) - echo frv-unknown-linux-gnu + echo frv-unknown-linux-${LIBC} exit ;; ia64:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; m32r*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; m68*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; mips:Linux:*:*) eval $set_cc_for_build @@ -856,8 +886,12 @@ EOF #endif #endif EOF - eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n '/^CPU/{s: ::g;p;}'`" - test x"${CPU}" != x && { echo "${CPU}-unknown-linux-gnu"; exit; } + eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n ' + /^CPU/{ + s: ::g + p + }'`" + test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; } ;; mips64:Linux:*:*) eval $set_cc_for_build @@ -875,17 +909,21 @@ EOF #endif #endif EOF - eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n '/^CPU/{s: ::g;p;}'`" - test x"${CPU}" != x && { echo "${CPU}-unknown-linux-gnu"; exit; } + eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n ' + /^CPU/{ + s: ::g + p + }'`" + test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; } ;; or32:Linux:*:*) - echo or32-unknown-linux-gnu + echo or32-unknown-linux-${LIBC} exit ;; ppc:Linux:*:*) - echo powerpc-unknown-linux-gnu + echo powerpc-unknown-linux-${LIBC} exit ;; ppc64:Linux:*:*) - echo powerpc64-unknown-linux-gnu + echo powerpc64-unknown-linux-${LIBC} exit ;; alpha:Linux:*:*) case `sed -n '/^cpu model/s/^.*: \(.*\)/\1/p' < /proc/cpuinfo` in @@ -898,37 +936,40 @@ EOF EV68*) UNAME_MACHINE=alphaev68 ;; esac objdump --private-headers /bin/sh | grep ld.so.1 >/dev/null - if test "$?" = 0 ; then LIBC="libc1" ; else LIBC="" ; fi - echo ${UNAME_MACHINE}-unknown-linux-gnu${LIBC} + if test "$?" = 0 ; then LIBC="gnulibc1" ; fi + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; parisc:Linux:*:* | hppa:Linux:*:*) # Look for CPU level case `grep '^cpu[^a-z]*:' /proc/cpuinfo 2>/dev/null | cut -d' ' -f2` in - PA7*) echo hppa1.1-unknown-linux-gnu ;; - PA8*) echo hppa2.0-unknown-linux-gnu ;; - *) echo hppa-unknown-linux-gnu ;; + PA7*) echo hppa1.1-unknown-linux-${LIBC} ;; + PA8*) echo hppa2.0-unknown-linux-${LIBC} ;; + *) echo hppa-unknown-linux-${LIBC} ;; esac exit ;; parisc64:Linux:*:* | hppa64:Linux:*:*) - echo hppa64-unknown-linux-gnu + echo hppa64-unknown-linux-${LIBC} exit ;; s390:Linux:*:* | s390x:Linux:*:*) echo ${UNAME_MACHINE}-ibm-linux exit ;; sh64*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; sh*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; sparc:Linux:*:* | sparc64:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; vax:Linux:*:*) - echo ${UNAME_MACHINE}-dec-linux-gnu + echo ${UNAME_MACHINE}-dec-linux-${LIBC} exit ;; x86_64:Linux:*:*) - echo x86_64-unknown-linux-gnu + echo x86_64-unknown-linux-${LIBC} + exit ;; + xtensa:Linux:*:*) + echo xtensa-unknown-linux-${LIBC} exit ;; i*86:Linux:*:*) # The BFD linker knows what the default object file format is, so @@ -943,20 +984,22 @@ EOF p'` case "$ld_supported_targets" in elf32-i386) - TENTATIVE="${UNAME_MACHINE}-pc-linux-gnu" + TENTATIVE="${UNAME_MACHINE}-pc-linux-${LIBC}" ;; a.out-i386-linux) - echo "${UNAME_MACHINE}-pc-linux-gnuaout" + echo "${UNAME_MACHINE}-pc-linux-${LIBC}aout" exit ;; coff-i386) - echo "${UNAME_MACHINE}-pc-linux-gnucoff" + echo "${UNAME_MACHINE}-pc-linux-${LIBC}coff" exit ;; "") # Either a pre-BFD a.out linker (linux-gnuoldld) or # one that does not give us useful --help. - echo "${UNAME_MACHINE}-pc-linux-gnuoldld" + echo "${UNAME_MACHINE}-pc-linux-${LIBC}oldld" exit ;; esac + # This should get integrated into the C code below, but now we hack + if [ "$LIBC" != "gnu" ] ; then echo "$TENTATIVE" && exit 0 ; fi # Determine whether the default compiler is a.out or elf eval $set_cc_for_build sed 's/^ //' << EOF >$dummy.c @@ -972,7 +1015,7 @@ EOF LIBC=gnulibc1 # endif #else - #if defined(__INTEL_COMPILER) || defined(__PGI) + #if defined(__INTEL_COMPILER) || defined(__PGI) || defined(__SUNPRO_C) || defined(__SUNPRO_CC) LIBC=gnu #else LIBC=gnuaout @@ -982,7 +1025,11 @@ EOF LIBC=dietlibc #endif EOF - eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n '/^LIBC/{s: ::g;p;}'`" + eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n ' + /^LIBC/{ + s: ::g + p + }'`" test x"${LIBC}" != x && { echo "${UNAME_MACHINE}-pc-linux-${LIBC}" exit @@ -1184,6 +1231,15 @@ EOF SX-6:SUPER-UX:*:*) echo sx6-nec-superux${UNAME_RELEASE} exit ;; + SX-7:SUPER-UX:*:*) + echo sx7-nec-superux${UNAME_RELEASE} + exit ;; + SX-8:SUPER-UX:*:*) + echo sx8-nec-superux${UNAME_RELEASE} + exit ;; + SX-8R:SUPER-UX:*:*) + echo sx8r-nec-superux${UNAME_RELEASE} + exit ;; Power*:Rhapsody:*:*) echo powerpc-apple-rhapsody${UNAME_RELEASE} exit ;; diff --git a/libpcre/config.h.generic b/libpcre/config.h.generic new file mode 100644 index 000000000..0656ac219 --- /dev/null +++ b/libpcre/config.h.generic @@ -0,0 +1,271 @@ +/* config.h. Generated from config.h.in by configure. */ +/* config.h.in. Generated from configure.ac by autoheader. */ + + +/* On Unix-like systems config.h.in is converted by "configure" into config.h. +Some other environments also support the use of "configure". PCRE is written in +Standard C, but there are a few non-standard things it can cope with, allowing +it to run on SunOS4 and other "close to standard" systems. + +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macros the way you need them. Alternatively, you can avoid editing by using -D +on the compiler command line to set the macro values. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */ + +/* If you are compiling for a system that uses EBCDIC instead of ASCII + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic. */ +/* #undef EBCDIC */ + +/* Define to 1 if you have the `bcopy' function. */ +#ifndef HAVE_BCOPY +#define HAVE_BCOPY 1 +#endif + +/* Define to 1 if you have the header file. */ +/* #undef HAVE_BITS_TYPE_TRAITS_H */ + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_DIRENT_H +#define HAVE_DIRENT_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_DLFCN_H +#define HAVE_DLFCN_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_INTTYPES_H +#define HAVE_INTTYPES_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_LIMITS_H +#define HAVE_LIMITS_H 1 +#endif + +/* Define to 1 if the system has the type `long long'. */ +#ifndef HAVE_LONG_LONG +#define HAVE_LONG_LONG 1 +#endif + +/* Define to 1 if you have the `memmove' function. */ +#ifndef HAVE_MEMMOVE +#define HAVE_MEMMOVE 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_MEMORY_H +#define HAVE_MEMORY_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_STDINT_H +#define HAVE_STDINT_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_STDLIB_H +#define HAVE_STDLIB_H 1 +#endif + +/* Define to 1 if you have the `strerror' function. */ +#ifndef HAVE_STRERROR +#define HAVE_STRERROR 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_STRING +#define HAVE_STRING 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_STRINGS_H +#define HAVE_STRINGS_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_STRING_H +#define HAVE_STRING_H 1 +#endif + +/* Define to 1 if you have the `strtoll' function. */ +#ifndef HAVE_STRTOLL +#define HAVE_STRTOLL 1 +#endif + +/* Define to 1 if you have the `strtoq' function. */ +#ifndef HAVE_STRTOQ +#define HAVE_STRTOQ 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_SYS_STAT_H +#define HAVE_SYS_STAT_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_SYS_TYPES_H +#define HAVE_SYS_TYPES_H 1 +#endif + +/* Define to 1 if you have the header file. */ +/* #undef HAVE_TYPE_TRAITS_H */ + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_UNISTD_H +#define HAVE_UNISTD_H 1 +#endif + +/* Define to 1 if the system has the type `unsigned long long'. */ +#ifndef HAVE_UNSIGNED_LONG_LONG +#define HAVE_UNSIGNED_LONG_LONG 1 +#endif + +/* Define to 1 if you have the header file. */ +/* #undef HAVE_WINDOWS_H */ + +/* The value of LINK_SIZE determines the number of bytes used to store links + as offsets within the compiled regex. The default is 2, which allows for + compiled patterns up to 64K long. This covers the vast majority of cases. + However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows + for longer patterns in extreme cases. On systems that support it, + "configure" can be used to override this default. */ +#ifndef LINK_SIZE +#define LINK_SIZE 2 +#endif + +/* The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different limit. + The limit exists in order to catch runaway regular expressions that take + for ever to determine that they do not match. The default is set very large + so that it does not accidentally catch legitimate cases. On systems that + support it, "configure" can be used to override this default default. */ +#ifndef MATCH_LIMIT +#define MATCH_LIMIT 10000000 +#endif + +/* The above limit applies to all calls of match(), whether or not they + increase the recursion depth. In some environments it is desirable to limit + the depth of recursive calls of match() more strictly, in order to restrict + the maximum amount of stack (or heap, if NO_RECURSE is defined) that is + used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of + match(). To have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is + a runtime method for setting a different limit. On systems that support it, + "configure" can be used to override the default. */ +#ifndef MATCH_LIMIT_RECURSION +#define MATCH_LIMIT_RECURSION MATCH_LIMIT +#endif + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#ifndef MAX_DUPLENGTH +#define MAX_DUPLENGTH 30000 +#endif + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#ifndef MAX_NAME_COUNT +#define MAX_NAME_COUNT 10000 +#endif + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#ifndef MAX_NAME_SIZE +#define MAX_NAME_SIZE 32 +#endif + +/* The value of NEWLINE determines the newline character sequence. On + Unix-like systems, "configure" can be used to override the default, which + is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or + -2 (ANYCRLF). */ +#ifndef NEWLINE +#define NEWLINE 10 +#endif + +/* PCRE uses recursive function calls to handle backtracking while matching. + This can sometimes be a problem on systems that have stacks of limited + size. Define NO_RECURSE to get a version that doesn't use recursion in the + match() function; instead it creates its own stack by steam using + pcre_recurse_malloc() to obtain memory from the heap. For more detail, see + the comments and other stuff just above the match() function. On systems + that support it, "configure" can be used to set this in the Makefile (use + --disable-stack-for-recursion). */ +/* #undef NO_RECURSE */ + +/* Name of package */ +#define PACKAGE "pcre" + +/* Define to the address where bug reports for this package should be sent. */ +#define PACKAGE_BUGREPORT "" + +/* Define to the full name of this package. */ +#define PACKAGE_NAME "PCRE" + +/* Define to the full name and version of this package. */ +#define PACKAGE_STRING "PCRE 7.2" + +/* Define to the one symbol short name of this package. */ +#define PACKAGE_TARNAME "pcre" + +/* Define to the version of this package. */ +#define PACKAGE_VERSION "7.2" + + +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +/* #undef PCRE_EXP_DEFN */ + +/* Define if linking statically (TODO: make nice with Libtool) */ +/* #undef PCRE_STATIC */ + +/* When calling PCRE via the POSIX interface, additional working storage is + required for holding the pointers to capturing substrings because PCRE + requires three integers per substring, whereas the POSIX interface provides + only two. If the number of expected substrings is small, the wrapper + function uses space on the stack, because this is faster than using + malloc() for each call. The threshold above which the stack is no longer + used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it, + "configure" can be used to override this default. */ +#ifndef POSIX_MALLOC_THRESHOLD +#define POSIX_MALLOC_THRESHOLD 10 +#endif + +/* Define to 1 if you have the ANSI C header files. */ +#ifndef STDC_HEADERS +#define STDC_HEADERS 1 +#endif + +/* Define to enable support for Unicode properties */ +/* #undef SUPPORT_UCP */ + +/* Define to enable support for the UTF-8 Unicode encoding. */ +/* #undef SUPPORT_UTF8 */ + +/* Version number of package */ +#ifndef VERSION +#define VERSION "7.2" +#endif + +/* Define to empty if `const' does not conform to ANSI C. */ +/* #undef const */ + +/* Define to `unsigned int' if does not define. */ +/* #undef size_t */ diff --git a/libpcre/config.h.in b/libpcre/config.h.in index efc537154..4145c54c7 100644 --- a/libpcre/config.h.in +++ b/libpcre/config.h.in @@ -1,143 +1,210 @@ +/* config.h.in. Generated from configure.ac by autoheader. */ -/* On Unix-like systems config.in is converted by "configure" into config.h. + +/* On Unix-like systems config.h.in is converted by "configure" into config.h. Some other environments also support the use of "configure". PCRE is written in Standard C, but there are a few non-standard things it can cope with, allowing it to run on SunOS4 and other "close to standard" systems. -On a non-Unix-like system you should just copy this file into config.h, and set -up the macros the way you need them. You should normally change the definitions -of HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because of the way -autoconf works, these cannot be made the defaults. If your system has bcopy() -and not memmove(), change the definition of HAVE_BCOPY instead of HAVE_MEMMOVE. -If your system has neither bcopy() nor memmove(), leave them both as 0; an -emulation function will be used. */ +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macros the way you need them. Alternatively, you can avoid editing by using -D +on the compiler command line to set the macro values. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */ /* If you are compiling for a system that uses EBCDIC instead of ASCII -character codes, define this macro as 1. On systems that can use "configure", -this can be done via --enable-ebcdic. */ + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic. */ +#undef EBCDIC -#ifndef EBCDIC -#define EBCDIC 0 -#endif +/* Define to 1 if you have the `bcopy' function. */ +#undef HAVE_BCOPY -/* If you are compiling for a system other than a Unix-like system or Win32, -and it needs some magic to be inserted before the definition of a function that -is exported by the library, define this macro to contain the relevant magic. If -you do not define this macro, it defaults to "extern" for a C compiler and -"extern C" for a C++ compiler on non-Win32 systems. This macro apears at the -start of every exported function that is part of the external API. It does not -appear on functions that are "external" in the C sense, but which are internal -to the library. */ +/* Define to 1 if you have the header file. */ +#undef HAVE_BITS_TYPE_TRAITS_H -/* #define PCRE_DATA_SCOPE */ +/* Define to 1 if you have the header file. */ +#undef HAVE_DIRENT_H -/* Define the following macro to empty if the "const" keyword does not work. */ +/* Define to 1 if you have the header file. */ +#undef HAVE_DLFCN_H -#undef const +/* Define to 1 if you have the header file. */ +#undef HAVE_INTTYPES_H -/* Define the following macro to "unsigned" if does not define -size_t. */ +/* Define to 1 if you have the header file. */ +#undef HAVE_LIMITS_H -#undef size_t +/* Define to 1 if the system has the type `long long'. */ +#undef HAVE_LONG_LONG -/* The following two definitions are mainly for the benefit of SunOS4, which -does not have the strerror() or memmove() functions that should be present in -all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should -normally be defined with the value 1 for other systems, but unfortunately we -cannot make this the default because "configure" files generated by autoconf -will only change 0 to 1; they won't change 1 to 0 if the functions are not -found. */ +/* Define to 1 if you have the `memmove' function. */ +#undef HAVE_MEMMOVE -#define HAVE_STRERROR 0 -#define HAVE_MEMMOVE 0 +/* Define to 1 if you have the header file. */ +#undef HAVE_MEMORY_H -/* There are some non-Unix-like systems that don't even have bcopy(). If this -macro is false, an emulation is used. If HAVE_MEMMOVE is set to 1, the value of -HAVE_BCOPY is not relevant. */ +/* Define to 1 if you have the header file. */ +#undef HAVE_STDINT_H -#define HAVE_BCOPY 0 +/* Define to 1 if you have the header file. */ +#undef HAVE_STDLIB_H -/* The value of NEWLINE determines the newline character. The default is to -leave it up to the compiler, but some sites want to force a particular value. -On Unix-like systems, "configure" can be used to override this default. */ +/* Define to 1 if you have the `strerror' function. */ +#undef HAVE_STRERROR -#ifndef NEWLINE -#define NEWLINE '\n' -#endif +/* Define to 1 if you have the header file. */ +#undef HAVE_STRING -/* The value of LINK_SIZE determines the number of bytes used to store links as -offsets within the compiled regex. The default is 2, which allows for compiled -patterns up to 64K long. This covers the vast majority of cases. However, PCRE -can also be compiled to use 3 or 4 bytes instead. This allows for longer -patterns in extreme cases. On systems that support it, "configure" can be used -to override this default. */ +/* Define to 1 if you have the header file. */ +#undef HAVE_STRINGS_H -#ifndef LINK_SIZE -#define LINK_SIZE 2 -#endif +/* Define to 1 if you have the header file. */ +#undef HAVE_STRING_H -/* When calling PCRE via the POSIX interface, additional working storage is -required for holding the pointers to capturing substrings because PCRE requires -three integers per substring, whereas the POSIX interface provides only two. If -the number of expected substrings is small, the wrapper function uses space on -the stack, because this is faster than using malloc() for each call. The -threshold above which the stack is no longer used is defined by POSIX_MALLOC_ -THRESHOLD. On systems that support it, "configure" can be used to override this -default. */ +/* Define to 1 if you have the `strtoll' function. */ +#undef HAVE_STRTOLL -#ifndef POSIX_MALLOC_THRESHOLD -#define POSIX_MALLOC_THRESHOLD 10 -#endif +/* Define to 1 if you have the `strtoq' function. */ +#undef HAVE_STRTOQ -/* PCRE uses recursive function calls to handle backtracking while matching. -This can sometimes be a problem on systems that have stacks of limited size. -Define NO_RECURSE to get a version that doesn't use recursion in the match() -function; instead it creates its own stack by steam using pcre_recurse_malloc() -to obtain memory from the heap. For more detail, see the comments and other -stuff just above the match() function. On systems that support it, "configure" -can be used to set this in the Makefile (use --disable-stack-for-recursion). */ +/* Define to 1 if you have the header file. */ +#undef HAVE_SYS_STAT_H -/* #define NO_RECURSE */ +/* Define to 1 if you have the header file. */ +#undef HAVE_SYS_TYPES_H -/* The value of MATCH_LIMIT determines the default number of times the internal -match() function can be called during a single execution of pcre_exec(). There -is a runtime interface for setting a different limit. The limit exists in order -to catch runaway regular expressions that take for ever to determine that they -do not match. The default is set very large so that it does not accidentally -catch legitimate cases. On systems that support it, "configure" can be used to -override this default default. */ +/* Define to 1 if you have the header file. */ +#undef HAVE_TYPE_TRAITS_H -#ifndef MATCH_LIMIT -#define MATCH_LIMIT 10000000 -#endif +/* Define to 1 if you have the header file. */ +#undef HAVE_UNISTD_H + +/* Define to 1 if the system has the type `unsigned long long'. */ +#undef HAVE_UNSIGNED_LONG_LONG + +/* Define to 1 if you have the header file. */ +#undef HAVE_WINDOWS_H + +/* The value of LINK_SIZE determines the number of bytes used to store links + as offsets within the compiled regex. The default is 2, which allows for + compiled patterns up to 64K long. This covers the vast majority of cases. + However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows + for longer patterns in extreme cases. On systems that support it, + "configure" can be used to override this default. */ +#undef LINK_SIZE + +/* The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different limit. + The limit exists in order to catch runaway regular expressions that take + for ever to determine that they do not match. The default is set very large + so that it does not accidentally catch legitimate cases. On systems that + support it, "configure" can be used to override this default default. */ +#undef MATCH_LIMIT /* The above limit applies to all calls of match(), whether or not they -increase the recursion depth. In some environments it is desirable to limit the -depth of recursive calls of match() more strictly, in order to restrict the -maximum amount of stack (or heap, if NO_RECURSE is defined) that is used. The -value of MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To -have any useful effect, it must be less than the value of MATCH_LIMIT. There is -a runtime method for setting a different limit. On systems that support it, -"configure" can be used to override this default default. */ + increase the recursion depth. In some environments it is desirable to limit + the depth of recursive calls of match() more strictly, in order to restrict + the maximum amount of stack (or heap, if NO_RECURSE is defined) that is + used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of + match(). To have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is + a runtime method for setting a different limit. On systems that support it, + "configure" can be used to override the default. */ +#undef MATCH_LIMIT_RECURSION -#ifndef MATCH_LIMIT_RECURSION -#define MATCH_LIMIT_RECURSION MATCH_LIMIT -#endif +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#undef MAX_DUPLENGTH -/* These three limits are parameterized just in case anybody ever wants to -change them. Care must be taken if they are increased, because they guard -against integer overflow caused by enormously large patterns. */ +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#undef MAX_NAME_COUNT -#ifndef MAX_NAME_SIZE -#define MAX_NAME_SIZE 32 -#endif +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#undef MAX_NAME_SIZE -#ifndef MAX_NAME_COUNT -#define MAX_NAME_COUNT 10000 -#endif +/* The value of NEWLINE determines the newline character sequence. On + Unix-like systems, "configure" can be used to override the default, which + is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or + -2 (ANYCRLF). */ +#undef NEWLINE -#ifndef MAX_DUPLENGTH -#define MAX_DUPLENGTH 30000 -#endif +/* PCRE uses recursive function calls to handle backtracking while matching. + This can sometimes be a problem on systems that have stacks of limited + size. Define NO_RECURSE to get a version that doesn't use recursion in the + match() function; instead it creates its own stack by steam using + pcre_recurse_malloc() to obtain memory from the heap. For more detail, see + the comments and other stuff just above the match() function. On systems + that support it, "configure" can be used to set this in the Makefile (use + --disable-stack-for-recursion). */ +#undef NO_RECURSE -/* End */ +/* Name of package */ +#undef PACKAGE + +/* Define to the address where bug reports for this package should be sent. */ +#undef PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#undef PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#undef PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#undef PACKAGE_TARNAME + +/* Define to the version of this package. */ +#undef PACKAGE_VERSION + + +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +#undef PCRE_EXP_DEFN + +/* Define if linking statically (TODO: make nice with Libtool) */ +#undef PCRE_STATIC + +/* When calling PCRE via the POSIX interface, additional working storage is + required for holding the pointers to capturing substrings because PCRE + requires three integers per substring, whereas the POSIX interface provides + only two. If the number of expected substrings is small, the wrapper + function uses space on the stack, because this is faster than using + malloc() for each call. The threshold above which the stack is no longer + used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it, + "configure" can be used to override this default. */ +#undef POSIX_MALLOC_THRESHOLD + +/* Define to 1 if you have the ANSI C header files. */ +#undef STDC_HEADERS + +/* Define to enable support for Unicode properties */ +#undef SUPPORT_UCP + +/* Define to enable support for the UTF-8 Unicode encoding. */ +#undef SUPPORT_UTF8 + +/* Version number of package */ +#undef VERSION + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to `unsigned int' if does not define. */ +#undef size_t diff --git a/libpcre/config.sub b/libpcre/config.sub index 8f7b7381c..2a4932e7f 100755 --- a/libpcre/config.sub +++ b/libpcre/config.sub @@ -1,9 +1,10 @@ #! /bin/sh # Configuration validation subroutine script. # Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, -# 2000, 2001, 2002, 2003, 2004, 2005 Free Software Foundation, Inc. +# 2000, 2001, 2002, 2003, 2004, 2005, 2006 Free Software Foundation, +# Inc. -timestamp='2005-12-23' +timestamp='2007-01-18' # This file is (in principle) common to ALL GNU software. # The presence of a machine in this file suggests that SOME GNU software @@ -240,15 +241,16 @@ case $basic_machine in | alpha | alphaev[4-8] | alphaev56 | alphaev6[78] | alphapca5[67] \ | alpha64 | alpha64ev[4-8] | alpha64ev56 | alpha64ev6[78] | alpha64pca5[67] \ | am33_2.0 \ - | arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr \ + | arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr | avr32 \ | bfin \ | c4x | clipper \ - | d10v | d30v | dlx | dsp16xx \ - | fr30 | frv \ + | d10v | d30v | dlx | dsp16xx | dvp \ + | fido | fr30 | frv \ | h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \ | i370 | i860 | i960 | ia64 \ | ip2k | iq2000 \ - | m32r | m32rle | m68000 | m68k | m88k | maxq | mb | microblaze | mcore \ + | m32c | m32r | m32rle | m68000 | m68k | m88k \ + | maxq | mb | microblaze | mcore | mep \ | mips | mipsbe | mipseb | mipsel | mipsle \ | mips16 \ | mips64 | mips64el \ @@ -268,26 +270,25 @@ case $basic_machine in | mn10200 | mn10300 \ | mt \ | msp430 \ + | nios | nios2 \ | ns16k | ns32k \ | or32 \ | pdp10 | pdp11 | pj | pjl \ | powerpc | powerpc64 | powerpc64le | powerpcle | ppcbe \ | pyramid \ - | sh | sh[1234] | sh[24]a | sh[23]e | sh[34]eb | shbe | shle | sh[1234]le | sh3ele \ + | score \ + | sh | sh[1234] | sh[24]a | sh[24]a*eb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \ | sh64 | sh64le \ - | sparc | sparc64 | sparc64b | sparc86x | sparclet | sparclite \ - | sparcv8 | sparcv9 | sparcv9b \ - | strongarm \ + | sparc | sparc64 | sparc64b | sparc64v | sparc86x | sparclet | sparclite \ + | sparcv8 | sparcv9 | sparcv9b | sparcv9v \ + | spu | strongarm \ | tahoe | thumb | tic4x | tic80 | tron \ | v850 | v850e \ | we32k \ - | x86 | xscale | xscalee[bl] | xstormy16 | xtensa \ + | x86 | xc16x | xscale | xscalee[bl] | xstormy16 | xtensa \ | z8k) basic_machine=$basic_machine-unknown ;; - m32c) - basic_machine=$basic_machine-unknown - ;; m6811 | m68hc11 | m6812 | m68hc12) # Motorola 68HC11/12. basic_machine=$basic_machine-unknown @@ -317,18 +318,18 @@ case $basic_machine in | alpha64-* | alpha64ev[4-8]-* | alpha64ev56-* | alpha64ev6[78]-* \ | alphapca5[67]-* | alpha64pca5[67]-* | arc-* \ | arm-* | armbe-* | armle-* | armeb-* | armv*-* \ - | avr-* \ + | avr-* | avr32-* \ | bfin-* | bs2000-* \ | c[123]* | c30-* | [cjt]90-* | c4x-* | c54x-* | c55x-* | c6x-* \ | clipper-* | craynv-* | cydra-* \ | d10v-* | d30v-* | dlx-* \ | elxsi-* \ - | f30[01]-* | f700-* | fr30-* | frv-* | fx80-* \ + | f30[01]-* | f700-* | fido-* | fr30-* | frv-* | fx80-* \ | h8300-* | h8500-* \ | hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \ | i*86-* | i860-* | i960-* | ia64-* \ | ip2k-* | iq2000-* \ - | m32r-* | m32rle-* \ + | m32c-* | m32r-* | m32rle-* \ | m68000-* | m680[012346]0-* | m68360-* | m683?2-* | m68k-* \ | m88110-* | m88k-* | maxq-* | mcore-* \ | mips-* | mipsbe-* | mipseb-* | mipsel-* | mipsle-* \ @@ -350,29 +351,28 @@ case $basic_machine in | mmix-* \ | mt-* \ | msp430-* \ + | nios-* | nios2-* \ | none-* | np1-* | ns16k-* | ns32k-* \ | orion-* \ | pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \ | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* | ppcbe-* \ | pyramid-* \ | romp-* | rs6000-* \ - | sh-* | sh[1234]-* | sh[24]a-* | sh[23]e-* | sh[34]eb-* | shbe-* \ + | sh-* | sh[1234]-* | sh[24]a-* | sh[24]a*eb-* | sh[23]e-* | sh[34]eb-* | sheb-* | shbe-* \ | shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \ - | sparc-* | sparc64-* | sparc64b-* | sparc86x-* | sparclet-* \ + | sparc-* | sparc64-* | sparc64b-* | sparc64v-* | sparc86x-* | sparclet-* \ | sparclite-* \ - | sparcv8-* | sparcv9-* | sparcv9b-* | strongarm-* | sv1-* | sx?-* \ + | sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | strongarm-* | sv1-* | sx?-* \ | tahoe-* | thumb-* \ | tic30-* | tic4x-* | tic54x-* | tic55x-* | tic6x-* | tic80-* \ | tron-* \ | v850-* | v850e-* | vax-* \ | we32k-* \ - | x86-* | x86_64-* | xps100-* | xscale-* | xscalee[bl]-* \ + | x86-* | x86_64-* | xc16x-* | xps100-* | xscale-* | xscalee[bl]-* \ | xstormy16-* | xtensa-* \ | ymp-* \ | z8k-*) ;; - m32c-*) - ;; # Recognize the various machine names and aliases which stand # for a CPU type and a company and sometimes even an OS. 386bsd) @@ -690,6 +690,24 @@ case $basic_machine in basic_machine=m68k-atari os=-mint ;; + mipsEE* | ee | ps2) + basic_machine=mips64r5900el-scei + case $os in + -linux*) + ;; + *) + os=-elf + ;; + esac + ;; + iop) + basic_machine=mipsel-scei + os=-irx + ;; + dvp) + basic_machine=dvp-scei + os=-elf + ;; mips3*-*) basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'` ;; @@ -910,6 +928,10 @@ case $basic_machine in sb1el) basic_machine=mipsisa64sb1el-unknown ;; + sde) + basic_machine=mipsisa32-sde + os=-elf + ;; sei) basic_machine=mips-sei os=-seiux @@ -921,6 +943,9 @@ case $basic_machine in basic_machine=sh-hitachi os=-hms ;; + sh5el) + basic_machine=sh5le-unknown + ;; sh64) basic_machine=sh64-unknown ;; @@ -1126,7 +1151,7 @@ case $basic_machine in sh[1234] | sh[24]a | sh[34]eb | sh[1234]le | sh[23]ele) basic_machine=sh-unknown ;; - sparc | sparcv8 | sparcv9 | sparcv9b) + sparc | sparcv8 | sparcv9 | sparcv9b | sparcv9v) basic_machine=sparc-sun ;; cydra) @@ -1199,7 +1224,8 @@ case $os in | -aos* \ | -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \ | -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \ - | -hiux* | -386bsd* | -knetbsd* | -mirbsd* | -netbsd* | -openbsd* \ + | -hiux* | -386bsd* | -knetbsd* | -mirbsd* | -netbsd* \ + | -openbsd* | -solidbsd* \ | -ekkobsd* | -kfreebsd* | -freebsd* | -riscix* | -lynxos* \ | -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \ | -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \ @@ -1214,7 +1240,7 @@ case $os in | -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \ | -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \ | -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \ - | -skyos* | -haiku* | -rdos*) + | -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -irx*) # Remember, each alternative MUST END IN *, to match a version number. ;; -qnx*) @@ -1366,6 +1392,12 @@ else # system, and we'll never get to this point. case $basic_machine in + score-*) + os=-elf + ;; + spu-*) + os=-elf + ;; *-acorn) os=-riscix1.2 ;; @@ -1375,9 +1407,9 @@ case $basic_machine in arm*-semi) os=-aout ;; - c4x-* | tic4x-*) - os=-coff - ;; + c4x-* | tic4x-*) + os=-coff + ;; # This must come before the *-dec entry. pdp10-*) os=-tops20 @@ -1403,6 +1435,9 @@ case $basic_machine in m68*-cisco) os=-aout ;; + mep-*) + os=-elf + ;; mips*-cisco) os=-elf ;; diff --git a/libpcre/configure b/libpcre/configure index ba13c87e3..5e1dd9c4a 100755 --- a/libpcre/configure +++ b/libpcre/configure @@ -1,81 +1,35 @@ #! /bin/sh # Guess values for system-dependent variables and create Makefiles. -# Generated by GNU Autoconf 2.59. +# Generated by GNU Autoconf 2.61 for PCRE 7.2. # -# Copyright (C) 2003 Free Software Foundation, Inc. +# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001, +# 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. # This configure script is free software; the Free Software Foundation # gives unlimited permission to copy, distribute and modify it. ## --------------------- ## ## M4sh Initialization. ## ## --------------------- ## -# Be Bourne compatible +# Be more Bourne compatible +DUALCASE=1; export DUALCASE # for MKS sh if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then emulate sh NULLCMD=: # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which # is contrary to our usage. Disable this feature. alias -g '${1+"$@"}'='"$@"' -elif test -n "${BASH_VERSION+set}" && (set -o posix) >/dev/null 2>&1; then - set -o posix -fi -DUALCASE=1; export DUALCASE # for MKS sh - -# Support unset when possible. -if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then - as_unset=unset + setopt NO_GLOB_SUBST else - as_unset=false + case `(set -o) 2>/dev/null` in + *posix*) set -o posix ;; +esac + fi -# Work around bugs in pre-3.0 UWIN ksh. -$as_unset ENV MAIL MAILPATH -PS1='$ ' -PS2='> ' -PS4='+ ' - -# NLS nuisances. -for as_var in \ - LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ - LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ - LC_TELEPHONE LC_TIME -do - if (set +x; test -z "`(eval $as_var=C; export $as_var) 2>&1`"); then - eval $as_var=C; export $as_var - else - $as_unset $as_var - fi -done - -# Required to use basename. -if expr a : '\(a\)' >/dev/null 2>&1; then - as_expr=expr -else - as_expr=false -fi - -if (basename /) >/dev/null 2>&1 && test "X`basename / 2>&1`" = "X/"; then - as_basename=basename -else - as_basename=false -fi -# Name of the executable. -as_me=`$as_basename "$0" || -$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ - X"$0" : 'X\(//\)$' \| \ - X"$0" : 'X\(/\)$' \| \ - . : '\(.\)' 2>/dev/null || -echo X/"$0" | - sed '/^.*\/\([^/][^/]*\)\/*$/{ s//\1/; q; } - /^X\/\(\/\/\)$/{ s//\1/; q; } - /^X\/\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - - -# PATH needs CR, and LINENO needs CR and PATH. +# PATH needs CR # Avoid depending upon Character Ranges. as_cr_letters='abcdefghijklmnopqrstuvwxyz' as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' @@ -96,124 +50,466 @@ if test "${PATH_SEPARATOR+set}" != set; then rm -f conf$$.sh fi +# Support unset when possible. +if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then + as_unset=unset +else + as_unset=false +fi - as_lineno_1=$LINENO - as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` - test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" || { - # Find who we are. Look in the path if we contain no path at all - # relative or not. - case $0 in - *[\\/]* ) as_myself=$0 ;; - *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR + +# IFS +# We need space, tab and new line, in precisely that order. Quoting is +# there to prevent editors from complaining about space-tab. +# (If _AS_PATH_WALK were called with IFS unset, it would disable word +# splitting by setting IFS to empty value.) +as_nl=' +' +IFS=" "" $as_nl" + +# Find who we are. Look in the path if we contain no directory separator. +case $0 in + *[\\/]* ) as_myself=$0 ;; + *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR for as_dir in $PATH do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break done +IFS=$as_save_IFS - ;; - esac - # We did not find ourselves, most probably we were run as `sh COMMAND' - # in which case we are not to be found in the path. - if test "x$as_myself" = x; then - as_myself=$0 + ;; +esac +# We did not find ourselves, most probably we were run as `sh COMMAND' +# in which case we are not to be found in the path. +if test "x$as_myself" = x; then + as_myself=$0 +fi +if test ! -f "$as_myself"; then + echo "$as_myself: error: cannot find myself; rerun with an absolute file name" >&2 + { (exit 1); exit 1; } +fi + +# Work around bugs in pre-3.0 UWIN ksh. +for as_var in ENV MAIL MAILPATH +do ($as_unset $as_var) >/dev/null 2>&1 && $as_unset $as_var +done +PS1='$ ' +PS2='> ' +PS4='+ ' + +# NLS nuisances. +for as_var in \ + LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ + LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ + LC_TELEPHONE LC_TIME +do + if (set +x; test -z "`(eval $as_var=C; export $as_var) 2>&1`"); then + eval $as_var=C; export $as_var + else + ($as_unset $as_var) >/dev/null 2>&1 && $as_unset $as_var fi - if test ! -f "$as_myself"; then - { echo "$as_me: error: cannot find myself; rerun with an absolute path" >&2 - { (exit 1); exit 1; }; } - fi - case $CONFIG_SHELL in - '') +done + +# Required to use basename. +if expr a : '\(a\)' >/dev/null 2>&1 && + test "X`expr 00001 : '.*\(...\)'`" = X001; then + as_expr=expr +else + as_expr=false +fi + +if (basename -- /) >/dev/null 2>&1 && test "X`basename -- / 2>&1`" = "X/"; then + as_basename=basename +else + as_basename=false +fi + + +# Name of the executable. +as_me=`$as_basename -- "$0" || +$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)' \| . 2>/dev/null || +echo X/"$0" | + sed '/^.*\/\([^/][^/]*\)\/*$/{ + s//\1/ + q + } + /^X\/\(\/\/\)$/{ + s//\1/ + q + } + /^X\/\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + +# CDPATH. +$as_unset CDPATH + + +if test "x$CONFIG_SHELL" = x; then + if (eval ":") 2>/dev/null; then + as_have_required=yes +else + as_have_required=no +fi + + if test $as_have_required = yes && (eval ": +(as_func_return () { + (exit \$1) +} +as_func_success () { + as_func_return 0 +} +as_func_failure () { + as_func_return 1 +} +as_func_ret_success () { + return 0 +} +as_func_ret_failure () { + return 1 +} + +exitcode=0 +if as_func_success; then + : +else + exitcode=1 + echo as_func_success failed. +fi + +if as_func_failure; then + exitcode=1 + echo as_func_failure succeeded. +fi + +if as_func_ret_success; then + : +else + exitcode=1 + echo as_func_ret_success failed. +fi + +if as_func_ret_failure; then + exitcode=1 + echo as_func_ret_failure succeeded. +fi + +if ( set x; as_func_ret_success y && test x = \"\$1\" ); then + : +else + exitcode=1 + echo positional parameters were not saved. +fi + +test \$exitcode = 0) || { (exit 1); exit 1; } + +( + as_lineno_1=\$LINENO + as_lineno_2=\$LINENO + test \"x\$as_lineno_1\" != \"x\$as_lineno_2\" && + test \"x\`expr \$as_lineno_1 + 1\`\" = \"x\$as_lineno_2\") || { (exit 1); exit 1; } +") 2> /dev/null; then + : +else + as_candidate_shells= as_save_IFS=$IFS; IFS=$PATH_SEPARATOR for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. - for as_base in sh bash ksh sh5; do - case $as_dir in + case $as_dir in /*) - if ("$as_dir/$as_base" -c ' + for as_base in sh bash ksh sh5; do + as_candidate_shells="$as_candidate_shells $as_dir/$as_base" + done;; + esac +done +IFS=$as_save_IFS + + + for as_shell in $as_candidate_shells $SHELL; do + # Try only shells that exist, to save several forks. + if { test -f "$as_shell" || test -f "$as_shell.exe"; } && + { ("$as_shell") 2> /dev/null <<\_ASEOF +if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then + emulate sh + NULLCMD=: + # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which + # is contrary to our usage. Disable this feature. + alias -g '${1+"$@"}'='"$@"' + setopt NO_GLOB_SUBST +else + case `(set -o) 2>/dev/null` in + *posix*) set -o posix ;; +esac + +fi + + +: +_ASEOF +}; then + CONFIG_SHELL=$as_shell + as_have_required=yes + if { "$as_shell" 2> /dev/null <<\_ASEOF +if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then + emulate sh + NULLCMD=: + # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which + # is contrary to our usage. Disable this feature. + alias -g '${1+"$@"}'='"$@"' + setopt NO_GLOB_SUBST +else + case `(set -o) 2>/dev/null` in + *posix*) set -o posix ;; +esac + +fi + + +: +(as_func_return () { + (exit $1) +} +as_func_success () { + as_func_return 0 +} +as_func_failure () { + as_func_return 1 +} +as_func_ret_success () { + return 0 +} +as_func_ret_failure () { + return 1 +} + +exitcode=0 +if as_func_success; then + : +else + exitcode=1 + echo as_func_success failed. +fi + +if as_func_failure; then + exitcode=1 + echo as_func_failure succeeded. +fi + +if as_func_ret_success; then + : +else + exitcode=1 + echo as_func_ret_success failed. +fi + +if as_func_ret_failure; then + exitcode=1 + echo as_func_ret_failure succeeded. +fi + +if ( set x; as_func_ret_success y && test x = "$1" ); then + : +else + exitcode=1 + echo positional parameters were not saved. +fi + +test $exitcode = 0) || { (exit 1); exit 1; } + +( as_lineno_1=$LINENO as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" ') 2>/dev/null; then - $as_unset BASH_ENV || test "${BASH_ENV+set}" != set || { BASH_ENV=; export BASH_ENV; } - $as_unset ENV || test "${ENV+set}" != set || { ENV=; export ENV; } - CONFIG_SHELL=$as_dir/$as_base - export CONFIG_SHELL - exec "$CONFIG_SHELL" "$0" ${1+"$@"} - fi;; - esac - done -done -;; - esac + test "x`expr $as_lineno_1 + 1`" = "x$as_lineno_2") || { (exit 1); exit 1; } + +_ASEOF +}; then + break +fi + +fi + + done + + if test "x$CONFIG_SHELL" != x; then + for as_var in BASH_ENV ENV + do ($as_unset $as_var) >/dev/null 2>&1 && $as_unset $as_var + done + export CONFIG_SHELL + exec "$CONFIG_SHELL" "$as_myself" ${1+"$@"} +fi + + + if test $as_have_required = no; then + echo This script requires a shell more modern than all the + echo shells that I found on your system. Please install a + echo modern shell, or manually run the script under such a + echo shell if you do have one. + { (exit 1); exit 1; } +fi + + +fi + +fi + + + +(eval "as_func_return () { + (exit \$1) +} +as_func_success () { + as_func_return 0 +} +as_func_failure () { + as_func_return 1 +} +as_func_ret_success () { + return 0 +} +as_func_ret_failure () { + return 1 +} + +exitcode=0 +if as_func_success; then + : +else + exitcode=1 + echo as_func_success failed. +fi + +if as_func_failure; then + exitcode=1 + echo as_func_failure succeeded. +fi + +if as_func_ret_success; then + : +else + exitcode=1 + echo as_func_ret_success failed. +fi + +if as_func_ret_failure; then + exitcode=1 + echo as_func_ret_failure succeeded. +fi + +if ( set x; as_func_ret_success y && test x = \"\$1\" ); then + : +else + exitcode=1 + echo positional parameters were not saved. +fi + +test \$exitcode = 0") || { + echo No shell found that supports shell functions. + echo Please tell autoconf@gnu.org about your system, + echo including any error possibly output before this + echo message +} + + + + as_lineno_1=$LINENO + as_lineno_2=$LINENO + test "x$as_lineno_1" != "x$as_lineno_2" && + test "x`expr $as_lineno_1 + 1`" = "x$as_lineno_2" || { # Create $as_me.lineno as a copy of $as_myself, but with $LINENO # uniformly replaced by the line number. The first 'sed' inserts a - # line-number line before each line; the second 'sed' does the real - # work. The second script uses 'N' to pair each line-number line - # with the numbered line, and appends trailing '-' during - # substitution so that $LINENO is not a special case at line end. + # line-number line after each line using $LINENO; the second 'sed' + # does the real work. The second script uses 'N' to pair each + # line-number line with the line containing $LINENO, and appends + # trailing '-' during substitution so that $LINENO is not a special + # case at line end. # (Raja R Harinath suggested sed '=', and Paul Eggert wrote the - # second 'sed' script. Blame Lee E. McMahon for sed's syntax. :-) - sed '=' <$as_myself | + # scripts with optimization help from Paolo Bonzini. Blame Lee + # E. McMahon (1931-1989) for sed's syntax. :-) + sed -n ' + p + /[$]LINENO/= + ' <$as_myself | sed ' + s/[$]LINENO.*/&-/ + t lineno + b + :lineno N - s,$,-, - : loop - s,^\(['$as_cr_digits']*\)\(.*\)[$]LINENO\([^'$as_cr_alnum'_]\),\1\2\1\3, + :loop + s/[$]LINENO\([^'$as_cr_alnum'_].*\n\)\(.*\)/\2\1\2/ t loop - s,-$,, - s,^['$as_cr_digits']*\n,, + s/-\n.*// ' >$as_me.lineno && - chmod +x $as_me.lineno || + chmod +x "$as_me.lineno" || { echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2 { (exit 1); exit 1; }; } # Don't try to exec as it changes $[0], causing all sort of problems # (the dirname of $[0] is not the place where we might find the - # original and so on. Autoconf is especially sensible to this). - . ./$as_me.lineno + # original and so on. Autoconf is especially sensitive to this). + . "./$as_me.lineno" # Exit status is that of the last command. exit } -case `echo "testing\c"; echo 1,2,3`,`echo -n testing; echo 1,2,3` in - *c*,-n*) ECHO_N= ECHO_C=' -' ECHO_T=' ' ;; - *c*,* ) ECHO_N=-n ECHO_C= ECHO_T= ;; - *) ECHO_N= ECHO_C='\c' ECHO_T= ;; +if (as_dir=`dirname -- /` && test "X$as_dir" = X/) >/dev/null 2>&1; then + as_dirname=dirname +else + as_dirname=false +fi + +ECHO_C= ECHO_N= ECHO_T= +case `echo -n x` in +-n*) + case `echo 'x\c'` in + *c*) ECHO_T=' ';; # ECHO_T is single tab character. + *) ECHO_C='\c';; + esac;; +*) + ECHO_N='-n';; esac -if expr a : '\(a\)' >/dev/null 2>&1; then +if expr a : '\(a\)' >/dev/null 2>&1 && + test "X`expr 00001 : '.*\(...\)'`" = X001; then as_expr=expr else as_expr=false fi rm -f conf$$ conf$$.exe conf$$.file +if test -d conf$$.dir; then + rm -f conf$$.dir/conf$$.file +else + rm -f conf$$.dir + mkdir conf$$.dir +fi echo >conf$$.file if ln -s conf$$.file conf$$ 2>/dev/null; then - # We could just check for DJGPP; but this test a) works b) is more generic - # and c) will remain valid once DJGPP supports symlinks (DJGPP 2.04). - if test -f conf$$.exe; then - # Don't use ln at all; we don't have any links + as_ln_s='ln -s' + # ... but there are two gotchas: + # 1) On MSYS, both `ln -s file dir' and `ln file dir' fail. + # 2) DJGPP < 2.04 has no symlinks; `ln -s' creates a wrapper executable. + # In both cases, we have to default to `cp -p'. + ln -s conf$$.file conf$$.dir 2>/dev/null && test ! -f conf$$.exe || as_ln_s='cp -p' - else - as_ln_s='ln -s' - fi elif ln conf$$.file conf$$ 2>/dev/null; then as_ln_s=ln else as_ln_s='cp -p' fi -rm -f conf$$ conf$$.exe conf$$.file +rm -f conf$$ conf$$.exe conf$$.dir/conf$$.file conf$$.file +rmdir conf$$.dir 2>/dev/null if mkdir -p . 2>/dev/null; then as_mkdir_p=: @@ -222,7 +518,28 @@ else as_mkdir_p=false fi -as_executable_p="test -f" +if test -x / >/dev/null 2>&1; then + as_test_x='test -x' +else + if ls -dL / >/dev/null 2>&1; then + as_ls_L_option=L + else + as_ls_L_option= + fi + as_test_x=' + eval sh -c '\'' + if test -d "$1"; then + test -d "$1/."; + else + case $1 in + -*)set "./$1";; + esac; + case `ls -ld'$as_ls_L_option' "$1" 2>/dev/null` in + ???[sx]*):;;*)false;;esac;fi + '\'' sh + ' +fi +as_executable_p=$as_test_x # Sed expression to map a string onto a valid CPP name. as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" @@ -231,87 +548,183 @@ as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" as_tr_sh="eval sed 'y%*+%pp%;s%[^_$as_cr_alnum]%_%g'" -# IFS -# We need space, tab and new line, in precisely that order. -as_nl=' -' -IFS=" $as_nl" - -# CDPATH. -$as_unset CDPATH +exec 7<&0 &1 # Name of the host. # hostname on some systems (SVR3.2, Linux) returns a bogus exit status, # so uname gets run too. ac_hostname=`(hostname || uname -n) 2>/dev/null | sed 1q` -exec 6>&1 - # # Initializations. # ac_default_prefix=/usr/local +ac_clean_files= ac_config_libobj_dir=. +LIBOBJS= cross_compiling=no subdirs= MFLAGS= MAKEFLAGS= SHELL=${CONFIG_SHELL-/bin/sh} -# Maximum number of lines to put in a shell here document. -# This variable seems obsolete. It should probably be removed, and -# only ac_max_sed_lines should be used. -: ${ac_max_here_lines=38} - # Identity of this package. -PACKAGE_NAME= -PACKAGE_TARNAME= -PACKAGE_VERSION= -PACKAGE_STRING= -PACKAGE_BUGREPORT= +PACKAGE_NAME='PCRE' +PACKAGE_TARNAME='pcre' +PACKAGE_VERSION='7.2' +PACKAGE_STRING='PCRE 7.2' +PACKAGE_BUGREPORT='' -ac_unique_file="dftables.c" -ac_unique_file="pcre.h" +ac_unique_file="pcre.h.in" # Factoring default headers for most tests. ac_includes_default="\ #include -#if HAVE_SYS_TYPES_H +#ifdef HAVE_SYS_TYPES_H # include #endif -#if HAVE_SYS_STAT_H +#ifdef HAVE_SYS_STAT_H # include #endif -#if STDC_HEADERS +#ifdef STDC_HEADERS # include # include #else -# if HAVE_STDLIB_H +# ifdef HAVE_STDLIB_H # include # endif #endif -#if HAVE_STRING_H -# if !STDC_HEADERS && HAVE_MEMORY_H +#ifdef HAVE_STRING_H +# if !defined STDC_HEADERS && defined HAVE_MEMORY_H # include # endif # include #endif -#if HAVE_STRINGS_H +#ifdef HAVE_STRINGS_H # include #endif -#if HAVE_INTTYPES_H +#ifdef HAVE_INTTYPES_H # include -#else -# if HAVE_STDINT_H -# include -# endif #endif -#if HAVE_UNISTD_H +#ifdef HAVE_STDINT_H +# include +#endif +#ifdef HAVE_UNISTD_H # include #endif" -ac_subst_vars='SHELL PATH_SEPARATOR PACKAGE_NAME PACKAGE_TARNAME PACKAGE_VERSION PACKAGE_STRING PACKAGE_BUGREPORT exec_prefix prefix program_transform_name bindir sbindir libexecdir datadir sysconfdir sharedstatedir localstatedir libdir includedir oldincludedir infodir mandir build_alias host_alias target_alias DEFS ECHO_C ECHO_N ECHO_T LIBS CC CFLAGS LDFLAGS CPPFLAGS ac_ct_CC EXEEXT OBJEXT RANLIB ac_ct_RANLIB CPP EGREP pcre_have_long_long pcre_have_ulong_long build build_cpu build_vendor build_os host host_cpu host_vendor host_os BUILD_EXEEXT BUILD_OBJEXT CC_FOR_BUILD CFLAGS_FOR_BUILD CXXLDFLAGS EBCDIC HAVE_MEMMOVE HAVE_STRERROR LINK_SIZE MATCH_LIMIT MATCH_LIMIT_RECURSION NEWLINE NO_RECURSE PCRE_LIB_VERSION PCRE_POSIXLIB_VERSION PCRE_VERSION POSIX_MALLOC_THRESHOLD UCP UTF8 POSIX_OBJ POSIX_LOBJ POSIX_LIB LIBOBJS LTLIBOBJS' +ac_subst_vars='SHELL +PATH_SEPARATOR +PACKAGE_NAME +PACKAGE_TARNAME +PACKAGE_VERSION +PACKAGE_STRING +PACKAGE_BUGREPORT +exec_prefix +prefix +program_transform_name +bindir +sbindir +libexecdir +datarootdir +datadir +sysconfdir +sharedstatedir +localstatedir +includedir +oldincludedir +docdir +infodir +htmldir +dvidir +pdfdir +psdir +libdir +localedir +mandir +DEFS +ECHO_C +ECHO_N +ECHO_T +LIBS +build_alias +host_alias +target_alias +INSTALL_PROGRAM +INSTALL_SCRIPT +INSTALL_DATA +am__isrc +CYGPATH_W +PACKAGE +VERSION +ACLOCAL +AUTOCONF +AUTOMAKE +AUTOHEADER +MAKEINFO +install_sh +STRIP +INSTALL_STRIP_PROGRAM +mkdir_p +AWK +SET_MAKE +am__leading_dot +AMTAR +am__tar +am__untar +CC +CFLAGS +LDFLAGS +CPPFLAGS +ac_ct_CC +EXEEXT +OBJEXT +DEPDIR +am__include +am__quote +AMDEP_TRUE +AMDEP_FALSE +AMDEPBACKSLASH +CCDEPMODE +am__fastdepCC_TRUE +am__fastdepCC_FALSE +RANLIB +LN_S +PCRE_MAJOR +PCRE_MINOR +PCRE_PRERELEASE +PCRE_DATE +CPP +GREP +EGREP +pcre_have_type_traits +pcre_have_bits_type_traits +WITH_REBUILD_CHARTABLES_TRUE +WITH_REBUILD_CHARTABLES_FALSE +pcre_have_long_long +pcre_have_ulong_long +build +build_cpu +build_vendor +build_os +host +host_cpu +host_vendor +host_os +EXTRA_LIBPCRE_LDFLAGS +LIBOBJS +LTLIBOBJS' ac_subst_files='' + ac_precious_vars='build_alias +host_alias +target_alias +CC +CFLAGS +LDFLAGS +LIBS +CPPFLAGS +CPP' + # Initialize some variables set by options. ac_init_help= @@ -338,34 +751,48 @@ x_libraries=NONE # and all the variables that are supposed to be based on exec_prefix # by default will actually change. # Use braces instead of parens because sh, perl, etc. also accept them. +# (The list follows the same order as the GNU Coding Standards.) bindir='${exec_prefix}/bin' sbindir='${exec_prefix}/sbin' libexecdir='${exec_prefix}/libexec' -datadir='${prefix}/share' +datarootdir='${prefix}/share' +datadir='${datarootdir}' sysconfdir='${prefix}/etc' sharedstatedir='${prefix}/com' localstatedir='${prefix}/var' -libdir='${exec_prefix}/lib' includedir='${prefix}/include' oldincludedir='/usr/include' -infodir='${prefix}/info' -mandir='${prefix}/man' +docdir='${datarootdir}/doc/${PACKAGE_TARNAME}' +infodir='${datarootdir}/info' +htmldir='${docdir}' +dvidir='${docdir}' +pdfdir='${docdir}' +psdir='${docdir}' +libdir='${exec_prefix}/lib' +localedir='${datarootdir}/locale' +mandir='${datarootdir}/man' ac_prev= +ac_dashdash= for ac_option do # If the previous option needs an argument, assign it. if test -n "$ac_prev"; then - eval "$ac_prev=\$ac_option" + eval $ac_prev=\$ac_option ac_prev= continue fi - ac_optarg=`expr "x$ac_option" : 'x[^=]*=\(.*\)'` + case $ac_option in + *=*) ac_optarg=`expr "X$ac_option" : '[^=]*=\(.*\)'` ;; + *) ac_optarg=yes ;; + esac # Accept the important Cygnus configure options, so we can diagnose typos. - case $ac_option in + case $ac_dashdash$ac_option in + --) + ac_dashdash=yes ;; -bindir | --bindir | --bindi | --bind | --bin | --bi) ac_prev=bindir ;; @@ -387,33 +814,45 @@ do --config-cache | -C) cache_file=config.cache ;; - -datadir | --datadir | --datadi | --datad | --data | --dat | --da) + -datadir | --datadir | --datadi | --datad) ac_prev=datadir ;; - -datadir=* | --datadir=* | --datadi=* | --datad=* | --data=* | --dat=* \ - | --da=*) + -datadir=* | --datadir=* | --datadi=* | --datad=*) datadir=$ac_optarg ;; + -datarootdir | --datarootdir | --datarootdi | --datarootd | --dataroot \ + | --dataroo | --dataro | --datar) + ac_prev=datarootdir ;; + -datarootdir=* | --datarootdir=* | --datarootdi=* | --datarootd=* \ + | --dataroot=* | --dataroo=* | --dataro=* | --datar=*) + datarootdir=$ac_optarg ;; + -disable-* | --disable-*) ac_feature=`expr "x$ac_option" : 'x-*disable-\(.*\)'` # Reject names that are not valid shell variable names. - expr "x$ac_feature" : ".*[^-_$as_cr_alnum]" >/dev/null && + expr "x$ac_feature" : ".*[^-._$as_cr_alnum]" >/dev/null && { echo "$as_me: error: invalid feature name: $ac_feature" >&2 { (exit 1); exit 1; }; } - ac_feature=`echo $ac_feature | sed 's/-/_/g'` - eval "enable_$ac_feature=no" ;; + ac_feature=`echo $ac_feature | sed 's/[-.]/_/g'` + eval enable_$ac_feature=no ;; + + -docdir | --docdir | --docdi | --doc | --do) + ac_prev=docdir ;; + -docdir=* | --docdir=* | --docdi=* | --doc=* | --do=*) + docdir=$ac_optarg ;; + + -dvidir | --dvidir | --dvidi | --dvid | --dvi | --dv) + ac_prev=dvidir ;; + -dvidir=* | --dvidir=* | --dvidi=* | --dvid=* | --dvi=* | --dv=*) + dvidir=$ac_optarg ;; -enable-* | --enable-*) ac_feature=`expr "x$ac_option" : 'x-*enable-\([^=]*\)'` # Reject names that are not valid shell variable names. - expr "x$ac_feature" : ".*[^-_$as_cr_alnum]" >/dev/null && + expr "x$ac_feature" : ".*[^-._$as_cr_alnum]" >/dev/null && { echo "$as_me: error: invalid feature name: $ac_feature" >&2 { (exit 1); exit 1; }; } - ac_feature=`echo $ac_feature | sed 's/-/_/g'` - case $ac_option in - *=*) ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"`;; - *) ac_optarg=yes ;; - esac - eval "enable_$ac_feature='$ac_optarg'" ;; + ac_feature=`echo $ac_feature | sed 's/[-.]/_/g'` + eval enable_$ac_feature=\$ac_optarg ;; -exec-prefix | --exec_prefix | --exec-prefix | --exec-prefi \ | --exec-pref | --exec-pre | --exec-pr | --exec-p | --exec- \ @@ -440,6 +879,12 @@ do -host=* | --host=* | --hos=* | --ho=*) host_alias=$ac_optarg ;; + -htmldir | --htmldir | --htmldi | --htmld | --html | --htm | --ht) + ac_prev=htmldir ;; + -htmldir=* | --htmldir=* | --htmldi=* | --htmld=* | --html=* | --htm=* \ + | --ht=*) + htmldir=$ac_optarg ;; + -includedir | --includedir | --includedi | --included | --include \ | --includ | --inclu | --incl | --inc) ac_prev=includedir ;; @@ -464,13 +909,16 @@ do | --libexe=* | --libex=* | --libe=*) libexecdir=$ac_optarg ;; + -localedir | --localedir | --localedi | --localed | --locale) + ac_prev=localedir ;; + -localedir=* | --localedir=* | --localedi=* | --localed=* | --locale=*) + localedir=$ac_optarg ;; + -localstatedir | --localstatedir | --localstatedi | --localstated \ - | --localstate | --localstat | --localsta | --localst \ - | --locals | --local | --loca | --loc | --lo) + | --localstate | --localstat | --localsta | --localst | --locals) ac_prev=localstatedir ;; -localstatedir=* | --localstatedir=* | --localstatedi=* | --localstated=* \ - | --localstate=* | --localstat=* | --localsta=* | --localst=* \ - | --locals=* | --local=* | --loca=* | --loc=* | --lo=*) + | --localstate=* | --localstat=* | --localsta=* | --localst=* | --locals=*) localstatedir=$ac_optarg ;; -mandir | --mandir | --mandi | --mand | --man | --ma | --m) @@ -535,6 +983,16 @@ do | --progr-tra=* | --program-tr=* | --program-t=*) program_transform_name=$ac_optarg ;; + -pdfdir | --pdfdir | --pdfdi | --pdfd | --pdf | --pd) + ac_prev=pdfdir ;; + -pdfdir=* | --pdfdir=* | --pdfdi=* | --pdfd=* | --pdf=* | --pd=*) + pdfdir=$ac_optarg ;; + + -psdir | --psdir | --psdi | --psd | --ps) + ac_prev=psdir ;; + -psdir=* | --psdir=* | --psdi=* | --psd=* | --ps=*) + psdir=$ac_optarg ;; + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ | -silent | --silent | --silen | --sile | --sil) silent=yes ;; @@ -587,24 +1045,20 @@ do -with-* | --with-*) ac_package=`expr "x$ac_option" : 'x-*with-\([^=]*\)'` # Reject names that are not valid shell variable names. - expr "x$ac_package" : ".*[^-_$as_cr_alnum]" >/dev/null && + expr "x$ac_package" : ".*[^-._$as_cr_alnum]" >/dev/null && { echo "$as_me: error: invalid package name: $ac_package" >&2 { (exit 1); exit 1; }; } - ac_package=`echo $ac_package| sed 's/-/_/g'` - case $ac_option in - *=*) ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"`;; - *) ac_optarg=yes ;; - esac - eval "with_$ac_package='$ac_optarg'" ;; + ac_package=`echo $ac_package | sed 's/[-.]/_/g'` + eval with_$ac_package=\$ac_optarg ;; -without-* | --without-*) ac_package=`expr "x$ac_option" : 'x-*without-\(.*\)'` # Reject names that are not valid shell variable names. - expr "x$ac_package" : ".*[^-_$as_cr_alnum]" >/dev/null && + expr "x$ac_package" : ".*[^-._$as_cr_alnum]" >/dev/null && { echo "$as_me: error: invalid package name: $ac_package" >&2 { (exit 1); exit 1; }; } - ac_package=`echo $ac_package | sed 's/-/_/g'` - eval "with_$ac_package=no" ;; + ac_package=`echo $ac_package | sed 's/[-.]/_/g'` + eval with_$ac_package=no ;; --x) # Obsolete; use --with-x. @@ -635,8 +1089,7 @@ Try \`$0 --help' for more information." >&2 expr "x$ac_envvar" : ".*[^_$as_cr_alnum]" >/dev/null && { echo "$as_me: error: invalid variable name: $ac_envvar" >&2 { (exit 1); exit 1; }; } - ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"` - eval "$ac_envvar='$ac_optarg'" + eval $ac_envvar=\$ac_optarg export $ac_envvar ;; *) @@ -656,27 +1109,19 @@ if test -n "$ac_prev"; then { (exit 1); exit 1; }; } fi -# Be sure to have absolute paths. -for ac_var in exec_prefix prefix +# Be sure to have absolute directory names. +for ac_var in exec_prefix prefix bindir sbindir libexecdir datarootdir \ + datadir sysconfdir sharedstatedir localstatedir includedir \ + oldincludedir docdir infodir htmldir dvidir pdfdir psdir \ + libdir localedir mandir do - eval ac_val=$`echo $ac_var` + eval ac_val=\$$ac_var case $ac_val in - [\\/$]* | ?:[\\/]* | NONE | '' ) ;; - *) { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 - { (exit 1); exit 1; }; };; - esac -done - -# Be sure to have absolute paths. -for ac_var in bindir sbindir libexecdir datadir sysconfdir sharedstatedir \ - localstatedir libdir includedir oldincludedir infodir mandir -do - eval ac_val=$`echo $ac_var` - case $ac_val in - [\\/$]* | ?:[\\/]* ) ;; - *) { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 - { (exit 1); exit 1; }; };; + [\\/$]* | ?:[\\/]* ) continue;; + NONE | '' ) case $ac_var in *prefix ) continue;; esac;; esac + { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 + { (exit 1); exit 1; }; } done # There might be people who depend on the old broken behavior: `$host' @@ -703,74 +1148,76 @@ test -n "$host_alias" && ac_tool_prefix=$host_alias- test "$silent" = yes && exec 6>/dev/null +ac_pwd=`pwd` && test -n "$ac_pwd" && +ac_ls_di=`ls -di .` && +ac_pwd_ls_di=`cd "$ac_pwd" && ls -di .` || + { echo "$as_me: error: Working directory cannot be determined" >&2 + { (exit 1); exit 1; }; } +test "X$ac_ls_di" = "X$ac_pwd_ls_di" || + { echo "$as_me: error: pwd does not report name of working directory" >&2 + { (exit 1); exit 1; }; } + + # Find the source files, if location was not specified. if test -z "$srcdir"; then ac_srcdir_defaulted=yes - # Try the directory containing this script, then its parent. - ac_confdir=`(dirname "$0") 2>/dev/null || + # Try the directory containing this script, then the parent directory. + ac_confdir=`$as_dirname -- "$0" || $as_expr X"$0" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ X"$0" : 'X\(//\)[^/]' \| \ X"$0" : 'X\(//\)$' \| \ - X"$0" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || + X"$0" : 'X\(/\)' \| . 2>/dev/null || echo X"$0" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` srcdir=$ac_confdir - if test ! -r $srcdir/$ac_unique_file; then + if test ! -r "$srcdir/$ac_unique_file"; then srcdir=.. fi else ac_srcdir_defaulted=no fi -if test ! -r $srcdir/$ac_unique_file; then - if test "$ac_srcdir_defaulted" = yes; then - { echo "$as_me: error: cannot find sources ($ac_unique_file) in $ac_confdir or .." >&2 +if test ! -r "$srcdir/$ac_unique_file"; then + test "$ac_srcdir_defaulted" = yes && srcdir="$ac_confdir or .." + { echo "$as_me: error: cannot find sources ($ac_unique_file) in $srcdir" >&2 { (exit 1); exit 1; }; } - else - { echo "$as_me: error: cannot find sources ($ac_unique_file) in $srcdir" >&2 - { (exit 1); exit 1; }; } - fi fi -(cd $srcdir && test -r ./$ac_unique_file) 2>/dev/null || - { echo "$as_me: error: sources are in $srcdir, but \`cd $srcdir' does not work" >&2 +ac_msg="sources are in $srcdir, but \`cd $srcdir' does not work" +ac_abs_confdir=`( + cd "$srcdir" && test -r "./$ac_unique_file" || { echo "$as_me: error: $ac_msg" >&2 { (exit 1); exit 1; }; } -srcdir=`echo "$srcdir" | sed 's%\([^\\/]\)[\\/]*$%\1%'` -ac_env_build_alias_set=${build_alias+set} -ac_env_build_alias_value=$build_alias -ac_cv_env_build_alias_set=${build_alias+set} -ac_cv_env_build_alias_value=$build_alias -ac_env_host_alias_set=${host_alias+set} -ac_env_host_alias_value=$host_alias -ac_cv_env_host_alias_set=${host_alias+set} -ac_cv_env_host_alias_value=$host_alias -ac_env_target_alias_set=${target_alias+set} -ac_env_target_alias_value=$target_alias -ac_cv_env_target_alias_set=${target_alias+set} -ac_cv_env_target_alias_value=$target_alias -ac_env_CC_set=${CC+set} -ac_env_CC_value=$CC -ac_cv_env_CC_set=${CC+set} -ac_cv_env_CC_value=$CC -ac_env_CFLAGS_set=${CFLAGS+set} -ac_env_CFLAGS_value=$CFLAGS -ac_cv_env_CFLAGS_set=${CFLAGS+set} -ac_cv_env_CFLAGS_value=$CFLAGS -ac_env_LDFLAGS_set=${LDFLAGS+set} -ac_env_LDFLAGS_value=$LDFLAGS -ac_cv_env_LDFLAGS_set=${LDFLAGS+set} -ac_cv_env_LDFLAGS_value=$LDFLAGS -ac_env_CPPFLAGS_set=${CPPFLAGS+set} -ac_env_CPPFLAGS_value=$CPPFLAGS -ac_cv_env_CPPFLAGS_set=${CPPFLAGS+set} -ac_cv_env_CPPFLAGS_value=$CPPFLAGS -ac_env_CPP_set=${CPP+set} -ac_env_CPP_value=$CPP -ac_cv_env_CPP_set=${CPP+set} -ac_cv_env_CPP_value=$CPP + pwd)` +# When building in place, set srcdir=. +if test "$ac_abs_confdir" = "$ac_pwd"; then + srcdir=. +fi +# Remove unnecessary trailing slashes from srcdir. +# Double slashes in file names in object file debugging info +# mess up M-x gdb in Emacs. +case $srcdir in +*/) srcdir=`expr "X$srcdir" : 'X\(.*[^/]\)' \| "X$srcdir" : 'X\(.*\)'`;; +esac +for ac_var in $ac_precious_vars; do + eval ac_env_${ac_var}_set=\${${ac_var}+set} + eval ac_env_${ac_var}_value=\$${ac_var} + eval ac_cv_env_${ac_var}_set=\${${ac_var}+set} + eval ac_cv_env_${ac_var}_value=\$${ac_var} +done # # Report the --help message. @@ -779,7 +1226,7 @@ if test "$ac_init_help" = "long"; then # Omit some internal or obsolete options to make the list less imposing. # This message is too long to be a string in the A/UX 3.1 sh. cat <<_ACEOF -\`configure' configures this package to adapt to many kinds of systems. +\`configure' configures PCRE 7.2 to adapt to many kinds of systems. Usage: $0 [OPTION]... [VAR=VALUE]... @@ -799,9 +1246,6 @@ Configuration: -n, --no-create do not create output files --srcdir=DIR find the sources in DIR [configure dir or \`..'] -_ACEOF - - cat <<_ACEOF Installation directories: --prefix=PREFIX install architecture-independent files in PREFIX [$ac_default_prefix] @@ -819,19 +1263,31 @@ Fine tuning of the installation directories: --bindir=DIR user executables [EPREFIX/bin] --sbindir=DIR system admin executables [EPREFIX/sbin] --libexecdir=DIR program executables [EPREFIX/libexec] - --datadir=DIR read-only architecture-independent data [PREFIX/share] --sysconfdir=DIR read-only single-machine data [PREFIX/etc] --sharedstatedir=DIR modifiable architecture-independent data [PREFIX/com] --localstatedir=DIR modifiable single-machine data [PREFIX/var] --libdir=DIR object code libraries [EPREFIX/lib] --includedir=DIR C header files [PREFIX/include] --oldincludedir=DIR C header files for non-gcc [/usr/include] - --infodir=DIR info documentation [PREFIX/info] - --mandir=DIR man documentation [PREFIX/man] + --datarootdir=DIR read-only arch.-independent data root [PREFIX/share] + --datadir=DIR read-only architecture-independent data [DATAROOTDIR] + --infodir=DIR info documentation [DATAROOTDIR/info] + --localedir=DIR locale-dependent data [DATAROOTDIR/locale] + --mandir=DIR man documentation [DATAROOTDIR/man] + --docdir=DIR documentation root [DATAROOTDIR/doc/pcre] + --htmldir=DIR html documentation [DOCDIR] + --dvidir=DIR dvi documentation [DOCDIR] + --pdfdir=DIR pdf documentation [DOCDIR] + --psdir=DIR ps documentation [DOCDIR] _ACEOF cat <<\_ACEOF +Program names: + --program-prefix=PREFIX prepend PREFIX to installed program names + --program-suffix=SUFFIX append SUFFIX to installed program names + --program-transform-name=PROGRAM run sed PROGRAM on installed program names + System types: --build=BUILD configure for building on BUILD [guessed] --host=HOST cross-compile to build programs to run on HOST [BUILD] @@ -839,153 +1295,139 @@ _ACEOF fi if test -n "$ac_init_help"; then - + case $ac_init_help in + short | recursive ) echo "Configuration of PCRE 7.2:";; + esac cat <<\_ACEOF Optional Features: --disable-FEATURE do not include FEATURE (same as --enable-FEATURE=no) --enable-FEATURE[=ARG] include FEATURE [ARG=yes] - --enable-utf8 enable UTF8 support - --enable-unicode-properties enable Unicode properties support - --enable-newline-is-cr use CR as the newline character - --enable-newline-is-lf use LF as the newline character - --enable-newline-is-crlf use CRLF as the newline sequence - --enable-ebcdic assume EBCDIC coding rather than ASCII - --disable-stack-for-recursion disable use of stack recursion when matching + --disable-dependency-tracking speeds up one-time build + --enable-dependency-tracking do not reject slow dependency extractors + --enable-rebuild-chartables + rebuild character tables in current locale + --enable-utf8 enable UTF-8 support + --enable-unicode-properties + enable Unicode properties support (implies + --enable-utf8) + --enable-newline-is-cr use CR as newline character + --enable-newline-is-lf use LF as newline character (default) + --enable-newline-is-crlf + use CRLF as newline sequence + --enable-newline-is-anycrlf + use CR, LF, or CRLF as newline sequence + --enable-newline-is-any use any valid Unicode newline sequence + --enable-ebcdic assume EBCDIC coding rather than ASCII (implies + --enable-rebuild-chartables) + --disable-stack-for-recursion + don't use stack recursion when matching Optional Packages: --with-PACKAGE[=ARG] use PACKAGE [ARG=yes] --without-PACKAGE do not use PACKAGE (same as --with-PACKAGE=no) - --with-posix-malloc-threshold=10 threshold for POSIX malloc usage - --with-link-size=2 internal link size (2, 3, or 4 allowed) - --with-match-limit=10000000 default limit on internal looping - --with-match-limit-recursion=10000000 default limit on internal recursion + --with-posix-malloc-threshold=NBYTES + threshold for POSIX malloc usage (default=10) + --with-link-size=N internal link size (2, 3, or 4 allowed; default=2) + --with-match-limit=N default limit on internal looping (default=10000000) + --with-match-limit-recursion=N + default limit on internal recursion + (default=MATCH_LIMIT) Some influential environment variables: CC C compiler command CFLAGS C compiler flags LDFLAGS linker flags, e.g. -L if you have libraries in a nonstandard directory - CPPFLAGS C/C++ preprocessor flags, e.g. -I if you have - headers in a nonstandard directory + LIBS libraries to pass to the linker, e.g. -l + CPPFLAGS C/C++/Objective C preprocessor flags, e.g. -I if + you have headers in a nonstandard directory CPP C preprocessor Use these variables to override the choices made by `configure' or to help it to find libraries and programs with nonstandard names/locations. _ACEOF +ac_status=$? fi if test "$ac_init_help" = "recursive"; then # If there are subdirs, report their specific --help. - ac_popdir=`pwd` for ac_dir in : $ac_subdirs_all; do test "x$ac_dir" = x: && continue - test -d $ac_dir || continue + test -d "$ac_dir" || continue ac_builddir=. -if test "$ac_dir" != .; then +case "$ac_dir" in +.) ac_dir_suffix= ac_top_builddir_sub=. ac_top_build_prefix= ;; +*) ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` - # A "../" for each directory in $ac_dir_suffix. - ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` -else - ac_dir_suffix= ac_top_builddir= -fi + # A ".." for each directory in $ac_dir_suffix. + ac_top_builddir_sub=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,/..,g;s,/,,'` + case $ac_top_builddir_sub in + "") ac_top_builddir_sub=. ac_top_build_prefix= ;; + *) ac_top_build_prefix=$ac_top_builddir_sub/ ;; + esac ;; +esac +ac_abs_top_builddir=$ac_pwd +ac_abs_builddir=$ac_pwd$ac_dir_suffix +# for backward compatibility: +ac_top_builddir=$ac_top_build_prefix case $srcdir in - .) # No --srcdir option. We are building in place. + .) # We are building in place. ac_srcdir=. - if test -z "$ac_top_builddir"; then - ac_top_srcdir=. - else - ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` - fi ;; - [\\/]* | ?:[\\/]* ) # Absolute path. + ac_top_srcdir=$ac_top_builddir_sub + ac_abs_top_srcdir=$ac_pwd ;; + [\\/]* | ?:[\\/]* ) # Absolute name. ac_srcdir=$srcdir$ac_dir_suffix; - ac_top_srcdir=$srcdir ;; - *) # Relative path. - ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix - ac_top_srcdir=$ac_top_builddir$srcdir ;; + ac_top_srcdir=$srcdir + ac_abs_top_srcdir=$srcdir ;; + *) # Relative name. + ac_srcdir=$ac_top_build_prefix$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_build_prefix$srcdir + ac_abs_top_srcdir=$ac_pwd/$srcdir ;; esac +ac_abs_srcdir=$ac_abs_top_srcdir$ac_dir_suffix -# Do not use `cd foo && pwd` to compute absolute paths, because -# the directories may not exist. -case `pwd` in -.) ac_abs_builddir="$ac_dir";; -*) - case "$ac_dir" in - .) ac_abs_builddir=`pwd`;; - [\\/]* | ?:[\\/]* ) ac_abs_builddir="$ac_dir";; - *) ac_abs_builddir=`pwd`/"$ac_dir";; - esac;; -esac -case $ac_abs_builddir in -.) ac_abs_top_builddir=${ac_top_builddir}.;; -*) - case ${ac_top_builddir}. in - .) ac_abs_top_builddir=$ac_abs_builddir;; - [\\/]* | ?:[\\/]* ) ac_abs_top_builddir=${ac_top_builddir}.;; - *) ac_abs_top_builddir=$ac_abs_builddir/${ac_top_builddir}.;; - esac;; -esac -case $ac_abs_builddir in -.) ac_abs_srcdir=$ac_srcdir;; -*) - case $ac_srcdir in - .) ac_abs_srcdir=$ac_abs_builddir;; - [\\/]* | ?:[\\/]* ) ac_abs_srcdir=$ac_srcdir;; - *) ac_abs_srcdir=$ac_abs_builddir/$ac_srcdir;; - esac;; -esac -case $ac_abs_builddir in -.) ac_abs_top_srcdir=$ac_top_srcdir;; -*) - case $ac_top_srcdir in - .) ac_abs_top_srcdir=$ac_abs_builddir;; - [\\/]* | ?:[\\/]* ) ac_abs_top_srcdir=$ac_top_srcdir;; - *) ac_abs_top_srcdir=$ac_abs_builddir/$ac_top_srcdir;; - esac;; -esac - - cd $ac_dir - # Check for guested configure; otherwise get Cygnus style configure. - if test -f $ac_srcdir/configure.gnu; then - echo - $SHELL $ac_srcdir/configure.gnu --help=recursive - elif test -f $ac_srcdir/configure; then - echo - $SHELL $ac_srcdir/configure --help=recursive - elif test -f $ac_srcdir/configure.ac || - test -f $ac_srcdir/configure.in; then - echo - $ac_configure --help + cd "$ac_dir" || { ac_status=$?; continue; } + # Check for guested configure. + if test -f "$ac_srcdir/configure.gnu"; then + echo && + $SHELL "$ac_srcdir/configure.gnu" --help=recursive + elif test -f "$ac_srcdir/configure"; then + echo && + $SHELL "$ac_srcdir/configure" --help=recursive else echo "$as_me: WARNING: no configuration information is in $ac_dir" >&2 - fi - cd $ac_popdir + fi || ac_status=$? + cd "$ac_pwd" || { ac_status=$?; break; } done fi -test -n "$ac_init_help" && exit 0 +test -n "$ac_init_help" && exit $ac_status if $ac_init_version; then cat <<\_ACEOF +PCRE configure 7.2 +generated by GNU Autoconf 2.61 -Copyright (C) 2003 Free Software Foundation, Inc. +Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001, +2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. This configure script is free software; the Free Software Foundation gives unlimited permission to copy, distribute and modify it. _ACEOF - exit 0 + exit fi -exec 5>config.log -cat >&5 <<_ACEOF +cat >config.log <<_ACEOF This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. -It was created by $as_me, which was -generated by GNU Autoconf 2.59. Invocation command line was +It was created by PCRE $as_me 7.2, which was +generated by GNU Autoconf 2.61. Invocation command line was $ $0 $@ _ACEOF +exec 5>>config.log { cat <<_ASUNAME ## --------- ## @@ -1004,7 +1446,7 @@ uname -v = `(uname -v) 2>/dev/null || echo unknown` /bin/arch = `(/bin/arch) 2>/dev/null || echo unknown` /usr/bin/arch -k = `(/usr/bin/arch -k) 2>/dev/null || echo unknown` /usr/convex/getsysinfo = `(/usr/convex/getsysinfo) 2>/dev/null || echo unknown` -hostinfo = `(hostinfo) 2>/dev/null || echo unknown` +/usr/bin/hostinfo = `(/usr/bin/hostinfo) 2>/dev/null || echo unknown` /bin/machine = `(/bin/machine) 2>/dev/null || echo unknown` /usr/bin/oslevel = `(/usr/bin/oslevel) 2>/dev/null || echo unknown` /bin/universe = `(/bin/universe) 2>/dev/null || echo unknown` @@ -1018,6 +1460,7 @@ do test -z "$as_dir" && as_dir=. echo "PATH: $as_dir" done +IFS=$as_save_IFS } >&5 @@ -1039,7 +1482,6 @@ _ACEOF ac_configure_args= ac_configure_args0= ac_configure_args1= -ac_sep= ac_must_keep_next=false for ac_pass in 1 2 do @@ -1050,7 +1492,7 @@ do -q | -quiet | --quiet | --quie | --qui | --qu | --q \ | -silent | --silent | --silen | --sile | --sil) continue ;; - *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?\"\']*) + *\'*) ac_arg=`echo "$ac_arg" | sed "s/'/'\\\\\\\\''/g"` ;; esac case $ac_pass in @@ -1072,9 +1514,7 @@ do -* ) ac_must_keep_next=true ;; esac fi - ac_configure_args="$ac_configure_args$ac_sep'$ac_arg'" - # Get rid of the leading space. - ac_sep=" " + ac_configure_args="$ac_configure_args '$ac_arg'" ;; esac done @@ -1085,8 +1525,8 @@ $as_unset ac_configure_args1 || test "${ac_configure_args1+set}" != set || { ac_ # When interrupted or exit'd, cleanup temporary files, and complete # config.log. We remove comments because anyway the quotes in there # would cause problems or look ugly. -# WARNING: Be sure not to use single quotes in there, as some shells, -# such as our DU 5.0 friend, will then `close' the trap. +# WARNING: Use '\'' to represent an apostrophe within the trap. +# WARNING: Do not start the trap code with a newline, due to a FreeBSD 4.0 bug. trap 'exit_status=$? # Save into config.log some information that might help in debugging. { @@ -1099,20 +1539,34 @@ trap 'exit_status=$? _ASBOX echo # The following way of writing the cache mishandles newlines in values, -{ +( + for ac_var in `(set) 2>&1 | sed -n '\''s/^\([a-zA-Z_][a-zA-Z0-9_]*\)=.*/\1/p'\''`; do + eval ac_val=\$$ac_var + case $ac_val in #( + *${as_nl}*) + case $ac_var in #( + *_cv_*) { echo "$as_me:$LINENO: WARNING: Cache variable $ac_var contains a newline." >&5 +echo "$as_me: WARNING: Cache variable $ac_var contains a newline." >&2;} ;; + esac + case $ac_var in #( + _ | IFS | as_nl) ;; #( + *) $as_unset $ac_var ;; + esac ;; + esac + done (set) 2>&1 | - case `(ac_space='"'"' '"'"'; set | grep ac_space) 2>&1` in - *ac_space=\ *) + case $as_nl`(ac_space='\'' '\''; set) 2>&1` in #( + *${as_nl}ac_space=\ *) sed -n \ - "s/'"'"'/'"'"'\\\\'"'"''"'"'/g; - s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='"'"'\\2'"'"'/p" - ;; + "s/'\''/'\''\\\\'\'''\''/g; + s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='\''\\2'\''/p" + ;; #( *) - sed -n \ - "s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1=\\2/p" + sed -n "/^[_$as_cr_alnum]*_cv_[_$as_cr_alnum]*=/p" ;; - esac; -} + esac | + sort +) echo cat <<\_ASBOX @@ -1123,22 +1577,28 @@ _ASBOX echo for ac_var in $ac_subst_vars do - eval ac_val=$`echo $ac_var` - echo "$ac_var='"'"'$ac_val'"'"'" + eval ac_val=\$$ac_var + case $ac_val in + *\'\''*) ac_val=`echo "$ac_val" | sed "s/'\''/'\''\\\\\\\\'\'''\''/g"`;; + esac + echo "$ac_var='\''$ac_val'\''" done | sort echo if test -n "$ac_subst_files"; then cat <<\_ASBOX -## ------------- ## -## Output files. ## -## ------------- ## +## ------------------- ## +## File substitutions. ## +## ------------------- ## _ASBOX echo for ac_var in $ac_subst_files do - eval ac_val=$`echo $ac_var` - echo "$ac_var='"'"'$ac_val'"'"'" + eval ac_val=\$$ac_var + case $ac_val in + *\'\''*) ac_val=`echo "$ac_val" | sed "s/'\''/'\''\\\\\\\\'\'''\''/g"`;; + esac + echo "$ac_var='\''$ac_val'\''" done | sort echo fi @@ -1150,26 +1610,24 @@ _ASBOX ## ----------- ## _ASBOX echo - sed "/^$/d" confdefs.h | sort + cat confdefs.h echo fi test "$ac_signal" != 0 && echo "$as_me: caught signal $ac_signal" echo "$as_me: exit $exit_status" } >&5 - rm -f core *.core && - rm -rf conftest* confdefs* conf$$* $ac_clean_files && + rm -f core *.core core.conftest.* && + rm -f -r conftest* confdefs* conf$$* $ac_clean_files && exit $exit_status - ' 0 +' 0 for ac_signal in 1 2 13 15; do trap 'ac_signal='$ac_signal'; { (exit 1); exit 1; }' $ac_signal done ac_signal=0 # confdefs.h avoids OS command line length limits that DEFS can exceed. -rm -rf conftest* confdefs.h -# AIX cpp loses on an empty file, so make sure it contains at least a newline. -echo >confdefs.h +rm -f -r conftest* confdefs.h # Predefined preprocessor variables. @@ -1200,14 +1658,17 @@ _ACEOF # Let the site file select an alternate cache file if it wants to. # Prefer explicitly selected file to automatically selected ones. -if test -z "$CONFIG_SITE"; then - if test "x$prefix" != xNONE; then - CONFIG_SITE="$prefix/share/config.site $prefix/etc/config.site" - else - CONFIG_SITE="$ac_default_prefix/share/config.site $ac_default_prefix/etc/config.site" - fi +if test -n "$CONFIG_SITE"; then + set x "$CONFIG_SITE" +elif test "x$prefix" != xNONE; then + set x "$prefix/share/config.site" "$prefix/etc/config.site" +else + set x "$ac_default_prefix/share/config.site" \ + "$ac_default_prefix/etc/config.site" fi -for ac_site_file in $CONFIG_SITE; do +shift +for ac_site_file +do if test -r "$ac_site_file"; then { echo "$as_me:$LINENO: loading site script $ac_site_file" >&5 echo "$as_me: loading site script $ac_site_file" >&6;} @@ -1223,8 +1684,8 @@ if test -r "$cache_file"; then { echo "$as_me:$LINENO: loading cache $cache_file" >&5 echo "$as_me: loading cache $cache_file" >&6;} case $cache_file in - [\\/]* | ?:[\\/]* ) . $cache_file;; - *) . ./$cache_file;; + [\\/]* | ?:[\\/]* ) . "$cache_file";; + *) . "./$cache_file";; esac fi else @@ -1236,12 +1697,11 @@ fi # Check that the precious variables saved in the cache have kept the same # value. ac_cache_corrupted=false -for ac_var in `(set) 2>&1 | - sed -n 's/^ac_env_\([a-zA-Z_0-9]*\)_set=.*/\1/p'`; do +for ac_var in $ac_precious_vars; do eval ac_old_set=\$ac_cv_env_${ac_var}_set eval ac_new_set=\$ac_env_${ac_var}_set - eval ac_old_val="\$ac_cv_env_${ac_var}_value" - eval ac_new_val="\$ac_env_${ac_var}_value" + eval ac_old_val=\$ac_cv_env_${ac_var}_value + eval ac_new_val=\$ac_env_${ac_var}_value case $ac_old_set,$ac_new_set in set,) { echo "$as_me:$LINENO: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&5 @@ -1266,8 +1726,7 @@ echo "$as_me: current value: $ac_new_val" >&2;} # Pass precious variables to config.status. if test "$ac_new_set" = set; then case $ac_new_val in - *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?\"\']*) - ac_arg=$ac_var=`echo "$ac_new_val" | sed "s/'/'\\\\\\\\''/g"` ;; + *\'*) ac_arg=$ac_var=`echo "$ac_new_val" | sed "s/'/'\\\\\\\\''/g"` ;; *) ac_arg=$ac_var=$ac_new_val ;; esac case " $ac_configure_args " in @@ -1284,6 +1743,30 @@ echo "$as_me: error: run \`make distclean' and/or \`rm $cache_file' and start ov { (exit 1); exit 1; }; } fi + + + + + + + + + + + + + + + + + + + + + + + + ac_ext=c ac_cpp='$CPP $CPPFLAGS' ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' @@ -1292,43 +1775,503 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu +am__api_version='1.10' + +ac_aux_dir= +for ac_dir in "$srcdir" "$srcdir/.." "$srcdir/../.."; do + if test -f "$ac_dir/install-sh"; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/install-sh -c" + break + elif test -f "$ac_dir/install.sh"; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/install.sh -c" + break + elif test -f "$ac_dir/shtool"; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/shtool install -c" + break + fi +done +if test -z "$ac_aux_dir"; then + { { echo "$as_me:$LINENO: error: cannot find install-sh or install.sh in \"$srcdir\" \"$srcdir/..\" \"$srcdir/../..\"" >&5 +echo "$as_me: error: cannot find install-sh or install.sh in \"$srcdir\" \"$srcdir/..\" \"$srcdir/../..\"" >&2;} + { (exit 1); exit 1; }; } +fi + +# These three variables are undocumented and unsupported, +# and are intended to be withdrawn in a future Autoconf release. +# They can cause serious problems if a builder's source tree is in a directory +# whose full name contains unusual characters. +ac_config_guess="$SHELL $ac_aux_dir/config.guess" # Please don't use this var. +ac_config_sub="$SHELL $ac_aux_dir/config.sub" # Please don't use this var. +ac_configure="$SHELL $ac_aux_dir/configure" # Please don't use this var. + + +# Find a good install program. We prefer a C program (faster), +# so one script is as good as another. But avoid the broken or +# incompatible versions: +# SysV /etc/install, /usr/sbin/install +# SunOS /usr/etc/install +# IRIX /sbin/install +# AIX /bin/install +# AmigaOS /C/install, which installs bootblocks on floppy discs +# AIX 4 /usr/bin/installbsd, which doesn't work without a -g flag +# AFS /usr/afsws/bin/install, which mishandles nonexistent args +# SVR4 /usr/ucb/install, which tries to use the nonexistent group "staff" +# OS/2's system install, which has a completely different semantic +# ./install, which can be erroneously created by make from ./install.sh. +{ echo "$as_me:$LINENO: checking for a BSD-compatible install" >&5 +echo $ECHO_N "checking for a BSD-compatible install... $ECHO_C" >&6; } +if test -z "$INSTALL"; then +if test "${ac_cv_path_install+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + # Account for people who put trailing slashes in PATH elements. +case $as_dir/ in + ./ | .// | /cC/* | \ + /etc/* | /usr/sbin/* | /usr/etc/* | /sbin/* | /usr/afsws/bin/* | \ + ?:\\/os2\\/install\\/* | ?:\\/OS2\\/INSTALL\\/* | \ + /usr/ucb/* ) ;; + *) + # OSF1 and SCO ODT 3.0 have their own names for install. + # Don't use installbsd from OSF since it installs stuff as root + # by default. + for ac_prog in ginstall scoinst install; do + for ac_exec_ext in '' $ac_executable_extensions; do + if { test -f "$as_dir/$ac_prog$ac_exec_ext" && $as_test_x "$as_dir/$ac_prog$ac_exec_ext"; }; then + if test $ac_prog = install && + grep dspmsg "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # AIX install. It has an incompatible calling convention. + : + elif test $ac_prog = install && + grep pwplus "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # program-specific install script used by HP pwplus--don't use. + : + else + ac_cv_path_install="$as_dir/$ac_prog$ac_exec_ext -c" + break 3 + fi + fi + done + done + ;; +esac +done +IFS=$as_save_IFS + + +fi + if test "${ac_cv_path_install+set}" = set; then + INSTALL=$ac_cv_path_install + else + # As a last resort, use the slow shell script. Don't cache a + # value for INSTALL within a source directory, because that will + # break other packages using the cache if that directory is + # removed, or if the value is a relative name. + INSTALL=$ac_install_sh + fi +fi +{ echo "$as_me:$LINENO: result: $INSTALL" >&5 +echo "${ECHO_T}$INSTALL" >&6; } + +# Use test -z because SunOS4 sh mishandles braces in ${var-val}. +# It thinks the first close brace ends the variable substitution. +test -z "$INSTALL_PROGRAM" && INSTALL_PROGRAM='${INSTALL}' + +test -z "$INSTALL_SCRIPT" && INSTALL_SCRIPT='${INSTALL}' + +test -z "$INSTALL_DATA" && INSTALL_DATA='${INSTALL} -m 644' + +{ echo "$as_me:$LINENO: checking whether build environment is sane" >&5 +echo $ECHO_N "checking whether build environment is sane... $ECHO_C" >&6; } +# Just in case +sleep 1 +echo timestamp > conftest.file +# Do `set' in a subshell so we don't clobber the current shell's +# arguments. Must try -L first in case configure is actually a +# symlink; some systems play weird games with the mod time of symlinks +# (eg FreeBSD returns the mod time of the symlink's containing +# directory). +if ( + set X `ls -Lt $srcdir/configure conftest.file 2> /dev/null` + if test "$*" = "X"; then + # -L didn't work. + set X `ls -t $srcdir/configure conftest.file` + fi + rm -f conftest.file + if test "$*" != "X $srcdir/configure conftest.file" \ + && test "$*" != "X conftest.file $srcdir/configure"; then + + # If neither matched, then we have a broken ls. This can happen + # if, for instance, CONFIG_SHELL is bash and it inherits a + # broken ls alias from the environment. This has actually + # happened. Such a system could not be considered "sane". + { { echo "$as_me:$LINENO: error: ls -t appears to fail. Make sure there is not a broken +alias in your environment" >&5 +echo "$as_me: error: ls -t appears to fail. Make sure there is not a broken +alias in your environment" >&2;} + { (exit 1); exit 1; }; } + fi + + test "$2" = conftest.file + ) +then + # Ok. + : +else + { { echo "$as_me:$LINENO: error: newly created file is older than distributed files! +Check your system clock" >&5 +echo "$as_me: error: newly created file is older than distributed files! +Check your system clock" >&2;} + { (exit 1); exit 1; }; } +fi +{ echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6; } +test "$program_prefix" != NONE && + program_transform_name="s&^&$program_prefix&;$program_transform_name" +# Use a double $ so make ignores it. +test "$program_suffix" != NONE && + program_transform_name="s&\$&$program_suffix&;$program_transform_name" +# Double any \ or $. echo might interpret backslashes. +# By default was `s,x,x', remove it if useless. +cat <<\_ACEOF >conftest.sed +s/[\\$]/&&/g;s/;s,x,x,$// +_ACEOF +program_transform_name=`echo $program_transform_name | sed -f conftest.sed` +rm -f conftest.sed + +# expand $ac_aux_dir to an absolute path +am_aux_dir=`cd $ac_aux_dir && pwd` + +test x"${MISSING+set}" = xset || MISSING="\${SHELL} $am_aux_dir/missing" +# Use eval to expand $SHELL +if eval "$MISSING --run true"; then + am_missing_run="$MISSING --run " +else + am_missing_run= + { echo "$as_me:$LINENO: WARNING: \`missing' script is too old or missing" >&5 +echo "$as_me: WARNING: \`missing' script is too old or missing" >&2;} +fi + +{ echo "$as_me:$LINENO: checking for a thread-safe mkdir -p" >&5 +echo $ECHO_N "checking for a thread-safe mkdir -p... $ECHO_C" >&6; } +if test -z "$MKDIR_P"; then + if test "${ac_cv_path_mkdir+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/opt/sfw/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in mkdir gmkdir; do + for ac_exec_ext in '' $ac_executable_extensions; do + { test -f "$as_dir/$ac_prog$ac_exec_ext" && $as_test_x "$as_dir/$ac_prog$ac_exec_ext"; } || continue + case `"$as_dir/$ac_prog$ac_exec_ext" --version 2>&1` in #( + 'mkdir (GNU coreutils) '* | \ + 'mkdir (coreutils) '* | \ + 'mkdir (fileutils) '4.1*) + ac_cv_path_mkdir=$as_dir/$ac_prog$ac_exec_ext + break 3;; + esac + done + done +done +IFS=$as_save_IFS + +fi + + if test "${ac_cv_path_mkdir+set}" = set; then + MKDIR_P="$ac_cv_path_mkdir -p" + else + # As a last resort, use the slow shell script. Don't cache a + # value for MKDIR_P within a source directory, because that will + # break other packages using the cache if that directory is + # removed, or if the value is a relative name. + test -d ./--version && rmdir ./--version + MKDIR_P="$ac_install_sh -d" + fi +fi +{ echo "$as_me:$LINENO: result: $MKDIR_P" >&5 +echo "${ECHO_T}$MKDIR_P" >&6; } + +mkdir_p="$MKDIR_P" +case $mkdir_p in + [\\/$]* | ?:[\\/]*) ;; + */*) mkdir_p="\$(top_builddir)/$mkdir_p" ;; +esac + +for ac_prog in gawk mawk nawk awk +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } +if test "${ac_cv_prog_AWK+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$AWK"; then + ac_cv_prog_AWK="$AWK" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then + ac_cv_prog_AWK="$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done +IFS=$as_save_IFS + +fi +fi +AWK=$ac_cv_prog_AWK +if test -n "$AWK"; then + { echo "$as_me:$LINENO: result: $AWK" >&5 +echo "${ECHO_T}$AWK" >&6; } +else + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } +fi + + + test -n "$AWK" && break +done + +{ echo "$as_me:$LINENO: checking whether ${MAKE-make} sets \$(MAKE)" >&5 +echo $ECHO_N "checking whether ${MAKE-make} sets \$(MAKE)... $ECHO_C" >&6; } +set x ${MAKE-make}; ac_make=`echo "$2" | sed 's/+/p/g; s/[^a-zA-Z0-9_]/_/g'` +if { as_var=ac_cv_prog_make_${ac_make}_set; eval "test \"\${$as_var+set}\" = set"; }; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.make <<\_ACEOF +SHELL = /bin/sh +all: + @echo '@@@%%%=$(MAKE)=@@@%%%' +_ACEOF +# GNU make sometimes prints "make[1]: Entering...", which would confuse us. +case `${MAKE-make} -f conftest.make 2>/dev/null` in + *@@@%%%=?*=@@@%%%*) + eval ac_cv_prog_make_${ac_make}_set=yes;; + *) + eval ac_cv_prog_make_${ac_make}_set=no;; +esac +rm -f conftest.make +fi +if eval test \$ac_cv_prog_make_${ac_make}_set = yes; then + { echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6; } + SET_MAKE= +else + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } + SET_MAKE="MAKE=${MAKE-make}" +fi + +rm -rf .tst 2>/dev/null +mkdir .tst 2>/dev/null +if test -d .tst; then + am__leading_dot=. +else + am__leading_dot=_ +fi +rmdir .tst 2>/dev/null + +if test "`cd $srcdir && pwd`" != "`pwd`"; then + # Use -I$(srcdir) only when $(srcdir) != ., so that make's output + # is not polluted with repeated "-I." + am__isrc=' -I$(srcdir)' + # test to see if srcdir already configured + if test -f $srcdir/config.status; then + { { echo "$as_me:$LINENO: error: source directory already configured; run \"make distclean\" there first" >&5 +echo "$as_me: error: source directory already configured; run \"make distclean\" there first" >&2;} + { (exit 1); exit 1; }; } + fi +fi + +# test whether we have cygpath +if test -z "$CYGPATH_W"; then + if (cygpath --version) >/dev/null 2>/dev/null; then + CYGPATH_W='cygpath -w' + else + CYGPATH_W=echo + fi +fi + + +# Define the identity of the package. + PACKAGE='pcre' + VERSION='7.2' + + +cat >>confdefs.h <<_ACEOF +#define PACKAGE "$PACKAGE" +_ACEOF + + +cat >>confdefs.h <<_ACEOF +#define VERSION "$VERSION" +_ACEOF + +# Some tools Automake needs. + +ACLOCAL=${ACLOCAL-"${am_missing_run}aclocal-${am__api_version}"} + + +AUTOCONF=${AUTOCONF-"${am_missing_run}autoconf"} + + +AUTOMAKE=${AUTOMAKE-"${am_missing_run}automake-${am__api_version}"} + + +AUTOHEADER=${AUTOHEADER-"${am_missing_run}autoheader"} + + +MAKEINFO=${MAKEINFO-"${am_missing_run}makeinfo"} + +install_sh=${install_sh-"\$(SHELL) $am_aux_dir/install-sh"} + +# Installed binaries are usually stripped using `strip' when the user +# run `make install-strip'. However `strip' might not be the right +# tool to use in cross-compilation environments, therefore Automake +# will honor the `STRIP' environment variable to overrule this program. +if test "$cross_compiling" != no; then + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}strip", so it can be a program name with args. +set dummy ${ac_tool_prefix}strip; ac_word=$2 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } +if test "${ac_cv_prog_STRIP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$STRIP"; then + ac_cv_prog_STRIP="$STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then + ac_cv_prog_STRIP="${ac_tool_prefix}strip" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done +IFS=$as_save_IFS + +fi +fi +STRIP=$ac_cv_prog_STRIP +if test -n "$STRIP"; then + { echo "$as_me:$LINENO: result: $STRIP" >&5 +echo "${ECHO_T}$STRIP" >&6; } +else + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_STRIP"; then + ac_ct_STRIP=$STRIP + # Extract the first word of "strip", so it can be a program name with args. +set dummy strip; ac_word=$2 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } +if test "${ac_cv_prog_ac_ct_STRIP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_STRIP"; then + ac_cv_prog_ac_ct_STRIP="$ac_ct_STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then + ac_cv_prog_ac_ct_STRIP="strip" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done +IFS=$as_save_IFS + +fi +fi +ac_ct_STRIP=$ac_cv_prog_ac_ct_STRIP +if test -n "$ac_ct_STRIP"; then + { echo "$as_me:$LINENO: result: $ac_ct_STRIP" >&5 +echo "${ECHO_T}$ac_ct_STRIP" >&6; } +else + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } +fi + + if test "x$ac_ct_STRIP" = x; then + STRIP=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ echo "$as_me:$LINENO: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&5 +echo "$as_me: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&2;} +ac_tool_warned=yes ;; +esac + STRIP=$ac_ct_STRIP + fi +else + STRIP="$ac_cv_prog_STRIP" +fi + +fi +INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s" + +# We need awk for the "check" target. The system "awk" is bad on +# some platforms. +# Always define AMTAR for backward compatibility. + +AMTAR=${AMTAR-"${am_missing_run}tar"} + +am__tar='${AMTAR} chof - "$$tardir"'; am__untar='${AMTAR} xf -' +ac_config_headers="$ac_config_headers config.h" +# The default CFLAGS and CXXFLAGS in Autoconf are "-g -O2" for gcc and just +# "-g" for any other compiler. There doesn't seem to be a standard way of +# getting rid of the -g (which I don't think is needed for a production +# library). This fudge seems to achieve the necessary. First, we remember the +# externally set values of CFLAGS and CXXFLAGS. Then call the AC_PROG_CC and +# AC_PROG_CXX macros to find the compilers - if CFLAGS and CXXFLAGS are not +# set, they will be set to Autoconf's defaults. Afterwards, if the original +# values were not set, remove the -g from the Autoconf defaults. +# (PH 02-May-07) - - - - - - - - - - - - - - ac_config_headers="$ac_config_headers config.h" - - - -POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 - - -PCRE_LIB_VERSION=0:1:0 -PCRE_POSIXLIB_VERSION=0:0:0 - - -PCRE_MAJOR=`grep '#define PCRE_MAJOR' ${srcdir}/pcre.h | cut -c 29-` -PCRE_MINOR=`grep '#define PCRE_MINOR' ${srcdir}/pcre.h | cut -c 29-` -PCRE_PRERELEASE=`grep '#define PCRE_PRERELEASE' ${srcdir}/pcre.h | cut -c 29-` -PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR}${PCRE_PRERELEASE} - +remember_set_CFLAGS="$CFLAGS" ac_ext=c ac_cpp='$CPP $CPPFLAGS' @@ -1338,8 +2281,8 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu if test -n "$ac_tool_prefix"; then # Extract the first word of "${ac_tool_prefix}gcc", so it can be a program name with args. set dummy ${ac_tool_prefix}gcc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_CC+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1352,32 +2295,34 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_CC="${ac_tool_prefix}gcc" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS fi fi CC=$ac_cv_prog_CC if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 + { echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi + fi if test -z "$ac_cv_prog_CC"; then ac_ct_CC=$CC # Extract the first word of "gcc", so it can be a program name with args. set dummy gcc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_ac_ct_CC+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1390,36 +2335,51 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_ac_ct_CC="gcc" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS fi fi ac_ct_CC=$ac_cv_prog_ac_ct_CC if test -n "$ac_ct_CC"; then - echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 -echo "${ECHO_T}$ac_ct_CC" >&6 + { echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 +echo "${ECHO_T}$ac_ct_CC" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi - CC=$ac_ct_CC + if test "x$ac_ct_CC" = x; then + CC="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ echo "$as_me:$LINENO: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&5 +echo "$as_me: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&2;} +ac_tool_warned=yes ;; +esac + CC=$ac_ct_CC + fi else CC="$ac_cv_prog_CC" fi if test -z "$CC"; then - if test -n "$ac_tool_prefix"; then - # Extract the first word of "${ac_tool_prefix}cc", so it can be a program name with args. + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}cc", so it can be a program name with args. set dummy ${ac_tool_prefix}cc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_CC+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1432,74 +2392,34 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_CC="${ac_tool_prefix}cc" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS fi fi CC=$ac_cv_prog_CC if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 + { echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi -fi -if test -z "$ac_cv_prog_CC"; then - ac_ct_CC=$CC - # Extract the first word of "cc", so it can be a program name with args. -set dummy cc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_ac_ct_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$ac_ct_CC"; then - ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_ac_ct_CC="cc" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 + fi -done -done - -fi -fi -ac_ct_CC=$ac_cv_prog_ac_ct_CC -if test -n "$ac_ct_CC"; then - echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 -echo "${ECHO_T}$ac_ct_CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - CC=$ac_ct_CC -else - CC="$ac_cv_prog_CC" -fi - fi if test -z "$CC"; then # Extract the first word of "cc", so it can be a program name with args. set dummy cc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_CC+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1513,7 +2433,7 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then if test "$as_dir/$ac_word$ac_exec_ext" = "/usr/ucb/cc"; then ac_prog_rejected=yes continue @@ -1524,6 +2444,7 @@ do fi done done +IFS=$as_save_IFS if test $ac_prog_rejected = yes; then # We found a bogon in the path, so make sure we never use it. @@ -1541,22 +2462,23 @@ fi fi CC=$ac_cv_prog_CC if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 + { echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi + fi if test -z "$CC"; then if test -n "$ac_tool_prefix"; then - for ac_prog in cl + for ac_prog in cl.exe do # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. set dummy $ac_tool_prefix$ac_prog; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_CC+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1569,36 +2491,38 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_CC="$ac_tool_prefix$ac_prog" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS fi fi CC=$ac_cv_prog_CC if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 + { echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi + test -n "$CC" && break done fi if test -z "$CC"; then ac_ct_CC=$CC - for ac_prog in cl + for ac_prog in cl.exe do # Extract the first word of "$ac_prog", so it can be a program name with args. set dummy $ac_prog; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_ac_ct_CC+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1611,29 +2535,45 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_ac_ct_CC="$ac_prog" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS fi fi ac_ct_CC=$ac_cv_prog_ac_ct_CC if test -n "$ac_ct_CC"; then - echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 -echo "${ECHO_T}$ac_ct_CC" >&6 + { echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 +echo "${ECHO_T}$ac_ct_CC" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi + test -n "$ac_ct_CC" && break done - CC=$ac_ct_CC + if test "x$ac_ct_CC" = x; then + CC="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ echo "$as_me:$LINENO: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&5 +echo "$as_me: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&2;} +ac_tool_warned=yes ;; +esac + CC=$ac_ct_CC + fi fi fi @@ -1646,21 +2586,35 @@ See \`config.log' for more details." >&2;} { (exit 1); exit 1; }; } # Provide some information about the compiler. -echo "$as_me:$LINENO:" \ - "checking for C compiler version" >&5 +echo "$as_me:$LINENO: checking for C compiler version" >&5 ac_compiler=`set X $ac_compile; echo $2` -{ (eval echo "$as_me:$LINENO: \"$ac_compiler --version &5\"") >&5 - (eval $ac_compiler --version &5) 2>&5 +{ (ac_try="$ac_compiler --version >&5" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compiler --version >&5") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); } -{ (eval echo "$as_me:$LINENO: \"$ac_compiler -v &5\"") >&5 - (eval $ac_compiler -v &5) 2>&5 +{ (ac_try="$ac_compiler -v >&5" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compiler -v >&5") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); } -{ (eval echo "$as_me:$LINENO: \"$ac_compiler -V &5\"") >&5 - (eval $ac_compiler -V &5) 2>&5 +{ (ac_try="$ac_compiler -V >&5" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compiler -V >&5") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); } @@ -1685,47 +2639,77 @@ ac_clean_files="$ac_clean_files a.out a.exe b.out" # Try to create an executable without -o first, disregard a.out. # It will help us diagnose broken compilers, and finding out an intuition # of exeext. -echo "$as_me:$LINENO: checking for C compiler default output file name" >&5 -echo $ECHO_N "checking for C compiler default output file name... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for C compiler default output file name" >&5 +echo $ECHO_N "checking for C compiler default output file name... $ECHO_C" >&6; } ac_link_default=`echo "$ac_link" | sed 's/ -o *conftest[^ ]*//'` -if { (eval echo "$as_me:$LINENO: \"$ac_link_default\"") >&5 - (eval $ac_link_default) 2>&5 +# +# List of possible output files, starting from the most likely. +# The algorithm is not robust to junk in `.', hence go to wildcards (a.*) +# only as a last resort. b.out is created by i960 compilers. +ac_files='a_out.exe a.exe conftest.exe a.out conftest a.* conftest.* b.out' +# +# The IRIX 6 linker writes into existing files which may not be +# executable, retaining their permissions. Remove them first so a +# subsequent execution test works. +ac_rmfiles= +for ac_file in $ac_files +do + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.o | *.obj ) ;; + * ) ac_rmfiles="$ac_rmfiles $ac_file";; + esac +done +rm -f $ac_rmfiles + +if { (ac_try="$ac_link_default" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_link_default") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); }; then - # Find the output, starting from the most likely. This scheme is -# not robust to junk in `.', hence go to wildcards (a.*) only as a last -# resort. - -# Be careful to initialize this variable, since it used to be cached. -# Otherwise an old cache value of `no' led to `EXEEXT = no' in a Makefile. -ac_cv_exeext= -# b.out is created by i960 compilers. -for ac_file in a_out.exe a.exe conftest.exe a.out conftest a.* conftest.* b.out + # Autoconf-2.13 could set the ac_cv_exeext variable to `no'. +# So ignore a value of `no', otherwise this would lead to `EXEEXT = no' +# in a Makefile. We should not override ac_cv_exeext if it was cached, +# so that the user can short-circuit this test for compilers unknown to +# Autoconf. +for ac_file in $ac_files '' do test -f "$ac_file" || continue case $ac_file in - *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.o | *.obj ) - ;; - conftest.$ac_ext ) - # This is the source file. + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.o | *.obj ) ;; [ab].out ) # We found the default executable, but exeext='' is most # certainly right. break;; *.* ) - ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` - # FIXME: I believe we export ac_cv_exeext for Libtool, - # but it would be cool to find out if it's true. Does anybody - # maintain Libtool? --akim. - export ac_cv_exeext + if test "${ac_cv_exeext+set}" = set && test "$ac_cv_exeext" != no; + then :; else + ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` + fi + # We set ac_cv_exeext here because the later test for it is not + # safe: cross compilers may not add the suffix if given an `-o' + # argument, so we may need to know it at that point already. + # Even if this section looks crufty: it has the advantage of + # actually working. break;; * ) break;; esac done +test "$ac_cv_exeext" = no && ac_cv_exeext= + else + ac_file='' +fi + +{ echo "$as_me:$LINENO: result: $ac_file" >&5 +echo "${ECHO_T}$ac_file" >&6; } +if test -z "$ac_file"; then echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 @@ -1737,19 +2721,21 @@ See \`config.log' for more details." >&2;} fi ac_exeext=$ac_cv_exeext -echo "$as_me:$LINENO: result: $ac_file" >&5 -echo "${ECHO_T}$ac_file" >&6 -# Check the compiler produces executables we can run. If not, either +# Check that the compiler produces executables we can run. If not, either # the compiler is broken, or we cross compile. -echo "$as_me:$LINENO: checking whether the C compiler works" >&5 -echo $ECHO_N "checking whether the C compiler works... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking whether the C compiler works" >&5 +echo $ECHO_N "checking whether the C compiler works... $ECHO_C" >&6; } # FIXME: These cross compiler hacks should be removed for Autoconf 3.0 # If not cross compiling, check that we can run a simple program. if test "$cross_compiling" != yes; then if { ac_try='./$ac_file' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 + { (case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_try") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); }; }; then @@ -1768,22 +2754,27 @@ See \`config.log' for more details." >&2;} fi fi fi -echo "$as_me:$LINENO: result: yes" >&5 -echo "${ECHO_T}yes" >&6 +{ echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6; } rm -f a.out a.exe conftest$ac_cv_exeext b.out ac_clean_files=$ac_clean_files_save -# Check the compiler produces executables we can run. If not, either +# Check that the compiler produces executables we can run. If not, either # the compiler is broken, or we cross compile. -echo "$as_me:$LINENO: checking whether we are cross compiling" >&5 -echo $ECHO_N "checking whether we are cross compiling... $ECHO_C" >&6 -echo "$as_me:$LINENO: result: $cross_compiling" >&5 -echo "${ECHO_T}$cross_compiling" >&6 +{ echo "$as_me:$LINENO: checking whether we are cross compiling" >&5 +echo $ECHO_N "checking whether we are cross compiling... $ECHO_C" >&6; } +{ echo "$as_me:$LINENO: result: $cross_compiling" >&5 +echo "${ECHO_T}$cross_compiling" >&6; } -echo "$as_me:$LINENO: checking for suffix of executables" >&5 -echo $ECHO_N "checking for suffix of executables... $ECHO_C" >&6 -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 +{ echo "$as_me:$LINENO: checking for suffix of executables" >&5 +echo $ECHO_N "checking for suffix of executables... $ECHO_C" >&6; } +if { (ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_link") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); }; then @@ -1794,9 +2785,8 @@ if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 for ac_file in conftest.exe conftest conftest.*; do test -f "$ac_file" || continue case $ac_file in - *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.o | *.obj ) ;; + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.o | *.obj ) ;; *.* ) ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` - export ac_cv_exeext break;; * ) break;; esac @@ -1810,14 +2800,14 @@ See \`config.log' for more details." >&2;} fi rm -f conftest$ac_cv_exeext -echo "$as_me:$LINENO: result: $ac_cv_exeext" >&5 -echo "${ECHO_T}$ac_cv_exeext" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_exeext" >&5 +echo "${ECHO_T}$ac_cv_exeext" >&6; } rm -f conftest.$ac_ext EXEEXT=$ac_cv_exeext ac_exeext=$EXEEXT -echo "$as_me:$LINENO: checking for suffix of object files" >&5 -echo $ECHO_N "checking for suffix of object files... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for suffix of object files" >&5 +echo $ECHO_N "checking for suffix of object files... $ECHO_C" >&6; } if test "${ac_cv_objext+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1837,14 +2827,20 @@ main () } _ACEOF rm -f conftest.o conftest.obj -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); }; then - for ac_file in `(ls conftest.o conftest.obj; ls conftest.*) 2>/dev/null`; do + for ac_file in conftest.o conftest.obj conftest.*; do + test -f "$ac_file" || continue; case $ac_file in - *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg ) ;; + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf ) ;; *) ac_cv_objext=`expr "$ac_file" : '.*\.\(.*\)'` break;; esac @@ -1862,12 +2858,12 @@ fi rm -f conftest.$ac_cv_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: $ac_cv_objext" >&5 -echo "${ECHO_T}$ac_cv_objext" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_objext" >&5 +echo "${ECHO_T}$ac_cv_objext" >&6; } OBJEXT=$ac_cv_objext ac_objext=$OBJEXT -echo "$as_me:$LINENO: checking whether we are using the GNU C compiler" >&5 -echo $ECHO_N "checking whether we are using the GNU C compiler... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking whether we are using the GNU C compiler" >&5 +echo $ECHO_N "checking whether we are using the GNU C compiler... $ECHO_C" >&6; } if test "${ac_cv_c_compiler_gnu+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -1890,50 +2886,49 @@ main () } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_compiler_gnu=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_compiler_gnu=no + ac_compiler_gnu=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext ac_cv_c_compiler_gnu=$ac_compiler_gnu fi -echo "$as_me:$LINENO: result: $ac_cv_c_compiler_gnu" >&5 -echo "${ECHO_T}$ac_cv_c_compiler_gnu" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_c_compiler_gnu" >&5 +echo "${ECHO_T}$ac_cv_c_compiler_gnu" >&6; } GCC=`test $ac_compiler_gnu = yes && echo yes` ac_test_CFLAGS=${CFLAGS+set} ac_save_CFLAGS=$CFLAGS -CFLAGS="-g" -echo "$as_me:$LINENO: checking whether $CC accepts -g" >&5 -echo $ECHO_N "checking whether $CC accepts -g... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking whether $CC accepts -g" >&5 +echo $ECHO_N "checking whether $CC accepts -g... $ECHO_C" >&6; } if test "${ac_cv_prog_cc_g+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else - cat >conftest.$ac_ext <<_ACEOF + ac_save_c_werror_flag=$ac_c_werror_flag + ac_c_werror_flag=yes + ac_cv_prog_cc_g=no + CFLAGS="-g" + cat >conftest.$ac_ext <<_ACEOF /* confdefs.h. */ _ACEOF cat confdefs.h >>conftest.$ac_ext @@ -1949,38 +2944,118 @@ main () } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_cv_prog_cc_g=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_cv_prog_cc_g=no + CFLAGS="" + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_c_werror_flag=$ac_save_c_werror_flag + CFLAGS="-g" + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then + ac_cv_prog_cc_g=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: $ac_cv_prog_cc_g" >&5 -echo "${ECHO_T}$ac_cv_prog_cc_g" >&6 + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + ac_c_werror_flag=$ac_save_c_werror_flag +fi +{ echo "$as_me:$LINENO: result: $ac_cv_prog_cc_g" >&5 +echo "${ECHO_T}$ac_cv_prog_cc_g" >&6; } if test "$ac_test_CFLAGS" = set; then CFLAGS=$ac_save_CFLAGS elif test $ac_cv_prog_cc_g = yes; then @@ -1996,12 +3071,12 @@ else CFLAGS= fi fi -echo "$as_me:$LINENO: checking for $CC option to accept ANSI C" >&5 -echo $ECHO_N "checking for $CC option to accept ANSI C... $ECHO_C" >&6 -if test "${ac_cv_prog_cc_stdc+set}" = set; then +{ echo "$as_me:$LINENO: checking for $CC option to accept ISO C89" >&5 +echo $ECHO_N "checking for $CC option to accept ISO C89... $ECHO_C" >&6; } +if test "${ac_cv_prog_cc_c89+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else - ac_cv_prog_cc_stdc=no + ac_cv_prog_cc_c89=no ac_save_CC=$CC cat >conftest.$ac_ext <<_ACEOF /* confdefs.h. */ @@ -2035,12 +3110,17 @@ static char *f (char * (*g) (char **, int), char **p, ...) /* OSF 4.0 Compaq cc is some sort of almost-ANSI by default. It has function prototypes and stuff, but not '\xHH' hex character constants. These don't provoke an error unfortunately, instead are silently treated - as 'x'. The following induces an error, until -std1 is added to get + as 'x'. The following induces an error, until -std is added to get proper ANSI mode. Curiously '\x00'!='x' always comes out true, for an array size at least. It's necessary to write '\x00'==0 to get something - that's true only with -std1. */ + that's true only with -std. */ int osf4_cc_array ['\x00' == 0 ? 1 : -1]; +/* IBM C 6 for AIX is almost-ANSI by default, but it replaces macro parameters + inside strings and character constants. */ +#define FOO(x) 'x' +int xlc6_cc_array[FOO(a) == 'x' ? 1 : -1]; + int test (int i, double x); struct s1 {int (*f) (int a);}; struct s2 {int (*f) (double a);}; @@ -2055,217 +3135,238 @@ return f (e, argv, 0) != argv[0] || f (e, argv, 1) != argv[1]; return 0; } _ACEOF -# Don't try gcc -ansi; that turns off useful extensions and -# breaks some systems' header files. -# AIX -qlanglvl=ansi -# Ultrix and OSF/1 -std1 -# HP-UX 10.20 and later -Ae -# HP-UX older versions -Aa -D_HPUX_SOURCE -# SVR4 -Xc -D__EXTENSIONS__ -for ac_arg in "" -qlanglvl=ansi -std1 -Ae "-Aa -D_HPUX_SOURCE" "-Xc -D__EXTENSIONS__" +for ac_arg in '' -qlanglvl=extc89 -qlanglvl=ansi -std \ + -Ae "-Aa -D_HPUX_SOURCE" "-Xc -D__EXTENSIONS__" do CC="$ac_save_CC $ac_arg" rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_prog_cc_stdc=$ac_arg -break + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then + ac_cv_prog_cc_c89=$ac_arg else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 + fi -rm -f conftest.err conftest.$ac_objext + +rm -f core conftest.err conftest.$ac_objext + test "x$ac_cv_prog_cc_c89" != "xno" && break done -rm -f conftest.$ac_ext conftest.$ac_objext +rm -f conftest.$ac_ext CC=$ac_save_CC fi - -case "x$ac_cv_prog_cc_stdc" in - x|xno) - echo "$as_me:$LINENO: result: none needed" >&5 -echo "${ECHO_T}none needed" >&6 ;; +# AC_CACHE_VAL +case "x$ac_cv_prog_cc_c89" in + x) + { echo "$as_me:$LINENO: result: none needed" >&5 +echo "${ECHO_T}none needed" >&6; } ;; + xno) + { echo "$as_me:$LINENO: result: unsupported" >&5 +echo "${ECHO_T}unsupported" >&6; } ;; *) - echo "$as_me:$LINENO: result: $ac_cv_prog_cc_stdc" >&5 -echo "${ECHO_T}$ac_cv_prog_cc_stdc" >&6 - CC="$CC $ac_cv_prog_cc_stdc" ;; + CC="$CC $ac_cv_prog_cc_c89" + { echo "$as_me:$LINENO: result: $ac_cv_prog_cc_c89" >&5 +echo "${ECHO_T}$ac_cv_prog_cc_c89" >&6; } ;; esac -# Some people use a C++ compiler to compile C. Since we use `exit', -# in C++ we need to declare it. In case someone uses the same compiler -# for both compiling C and C++ we need to have the C++ compiler decide -# the declaration of exit, since it's the most demanding environment. -cat >conftest.$ac_ext <<_ACEOF -#ifndef __cplusplus - choke me -#endif -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - for ac_declaration in \ - '' \ - 'extern "C" void std::exit (int) throw (); using std::exit;' \ - 'extern "C" void std::exit (int); using std::exit;' \ - 'extern "C" void exit (int) throw ();' \ - 'extern "C" void exit (int);' \ - 'void exit (int);' -do - cat >conftest.$ac_ext <<_ACEOF -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_declaration -#include -int -main () -{ -exit (42); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - : -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 -continue -fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext - cat >conftest.$ac_ext <<_ACEOF -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_declaration -int -main () -{ -exit (42); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - break -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext -done -rm -f conftest* -if test -n "$ac_declaration"; then - echo '#ifdef __cplusplus' >>confdefs.h - echo $ac_declaration >>confdefs.h - echo '#endif' >>confdefs.h -fi - -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext ac_ext=c ac_cpp='$CPP $CPPFLAGS' ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' ac_compiler_gnu=$ac_cv_c_compiler_gnu +DEPDIR="${am__leading_dot}deps" + +ac_config_commands="$ac_config_commands depfiles" + + +am_make=${MAKE-make} +cat > confinc << 'END' +am__doit: + @echo done +.PHONY: am__doit +END +# If we don't find an include directive, just comment out the code. +{ echo "$as_me:$LINENO: checking for style of include used by $am_make" >&5 +echo $ECHO_N "checking for style of include used by $am_make... $ECHO_C" >&6; } +am__include="#" +am__quote= +_am_result=none +# First try GNU make style include. +echo "include confinc" > confmf +# We grep out `Entering directory' and `Leaving directory' +# messages which can occur if `w' ends up in MAKEFLAGS. +# In particular we don't look at `^make:' because GNU make might +# be invoked under some other name (usually "gmake"), in which +# case it prints its new name instead of `make'. +if test "`$am_make -s -f confmf 2> /dev/null | grep -v 'ing directory'`" = "done"; then + am__include=include + am__quote= + _am_result=GNU +fi +# Now try BSD make style include. +if test "$am__include" = "#"; then + echo '.include "confinc"' > confmf + if test "`$am_make -s -f confmf 2> /dev/null`" = "done"; then + am__include=.include + am__quote="\"" + _am_result=BSD + fi +fi + + +{ echo "$as_me:$LINENO: result: $_am_result" >&5 +echo "${ECHO_T}$_am_result" >&6; } +rm -f confinc confmf + +# Check whether --enable-dependency-tracking was given. +if test "${enable_dependency_tracking+set}" = set; then + enableval=$enable_dependency_tracking; +fi + +if test "x$enable_dependency_tracking" != xno; then + am_depcomp="$ac_aux_dir/depcomp" + AMDEPBACKSLASH='\' +fi + if test "x$enable_dependency_tracking" != xno; then + AMDEP_TRUE= + AMDEP_FALSE='#' +else + AMDEP_TRUE='#' + AMDEP_FALSE= +fi + + + +depcc="$CC" am_compiler_list= + +{ echo "$as_me:$LINENO: checking dependency style of $depcc" >&5 +echo $ECHO_N "checking dependency style of $depcc... $ECHO_C" >&6; } +if test "${am_cv_CC_dependencies_compiler_type+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -z "$AMDEP_TRUE" && test -f "$am_depcomp"; then + # We make a subdir and do the tests there. Otherwise we can end up + # making bogus files that we don't know about and never remove. For + # instance it was reported that on HP-UX the gcc test will end up + # making a dummy file named `D' -- because `-MD' means `put the output + # in D'. + mkdir conftest.dir + # Copy depcomp to subdir because otherwise we won't find it if we're + # using a relative directory. + cp "$am_depcomp" conftest.dir + cd conftest.dir + # We will build objects and dependencies in a subdirectory because + # it helps to detect inapplicable dependency modes. For instance + # both Tru64's cc and ICC support -MD to output dependencies as a + # side effect of compilation, but ICC will put the dependencies in + # the current directory while Tru64 will put them in the object + # directory. + mkdir sub + + am_cv_CC_dependencies_compiler_type=none + if test "$am_compiler_list" = ""; then + am_compiler_list=`sed -n 's/^#*\([a-zA-Z0-9]*\))$/\1/p' < ./depcomp` + fi + for depmode in $am_compiler_list; do + # Setup a source with many dependencies, because some compilers + # like to wrap large dependency lists on column 80 (with \), and + # we should not choose a depcomp mode which is confused by this. + # + # We need to recreate these files for each test, as the compiler may + # overwrite some of them when testing with obscure command lines. + # This happens at least with the AIX C compiler. + : > sub/conftest.c + for i in 1 2 3 4 5 6; do + echo '#include "conftst'$i'.h"' >> sub/conftest.c + # Using `: > sub/conftst$i.h' creates only sub/conftst1.h with + # Solaris 8's {/usr,}/bin/sh. + touch sub/conftst$i.h + done + echo "${am__include} ${am__quote}sub/conftest.Po${am__quote}" > confmf + + case $depmode in + nosideeffect) + # after this tag, mechanisms are not by side-effect, so they'll + # only be used when explicitly requested + if test "x$enable_dependency_tracking" = xyes; then + continue + else + break + fi + ;; + none) break ;; + esac + # We check with `-c' and `-o' for the sake of the "dashmstdout" + # mode. It turns out that the SunPro C++ compiler does not properly + # handle `-M -o', and we need to detect this. + if depmode=$depmode \ + source=sub/conftest.c object=sub/conftest.${OBJEXT-o} \ + depfile=sub/conftest.Po tmpdepfile=sub/conftest.TPo \ + $SHELL ./depcomp $depcc -c -o sub/conftest.${OBJEXT-o} sub/conftest.c \ + >/dev/null 2>conftest.err && + grep sub/conftst1.h sub/conftest.Po > /dev/null 2>&1 && + grep sub/conftst6.h sub/conftest.Po > /dev/null 2>&1 && + grep sub/conftest.${OBJEXT-o} sub/conftest.Po > /dev/null 2>&1 && + ${MAKE-make} -s -f confmf > /dev/null 2>&1; then + # icc doesn't choke on unknown options, it will just issue warnings + # or remarks (even with -Werror). So we grep stderr for any message + # that says an option was ignored or not supported. + # When given -MP, icc 7.0 and 7.1 complain thusly: + # icc: Command line warning: ignoring option '-M'; no argument required + # The diagnosis changed in icc 8.0: + # icc: Command line remark: option '-MP' not supported + if (grep 'ignoring option' conftest.err || + grep 'not supported' conftest.err) >/dev/null 2>&1; then :; else + am_cv_CC_dependencies_compiler_type=$depmode + break + fi + fi + done + + cd .. + rm -rf conftest.dir +else + am_cv_CC_dependencies_compiler_type=none +fi + +fi +{ echo "$as_me:$LINENO: result: $am_cv_CC_dependencies_compiler_type" >&5 +echo "${ECHO_T}$am_cv_CC_dependencies_compiler_type" >&6; } +CCDEPMODE=depmode=$am_cv_CC_dependencies_compiler_type + + if + test "x$enable_dependency_tracking" != xno \ + && test "$am_cv_CC_dependencies_compiler_type" = gcc3; then + am__fastdepCC_TRUE= + am__fastdepCC_FALSE='#' +else + am__fastdepCC_TRUE='#' + am__fastdepCC_FALSE= +fi if test -n "$ac_tool_prefix"; then # Extract the first word of "${ac_tool_prefix}ranlib", so it can be a program name with args. set dummy ${ac_tool_prefix}ranlib; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_RANLIB+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -2278,32 +3379,34 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_RANLIB="${ac_tool_prefix}ranlib" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS fi fi RANLIB=$ac_cv_prog_RANLIB if test -n "$RANLIB"; then - echo "$as_me:$LINENO: result: $RANLIB" >&5 -echo "${ECHO_T}$RANLIB" >&6 + { echo "$as_me:$LINENO: result: $RANLIB" >&5 +echo "${ECHO_T}$RANLIB" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi + fi if test -z "$ac_cv_prog_RANLIB"; then ac_ct_RANLIB=$RANLIB # Extract the first word of "ranlib", so it can be a program name with args. set dummy ranlib; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6; } if test "${ac_cv_prog_ac_ct_RANLIB+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -2316,48 +3419,350 @@ do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if { test -f "$as_dir/$ac_word$ac_exec_ext" && $as_test_x "$as_dir/$ac_word$ac_exec_ext"; }; then ac_cv_prog_ac_ct_RANLIB="ranlib" echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 break 2 fi done done +IFS=$as_save_IFS - test -z "$ac_cv_prog_ac_ct_RANLIB" && ac_cv_prog_ac_ct_RANLIB=":" fi fi ac_ct_RANLIB=$ac_cv_prog_ac_ct_RANLIB if test -n "$ac_ct_RANLIB"; then - echo "$as_me:$LINENO: result: $ac_ct_RANLIB" >&5 -echo "${ECHO_T}$ac_ct_RANLIB" >&6 + { echo "$as_me:$LINENO: result: $ac_ct_RANLIB" >&5 +echo "${ECHO_T}$ac_ct_RANLIB" >&6; } else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 + { echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6; } fi - RANLIB=$ac_ct_RANLIB + if test "x$ac_ct_RANLIB" = x; then + RANLIB=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ echo "$as_me:$LINENO: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&5 +echo "$as_me: WARNING: In the future, Autoconf will not detect cross-tools +whose name does not start with the host triplet. If you think this +configuration is useful to you, please write to autoconf@gnu.org." >&2;} +ac_tool_warned=yes ;; +esac + RANLIB=$ac_ct_RANLIB + fi else RANLIB="$ac_cv_prog_RANLIB" fi +if test "x$remember_set_CFLAGS" = "x" +then + if test "$CFLAGS" = "-g -O2" + then + CFLAGS="-O2" + elif test "$CFLAGS" = "-g" + then + CFLAGS="" + fi +fi -CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} -CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} -CPPFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CPPFLAGS)'} -BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} -BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} +# Find a good install program. We prefer a C program (faster), +# so one script is as good as another. But avoid the broken or +# incompatible versions: +# SysV /etc/install, /usr/sbin/install +# SunOS /usr/etc/install +# IRIX /sbin/install +# AIX /bin/install +# AmigaOS /C/install, which installs bootblocks on floppy discs +# AIX 4 /usr/bin/installbsd, which doesn't work without a -g flag +# AFS /usr/afsws/bin/install, which mishandles nonexistent args +# SVR4 /usr/ucb/install, which tries to use the nonexistent group "staff" +# OS/2's system install, which has a completely different semantic +# ./install, which can be erroneously created by make from ./install.sh. +{ echo "$as_me:$LINENO: checking for a BSD-compatible install" >&5 +echo $ECHO_N "checking for a BSD-compatible install... $ECHO_C" >&6; } +if test -z "$INSTALL"; then +if test "${ac_cv_path_install+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + # Account for people who put trailing slashes in PATH elements. +case $as_dir/ in + ./ | .// | /cC/* | \ + /etc/* | /usr/sbin/* | /usr/etc/* | /sbin/* | /usr/afsws/bin/* | \ + ?:\\/os2\\/install\\/* | ?:\\/OS2\\/INSTALL\\/* | \ + /usr/ucb/* ) ;; + *) + # OSF1 and SCO ODT 3.0 have their own names for install. + # Don't use installbsd from OSF since it installs stuff as root + # by default. + for ac_prog in ginstall scoinst install; do + for ac_exec_ext in '' $ac_executable_extensions; do + if { test -f "$as_dir/$ac_prog$ac_exec_ext" && $as_test_x "$as_dir/$ac_prog$ac_exec_ext"; }; then + if test $ac_prog = install && + grep dspmsg "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # AIX install. It has an incompatible calling convention. + : + elif test $ac_prog = install && + grep pwplus "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # program-specific install script used by HP pwplus--don't use. + : + else + ac_cv_path_install="$as_dir/$ac_prog$ac_exec_ext -c" + break 3 + fi + fi + done + done + ;; +esac +done +IFS=$as_save_IFS +fi + if test "${ac_cv_path_install+set}" = set; then + INSTALL=$ac_cv_path_install + else + # As a last resort, use the slow shell script. Don't cache a + # value for INSTALL within a source directory, because that will + # break other packages using the cache if that directory is + # removed, or if the value is a relative name. + INSTALL=$ac_install_sh + fi +fi +{ echo "$as_me:$LINENO: result: $INSTALL" >&5 +echo "${ECHO_T}$INSTALL" >&6; } + +# Use test -z because SunOS4 sh mishandles braces in ${var-val}. +# It thinks the first close brace ends the variable substitution. +test -z "$INSTALL_PROGRAM" && INSTALL_PROGRAM='${INSTALL}' + +test -z "$INSTALL_SCRIPT" && INSTALL_SCRIPT='${INSTALL}' + +test -z "$INSTALL_DATA" && INSTALL_DATA='${INSTALL} -m 644' + +{ echo "$as_me:$LINENO: checking whether ln -s works" >&5 +echo $ECHO_N "checking whether ln -s works... $ECHO_C" >&6; } +LN_S=$as_ln_s +if test "$LN_S" = "ln -s"; then + { echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6; } +else + { echo "$as_me:$LINENO: result: no, using $LN_S" >&5 +echo "${ECHO_T}no, using $LN_S" >&6; } +fi + + +PCRE_MAJOR="7" +PCRE_MINOR="2" +PCRE_PRERELEASE="" +PCRE_DATE="2007-06-19" + + + + + + +# Set a more sensible default value for $(htmldir). +if test "x$htmldir" = 'x${docdir}' +then + htmldir='${docdir}/html' +fi + +# Handle --enable-rebuild-chartables +# Check whether --enable-rebuild-chartables was given. +if test "${enable_rebuild_chartables+set}" = set; then + enableval=$enable_rebuild_chartables; +else + enable_rebuild_chartables=no +fi + + +# Handle --enable-utf8 (disabled by default) +# Check whether --enable-utf8 was given. +if test "${enable_utf8+set}" = set; then + enableval=$enable_utf8; +else + enable_utf8=unset +fi + + +# Handle --enable-unicode-properties +# Check whether --enable-unicode-properties was given. +if test "${enable_unicode_properties+set}" = set; then + enableval=$enable_unicode_properties; +else + enable_unicode_properties=no +fi + + +# Handle --enable-newline=NL + +# Separate newline options +ac_pcre_newline=lf +# Check whether --enable-newline-is-cr was given. +if test "${enable_newline_is_cr+set}" = set; then + enableval=$enable_newline_is_cr; ac_pcre_newline=cr +fi + +# Check whether --enable-newline-is-lf was given. +if test "${enable_newline_is_lf+set}" = set; then + enableval=$enable_newline_is_lf; ac_pcre_newline=lf +fi + +# Check whether --enable-newline-is-crlf was given. +if test "${enable_newline_is_crlf+set}" = set; then + enableval=$enable_newline_is_crlf; ac_pcre_newline=crlf +fi + +# Check whether --enable-newline-is-anycrlf was given. +if test "${enable_newline_is_anycrlf+set}" = set; then + enableval=$enable_newline_is_anycrlf; ac_pcre_newline=anycrlf +fi + +# Check whether --enable-newline-is-any was given. +if test "${enable_newline_is_any+set}" = set; then + enableval=$enable_newline_is_any; ac_pcre_newline=any +fi + +enable_newline="$ac_pcre_newline" + +# Handle --enable-ebcdic +# Check whether --enable-ebcdic was given. +if test "${enable_ebcdic+set}" = set; then + enableval=$enable_ebcdic; +else + enable_ebcdic=no +fi + + +# Handle --disable-stack-for-recursion +# Check whether --enable-stack-for-recursion was given. +if test "${enable_stack_for_recursion+set}" = set; then + enableval=$enable_stack_for_recursion; +else + enable_stack_for_recursion=yes +fi + + +# Handle --with-posix-malloc-threshold=NBYTES + +# Check whether --with-posix-malloc-threshold was given. +if test "${with_posix_malloc_threshold+set}" = set; then + withval=$with_posix_malloc_threshold; +else + with_posix_malloc_threshold=10 +fi + + +# Handle --with-link-size=N + +# Check whether --with-link-size was given. +if test "${with_link_size+set}" = set; then + withval=$with_link_size; +else + with_link_size=2 +fi + + +# Handle --with-match-limit=N + +# Check whether --with-match-limit was given. +if test "${with_match_limit+set}" = set; then + withval=$with_match_limit; +else + with_match_limit=10000000 +fi + + +# Handle --with-match-limit_recursion=N +# +# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION +# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric +# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some +# different numeric value (or even the same numeric value as MATCH_LIMIT, +# though no longer defined in terms of the latter). +# + +# Check whether --with-match-limit-recursion was given. +if test "${with_match_limit_recursion+set}" = set; then + withval=$with_match_limit_recursion; +else + with_match_limit_recursion=MATCH_LIMIT +fi + + +# Make sure that if enable_unicode_properties was set, that UTF-8 support +# is enabled. +# +if test "x$enable_unicode_properties" = "xyes" +then + if test "x$enable_utf8" = "xno" + then + { { echo "$as_me:$LINENO: error: support for Unicode properties requires UTF-8 support" >&5 +echo "$as_me: error: support for Unicode properties requires UTF-8 support" >&2;} + { (exit 1); exit 1; }; } + fi + enable_utf8=yes +fi + +if test "x$enable_utf8" = "xunset" +then + enable_utf8=no +fi + +# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. +# +if test "x$enable_ebcdic" = "xyes" +then + enable_rebuild_chartables=yes +fi + +# Convert the newline identifier into the appropriate integer value. +case "$enable_newline" in + lf) ac_pcre_newline_value=10 ;; + cr) ac_pcre_newline_value=13 ;; + crlf) ac_pcre_newline_value=3338 ;; + anycrlf) ac_pcre_newline_value=-2 ;; + any) ac_pcre_newline_value=-1 ;; + *) + { { echo "$as_me:$LINENO: error: invalid argument \"$enable_newline\" to --enable-newline option" >&5 +echo "$as_me: error: invalid argument \"$enable_newline\" to --enable-newline option" >&2;} + { (exit 1); exit 1; }; } + ;; +esac + +# Check argument to --with-link-size +case "$with_link_size" in + 2|3|4) ;; + *) + { { echo "$as_me:$LINENO: error: invalid argument \"$with_link_size\" to --with-link-size option" >&5 +echo "$as_me: error: invalid argument \"$with_link_size\" to --with-link-size option" >&2;} + { (exit 1); exit 1; }; } + ;; +esac + + + + +# Checks for header files. ac_ext=c ac_cpp='$CPP $CPPFLAGS' ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' ac_compiler_gnu=$ac_cv_c_compiler_gnu -echo "$as_me:$LINENO: checking how to run the C preprocessor" >&5 -echo $ECHO_N "checking how to run the C preprocessor... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking how to run the C preprocessor" >&5 +echo $ECHO_N "checking how to run the C preprocessor... $ECHO_C" >&6; } # On Suns, sometimes $CPP names a directory. if test -n "$CPP" && test -d "$CPP"; then CPP= @@ -2391,24 +3796,22 @@ cat >>conftest.$ac_ext <<_ACEOF #endif Syntax error _ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 +if { (ac_try="$ac_cpp conftest.$ac_ext" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_cpp conftest.$ac_ext") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - ac_cpp_err=$ac_cpp_err$ac_c_werror_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then + (exit $ac_status); } >/dev/null && { + test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" || + test ! -s conftest.err + }; then : else echo "$as_me: failed program was:" >&5 @@ -2417,9 +3820,10 @@ sed 's/^/| /' conftest.$ac_ext >&5 # Broken: fails on valid input. continue fi + rm -f conftest.err conftest.$ac_ext - # OK, works on sane cases. Now check whether non-existent headers + # OK, works on sane cases. Now check whether nonexistent headers # can be detected and how. cat >conftest.$ac_ext <<_ACEOF /* confdefs.h. */ @@ -2429,24 +3833,22 @@ cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ #include _ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 +if { (ac_try="$ac_cpp conftest.$ac_ext" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_cpp conftest.$ac_ext") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - ac_cpp_err=$ac_cpp_err$ac_c_werror_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then + (exit $ac_status); } >/dev/null && { + test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" || + test ! -s conftest.err + }; then # Broken: success on invalid input. continue else @@ -2457,6 +3859,7 @@ sed 's/^/| /' conftest.$ac_ext >&5 ac_preproc_ok=: break fi + rm -f conftest.err conftest.$ac_ext done @@ -2474,8 +3877,8 @@ fi else ac_cv_prog_CPP=$CPP fi -echo "$as_me:$LINENO: result: $CPP" >&5 -echo "${ECHO_T}$CPP" >&6 +{ echo "$as_me:$LINENO: result: $CPP" >&5 +echo "${ECHO_T}$CPP" >&6; } ac_preproc_ok=false for ac_c_preproc_warn_flag in '' yes do @@ -2498,24 +3901,22 @@ cat >>conftest.$ac_ext <<_ACEOF #endif Syntax error _ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 +if { (ac_try="$ac_cpp conftest.$ac_ext" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_cpp conftest.$ac_ext") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - ac_cpp_err=$ac_cpp_err$ac_c_werror_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then + (exit $ac_status); } >/dev/null && { + test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" || + test ! -s conftest.err + }; then : else echo "$as_me: failed program was:" >&5 @@ -2524,9 +3925,10 @@ sed 's/^/| /' conftest.$ac_ext >&5 # Broken: fails on valid input. continue fi + rm -f conftest.err conftest.$ac_ext - # OK, works on sane cases. Now check whether non-existent headers + # OK, works on sane cases. Now check whether nonexistent headers # can be detected and how. cat >conftest.$ac_ext <<_ACEOF /* confdefs.h. */ @@ -2536,24 +3938,22 @@ cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ #include _ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 +if { (ac_try="$ac_cpp conftest.$ac_ext" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_cpp conftest.$ac_ext") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - ac_cpp_err=$ac_cpp_err$ac_c_werror_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then + (exit $ac_status); } >/dev/null && { + test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" || + test ! -s conftest.err + }; then # Broken: success on invalid input. continue else @@ -2564,6 +3964,7 @@ sed 's/^/| /' conftest.$ac_ext >&5 ac_preproc_ok=: break fi + rm -f conftest.err conftest.$ac_ext done @@ -2586,23 +3987,170 @@ ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $ ac_compiler_gnu=$ac_cv_c_compiler_gnu -echo "$as_me:$LINENO: checking for egrep" >&5 -echo $ECHO_N "checking for egrep... $ECHO_C" >&6 -if test "${ac_cv_prog_egrep+set}" = set; then +{ echo "$as_me:$LINENO: checking for grep that handles long lines and -e" >&5 +echo $ECHO_N "checking for grep that handles long lines and -e... $ECHO_C" >&6; } +if test "${ac_cv_path_GREP+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else - if echo a | (grep -E '(a|b)') >/dev/null 2>&1 - then ac_cv_prog_egrep='grep -E' - else ac_cv_prog_egrep='egrep' + # Extract the first word of "grep ggrep" to use in msg output +if test -z "$GREP"; then +set dummy grep ggrep; ac_prog_name=$2 +if test "${ac_cv_path_GREP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_path_GREP_found=false +# Loop through the user's path and test for each of PROGNAME-LIST +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in grep ggrep; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_GREP="$as_dir/$ac_prog$ac_exec_ext" + { test -f "$ac_path_GREP" && $as_test_x "$ac_path_GREP"; } || continue + # Check for GNU ac_path_GREP and select it if it is found. + # Check for GNU $ac_path_GREP +case `"$ac_path_GREP" --version 2>&1` in +*GNU*) + ac_cv_path_GREP="$ac_path_GREP" ac_path_GREP_found=:;; +*) + ac_count=0 + echo $ECHO_N "0123456789$ECHO_C" >"conftest.in" + while : + do + cat "conftest.in" "conftest.in" >"conftest.tmp" + mv "conftest.tmp" "conftest.in" + cp "conftest.in" "conftest.nl" + echo 'GREP' >> "conftest.nl" + "$ac_path_GREP" -e 'GREP$' -e '-(cannot match)-' < "conftest.nl" >"conftest.out" 2>/dev/null || break + diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break + ac_count=`expr $ac_count + 1` + if test $ac_count -gt ${ac_path_GREP_max-0}; then + # Best one so far, save it but keep looking for a better one + ac_cv_path_GREP="$ac_path_GREP" + ac_path_GREP_max=$ac_count fi + # 10*(2^10) chars as input seems more than enough + test $ac_count -gt 10 && break + done + rm -f conftest.in conftest.tmp conftest.nl conftest.out;; +esac + + + $ac_path_GREP_found && break 3 + done +done + +done +IFS=$as_save_IFS + + +fi + +GREP="$ac_cv_path_GREP" +if test -z "$GREP"; then + { { echo "$as_me:$LINENO: error: no acceptable $ac_prog_name could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" >&5 +echo "$as_me: error: no acceptable $ac_prog_name could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" >&2;} + { (exit 1); exit 1; }; } +fi + +else + ac_cv_path_GREP=$GREP fi -echo "$as_me:$LINENO: result: $ac_cv_prog_egrep" >&5 -echo "${ECHO_T}$ac_cv_prog_egrep" >&6 - EGREP=$ac_cv_prog_egrep -echo "$as_me:$LINENO: checking for ANSI C header files" >&5 -echo $ECHO_N "checking for ANSI C header files... $ECHO_C" >&6 +fi +{ echo "$as_me:$LINENO: result: $ac_cv_path_GREP" >&5 +echo "${ECHO_T}$ac_cv_path_GREP" >&6; } + GREP="$ac_cv_path_GREP" + + +{ echo "$as_me:$LINENO: checking for egrep" >&5 +echo $ECHO_N "checking for egrep... $ECHO_C" >&6; } +if test "${ac_cv_path_EGREP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if echo a | $GREP -E '(a|b)' >/dev/null 2>&1 + then ac_cv_path_EGREP="$GREP -E" + else + # Extract the first word of "egrep" to use in msg output +if test -z "$EGREP"; then +set dummy egrep; ac_prog_name=$2 +if test "${ac_cv_path_EGREP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_path_EGREP_found=false +# Loop through the user's path and test for each of PROGNAME-LIST +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in egrep; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_EGREP="$as_dir/$ac_prog$ac_exec_ext" + { test -f "$ac_path_EGREP" && $as_test_x "$ac_path_EGREP"; } || continue + # Check for GNU ac_path_EGREP and select it if it is found. + # Check for GNU $ac_path_EGREP +case `"$ac_path_EGREP" --version 2>&1` in +*GNU*) + ac_cv_path_EGREP="$ac_path_EGREP" ac_path_EGREP_found=:;; +*) + ac_count=0 + echo $ECHO_N "0123456789$ECHO_C" >"conftest.in" + while : + do + cat "conftest.in" "conftest.in" >"conftest.tmp" + mv "conftest.tmp" "conftest.in" + cp "conftest.in" "conftest.nl" + echo 'EGREP' >> "conftest.nl" + "$ac_path_EGREP" 'EGREP$' < "conftest.nl" >"conftest.out" 2>/dev/null || break + diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break + ac_count=`expr $ac_count + 1` + if test $ac_count -gt ${ac_path_EGREP_max-0}; then + # Best one so far, save it but keep looking for a better one + ac_cv_path_EGREP="$ac_path_EGREP" + ac_path_EGREP_max=$ac_count + fi + # 10*(2^10) chars as input seems more than enough + test $ac_count -gt 10 && break + done + rm -f conftest.in conftest.tmp conftest.nl conftest.out;; +esac + + + $ac_path_EGREP_found && break 3 + done +done + +done +IFS=$as_save_IFS + + +fi + +EGREP="$ac_cv_path_EGREP" +if test -z "$EGREP"; then + { { echo "$as_me:$LINENO: error: no acceptable $ac_prog_name could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" >&5 +echo "$as_me: error: no acceptable $ac_prog_name could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" >&2;} + { (exit 1); exit 1; }; } +fi + +else + ac_cv_path_EGREP=$EGREP +fi + + + fi +fi +{ echo "$as_me:$LINENO: result: $ac_cv_path_EGREP" >&5 +echo "${ECHO_T}$ac_cv_path_EGREP" >&6; } + EGREP="$ac_cv_path_EGREP" + + +{ echo "$as_me:$LINENO: checking for ANSI C header files" >&5 +echo $ECHO_N "checking for ANSI C header files... $ECHO_C" >&6; } if test "${ac_cv_header_stdc+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -2626,35 +4174,31 @@ main () } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_cv_header_stdc=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_cv_header_stdc=no + ac_cv_header_stdc=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext if test $ac_cv_header_stdc = yes; then # SunOS 4.x string.h does not declare mem*, contrary to ANSI. @@ -2710,6 +4254,7 @@ cat confdefs.h >>conftest.$ac_ext cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ #include +#include #if ((' ' & 0x0FF) == 0x020) # define ISLOWER(c) ('a' <= (c) && (c) <= 'z') # define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) @@ -2729,18 +4274,27 @@ main () for (i = 0; i < 256; i++) if (XOR (islower (i), ISLOWER (i)) || toupper (i) != TOUPPER (i)) - exit(2); - exit (0); + return 2; + return 0; } _ACEOF rm -f conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 +if { (ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_link") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); } && { ac_try='./conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 + { (case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_try") 2>&5 ac_status=$? echo "$as_me:$LINENO: \$? = $ac_status" >&5 (exit $ac_status); }; }; then @@ -2753,12 +4307,14 @@ sed 's/^/| /' conftest.$ac_ext >&5 ( exit $ac_status ) ac_cv_header_stdc=no fi -rm -f core *.core gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext +rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext +fi + + fi fi -fi -echo "$as_me:$LINENO: result: $ac_cv_header_stdc" >&5 -echo "${ECHO_T}$ac_cv_header_stdc" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_header_stdc" >&5 +echo "${ECHO_T}$ac_cv_header_stdc" >&6; } if test $ac_cv_header_stdc = yes; then cat >>confdefs.h <<\_ACEOF @@ -2781,9 +4337,9 @@ for ac_header in sys/types.h sys/stat.h stdlib.h string.h memory.h strings.h \ inttypes.h stdint.h unistd.h do as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` -echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then +{ echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6; } +if { as_var=$as_ac_Header; eval "test \"\${$as_var+set}\" = set"; }; then echo $ECHO_N "(cached) $ECHO_C" >&6 else cat >conftest.$ac_ext <<_ACEOF @@ -2797,38 +4353,35 @@ $ac_includes_default #include <$ac_header> _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then eval "$as_ac_Header=yes" else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -eval "$as_ac_Header=no" + eval "$as_ac_Header=no" fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +ac_res=`eval echo '${'$as_ac_Header'}'` + { echo "$as_me:$LINENO: result: $ac_res" >&5 +echo "${ECHO_T}$ac_res" >&6; } if test `eval echo '${'$as_ac_Header'}'` = yes; then cat >>confdefs.h <<_ACEOF #define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 @@ -2840,21 +4393,26 @@ done -for ac_header in limits.h + + + + +for ac_header in limits.h sys/types.h sys/stat.h dirent.h windows.h do as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then +if { as_var=$as_ac_Header; eval "test \"\${$as_var+set}\" = set"; }; then + { echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6; } +if { as_var=$as_ac_Header; eval "test \"\${$as_var+set}\" = set"; }; then echo $ECHO_N "(cached) $ECHO_C" >&6 fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +ac_res=`eval echo '${'$as_ac_Header'}'` + { echo "$as_me:$LINENO: result: $ac_res" >&5 +echo "${ECHO_T}$ac_res" >&6; } else # Is the header compilable? -echo "$as_me:$LINENO: checking $ac_header usability" >&5 -echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking $ac_header usability" >&5 +echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6; } cat >conftest.$ac_ext <<_ACEOF /* confdefs.h. */ _ACEOF @@ -2865,41 +4423,37 @@ $ac_includes_default #include <$ac_header> _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_header_compiler=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_header_compiler=no + ac_header_compiler=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext -echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 -echo "${ECHO_T}$ac_header_compiler" >&6 + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +{ echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 +echo "${ECHO_T}$ac_header_compiler" >&6; } # Is the header present? -echo "$as_me:$LINENO: checking $ac_header presence" >&5 -echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking $ac_header presence" >&5 +echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6; } cat >conftest.$ac_ext <<_ACEOF /* confdefs.h. */ _ACEOF @@ -2908,24 +4462,22 @@ cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ #include <$ac_header> _ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 +if { (ac_try="$ac_cpp conftest.$ac_ext" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_cpp conftest.$ac_ext") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - ac_cpp_err=$ac_cpp_err$ac_c_werror_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then + (exit $ac_status); } >/dev/null && { + test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" || + test ! -s conftest.err + }; then ac_header_preproc=yes else echo "$as_me: failed program was:" >&5 @@ -2933,9 +4485,10 @@ sed 's/^/| /' conftest.$ac_ext >&5 ac_header_preproc=no fi + rm -f conftest.err conftest.$ac_ext -echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 -echo "${ECHO_T}$ac_header_preproc" >&6 +{ echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 +echo "${ECHO_T}$ac_header_preproc" >&6; } # So? What about this header? case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in @@ -2959,25 +4512,19 @@ echo "$as_me: WARNING: $ac_header: section \"Present But Cannot Be Compiled\ echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} { echo "$as_me:$LINENO: WARNING: $ac_header: in the future, the compiler will take precedence" >&5 echo "$as_me: WARNING: $ac_header: in the future, the compiler will take precedence" >&2;} - ( - cat <<\_ASBOX -## ------------------------------------------ ## -## Report this to the AC_PACKAGE_NAME lists. ## -## ------------------------------------------ ## -_ASBOX - ) | - sed "s/^/$as_me: WARNING: /" >&2 + ;; esac -echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then +{ echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6; } +if { as_var=$as_ac_Header; eval "test \"\${$as_var+set}\" = set"; }; then echo $ECHO_N "(cached) $ECHO_C" >&6 else eval "$as_ac_Header=\$ac_header_preproc" fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +ac_res=`eval echo '${'$as_ac_Header'}'` + { echo "$as_me:$LINENO: result: $ac_res" >&5 +echo "${ECHO_T}$ac_res" >&6; } fi if test `eval echo '${'$as_ac_Header'}'` = yes; then @@ -2990,9 +4537,24 @@ fi done +# Using AC_SUBST eliminates the need to include config.h in a public .h file -echo "$as_me:$LINENO: checking for an ANSI C-conforming const" >&5 -echo $ECHO_N "checking for an ANSI C-conforming const... $ECHO_C" >&6 + + +# Conditional compilation + if test "x$enable_rebuild_chartables" = "xyes"; then + WITH_REBUILD_CHARTABLES_TRUE= + WITH_REBUILD_CHARTABLES_FALSE='#' +else + WITH_REBUILD_CHARTABLES_TRUE='#' + WITH_REBUILD_CHARTABLES_FALSE= +fi + + +# Checks for typedefs, structures, and compiler characteristics. + +{ echo "$as_me:$LINENO: checking for an ANSI C-conforming const" >&5 +echo $ECHO_N "checking for an ANSI C-conforming const... $ECHO_C" >&6; } if test "${ac_cv_c_const+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -3010,10 +4572,10 @@ main () #ifndef __cplusplus /* Ultrix mips cc rejects this. */ typedef int charset[2]; - const charset x; + const charset cs; /* SunOS 4.1.1 cc rejects this. */ - char const *const *ccp; - char **p; + char const *const *pcpcc; + char **ppc; /* NEC SVR4.0.2 mips cc rejects this. */ struct point {int x, y;}; static struct point const zero = {0,0}; @@ -3022,16 +4584,17 @@ main () an arm of an if-expression whose if-part is not a constant expression */ const char *g = "string"; - ccp = &g + (g ? g-g : 0); + pcpcc = &g + (g ? g-g : 0); /* HPUX 7.0 cc rejects these. */ - ++ccp; - p = (char**) ccp; - ccp = (char const *const *) p; + ++pcpcc; + ppc = (char**) pcpcc; + pcpcc = (char const *const *) ppc; { /* SCO 3.2v4 cc rejects this. */ char *t; char const *s = 0 ? (char *) 0 : (char const *) 0; *t++ = 0; + if (s) return 0; } { /* Someone thinks the Sun supposedly-ANSI compiler will reject this. */ int x[] = {25, 17}; @@ -3050,7 +4613,9 @@ main () } { /* ULTRIX-32 V3.1 (Rev 9) vcc rejects this */ const int foo = 10; + if (!foo) return 0; } + return !cs[0] && !zero.x; #endif ; @@ -3058,38 +4623,34 @@ main () } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_cv_c_const=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_cv_c_const=no + ac_cv_c_const=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: $ac_cv_c_const" >&5 -echo "${ECHO_T}$ac_cv_c_const" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_c_const" >&5 +echo "${ECHO_T}$ac_cv_c_const" >&6; } if test $ac_cv_c_const = no; then cat >>confdefs.h <<\_ACEOF @@ -3098,8 +4659,8 @@ _ACEOF fi -echo "$as_me:$LINENO: checking for size_t" >&5 -echo $ECHO_N "checking for size_t... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for size_t" >&5 +echo $ECHO_N "checking for size_t... $ECHO_C" >&6; } if test "${ac_cv_type_size_t+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -3110,63 +4671,60 @@ cat confdefs.h >>conftest.$ac_ext cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ $ac_includes_default +typedef size_t ac__type_new_; int main () { -if ((size_t *) 0) +if ((ac__type_new_ *) 0) return 0; -if (sizeof (size_t)) +if (sizeof (ac__type_new_)) return 0; ; return 0; } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_cv_type_size_t=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_cv_type_size_t=no + ac_cv_type_size_t=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: $ac_cv_type_size_t" >&5 -echo "${ECHO_T}$ac_cv_type_size_t" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_type_size_t" >&5 +echo "${ECHO_T}$ac_cv_type_size_t" >&6; } if test $ac_cv_type_size_t = yes; then : else cat >>confdefs.h <<_ACEOF -#define size_t unsigned +#define size_t unsigned int _ACEOF fi -echo "$as_me:$LINENO: checking for long long" >&5 -echo $ECHO_N "checking for long long... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for long long" >&5 +echo $ECHO_N "checking for long long... $ECHO_C" >&6; } if test "${ac_cv_type_long_long+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -3177,50 +4735,47 @@ cat confdefs.h >>conftest.$ac_ext cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ $ac_includes_default +typedef long long ac__type_new_; int main () { -if ((long long *) 0) +if ((ac__type_new_ *) 0) return 0; -if (sizeof (long long)) +if (sizeof (ac__type_new_)) return 0; ; return 0; } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_cv_type_long_long=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_cv_type_long_long=no + ac_cv_type_long_long=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: $ac_cv_type_long_long" >&5 -echo "${ECHO_T}$ac_cv_type_long_long" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_type_long_long" >&5 +echo "${ECHO_T}$ac_cv_type_long_long" >&6; } if test $ac_cv_type_long_long = yes; then cat >>confdefs.h <<_ACEOF @@ -3232,8 +4787,8 @@ else pcre_have_long_long="0" fi -echo "$as_me:$LINENO: checking for unsigned long long" >&5 -echo $ECHO_N "checking for unsigned long long... $ECHO_C" >&6 +{ echo "$as_me:$LINENO: checking for unsigned long long" >&5 +echo $ECHO_N "checking for unsigned long long... $ECHO_C" >&6; } if test "${ac_cv_type_unsigned_long_long+set}" = set; then echo $ECHO_N "(cached) $ECHO_C" >&6 else @@ -3244,50 +4799,47 @@ cat confdefs.h >>conftest.$ac_ext cat >>conftest.$ac_ext <<_ACEOF /* end confdefs.h. */ $ac_includes_default +typedef unsigned long long ac__type_new_; int main () { -if ((unsigned long long *) 0) +if ((ac__type_new_ *) 0) return 0; -if (sizeof (unsigned long long)) +if (sizeof (ac__type_new_)) return 0; ; return 0; } _ACEOF rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>conftest.er1 +if { (ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_compile") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then ac_cv_type_unsigned_long_long=yes else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -ac_cv_type_unsigned_long_long=no + ac_cv_type_unsigned_long_long=no fi -rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: $ac_cv_type_unsigned_long_long" >&5 -echo "${ECHO_T}$ac_cv_type_unsigned_long_long" >&6 +{ echo "$as_me:$LINENO: result: $ac_cv_type_unsigned_long_long" >&5 +echo "${ECHO_T}$ac_cv_type_unsigned_long_long" >&6; } if test $ac_cv_type_unsigned_long_long = yes; then cat >>confdefs.h <<_ACEOF @@ -3302,6 +4854,7 @@ fi +# Checks for library functions. @@ -3311,9 +4864,9 @@ fi for ac_func in bcopy memmove strerror strtoq strtoll do as_ac_var=`echo "ac_cv_func_$ac_func" | $as_tr_sh` -echo "$as_me:$LINENO: checking for $ac_func" >&5 -echo $ECHO_N "checking for $ac_func... $ECHO_C" >&6 -if eval "test \"\${$as_ac_var+set}\" = set"; then +{ echo "$as_me:$LINENO: checking for $ac_func" >&5 +echo $ECHO_N "checking for $ac_func... $ECHO_C" >&6; } +if { as_var=$as_ac_var; eval "test \"\${$as_var+set}\" = set"; }; then echo $ECHO_N "(cached) $ECHO_C" >&6 else cat >conftest.$ac_ext <<_ACEOF @@ -3339,68 +4892,60 @@ cat >>conftest.$ac_ext <<_ACEOF #undef $ac_func -/* Override any gcc2 internal prototype to avoid an error. */ +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ #ifdef __cplusplus extern "C" -{ #endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ char $ac_func (); /* The GNU C library defines this for functions which it implements to always fail with ENOSYS. Some functions are actually named something starting with __ and the normal name is an alias. */ -#if defined (__stub_$ac_func) || defined (__stub___$ac_func) +#if defined __stub_$ac_func || defined __stub___$ac_func choke me -#else -char (*f) () = $ac_func; -#endif -#ifdef __cplusplus -} #endif int main () { -return f != $ac_func; +return $ac_func (); ; return 0; } _ACEOF rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>conftest.er1 +if { (ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5 + (eval "$ac_link") 2>conftest.er1 ac_status=$? grep -v '^ *+' conftest.er1 >conftest.err rm -f conftest.er1 cat conftest.err >&5 echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -z "$ac_c_werror_flag" - || test ! -s conftest.err' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then + (exit $ac_status); } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest$ac_exeext && + $as_test_x conftest$ac_exeext; then eval "$as_ac_var=yes" else echo "$as_me: failed program was:" >&5 sed 's/^/| /' conftest.$ac_ext >&5 -eval "$as_ac_var=no" + eval "$as_ac_var=no" fi -rm -f conftest.err conftest.$ac_objext \ + +rm -f core conftest.err conftest.$ac_objext conftest_ipa8_conftest.oo \ conftest$ac_exeext conftest.$ac_ext fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_var'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_var'}'`" >&6 +ac_res=`eval echo '${'$as_ac_var'}'` + { echo "$as_me:$LINENO: result: $ac_res" >&5 +echo "${ECHO_T}$ac_res" >&6; } if test `eval echo '${'$as_ac_var'}'` = yes; then cat >>confdefs.h <<_ACEOF #define `echo "HAVE_$ac_func" | $as_tr_cpp` 1 @@ -3410,245 +4955,218 @@ fi done +# This facilitates -ansi builds under Linux -# Check whether --enable-utf8 or --disable-utf8 was given. -if test "${enable_utf8+set}" = set; then - enableval="$enable_utf8" - if test "$enableval" = "yes"; then - UTF8=-DSUPPORT_UTF8 -fi - -fi; - - -# Check whether --enable-unicode-properties or --disable-unicode-properties was given. -if test "${enable_unicode_properties+set}" = set; then - enableval="$enable_unicode_properties" - if test "$enableval" = "yes"; then - UCP=-DSUPPORT_UCP -fi - -fi; - - -# Check whether --enable-newline-is-cr or --disable-newline-is-cr was given. -if test "${enable_newline_is_cr+set}" = set; then - enableval="$enable_newline_is_cr" - if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=13 -fi - -fi; - - -# Check whether --enable-newline-is-lf or --disable-newline-is-lf was given. -if test "${enable_newline_is_lf+set}" = set; then - enableval="$enable_newline_is_lf" - if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=10 -fi - -fi; - - -# Check whether --enable-newline-is-crlf or --disable-newline-is-crlf was given. -if test "${enable_newline_is_crlf+set}" = set; then - enableval="$enable_newline_is_crlf" - if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=3338 -fi - -fi; - - -# Check whether --enable-ebcdic or --disable-ebcdic was given. -if test "${enable_ebcdic+set}" = set; then - enableval="$enable_ebcdic" - if test "$enableval" == "yes"; then - EBCDIC=-DEBCDIC=1 -fi - -fi; - - -# Check whether --enable-stack-for-recursion or --disable-stack-for-recursion was given. -if test "${enable_stack_for_recursion+set}" = set; then - enableval="$enable_stack_for_recursion" - if test "$enableval" = "no"; then - NO_RECURSE=-DNO_RECURSE -fi - -fi; - - - - -# Check whether --with-posix-malloc-threshold or --without-posix-malloc-threshold was given. -if test "${with_posix_malloc_threshold+set}" = set; then - withval="$with_posix_malloc_threshold" - POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval - -fi; - - - -# Check whether --with-link-size or --without-link-size was given. -if test "${with_link_size+set}" = set; then - withval="$with_link_size" - LINK_SIZE=-DLINK_SIZE=$withval - -fi; - - - -# Check whether --with-match-limit or --without-match-limit was given. -if test "${with_match_limit+set}" = set; then - withval="$with_match_limit" - MATCH_LIMIT=-DMATCH_LIMIT=$withval - -fi; - - - -# Check whether --with-match-limit-recursion or --without-match-limit-recursion was given. -if test "${with_match_limit_recursion+set}" = set; then - withval="$with_match_limit_recursion" - MATCH_LIMIT_RECURSION=-DMATCH_LIMIT_RECURSION=$withval - -fi; - - -if test "$UCP" != "" ; then - UTF8=-DSUPPORT_UTF8 -fi - -ac_aux_dir= -for ac_dir in $srcdir $srcdir/.. $srcdir/../..; do - if test -f $ac_dir/install-sh; then - ac_aux_dir=$ac_dir - ac_install_sh="$ac_aux_dir/install-sh -c" - break - elif test -f $ac_dir/install.sh; then - ac_aux_dir=$ac_dir - ac_install_sh="$ac_aux_dir/install.sh -c" - break - elif test -f $ac_dir/shtool; then - ac_aux_dir=$ac_dir - ac_install_sh="$ac_aux_dir/shtool install -c" - break - fi -done -if test -z "$ac_aux_dir"; then - { { echo "$as_me:$LINENO: error: cannot find install-sh or install.sh in $srcdir $srcdir/.. $srcdir/../.." >&5 -echo "$as_me: error: cannot find install-sh or install.sh in $srcdir $srcdir/.. $srcdir/../.." >&2;} - { (exit 1); exit 1; }; } -fi -ac_config_guess="$SHELL $ac_aux_dir/config.guess" -ac_config_sub="$SHELL $ac_aux_dir/config.sub" -ac_configure="$SHELL $ac_aux_dir/configure" # This should be Cygnus configure. - -# Make sure we can run config.sub. -$ac_config_sub sun4 >/dev/null 2>&1 || - { { echo "$as_me:$LINENO: error: cannot run $ac_config_sub" >&5 -echo "$as_me: error: cannot run $ac_config_sub" >&2;} - { (exit 1); exit 1; }; } - -echo "$as_me:$LINENO: checking build system type" >&5 -echo $ECHO_N "checking build system type... $ECHO_C" >&6 -if test "${ac_cv_build+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_cv_build_alias=$build_alias -test -z "$ac_cv_build_alias" && - ac_cv_build_alias=`$ac_config_guess` -test -z "$ac_cv_build_alias" && - { { echo "$as_me:$LINENO: error: cannot guess build type; you must specify one" >&5 -echo "$as_me: error: cannot guess build type; you must specify one" >&2;} - { (exit 1); exit 1; }; } -ac_cv_build=`$ac_config_sub $ac_cv_build_alias` || - { { echo "$as_me:$LINENO: error: $ac_config_sub $ac_cv_build_alias failed" >&5 -echo "$as_me: error: $ac_config_sub $ac_cv_build_alias failed" >&2;} - { (exit 1); exit 1; }; } - -fi -echo "$as_me:$LINENO: result: $ac_cv_build" >&5 -echo "${ECHO_T}$ac_cv_build" >&6 -build=$ac_cv_build -build_cpu=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` -build_vendor=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` -build_os=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` - - -echo "$as_me:$LINENO: checking host system type" >&5 -echo $ECHO_N "checking host system type... $ECHO_C" >&6 -if test "${ac_cv_host+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_cv_host_alias=$host_alias -test -z "$ac_cv_host_alias" && - ac_cv_host_alias=$ac_cv_build_alias -ac_cv_host=`$ac_config_sub $ac_cv_host_alias` || - { { echo "$as_me:$LINENO: error: $ac_config_sub $ac_cv_host_alias failed" >&5 -echo "$as_me: error: $ac_config_sub $ac_cv_host_alias failed" >&2;} - { (exit 1); exit 1; }; } - -fi -echo "$as_me:$LINENO: result: $ac_cv_host" >&5 -echo "${ECHO_T}$ac_cv_host" >&6 -host=$ac_cv_host -host_cpu=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` -host_vendor=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` -host_os=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` - - - -case "$host" in - i386-apple-darwin*) - macosx=yes - cat >>confdefs.h <<\_ACEOF -#define MACOSX 1 -_ACEOF - - needs_cpp_precomp=yes - CFLAGS="$CFLAGS -fno-thread-jumps" - ;; -esac - - - - - - - - - - - - - - - - - - - - - - - - - - - -if test "x$enable_shared" = "xno" ; then +# We only want static libs cat >>confdefs.h <<\_ACEOF #define PCRE_STATIC 1 _ACEOF + +# Here is where pcre specific defines are handled + +if test "$enable_utf8" = "yes"; then + +cat >>confdefs.h <<\_ACEOF +#define SUPPORT_UTF8 +_ACEOF + fi - ac_config_files="$ac_config_files Makefile" +if test "$enable_unicode_properties" = "yes"; then + +cat >>confdefs.h <<\_ACEOF +#define SUPPORT_UCP +_ACEOF + +fi + +if test "$enable_stack_for_recursion" = "no"; then + +cat >>confdefs.h <<\_ACEOF +#define NO_RECURSE +_ACEOF + +fi + + +cat >>confdefs.h <<_ACEOF +#define NEWLINE $ac_pcre_newline_value +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define LINK_SIZE $with_link_size +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define POSIX_MALLOC_THRESHOLD $with_posix_malloc_threshold +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define MATCH_LIMIT $with_match_limit +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define MATCH_LIMIT_RECURSION $with_match_limit_recursion +_ACEOF + + + +cat >>confdefs.h <<\_ACEOF +#define MAX_NAME_SIZE 32 +_ACEOF + + + +cat >>confdefs.h <<\_ACEOF +#define MAX_NAME_COUNT 10000 +_ACEOF + + + +cat >>confdefs.h <<\_ACEOF +#define MAX_DUPLENGTH 30000 +_ACEOF + + + + + +if test "$enable_ebcdic" = "yes"; then + +cat >>confdefs.h <<_ACEOF +#define EBCDIC +_ACEOF + +fi + +# Make sure we can run config.sub. +$SHELL "$ac_aux_dir/config.sub" sun4 >/dev/null 2>&1 || + { { echo "$as_me:$LINENO: error: cannot run $SHELL $ac_aux_dir/config.sub" >&5 +echo "$as_me: error: cannot run $SHELL $ac_aux_dir/config.sub" >&2;} + { (exit 1); exit 1; }; } + +{ echo "$as_me:$LINENO: checking build system type" >&5 +echo $ECHO_N "checking build system type... $ECHO_C" >&6; } +if test "${ac_cv_build+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_build_alias=$build_alias +test "x$ac_build_alias" = x && + ac_build_alias=`$SHELL "$ac_aux_dir/config.guess"` +test "x$ac_build_alias" = x && + { { echo "$as_me:$LINENO: error: cannot guess build type; you must specify one" >&5 +echo "$as_me: error: cannot guess build type; you must specify one" >&2;} + { (exit 1); exit 1; }; } +ac_cv_build=`$SHELL "$ac_aux_dir/config.sub" $ac_build_alias` || + { { echo "$as_me:$LINENO: error: $SHELL $ac_aux_dir/config.sub $ac_build_alias failed" >&5 +echo "$as_me: error: $SHELL $ac_aux_dir/config.sub $ac_build_alias failed" >&2;} + { (exit 1); exit 1; }; } + +fi +{ echo "$as_me:$LINENO: result: $ac_cv_build" >&5 +echo "${ECHO_T}$ac_cv_build" >&6; } +case $ac_cv_build in +*-*-*) ;; +*) { { echo "$as_me:$LINENO: error: invalid value of canonical build" >&5 +echo "$as_me: error: invalid value of canonical build" >&2;} + { (exit 1); exit 1; }; };; +esac +build=$ac_cv_build +ac_save_IFS=$IFS; IFS='-' +set x $ac_cv_build +shift +build_cpu=$1 +build_vendor=$2 +shift; shift +# Remember, the first character of IFS is used to create $*, +# except with old shells: +build_os=$* +IFS=$ac_save_IFS +case $build_os in *\ *) build_os=`echo "$build_os" | sed 's/ /-/g'`;; esac + + +{ echo "$as_me:$LINENO: checking host system type" >&5 +echo $ECHO_N "checking host system type... $ECHO_C" >&6; } +if test "${ac_cv_host+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test "x$host_alias" = x; then + ac_cv_host=$ac_cv_build +else + ac_cv_host=`$SHELL "$ac_aux_dir/config.sub" $host_alias` || + { { echo "$as_me:$LINENO: error: $SHELL $ac_aux_dir/config.sub $host_alias failed" >&5 +echo "$as_me: error: $SHELL $ac_aux_dir/config.sub $host_alias failed" >&2;} + { (exit 1); exit 1; }; } +fi + +fi +{ echo "$as_me:$LINENO: result: $ac_cv_host" >&5 +echo "${ECHO_T}$ac_cv_host" >&6; } +case $ac_cv_host in +*-*-*) ;; +*) { { echo "$as_me:$LINENO: error: invalid value of canonical host" >&5 +echo "$as_me: error: invalid value of canonical host" >&2;} + { (exit 1); exit 1; }; };; +esac +host=$ac_cv_host +ac_save_IFS=$IFS; IFS='-' +set x $ac_cv_host +shift +host_cpu=$1 +host_vendor=$2 +shift; shift +# Remember, the first character of IFS is used to create $*, +# except with old shells: +host_os=$* +IFS=$ac_save_IFS +case $host_os in *\ *) host_os=`echo "$host_os" | sed 's/ /-/g'`;; esac + + + +case "$host" in + i386-apple-darwin*) + macosx=yes + +cat >>confdefs.h <<\_ACEOF +#define MACOSX +_ACEOF + + CFLAGS="$CFLAGS -fno-thread-jumps" + ;; +esac + + + +# The extra LDFLAGS for each particular library +# (Note: The libpcre*_version bits are m4 variables, assigned above) + +EXTRA_LIBPCRE_LDFLAGS="$NO_UNDEFINED -version-info libpcre_version" + + + +# Produce these files, in addition to config.h. +ac_config_files="$ac_config_files Makefile pcre-config pcre.h" + + +# Make the generated script files executable. +ac_config_commands="$ac_config_commands script-chmod" + + +# Make sure that pcre_chartables.c is removed in case the method for +# creating it was changed by reconfiguration. +ac_config_commands="$ac_config_commands delete-old-chartables" + + cat >confcache <<\_ACEOF # This file is a shell script that caches the results of configure # tests run on this system so they can be shared between configure @@ -3667,39 +5185,58 @@ _ACEOF # The following way of writing the cache mishandles newlines in values, # but we know of no workaround that is simple, portable, and efficient. -# So, don't put newlines in cache variables' values. +# So, we kill variables containing newlines. # Ultrix sh set writes to stderr and can't be redirected directly, # and sets the high bit in the cache file unless we assign to the vars. -{ +( + for ac_var in `(set) 2>&1 | sed -n 's/^\([a-zA-Z_][a-zA-Z0-9_]*\)=.*/\1/p'`; do + eval ac_val=\$$ac_var + case $ac_val in #( + *${as_nl}*) + case $ac_var in #( + *_cv_*) { echo "$as_me:$LINENO: WARNING: Cache variable $ac_var contains a newline." >&5 +echo "$as_me: WARNING: Cache variable $ac_var contains a newline." >&2;} ;; + esac + case $ac_var in #( + _ | IFS | as_nl) ;; #( + *) $as_unset $ac_var ;; + esac ;; + esac + done + (set) 2>&1 | - case `(ac_space=' '; set | grep ac_space) 2>&1` in - *ac_space=\ *) + case $as_nl`(ac_space=' '; set) 2>&1` in #( + *${as_nl}ac_space=\ *) # `set' does not quote correctly, so add quotes (double-quote # substitution turns \\\\ into \\, and sed turns \\ into \). sed -n \ "s/'/'\\\\''/g; s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='\\2'/p" - ;; + ;; #( *) # `set' quotes correctly as required by POSIX, so do not add quotes. - sed -n \ - "s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1=\\2/p" + sed -n "/^[_$as_cr_alnum]*_cv_[_$as_cr_alnum]*=/p" ;; - esac; -} | + esac | + sort +) | sed ' + /^ac_cv_env_/b end t clear - : clear + :clear s/^\([^=]*\)=\(.*[{}].*\)$/test "${\1+set}" = set || &/ t end - /^ac_cv_env/!s/^\([^=]*\)=\(.*\)$/\1=${\1=\2}/ - : end' >>confcache -if diff $cache_file confcache >/dev/null 2>&1; then :; else - if test -w $cache_file; then - test "x$cache_file" != "x/dev/null" && echo "updating cache $cache_file" + s/^\([^=]*\)=\(.*\)$/\1=${\1=\2}/ + :end' >>confcache +if diff "$cache_file" confcache >/dev/null 2>&1; then :; else + if test -w "$cache_file"; then + test "x$cache_file" != "x/dev/null" && + { echo "$as_me:$LINENO: updating cache $cache_file" >&5 +echo "$as_me: updating cache $cache_file" >&6;} cat confcache >$cache_file else - echo "not updating unwritable cache $cache_file" + { echo "$as_me:$LINENO: not updating unwritable cache $cache_file" >&5 +echo "$as_me: not updating unwritable cache $cache_file" >&6;} fi fi rm -f confcache @@ -3708,38 +5245,45 @@ test "x$prefix" = xNONE && prefix=$ac_default_prefix # Let make expand exec_prefix. test "x$exec_prefix" = xNONE && exec_prefix='${prefix}' -# VPATH may cause trouble with some makes, so we remove $(srcdir), -# ${srcdir} and @srcdir@ from VPATH if srcdir is ".", strip leading and -# trailing colons and then remove the whole line if VPATH becomes empty -# (actually we leave an empty line to preserve line numbers). -if test "x$srcdir" = x.; then - ac_vpsub='/^[ ]*VPATH[ ]*=/{ -s/:*\$(srcdir):*/:/; -s/:*\${srcdir}:*/:/; -s/:*@srcdir@:*/:/; -s/^\([^=]*=[ ]*\):*/\1/; -s/:*$//; -s/^[^=]*=[ ]*$//; -}' -fi - DEFS=-DHAVE_CONFIG_H ac_libobjs= ac_ltlibobjs= for ac_i in : $LIBOBJS; do test "x$ac_i" = x: && continue # 1. Remove the extension, and $U if already installed. - ac_i=`echo "$ac_i" | - sed 's/\$U\././;s/\.o$//;s/\.obj$//'` - # 2. Add them. - ac_libobjs="$ac_libobjs $ac_i\$U.$ac_objext" - ac_ltlibobjs="$ac_ltlibobjs $ac_i"'$U.lo' + ac_script='s/\$U\././;s/\.o$//;s/\.obj$//' + ac_i=`echo "$ac_i" | sed "$ac_script"` + # 2. Prepend LIBOBJDIR. When used with automake>=1.10 LIBOBJDIR + # will be set to the directory where LIBOBJS objects are built. + ac_libobjs="$ac_libobjs \${LIBOBJDIR}$ac_i\$U.$ac_objext" + ac_ltlibobjs="$ac_ltlibobjs \${LIBOBJDIR}$ac_i"'$U.lo' done LIBOBJS=$ac_libobjs LTLIBOBJS=$ac_ltlibobjs +if test -z "${AMDEP_TRUE}" && test -z "${AMDEP_FALSE}"; then + { { echo "$as_me:$LINENO: error: conditional \"AMDEP\" was never defined. +Usually this means the macro was only invoked conditionally." >&5 +echo "$as_me: error: conditional \"AMDEP\" was never defined. +Usually this means the macro was only invoked conditionally." >&2;} + { (exit 1); exit 1; }; } +fi +if test -z "${am__fastdepCC_TRUE}" && test -z "${am__fastdepCC_FALSE}"; then + { { echo "$as_me:$LINENO: error: conditional \"am__fastdepCC\" was never defined. +Usually this means the macro was only invoked conditionally." >&5 +echo "$as_me: error: conditional \"am__fastdepCC\" was never defined. +Usually this means the macro was only invoked conditionally." >&2;} + { (exit 1); exit 1; }; } +fi +if test -z "${WITH_REBUILD_CHARTABLES_TRUE}" && test -z "${WITH_REBUILD_CHARTABLES_FALSE}"; then + { { echo "$as_me:$LINENO: error: conditional \"WITH_REBUILD_CHARTABLES\" was never defined. +Usually this means the macro was only invoked conditionally." >&5 +echo "$as_me: error: conditional \"WITH_REBUILD_CHARTABLES\" was never defined. +Usually this means the macro was only invoked conditionally." >&2;} + { (exit 1); exit 1; }; } +fi : ${CONFIG_STATUS=./config.status} ac_clean_files_save=$ac_clean_files @@ -3764,73 +5308,26 @@ cat >>$CONFIG_STATUS <<\_ACEOF ## M4sh Initialization. ## ## --------------------- ## -# Be Bourne compatible +# Be more Bourne compatible +DUALCASE=1; export DUALCASE # for MKS sh if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then emulate sh NULLCMD=: # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which # is contrary to our usage. Disable this feature. alias -g '${1+"$@"}'='"$@"' -elif test -n "${BASH_VERSION+set}" && (set -o posix) >/dev/null 2>&1; then - set -o posix -fi -DUALCASE=1; export DUALCASE # for MKS sh - -# Support unset when possible. -if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then - as_unset=unset + setopt NO_GLOB_SUBST else - as_unset=false + case `(set -o) 2>/dev/null` in + *posix*) set -o posix ;; +esac + fi -# Work around bugs in pre-3.0 UWIN ksh. -$as_unset ENV MAIL MAILPATH -PS1='$ ' -PS2='> ' -PS4='+ ' - -# NLS nuisances. -for as_var in \ - LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ - LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ - LC_TELEPHONE LC_TIME -do - if (set +x; test -z "`(eval $as_var=C; export $as_var) 2>&1`"); then - eval $as_var=C; export $as_var - else - $as_unset $as_var - fi -done - -# Required to use basename. -if expr a : '\(a\)' >/dev/null 2>&1; then - as_expr=expr -else - as_expr=false -fi - -if (basename /) >/dev/null 2>&1 && test "X`basename / 2>&1`" = "X/"; then - as_basename=basename -else - as_basename=false -fi -# Name of the executable. -as_me=`$as_basename "$0" || -$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ - X"$0" : 'X\(//\)$' \| \ - X"$0" : 'X\(/\)$' \| \ - . : '\(.\)' 2>/dev/null || -echo X/"$0" | - sed '/^.*\/\([^/][^/]*\)\/*$/{ s//\1/; q; } - /^X\/\(\/\/\)$/{ s//\1/; q; } - /^X\/\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - - -# PATH needs CR, and LINENO needs CR and PATH. +# PATH needs CR # Avoid depending upon Character Ranges. as_cr_letters='abcdefghijklmnopqrstuvwxyz' as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' @@ -3851,126 +5348,198 @@ if test "${PATH_SEPARATOR+set}" != set; then rm -f conf$$.sh fi +# Support unset when possible. +if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then + as_unset=unset +else + as_unset=false +fi - as_lineno_1=$LINENO - as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` - test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" || { - # Find who we are. Look in the path if we contain no path at all - # relative or not. - case $0 in - *[\\/]* ) as_myself=$0 ;; - *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR + +# IFS +# We need space, tab and new line, in precisely that order. Quoting is +# there to prevent editors from complaining about space-tab. +# (If _AS_PATH_WALK were called with IFS unset, it would disable word +# splitting by setting IFS to empty value.) +as_nl=' +' +IFS=" "" $as_nl" + +# Find who we are. Look in the path if we contain no directory separator. +case $0 in + *[\\/]* ) as_myself=$0 ;; + *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR for as_dir in $PATH do IFS=$as_save_IFS test -z "$as_dir" && as_dir=. test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break done +IFS=$as_save_IFS - ;; - esac - # We did not find ourselves, most probably we were run as `sh COMMAND' - # in which case we are not to be found in the path. - if test "x$as_myself" = x; then - as_myself=$0 - fi - if test ! -f "$as_myself"; then - { { echo "$as_me:$LINENO: error: cannot find myself; rerun with an absolute path" >&5 -echo "$as_me: error: cannot find myself; rerun with an absolute path" >&2;} - { (exit 1); exit 1; }; } - fi - case $CONFIG_SHELL in - '') - as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH + ;; +esac +# We did not find ourselves, most probably we were run as `sh COMMAND' +# in which case we are not to be found in the path. +if test "x$as_myself" = x; then + as_myself=$0 +fi +if test ! -f "$as_myself"; then + echo "$as_myself: error: cannot find myself; rerun with an absolute file name" >&2 + { (exit 1); exit 1; } +fi + +# Work around bugs in pre-3.0 UWIN ksh. +for as_var in ENV MAIL MAILPATH +do ($as_unset $as_var) >/dev/null 2>&1 && $as_unset $as_var +done +PS1='$ ' +PS2='> ' +PS4='+ ' + +# NLS nuisances. +for as_var in \ + LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ + LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ + LC_TELEPHONE LC_TIME do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for as_base in sh bash ksh sh5; do - case $as_dir in - /*) - if ("$as_dir/$as_base" -c ' + if (set +x; test -z "`(eval $as_var=C; export $as_var) 2>&1`"); then + eval $as_var=C; export $as_var + else + ($as_unset $as_var) >/dev/null 2>&1 && $as_unset $as_var + fi +done + +# Required to use basename. +if expr a : '\(a\)' >/dev/null 2>&1 && + test "X`expr 00001 : '.*\(...\)'`" = X001; then + as_expr=expr +else + as_expr=false +fi + +if (basename -- /) >/dev/null 2>&1 && test "X`basename -- / 2>&1`" = "X/"; then + as_basename=basename +else + as_basename=false +fi + + +# Name of the executable. +as_me=`$as_basename -- "$0" || +$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)' \| . 2>/dev/null || +echo X/"$0" | + sed '/^.*\/\([^/][^/]*\)\/*$/{ + s//\1/ + q + } + /^X\/\(\/\/\)$/{ + s//\1/ + q + } + /^X\/\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + +# CDPATH. +$as_unset CDPATH + + + as_lineno_1=$LINENO as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" ') 2>/dev/null; then - $as_unset BASH_ENV || test "${BASH_ENV+set}" != set || { BASH_ENV=; export BASH_ENV; } - $as_unset ENV || test "${ENV+set}" != set || { ENV=; export ENV; } - CONFIG_SHELL=$as_dir/$as_base - export CONFIG_SHELL - exec "$CONFIG_SHELL" "$0" ${1+"$@"} - fi;; - esac - done -done -;; - esac + test "x`expr $as_lineno_1 + 1`" = "x$as_lineno_2" || { # Create $as_me.lineno as a copy of $as_myself, but with $LINENO # uniformly replaced by the line number. The first 'sed' inserts a - # line-number line before each line; the second 'sed' does the real - # work. The second script uses 'N' to pair each line-number line - # with the numbered line, and appends trailing '-' during - # substitution so that $LINENO is not a special case at line end. + # line-number line after each line using $LINENO; the second 'sed' + # does the real work. The second script uses 'N' to pair each + # line-number line with the line containing $LINENO, and appends + # trailing '-' during substitution so that $LINENO is not a special + # case at line end. # (Raja R Harinath suggested sed '=', and Paul Eggert wrote the - # second 'sed' script. Blame Lee E. McMahon for sed's syntax. :-) - sed '=' <$as_myself | + # scripts with optimization help from Paolo Bonzini. Blame Lee + # E. McMahon (1931-1989) for sed's syntax. :-) + sed -n ' + p + /[$]LINENO/= + ' <$as_myself | sed ' + s/[$]LINENO.*/&-/ + t lineno + b + :lineno N - s,$,-, - : loop - s,^\(['$as_cr_digits']*\)\(.*\)[$]LINENO\([^'$as_cr_alnum'_]\),\1\2\1\3, + :loop + s/[$]LINENO\([^'$as_cr_alnum'_].*\n\)\(.*\)/\2\1\2/ t loop - s,-$,, - s,^['$as_cr_digits']*\n,, + s/-\n.*// ' >$as_me.lineno && - chmod +x $as_me.lineno || - { { echo "$as_me:$LINENO: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&5 -echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2;} + chmod +x "$as_me.lineno" || + { echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2 { (exit 1); exit 1; }; } # Don't try to exec as it changes $[0], causing all sort of problems # (the dirname of $[0] is not the place where we might find the - # original and so on. Autoconf is especially sensible to this). - . ./$as_me.lineno + # original and so on. Autoconf is especially sensitive to this). + . "./$as_me.lineno" # Exit status is that of the last command. exit } -case `echo "testing\c"; echo 1,2,3`,`echo -n testing; echo 1,2,3` in - *c*,-n*) ECHO_N= ECHO_C=' -' ECHO_T=' ' ;; - *c*,* ) ECHO_N=-n ECHO_C= ECHO_T= ;; - *) ECHO_N= ECHO_C='\c' ECHO_T= ;; +if (as_dir=`dirname -- /` && test "X$as_dir" = X/) >/dev/null 2>&1; then + as_dirname=dirname +else + as_dirname=false +fi + +ECHO_C= ECHO_N= ECHO_T= +case `echo -n x` in +-n*) + case `echo 'x\c'` in + *c*) ECHO_T=' ';; # ECHO_T is single tab character. + *) ECHO_C='\c';; + esac;; +*) + ECHO_N='-n';; esac -if expr a : '\(a\)' >/dev/null 2>&1; then +if expr a : '\(a\)' >/dev/null 2>&1 && + test "X`expr 00001 : '.*\(...\)'`" = X001; then as_expr=expr else as_expr=false fi rm -f conf$$ conf$$.exe conf$$.file +if test -d conf$$.dir; then + rm -f conf$$.dir/conf$$.file +else + rm -f conf$$.dir + mkdir conf$$.dir +fi echo >conf$$.file if ln -s conf$$.file conf$$ 2>/dev/null; then - # We could just check for DJGPP; but this test a) works b) is more generic - # and c) will remain valid once DJGPP supports symlinks (DJGPP 2.04). - if test -f conf$$.exe; then - # Don't use ln at all; we don't have any links + as_ln_s='ln -s' + # ... but there are two gotchas: + # 1) On MSYS, both `ln -s file dir' and `ln file dir' fail. + # 2) DJGPP < 2.04 has no symlinks; `ln -s' creates a wrapper executable. + # In both cases, we have to default to `cp -p'. + ln -s conf$$.file conf$$.dir 2>/dev/null && test ! -f conf$$.exe || as_ln_s='cp -p' - else - as_ln_s='ln -s' - fi elif ln conf$$.file conf$$ 2>/dev/null; then as_ln_s=ln else as_ln_s='cp -p' fi -rm -f conf$$ conf$$.exe conf$$.file +rm -f conf$$ conf$$.exe conf$$.dir/conf$$.file conf$$.file +rmdir conf$$.dir 2>/dev/null if mkdir -p . 2>/dev/null; then as_mkdir_p=: @@ -3979,7 +5548,28 @@ else as_mkdir_p=false fi -as_executable_p="test -f" +if test -x / >/dev/null 2>&1; then + as_test_x='test -x' +else + if ls -dL / >/dev/null 2>&1; then + as_ls_L_option=L + else + as_ls_L_option= + fi + as_test_x=' + eval sh -c '\'' + if test -d "$1"; then + test -d "$1/."; + else + case $1 in + -*)set "./$1";; + esac; + case `ls -ld'$as_ls_L_option' "$1" 2>/dev/null` in + ???[sx]*):;;*)false;;esac;fi + '\'' sh + ' +fi +as_executable_p=$as_test_x # Sed expression to map a string onto a valid CPP name. as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" @@ -3988,31 +5578,14 @@ as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" as_tr_sh="eval sed 'y%*+%pp%;s%[^_$as_cr_alnum]%_%g'" -# IFS -# We need space, tab and new line, in precisely that order. -as_nl=' -' -IFS=" $as_nl" - -# CDPATH. -$as_unset CDPATH - exec 6>&1 -# Open the log real soon, to keep \$[0] and so on meaningful, and to +# Save the log message, to keep $[0] and so on meaningful, and to # report actual input values of CONFIG_FILES etc. instead of their -# values after options handling. Logging --version etc. is OK. -exec 5>>config.log -{ - echo - sed 'h;s/./-/g;s/^.../## /;s/...$/ ##/;p;x;p;x' <<_ASBOX -## Running $as_me. ## -_ASBOX -} >&5 -cat >&5 <<_CSEOF - -This file was extended by $as_me, which was -generated by GNU Autoconf 2.59. Invocation command line was +# values after options handling. +ac_log=" +This file was extended by PCRE $as_me 7.2, which was +generated by GNU Autoconf 2.61. Invocation command line was CONFIG_FILES = $CONFIG_FILES CONFIG_HEADERS = $CONFIG_HEADERS @@ -4020,30 +5593,20 @@ generated by GNU Autoconf 2.59. Invocation command line was CONFIG_COMMANDS = $CONFIG_COMMANDS $ $0 $@ -_CSEOF -echo "on `(hostname || uname -n) 2>/dev/null | sed 1q`" >&5 -echo >&5 +on `(hostname || uname -n) 2>/dev/null | sed 1q` +" + _ACEOF +cat >>$CONFIG_STATUS <<_ACEOF # Files that config.status was made for. -if test -n "$ac_config_files"; then - echo "config_files=\"$ac_config_files\"" >>$CONFIG_STATUS -fi +config_files="$ac_config_files" +config_headers="$ac_config_headers" +config_commands="$ac_config_commands" -if test -n "$ac_config_headers"; then - echo "config_headers=\"$ac_config_headers\"" >>$CONFIG_STATUS -fi - -if test -n "$ac_config_links"; then - echo "config_links=\"$ac_config_links\"" >>$CONFIG_STATUS -fi - -if test -n "$ac_config_commands"; then - echo "config_commands=\"$ac_config_commands\"" >>$CONFIG_STATUS -fi +_ACEOF cat >>$CONFIG_STATUS <<\_ACEOF - ac_cs_usage="\ \`$as_me' instantiates files from templates according to the current configuration. @@ -4051,7 +5614,7 @@ current configuration. Usage: $0 [OPTIONS] [FILE]... -h, --help print this help, then exit - -V, --version print version number, then exit + -V, --version print version number and configuration settings, then exit -q, --quiet do not print progress messages -d, --debug don't remove temporary files --recheck update $as_me by reconfiguring in the same conditions @@ -4066,19 +5629,26 @@ $config_files Configuration headers: $config_headers -Report bugs to ." -_ACEOF +Configuration commands: +$config_commands +Report bugs to ." + +_ACEOF cat >>$CONFIG_STATUS <<_ACEOF ac_cs_version="\\ -config.status -configured by $0, generated by GNU Autoconf 2.59, - with options \\"`echo "$ac_configure_args" | sed 's/[\\""\`\$]/\\\\&/g'`\\" +PCRE config.status 7.2 +configured by $0, generated by GNU Autoconf 2.61, + with options \\"`echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`\\" -Copyright (C) 2003 Free Software Foundation, Inc. +Copyright (C) 2006 Free Software Foundation, Inc. This config.status script is free software; the Free Software Foundation gives unlimited permission to copy, distribute and modify it." -srcdir=$srcdir + +ac_pwd='$ac_pwd' +srcdir='$srcdir' +INSTALL='$INSTALL' +MKDIR_P='$MKDIR_P' _ACEOF cat >>$CONFIG_STATUS <<\_ACEOF @@ -4089,39 +5659,24 @@ while test $# != 0 do case $1 in --*=*) - ac_option=`expr "x$1" : 'x\([^=]*\)='` - ac_optarg=`expr "x$1" : 'x[^=]*=\(.*\)'` + ac_option=`expr "X$1" : 'X\([^=]*\)='` + ac_optarg=`expr "X$1" : 'X[^=]*=\(.*\)'` ac_shift=: ;; - -*) + *) ac_option=$1 ac_optarg=$2 ac_shift=shift ;; - *) # This is not an option, so the user has probably given explicit - # arguments. - ac_option=$1 - ac_need_defaults=false;; esac case $ac_option in # Handling of the options. -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF -recheck | --recheck | --rechec | --reche | --rech | --rec | --re | --r) ac_cs_recheck=: ;; - --version | --vers* | -V ) - echo "$ac_cs_version"; exit 0 ;; - --he | --h) - # Conflict between --help and --header - { { echo "$as_me:$LINENO: error: ambiguous option: $1 -Try \`$0 --help' for more information." >&5 -echo "$as_me: error: ambiguous option: $1 -Try \`$0 --help' for more information." >&2;} - { (exit 1); exit 1; }; };; - --help | --hel | -h ) - echo "$ac_cs_usage"; exit 0 ;; - --debug | --d* | -d ) + --version | --versio | --versi | --vers | --ver | --ve | --v | -V ) + echo "$ac_cs_version"; exit ;; + --debug | --debu | --deb | --de | --d | -d ) debug=: ;; --file | --fil | --fi | --f ) $ac_shift @@ -4131,18 +5686,24 @@ Try \`$0 --help' for more information." >&2;} $ac_shift CONFIG_HEADERS="$CONFIG_HEADERS $ac_optarg" ac_need_defaults=false;; + --he | --h) + # Conflict between --help and --header + { echo "$as_me: error: ambiguous option: $1 +Try \`$0 --help' for more information." >&2 + { (exit 1); exit 1; }; };; + --help | --hel | -h ) + echo "$ac_cs_usage"; exit ;; -q | -quiet | --quiet | --quie | --qui | --qu | --q \ | -silent | --silent | --silen | --sile | --sil | --si | --s) ac_cs_silent=: ;; # This is an error. - -*) { { echo "$as_me:$LINENO: error: unrecognized option: $1 -Try \`$0 --help' for more information." >&5 -echo "$as_me: error: unrecognized option: $1 -Try \`$0 --help' for more information." >&2;} + -*) { echo "$as_me: error: unrecognized option: $1 +Try \`$0 --help' for more information." >&2 { (exit 1); exit 1; }; } ;; - *) ac_config_targets="$ac_config_targets $1" ;; + *) ac_config_targets="$ac_config_targets $1" + ac_need_defaults=false ;; esac shift @@ -4158,29 +5719,53 @@ fi _ACEOF cat >>$CONFIG_STATUS <<_ACEOF if \$ac_cs_recheck; then - echo "running $SHELL $0 " $ac_configure_args \$ac_configure_extra_args " --no-create --no-recursion" >&6 - exec $SHELL $0 $ac_configure_args \$ac_configure_extra_args --no-create --no-recursion + echo "running CONFIG_SHELL=$SHELL $SHELL $0 "$ac_configure_args \$ac_configure_extra_args " --no-create --no-recursion" >&6 + CONFIG_SHELL=$SHELL + export CONFIG_SHELL + exec $SHELL "$0"$ac_configure_args \$ac_configure_extra_args --no-create --no-recursion fi _ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF +exec 5>>config.log +{ + echo + sed 'h;s/./-/g;s/^.../## /;s/...$/ ##/;p;x;p;x' <<_ASBOX +## Running $as_me. ## +_ASBOX + echo "$ac_log" +} >&5 +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF +# +# INIT-COMMANDS +# +AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir" - - +_ACEOF cat >>$CONFIG_STATUS <<\_ACEOF + +# Handling of arguments. for ac_config_target in $ac_config_targets do - case "$ac_config_target" in - # Handling of arguments. - "Makefile" ) CONFIG_FILES="$CONFIG_FILES Makefile" ;; - "config.h" ) CONFIG_HEADERS="$CONFIG_HEADERS config.h" ;; + case $ac_config_target in + "config.h") CONFIG_HEADERS="$CONFIG_HEADERS config.h" ;; + "depfiles") CONFIG_COMMANDS="$CONFIG_COMMANDS depfiles" ;; + "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;; + "pcre-config") CONFIG_FILES="$CONFIG_FILES pcre-config" ;; + "pcre.h") CONFIG_FILES="$CONFIG_FILES pcre.h" ;; + "script-chmod") CONFIG_COMMANDS="$CONFIG_COMMANDS script-chmod" ;; + "delete-old-chartables") CONFIG_COMMANDS="$CONFIG_COMMANDS delete-old-chartables" ;; + *) { { echo "$as_me:$LINENO: error: invalid argument: $ac_config_target" >&5 echo "$as_me: error: invalid argument: $ac_config_target" >&2;} { (exit 1); exit 1; }; };; esac done + # If the user did not use the arguments to specify the items to instantiate, # then the envvar interface is used. Set only those that are not. # We use the long form for the default assignment because of an extremely @@ -4188,328 +5773,465 @@ done if $ac_need_defaults; then test "${CONFIG_FILES+set}" = set || CONFIG_FILES=$config_files test "${CONFIG_HEADERS+set}" = set || CONFIG_HEADERS=$config_headers + test "${CONFIG_COMMANDS+set}" = set || CONFIG_COMMANDS=$config_commands fi # Have a temporary directory for convenience. Make it in the build tree -# simply because there is no reason to put it here, and in addition, +# simply because there is no reason against having it here, and in addition, # creating and moving files from /tmp can sometimes cause problems. -# Create a temporary directory, and hook for its removal unless debugging. +# Hook for its removal unless debugging. +# Note that there is a small window in which the directory will not be cleaned: +# after its creation but before its name has been assigned to `$tmp'. $debug || { - trap 'exit_status=$?; rm -rf $tmp && exit $exit_status' 0 + tmp= + trap 'exit_status=$? + { test -z "$tmp" || test ! -d "$tmp" || rm -fr "$tmp"; } && exit $exit_status +' 0 trap '{ (exit 1); exit 1; }' 1 2 13 15 } - # Create a (secure) tmp directory for tmp files. { - tmp=`(umask 077 && mktemp -d -q "./confstatXXXXXX") 2>/dev/null` && + tmp=`(umask 077 && mktemp -d "./confXXXXXX") 2>/dev/null` && test -n "$tmp" && test -d "$tmp" } || { - tmp=./confstat$$-$RANDOM - (umask 077 && mkdir $tmp) + tmp=./conf$$-$RANDOM + (umask 077 && mkdir "$tmp") } || { echo "$me: cannot create a temporary directory in ." >&2 { (exit 1); exit 1; } } -_ACEOF - -cat >>$CONFIG_STATUS <<_ACEOF - # -# CONFIG_FILES section. +# Set up the sed scripts for CONFIG_FILES section. # # No need to generate the scripts if there are no CONFIG_FILES. # This happens for instance when ./config.status config.h -if test -n "\$CONFIG_FILES"; then - # Protect against being on the right side of a sed subst in config.status. - sed 's/,@/@@/; s/@,/@@/; s/,;t t\$/@;t t/; /@;t t\$/s/[\\\\&,]/\\\\&/g; - s/@@/,@/; s/@@/@,/; s/@;t t\$/,;t t/' >\$tmp/subs.sed <<\\CEOF -s,@SHELL@,$SHELL,;t t -s,@PATH_SEPARATOR@,$PATH_SEPARATOR,;t t -s,@PACKAGE_NAME@,$PACKAGE_NAME,;t t -s,@PACKAGE_TARNAME@,$PACKAGE_TARNAME,;t t -s,@PACKAGE_VERSION@,$PACKAGE_VERSION,;t t -s,@PACKAGE_STRING@,$PACKAGE_STRING,;t t -s,@PACKAGE_BUGREPORT@,$PACKAGE_BUGREPORT,;t t -s,@exec_prefix@,$exec_prefix,;t t -s,@prefix@,$prefix,;t t -s,@program_transform_name@,$program_transform_name,;t t -s,@bindir@,$bindir,;t t -s,@sbindir@,$sbindir,;t t -s,@libexecdir@,$libexecdir,;t t -s,@datadir@,$datadir,;t t -s,@sysconfdir@,$sysconfdir,;t t -s,@sharedstatedir@,$sharedstatedir,;t t -s,@localstatedir@,$localstatedir,;t t -s,@libdir@,$libdir,;t t -s,@includedir@,$includedir,;t t -s,@oldincludedir@,$oldincludedir,;t t -s,@infodir@,$infodir,;t t -s,@mandir@,$mandir,;t t -s,@build_alias@,$build_alias,;t t -s,@host_alias@,$host_alias,;t t -s,@target_alias@,$target_alias,;t t -s,@DEFS@,$DEFS,;t t -s,@ECHO_C@,$ECHO_C,;t t -s,@ECHO_N@,$ECHO_N,;t t -s,@ECHO_T@,$ECHO_T,;t t -s,@LIBS@,$LIBS,;t t -s,@CC@,$CC,;t t -s,@CFLAGS@,$CFLAGS,;t t -s,@LDFLAGS@,$LDFLAGS,;t t -s,@CPPFLAGS@,$CPPFLAGS,;t t -s,@ac_ct_CC@,$ac_ct_CC,;t t -s,@EXEEXT@,$EXEEXT,;t t -s,@OBJEXT@,$OBJEXT,;t t -s,@RANLIB@,$RANLIB,;t t -s,@ac_ct_RANLIB@,$ac_ct_RANLIB,;t t -s,@CPP@,$CPP,;t t -s,@EGREP@,$EGREP,;t t -s,@pcre_have_long_long@,$pcre_have_long_long,;t t -s,@pcre_have_ulong_long@,$pcre_have_ulong_long,;t t -s,@build@,$build,;t t -s,@build_cpu@,$build_cpu,;t t -s,@build_vendor@,$build_vendor,;t t -s,@build_os@,$build_os,;t t -s,@host@,$host,;t t -s,@host_cpu@,$host_cpu,;t t -s,@host_vendor@,$host_vendor,;t t -s,@host_os@,$host_os,;t t -s,@BUILD_EXEEXT@,$BUILD_EXEEXT,;t t -s,@BUILD_OBJEXT@,$BUILD_OBJEXT,;t t -s,@CC_FOR_BUILD@,$CC_FOR_BUILD,;t t -s,@CFLAGS_FOR_BUILD@,$CFLAGS_FOR_BUILD,;t t -s,@CXXLDFLAGS@,$CXXLDFLAGS,;t t -s,@EBCDIC@,$EBCDIC,;t t -s,@HAVE_MEMMOVE@,$HAVE_MEMMOVE,;t t -s,@HAVE_STRERROR@,$HAVE_STRERROR,;t t -s,@LINK_SIZE@,$LINK_SIZE,;t t -s,@MATCH_LIMIT@,$MATCH_LIMIT,;t t -s,@MATCH_LIMIT_RECURSION@,$MATCH_LIMIT_RECURSION,;t t -s,@NEWLINE@,$NEWLINE,;t t -s,@NO_RECURSE@,$NO_RECURSE,;t t -s,@PCRE_LIB_VERSION@,$PCRE_LIB_VERSION,;t t -s,@PCRE_POSIXLIB_VERSION@,$PCRE_POSIXLIB_VERSION,;t t -s,@PCRE_VERSION@,$PCRE_VERSION,;t t -s,@POSIX_MALLOC_THRESHOLD@,$POSIX_MALLOC_THRESHOLD,;t t -s,@UCP@,$UCP,;t t -s,@UTF8@,$UTF8,;t t -s,@POSIX_OBJ@,$POSIX_OBJ,;t t -s,@POSIX_LOBJ@,$POSIX_LOBJ,;t t -s,@POSIX_LIB@,$POSIX_LIB,;t t -s,@LIBOBJS@,$LIBOBJS,;t t -s,@LTLIBOBJS@,$LTLIBOBJS,;t t -CEOF +if test -n "$CONFIG_FILES"; then _ACEOF - cat >>$CONFIG_STATUS <<\_ACEOF - # Split the substitutions into bite-sized pieces for seds with - # small command number limits, like on Digital OSF/1 and HP-UX. - ac_max_sed_lines=48 - ac_sed_frag=1 # Number of current file. - ac_beg=1 # First line for current file. - ac_end=$ac_max_sed_lines # Line after last line for current file. - ac_more_lines=: - ac_sed_cmds= - while $ac_more_lines; do - if test $ac_beg -gt 1; then - sed "1,${ac_beg}d; ${ac_end}q" $tmp/subs.sed >$tmp/subs.frag - else - sed "${ac_end}q" $tmp/subs.sed >$tmp/subs.frag - fi - if test ! -s $tmp/subs.frag; then - ac_more_lines=false - else - # The purpose of the label and of the branching condition is to - # speed up the sed processing (if there are no `@' at all, there - # is no need to browse any of the substitutions). - # These are the two extra sed commands mentioned above. - (echo ':t - /@[a-zA-Z_][a-zA-Z_0-9]*@/!b' && cat $tmp/subs.frag) >$tmp/subs-$ac_sed_frag.sed - if test -z "$ac_sed_cmds"; then - ac_sed_cmds="sed -f $tmp/subs-$ac_sed_frag.sed" - else - ac_sed_cmds="$ac_sed_cmds | sed -f $tmp/subs-$ac_sed_frag.sed" - fi - ac_sed_frag=`expr $ac_sed_frag + 1` - ac_beg=$ac_end - ac_end=`expr $ac_end + $ac_max_sed_lines` - fi - done - if test -z "$ac_sed_cmds"; then - ac_sed_cmds=cat + + +ac_delim='%!_!# ' +for ac_last_try in false false false false false :; do + cat >conf$$subs.sed <<_ACEOF +SHELL!$SHELL$ac_delim +PATH_SEPARATOR!$PATH_SEPARATOR$ac_delim +PACKAGE_NAME!$PACKAGE_NAME$ac_delim +PACKAGE_TARNAME!$PACKAGE_TARNAME$ac_delim +PACKAGE_VERSION!$PACKAGE_VERSION$ac_delim +PACKAGE_STRING!$PACKAGE_STRING$ac_delim +PACKAGE_BUGREPORT!$PACKAGE_BUGREPORT$ac_delim +exec_prefix!$exec_prefix$ac_delim +prefix!$prefix$ac_delim +program_transform_name!$program_transform_name$ac_delim +bindir!$bindir$ac_delim +sbindir!$sbindir$ac_delim +libexecdir!$libexecdir$ac_delim +datarootdir!$datarootdir$ac_delim +datadir!$datadir$ac_delim +sysconfdir!$sysconfdir$ac_delim +sharedstatedir!$sharedstatedir$ac_delim +localstatedir!$localstatedir$ac_delim +includedir!$includedir$ac_delim +oldincludedir!$oldincludedir$ac_delim +docdir!$docdir$ac_delim +infodir!$infodir$ac_delim +htmldir!$htmldir$ac_delim +dvidir!$dvidir$ac_delim +pdfdir!$pdfdir$ac_delim +psdir!$psdir$ac_delim +libdir!$libdir$ac_delim +localedir!$localedir$ac_delim +mandir!$mandir$ac_delim +DEFS!$DEFS$ac_delim +ECHO_C!$ECHO_C$ac_delim +ECHO_N!$ECHO_N$ac_delim +ECHO_T!$ECHO_T$ac_delim +LIBS!$LIBS$ac_delim +build_alias!$build_alias$ac_delim +host_alias!$host_alias$ac_delim +target_alias!$target_alias$ac_delim +INSTALL_PROGRAM!$INSTALL_PROGRAM$ac_delim +INSTALL_SCRIPT!$INSTALL_SCRIPT$ac_delim +INSTALL_DATA!$INSTALL_DATA$ac_delim +am__isrc!$am__isrc$ac_delim +CYGPATH_W!$CYGPATH_W$ac_delim +PACKAGE!$PACKAGE$ac_delim +VERSION!$VERSION$ac_delim +ACLOCAL!$ACLOCAL$ac_delim +AUTOCONF!$AUTOCONF$ac_delim +AUTOMAKE!$AUTOMAKE$ac_delim +AUTOHEADER!$AUTOHEADER$ac_delim +MAKEINFO!$MAKEINFO$ac_delim +install_sh!$install_sh$ac_delim +STRIP!$STRIP$ac_delim +INSTALL_STRIP_PROGRAM!$INSTALL_STRIP_PROGRAM$ac_delim +mkdir_p!$mkdir_p$ac_delim +AWK!$AWK$ac_delim +SET_MAKE!$SET_MAKE$ac_delim +am__leading_dot!$am__leading_dot$ac_delim +AMTAR!$AMTAR$ac_delim +am__tar!$am__tar$ac_delim +am__untar!$am__untar$ac_delim +CC!$CC$ac_delim +CFLAGS!$CFLAGS$ac_delim +LDFLAGS!$LDFLAGS$ac_delim +CPPFLAGS!$CPPFLAGS$ac_delim +ac_ct_CC!$ac_ct_CC$ac_delim +EXEEXT!$EXEEXT$ac_delim +OBJEXT!$OBJEXT$ac_delim +DEPDIR!$DEPDIR$ac_delim +am__include!$am__include$ac_delim +am__quote!$am__quote$ac_delim +AMDEP_TRUE!$AMDEP_TRUE$ac_delim +AMDEP_FALSE!$AMDEP_FALSE$ac_delim +AMDEPBACKSLASH!$AMDEPBACKSLASH$ac_delim +CCDEPMODE!$CCDEPMODE$ac_delim +am__fastdepCC_TRUE!$am__fastdepCC_TRUE$ac_delim +am__fastdepCC_FALSE!$am__fastdepCC_FALSE$ac_delim +RANLIB!$RANLIB$ac_delim +LN_S!$LN_S$ac_delim +PCRE_MAJOR!$PCRE_MAJOR$ac_delim +PCRE_MINOR!$PCRE_MINOR$ac_delim +PCRE_PRERELEASE!$PCRE_PRERELEASE$ac_delim +PCRE_DATE!$PCRE_DATE$ac_delim +CPP!$CPP$ac_delim +GREP!$GREP$ac_delim +EGREP!$EGREP$ac_delim +pcre_have_type_traits!$pcre_have_type_traits$ac_delim +pcre_have_bits_type_traits!$pcre_have_bits_type_traits$ac_delim +WITH_REBUILD_CHARTABLES_TRUE!$WITH_REBUILD_CHARTABLES_TRUE$ac_delim +WITH_REBUILD_CHARTABLES_FALSE!$WITH_REBUILD_CHARTABLES_FALSE$ac_delim +pcre_have_long_long!$pcre_have_long_long$ac_delim +pcre_have_ulong_long!$pcre_have_ulong_long$ac_delim +build!$build$ac_delim +build_cpu!$build_cpu$ac_delim +build_vendor!$build_vendor$ac_delim +build_os!$build_os$ac_delim +host!$host$ac_delim +host_cpu!$host_cpu$ac_delim +host_vendor!$host_vendor$ac_delim +_ACEOF + + if test `sed -n "s/.*$ac_delim\$/X/p" conf$$subs.sed | grep -c X` = 97; then + break + elif $ac_last_try; then + { { echo "$as_me:$LINENO: error: could not make $CONFIG_STATUS" >&5 +echo "$as_me: error: could not make $CONFIG_STATUS" >&2;} + { (exit 1); exit 1; }; } + else + ac_delim="$ac_delim!$ac_delim _$ac_delim!! " fi +done + +ac_eof=`sed -n '/^CEOF[0-9]*$/s/CEOF/0/p' conf$$subs.sed` +if test -n "$ac_eof"; then + ac_eof=`echo "$ac_eof" | sort -nru | sed 1q` + ac_eof=`expr $ac_eof + 1` +fi + +cat >>$CONFIG_STATUS <<_ACEOF +cat >"\$tmp/subs-1.sed" <<\CEOF$ac_eof +/@[a-zA-Z_][a-zA-Z_0-9]*@/!b +_ACEOF +sed ' +s/[,\\&]/\\&/g; s/@/@|#_!!_#|/g +s/^/s,@/; s/!/@,|#_!!_#|/ +:n +t n +s/'"$ac_delim"'$/,g/; t +s/$/\\/; p +N; s/^.*\n//; s/[,\\&]/\\&/g; s/@/@|#_!!_#|/g; b n +' >>$CONFIG_STATUS >$CONFIG_STATUS <<_ACEOF +CEOF$ac_eof +_ACEOF + + +ac_delim='%!_!# ' +for ac_last_try in false false false false false :; do + cat >conf$$subs.sed <<_ACEOF +host_os!$host_os$ac_delim +EXTRA_LIBPCRE_LDFLAGS!$EXTRA_LIBPCRE_LDFLAGS$ac_delim +LIBOBJS!$LIBOBJS$ac_delim +LTLIBOBJS!$LTLIBOBJS$ac_delim +_ACEOF + + if test `sed -n "s/.*$ac_delim\$/X/p" conf$$subs.sed | grep -c X` = 4; then + break + elif $ac_last_try; then + { { echo "$as_me:$LINENO: error: could not make $CONFIG_STATUS" >&5 +echo "$as_me: error: could not make $CONFIG_STATUS" >&2;} + { (exit 1); exit 1; }; } + else + ac_delim="$ac_delim!$ac_delim _$ac_delim!! " + fi +done + +ac_eof=`sed -n '/^CEOF[0-9]*$/s/CEOF/0/p' conf$$subs.sed` +if test -n "$ac_eof"; then + ac_eof=`echo "$ac_eof" | sort -nru | sed 1q` + ac_eof=`expr $ac_eof + 1` +fi + +cat >>$CONFIG_STATUS <<_ACEOF +cat >"\$tmp/subs-2.sed" <<\CEOF$ac_eof +/@[a-zA-Z_][a-zA-Z_0-9]*@/!b end +_ACEOF +sed ' +s/[,\\&]/\\&/g; s/@/@|#_!!_#|/g +s/^/s,@/; s/!/@,|#_!!_#|/ +:n +t n +s/'"$ac_delim"'$/,g/; t +s/$/\\/; p +N; s/^.*\n//; s/[,\\&]/\\&/g; s/@/@|#_!!_#|/g; b n +' >>$CONFIG_STATUS >$CONFIG_STATUS <<_ACEOF +:end +s/|#_!!_#|//g +CEOF$ac_eof +_ACEOF + + +# VPATH may cause trouble with some makes, so we remove $(srcdir), +# ${srcdir} and @srcdir@ from VPATH if srcdir is ".", strip leading and +# trailing colons and then remove the whole line if VPATH becomes empty +# (actually we leave an empty line to preserve line numbers). +if test "x$srcdir" = x.; then + ac_vpsub='/^[ ]*VPATH[ ]*=/{ +s/:*\$(srcdir):*/:/ +s/:*\${srcdir}:*/:/ +s/:*@srcdir@:*/:/ +s/^\([^=]*=[ ]*\):*/\1/ +s/:*$// +s/^[^=]*=[ ]*$// +}' +fi + +cat >>$CONFIG_STATUS <<\_ACEOF fi # test -n "$CONFIG_FILES" -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF -for ac_file in : $CONFIG_FILES; do test "x$ac_file" = x: && continue - # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". - case $ac_file in - - | *:- | *:-:* ) # input from stdin - cat >$tmp/stdin - ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - *:* ) ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - * ) ac_file_in=$ac_file.in ;; + +for ac_tag in :F $CONFIG_FILES :H $CONFIG_HEADERS :C $CONFIG_COMMANDS +do + case $ac_tag in + :[FHLC]) ac_mode=$ac_tag; continue;; + esac + case $ac_mode$ac_tag in + :[FHL]*:*);; + :L* | :C*:*) { { echo "$as_me:$LINENO: error: Invalid tag $ac_tag." >&5 +echo "$as_me: error: Invalid tag $ac_tag." >&2;} + { (exit 1); exit 1; }; };; + :[FH]-) ac_tag=-:-;; + :[FH]*) ac_tag=$ac_tag:$ac_tag.in;; + esac + ac_save_IFS=$IFS + IFS=: + set x $ac_tag + IFS=$ac_save_IFS + shift + ac_file=$1 + shift + + case $ac_mode in + :L) ac_source=$1;; + :[FH]) + ac_file_inputs= + for ac_f + do + case $ac_f in + -) ac_f="$tmp/stdin";; + *) # Look for the file first in the build tree, then in the source tree + # (if the path is not absolute). The absolute path cannot be DOS-style, + # because $ac_f cannot contain `:'. + test -f "$ac_f" || + case $ac_f in + [\\/$]*) false;; + *) test -f "$srcdir/$ac_f" && ac_f="$srcdir/$ac_f";; + esac || + { { echo "$as_me:$LINENO: error: cannot find input file: $ac_f" >&5 +echo "$as_me: error: cannot find input file: $ac_f" >&2;} + { (exit 1); exit 1; }; };; + esac + ac_file_inputs="$ac_file_inputs $ac_f" + done + + # Let's still pretend it is `configure' which instantiates (i.e., don't + # use $as_me), people would be surprised to read: + # /* config.h. Generated by config.status. */ + configure_input="Generated from "`IFS=: + echo $* | sed 's|^[^:]*/||;s|:[^:]*/|, |g'`" by configure." + if test x"$ac_file" != x-; then + configure_input="$ac_file. $configure_input" + { echo "$as_me:$LINENO: creating $ac_file" >&5 +echo "$as_me: creating $ac_file" >&6;} + fi + + case $ac_tag in + *:-:* | *:-) cat >"$tmp/stdin";; + esac + ;; esac - # Compute @srcdir@, @top_srcdir@, and @INSTALL@ for subdirectories. - ac_dir=`(dirname "$ac_file") 2>/dev/null || + ac_dir=`$as_dirname -- "$ac_file" || $as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ X"$ac_file" : 'X\(//\)[^/]' \| \ X"$ac_file" : 'X\(//\)$' \| \ - X"$ac_file" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || + X"$ac_file" : 'X\(/\)' \| . 2>/dev/null || echo X"$ac_file" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - { if $as_mkdir_p; then - mkdir -p "$ac_dir" - else - as_dir="$ac_dir" + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + { as_dir="$ac_dir" + case $as_dir in #( + -*) as_dir=./$as_dir;; + esac + test -d "$as_dir" || { $as_mkdir_p && mkdir -p "$as_dir"; } || { as_dirs= - while test ! -d "$as_dir"; do - as_dirs="$as_dir $as_dirs" - as_dir=`(dirname "$as_dir") 2>/dev/null || + while :; do + case $as_dir in #( + *\'*) as_qdir=`echo "$as_dir" | sed "s/'/'\\\\\\\\''/g"`;; #( + *) as_qdir=$as_dir;; + esac + as_dirs="'$as_qdir' $as_dirs" + as_dir=`$as_dirname -- "$as_dir" || $as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ X"$as_dir" : 'X\(//\)[^/]' \| \ X"$as_dir" : 'X\(//\)$' \| \ - X"$as_dir" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || + X"$as_dir" : 'X\(/\)' \| . 2>/dev/null || echo X"$as_dir" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + test -d "$as_dir" && break done - test ! -n "$as_dirs" || mkdir $as_dirs - fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 -echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} + test -z "$as_dirs" || eval "mkdir $as_dirs" + } || test -d "$as_dir" || { { echo "$as_me:$LINENO: error: cannot create directory $as_dir" >&5 +echo "$as_me: error: cannot create directory $as_dir" >&2;} { (exit 1); exit 1; }; }; } - ac_builddir=. -if test "$ac_dir" != .; then +case "$ac_dir" in +.) ac_dir_suffix= ac_top_builddir_sub=. ac_top_build_prefix= ;; +*) ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` - # A "../" for each directory in $ac_dir_suffix. - ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` -else - ac_dir_suffix= ac_top_builddir= -fi + # A ".." for each directory in $ac_dir_suffix. + ac_top_builddir_sub=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,/..,g;s,/,,'` + case $ac_top_builddir_sub in + "") ac_top_builddir_sub=. ac_top_build_prefix= ;; + *) ac_top_build_prefix=$ac_top_builddir_sub/ ;; + esac ;; +esac +ac_abs_top_builddir=$ac_pwd +ac_abs_builddir=$ac_pwd$ac_dir_suffix +# for backward compatibility: +ac_top_builddir=$ac_top_build_prefix case $srcdir in - .) # No --srcdir option. We are building in place. + .) # We are building in place. ac_srcdir=. - if test -z "$ac_top_builddir"; then - ac_top_srcdir=. - else - ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` - fi ;; - [\\/]* | ?:[\\/]* ) # Absolute path. + ac_top_srcdir=$ac_top_builddir_sub + ac_abs_top_srcdir=$ac_pwd ;; + [\\/]* | ?:[\\/]* ) # Absolute name. ac_srcdir=$srcdir$ac_dir_suffix; - ac_top_srcdir=$srcdir ;; - *) # Relative path. - ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix - ac_top_srcdir=$ac_top_builddir$srcdir ;; -esac - -# Do not use `cd foo && pwd` to compute absolute paths, because -# the directories may not exist. -case `pwd` in -.) ac_abs_builddir="$ac_dir";; -*) - case "$ac_dir" in - .) ac_abs_builddir=`pwd`;; - [\\/]* | ?:[\\/]* ) ac_abs_builddir="$ac_dir";; - *) ac_abs_builddir=`pwd`/"$ac_dir";; - esac;; -esac -case $ac_abs_builddir in -.) ac_abs_top_builddir=${ac_top_builddir}.;; -*) - case ${ac_top_builddir}. in - .) ac_abs_top_builddir=$ac_abs_builddir;; - [\\/]* | ?:[\\/]* ) ac_abs_top_builddir=${ac_top_builddir}.;; - *) ac_abs_top_builddir=$ac_abs_builddir/${ac_top_builddir}.;; - esac;; -esac -case $ac_abs_builddir in -.) ac_abs_srcdir=$ac_srcdir;; -*) - case $ac_srcdir in - .) ac_abs_srcdir=$ac_abs_builddir;; - [\\/]* | ?:[\\/]* ) ac_abs_srcdir=$ac_srcdir;; - *) ac_abs_srcdir=$ac_abs_builddir/$ac_srcdir;; - esac;; -esac -case $ac_abs_builddir in -.) ac_abs_top_srcdir=$ac_top_srcdir;; -*) - case $ac_top_srcdir in - .) ac_abs_top_srcdir=$ac_abs_builddir;; - [\\/]* | ?:[\\/]* ) ac_abs_top_srcdir=$ac_top_srcdir;; - *) ac_abs_top_srcdir=$ac_abs_builddir/$ac_top_srcdir;; - esac;; + ac_top_srcdir=$srcdir + ac_abs_top_srcdir=$srcdir ;; + *) # Relative name. + ac_srcdir=$ac_top_build_prefix$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_build_prefix$srcdir + ac_abs_top_srcdir=$ac_pwd/$srcdir ;; esac +ac_abs_srcdir=$ac_abs_top_srcdir$ac_dir_suffix + case $ac_mode in + :F) + # + # CONFIG_FILE + # - if test x"$ac_file" != x-; then - { echo "$as_me:$LINENO: creating $ac_file" >&5 -echo "$as_me: creating $ac_file" >&6;} - rm -f "$ac_file" - fi - # Let's still pretend it is `configure' which instantiates (i.e., don't - # use $as_me), people would be surprised to read: - # /* config.h. Generated by config.status. */ - if test x"$ac_file" = x-; then - configure_input= - else - configure_input="$ac_file. " - fi - configure_input=$configure_input"Generated from `echo $ac_file_in | - sed 's,.*/,,'` by configure." - - # First look for the input files in the build tree, otherwise in the - # src tree. - ac_file_inputs=`IFS=: - for f in $ac_file_in; do - case $f in - -) echo $tmp/stdin ;; - [\\/$]*) - # Absolute (can't be DOS-style, as IFS=:) - test -f "$f" || { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - echo "$f";; - *) # Relative - if test -f "$f"; then - # Build tree - echo "$f" - elif test -f "$srcdir/$f"; then - # Source tree - echo "$srcdir/$f" - else - # /dev/null tree - { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - fi;; - esac - done` || { (exit 1); exit 1; } + case $INSTALL in + [\\/$]* | ?:[\\/]* ) ac_INSTALL=$INSTALL ;; + *) ac_INSTALL=$ac_top_build_prefix$INSTALL ;; + esac + ac_MKDIR_P=$MKDIR_P + case $MKDIR_P in + [\\/$]* | ?:[\\/]* ) ;; + */*) ac_MKDIR_P=$ac_top_build_prefix$MKDIR_P ;; + esac _ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF +# If the template does not know about datarootdir, expand it. +# FIXME: This hack should be removed a few years after 2.60. +ac_datarootdir_hack=; ac_datarootdir_seen= + +case `sed -n '/datarootdir/ { + p + q +} +/@datadir@/p +/@docdir@/p +/@infodir@/p +/@localedir@/p +/@mandir@/p +' $ac_file_inputs` in +*datarootdir*) ac_datarootdir_seen=yes;; +*@datadir@*|*@docdir@*|*@infodir@*|*@localedir@*|*@mandir@*) + { echo "$as_me:$LINENO: WARNING: $ac_file_inputs seems to ignore the --datarootdir setting" >&5 +echo "$as_me: WARNING: $ac_file_inputs seems to ignore the --datarootdir setting" >&2;} +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF + ac_datarootdir_hack=' + s&@datadir@&$datadir&g + s&@docdir@&$docdir&g + s&@infodir@&$infodir&g + s&@localedir@&$localedir&g + s&@mandir@&$mandir&g + s&\\\${datarootdir}&$datarootdir&g' ;; +esac +_ACEOF + +# Neutralize VPATH when `$srcdir' = `.'. +# Shell code in configure.ac might set extrasub. +# FIXME: do we really want to maintain this feature? cat >>$CONFIG_STATUS <<_ACEOF sed "$ac_vpsub $extrasub @@ -4517,251 +6239,303 @@ _ACEOF cat >>$CONFIG_STATUS <<\_ACEOF :t /@[a-zA-Z_][a-zA-Z_0-9]*@/!b -s,@configure_input@,$configure_input,;t t -s,@srcdir@,$ac_srcdir,;t t -s,@abs_srcdir@,$ac_abs_srcdir,;t t -s,@top_srcdir@,$ac_top_srcdir,;t t -s,@abs_top_srcdir@,$ac_abs_top_srcdir,;t t -s,@builddir@,$ac_builddir,;t t -s,@abs_builddir@,$ac_abs_builddir,;t t -s,@top_builddir@,$ac_top_builddir,;t t -s,@abs_top_builddir@,$ac_abs_top_builddir,;t t -" $ac_file_inputs | (eval "$ac_sed_cmds") >$tmp/out - rm -f $tmp/stdin - if test x"$ac_file" != x-; then - mv $tmp/out $ac_file - else - cat $tmp/out - rm -f $tmp/out - fi +s&@configure_input@&$configure_input&;t t +s&@top_builddir@&$ac_top_builddir_sub&;t t +s&@srcdir@&$ac_srcdir&;t t +s&@abs_srcdir@&$ac_abs_srcdir&;t t +s&@top_srcdir@&$ac_top_srcdir&;t t +s&@abs_top_srcdir@&$ac_abs_top_srcdir&;t t +s&@builddir@&$ac_builddir&;t t +s&@abs_builddir@&$ac_abs_builddir&;t t +s&@abs_top_builddir@&$ac_abs_top_builddir&;t t +s&@INSTALL@&$ac_INSTALL&;t t +s&@MKDIR_P@&$ac_MKDIR_P&;t t +$ac_datarootdir_hack +" $ac_file_inputs | sed -f "$tmp/subs-1.sed" | sed -f "$tmp/subs-2.sed" >$tmp/out -done -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF +test -z "$ac_datarootdir_hack$ac_datarootdir_seen" && + { ac_out=`sed -n '/\${datarootdir}/p' "$tmp/out"`; test -n "$ac_out"; } && + { ac_out=`sed -n '/^[ ]*datarootdir[ ]*:*=/p' "$tmp/out"`; test -z "$ac_out"; } && + { echo "$as_me:$LINENO: WARNING: $ac_file contains a reference to the variable \`datarootdir' +which seems to be undefined. Please make sure it is defined." >&5 +echo "$as_me: WARNING: $ac_file contains a reference to the variable \`datarootdir' +which seems to be undefined. Please make sure it is defined." >&2;} -# -# CONFIG_HEADER section. -# - -# These sed commands are passed to sed as "A NAME B NAME C VALUE D", where -# NAME is the cpp macro being defined and VALUE is the value it is being given. -# -# ac_d sets the value in "#define NAME VALUE" lines. -ac_dA='s,^\([ ]*\)#\([ ]*define[ ][ ]*\)' -ac_dB='[ ].*$,\1#\2' -ac_dC=' ' -ac_dD=',;t' -# ac_u turns "#undef NAME" without trailing blanks into "#define NAME VALUE". -ac_uA='s,^\([ ]*\)#\([ ]*\)undef\([ ][ ]*\)' -ac_uB='$,\1#\2define\3' -ac_uC=' ' -ac_uD=',;t' - -for ac_file in : $CONFIG_HEADERS; do test "x$ac_file" = x: && continue - # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". + rm -f "$tmp/stdin" case $ac_file in - - | *:- | *:-:* ) # input from stdin - cat >$tmp/stdin - ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - *:* ) ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - * ) ac_file_in=$ac_file.in ;; + -) cat "$tmp/out"; rm -f "$tmp/out";; + *) rm -f "$ac_file"; mv "$tmp/out" $ac_file;; esac - - test x"$ac_file" != x- && { echo "$as_me:$LINENO: creating $ac_file" >&5 -echo "$as_me: creating $ac_file" >&6;} - - # First look for the input files in the build tree, otherwise in the - # src tree. - ac_file_inputs=`IFS=: - for f in $ac_file_in; do - case $f in - -) echo $tmp/stdin ;; - [\\/$]*) - # Absolute (can't be DOS-style, as IFS=:) - test -f "$f" || { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - # Do quote $f, to prevent DOS paths from being IFS'd. - echo "$f";; - *) # Relative - if test -f "$f"; then - # Build tree - echo "$f" - elif test -f "$srcdir/$f"; then - # Source tree - echo "$srcdir/$f" - else - # /dev/null tree - { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - fi;; - esac - done` || { (exit 1); exit 1; } - # Remove the trailing spaces. - sed 's/[ ]*$//' $ac_file_inputs >$tmp/in - + ;; + :H) + # + # CONFIG_HEADER + # _ACEOF -# Transform confdefs.h into two sed scripts, `conftest.defines' and -# `conftest.undefs', that substitutes the proper values into -# config.h.in to produce config.h. The first handles `#define' -# templates, and the second `#undef' templates. -# And first: Protect against being on the right side of a sed subst in -# config.status. Protect against being in an unquoted here document -# in config.status. -rm -f conftest.defines conftest.undefs -# Using a here document instead of a string reduces the quoting nightmare. -# Putting comments in sed scripts is not portable. -# -# `end' is used to avoid that the second main sed command (meant for -# 0-ary CPP macros) applies to n-ary macro definitions. -# See the Autoconf documentation for `clear'. -cat >confdef2sed.sed <<\_ACEOF -s/[\\&,]/\\&/g -s,[\\$`],\\&,g -t clear -: clear -s,^[ ]*#[ ]*define[ ][ ]*\([^ (][^ (]*\)\(([^)]*)\)[ ]*\(.*\)$,${ac_dA}\1${ac_dB}\1\2${ac_dC}\3${ac_dD},gp -t end -s,^[ ]*#[ ]*define[ ][ ]*\([^ ][^ ]*\)[ ]*\(.*\)$,${ac_dA}\1${ac_dB}\1${ac_dC}\2${ac_dD},gp -: end -_ACEOF -# If some macros were called several times there might be several times -# the same #defines, which is useless. Nevertheless, we may not want to -# sort them, since we want the *last* AC-DEFINE to be honored. -uniq confdefs.h | sed -n -f confdef2sed.sed >conftest.defines -sed 's/ac_d/ac_u/g' conftest.defines >conftest.undefs -rm -f confdef2sed.sed +# Transform confdefs.h into a sed script `conftest.defines', that +# substitutes the proper values into config.h.in to produce config.h. +rm -f conftest.defines conftest.tail +# First, append a space to every undef/define line, to ease matching. +echo 's/$/ /' >conftest.defines +# Then, protect against being on the right side of a sed subst, or in +# an unquoted here document, in config.status. If some macros were +# called several times there might be several #defines for the same +# symbol, which is useless. But do not sort them, since the last +# AC_DEFINE must be honored. +ac_word_re=[_$as_cr_Letters][_$as_cr_alnum]* +# These sed commands are passed to sed as "A NAME B PARAMS C VALUE D", where +# NAME is the cpp macro being defined, VALUE is the value it is being given. +# PARAMS is the parameter list in the macro definition--in most cases, it's +# just an empty string. +ac_dA='s,^\\([ #]*\\)[^ ]*\\([ ]*' +ac_dB='\\)[ (].*,\\1define\\2' +ac_dC=' ' +ac_dD=' ,' -# This sed command replaces #undef with comments. This is necessary, for +uniq confdefs.h | + sed -n ' + t rset + :rset + s/^[ ]*#[ ]*define[ ][ ]*// + t ok + d + :ok + s/[\\&,]/\\&/g + s/^\('"$ac_word_re"'\)\(([^()]*)\)[ ]*\(.*\)/ '"$ac_dA"'\1'"$ac_dB"'\2'"${ac_dC}"'\3'"$ac_dD"'/p + s/^\('"$ac_word_re"'\)[ ]*\(.*\)/'"$ac_dA"'\1'"$ac_dB$ac_dC"'\2'"$ac_dD"'/p + ' >>conftest.defines + +# Remove the space that was appended to ease matching. +# Then replace #undef with comments. This is necessary, for # example, in the case of _POSIX_SOURCE, which is predefined and required # on some systems where configure will not decide to define it. -cat >>conftest.undefs <<\_ACEOF -s,^[ ]*#[ ]*undef[ ][ ]*[a-zA-Z_][a-zA-Z_0-9]*,/* & */, -_ACEOF +# (The regexp can be short, since the line contains either #define or #undef.) +echo 's/ $// +s,^[ #]*u.*,/* & */,' >>conftest.defines -# Break up conftest.defines because some shells have a limit on the size -# of here documents, and old seds have small limits too (100 cmds). -echo ' # Handle all the #define templates only if necessary.' >>$CONFIG_STATUS -echo ' if grep "^[ ]*#[ ]*define" $tmp/in >/dev/null; then' >>$CONFIG_STATUS -echo ' # If there are no defines, we may have an empty if/fi' >>$CONFIG_STATUS -echo ' :' >>$CONFIG_STATUS -rm -f conftest.tail -while grep . conftest.defines >/dev/null +# Break up conftest.defines: +ac_max_sed_lines=50 + +# First sed command is: sed -f defines.sed $ac_file_inputs >"$tmp/out1" +# Second one is: sed -f defines.sed "$tmp/out1" >"$tmp/out2" +# Third one will be: sed -f defines.sed "$tmp/out2" >"$tmp/out1" +# et cetera. +ac_in='$ac_file_inputs' +ac_out='"$tmp/out1"' +ac_nxt='"$tmp/out2"' + +while : do - # Write a limited-size here document to $tmp/defines.sed. - echo ' cat >$tmp/defines.sed <>$CONFIG_STATUS - # Speed up: don't consider the non `#define' lines. - echo '/^[ ]*#[ ]*define/!b' >>$CONFIG_STATUS - # Work around the forget-to-reset-the-flag bug. - echo 't clr' >>$CONFIG_STATUS - echo ': clr' >>$CONFIG_STATUS - sed ${ac_max_here_lines}q conftest.defines >>$CONFIG_STATUS + # Write a here document: + cat >>$CONFIG_STATUS <<_ACEOF + # First, check the format of the line: + cat >"\$tmp/defines.sed" <<\\CEOF +/^[ ]*#[ ]*undef[ ][ ]*$ac_word_re[ ]*\$/b def +/^[ ]*#[ ]*define[ ][ ]*$ac_word_re[( ]/b def +b +:def +_ACEOF + sed ${ac_max_sed_lines}q conftest.defines >>$CONFIG_STATUS echo 'CEOF - sed -f $tmp/defines.sed $tmp/in >$tmp/out - rm -f $tmp/in - mv $tmp/out $tmp/in -' >>$CONFIG_STATUS - sed 1,${ac_max_here_lines}d conftest.defines >conftest.tail + sed -f "$tmp/defines.sed"' "$ac_in >$ac_out" >>$CONFIG_STATUS + ac_in=$ac_out; ac_out=$ac_nxt; ac_nxt=$ac_in + sed 1,${ac_max_sed_lines}d conftest.defines >conftest.tail + grep . conftest.tail >/dev/null || break rm -f conftest.defines mv conftest.tail conftest.defines done -rm -f conftest.defines -echo ' fi # grep' >>$CONFIG_STATUS -echo >>$CONFIG_STATUS - -# Break up conftest.undefs because some shells have a limit on the size -# of here documents, and old seds have small limits too (100 cmds). -echo ' # Handle all the #undef templates' >>$CONFIG_STATUS -rm -f conftest.tail -while grep . conftest.undefs >/dev/null -do - # Write a limited-size here document to $tmp/undefs.sed. - echo ' cat >$tmp/undefs.sed <>$CONFIG_STATUS - # Speed up: don't consider the non `#undef' - echo '/^[ ]*#[ ]*undef/!b' >>$CONFIG_STATUS - # Work around the forget-to-reset-the-flag bug. - echo 't clr' >>$CONFIG_STATUS - echo ': clr' >>$CONFIG_STATUS - sed ${ac_max_here_lines}q conftest.undefs >>$CONFIG_STATUS - echo 'CEOF - sed -f $tmp/undefs.sed $tmp/in >$tmp/out - rm -f $tmp/in - mv $tmp/out $tmp/in -' >>$CONFIG_STATUS - sed 1,${ac_max_here_lines}d conftest.undefs >conftest.tail - rm -f conftest.undefs - mv conftest.tail conftest.undefs -done -rm -f conftest.undefs +rm -f conftest.defines conftest.tail +echo "ac_result=$ac_in" >>$CONFIG_STATUS cat >>$CONFIG_STATUS <<\_ACEOF - # Let's still pretend it is `configure' which instantiates (i.e., don't - # use $as_me), people would be surprised to read: - # /* config.h. Generated by config.status. */ - if test x"$ac_file" = x-; then - echo "/* Generated by configure. */" >$tmp/config.h - else - echo "/* $ac_file. Generated by configure. */" >$tmp/config.h - fi - cat $tmp/in >>$tmp/config.h - rm -f $tmp/in if test x"$ac_file" != x-; then - if diff $ac_file $tmp/config.h >/dev/null 2>&1; then + echo "/* $configure_input */" >"$tmp/config.h" + cat "$ac_result" >>"$tmp/config.h" + if diff $ac_file "$tmp/config.h" >/dev/null 2>&1; then { echo "$as_me:$LINENO: $ac_file is unchanged" >&5 echo "$as_me: $ac_file is unchanged" >&6;} else - ac_dir=`(dirname "$ac_file") 2>/dev/null || -$as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$ac_file" : 'X\(//\)[^/]' \| \ - X"$ac_file" : 'X\(//\)$' \| \ - X"$ac_file" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$ac_file" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - { if $as_mkdir_p; then - mkdir -p "$ac_dir" + rm -f $ac_file + mv "$tmp/config.h" $ac_file + fi else - as_dir="$ac_dir" + echo "/* $configure_input */" + cat "$ac_result" + fi + rm -f "$tmp/out12" +# Compute $ac_file's index in $config_headers. +_am_stamp_count=1 +for _am_header in $config_headers :; do + case $_am_header in + $ac_file | $ac_file:* ) + break ;; + * ) + _am_stamp_count=`expr $_am_stamp_count + 1` ;; + esac +done +echo "timestamp for $ac_file" >`$as_dirname -- $ac_file || +$as_expr X$ac_file : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X$ac_file : 'X\(//\)[^/]' \| \ + X$ac_file : 'X\(//\)$' \| \ + X$ac_file : 'X\(/\)' \| . 2>/dev/null || +echo X$ac_file | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'`/stamp-h$_am_stamp_count + ;; + + :C) { echo "$as_me:$LINENO: executing $ac_file commands" >&5 +echo "$as_me: executing $ac_file commands" >&6;} + ;; + esac + + + case $ac_file$ac_mode in + "depfiles":C) test x"$AMDEP_TRUE" != x"" || for mf in $CONFIG_FILES; do + # Strip MF so we end up with the name of the file. + mf=`echo "$mf" | sed -e 's/:.*$//'` + # Check whether this is an Automake generated Makefile or not. + # We used to match only the files named `Makefile.in', but + # some people rename them; so instead we look at the file content. + # Grep'ing the first line is not enough: some people post-process + # each Makefile.in and add a new line on top of each file to say so. + # Grep'ing the whole file is not good either: AIX grep has a line + # limit of 2048, but all sed's we know have understand at least 4000. + if sed 10q "$mf" | grep '^#.*generated by automake' > /dev/null 2>&1; then + dirpart=`$as_dirname -- "$mf" || +$as_expr X"$mf" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$mf" : 'X\(//\)[^/]' \| \ + X"$mf" : 'X\(//\)$' \| \ + X"$mf" : 'X\(/\)' \| . 2>/dev/null || +echo X"$mf" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + else + continue + fi + # Extract the definition of DEPDIR, am__include, and am__quote + # from the Makefile without running `make'. + DEPDIR=`sed -n 's/^DEPDIR = //p' < "$mf"` + test -z "$DEPDIR" && continue + am__include=`sed -n 's/^am__include = //p' < "$mf"` + test -z "am__include" && continue + am__quote=`sed -n 's/^am__quote = //p' < "$mf"` + # When using ansi2knr, U may be empty or an underscore; expand it + U=`sed -n 's/^U = //p' < "$mf"` + # Find all dependency output files, they are included files with + # $(DEPDIR) in their names. We invoke sed twice because it is the + # simplest approach to changing $(DEPDIR) to its actual value in the + # expansion. + for file in `sed -n " + s/^$am__include $am__quote\(.*(DEPDIR).*\)$am__quote"'$/\1/p' <"$mf" | \ + sed -e 's/\$(DEPDIR)/'"$DEPDIR"'/g' -e 's/\$U/'"$U"'/g'`; do + # Make sure the directory exists. + test -f "$dirpart/$file" && continue + fdir=`$as_dirname -- "$file" || +$as_expr X"$file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$file" : 'X\(//\)[^/]' \| \ + X"$file" : 'X\(//\)$' \| \ + X"$file" : 'X\(/\)' \| . 2>/dev/null || +echo X"$file" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + { as_dir=$dirpart/$fdir + case $as_dir in #( + -*) as_dir=./$as_dir;; + esac + test -d "$as_dir" || { $as_mkdir_p && mkdir -p "$as_dir"; } || { as_dirs= - while test ! -d "$as_dir"; do - as_dirs="$as_dir $as_dirs" - as_dir=`(dirname "$as_dir") 2>/dev/null || + while :; do + case $as_dir in #( + *\'*) as_qdir=`echo "$as_dir" | sed "s/'/'\\\\\\\\''/g"`;; #( + *) as_qdir=$as_dir;; + esac + as_dirs="'$as_qdir' $as_dirs" + as_dir=`$as_dirname -- "$as_dir" || $as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ X"$as_dir" : 'X\(//\)[^/]' \| \ X"$as_dir" : 'X\(//\)$' \| \ - X"$as_dir" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || + X"$as_dir" : 'X\(/\)' \| . 2>/dev/null || echo X"$as_dir" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + test -d "$as_dir" && break done - test ! -n "$as_dirs" || mkdir $as_dirs - fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 -echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} + test -z "$as_dirs" || eval "mkdir $as_dirs" + } || test -d "$as_dir" || { { echo "$as_me:$LINENO: error: cannot create directory $as_dir" >&5 +echo "$as_me: error: cannot create directory $as_dir" >&2;} { (exit 1); exit 1; }; }; } - - rm -f $ac_file - mv $tmp/config.h $ac_file - fi - else - cat $tmp/config.h - rm -f $tmp/config.h - fi + # echo "creating $dirpart/$file" + echo '# dummy' > "$dirpart/$file" + done done -_ACEOF + ;; + "script-chmod":C) chmod a+x pcre-config ;; + "delete-old-chartables":C) rm -f pcre_chartables.c ;; + + esac +done # for ac_tag -cat >>$CONFIG_STATUS <<\_ACEOF { (exit 0); exit 0; } _ACEOF @@ -4790,3 +6564,4 @@ if test "$no_create" != yes; then $ac_cs_success || { (exit 1); exit 1; } fi + diff --git a/libpcre/configure.ac b/libpcre/configure.ac index 240e78432..22b529848 100644 --- a/libpcre/configure.ac +++ b/libpcre/configure.ac @@ -1,229 +1,393 @@ dnl Process this file with autoconf to produce a configure script. -dnl This has been stripped down a bit by fyodor@insecure.org for -dnl inclusion in Nmap (removed libtool and dynamic library stuff) +dnl NOTE FOR MAINTAINERS: Do not use major or minor version numbers with +dnl leading zeros, because they may be treated as octal constants. The +dnl PCRE_PRERELEASE feature is for identifying release candidates. It might +dnl be defined as -RC2, for example. For real releases, it should be defined +dnl empty. -dnl This configure.in file has been hacked around quite a lot as a result of -dnl patches that various people have sent to me (PH). Sometimes the information -dnl I get is contradictory. I've tried to put in comments that explain things, -dnl but in some cases the information is second-hand and I have no way of -dnl verifying it. I am not an autoconf or libtool expert! - -dnl This is required at the start; the name is the name of a file -dnl it should be seeing, to verify it is in the same directory. - -AC_INIT(dftables.c) -AC_CONFIG_SRCDIR([pcre.h]) - -dnl A safety precaution +m4_define(pcre_major, [7]) +m4_define(pcre_minor, [2]) +m4_define(pcre_prerelease, []) +m4_define(pcre_date, [2007-06-19]) AC_PREREQ(2.57) +AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre) +AC_CONFIG_SRCDIR([pcre.h.in]) +AM_INIT_AUTOMAKE([dist-bzip2 dist-zip]) +AC_CONFIG_HEADERS(config.h) -dnl Arrange to build config.h from config.h.in. -dnl Manual says this macro should come right after AC_INIT. -AC_CONFIG_HEADER(config.h) +# The default CFLAGS and CXXFLAGS in Autoconf are "-g -O2" for gcc and just +# "-g" for any other compiler. There doesn't seem to be a standard way of +# getting rid of the -g (which I don't think is needed for a production +# library). This fudge seems to achieve the necessary. First, we remember the +# externally set values of CFLAGS and CXXFLAGS. Then call the AC_PROG_CC and +# AC_PROG_CXX macros to find the compilers - if CFLAGS and CXXFLAGS are not +# set, they will be set to Autoconf's defaults. Afterwards, if the original +# values were not set, remove the -g from the Autoconf defaults. +# (PH 02-May-07) -dnl Default values for miscellaneous macros - -POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 - -dnl Provide versioning information for libtool shared libraries that -dnl are built by default on Unix systems. - -PCRE_LIB_VERSION=0:1:0 -PCRE_POSIXLIB_VERSION=0:0:0 - -dnl Find the PCRE version from the pcre.h file. The PCRE_VERSION variable is -dnl substituted in pcre-config.in. - -PCRE_MAJOR=`grep '#define PCRE_MAJOR' ${srcdir}/pcre.h | cut -c 29-` -PCRE_MINOR=`grep '#define PCRE_MINOR' ${srcdir}/pcre.h | cut -c 29-` -PCRE_PRERELEASE=`grep '#define PCRE_PRERELEASE' ${srcdir}/pcre.h | cut -c 29-` -PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR}${PCRE_PRERELEASE} - -dnl Checks for programs. +remember_set_CFLAGS="$CFLAGS" AC_PROG_CC - AC_PROG_RANLIB -dnl We need to find a compiler for compiling a program to run on the local host -dnl while building. It needs to be different from CC when cross-compiling. -dnl There is a macro called AC_PROG_CC_FOR_BUILD in the GNU archive for -dnl figuring this out automatically. Unfortunately, it does not work with the -dnl latest versions of autoconf. So for the moment, we just default to the -dnl same values as the "main" compiler. People who are cross-compiling will -dnl just have to adjust the Makefile by hand or set these values when they -dnl run "configure". +if test "x$remember_set_CFLAGS" = "x" +then + if test "$CFLAGS" = "-g -O2" + then + CFLAGS="-O2" + elif test "$CFLAGS" = "-g" + then + CFLAGS="" + fi +fi -CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} -CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} -CPPFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CPPFLAGS)'} -BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} -BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} +AC_PROG_INSTALL +AC_PROG_LN_S -dnl Checks for header files. +PCRE_MAJOR="pcre_major" +PCRE_MINOR="pcre_minor" +PCRE_PRERELEASE="pcre_prerelease" +PCRE_DATE="pcre_date" +AC_SUBST(PCRE_MAJOR) +AC_SUBST(PCRE_MINOR) +AC_SUBST(PCRE_PRERELEASE) +AC_SUBST(PCRE_DATE) + +# Set a more sensible default value for $(htmldir). +if test "x$htmldir" = 'x${docdir}' +then + htmldir='${docdir}/html' +fi + +# Handle --enable-rebuild-chartables +AC_ARG_ENABLE(rebuild-chartables, + AS_HELP_STRING([--enable-rebuild-chartables], + [rebuild character tables in current locale]), + , enable_rebuild_chartables=no) + +# Handle --enable-utf8 (disabled by default) +AC_ARG_ENABLE(utf8, + AS_HELP_STRING([--enable-utf8], + [enable UTF-8 support]), + , enable_utf8=unset) + +# Handle --enable-unicode-properties +AC_ARG_ENABLE(unicode-properties, + AS_HELP_STRING([--enable-unicode-properties], + [enable Unicode properties support (implies --enable-utf8)]), + , enable_unicode_properties=no) + +# Handle --enable-newline=NL +dnl AC_ARG_ENABLE(newline, +dnl AS_HELP_STRING([--enable-newline=NL], +dnl [use NL as newline (lf, cr, crlf, anycrlf, any; default=lf)]), +dnl , enable_newline=lf) + +# Separate newline options +ac_pcre_newline=lf +AC_ARG_ENABLE(newline-is-cr, + AS_HELP_STRING([--enable-newline-is-cr], + [use CR as newline character]), + ac_pcre_newline=cr) +AC_ARG_ENABLE(newline-is-lf, + AS_HELP_STRING([--enable-newline-is-lf], + [use LF as newline character (default)]), + ac_pcre_newline=lf) +AC_ARG_ENABLE(newline-is-crlf, + AS_HELP_STRING([--enable-newline-is-crlf], + [use CRLF as newline sequence]), + ac_pcre_newline=crlf) +AC_ARG_ENABLE(newline-is-anycrlf, + AS_HELP_STRING([--enable-newline-is-anycrlf], + [use CR, LF, or CRLF as newline sequence]), + ac_pcre_newline=anycrlf) +AC_ARG_ENABLE(newline-is-any, + AS_HELP_STRING([--enable-newline-is-any], + [use any valid Unicode newline sequence]), + ac_pcre_newline=any) +enable_newline="$ac_pcre_newline" + +# Handle --enable-ebcdic +AC_ARG_ENABLE(ebcdic, + AS_HELP_STRING([--enable-ebcdic], + [assume EBCDIC coding rather than ASCII (implies --enable-rebuild-chartables)]), + , enable_ebcdic=no) + +# Handle --disable-stack-for-recursion +AC_ARG_ENABLE(stack-for-recursion, + AS_HELP_STRING([--disable-stack-for-recursion], + [don't use stack recursion when matching]), + , enable_stack_for_recursion=yes) + +# Handle --with-posix-malloc-threshold=NBYTES +AC_ARG_WITH(posix-malloc-threshold, + AS_HELP_STRING([--with-posix-malloc-threshold=NBYTES], + [threshold for POSIX malloc usage (default=10)]), + , with_posix_malloc_threshold=10) + +# Handle --with-link-size=N +AC_ARG_WITH(link-size, + AS_HELP_STRING([--with-link-size=N], + [internal link size (2, 3, or 4 allowed; default=2)]), + , with_link_size=2) + +# Handle --with-match-limit=N +AC_ARG_WITH(match-limit, + AS_HELP_STRING([--with-match-limit=N], + [default limit on internal looping (default=10000000)]), + , with_match_limit=10000000) + +# Handle --with-match-limit_recursion=N +# +# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION +# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric +# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some +# different numeric value (or even the same numeric value as MATCH_LIMIT, +# though no longer defined in terms of the latter). +# +AC_ARG_WITH(match-limit-recursion, + AS_HELP_STRING([--with-match-limit-recursion=N], + [default limit on internal recursion (default=MATCH_LIMIT)]), + , with_match_limit_recursion=MATCH_LIMIT) + +# Make sure that if enable_unicode_properties was set, that UTF-8 support +# is enabled. +# +if test "x$enable_unicode_properties" = "xyes" +then + if test "x$enable_utf8" = "xno" + then + AC_MSG_ERROR([support for Unicode properties requires UTF-8 support]) + fi + enable_utf8=yes +fi + +if test "x$enable_utf8" = "xunset" +then + enable_utf8=no +fi + +# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. +# +if test "x$enable_ebcdic" = "xyes" +then + enable_rebuild_chartables=yes +fi + +# Convert the newline identifier into the appropriate integer value. +case "$enable_newline" in + lf) ac_pcre_newline_value=10 ;; + cr) ac_pcre_newline_value=13 ;; + crlf) ac_pcre_newline_value=3338 ;; + anycrlf) ac_pcre_newline_value=-2 ;; + any) ac_pcre_newline_value=-1 ;; + *) + AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option]) + ;; +esac + +# Check argument to --with-link-size +case "$with_link_size" in + 2|3|4) ;; + *) + AC_MSG_ERROR([invalid argument \"$with_link_size\" to --with-link-size option]) + ;; +esac + +AH_TOP([ +/* On Unix-like systems config.h.in is converted by "configure" into config.h. +Some other environments also support the use of "configure". PCRE is written in +Standard C, but there are a few non-standard things it can cope with, allowing +it to run on SunOS4 and other "close to standard" systems. + +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macros the way you need them. Alternatively, you can avoid editing by using -D +on the compiler command line to set the macro values. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */]) + +# Checks for header files. AC_HEADER_STDC -AC_CHECK_HEADERS(limits.h) +AC_CHECK_HEADERS(limits.h sys/types.h sys/stat.h dirent.h windows.h) -dnl Checks for typedefs, structures, and compiler characteristics. +# Using AC_SUBST eliminates the need to include config.h in a public .h file +AC_SUBST(pcre_have_type_traits) +AC_SUBST(pcre_have_bits_type_traits) + +# Conditional compilation +AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xyes") + +# Checks for typedefs, structures, and compiler characteristics. AC_C_CONST AC_TYPE_SIZE_T -AC_CHECK_TYPES([long long], [pcre_have_long_long="1"], [pcre_have_long_long="0"]) -AC_CHECK_TYPES([unsigned long long], [pcre_have_ulong_long="1"], [pcre_have_ulong_long="0"]) +AC_CHECK_TYPES([long long], + [pcre_have_long_long="1"], + [pcre_have_long_long="0"]) +AC_CHECK_TYPES([unsigned long long], + [pcre_have_ulong_long="1"], + [pcre_have_ulong_long="0"]) AC_SUBST(pcre_have_long_long) AC_SUBST(pcre_have_ulong_long) -dnl Checks for library functions. +# Checks for library functions. AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll) -dnl Handle --enable-utf8 +# This facilitates -ansi builds under Linux +dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc]) -AC_ARG_ENABLE(utf8, -[ --enable-utf8 enable UTF8 support], -if test "$enableval" = "yes"; then - UTF8=-DSUPPORT_UTF8 -fi -) +# We only want static libs +AC_DEFINE([PCRE_STATIC], [1], [ + Define if linking statically (TODO: make nice with Libtool)]) -dnl Handle --enable-unicode-properties +# Here is where pcre specific defines are handled -AC_ARG_ENABLE(unicode-properties, -[ --enable-unicode-properties enable Unicode properties support], -if test "$enableval" = "yes"; then - UCP=-DSUPPORT_UCP -fi -) - -dnl Handle --enable-newline-is-cr - -AC_ARG_ENABLE(newline-is-cr, -[ --enable-newline-is-cr use CR as the newline character], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=13 -fi -) - -dnl Handle --enable-newline-is-lf - -AC_ARG_ENABLE(newline-is-lf, -[ --enable-newline-is-lf use LF as the newline character], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=10 -fi -) - -dnl Handle --enable-newline-is-crlf - -AC_ARG_ENABLE(newline-is-crlf, -[ --enable-newline-is-crlf use CRLF as the newline sequence], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=3338 -fi -) - -dnl Handle --enable-ebcdic - -AC_ARG_ENABLE(ebcdic, -[ --enable-ebcdic assume EBCDIC coding rather than ASCII], -if test "$enableval" == "yes"; then - EBCDIC=-DEBCDIC=1 -fi -) - -dnl Handle --disable-stack-for-recursion - -AC_ARG_ENABLE(stack-for-recursion, -[ --disable-stack-for-recursion disable use of stack recursion when matching], -if test "$enableval" = "no"; then - NO_RECURSE=-DNO_RECURSE -fi -) - -dnl There doesn't seem to be a straightforward way of having parameters -dnl that set values, other than fudging the --with thing. So that's what -dnl I've done. - -dnl Handle --with-posix-malloc-threshold=n - -AC_ARG_WITH(posix-malloc-threshold, -[ --with-posix-malloc-threshold=10 threshold for POSIX malloc usage], - POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval -) - -dnl Handle --with-link-size=n - -AC_ARG_WITH(link-size, -[ --with-link-size=2 internal link size (2, 3, or 4 allowed)], - LINK_SIZE=-DLINK_SIZE=$withval -) - -dnl Handle --with-match-limit=n - -AC_ARG_WITH(match-limit, -[ --with-match-limit=10000000 default limit on internal looping], - MATCH_LIMIT=-DMATCH_LIMIT=$withval -) - -dnl Handle --with-match-limit_recursion=n - -AC_ARG_WITH(match-limit-recursion, -[ --with-match-limit-recursion=10000000 default limit on internal recursion], - MATCH_LIMIT_RECURSION=-DMATCH_LIMIT_RECURSION=$withval -) - -dnl Unicode character property support implies UTF-8 support - -if test "$UCP" != "" ; then - UTF8=-DSUPPORT_UTF8 +if test "$enable_utf8" = "yes"; then + AC_DEFINE([SUPPORT_UTF8], [], [ + Define to enable support for the UTF-8 Unicode encoding.]) fi -dnl MacOSX on Intel Hack to remove thread-jumps +if test "$enable_unicode_properties" = "yes"; then + AC_DEFINE([SUPPORT_UCP], [], [ + Define to enable support for Unicode properties]) +fi + +if test "$enable_stack_for_recursion" = "no"; then + AC_DEFINE([NO_RECURSE], [], [ + PCRE uses recursive function calls to handle backtracking while + matching. This can sometimes be a problem on systems that have + stacks of limited size. Define NO_RECURSE to get a version that + doesn't use recursion in the match() function; instead it creates + its own stack by steam using pcre_recurse_malloc() to obtain memory + from the heap. For more detail, see the comments and other stuff + just above the match() function. On systems that support it, + "configure" can be used to set this in the Makefile + (use --disable-stack-for-recursion).]) +fi + +AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [ + The value of NEWLINE determines the newline character sequence. On + Unix-like systems, "configure" can be used to override the default, + which is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), + -1 (ANY), or -2 (ANYCRLF).]) + +AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ + The value of LINK_SIZE determines the number of bytes used to store + links as offsets within the compiled regex. The default is 2, which + allows for compiled patterns up to 64K long. This covers the vast + majority of cases. However, PCRE can also be compiled to use 3 or 4 + bytes instead. This allows for longer patterns in extreme cases. On + systems that support it, "configure" can be used to override this default.]) + +AC_DEFINE_UNQUOTED([POSIX_MALLOC_THRESHOLD], [$with_posix_malloc_threshold], [ + When calling PCRE via the POSIX interface, additional working storage + is required for holding the pointers to capturing substrings because + PCRE requires three integers per substring, whereas the POSIX + interface provides only two. If the number of expected substrings is + small, the wrapper function uses space on the stack, because this is + faster than using malloc() for each call. The threshold above which + the stack is no longer used is defined by POSIX_MALLOC_THRESHOLD. On + systems that support it, "configure" can be used to override this + default.]) + +AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [ + The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different + limit. The limit exists in order to catch runaway regular + expressions that take for ever to determine that they do not match. + The default is set very large so that it does not accidentally catch + legitimate cases. On systems that support it, "configure" can be + used to override this default default.]) + +AC_DEFINE_UNQUOTED([MATCH_LIMIT_RECURSION], [$with_match_limit_recursion], [ + The above limit applies to all calls of match(), whether or not they + increase the recursion depth. In some environments it is desirable + to limit the depth of recursive calls of match() more strictly, in + order to restrict the maximum amount of stack (or heap, if + NO_RECURSE is defined) that is used. The value of + MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To + have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. + There is a runtime method for setting a different limit. On systems + that support it, "configure" can be used to override the default.]) + +AC_DEFINE([MAX_NAME_SIZE], [32], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AC_DEFINE([MAX_NAME_COUNT], [10000], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AC_DEFINE([MAX_DUPLENGTH], [30000], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AH_VERBATIM([PCRE_EXP_DEFN], [ +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +#undef PCRE_EXP_DEFN]) + +if test "$enable_ebcdic" = "yes"; then + AC_DEFINE_UNQUOTED([EBCDIC], [], [ + If you are compiling for a system that uses EBCDIC instead of ASCII + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic.]) +fi + +dnl Mac OS X on Intel hack to remove thread jumps AC_CANONICAL_HOST case "$host" in i386-apple-darwin*) - macosx=yes - AC_DEFINE(MACOSX) - needs_cpp_precomp=yes - CFLAGS="$CFLAGS -fno-thread-jumps" - ;; + macosx=yes + AC_DEFINE(MACOSX, [], [Mac OS X on Intel]) + CFLAGS="$CFLAGS -fno-thread-jumps" + ;; esac -dnl "Export" these variables - -AC_SUBST(BUILD_EXEEXT) -AC_SUBST(BUILD_OBJEXT) -AC_SUBST(CC_FOR_BUILD) -AC_SUBST(CFLAGS_FOR_BUILD) -AC_SUBST(CXXLDFLAGS) -AC_SUBST(EBCDIC) -AC_SUBST(HAVE_MEMMOVE) -AC_SUBST(HAVE_STRERROR) -AC_SUBST(LINK_SIZE) -AC_SUBST(MATCH_LIMIT) -AC_SUBST(MATCH_LIMIT_RECURSION) -AC_SUBST(NEWLINE) -AC_SUBST(NO_RECURSE) -AC_SUBST(PCRE_LIB_VERSION) -AC_SUBST(PCRE_POSIXLIB_VERSION) -AC_SUBST(PCRE_VERSION) -AC_SUBST(POSIX_MALLOC_THRESHOLD) -AC_SUBST(UCP) -AC_SUBST(UTF8) AC_SUBST(CFLAGS) -AC_SUBST(POSIX_OBJ) -AC_SUBST(POSIX_LOBJ) -AC_SUBST(POSIX_LIB) +# The extra LDFLAGS for each particular library +# (Note: The libpcre*_version bits are m4 variables, assigned above) -if test "x$enable_shared" = "xno" ; then - AC_DEFINE([PCRE_STATIC],[1],[to link statically]) -fi +EXTRA_LIBPCRE_LDFLAGS="$NO_UNDEFINED -version-info libpcre_version" -dnl This must be last; it determines what files are written as well as config.h -AC_OUTPUT(Makefile ) +AC_SUBST(EXTRA_LIBPCRE_LDFLAGS) + +# Produce these files, in addition to config.h. +AC_CONFIG_FILES( + Makefile + pcre-config + pcre.h +) + +# Make the generated script files executable. +AC_CONFIG_COMMANDS([script-chmod], [chmod a+x pcre-config]) + +# Make sure that pcre_chartables.c is removed in case the method for +# creating it was changed by reconfiguration. +AC_CONFIG_COMMANDS([delete-old-chartables], [rm -f pcre_chartables.c]) + +AC_OUTPUT + +dnl end configure.ac diff --git a/libpcre/depcomp b/libpcre/depcomp new file mode 100755 index 000000000..ca5ea4e1e --- /dev/null +++ b/libpcre/depcomp @@ -0,0 +1,584 @@ +#! /bin/sh +# depcomp - compile a program generating dependencies as side-effects + +scriptversion=2006-10-15.18 + +# Copyright (C) 1999, 2000, 2003, 2004, 2005, 2006 Free Software +# Foundation, Inc. + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2, or (at your option) +# any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA +# 02110-1301, USA. + +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# Originally written by Alexandre Oliva . + +case $1 in + '') + echo "$0: No command. Try \`$0 --help' for more information." 1>&2 + exit 1; + ;; + -h | --h*) + cat <<\EOF +Usage: depcomp [--help] [--version] PROGRAM [ARGS] + +Run PROGRAMS ARGS to compile a file, generating dependencies +as side-effects. + +Environment variables: + depmode Dependency tracking mode. + source Source file read by `PROGRAMS ARGS'. + object Object file output by `PROGRAMS ARGS'. + DEPDIR directory where to store dependencies. + depfile Dependency file to output. + tmpdepfile Temporary file to use when outputing dependencies. + libtool Whether libtool is used (yes/no). + +Report bugs to . +EOF + exit $? + ;; + -v | --v*) + echo "depcomp $scriptversion" + exit $? + ;; +esac + +if test -z "$depmode" || test -z "$source" || test -z "$object"; then + echo "depcomp: Variables source, object and depmode must be set" 1>&2 + exit 1 +fi + +# Dependencies for sub/bar.o or sub/bar.obj go into sub/.deps/bar.Po. +depfile=${depfile-`echo "$object" | + sed 's|[^\\/]*$|'${DEPDIR-.deps}'/&|;s|\.\([^.]*\)$|.P\1|;s|Pobj$|Po|'`} +tmpdepfile=${tmpdepfile-`echo "$depfile" | sed 's/\.\([^.]*\)$/.T\1/'`} + +rm -f "$tmpdepfile" + +# Some modes work just like other modes, but use different flags. We +# parameterize here, but still list the modes in the big case below, +# to make depend.m4 easier to write. Note that we *cannot* use a case +# here, because this file can only contain one case statement. +if test "$depmode" = hp; then + # HP compiler uses -M and no extra arg. + gccflag=-M + depmode=gcc +fi + +if test "$depmode" = dashXmstdout; then + # This is just like dashmstdout with a different argument. + dashmflag=-xM + depmode=dashmstdout +fi + +case "$depmode" in +gcc3) +## gcc 3 implements dependency tracking that does exactly what +## we want. Yay! Note: for some reason libtool 1.4 doesn't like +## it if -MD -MP comes after the -MF stuff. Hmm. +## Unfortunately, FreeBSD c89 acceptance of flags depends upon +## the command line argument order; so add the flags where they +## appear in depend2.am. Note that the slowdown incurred here +## affects only configure: in makefiles, %FASTDEP% shortcuts this. + for arg + do + case $arg in + -c) set fnord "$@" -MT "$object" -MD -MP -MF "$tmpdepfile" "$arg" ;; + *) set fnord "$@" "$arg" ;; + esac + shift # fnord + shift # $arg + done + "$@" + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + mv "$tmpdepfile" "$depfile" + ;; + +gcc) +## There are various ways to get dependency output from gcc. Here's +## why we pick this rather obscure method: +## - Don't want to use -MD because we'd like the dependencies to end +## up in a subdir. Having to rename by hand is ugly. +## (We might end up doing this anyway to support other compilers.) +## - The DEPENDENCIES_OUTPUT environment variable makes gcc act like +## -MM, not -M (despite what the docs say). +## - Using -M directly means running the compiler twice (even worse +## than renaming). + if test -z "$gccflag"; then + gccflag=-MD, + fi + "$@" -Wp,"$gccflag$tmpdepfile" + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + echo "$object : \\" > "$depfile" + alpha=ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz +## The second -e expression handles DOS-style file names with drive letters. + sed -e 's/^[^:]*: / /' \ + -e 's/^['$alpha']:\/[^:]*: / /' < "$tmpdepfile" >> "$depfile" +## This next piece of magic avoids the `deleted header file' problem. +## The problem is that when a header file which appears in a .P file +## is deleted, the dependency causes make to die (because there is +## typically no way to rebuild the header). We avoid this by adding +## dummy dependencies for each header file. Too bad gcc doesn't do +## this for us directly. + tr ' ' ' +' < "$tmpdepfile" | +## Some versions of gcc put a space before the `:'. On the theory +## that the space means something, we add a space to the output as +## well. +## Some versions of the HPUX 10.20 sed can't process this invocation +## correctly. Breaking it into two sed invocations is a workaround. + sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +hp) + # This case exists only to let depend.m4 do its work. It works by + # looking at the text of this script. This case will never be run, + # since it is checked for above. + exit 1 + ;; + +sgi) + if test "$libtool" = yes; then + "$@" "-Wp,-MDupdate,$tmpdepfile" + else + "$@" -MDupdate "$tmpdepfile" + fi + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + + if test -f "$tmpdepfile"; then # yes, the sourcefile depend on other files + echo "$object : \\" > "$depfile" + + # Clip off the initial element (the dependent). Don't try to be + # clever and replace this with sed code, as IRIX sed won't handle + # lines with more than a fixed number of characters (4096 in + # IRIX 6.2 sed, 8192 in IRIX 6.5). We also remove comment lines; + # the IRIX cc adds comments like `#:fec' to the end of the + # dependency line. + tr ' ' ' +' < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' | \ + tr ' +' ' ' >> $depfile + echo >> $depfile + + # The second pass generates a dummy entry for each header file. + tr ' ' ' +' < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \ + >> $depfile + else + # The sourcefile does not contain any dependencies, so just + # store a dummy comment line, to avoid errors with the Makefile + # "include basename.Plo" scheme. + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" + ;; + +aix) + # The C for AIX Compiler uses -M and outputs the dependencies + # in a .u file. In older versions, this file always lives in the + # current directory. Also, the AIX compiler puts `$object:' at the + # start of each line; $object doesn't have directory information. + # Version 6 uses the directory in both cases. + stripped=`echo "$object" | sed 's/\(.*\)\..*$/\1/'` + tmpdepfile="$stripped.u" + if test "$libtool" = yes; then + "$@" -Wc,-M + else + "$@" -M + fi + stat=$? + + if test -f "$tmpdepfile"; then : + else + stripped=`echo "$stripped" | sed 's,^.*/,,'` + tmpdepfile="$stripped.u" + fi + + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + + if test -f "$tmpdepfile"; then + outname="$stripped.o" + # Each line is of the form `foo.o: dependent.h'. + # Do two passes, one to just change these to + # `$object: dependent.h' and one to simply `dependent.h:'. + sed -e "s,^$outname:,$object :," < "$tmpdepfile" > "$depfile" + sed -e "s,^$outname: \(.*\)$,\1:," < "$tmpdepfile" >> "$depfile" + else + # The sourcefile does not contain any dependencies, so just + # store a dummy comment line, to avoid errors with the Makefile + # "include basename.Plo" scheme. + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" + ;; + +icc) + # Intel's C compiler understands `-MD -MF file'. However on + # icc -MD -MF foo.d -c -o sub/foo.o sub/foo.c + # ICC 7.0 will fill foo.d with something like + # foo.o: sub/foo.c + # foo.o: sub/foo.h + # which is wrong. We want: + # sub/foo.o: sub/foo.c + # sub/foo.o: sub/foo.h + # sub/foo.c: + # sub/foo.h: + # ICC 7.1 will output + # foo.o: sub/foo.c sub/foo.h + # and will wrap long lines using \ : + # foo.o: sub/foo.c ... \ + # sub/foo.h ... \ + # ... + + "$@" -MD -MF "$tmpdepfile" + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + # Each line is of the form `foo.o: dependent.h', + # or `foo.o: dep1.h dep2.h \', or ` dep3.h dep4.h \'. + # Do two passes, one to just change these to + # `$object: dependent.h' and one to simply `dependent.h:'. + sed "s,^[^:]*:,$object :," < "$tmpdepfile" > "$depfile" + # Some versions of the HPUX 10.20 sed can't process this invocation + # correctly. Breaking it into two sed invocations is a workaround. + sed 's,^[^:]*: \(.*\)$,\1,;s/^\\$//;/^$/d;/:$/d' < "$tmpdepfile" | + sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +hp2) + # The "hp" stanza above does not work with aCC (C++) and HP's ia64 + # compilers, which have integrated preprocessors. The correct option + # to use with these is +Maked; it writes dependencies to a file named + # 'foo.d', which lands next to the object file, wherever that + # happens to be. + # Much of this is similar to the tru64 case; see comments there. + dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` + test "x$dir" = "x$object" && dir= + base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` + if test "$libtool" = yes; then + tmpdepfile1=$dir$base.d + tmpdepfile2=$dir.libs/$base.d + "$@" -Wc,+Maked + else + tmpdepfile1=$dir$base.d + tmpdepfile2=$dir$base.d + "$@" +Maked + fi + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile1" "$tmpdepfile2" + exit $stat + fi + + for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" + do + test -f "$tmpdepfile" && break + done + if test -f "$tmpdepfile"; then + sed -e "s,^.*\.[a-z]*:,$object:," "$tmpdepfile" > "$depfile" + # Add `dependent.h:' lines. + sed -ne '2,${; s/^ *//; s/ \\*$//; s/$/:/; p;}' "$tmpdepfile" >> "$depfile" + else + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" "$tmpdepfile2" + ;; + +tru64) + # The Tru64 compiler uses -MD to generate dependencies as a side + # effect. `cc -MD -o foo.o ...' puts the dependencies into `foo.o.d'. + # At least on Alpha/Redhat 6.1, Compaq CCC V6.2-504 seems to put + # dependencies in `foo.d' instead, so we check for that too. + # Subdirectories are respected. + dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` + test "x$dir" = "x$object" && dir= + base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` + + if test "$libtool" = yes; then + # With Tru64 cc, shared objects can also be used to make a + # static library. This mechanism is used in libtool 1.4 series to + # handle both shared and static libraries in a single compilation. + # With libtool 1.4, dependencies were output in $dir.libs/$base.lo.d. + # + # With libtool 1.5 this exception was removed, and libtool now + # generates 2 separate objects for the 2 libraries. These two + # compilations output dependencies in $dir.libs/$base.o.d and + # in $dir$base.o.d. We have to check for both files, because + # one of the two compilations can be disabled. We should prefer + # $dir$base.o.d over $dir.libs/$base.o.d because the latter is + # automatically cleaned when .libs/ is deleted, while ignoring + # the former would cause a distcleancheck panic. + tmpdepfile1=$dir.libs/$base.lo.d # libtool 1.4 + tmpdepfile2=$dir$base.o.d # libtool 1.5 + tmpdepfile3=$dir.libs/$base.o.d # libtool 1.5 + tmpdepfile4=$dir.libs/$base.d # Compaq CCC V6.2-504 + "$@" -Wc,-MD + else + tmpdepfile1=$dir$base.o.d + tmpdepfile2=$dir$base.d + tmpdepfile3=$dir$base.d + tmpdepfile4=$dir$base.d + "$@" -MD + fi + + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4" + exit $stat + fi + + for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4" + do + test -f "$tmpdepfile" && break + done + if test -f "$tmpdepfile"; then + sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile" + # That's a tab and a space in the []. + sed -e 's,^.*\.[a-z]*:[ ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile" + else + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" + ;; + +#nosideeffect) + # This comment above is used by automake to tell side-effect + # dependency tracking mechanisms from slower ones. + +dashmstdout) + # Important note: in order to support this mode, a compiler *must* + # always write the preprocessed file to stdout, regardless of -o. + "$@" || exit $? + + # Remove the call to Libtool. + if test "$libtool" = yes; then + while test $1 != '--mode=compile'; do + shift + done + shift + fi + + # Remove `-o $object'. + IFS=" " + for arg + do + case $arg in + -o) + shift + ;; + $object) + shift + ;; + *) + set fnord "$@" "$arg" + shift # fnord + shift # $arg + ;; + esac + done + + test -z "$dashmflag" && dashmflag=-M + # Require at least two characters before searching for `:' + # in the target name. This is to cope with DOS-style filenames: + # a dependency such as `c:/foo/bar' could be seen as target `c' otherwise. + "$@" $dashmflag | + sed 's:^[ ]*[^: ][^:][^:]*\:[ ]*:'"$object"'\: :' > "$tmpdepfile" + rm -f "$depfile" + cat < "$tmpdepfile" > "$depfile" + tr ' ' ' +' < "$tmpdepfile" | \ +## Some versions of the HPUX 10.20 sed can't process this invocation +## correctly. Breaking it into two sed invocations is a workaround. + sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +dashXmstdout) + # This case only exists to satisfy depend.m4. It is never actually + # run, as this mode is specially recognized in the preamble. + exit 1 + ;; + +makedepend) + "$@" || exit $? + # Remove any Libtool call + if test "$libtool" = yes; then + while test $1 != '--mode=compile'; do + shift + done + shift + fi + # X makedepend + shift + cleared=no + for arg in "$@"; do + case $cleared in + no) + set ""; shift + cleared=yes ;; + esac + case "$arg" in + -D*|-I*) + set fnord "$@" "$arg"; shift ;; + # Strip any option that makedepend may not understand. Remove + # the object too, otherwise makedepend will parse it as a source file. + -*|$object) + ;; + *) + set fnord "$@" "$arg"; shift ;; + esac + done + obj_suffix="`echo $object | sed 's/^.*\././'`" + touch "$tmpdepfile" + ${MAKEDEPEND-makedepend} -o"$obj_suffix" -f"$tmpdepfile" "$@" + rm -f "$depfile" + cat < "$tmpdepfile" > "$depfile" + sed '1,2d' "$tmpdepfile" | tr ' ' ' +' | \ +## Some versions of the HPUX 10.20 sed can't process this invocation +## correctly. Breaking it into two sed invocations is a workaround. + sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" "$tmpdepfile".bak + ;; + +cpp) + # Important note: in order to support this mode, a compiler *must* + # always write the preprocessed file to stdout. + "$@" || exit $? + + # Remove the call to Libtool. + if test "$libtool" = yes; then + while test $1 != '--mode=compile'; do + shift + done + shift + fi + + # Remove `-o $object'. + IFS=" " + for arg + do + case $arg in + -o) + shift + ;; + $object) + shift + ;; + *) + set fnord "$@" "$arg" + shift # fnord + shift # $arg + ;; + esac + done + + "$@" -E | + sed -n -e '/^# [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' \ + -e '/^#line [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' | + sed '$ s: \\$::' > "$tmpdepfile" + rm -f "$depfile" + echo "$object : \\" > "$depfile" + cat < "$tmpdepfile" >> "$depfile" + sed < "$tmpdepfile" '/^$/d;s/^ //;s/ \\$//;s/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +msvisualcpp) + # Important note: in order to support this mode, a compiler *must* + # always write the preprocessed file to stdout, regardless of -o, + # because we must use -o when running libtool. + "$@" || exit $? + IFS=" " + for arg + do + case "$arg" in + "-Gm"|"/Gm"|"-Gi"|"/Gi"|"-ZI"|"/ZI") + set fnord "$@" + shift + shift + ;; + *) + set fnord "$@" "$arg" + shift + shift + ;; + esac + done + "$@" -E | + sed -n '/^#line [0-9][0-9]* "\([^"]*\)"/ s::echo "`cygpath -u \\"\1\\"`":p' | sort | uniq > "$tmpdepfile" + rm -f "$depfile" + echo "$object : \\" > "$depfile" + . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s:: \1 \\:p' >> "$depfile" + echo " " >> "$depfile" + . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s::\1\::p' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +none) + exec "$@" + ;; + +*) + echo "Unknown depmode $depmode" 1>&2 + exit 1 + ;; +esac + +exit 0 + +# Local Variables: +# mode: shell-script +# sh-indentation: 2 +# eval: (add-hook 'write-file-hooks 'time-stamp) +# time-stamp-start: "scriptversion=" +# time-stamp-format: "%:y-%02m-%02d.%02H" +# time-stamp-end: "$" +# End: diff --git a/libpcre/dftables.c b/libpcre/dftables.c index 5ba207aeb..baa56a15c 100644 --- a/libpcre/dftables.c +++ b/libpcre/dftables.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -38,14 +38,15 @@ POSSIBILITY OF SUCH DAMAGE. */ -/* This is a freestanding support program to generate a file containing default -character tables for PCRE. The tables are built according to the default C +/* This is a freestanding support program to generate a file containing +character tables for PCRE. The tables are built according to the current locale. Now that pcre_maketables is a function visible to the outside world, we make use of its code from here in order to be consistent. */ #include #include #include +#include #include "pcre_internal.h" @@ -55,38 +56,57 @@ make use of its code from here in order to be consistent. */ int main(int argc, char **argv) { -int i; FILE *f; -const unsigned char *tables = pcre_maketables(); -const unsigned char *base_of_tables = tables; +int i = 1; +const unsigned char *tables; +const unsigned char *base_of_tables; -if (argc != 2) +/* By default, the default C locale is used rather than what the building user +happens to have set. However, if the -L option is given, set the locale from +the LC_xxx environment variables. */ + +if (argc > 1 && strcmp(argv[1], "-L") == 0) + { + setlocale(LC_ALL, ""); /* Set from environment variables */ + i++; + } + +if (argc < i + 1) { fprintf(stderr, "dftables: one filename argument is required\n"); return 1; } -f = fopen(argv[1], "wb"); +tables = pcre_maketables(); +base_of_tables = tables; + +f = fopen(argv[i], "wb"); if (f == NULL) { fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); return 1; } -/* There are two fprintf() calls here, because gcc in pedantic mode complains -about the very long string otherwise. */ +/* There are several fprintf() calls here, because gcc in pedantic mode +complains about the very long string otherwise. */ fprintf(f, "/*************************************************\n" "* Perl-Compatible Regular Expressions *\n" "*************************************************/\n\n" - "/* This file is automatically written by the dftables auxiliary \n" - "program. If you edit it by hand, you might like to edit the Makefile to \n" - "prevent its ever being regenerated.\n\n"); + "/* This file was automatically written by the dftables auxiliary\n" + "program. It contains character tables that are used when no external\n" + "tables are passed to PCRE by the application that calls it. The tables\n" + "are used only for characters whose code values are less than 256.\n\n"); +fprintf(f, + "The following #include is present because without it gcc 4.x may remove\n" + "the array definition from the final binary if PCRE is built into a static\n" + "library and dead code stripping is activated. This leads to link errors.\n" + "Pulling in the header ensures that the array gets flagged as \"someone\n" + "outside this compilation unit might reference this\" and so it will always\n" + "be supplied to the linker. */\n\n" + "#include \"pcre_internal.h\"\n\n"); fprintf(f, - "This file contains the default tables for characters with codes less than\n" - "128 (ASCII characters). These tables are used when no external tables are\n" - "passed to PCRE. */\n\n" "const unsigned char _pcre_default_tables[] = {\n\n" "/* This table is a lower casing table. */\n\n"); @@ -162,7 +182,7 @@ if (isprint(i-8)) fprintf(f, " %c -", i-8); else fprintf(f, "%3d-", i-8); if (isprint(i-1)) fprintf(f, " %c ", i-1); else fprintf(f, "%3d", i-1); -fprintf(f, " */\n\n/* End of chartables.c */\n"); +fprintf(f, " */\n\n/* End of pcre_chartables.c */\n"); fclose(f); free((void *)base_of_tables); diff --git a/libpcre/install-sh b/libpcre/install-sh index e9de23842..4fbbae7b7 100755 --- a/libpcre/install-sh +++ b/libpcre/install-sh @@ -1,36 +1,62 @@ #!/bin/sh -# # install - install a program, script, or datafile -# This comes from X11R5 (mit/util/scripts/install.sh). + +scriptversion=2006-10-14.15 + +# This originates from X11R5 (mit/util/scripts/install.sh), which was +# later released in X11R6 (xc/config/util/install.sh) with the +# following copyright and license. # -# Copyright 1991 by the Massachusetts Institute of Technology +# Copyright (C) 1994 X Consortium # -# Permission to use, copy, modify, distribute, and sell this software and its -# documentation for any purpose is hereby granted without fee, provided that -# the above copyright notice appear in all copies and that both that -# copyright notice and this permission notice appear in supporting -# documentation, and that the name of M.I.T. not be used in advertising or -# publicity pertaining to distribution of the software without specific, -# written prior permission. M.I.T. makes no representations about the -# suitability of this software for any purpose. It is provided "as is" -# without express or implied warranty. +# Permission is hereby granted, free of charge, to any person obtaining a copy +# of this software and associated documentation files (the "Software"), to +# deal in the Software without restriction, including without limitation the +# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or +# sell copies of the Software, and to permit persons to whom the Software is +# furnished to do so, subject to the following conditions: +# +# The above copyright notice and this permission notice shall be included in +# all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +# X CONSORTIUM BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN +# AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNEC- +# TION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +# +# Except as contained in this notice, the name of the X Consortium shall not +# be used in advertising or otherwise to promote the sale, use or other deal- +# ings in this Software without prior written authorization from the X Consor- +# tium. +# +# +# FSF changes to this file are in the public domain. # # Calling this script install-sh is preferred over install.sh, to prevent # `make' implicit rules from creating a file called install from it # when there is no Makefile. # # This script is compatible with the BSD install script, but was written -# from scratch. It can only install one file at a time, a restriction -# shared with many OS's install programs. +# from scratch. +nl=' +' +IFS=" "" $nl" # set DOITPROG to echo to test this script # Don't use :- since 4.3BSD and earlier shells don't like it. doit="${DOITPROG-}" +if test -z "$doit"; then + doit_exec=exec +else + doit_exec=$doit +fi - -# put in absolute paths if you don't have them in your path; or use env. vars. +# Put in absolute file names if you don't have them in your path; +# or use environment vars. mvprog="${MVPROG-mv}" cpprog="${CPPROG-cp}" @@ -41,211 +67,441 @@ stripprog="${STRIPPROG-strip}" rmprog="${RMPROG-rm}" mkdirprog="${MKDIRPROG-mkdir}" -transformbasename="" -transform_arg="" -instcmd="$mvprog" -chmodcmd="$chmodprog 0755" -chowncmd="" -chgrpcmd="" -stripcmd="" +posix_glob= +posix_mkdir= + +# Desired mode of installed file. +mode=0755 + +chmodcmd=$chmodprog +chowncmd= +chgrpcmd= +stripcmd= rmcmd="$rmprog -f" mvcmd="$mvprog" -src="" -dst="" -dir_arg="" +src= +dst= +dir_arg= +dstarg= +no_target_directory= -while [ x"$1" != x ]; do - case $1 in - -c) instcmd="$cpprog" - shift - continue;; +usage="Usage: $0 [OPTION]... [-T] SRCFILE DSTFILE + or: $0 [OPTION]... SRCFILES... DIRECTORY + or: $0 [OPTION]... -t DIRECTORY SRCFILES... + or: $0 [OPTION]... -d DIRECTORIES... - -d) dir_arg=true - shift - continue;; +In the 1st form, copy SRCFILE to DSTFILE. +In the 2nd and 3rd, copy all SRCFILES to DIRECTORY. +In the 4th, create DIRECTORIES. - -m) chmodcmd="$chmodprog $2" - shift - shift - continue;; +Options: +-c (ignored) +-d create directories instead of installing files. +-g GROUP $chgrpprog installed files to GROUP. +-m MODE $chmodprog installed files to MODE. +-o USER $chownprog installed files to USER. +-s $stripprog installed files. +-t DIRECTORY install into DIRECTORY. +-T report an error if DSTFILE is a directory. +--help display this help and exit. +--version display version info and exit. - -o) chowncmd="$chownprog $2" - shift - shift - continue;; +Environment variables override the default commands: + CHGRPPROG CHMODPROG CHOWNPROG CPPROG MKDIRPROG MVPROG RMPROG STRIPPROG +" - -g) chgrpcmd="$chgrpprog $2" - shift - shift - continue;; +while test $# -ne 0; do + case $1 in + -c) shift + continue;; - -s) stripcmd="$stripprog" - shift - continue;; + -d) dir_arg=true + shift + continue;; - -t=*) transformarg=`echo $1 | sed 's/-t=//'` - shift - continue;; + -g) chgrpcmd="$chgrpprog $2" + shift + shift + continue;; - -b=*) transformbasename=`echo $1 | sed 's/-b=//'` - shift - continue;; + --help) echo "$usage"; exit $?;; - *) if [ x"$src" = x ] - then - src=$1 - else - # this colon is to work around a 386BSD /bin/sh bug - : - dst=$1 - fi - shift - continue;; - esac -done + -m) mode=$2 + shift + shift + case $mode in + *' '* | *' '* | *' +'* | *'*'* | *'?'* | *'['*) + echo "$0: invalid mode: $mode" >&2 + exit 1;; + esac + continue;; -if [ x"$src" = x ] -then - echo "install: no input file specified" - exit 1 -else - true -fi + -o) chowncmd="$chownprog $2" + shift + shift + continue;; -if [ x"$dir_arg" != x ]; then - dst=$src - src="" - - if [ -d $dst ]; then - instcmd=: - chmodcmd="" - else - instcmd=mkdir - fi -else + -s) stripcmd=$stripprog + shift + continue;; -# Waiting for this to be detected by the "$instcmd $src $dsttmp" command -# might cause directories to be created, which would be especially bad -# if $src (and thus $dsttmp) contains '*'. - - if [ -f $src -o -d $src ] - then - true - else - echo "install: $src does not exist" - exit 1 - fi - - if [ x"$dst" = x ] - then - echo "install: no destination specified" - exit 1 - else - true - fi - -# If destination is a directory, append the input filename; if your system -# does not like double slashes in filenames, you may need to add some logic - - if [ -d $dst ] - then - dst="$dst"/`basename $src` - else - true - fi -fi - -## this sed command emulates the dirname command -dstdir=`echo $dst | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'` - -# Make sure that the destination directory exists. -# this part is taken from Noah Friedman's mkinstalldirs script - -# Skip lots of stat calls in the usual case. -if [ ! -d "$dstdir" ]; then -defaultIFS=' -' -IFS="${IFS-${defaultIFS}}" - -oIFS="${IFS}" -# Some sh's can't handle IFS=/ for some reason. -IFS='%' -set - `echo ${dstdir} | sed -e 's@/@%@g' -e 's@^%@/@'` -IFS="${oIFS}" - -pathcomp='' - -while [ $# -ne 0 ] ; do - pathcomp="${pathcomp}${1}" + -t) dstarg=$2 shift + shift + continue;; - if [ ! -d "${pathcomp}" ] ; - then - $mkdirprog "${pathcomp}" - else - true - fi + -T) no_target_directory=true + shift + continue;; - pathcomp="${pathcomp}/" + --version) echo "$0 $scriptversion"; exit $?;; + + --) shift + break;; + + -*) echo "$0: invalid option: $1" >&2 + exit 1;; + + *) break;; + esac done + +if test $# -ne 0 && test -z "$dir_arg$dstarg"; then + # When -d is used, all remaining arguments are directories to create. + # When -t is used, the destination is already specified. + # Otherwise, the last argument is the destination. Remove it from $@. + for arg + do + if test -n "$dstarg"; then + # $@ is not empty: it contains at least $arg. + set fnord "$@" "$dstarg" + shift # fnord + fi + shift # arg + dstarg=$arg + done fi -if [ x"$dir_arg" != x ] -then - $doit $instcmd $dst && +if test $# -eq 0; then + if test -z "$dir_arg"; then + echo "$0: no input file specified." >&2 + exit 1 + fi + # It's OK to call `install-sh -d' without argument. + # This can happen when creating conditional directories. + exit 0 +fi - if [ x"$chowncmd" != x ]; then $doit $chowncmd $dst; else true ; fi && - if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dst; else true ; fi && - if [ x"$stripcmd" != x ]; then $doit $stripcmd $dst; else true ; fi && - if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dst; else true ; fi -else +if test -z "$dir_arg"; then + trap '(exit $?); exit' 1 2 13 15 -# If we're going to rename the final executable, determine the name now. + # Set umask so as not to create temps with too-generous modes. + # However, 'strip' requires both read and write access to temps. + case $mode in + # Optimize common cases. + *644) cp_umask=133;; + *755) cp_umask=22;; - if [ x"$transformarg" = x ] - then - dstfile=`basename $dst` + *[0-7]) + if test -z "$stripcmd"; then + u_plus_rw= + else + u_plus_rw='% 200' + fi + cp_umask=`expr '(' 777 - $mode % 1000 ')' $u_plus_rw`;; + *) + if test -z "$stripcmd"; then + u_plus_rw= + else + u_plus_rw=,u+rw + fi + cp_umask=$mode$u_plus_rw;; + esac +fi + +for src +do + # Protect names starting with `-'. + case $src in + -*) src=./$src ;; + esac + + if test -n "$dir_arg"; then + dst=$src + dstdir=$dst + test -d "$dstdir" + dstdir_status=$? + else + + # Waiting for this to be detected by the "$cpprog $src $dsttmp" command + # might cause directories to be created, which would be especially bad + # if $src (and thus $dsttmp) contains '*'. + if test ! -f "$src" && test ! -d "$src"; then + echo "$0: $src does not exist." >&2 + exit 1 + fi + + if test -z "$dstarg"; then + echo "$0: no destination specified." >&2 + exit 1 + fi + + dst=$dstarg + # Protect names starting with `-'. + case $dst in + -*) dst=./$dst ;; + esac + + # If destination is a directory, append the input filename; won't work + # if double slashes aren't ignored. + if test -d "$dst"; then + if test -n "$no_target_directory"; then + echo "$0: $dstarg: Is a directory" >&2 + exit 1 + fi + dstdir=$dst + dst=$dstdir/`basename "$src"` + dstdir_status=0 + else + # Prefer dirname, but fall back on a substitute if dirname fails. + dstdir=` + (dirname "$dst") 2>/dev/null || + expr X"$dst" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$dst" : 'X\(//\)[^/]' \| \ + X"$dst" : 'X\(//\)$' \| \ + X"$dst" : 'X\(/\)' \| . 2>/dev/null || + echo X"$dst" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q' + ` + + test -d "$dstdir" + dstdir_status=$? + fi + fi + + obsolete_mkdir_used=false + + if test $dstdir_status != 0; then + case $posix_mkdir in + '') + # Create intermediate dirs using mode 755 as modified by the umask. + # This is like FreeBSD 'install' as of 1997-10-28. + umask=`umask` + case $stripcmd.$umask in + # Optimize common cases. + *[2367][2367]) mkdir_umask=$umask;; + .*0[02][02] | .[02][02] | .[02]) mkdir_umask=22;; + + *[0-7]) + mkdir_umask=`expr $umask + 22 \ + - $umask % 100 % 40 + $umask % 20 \ + - $umask % 10 % 4 + $umask % 2 + `;; + *) mkdir_umask=$umask,go-w;; + esac + + # With -d, create the new directory with the user-specified mode. + # Otherwise, rely on $mkdir_umask. + if test -n "$dir_arg"; then + mkdir_mode=-m$mode else - dstfile=`basename $dst $transformbasename | - sed $transformarg`$transformbasename + mkdir_mode= fi -# don't allow the sed command to completely eliminate the filename + posix_mkdir=false + case $umask in + *[123567][0-7][0-7]) + # POSIX mkdir -p sets u+wx bits regardless of umask, which + # is incompatible with FreeBSD 'install' when (umask & 300) != 0. + ;; + *) + tmpdir=${TMPDIR-/tmp}/ins$RANDOM-$$ + trap 'ret=$?; rmdir "$tmpdir/d" "$tmpdir" 2>/dev/null; exit $ret' 0 - if [ x"$dstfile" = x ] - then - dstfile=`basename $dst` + if (umask $mkdir_umask && + exec $mkdirprog $mkdir_mode -p -- "$tmpdir/d") >/dev/null 2>&1 + then + if test -z "$dir_arg" || { + # Check for POSIX incompatibilities with -m. + # HP-UX 11.23 and IRIX 6.5 mkdir -m -p sets group- or + # other-writeable bit of parent directory when it shouldn't. + # FreeBSD 6.1 mkdir -m -p sets mode of existing directory. + ls_ld_tmpdir=`ls -ld "$tmpdir"` + case $ls_ld_tmpdir in + d????-?r-*) different_mode=700;; + d????-?--*) different_mode=755;; + *) false;; + esac && + $mkdirprog -m$different_mode -p -- "$tmpdir" && { + ls_ld_tmpdir_1=`ls -ld "$tmpdir"` + test "$ls_ld_tmpdir" = "$ls_ld_tmpdir_1" + } + } + then posix_mkdir=: + fi + rmdir "$tmpdir/d" "$tmpdir" + else + # Remove any dirs left behind by ancient mkdir implementations. + rmdir ./$mkdir_mode ./-p ./-- 2>/dev/null + fi + trap '' 0;; + esac;; + esac + + if + $posix_mkdir && ( + umask $mkdir_umask && + $doit_exec $mkdirprog $mkdir_mode -p -- "$dstdir" + ) + then : + else + + # The umask is ridiculous, or mkdir does not conform to POSIX, + # or it failed possibly due to a race condition. Create the + # directory the slow way, step by step, checking for races as we go. + + case $dstdir in + /*) prefix=/ ;; + -*) prefix=./ ;; + *) prefix= ;; + esac + + case $posix_glob in + '') + if (set -f) 2>/dev/null; then + posix_glob=true + else + posix_glob=false + fi ;; + esac + + oIFS=$IFS + IFS=/ + $posix_glob && set -f + set fnord $dstdir + shift + $posix_glob && set +f + IFS=$oIFS + + prefixes= + + for d + do + test -z "$d" && continue + + prefix=$prefix$d + if test -d "$prefix"; then + prefixes= else - true + if $posix_mkdir; then + (umask=$mkdir_umask && + $doit_exec $mkdirprog $mkdir_mode -p -- "$dstdir") && break + # Don't fail if two instances are running concurrently. + test -d "$prefix" || exit 1 + else + case $prefix in + *\'*) qprefix=`echo "$prefix" | sed "s/'/'\\\\\\\\''/g"`;; + *) qprefix=$prefix;; + esac + prefixes="$prefixes '$qprefix'" + fi fi + prefix=$prefix/ + done -# Make a temp file name in the proper directory. + if test -n "$prefixes"; then + # Don't fail if two instances are running concurrently. + (umask $mkdir_umask && + eval "\$doit_exec \$mkdirprog $prefixes") || + test -d "$dstdir" || exit 1 + obsolete_mkdir_used=true + fi + fi + fi - dsttmp=$dstdir/#inst.$$# + if test -n "$dir_arg"; then + { test -z "$chowncmd" || $doit $chowncmd "$dst"; } && + { test -z "$chgrpcmd" || $doit $chgrpcmd "$dst"; } && + { test "$obsolete_mkdir_used$chowncmd$chgrpcmd" = false || + test -z "$chmodcmd" || $doit $chmodcmd $mode "$dst"; } || exit 1 + else -# Move or copy the file name to the temp name + # Make a couple of temp file names in the proper directory. + dsttmp=$dstdir/_inst.$$_ + rmtmp=$dstdir/_rm.$$_ - $doit $instcmd $src $dsttmp && + # Trap to clean up those temp files at exit. + trap 'ret=$?; rm -f "$dsttmp" "$rmtmp" && exit $ret' 0 - trap "rm -f ${dsttmp}" 0 && + # Copy the file name to the temp name. + (umask $cp_umask && $doit_exec $cpprog "$src" "$dsttmp") && -# and set any options; do chmod last to preserve setuid bits + # and set any options; do chmod last to preserve setuid bits. + # + # If any of these fail, we abort the whole thing. If we want to + # ignore errors from any of these, just make sure not to ignore + # errors from the above "$doit $cpprog $src $dsttmp" command. + # + { test -z "$chowncmd" || $doit $chowncmd "$dsttmp"; } \ + && { test -z "$chgrpcmd" || $doit $chgrpcmd "$dsttmp"; } \ + && { test -z "$stripcmd" || $doit $stripcmd "$dsttmp"; } \ + && { test -z "$chmodcmd" || $doit $chmodcmd $mode "$dsttmp"; } && -# If any of these fail, we abort the whole thing. If we want to -# ignore errors from any of these, just make sure not to ignore -# errors from the above "$doit $instcmd $src $dsttmp" command. + # Now rename the file to the real destination. + { $doit $mvcmd -f "$dsttmp" "$dst" 2>/dev/null \ + || { + # The rename failed, perhaps because mv can't rename something else + # to itself, or perhaps because mv is so ancient that it does not + # support -f. - if [ x"$chowncmd" != x ]; then $doit $chowncmd $dsttmp; else true;fi && - if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dsttmp; else true;fi && - if [ x"$stripcmd" != x ]; then $doit $stripcmd $dsttmp; else true;fi && - if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dsttmp; else true;fi && + # Now remove or move aside any old file at destination location. + # We try this two ways since rm can't unlink itself on some + # systems and the destination file might be busy for other + # reasons. In this case, the final cleanup might fail but the new + # file should still install successfully. + { + if test -f "$dst"; then + $doit $rmcmd -f "$dst" 2>/dev/null \ + || { $doit $mvcmd -f "$dst" "$rmtmp" 2>/dev/null \ + && { $doit $rmcmd -f "$rmtmp" 2>/dev/null; :; }; }\ + || { + echo "$0: cannot unlink or rename $dst" >&2 + (exit 1); exit 1 + } + else + : + fi + } && -# Now rename the file to the real destination. + # Now rename the file to the real destination. + $doit $mvcmd "$dsttmp" "$dst" + } + } || exit 1 - $doit $rmcmd -f $dstdir/$dstfile && - $doit $mvcmd $dsttmp $dstdir/$dstfile + trap '' 0 + fi +done -fi && - - -exit 0 +# Local variables: +# eval: (add-hook 'write-file-hooks 'time-stamp) +# time-stamp-start: "scriptversion=" +# time-stamp-format: "%:y-%02m-%02d.%02H" +# time-stamp-end: "$" +# End: diff --git a/libpcre/libpcre.vcproj b/libpcre/libpcre.vcproj index 765c7678b..4cb4c6d3e 100644 --- a/libpcre/libpcre.vcproj +++ b/libpcre/libpcre.vcproj @@ -190,6 +190,14 @@ RelativePath=".\pcre_maketables.c" > + + + + @@ -206,6 +214,14 @@ RelativePath=".\pcre_try_flipped.c" > + + + + @@ -232,14 +248,6 @@ RelativePath=".\pcre_internal.h" > - - - - @@ -248,6 +256,14 @@ RelativePath=".\ucp.h" > + + + + chartables.c - -bcc32 -c -RT- -y- -v- -u- -P- -O2 -5 -DSTATIC -DVPCOMPAT -UDFTABLES -I%BORLAND%\include get.c maketables.c pcre.c study.c - -tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset -tlib pcre.lib +get.obj +maketables.obj +pcre.obj +study.obj +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj - -del *.obj *.exe *.tds *.bak >nul 2>nul - -echo --- -echo Now the library should be complete. Please check all messages above. -echo Don't care for warnings, it's OK. diff --git a/libpcre/missing b/libpcre/missing new file mode 100755 index 000000000..1c8ff7049 --- /dev/null +++ b/libpcre/missing @@ -0,0 +1,367 @@ +#! /bin/sh +# Common stub for a few missing GNU programs while installing. + +scriptversion=2006-05-10.23 + +# Copyright (C) 1996, 1997, 1999, 2000, 2002, 2003, 2004, 2005, 2006 +# Free Software Foundation, Inc. +# Originally by Fran,cois Pinard , 1996. + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2, or (at your option) +# any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA +# 02110-1301, USA. + +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +if test $# -eq 0; then + echo 1>&2 "Try \`$0 --help' for more information" + exit 1 +fi + +run=: +sed_output='s/.* --output[ =]\([^ ]*\).*/\1/p' +sed_minuso='s/.* -o \([^ ]*\).*/\1/p' + +# In the cases where this matters, `missing' is being run in the +# srcdir already. +if test -f configure.ac; then + configure_ac=configure.ac +else + configure_ac=configure.in +fi + +msg="missing on your system" + +case $1 in +--run) + # Try to run requested program, and just exit if it succeeds. + run= + shift + "$@" && exit 0 + # Exit code 63 means version mismatch. This often happens + # when the user try to use an ancient version of a tool on + # a file that requires a minimum version. In this case we + # we should proceed has if the program had been absent, or + # if --run hadn't been passed. + if test $? = 63; then + run=: + msg="probably too old" + fi + ;; + + -h|--h|--he|--hel|--help) + echo "\ +$0 [OPTION]... PROGRAM [ARGUMENT]... + +Handle \`PROGRAM [ARGUMENT]...' for when PROGRAM is missing, or return an +error status if there is no known handling for PROGRAM. + +Options: + -h, --help display this help and exit + -v, --version output version information and exit + --run try to run the given command, and emulate it if it fails + +Supported PROGRAM values: + aclocal touch file \`aclocal.m4' + autoconf touch file \`configure' + autoheader touch file \`config.h.in' + autom4te touch the output file, or create a stub one + automake touch all \`Makefile.in' files + bison create \`y.tab.[ch]', if possible, from existing .[ch] + flex create \`lex.yy.c', if possible, from existing .c + help2man touch the output file + lex create \`lex.yy.c', if possible, from existing .c + makeinfo touch the output file + tar try tar, gnutar, gtar, then tar without non-portable flags + yacc create \`y.tab.[ch]', if possible, from existing .[ch] + +Send bug reports to ." + exit $? + ;; + + -v|--v|--ve|--ver|--vers|--versi|--versio|--version) + echo "missing $scriptversion (GNU Automake)" + exit $? + ;; + + -*) + echo 1>&2 "$0: Unknown \`$1' option" + echo 1>&2 "Try \`$0 --help' for more information" + exit 1 + ;; + +esac + +# Now exit if we have it, but it failed. Also exit now if we +# don't have it and --version was passed (most likely to detect +# the program). +case $1 in + lex|yacc) + # Not GNU programs, they don't have --version. + ;; + + tar) + if test -n "$run"; then + echo 1>&2 "ERROR: \`tar' requires --run" + exit 1 + elif test "x$2" = "x--version" || test "x$2" = "x--help"; then + exit 1 + fi + ;; + + *) + if test -z "$run" && ($1 --version) > /dev/null 2>&1; then + # We have it, but it failed. + exit 1 + elif test "x$2" = "x--version" || test "x$2" = "x--help"; then + # Could not run --version or --help. This is probably someone + # running `$TOOL --version' or `$TOOL --help' to check whether + # $TOOL exists and not knowing $TOOL uses missing. + exit 1 + fi + ;; +esac + +# If it does not exist, or fails to run (possibly an outdated version), +# try to emulate it. +case $1 in + aclocal*) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified \`acinclude.m4' or \`${configure_ac}'. You might want + to install the \`Automake' and \`Perl' packages. Grab them from + any GNU archive site." + touch aclocal.m4 + ;; + + autoconf) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified \`${configure_ac}'. You might want to install the + \`Autoconf' and \`GNU m4' packages. Grab them from any GNU + archive site." + touch configure + ;; + + autoheader) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified \`acconfig.h' or \`${configure_ac}'. You might want + to install the \`Autoconf' and \`GNU m4' packages. Grab them + from any GNU archive site." + files=`sed -n 's/^[ ]*A[CM]_CONFIG_HEADER(\([^)]*\)).*/\1/p' ${configure_ac}` + test -z "$files" && files="config.h" + touch_files= + for f in $files; do + case $f in + *:*) touch_files="$touch_files "`echo "$f" | + sed -e 's/^[^:]*://' -e 's/:.*//'`;; + *) touch_files="$touch_files $f.in";; + esac + done + touch $touch_files + ;; + + automake*) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified \`Makefile.am', \`acinclude.m4' or \`${configure_ac}'. + You might want to install the \`Automake' and \`Perl' packages. + Grab them from any GNU archive site." + find . -type f -name Makefile.am -print | + sed 's/\.am$/.in/' | + while read f; do touch "$f"; done + ;; + + autom4te) + echo 1>&2 "\ +WARNING: \`$1' is needed, but is $msg. + You might have modified some files without having the + proper tools for further handling them. + You can get \`$1' as part of \`Autoconf' from any GNU + archive site." + + file=`echo "$*" | sed -n "$sed_output"` + test -z "$file" && file=`echo "$*" | sed -n "$sed_minuso"` + if test -f "$file"; then + touch $file + else + test -z "$file" || exec >$file + echo "#! /bin/sh" + echo "# Created by GNU Automake missing as a replacement of" + echo "# $ $@" + echo "exit 0" + chmod +x $file + exit 1 + fi + ;; + + bison|yacc) + echo 1>&2 "\ +WARNING: \`$1' $msg. You should only need it if + you modified a \`.y' file. You may need the \`Bison' package + in order for those modifications to take effect. You can get + \`Bison' from any GNU archive site." + rm -f y.tab.c y.tab.h + if test $# -ne 1; then + eval LASTARG="\${$#}" + case $LASTARG in + *.y) + SRCFILE=`echo "$LASTARG" | sed 's/y$/c/'` + if test -f "$SRCFILE"; then + cp "$SRCFILE" y.tab.c + fi + SRCFILE=`echo "$LASTARG" | sed 's/y$/h/'` + if test -f "$SRCFILE"; then + cp "$SRCFILE" y.tab.h + fi + ;; + esac + fi + if test ! -f y.tab.h; then + echo >y.tab.h + fi + if test ! -f y.tab.c; then + echo 'main() { return 0; }' >y.tab.c + fi + ;; + + lex|flex) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified a \`.l' file. You may need the \`Flex' package + in order for those modifications to take effect. You can get + \`Flex' from any GNU archive site." + rm -f lex.yy.c + if test $# -ne 1; then + eval LASTARG="\${$#}" + case $LASTARG in + *.l) + SRCFILE=`echo "$LASTARG" | sed 's/l$/c/'` + if test -f "$SRCFILE"; then + cp "$SRCFILE" lex.yy.c + fi + ;; + esac + fi + if test ! -f lex.yy.c; then + echo 'main() { return 0; }' >lex.yy.c + fi + ;; + + help2man) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified a dependency of a manual page. You may need the + \`Help2man' package in order for those modifications to take + effect. You can get \`Help2man' from any GNU archive site." + + file=`echo "$*" | sed -n "$sed_output"` + test -z "$file" && file=`echo "$*" | sed -n "$sed_minuso"` + if test -f "$file"; then + touch $file + else + test -z "$file" || exec >$file + echo ".ab help2man is required to generate this page" + exit 1 + fi + ;; + + makeinfo) + echo 1>&2 "\ +WARNING: \`$1' is $msg. You should only need it if + you modified a \`.texi' or \`.texinfo' file, or any other file + indirectly affecting the aspect of the manual. The spurious + call might also be the consequence of using a buggy \`make' (AIX, + DU, IRIX). You might want to install the \`Texinfo' package or + the \`GNU make' package. Grab either from any GNU archive site." + # The file to touch is that specified with -o ... + file=`echo "$*" | sed -n "$sed_output"` + test -z "$file" && file=`echo "$*" | sed -n "$sed_minuso"` + if test -z "$file"; then + # ... or it is the one specified with @setfilename ... + infile=`echo "$*" | sed 's/.* \([^ ]*\) *$/\1/'` + file=`sed -n ' + /^@setfilename/{ + s/.* \([^ ]*\) *$/\1/ + p + q + }' $infile` + # ... or it is derived from the source name (dir/f.texi becomes f.info) + test -z "$file" && file=`echo "$infile" | sed 's,.*/,,;s,.[^.]*$,,'`.info + fi + # If the file does not exist, the user really needs makeinfo; + # let's fail without touching anything. + test -f $file || exit 1 + touch $file + ;; + + tar) + shift + + # We have already tried tar in the generic part. + # Look for gnutar/gtar before invocation to avoid ugly error + # messages. + if (gnutar --version > /dev/null 2>&1); then + gnutar "$@" && exit 0 + fi + if (gtar --version > /dev/null 2>&1); then + gtar "$@" && exit 0 + fi + firstarg="$1" + if shift; then + case $firstarg in + *o*) + firstarg=`echo "$firstarg" | sed s/o//` + tar "$firstarg" "$@" && exit 0 + ;; + esac + case $firstarg in + *h*) + firstarg=`echo "$firstarg" | sed s/h//` + tar "$firstarg" "$@" && exit 0 + ;; + esac + fi + + echo 1>&2 "\ +WARNING: I can't seem to be able to run \`tar' with the given arguments. + You may want to install GNU tar or Free paxutils, or check the + command line arguments." + exit 1 + ;; + + *) + echo 1>&2 "\ +WARNING: \`$1' is needed, and is $msg. + You might have modified some files without having the + proper tools for further handling them. Check the \`README' file, + it often tells you about the needed prerequisites for installing + this package. You may also peek at any GNU archive site, in case + some other package would contain this missing \`$1' program." + exit 1 + ;; +esac + +exit 0 + +# Local variables: +# eval: (add-hook 'write-file-hooks 'time-stamp) +# time-stamp-start: "scriptversion=" +# time-stamp-format: "%:y-%02m-%02d.%02H" +# time-stamp-end: "$" +# End: diff --git a/libpcre/mkinstalldirs b/libpcre/mkinstalldirs deleted file mode 100755 index 6b3b5fc5d..000000000 --- a/libpcre/mkinstalldirs +++ /dev/null @@ -1,40 +0,0 @@ -#! /bin/sh -# mkinstalldirs --- make directory hierarchy -# Author: Noah Friedman -# Created: 1993-05-16 -# Public domain - -# $Id$ - -errstatus=0 - -for file -do - set fnord `echo ":$file" | sed -ne 's/^:\//#/;s/^://;s/\// /g;s/^#/\//;p'` - shift - - pathcomp= - for d - do - pathcomp="$pathcomp$d" - case "$pathcomp" in - -* ) pathcomp=./$pathcomp ;; - esac - - if test ! -d "$pathcomp"; then - echo "mkdir $pathcomp" - - mkdir "$pathcomp" || lasterr=$? - - if test ! -d "$pathcomp"; then - errstatus=$lasterr - fi - fi - - pathcomp="$pathcomp/" - done -done - -exit $errstatus - -# mkinstalldirs ends here diff --git a/libpcre/pcre-config.in b/libpcre/pcre-config.in new file mode 100644 index 000000000..3b52101b9 --- /dev/null +++ b/libpcre/pcre-config.in @@ -0,0 +1,69 @@ +#!/bin/sh + +prefix=@prefix@ +exec_prefix=@exec_prefix@ +exec_prefix_set=no + +usage="\ +Usage: pcre-config [--prefix] [--exec-prefix] [--version] [--libs] [--libs-posix] [--cflags] [--cflags-posix]" + +if test $# -eq 0; then + echo "${usage}" 1>&2 + exit 1 +fi + +libR= +case `uname -s` in + *SunOS*) + libR=" -R@libdir@" + ;; + *BSD*) + libR=" -Wl,-R@libdir@" + ;; +esac + +while test $# -gt 0; do + case "$1" in + -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + case $1 in + --prefix=*) + prefix=$optarg + if test $exec_prefix_set = no ; then + exec_prefix=$optarg + fi + ;; + --prefix) + echo $prefix + ;; + --exec-prefix=*) + exec_prefix=$optarg + exec_prefix_set=yes + ;; + --exec-prefix) + echo $exec_prefix + ;; + --version) + echo @PACKAGE_VERSION@ + ;; + --cflags | --cflags-posix) + if test @includedir@ != /usr/include ; then + includes=-I@includedir@ + fi + echo $includes + ;; + --libs-posix) + echo -L@libdir@$libR -lpcreposix -lpcre + ;; + --libs) + echo -L@libdir@$libR -lpcre + ;; + *) + echo "${usage}" 1>&2 + exit 1 + ;; + esac + shift +done diff --git a/libpcre/pcre.h b/libpcre/pcre.h index 8ca3aab1a..acbf28c52 100644 --- a/libpcre/pcre.h +++ b/libpcre/pcre.h @@ -5,7 +5,7 @@ /* This is the public header file for the PCRE library, to be #included by applications that call the PCRE functions. - Copyright (c) 1997-2005 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -41,46 +41,33 @@ POSSIBILITY OF SUCH DAMAGE. /* The current PCRE version information. */ -/* NOTES FOR FUTURE MAINTAINERS: Do not use numbers with leading zeros, because -they may be treated as octal constants. The PCRE_PRERELEASE feature is for -identifying release candidates. It might be defined as -RC2, for example. In -real releases, it should be defined empty. Do not change the alignment of these -statments. The code in ./configure greps out the version numbers by using "cut" -to get values from column 29 onwards. These are substituted into pcre-config -and libpcre.pc. The values are not put into configure.ac and substituted here -(which would simplify this issue) because that makes life harder for those who -cannot run ./configure. As it now stands, this file need not be edited in that -circumstance. */ +#define PCRE_MAJOR 7 +#define PCRE_MINOR 2 +#define PCRE_PRERELEASE +#define PCRE_DATE 2007-06-19 -#define PCRE_MAJOR 6 -#define PCRE_MINOR 7 -#define PCRE_PRERELEASE -#define PCRE_DATE 04-Jul-2006 - -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. -- COMMENTED OUT BECAUSE I COMPILE STATICALLY */ +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change an existing definition of PCRE_EXP_DECL. */ /* -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 # ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) +# define PCRE_EXP_DECL extern __declspec(dllimport) # endif # endif #endif */ -/* Otherwise, we use the standard "extern". */ +/* By default, we use the standard "extern" declarations. */ -#ifndef PCRE_DATA_SCOPE +#ifndef PCRE_EXP_DECL # ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" +# define PCRE_EXP_DECL extern "C" # else -# define PCRE_DATA_SCOPE extern +# define PCRE_EXP_DECL extern # endif #endif @@ -120,6 +107,8 @@ extern "C" { #define PCRE_NEWLINE_CR 0x00100000 #define PCRE_NEWLINE_LF 0x00200000 #define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* Exec-time and get/set-time error codes */ @@ -127,7 +116,8 @@ extern "C" { #define PCRE_ERROR_NULL (-2) #define PCRE_ERROR_BADOPTION (-3) #define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_NODE (-5) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ #define PCRE_ERROR_NOMEMORY (-6) #define PCRE_ERROR_NOSUBSTRING (-7) #define PCRE_ERROR_MATCHLIMIT (-8) @@ -144,6 +134,8 @@ extern "C" { #define PCRE_ERROR_DFA_WSSIZE (-19) #define PCRE_ERROR_DFA_RECURSE (-20) #define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) +#define PCRE_ERROR_BADNEWLINE (-23) /* Request types for pcre_fullinfo() */ @@ -160,6 +152,8 @@ extern "C" { #define PCRE_INFO_NAMETABLE 9 #define PCRE_INFO_STUDYSIZE 10 #define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 /* Request types for pcre_config(). Do not re-arrange, in order to remain compatible. */ @@ -238,52 +232,52 @@ that is triggered by the (?) regex item. For Virtual Pascal, these definitions have to take another form. */ #ifndef VPCOMPAT -PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_free)(void *); -PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); -PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); #else /* VPCOMPAT */ -PCRE_DATA_SCOPE void *pcre_malloc(size_t); -PCRE_DATA_SCOPE void pcre_free(void *); -PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t); -PCRE_DATA_SCOPE void pcre_stack_free(void *); -PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *); +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); #endif /* VPCOMPAT */ /* Exported PCRE functions */ -PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *, +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **, +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE int pcre_config(int, void *); -PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, int *, int, const char *, char *, int); -PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *, +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, int); -PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *, +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, const char *, int, int, int, int *, int , int *, int); -PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, int, int, int, int *, int); -PCRE_DATA_SCOPE void pcre_free_substring(const char *); -PCRE_DATA_SCOPE void pcre_free_substring_list(const char **); -PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int, +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, void *); -PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, int *, int, const char *, const char **); -PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *); -PCRE_DATA_SCOPE int pcre_get_stringtable_entries(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, char **, char **); -PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int, +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, const char **); -PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int, +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, const char ***); -PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *); -PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void); -PCRE_DATA_SCOPE int pcre_refcount(pcre *, int); -PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_DATA_SCOPE const char *pcre_version(void); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); #ifdef __cplusplus } /* extern "C" */ diff --git a/libpcre/pcre.h.generic b/libpcre/pcre.h.generic new file mode 100644 index 000000000..acbf28c52 --- /dev/null +++ b/libpcre/pcre.h.generic @@ -0,0 +1,286 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This is the public header file for the PCRE library, to be #included by +applications that call the PCRE functions. + + Copyright (c) 1997-2007 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifndef _PCRE_H +#define _PCRE_H + +/* The current PCRE version information. */ + +#define PCRE_MAJOR 7 +#define PCRE_MINOR 2 +#define PCRE_PRERELEASE +#define PCRE_DATE 2007-06-19 + +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change an existing definition of PCRE_EXP_DECL. */ + +/* +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 +# ifndef PCRE_STATIC +# define PCRE_EXP_DECL extern __declspec(dllimport) +# endif +# endif +#endif +*/ + +/* By default, we use the standard "extern" declarations. */ + +#ifndef PCRE_EXP_DECL +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +#endif + +/* Have to include stdlib.h in order to ensure that size_t is defined; +it is needed here for malloc. */ + +#include + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options */ + +#define PCRE_CASELESS 0x00000001 +#define PCRE_MULTILINE 0x00000002 +#define PCRE_DOTALL 0x00000004 +#define PCRE_EXTENDED 0x00000008 +#define PCRE_ANCHORED 0x00000010 +#define PCRE_DOLLAR_ENDONLY 0x00000020 +#define PCRE_EXTRA 0x00000040 +#define PCRE_NOTBOL 0x00000080 +#define PCRE_NOTEOL 0x00000100 +#define PCRE_UNGREEDY 0x00000200 +#define PCRE_NOTEMPTY 0x00000400 +#define PCRE_UTF8 0x00000800 +#define PCRE_NO_AUTO_CAPTURE 0x00001000 +#define PCRE_NO_UTF8_CHECK 0x00002000 +#define PCRE_AUTO_CALLOUT 0x00004000 +#define PCRE_PARTIAL 0x00008000 +#define PCRE_DFA_SHORTEST 0x00010000 +#define PCRE_DFA_RESTART 0x00020000 +#define PCRE_FIRSTLINE 0x00040000 +#define PCRE_DUPNAMES 0x00080000 +#define PCRE_NEWLINE_CR 0x00100000 +#define PCRE_NEWLINE_LF 0x00200000 +#define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 + +/* Exec-time and get/set-time error codes */ + +#define PCRE_ERROR_NOMATCH (-1) +#define PCRE_ERROR_NULL (-2) +#define PCRE_ERROR_BADOPTION (-3) +#define PCRE_ERROR_BADMAGIC (-4) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ +#define PCRE_ERROR_NOMEMORY (-6) +#define PCRE_ERROR_NOSUBSTRING (-7) +#define PCRE_ERROR_MATCHLIMIT (-8) +#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ +#define PCRE_ERROR_BADUTF8 (-10) +#define PCRE_ERROR_BADUTF8_OFFSET (-11) +#define PCRE_ERROR_PARTIAL (-12) +#define PCRE_ERROR_BADPARTIAL (-13) +#define PCRE_ERROR_INTERNAL (-14) +#define PCRE_ERROR_BADCOUNT (-15) +#define PCRE_ERROR_DFA_UITEM (-16) +#define PCRE_ERROR_DFA_UCOND (-17) +#define PCRE_ERROR_DFA_UMLIMIT (-18) +#define PCRE_ERROR_DFA_WSSIZE (-19) +#define PCRE_ERROR_DFA_RECURSE (-20) +#define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) +#define PCRE_ERROR_BADNEWLINE (-23) + +/* Request types for pcre_fullinfo() */ + +#define PCRE_INFO_OPTIONS 0 +#define PCRE_INFO_SIZE 1 +#define PCRE_INFO_CAPTURECOUNT 2 +#define PCRE_INFO_BACKREFMAX 3 +#define PCRE_INFO_FIRSTBYTE 4 +#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ +#define PCRE_INFO_FIRSTTABLE 5 +#define PCRE_INFO_LASTLITERAL 6 +#define PCRE_INFO_NAMEENTRYSIZE 7 +#define PCRE_INFO_NAMECOUNT 8 +#define PCRE_INFO_NAMETABLE 9 +#define PCRE_INFO_STUDYSIZE 10 +#define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 + +/* Request types for pcre_config(). Do not re-arrange, in order to remain +compatible. */ + +#define PCRE_CONFIG_UTF8 0 +#define PCRE_CONFIG_NEWLINE 1 +#define PCRE_CONFIG_LINK_SIZE 2 +#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 +#define PCRE_CONFIG_MATCH_LIMIT 4 +#define PCRE_CONFIG_STACKRECURSE 5 +#define PCRE_CONFIG_UNICODE_PROPERTIES 6 +#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 + +/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine +these bits, just add new ones on the end, in order to remain compatible. */ + +#define PCRE_EXTRA_STUDY_DATA 0x0001 +#define PCRE_EXTRA_MATCH_LIMIT 0x0002 +#define PCRE_EXTRA_CALLOUT_DATA 0x0004 +#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 + +/* Types */ + +struct real_pcre; /* declaration; the definition is private */ +typedef struct real_pcre pcre; + +/* When PCRE is compiled as a C++ library, the subject pointer type can be +replaced with a custom type. For conventional use, the public interface is a +const char *. */ + +#ifndef PCRE_SPTR +#define PCRE_SPTR const char * +#endif + +/* The structure for passing additional data to pcre_exec(). This is defined in +such as way as to be extensible. Always add new fields at the end, in order to +remain compatible. */ + +typedef struct pcre_extra { + unsigned long int flags; /* Bits for which fields are set */ + void *study_data; /* Opaque data from pcre_study() */ + unsigned long int match_limit; /* Maximum number of calls to match() */ + void *callout_data; /* Data passed back in callouts */ + const unsigned char *tables; /* Pointer to character tables */ + unsigned long int match_limit_recursion; /* Max recursive calls to match() */ +} pcre_extra; + +/* The structure for passing out data via the pcre_callout_function. We use a +structure so that new fields can be added on the end in future versions, +without changing the API of the function, thereby allowing old clients to work +without modification. */ + +typedef struct pcre_callout_block { + int version; /* Identifies version of block */ + /* ------------------------ Version 0 ------------------------------- */ + int callout_number; /* Number compiled into pattern */ + int *offset_vector; /* The offset vector */ + PCRE_SPTR subject; /* The subject being matched */ + int subject_length; /* The length of the subject */ + int start_match; /* Offset to start of this match attempt */ + int current_position; /* Where we currently are in the subject */ + int capture_top; /* Max current capture */ + int capture_last; /* Most recently closed capture */ + void *callout_data; /* Data passed in with the call */ + /* ------------------- Added for Version 1 -------------------------- */ + int pattern_position; /* Offset to next item in the pattern */ + int next_item_length; /* Length of next item in the pattern */ + /* ------------------------------------------------------------------ */ +} pcre_callout_block; + +/* Indirection for store get and free functions. These can be set to +alternative malloc/free functions if required. Special ones are used in the +non-recursive case for "frames". There is also an optional callout function +that is triggered by the (?) regex item. For Virtual Pascal, these definitions +have to take another form. */ + +#ifndef VPCOMPAT +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); +#else /* VPCOMPAT */ +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); +#endif /* VPCOMPAT */ + +/* Exported PCRE functions */ + +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, + const unsigned char *); +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, + int *, const unsigned char *); +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, + int *, int, const char *, char *, int); +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, + int); +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, + const char *, int, int, int, int *, int , int *, int); +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, + int, int, int, int *, int); +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, + void *); +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, + int *, int, const char *, const char **); +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, + char **, char **); +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, + const char **); +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, + const char ***); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcre.h */ diff --git a/libpcre/pcre.h.in b/libpcre/pcre.h.in index be1546c4e..6b157900b 100644 --- a/libpcre/pcre.h.in +++ b/libpcre/pcre.h.in @@ -2,10 +2,10 @@ * Perl-Compatible Regular Expressions * *************************************************/ -/* In its original form, this is the .in file that is transformed by -"configure" into pcre.h. +/* This is the public header file for the PCRE library, to be #included by +applications that call the PCRE functions. - Copyright (c) 1997-2005 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -39,34 +39,35 @@ POSSIBILITY OF SUCH DAMAGE. #ifndef _PCRE_H #define _PCRE_H -/* The file pcre.h is build by "configure". Do not edit it; instead -make changes to pcre.in. */ +/* The current PCRE version information. */ #define PCRE_MAJOR @PCRE_MAJOR@ #define PCRE_MINOR @PCRE_MINOR@ +#define PCRE_PRERELEASE @PCRE_PRERELEASE@ #define PCRE_DATE @PCRE_DATE@ -/* Win32 uses DLL by default; it needs special stuff for exported functions. */ +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change an existing definition of PCRE_EXP_DECL. */ -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else +/* +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 # ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) +# define PCRE_EXP_DECL extern __declspec(dllimport) # endif # endif #endif +*/ -/* For other operating systems, we use the standard "extern". */ +/* By default, we use the standard "extern" declarations. */ -#ifndef PCRE_DATA_SCOPE +#ifndef PCRE_EXP_DECL # ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" +# define PCRE_EXP_DECL extern "C" # else -# define PCRE_DATA_SCOPE extern +# define PCRE_EXP_DECL extern # endif #endif @@ -102,6 +103,12 @@ extern "C" { #define PCRE_DFA_SHORTEST 0x00010000 #define PCRE_DFA_RESTART 0x00020000 #define PCRE_FIRSTLINE 0x00040000 +#define PCRE_DUPNAMES 0x00080000 +#define PCRE_NEWLINE_CR 0x00100000 +#define PCRE_NEWLINE_LF 0x00200000 +#define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* Exec-time and get/set-time error codes */ @@ -109,7 +116,8 @@ extern "C" { #define PCRE_ERROR_NULL (-2) #define PCRE_ERROR_BADOPTION (-3) #define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_NODE (-5) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ #define PCRE_ERROR_NOMEMORY (-6) #define PCRE_ERROR_NOSUBSTRING (-7) #define PCRE_ERROR_MATCHLIMIT (-8) @@ -125,6 +133,9 @@ extern "C" { #define PCRE_ERROR_DFA_UMLIMIT (-18) #define PCRE_ERROR_DFA_WSSIZE (-19) #define PCRE_ERROR_DFA_RECURSE (-20) +#define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) +#define PCRE_ERROR_BADNEWLINE (-23) /* Request types for pcre_fullinfo() */ @@ -141,8 +152,11 @@ extern "C" { #define PCRE_INFO_NAMETABLE 9 #define PCRE_INFO_STUDYSIZE 10 #define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 -/* Request types for pcre_config() */ +/* Request types for pcre_config(). Do not re-arrange, in order to remain +compatible. */ #define PCRE_CONFIG_UTF8 0 #define PCRE_CONFIG_NEWLINE 1 @@ -151,19 +165,30 @@ extern "C" { #define PCRE_CONFIG_MATCH_LIMIT 4 #define PCRE_CONFIG_STACKRECURSE 5 #define PCRE_CONFIG_UNICODE_PROPERTIES 6 +#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -/* Bit flags for the pcre_extra structure */ +/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine +these bits, just add new ones on the end, in order to remain compatible. */ -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_STUDY_DATA 0x0001 +#define PCRE_EXTRA_MATCH_LIMIT 0x0002 +#define PCRE_EXTRA_CALLOUT_DATA 0x0004 +#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 /* Types */ struct real_pcre; /* declaration; the definition is private */ typedef struct real_pcre pcre; +/* When PCRE is compiled as a C++ library, the subject pointer type can be +replaced with a custom type. For conventional use, the public interface is a +const char *. */ + +#ifndef PCRE_SPTR +#define PCRE_SPTR const char * +#endif + /* The structure for passing additional data to pcre_exec(). This is defined in such as way as to be extensible. Always add new fields at the end, in order to remain compatible. */ @@ -174,6 +199,7 @@ typedef struct pcre_extra { unsigned long int match_limit; /* Maximum number of calls to match() */ void *callout_data; /* Data passed back in callouts */ const unsigned char *tables; /* Pointer to character tables */ + unsigned long int match_limit_recursion; /* Max recursive calls to match() */ } pcre_extra; /* The structure for passing out data via the pcre_callout_function. We use a @@ -186,7 +212,7 @@ typedef struct pcre_callout_block { /* ------------------------ Version 0 ------------------------------- */ int callout_number; /* Number compiled into pattern */ int *offset_vector; /* The offset vector */ - const char *subject; /* The subject being matched */ + PCRE_SPTR subject; /* The subject being matched */ int subject_length; /* The length of the subject */ int start_match; /* Offset to start of this match attempt */ int current_position; /* Where we currently are in the subject */ @@ -206,50 +232,52 @@ that is triggered by the (?) regex item. For Virtual Pascal, these definitions have to take another form. */ #ifndef VPCOMPAT -PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_free)(void *); -PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); -PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); #else /* VPCOMPAT */ -PCRE_DATA_SCOPE void *pcre_malloc(size_t); -PCRE_DATA_SCOPE void pcre_free(void *); -PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t); -PCRE_DATA_SCOPE void pcre_stack_free(void *); -PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *); +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); #endif /* VPCOMPAT */ /* Exported PCRE functions */ -PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *, +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **, +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE int pcre_config(int, void *); -PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, int *, int, const char *, char *, int); -PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *, +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, int); -PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *, +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, const char *, int, int, int, int *, int , int *, int); -PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, const char *, +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, int, int, int, int *, int); -PCRE_DATA_SCOPE void pcre_free_substring(const char *); -PCRE_DATA_SCOPE void pcre_free_substring_list(const char **); -PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int, +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, void *); -PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, int *, int, const char *, const char **); -PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *); -PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int, +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, + char **, char **); +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, const char **); -PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int, +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, const char ***); -PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *); -PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void); -PCRE_DATA_SCOPE int pcre_refcount(pcre *, int); -PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_DATA_SCOPE const char *pcre_version(void); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); #ifdef __cplusplus } /* extern "C" */ diff --git a/libpcre/pcre_chartables.c b/libpcre/pcre_chartables.c index d491433e2..6494d8e98 100644 --- a/libpcre/pcre_chartables.c +++ b/libpcre/pcre_chartables.c @@ -2,13 +2,25 @@ * Perl-Compatible Regular Expressions * *************************************************/ -/* This file is automatically written by the dftables auxiliary -program. If you edit it by hand, you might like to edit the Makefile to -prevent its ever being regenerated. +/* This file contains character tables that are used when no external tables +are passed to PCRE by the application that calls it. The tables are used only +for characters whose code values are less than 256. -This file contains the default tables for characters with codes less than -128 (ASCII characters). These tables are used when no external tables are -passed to PCRE. */ +This is a default version of the tables that assumes ASCII encoding. A program +called dftables (which is distributed with PCRE) can be used to build +alternative versions of this file. This is necessary if you are running in an +EBCDIC environment, or if you want to default to a different encoding, for +example ISO-8859-1. When dftables is run, it creates these tables in the +current locale. If PCRE is configured with --enable-rebuild-chartables, this +happens automatically. + +The following #include is present because without it gcc 4.x may remove the +array definition from the final binary if PCRE is built into a static library +and dead code stripping is activated. This leads to link errors. Pulling in the +header ensures that the array gets flagged as "someone outside this compilation +unit might reference this" and so it will always be supplied to the linker. */ + +#include "pcre_internal.h" const unsigned char _pcre_default_tables[] = { @@ -82,11 +94,10 @@ const unsigned char _pcre_default_tables[] = { 240,241,242,243,244,245,246,247, 248,249,250,251,252,253,254,255, -/* This table contains bit maps for various character classes. -Each map is 32 bytes long and the bits run from the least -significant end of each byte. The classes that have their own -maps are: space, xdigit, digit, upper, lower, word, graph -print, punct, and cntrl. Other classes are built from combinations. */ +/* This table contains bit maps for various character classes. Each map is 32 +bytes long and the bits run from the least significant end of each byte. The +classes that have their own maps are: space, xdigit, digit, upper, lower, word, +graph, print, punct, and cntrl. Other classes are built from combinations. */ 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, @@ -158,7 +169,7 @@ print, punct, and cntrl. Other classes are built from combinations. */ 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x00,0x00,0x80,0x10, /* X - _ */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ @@ -180,4 +191,4 @@ print, punct, and cntrl. Other classes are built from combinations. */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ -/* End of chartables.c */ +/* End of pcre_chartables.c */ diff --git a/libpcre/pcre_chartables.c.dist b/libpcre/pcre_chartables.c.dist new file mode 100644 index 000000000..6494d8e98 --- /dev/null +++ b/libpcre/pcre_chartables.c.dist @@ -0,0 +1,194 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This file contains character tables that are used when no external tables +are passed to PCRE by the application that calls it. The tables are used only +for characters whose code values are less than 256. + +This is a default version of the tables that assumes ASCII encoding. A program +called dftables (which is distributed with PCRE) can be used to build +alternative versions of this file. This is necessary if you are running in an +EBCDIC environment, or if you want to default to a different encoding, for +example ISO-8859-1. When dftables is run, it creates these tables in the +current locale. If PCRE is configured with --enable-rebuild-chartables, this +happens automatically. + +The following #include is present because without it gcc 4.x may remove the +array definition from the final binary if PCRE is built into a static library +and dead code stripping is activated. This leads to link errors. Pulling in the +header ensures that the array gets flagged as "someone outside this compilation +unit might reference this" and so it will always be supplied to the linker. */ + +#include "pcre_internal.h" + +const unsigned char _pcre_default_tables[] = { + +/* This table is a lower casing table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table is a case flipping table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 65, 66, 67, 68, 69, 70, 71, + 72, 73, 74, 75, 76, 77, 78, 79, + 80, 81, 82, 83, 84, 85, 86, 87, + 88, 89, 90,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table contains bit maps for various character classes. Each map is 32 +bytes long and the bits run from the least significant end of each byte. The +classes that have their own maps are: space, xdigit, digit, upper, lower, word, +graph, print, punct, and cntrl. Other classes are built from combinations. */ + + 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, + 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + +/* This table identifies various classes of character by individual bits: + 0x01 white space character + 0x02 letter + 0x04 decimal digit + 0x08 hexadecimal digit + 0x10 alphanumeric or '_' + 0x80 regular expression metacharacter or binary zero +*/ + + 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ + 0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ + 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ + 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ + 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ + +/* End of pcre_chartables.c */ diff --git a/libpcre/pcre_compile.c b/libpcre/pcre_compile.c index a91ae8861..c191539c8 100644 --- a/libpcre/pcre_compile.c +++ b/libpcre/pcre_compile.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,7 +42,11 @@ POSSIBILITY OF SUCH DAMAGE. supporting internal functions that are not used by other modules. */ -#define NLBLOCK cd /* The block containing newline information */ +#define NLBLOCK cd /* Block containing newline information */ +#define PSSTART start_pattern /* Field containing processed string start */ +#define PSEND end_pattern /* Field containing processed string end */ + + #include "pcre_internal.h" @@ -54,18 +58,28 @@ used by pcretest. DEBUG is not defined when building a production library. */ #endif +/* Macro for setting individual bits in class bitmaps. */ + +#define SETBIT(a,b) a[b/8] |= (1 << (b%8)) + /************************************************* * Code parameters and static tables * *************************************************/ -/* Maximum number of items on the nested bracket stacks at compile time. This -applies to the nesting of all kinds of parentheses. It does not limit -un-nested, non-capturing parentheses. This number can be made bigger if -necessary - it is used to dimension one int and one unsigned char vector at -compile time. */ +/* This value specifies the size of stack workspace that is used during the +first pre-compile phase that determines how much memory is required. The regex +is partly compiled into this space, but the compiled parts are discarded as +soon as they can be, so that hopefully there will never be an overrun. The code +does, however, check for an overrun. The largest amount I've seen used is 218, +so this number is very generous. -#define BRASTACK_SIZE 200 +The same workspace is used during the second, actual compile phase for +remembering forward references to groups so that they can be filled in at the +end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE +is 4 there is plenty of room. */ + +#define COMPILE_WORK_SIZE (4096) /* Table for handling escaped characters in the range '0'-'z'. Positive returns @@ -73,21 +87,21 @@ are simple data values; negative values are for special things like \d and so on. Zero means further processing is needed (for things like \x), or the escape is invalid. */ -#if !EBCDIC /* This is the "normal" table for ASCII systems */ +#ifndef EBCDIC /* This is the "normal" table for ASCII systems */ static const short int escapes[] = { 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */ - 0, 0, 0, 0, 0, 0, 0, 0, /* H - O */ --ESC_P, -ESC_Q, 0, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */ +-ESC_H, 0, 0, -ESC_K, 0, 0, 0, 0, /* H - O */ +-ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, -ESC_V, -ESC_W, /* P - W */ -ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */ - 0, 0, 0, 0, 0, 0, ESC_n, 0, /* h - o */ --ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, 0, -ESC_w, /* p - w */ +-ESC_h, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */ +-ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, -ESC_v, -ESC_w, /* p - w */ 0, 0, -ESC_z /* x - z */ }; -#else /* This is the "abnormal" table for EBCDIC systems */ +#else /* This is the "abnormal" table for EBCDIC systems */ static const short int escapes[] = { /* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', /* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, @@ -97,18 +111,18 @@ static const short int escapes[] = { /* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, /* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', /* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */ 0, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, 0, 'l', 0, ESC_n, 0, -ESC_p, +/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, +/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, /* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0, 0, -ESC_w, 0, +/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, /* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, /* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', /* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, /* D0 */ '}', 0, 0, 0, 0, 0, 0, -ESC_P, -/* D8 */-ESC_Q, 0, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0, 0, -ESC_W, -ESC_X, +/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, +/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, /* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, /* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 @@ -156,8 +170,13 @@ static const int posix_class_maps[] = { }; +#define STRING(a) # a +#define XSTRING(s) STRING(s) + /* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. */ +are passed to the outside world. Do not ever re-use any error number, because +they are documented. Always add a new error instead. Messages marked DEAD below +are no longer used. */ static const char *error_texts[] = { "no error", @@ -172,7 +191,7 @@ static const char *error_texts[] = { "range out of order in character class", "nothing to repeat", /* 10 */ - "operand of unlimited repeat could match the empty string", + "operand of unlimited repeat could match the empty string", /** DEAD **/ "internal error: unexpected repeat", "unrecognized character after (?", "POSIX named classes are supported only within a class", @@ -182,7 +201,7 @@ static const char *error_texts[] = { "erroffset passed as NULL", "unknown option bit(s) set", "missing ) after comment", - "parentheses nested too deeply", + "parentheses nested too deeply", /** DEAD **/ /* 20 */ "regular expression too large", "failed to get memory", @@ -194,12 +213,12 @@ static const char *error_texts[] = { "malformed number or name after (?(", "conditional group contains more than two branches", "assertion expected after (?(", - "(?R or (?digits must be followed by )", + "(?R or (?[+-]digits must be followed by )", /* 30 */ "unknown POSIX class name", "POSIX collating elements are not supported", "this version of PCRE is not compiled with PCRE_UTF8 support", - "spare error", + "spare error", /** DEAD **/ "character value in \\x{...} sequence is too large", /* 35 */ "invalid condition (?(0)", @@ -210,18 +229,26 @@ static const char *error_texts[] = { /* 40 */ "recursive call could loop indefinitely", "unrecognized character after (?P", - "syntax error after (?P", + "syntax error in subpattern name (missing terminator)", "two named subpatterns have the same name", "invalid UTF-8 string", /* 45 */ "support for \\P, \\p, and \\X has not been compiled", "malformed \\P or \\p sequence", "unknown property name after \\P or \\p", - "subpattern name is too long (maximum 32 characters)", - "too many named subpatterns (maximum 10,000)", + "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)", + "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")", /* 50 */ "repeated subpattern is too long", - "octal value is greater than \\377 (not in UTF-8 mode)" + "octal value is greater than \\377 (not in UTF-8 mode)", + "internal error: overran compiling workspace", + "internal error: previously-checked referenced subpattern not found", + "DEFINE group contains more than one branch", + /* 55 */ + "repeating a DEFINE group is not allowed", + "inconsistent NEWLINE options", + "\\g is not followed by a braced name or an optionally braced non-zero number", + "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number" }; @@ -241,7 +268,7 @@ For convenience, we use the same bit definitions as in chartables: Then we can use ctype_digit and ctype_xdigit in the code. */ -#if !EBCDIC /* This is the "normal" case, for ASCII systems */ +#ifndef EBCDIC /* This is the "normal" case, for ASCII systems */ static const unsigned char digitab[] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ @@ -277,7 +304,7 @@ static const unsigned char digitab[] = 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ -#else /* This is the "abnormal" case, for EBCDIC systems */ +#else /* This is the "abnormal" case, for EBCDIC systems */ static const unsigned char digitab[] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ @@ -291,7 +318,7 @@ static const unsigned char digitab[] = 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- ¬ */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ @@ -325,7 +352,7 @@ static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- ¬ */ + 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ @@ -352,8 +379,8 @@ static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ /* Definition to allow mutual recursion */ static BOOL - compile_regex(int, int, int *, uschar **, const uschar **, int *, BOOL, int, - int *, int *, branch_chain *, compile_data *); + compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int, + int *, int *, branch_chain *, compile_data *, int *); @@ -363,9 +390,11 @@ static BOOL /* This function is called when a \ has been encountered. It either returns a positive value for a simple escape such as \n, or a negative value which -encodes one of the more complicated things such as \d. When UTF-8 is enabled, -a positive value greater than 255 may be returned. On entry, ptr is pointing at -the \. On exit, it is on the final character of the escape sequence. +encodes one of the more complicated things such as \d. A backreference to group +n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When +UTF-8 is enabled, a positive value greater than 255 may be returned. On entry, +ptr is pointing at the \. On exit, it is on the final character of the escape +sequence. Arguments: ptrptr points to the pattern position pointer @@ -398,11 +427,11 @@ if (c == 0) *errorcodeptr = ERR1; a table. A non-zero result is something that can be returned immediately. Otherwise further processing may be required. */ -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ else if (c < '0' || c > 'z') {} /* Not alphameric */ else if ((i = escapes[c - '0']) != 0) c = i; -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ else if ((i = escapes[c - 0x48]) != 0) c = i; #endif @@ -412,6 +441,8 @@ else if ((i = escapes[c - 0x48]) != 0) c = i; else { const uschar *oldptr; + BOOL braced, negated; + switch (c) { /* A number of Perl escapes are not handled by PCRE. We give an explicit @@ -425,6 +456,59 @@ else *errorcodeptr = ERR37; break; + /* \g must be followed by a number, either plain or braced. If positive, it + is an absolute backreference. If negative, it is a relative backreference. + This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a + reference to a named group. This is part of Perl's movement towards a + unified syntax for back references. As this is synonymous with \k{name}, we + fudge it up by pretending it really was \k. */ + + case 'g': + if (ptr[1] == '{') + { + const uschar *p; + for (p = ptr+2; *p != 0 && *p != '}'; p++) + if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break; + if (*p != 0 && *p != '}') + { + c = -ESC_k; + break; + } + braced = TRUE; + ptr++; + } + else braced = FALSE; + + if (ptr[1] == '-') + { + negated = TRUE; + ptr++; + } + else negated = FALSE; + + c = 0; + while ((digitab[ptr[1]] & ctype_digit) != 0) + c = c * 10 + *(++ptr) - '0'; + + if (c == 0 || (braced && *(++ptr) != '}')) + { + *errorcodeptr = ERR57; + return 0; + } + + if (negated) + { + if (c > bracount) + { + *errorcodeptr = ERR15; + return 0; + } + c = bracount - (c - 1); + } + + c = -(ESC_REF + c); + break; + /* The handling of escape sequences consisting of a string of digits starting with one that is not zero is not straightforward. By experiment, the way Perl works seems to be as follows: @@ -495,10 +579,10 @@ else if (c == 0 && cc == '0') continue; /* Leading zeroes */ count++; -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ if (cc >= 'a') cc -= 32; /* Convert to upper case */ c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */ c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10)); #endif @@ -522,17 +606,19 @@ else { int cc; /* Some compilers don't like ++ */ cc = *(++ptr); /* in initializers */ -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ if (cc >= 'a') cc -= 32; /* Convert to upper case */ c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (cc <= 'z') cc += 64; /* Convert to upper case */ c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10)); #endif } break; - /* Other special escapes not starting with a digit are straightforward */ + /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. + This coding is ASCII-specific, but then the whole concept of \cx is + ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ case 'c': c = *(++ptr); @@ -542,14 +628,10 @@ else return 0; } - /* A letter is upper-cased; then the 0x40 bit is flipped. This coding - is ASCII-specific, but then the whole concept of \cx is ASCII-specific. - (However, an EBCDIC equivalent has now been added.) */ - -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ if (c >= 'a' && c <= 'z') c -= 32; c ^= 0x40; -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (c >= 'a' && c <= 'z') c += 64; c ^= 0xC0; #endif @@ -772,42 +854,111 @@ return p; /************************************************* -* Find forward referenced named subpattern * +* Find forward referenced subpattern * *************************************************/ -/* This function scans along a pattern looking for capturing subpatterns, and -counting them. If it finds a named pattern that matches the name it is given, -it returns its number. This is used for forward references to named -subpatterns. We know that if (?P< is encountered, the name will be terminated -by '>' because that is checked in the first pass. +/* This function scans along a pattern's text looking for capturing +subpatterns, and counting them. If it finds a named pattern that matches the +name it is given, it returns its number. Alternatively, if the name is NULL, it +returns when it reaches a given numbered subpattern. This is used for forward +references to subpatterns. We know that if (?P< is encountered, the name will +be terminated by '>' because that is checked in the first pass. Arguments: - pointer current position in the pattern - count current count of capturing parens - name name to seek - namelen name length + ptr current position in the pattern + count current count of capturing parens so far encountered + name name to seek, or NULL if seeking a numbered subpattern + lorn name length, or subpattern number if name is NULL + xmode TRUE if we are in /x mode Returns: the number of the named subpattern, or -1 if not found */ static int -find_named_parens(const uschar *ptr, int count, const uschar *name, int namelen) +find_parens(const uschar *ptr, int count, const uschar *name, int lorn, + BOOL xmode) { const uschar *thisname; + for (; *ptr != 0; ptr++) { - if (*ptr == '\\' && ptr[1] != 0) { ptr++; continue; } + int term; + + /* Skip over backslashed characters and also entire \Q...\E */ + + if (*ptr == '\\') + { + if (*(++ptr) == 0) return -1; + if (*ptr == 'Q') for (;;) + { + while (*(++ptr) != 0 && *ptr != '\\'); + if (*ptr == 0) return -1; + if (*(++ptr) == 'E') break; + } + continue; + } + + /* Skip over character classes */ + + if (*ptr == '[') + { + while (*(++ptr) != ']') + { + if (*ptr == '\\') + { + if (*(++ptr) == 0) return -1; + if (*ptr == 'Q') for (;;) + { + while (*(++ptr) != 0 && *ptr != '\\'); + if (*ptr == 0) return -1; + if (*(++ptr) == 'E') break; + } + continue; + } + } + continue; + } + + /* Skip comments in /x mode */ + + if (xmode && *ptr == '#') + { + while (*(++ptr) != 0 && *ptr != '\n'); + if (*ptr == 0) return -1; + continue; + } + + /* An opening parens must now be a real metacharacter */ + if (*ptr != '(') continue; - if (ptr[1] != '?') { count++; continue; } - if (ptr[2] == '(') { ptr += 2; continue; } - if (ptr[2] != 'P' || ptr[3] != '<') continue; + if (ptr[1] != '?') + { + count++; + if (name == NULL && count == lorn) return count; + continue; + } + + ptr += 2; + if (*ptr == 'P') ptr++; /* Allow optional P */ + + /* We have to disambiguate (? */ + + if ((*ptr != '<' || ptr[1] == '!' || ptr[1] == '=') && + *ptr != '\'') + continue; + count++; - ptr += 4; + + if (name == NULL && count == lorn) return count; + term = *ptr++; + if (term == '<') term = '>'; thisname = ptr; - while (*ptr != '>') ptr++; - if (namelen == ptr - thisname && strncmp(name, thisname, namelen) == 0) + while (*ptr != term) ptr++; + if (name != NULL && lorn == ptr - thisname && + strncmp((const char *)name, (const char *)thisname, lorn) == 0) return count; } + return -1; } @@ -862,7 +1013,8 @@ for (;;) case OP_CALLOUT: case OP_CREF: - case OP_BRANUMBER: + case OP_RREF: + case OP_DEF: code += _pcre_OP_lengths[*code]; break; @@ -907,14 +1059,14 @@ for (;;) { int d; register int op = *cc; - if (op >= OP_BRA) op = OP_BRA; switch (op) { + case OP_CBRA: case OP_BRA: case OP_ONCE: case OP_COND: - d = find_fixedlength(cc, options); + d = find_fixedlength(cc + ((op == OP_CBRA)? 2:0), options); if (d < 0) return d; branchlength += d; do cc += GET(cc, 1); while (*cc == OP_ALT); @@ -949,8 +1101,9 @@ for (;;) /* Skip over things that don't match chars */ case OP_REVERSE: - case OP_BRANUMBER: case OP_CREF: + case OP_RREF: + case OP_DEF: case OP_OPT: case OP_CALLOUT: case OP_SOD: @@ -1094,25 +1247,23 @@ for (;;) if (c == OP_XCLASS) code += GET(code, 1); - /* Handle bracketed group */ + /* Handle capturing bracket */ - else if (c > OP_BRA) + else if (c == OP_CBRA) { - int n = c - OP_BRA; - if (n > EXTRACT_BASIC_MAX) n = GET2(code, 2+LINK_SIZE); + int n = GET2(code, 1+LINK_SIZE); if (n == number) return (uschar *)code; - code += _pcre_OP_lengths[OP_BRA]; + code += _pcre_OP_lengths[c]; } - /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes - that are followed by a character may be followed by a multi-byte character. - The length in the table is a minimum, so we have to scan along to skip the - extra bytes. All opcodes are less than 128, so we can use relatively - efficient code. */ + /* In UTF-8 mode, opcodes that are followed by a character may be followed by + a multi-byte character. The length in the table is a minimum, so we have to + arrange to skip the extra bytes. */ else { code += _pcre_OP_lengths[c]; +#ifdef SUPPORT_UTF8 if (utf8) switch(c) { case OP_CHAR: @@ -1120,15 +1271,20 @@ for (;;) case OP_EXACT: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_QUERY: case OP_MINQUERY: - while ((*code & 0xc0) == 0x80) code++; + case OP_POSQUERY: + if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; break; } +#endif } } } @@ -1164,22 +1320,15 @@ for (;;) if (c == OP_XCLASS) code += GET(code, 1); - /* All bracketed groups have the same length. */ - - else if (c > OP_BRA) - { - code += _pcre_OP_lengths[OP_BRA]; - } - /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes that are followed by a character may be followed by a multi-byte character. - The length in the table is a minimum, so we have to scan along to skip the - extra bytes. All opcodes are less than 128, so we can use relatively - efficient code. */ + The length in the table is a minimum, so we have to arrange to skip the extra + bytes. */ else { code += _pcre_OP_lengths[c]; +#ifdef SUPPORT_UTF8 if (utf8) switch(c) { case OP_CHAR: @@ -1187,15 +1336,20 @@ for (;;) case OP_EXACT: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_QUERY: case OP_MINQUERY: - while ((*code & 0xc0) == 0x80) code++; + case OP_POSQUERY: + if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; break; } +#endif } } } @@ -1207,10 +1361,11 @@ for (;;) *************************************************/ /* This function scans through a branch of a compiled pattern to see whether it -can match the empty string or not. It is called only from could_be_empty() -below. Note that first_significant_code() skips over assertions. If we hit an -unclosed bracket, we return "empty" - this means we've struck an inner bracket -whose current branch will already have been scanned. +can match the empty string or not. It is called from could_be_empty() +below and from compile_branch() when checking for an unlimited repeat of a +group that can match nothing. Note that first_significant_code() skips over +assertions. If we hit an unclosed bracket, we return "empty" - this means we've +struck an inner bracket whose current branch will already have been scanned. Arguments: code points to start of search @@ -1224,7 +1379,7 @@ static BOOL could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8) { register int c; -for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); +for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE); code < endcode; code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE)) { @@ -1232,7 +1387,19 @@ for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); c = *code; - if (c >= OP_BRA) + /* Groups with zero repeats can of course be empty; skip them. */ + + if (c == OP_BRAZERO || c == OP_BRAMINZERO) + { + code += _pcre_OP_lengths[c]; + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* For other groups, scan the branches. */ + + if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE) { BOOL empty_branch; if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ @@ -1248,11 +1415,13 @@ for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); } while (*code == OP_ALT); if (!empty_branch) return FALSE; /* All branches are non-empty */ - code += 1 + LINK_SIZE; c = *code; + continue; } - else switch (c) + /* Handle the other opcodes */ + + switch (c) { /* Check for quantifiers after a class */ @@ -1308,12 +1477,15 @@ for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); case OP_NOT: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_EXACT: case OP_NOTPLUS: case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: case OP_NOTEXACT: case OP_TYPEPLUS: case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: case OP_TYPEEXACT: return FALSE; @@ -1325,16 +1497,19 @@ for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); case OP_ALT: return TRUE; - /* In UTF-8 mode, STAR, MINSTAR, QUERY, MINQUERY, UPTO, and MINUPTO may be - followed by a multibyte character */ + /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, + MINUPTO, and POSUPTO may be followed by a multibyte character */ #ifdef SUPPORT_UTF8 case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: if (utf8) while ((code[2] & 0xc0) == 0x80) code++; break; #endif @@ -1452,26 +1627,57 @@ earlier groups that are outside the current group). However, when a group is optional (i.e. the minimum quantifier is zero), OP_BRAZERO is inserted before it, after it has been compiled. This means that any OP_RECURSE items within it that refer to the group itself or any contained groups have to have their -offsets adjusted. That is the job of this function. Before it is called, the -partially compiled regex must be temporarily terminated with OP_END. +offsets adjusted. That one of the jobs of this function. Before it is called, +the partially compiled regex must be temporarily terminated with OP_END. + +This function has been extended with the possibility of forward references for +recursions and subroutine calls. It must also check the list of such references +for the group we are dealing with. If it finds that one of the recursions in +the current group is on this list, it adjusts the offset in the list, not the +value in the reference (which is a group number). Arguments: group points to the start of the group adjust the amount by which the group is to be moved utf8 TRUE in UTF-8 mode cd contains pointers to tables etc. + save_hwm the hwm forward reference pointer at the start of the group Returns: nothing */ static void -adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd) +adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd, + uschar *save_hwm) { uschar *ptr = group; while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL) { - int offset = GET(ptr, 1); - if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); + int offset; + uschar *hc; + + /* See if this recursion is on the forward reference list. If so, adjust the + reference. */ + + for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE) + { + offset = GET(hc, 0); + if (cd->start_code + offset == ptr + 1) + { + PUT(hc, 0, offset + adjust); + break; + } + } + + /* Otherwise, adjust the recursion offset if it's after the start of this + group. */ + + if (hc >= cd->hwm) + { + offset = GET(ptr, 1); + if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); + } + ptr += 1 + LINK_SIZE; } } @@ -1550,12 +1756,13 @@ Yield: TRUE when range returned; FALSE when no more */ static BOOL -get_othercase_range(int *cptr, int d, int *ocptr, int *odptr) +get_othercase_range(unsigned int *cptr, unsigned int d, unsigned int *ocptr, + unsigned int *odptr) { -int c, othercase, next; +unsigned int c, othercase, next; for (c = *cptr; c <= d; c++) - { if ((othercase = _pcre_ucp_othercase(c)) >= 0) break; } + { if ((othercase = _pcre_ucp_othercase(c)) != NOTACHAR) break; } if (c > d) return FALSE; @@ -1576,17 +1783,351 @@ return TRUE; #endif /* SUPPORT_UCP */ + +/************************************************* +* Check if auto-possessifying is possible * +*************************************************/ + +/* This function is called for unlimited repeats of certain items, to see +whether the next thing could possibly match the repeated item. If not, it makes +sense to automatically possessify the repeated item. + +Arguments: + op_code the repeated op code + this data for this item, depends on the opcode + utf8 TRUE in UTF-8 mode + utf8_char used for utf8 character bytes, NULL if not relevant + ptr next character in pattern + options options bits + cd contains pointers to tables etc. + +Returns: TRUE if possessifying is wanted +*/ + +static BOOL +check_auto_possessive(int op_code, int item, BOOL utf8, uschar *utf8_char, + const uschar *ptr, int options, compile_data *cd) +{ +int next; + +/* Skip whitespace and comments in extended mode */ + +if ((options & PCRE_EXTENDED) != 0) + { + for (;;) + { + while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; + if (*ptr == '#') + { + while (*(++ptr) != 0) + if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } + } + else break; + } + } + +/* If the next item is one that we can handle, get its value. A non-negative +value is a character, a negative value is an escape value. */ + +if (*ptr == '\\') + { + int temperrorcode = 0; + next = check_escape(&ptr, &temperrorcode, cd->bracount, options, FALSE); + if (temperrorcode != 0) return FALSE; + ptr++; /* Point after the escape sequence */ + } + +else if ((cd->ctypes[*ptr] & ctype_meta) == 0) + { +#ifdef SUPPORT_UTF8 + if (utf8) { GETCHARINC(next, ptr); } else +#endif + next = *ptr++; + } + +else return FALSE; + +/* Skip whitespace and comments in extended mode */ + +if ((options & PCRE_EXTENDED) != 0) + { + for (;;) + { + while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; + if (*ptr == '#') + { + while (*(++ptr) != 0) + if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } + } + else break; + } + } + +/* If the next thing is itself optional, we have to give up. */ + +if (*ptr == '*' || *ptr == '?' || strncmp((char *)ptr, "{0,", 3) == 0) + return FALSE; + +/* Now compare the next item with the previous opcode. If the previous is a +positive single character match, "item" either contains the character or, if +"item" is greater than 127 in utf8 mode, the character's bytes are in +utf8_char. */ + + +/* Handle cases when the next item is a character. */ + +if (next >= 0) switch(op_code) + { + case OP_CHAR: +#ifdef SUPPORT_UTF8 + if (utf8 && item > 127) { GETCHAR(item, utf8_char); } +#endif + return item != next; + + /* For CHARNC (caseless character) we must check the other case. If we have + Unicode property support, we can use it to test the other case of + high-valued characters. */ + + case OP_CHARNC: +#ifdef SUPPORT_UTF8 + if (utf8 && item > 127) { GETCHAR(item, utf8_char); } +#endif + if (item == next) return FALSE; +#ifdef SUPPORT_UTF8 + if (utf8) + { + unsigned int othercase; + if (next < 128) othercase = cd->fcc[next]; else +#ifdef SUPPORT_UCP + othercase = _pcre_ucp_othercase((unsigned int)next); +#else + othercase = NOTACHAR; +#endif + return (unsigned int)item != othercase; + } + else +#endif /* SUPPORT_UTF8 */ + return (item != cd->fcc[next]); /* Non-UTF-8 mode */ + + /* For OP_NOT, "item" must be a single-byte character. */ + + case OP_NOT: + if (next < 0) return FALSE; /* Not a character */ + if (item == next) return TRUE; + if ((options & PCRE_CASELESS) == 0) return FALSE; +#ifdef SUPPORT_UTF8 + if (utf8) + { + unsigned int othercase; + if (next < 128) othercase = cd->fcc[next]; else +#ifdef SUPPORT_UCP + othercase = _pcre_ucp_othercase(next); +#else + othercase = NOTACHAR; +#endif + return (unsigned int)item == othercase; + } + else +#endif /* SUPPORT_UTF8 */ + return (item == cd->fcc[next]); /* Non-UTF-8 mode */ + + case OP_DIGIT: + return next > 127 || (cd->ctypes[next] & ctype_digit) == 0; + + case OP_NOT_DIGIT: + return next <= 127 && (cd->ctypes[next] & ctype_digit) != 0; + + case OP_WHITESPACE: + return next > 127 || (cd->ctypes[next] & ctype_space) == 0; + + case OP_NOT_WHITESPACE: + return next <= 127 && (cd->ctypes[next] & ctype_space) != 0; + + case OP_WORDCHAR: + return next > 127 || (cd->ctypes[next] & ctype_word) == 0; + + case OP_NOT_WORDCHAR: + return next <= 127 && (cd->ctypes[next] & ctype_word) != 0; + + case OP_HSPACE: + case OP_NOT_HSPACE: + switch(next) + { + case 0x09: + case 0x20: + case 0xa0: + case 0x1680: + case 0x180e: + case 0x2000: + case 0x2001: + case 0x2002: + case 0x2003: + case 0x2004: + case 0x2005: + case 0x2006: + case 0x2007: + case 0x2008: + case 0x2009: + case 0x200A: + case 0x202f: + case 0x205f: + case 0x3000: + return op_code != OP_HSPACE; + default: + return op_code == OP_HSPACE; + } + + case OP_VSPACE: + case OP_NOT_VSPACE: + switch(next) + { + case 0x0a: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x85: + case 0x2028: + case 0x2029: + return op_code != OP_VSPACE; + default: + return op_code == OP_VSPACE; + } + + default: + return FALSE; + } + + +/* Handle the case when the next item is \d, \s, etc. */ + +switch(op_code) + { + case OP_CHAR: + case OP_CHARNC: +#ifdef SUPPORT_UTF8 + if (utf8 && item > 127) { GETCHAR(item, utf8_char); } +#endif + switch(-next) + { + case ESC_d: + return item > 127 || (cd->ctypes[item] & ctype_digit) == 0; + + case ESC_D: + return item <= 127 && (cd->ctypes[item] & ctype_digit) != 0; + + case ESC_s: + return item > 127 || (cd->ctypes[item] & ctype_space) == 0; + + case ESC_S: + return item <= 127 && (cd->ctypes[item] & ctype_space) != 0; + + case ESC_w: + return item > 127 || (cd->ctypes[item] & ctype_word) == 0; + + case ESC_W: + return item <= 127 && (cd->ctypes[item] & ctype_word) != 0; + + case ESC_h: + case ESC_H: + switch(item) + { + case 0x09: + case 0x20: + case 0xa0: + case 0x1680: + case 0x180e: + case 0x2000: + case 0x2001: + case 0x2002: + case 0x2003: + case 0x2004: + case 0x2005: + case 0x2006: + case 0x2007: + case 0x2008: + case 0x2009: + case 0x200A: + case 0x202f: + case 0x205f: + case 0x3000: + return -next != ESC_h; + default: + return -next == ESC_h; + } + + case ESC_v: + case ESC_V: + switch(item) + { + case 0x0a: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x85: + case 0x2028: + case 0x2029: + return -next != ESC_v; + default: + return -next == ESC_v; + } + + default: + return FALSE; + } + + case OP_DIGIT: + return next == -ESC_D || next == -ESC_s || next == -ESC_W || + next == -ESC_h || next == -ESC_v; + + case OP_NOT_DIGIT: + return next == -ESC_d; + + case OP_WHITESPACE: + return next == -ESC_S || next == -ESC_d || next == -ESC_w; + + case OP_NOT_WHITESPACE: + return next == -ESC_s || next == -ESC_h || next == -ESC_v; + + case OP_HSPACE: + return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w; + + case OP_NOT_HSPACE: + return next == -ESC_h; + + /* Can't have \S in here because VT matches \S (Perl anomaly) */ + case OP_VSPACE: + return next == -ESC_V || next == -ESC_d || next == -ESC_w; + + case OP_NOT_VSPACE: + return next == -ESC_v; + + case OP_WORDCHAR: + return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v; + + case OP_NOT_WORDCHAR: + return next == -ESC_w || next == -ESC_d; + + default: + return FALSE; + } + +/* Control does not reach here */ +} + + + /************************************************* * Compile one branch * *************************************************/ -/* Scan the pattern, compiling it into the code vector. If the options are +/* Scan the pattern, compiling it into the a vector. If the options are changed during the branch, the pointer is used to change the external options -bits. +bits. This function is used during the pre-compile phase when we are trying +to find out the amount of memory needed, as well as during the real compile +phase. The value of lengthptr distinguishes the two phases. Arguments: optionsptr pointer to the option bits - brackets points to number of extracting brackets used codeptr points to the pointer to the current code point ptrptr points to the current pattern pointer errorcodeptr points to error code variable @@ -1594,15 +2135,17 @@ Arguments: reqbyteptr set to the last literal character required, else < 0 bcptr points to current branch chain cd contains pointers to tables etc. + lengthptr NULL during the real compile phase + points to length accumulator during pre-compile phase Returns: TRUE on success FALSE, with *errorcodeptr set non-zero on error */ static BOOL -compile_branch(int *optionsptr, int *brackets, uschar **codeptr, - const uschar **ptrptr, int *errorcodeptr, int *firstbyteptr, - int *reqbyteptr, branch_chain *bcptr, compile_data *cd) +compile_branch(int *optionsptr, uschar **codeptr, const uschar **ptrptr, + int *errorcodeptr, int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, + compile_data *cd, int *lengthptr) { int repeat_type, op_type; int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ @@ -1613,8 +2156,11 @@ int zeroreqbyte, zerofirstbyte; int req_caseopt, reqvary, tempreqvary; int options = *optionsptr; int after_manual_callout = 0; +int length_prevgroup = 0; register int c; register uschar *code = *codeptr; +uschar *last_code = code; +uschar *orig_code = code; uschar *tempcode; BOOL inescq = FALSE; BOOL groupsetfirstbyte = FALSE; @@ -1622,6 +2168,7 @@ const uschar *ptr = *ptrptr; const uschar *tempptr; uschar *previous = NULL; uschar *previous_callout = NULL; +uschar *save_hwm = NULL; uschar classbits[32]; #ifdef SUPPORT_UTF8 @@ -1631,6 +2178,11 @@ uschar *class_utf8data; uschar utf8_char[6]; #else BOOL utf8 = FALSE; +uschar *utf8_char = NULL; +#endif + +#ifdef DEBUG +if (lengthptr != NULL) DPRINTF((">> start branch\n")); #endif /* Set up the default and non-default settings for greediness */ @@ -1664,20 +2216,78 @@ for (;; ptr++) BOOL negate_class; BOOL possessive_quantifier; BOOL is_quantifier; + BOOL is_recurse; + BOOL reset_bracount; int class_charcount; int class_lastchar; int newoptions; int recno; + int refsign; int skipbytes; int subreqbyte; int subfirstbyte; + int terminator; int mclength; uschar mcbuffer[8]; - /* Next byte in the pattern */ + /* Get next byte in the pattern */ c = *ptr; + /* If we are in the pre-compile phase, accumulate the length used for the + previous cycle of this loop. */ + + if (lengthptr != NULL) + { +#ifdef DEBUG + if (code > cd->hwm) cd->hwm = code; /* High water info */ +#endif + if (code > cd->start_workspace + COMPILE_WORK_SIZE) /* Check for overrun */ + { + *errorcodeptr = ERR52; + goto FAILED; + } + + /* There is at least one situation where code goes backwards: this is the + case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, + the class is simply eliminated. However, it is created first, so we have to + allow memory for it. Therefore, don't ever reduce the length at this point. + */ + + if (code < last_code) code = last_code; + *lengthptr += code - last_code; + DPRINTF(("length=%d added %d c=%c\n", *lengthptr, code - last_code, c)); + + /* If "previous" is set and it is not at the start of the work space, move + it back to there, in order to avoid filling up the work space. Otherwise, + if "previous" is NULL, reset the current code pointer to the start. */ + + if (previous != NULL) + { + if (previous > orig_code) + { + memmove(orig_code, previous, code - previous); + code -= previous - orig_code; + previous = orig_code; + } + } + else code = orig_code; + + /* Remember where this code item starts so we can pick up the length + next time round. */ + + last_code = code; + } + + /* In the real compile phase, just check the workspace used by the forward + reference list. */ + + else if (cd->hwm > cd->start_workspace + COMPILE_WORK_SIZE) + { + *errorcodeptr = ERR52; + goto FAILED; + } + /* If in \Q...\E, check for the end; if not, we have a literal */ if (inescq && c != 0) @@ -1692,7 +2302,8 @@ for (;; ptr++) { if (previous_callout != NULL) { - complete_callout(previous_callout, ptr, cd); + if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ + complete_callout(previous_callout, ptr, cd); previous_callout = NULL; } if ((options & PCRE_AUTO_CALLOUT) != 0) @@ -1713,7 +2324,8 @@ for (;; ptr++) if (!is_quantifier && previous_callout != NULL && after_manual_callout-- <= 0) { - complete_callout(previous_callout, ptr, cd); + if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ + complete_callout(previous_callout, ptr, cd); previous_callout = NULL; } @@ -1724,12 +2336,12 @@ for (;; ptr++) if ((cd->ctypes[c] & ctype_space) != 0) continue; if (c == '#') { - while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; - if (*ptr != 0) + while (*(++ptr) != 0) { - ptr += cd->nllen - 1; - continue; + if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; } } + if (*ptr != 0) continue; + /* Else fall through to handle end of string */ c = 0; } @@ -1745,17 +2357,23 @@ for (;; ptr++) switch(c) { - /* The branch terminates at end of string, |, or ). */ - - case 0: - case '|': + /* ===================================================================*/ + case 0: /* The branch terminates at string end */ + case '|': /* or | or ) */ case ')': *firstbyteptr = firstbyte; *reqbyteptr = reqbyte; *codeptr = code; *ptrptr = ptr; + if (lengthptr != NULL) + { + *lengthptr += code - last_code; /* To include callout length */ + DPRINTF((">> end branch\n")); + } return TRUE; + + /* ===================================================================*/ /* Handle single-character metacharacters. In multiline mode, ^ disables the setting of any following char as a first character. */ @@ -1784,6 +2402,8 @@ for (;; ptr++) *code++ = OP_ANY; break; + + /* ===================================================================*/ /* Character classes. If the included characters are all < 256, we build a 32-byte bitmap of the permitted characters, except in the special case where there is only one such character. For negated classes, we build the @@ -1822,32 +2442,32 @@ for (;; ptr++) } /* Keep a count of chars with values < 256 so that we can optimize the case - of just a single character (as long as it's < 256). For higher valued UTF-8 - characters, we don't yet do any optimization. */ + of just a single character (as long as it's < 256). However, For higher + valued UTF-8 characters, we don't yet do any optimization. */ class_charcount = 0; class_lastchar = -1; -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; /* No chars >= 256 */ - class_utf8data = code + LINK_SIZE + 34; /* For UTF-8 items */ -#endif - - /* Initialize the 32-char bit map to all zeros. We have to build the - map in a temporary bit of store, in case the class contains only 1 - character (< 256), because in that case the compiled code doesn't use the - bit map. */ + /* Initialize the 32-char bit map to all zeros. We build the map in a + temporary bit of memory, in case the class contains only 1 character (less + than 256), because in that case the compiled code doesn't use the bit map. + */ memset(classbits, 0, 32 * sizeof(uschar)); - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. The first pass - through the regex checked the overall syntax, so we don't need to be very - strict here. At the start of the loop, c contains the first byte of the - character. */ +#ifdef SUPPORT_UTF8 + class_utf8 = FALSE; /* No chars >= 256 */ + class_utf8data = code + LINK_SIZE + 2; /* For UTF-8 items */ +#endif - do + /* Process characters until ] is reached. By writing this as a "do" it + means that an initial ] is taken as a data character. At the start of the + loop, c contains the first byte of the character. */ + + if (c != 0) do { + const uschar *oldptr; + #ifdef SUPPORT_UTF8 if (utf8 && c > 127) { /* Braces are required because the */ @@ -1859,13 +2479,13 @@ for (;; ptr++) if (inescq) { - if (c == '\\' && ptr[1] == 'E') + if (c == '\\' && ptr[1] == 'E') /* If we are at \E */ { - inescq = FALSE; - ptr++; - continue; + inescq = FALSE; /* Reset literal state */ + ptr++; /* Skip the 'E' */ + continue; /* Carry on with next */ } - else goto LONE_SINGLE_CHARACTER; + goto CHECK_RANGE; /* Could be range if \E follows */ } /* Handle POSIX class names. Perl allows a negation extension of the @@ -1928,12 +2548,12 @@ for (;; ptr++) tabopt = posix_class_maps[posix_class + 2]; if (taboffset >= 0) - { + { if (tabopt >= 0) for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; - else + else for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; - } + } /* Not see if we need to remove any special characters. An option value of 1 removes vertical space and 2 removes underscore. */ @@ -1947,7 +2567,7 @@ for (;; ptr++) if (local_negate) for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; - else + else for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; ptr = tempptr + 1; @@ -1956,19 +2576,20 @@ for (;; ptr++) } /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. Escaped items are checked for - validity in the pre-compiling pass. The sequence \b is a special case. - Inside a class (and only there) it is treated as backspace. Elsewhere - it marks a word boundary. Other escapes have preset maps ready to - or into the one we are building. We assume they have more than one + of the specials, which just set a flag. The sequence \b is a special + case. Inside a class (and only there) it is treated as backspace. + Elsewhere it marks a word boundary. Other escapes have preset maps ready + to or into the one we are building. We assume they have more than one character in them, so set class_charcount bigger than one. */ if (c == '\\') { - c = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); + c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); + if (*errorcodeptr != 0) goto FAILED; if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */ else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */ + else if (-c == ESC_R) c = 'R'; /* \R is literal R in a class */ else if (-c == ESC_Q) /* Handle start of quoted string */ { if (ptr[1] == '\\' && ptr[2] == 'E') @@ -1983,7 +2604,10 @@ for (;; ptr++) { register const uschar *cbits = cd->cbits; class_charcount += 2; /* Greater than 1 is what matters */ - switch (-c) + + /* Save time by not doing this in the pre-compile phase. */ + + if (lengthptr == NULL) switch (-c) { case ESC_d: for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; @@ -2011,52 +2635,218 @@ for (;; ptr++) classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ continue; -#ifdef SUPPORT_UCP - case ESC_p: - case ESC_P: - { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - if (ptype < 0) goto FAILED; - class_utf8 = TRUE; - *class_utf8data++ = ((-c == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_utf8data++ = ptype; - *class_utf8data++ = pdata; - class_charcount -= 2; /* Not a < 256 character */ - } + case ESC_E: /* Perl ignores an orphan \E */ continue; -#endif - /* Unrecognized escapes are faulted if PCRE is running in its - strict mode. By default, for compatibility with Perl, they are - treated as literals. */ - - default: - if ((options & PCRE_EXTRA) != 0) - { - *errorcodeptr = ERR7; - goto FAILED; - } - c = *ptr; /* The final character */ - class_charcount -= 2; /* Undo the default count from above */ + default: /* Not recognized; fall through */ + break; /* Need "default" setting to stop compiler warning. */ } + + /* In the pre-compile phase, just do the recognition. */ + + else if (c == -ESC_d || c == -ESC_D || c == -ESC_w || + c == -ESC_W || c == -ESC_s || c == -ESC_S) continue; + + /* We need to deal with \H, \h, \V, and \v in both phases because + they use extra memory. */ + + if (-c == ESC_h) + { + SETBIT(classbits, 0x09); /* VT */ + SETBIT(classbits, 0x20); /* SPACE */ + SETBIT(classbits, 0xa0); /* NSBP */ +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data); + } +#endif + continue; + } + + if (-c == ESC_H) + { + for (c = 0; c < 32; c++) + { + int x = 0xff; + switch (c) + { + case 0x09/8: x ^= 1 << (0x09%8); break; + case 0x20/8: x ^= 1 << (0x20%8); break; + case 0xa0/8: x ^= 1 << (0xa0%8); break; + default: break; + } + classbits[c] |= x; + } + +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); + } +#endif + continue; + } + + if (-c == ESC_v) + { + SETBIT(classbits, 0x0a); /* LF */ + SETBIT(classbits, 0x0b); /* VT */ + SETBIT(classbits, 0x0c); /* FF */ + SETBIT(classbits, 0x0d); /* CR */ + SETBIT(classbits, 0x85); /* NEL */ +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); + } +#endif + continue; + } + + if (-c == ESC_V) + { + for (c = 0; c < 32; c++) + { + int x = 0xff; + switch (c) + { + case 0x0a/8: x ^= 1 << (0x0a%8); + x ^= 1 << (0x0b%8); + x ^= 1 << (0x0c%8); + x ^= 1 << (0x0d%8); + break; + case 0x85/8: x ^= 1 << (0x85%8); break; + default: break; + } + classbits[c] |= x; + } + +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); + } +#endif + continue; + } + + /* We need to deal with \P and \p in both phases. */ + +#ifdef SUPPORT_UCP + if (-c == ESC_p || -c == ESC_P) + { + BOOL negated; + int pdata; + int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); + if (ptype < 0) goto FAILED; + class_utf8 = TRUE; + *class_utf8data++ = ((-c == ESC_p) != negated)? + XCL_PROP : XCL_NOTPROP; + *class_utf8data++ = ptype; + *class_utf8data++ = pdata; + class_charcount -= 2; /* Not a < 256 character */ + continue; + } +#endif + /* Unrecognized escapes are faulted if PCRE is running in its + strict mode. By default, for compatibility with Perl, they are + treated as literals. */ + + if ((options & PCRE_EXTRA) != 0) + { + *errorcodeptr = ERR7; + goto FAILED; + } + + class_charcount -= 2; /* Undo the default count from above */ + c = *ptr; /* Get the final character and fall through */ } /* Fall through if we have a single character (c >= 0). This may be - > 256 in UTF-8 mode. */ + greater than 256 in UTF-8 mode. */ } /* End of backslash handling */ /* A single character may be followed by '-' to form a range. However, Perl does not permit ']' to be the end of the range. A '-' character - here is treated as a literal. */ + at the end is treated as a literal. Perl ignores orphaned \E sequences + entirely. The code for handling \Q and \E is messy. */ - if (ptr[1] == '-' && ptr[2] != ']') + CHECK_RANGE: + while (ptr[1] == '\\' && ptr[2] == 'E') + { + inescq = FALSE; + ptr += 2; + } + + oldptr = ptr; + + if (!inescq && ptr[1] == '-') { int d; ptr += 2; + while (*ptr == '\\' && ptr[1] == 'E') ptr += 2; + + /* If we hit \Q (not followed by \E) at this point, go into escaped + mode. */ + + while (*ptr == '\\' && ptr[1] == 'Q') + { + ptr += 2; + if (*ptr == '\\' && ptr[1] == 'E') { ptr += 2; continue; } + inescq = TRUE; + break; + } + + if (*ptr == 0 || (!inescq && *ptr == ']')) + { + ptr = oldptr; + goto LONE_SINGLE_CHARACTER; + } #ifdef SUPPORT_UTF8 if (utf8) @@ -2071,27 +2861,34 @@ for (;; ptr++) not any of the other escapes. Perl 5.6 treats a hyphen as a literal in such circumstances. */ - if (d == '\\') + if (!inescq && d == '\\') { - const uschar *oldptr = ptr; - d = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); + d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); + if (*errorcodeptr != 0) goto FAILED; - /* \b is backslash; \X is literal X; any other special means the '-' - was literal */ + /* \b is backslash; \X is literal X; \R is literal R; any other + special means the '-' was literal */ if (d < 0) { if (d == -ESC_b) d = '\b'; - else if (d == -ESC_X) d = 'X'; else + else if (d == -ESC_X) d = 'X'; + else if (d == -ESC_R) d = 'R'; else { - ptr = oldptr - 2; + ptr = oldptr; goto LONE_SINGLE_CHARACTER; /* A few lines below */ } } } - /* The check that the two values are in the correct order happens in - the pre-pass. Optimize one-character ranges */ + /* Check that the two values are in the correct order. Optimize + one-character ranges */ + + if (d < c) + { + *errorcodeptr = ERR8; + goto FAILED; + } if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ @@ -2112,19 +2909,23 @@ for (;; ptr++) #ifdef SUPPORT_UCP if ((options & PCRE_CASELESS) != 0) { - int occ, ocd; - int cc = c; - int origd = d; + unsigned int occ, ocd; + unsigned int cc = c; + unsigned int origd = d; while (get_othercase_range(&cc, origd, &occ, &ocd)) { - if (occ >= c && ocd <= d) continue; /* Skip embedded ranges */ + if (occ >= (unsigned int)c && + ocd <= (unsigned int)d) + continue; /* Skip embedded ranges */ - if (occ < c && ocd >= c - 1) /* Extend the basic range */ + if (occ < (unsigned int)c && + ocd >= (unsigned int)c - 1) /* Extend the basic range */ { /* if there is overlap, */ c = occ; /* noting that if occ < c */ continue; /* we can't have ocd > d */ } /* because a subrange is */ - if (ocd > d && occ <= d + 1) /* always shorter than */ + if (ocd > (unsigned int)d && + occ <= (unsigned int)d + 1) /* always shorter than */ { /* the basic range. */ d = ocd; continue; @@ -2172,7 +2973,12 @@ for (;; ptr++) ranges that lie entirely within 0-127 when there is UCP support; else for partial ranges without UCP support. */ - for (; c <= d; c++) + class_charcount += d - c + 1; + class_lastchar = d; + + /* We can save a bit of time by skipping this in the pre-compile. */ + + if (lengthptr == NULL) for (; c <= d; c++) { classbits[c/8] |= (1 << (c&7)); if ((options & PCRE_CASELESS) != 0) @@ -2180,8 +2986,6 @@ for (;; ptr++) int uc = cd->fcc[c]; /* flip case */ classbits[uc/8] |= (1 << (uc&7)); } - class_charcount++; /* in case a one-char range */ - class_lastchar = c; } continue; /* Go get the next char in the class */ @@ -2205,8 +3009,8 @@ for (;; ptr++) #ifdef SUPPORT_UCP if ((options & PCRE_CASELESS) != 0) { - int othercase; - if ((othercase = _pcre_ucp_othercase(c)) >= 0) + unsigned int othercase; + if ((othercase = _pcre_ucp_othercase(c)) != NOTACHAR) { *class_utf8data++ = XCL_SINGLE; class_utf8data += _pcre_ord2utf8(othercase, class_utf8data); @@ -2231,10 +3035,15 @@ for (;; ptr++) } } - /* Loop until ']' reached; the check for end of string happens inside the - loop. This "while" is the end of the "do" above. */ + /* Loop until ']' reached. This "while" is the end of the "do" above. */ - while ((c = *(++ptr)) != ']' || inescq); + while ((c = *(++ptr)) != 0 && (c != ']' || inescq)); + + if (c == 0) /* Missing terminating ']' */ + { + *errorcodeptr = ERR6; + goto FAILED; + } /* If class_charcount is 1, we saw precisely one character whose value is less than 256. In non-UTF-8 mode we can always optimize. In UTF-8 mode, we @@ -2298,7 +3107,7 @@ for (;; ptr++) /* If there are characters with values > 255, we have to compile an extended class, with its own opcode. If there are no characters < 256, - we can omit the bitmap. */ + we can omit the bitmap in the actual compiled code. */ #ifdef SUPPORT_UTF8 if (class_utf8) @@ -2308,24 +3117,17 @@ for (;; ptr++) code += LINK_SIZE; *code = negate_class? XCL_NOT : 0; - /* If the map is required, install it, and move on to the end of - the extra data */ + /* If the map is required, move up the extra data to make room for it; + otherwise just move the code pointer to the end of the extra data. */ if (class_charcount > 0) { *code++ |= XCL_MAP; + memmove(code + 32, code, class_utf8data - code); memcpy(code, classbits, 32); - code = class_utf8data; - } - - /* If the map is not required, slide down the extra data. */ - - else - { - int len = class_utf8data - (code + 33); - memmove(code + 1, code + 33, len); - code += len + 1; + code = class_utf8data + 32; } + else code = class_utf8data; /* Now fill in the complete length of the item */ @@ -2342,7 +3144,8 @@ for (;; ptr++) if (negate_class) { *code++ = OP_NCLASS; - for (c = 0; c < 32; c++) code[c] = ~classbits[c]; + if (lengthptr == NULL) /* Save time in the pre-compile phase */ + for (c = 0; c < 32; c++) code[c] = ~classbits[c]; } else { @@ -2352,6 +3155,8 @@ for (;; ptr++) code += 32; break; + + /* ===================================================================*/ /* Various kinds of repeat; '{' is not necessarily a quantifier, but this has been tested above. */ @@ -2419,20 +3224,6 @@ for (;; ptr++) } else repeat_type = greedy_default; - /* If previous was a recursion, we need to wrap it inside brackets so that - it can be replicated if necessary. */ - - if (*previous == OP_RECURSE) - { - memmove(previous + 1 + LINK_SIZE, previous, 1 + LINK_SIZE); - code += 1 + LINK_SIZE; - *previous = OP_BRA; - PUT(previous, 1, code - previous); - *code = OP_KET; - PUT(code, 1, code - previous); - code += 1 + LINK_SIZE; - } - /* If previous was a character match, abolish the item and generate a repeat item instead. If a char item has a minumum of more than one, ensure that it is set in reqbyte - it might not be if a sequence such as x{3} is @@ -2466,18 +3257,40 @@ for (;; ptr++) if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt; } + /* If the repetition is unlimited, it pays to see if the next thing on + the line is something that cannot possibly match this character. If so, + automatically possessifying this item gains some performance in the case + where the match fails. */ + + if (!possessive_quantifier && + repeat_max < 0 && + check_auto_possessive(*previous, c, utf8, utf8_char, ptr + 1, + options, cd)) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + } + goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ } /* If previous was a single negated character ([^a] or similar), we use one of the special opcodes, replacing it. The code is shared with single- character repeats by setting opt_type to add a suitable offset into - repeat_type. OP_NOT is currently used only for single-byte chars. */ + repeat_type. We can also test for auto-possessification. OP_NOT is + currently used only for single-byte chars. */ else if (*previous == OP_NOT) { op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ c = previous[1]; + if (!possessive_quantifier && + repeat_max < 0 && + check_auto_possessive(OP_NOT, c, utf8, NULL, ptr + 1, options, cd)) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + } goto OUTPUT_SINGLE_REPEAT; } @@ -2495,6 +3308,14 @@ for (;; ptr++) op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ c = *previous; + if (!possessive_quantifier && + repeat_max < 0 && + check_auto_possessive(c, 0, utf8, NULL, ptr + 1, options, cd)) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + } + OUTPUT_SINGLE_REPEAT: if (*previous == OP_PROP || *previous == OP_NOTPROP) { @@ -2535,7 +3356,7 @@ for (;; ptr++) } /* A repeat minimum of 1 is optimized into some special cases. If the - maximum is unlimited, we use OP_PLUS. Otherwise, the original item it + maximum is unlimited, we use OP_PLUS. Otherwise, the original item is left in place and, if the maximum is greater than 1, we use OP_UPTO with one less than the maximum. */ @@ -2588,7 +3409,8 @@ for (;; ptr++) } /* Else insert an UPTO if the max is greater than the min, again - preceded by the character, for the previously inserted code. */ + preceded by the character, for the previously inserted code. If the + UPTO is just for 1 instance, we can use QUERY instead. */ else if (repeat_max != repeat_min) { @@ -2607,8 +3429,16 @@ for (;; ptr++) *code++ = prop_value; } repeat_max -= repeat_min; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); + + if (repeat_max == 1) + { + *code++ = OP_QUERY + repeat_type; + } + else + { + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max); + } } } @@ -2675,14 +3505,30 @@ for (;; ptr++) /* If previous was a bracket group, we may have to replicate it in certain cases. */ - else if (*previous >= OP_BRA || *previous == OP_ONCE || - *previous == OP_COND) + else if (*previous == OP_BRA || *previous == OP_CBRA || + *previous == OP_ONCE || *previous == OP_COND) { register int i; int ketoffset = 0; int len = code - previous; uschar *bralink = NULL; + /* Repeating a DEFINE group is pointless */ + + if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) + { + *errorcodeptr = ERR55; + goto FAILED; + } + + /* This is a paranoid check to stop integer overflow later on */ + + if (len > MAX_DUPLENGTH) + { + *errorcodeptr = ERR50; + goto FAILED; + } + /* If the maximum repeat count is unlimited, find the end of the bracket by scanning through from the start, and compute the offset back to it from the current code pointer. There may be an OP_OPT setting following @@ -2717,13 +3563,14 @@ for (;; ptr++) /* If the maximum is 1 or unlimited, we just have to stick in the BRAZERO and do no more at this point. However, we do need to adjust any OP_RECURSE calls inside the group that refer to the group itself or - any internal group, because the offset is from the start of the whole - regex. Temporarily terminate the pattern while doing this. */ + any internal or forward referenced group, because the offset is from + the start of the whole regex. Temporarily terminate the pattern while + doing this. */ if (repeat_max <= 1) { *code = OP_END; - adjust_recurse(previous, 1, utf8, cd); + adjust_recurse(previous, 1, utf8, cd, save_hwm); memmove(previous+1, previous, len); code++; *previous++ = OP_BRAZERO + repeat_type; @@ -2741,7 +3588,7 @@ for (;; ptr++) { int offset; *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd); + adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd, save_hwm); memmove(previous + 2 + LINK_SIZE, previous, len); code += 2 + LINK_SIZE; *previous++ = OP_BRAZERO + repeat_type; @@ -2761,19 +3608,41 @@ for (;; ptr++) /* If the minimum is greater than zero, replicate the group as many times as necessary, and adjust the maximum to the number of subsequent copies that we need. If we set a first char from the group, and didn't - set a required char, copy the latter from the former. */ + set a required char, copy the latter from the former. If there are any + forward reference subroutine calls in the group, there will be entries on + the workspace list; replicate these with an appropriate increment. */ else { if (repeat_min > 1) { - if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; - for (i = 1; i < repeat_min; i++) + /* In the pre-compile phase, we don't actually do the replication. We + just adjust the length as if we had. */ + + if (lengthptr != NULL) + *lengthptr += (repeat_min - 1)*length_prevgroup; + + /* This is compiling for real */ + + else { - memcpy(code, previous, len); - code += len; + if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; + for (i = 1; i < repeat_min; i++) + { + uschar *hc; + uschar *this_hwm = cd->hwm; + memcpy(code, previous, len); + for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) + { + PUT(cd->hwm, 0, GET(hc, 0) + len); + cd->hwm += LINK_SIZE; + } + save_hwm = this_hwm; + code += len; + } } } + if (repeat_max > 0) repeat_max -= repeat_min; } @@ -2781,12 +3650,27 @@ for (;; ptr++) the maximum is limited, it replicates the group in a nested fashion, remembering the bracket starts on a stack. In the case of a zero minimum, the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. */ + the number of additional copies needed. Again, we must remember to + replicate entries on the forward reference list. */ if (repeat_max >= 0) { - for (i = repeat_max - 1; i >= 0; i--) + /* In the pre-compile phase, we don't actually do the replication. We + just adjust the length as if we had. For each repetition we must add 1 + to the length for BRAZERO and for all but the last repetition we must + add 2 + 2*LINKSIZE to allow for the nesting that occurs. */ + + if (lengthptr != NULL && repeat_max > 0) + *lengthptr += repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - + 2 - 2*LINK_SIZE; /* Last one doesn't nest */ + + /* This is compiling for real */ + + else for (i = repeat_max - 1; i >= 0; i--) { + uschar *hc; + uschar *this_hwm = cd->hwm; + *code++ = OP_BRAZERO + repeat_type; /* All but the final copy start a new nesting, maintaining the @@ -2802,6 +3686,12 @@ for (;; ptr++) } memcpy(code, previous, len); + for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) + { + PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); + cd->hwm += LINK_SIZE; + } + save_hwm = this_hwm; code += len; } @@ -2824,9 +3714,34 @@ for (;; ptr++) /* If the maximum is unlimited, set a repeater in the final copy. We can't just offset backwards from the current code point, because we don't know if there's been an options resetting after the ket. The - correct offset was computed above. */ + correct offset was computed above. - else code[-ketoffset] = OP_KETRMAX + repeat_type; + Then, when we are doing the actual compile phase, check to see whether + this group is a non-atomic one that could match an empty string. If so, + convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so + that runtime checking can be done. [This check is also applied to + atomic groups at runtime, but in a different way.] */ + + else + { + uschar *ketcode = code - ketoffset; + uschar *bracode = ketcode - GET(ketcode, 1); + *ketcode = OP_KETRMAX + repeat_type; + if (lengthptr == NULL && *bracode != OP_ONCE) + { + uschar *scode = bracode; + do + { + if (could_be_empty_branch(scode, ketcode, utf8)) + { + *bracode += OP_SBRA - OP_BRA; + break; + } + scode += GET(scode, 1); + } + while (*scode == OP_ALT); + } + } } /* Else there's some kind of shambles */ @@ -2837,22 +3752,53 @@ for (;; ptr++) goto FAILED; } - /* If the character following a repeat is '+', we wrap the entire repeated - item inside OP_ONCE brackets. This is just syntactic sugar, taken from - Sun's Java package. The repeated item starts at tempcode, not at previous, - which might be the first part of a string whose (former) last char we - repeated. However, we don't support '+' after a greediness '?'. */ + /* If the character following a repeat is '+', or if certain optimization + tests above succeeded, possessive_quantifier is TRUE. For some of the + simpler opcodes, there is an special alternative opcode for this. For + anything else, we wrap the entire repeated item inside OP_ONCE brackets. + The '+' notation is just syntactic sugar, taken from Sun's Java package, + but the special opcodes can optimize it a bit. The repeated item starts at + tempcode, not at previous, which might be the first part of a string whose + (former) last char we repeated. + + Possessifying an 'exact' quantifier has no effect, so we can ignore it. But + an 'upto' may follow. We skip over an 'exact' item, and then test the + length of what remains before proceeding. */ if (possessive_quantifier) { - int len = code - tempcode; - memmove(tempcode + 1+LINK_SIZE, tempcode, len); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); + int len; + if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT || + *tempcode == OP_NOTEXACT) + tempcode += _pcre_OP_lengths[*tempcode]; + len = code - tempcode; + if (len > 0) switch (*tempcode) + { + case OP_STAR: *tempcode = OP_POSSTAR; break; + case OP_PLUS: *tempcode = OP_POSPLUS; break; + case OP_QUERY: *tempcode = OP_POSQUERY; break; + case OP_UPTO: *tempcode = OP_POSUPTO; break; + + case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; + case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; + case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; + case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; + + case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; + case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; + case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; + case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; + + default: + memmove(tempcode + 1+LINK_SIZE, tempcode, len); + code += 1 + LINK_SIZE; + len += 1 + LINK_SIZE; + tempcode[0] = OP_ONCE; + *code++ = OP_KET; + PUTINC(code, 0, len); + PUT(tempcode, 1, len); + break; + } } /* In all case we no longer have a previous item. We also set the @@ -2865,162 +3811,311 @@ for (;; ptr++) break; - /* Start of nested bracket sub-expression, or comment or lookahead or - lookbehind or option setting or condition. First deal with special things - that can come after a bracket; all are introduced by ?, and the appearance - of any of them means that this is not a referencing group. They were - checked for validity in the first pass over the string, so we don't have to - check for syntax errors here. */ + /* ===================================================================*/ + /* Start of nested parenthesized sub-expression, or comment or lookahead or + lookbehind or option setting or condition or all the other extended + parenthesis forms. First deal with the specials; all are introduced by ?, + and the appearance of any of them means that this is not a capturing + group. */ case '(': newoptions = options; skipbytes = 0; + bravalue = OP_CBRA; + save_hwm = cd->hwm; + reset_bracount = FALSE; if (*(++ptr) == '?') { - int set, unset; + int i, set, unset, namelen; int *optset; + const uschar *name; + uschar *slot; switch (*(++ptr)) { case '#': /* Comment; skip to ket */ ptr++; - while (*ptr != ')') ptr++; + while (*ptr != 0 && *ptr != ')') ptr++; + if (*ptr == 0) + { + *errorcodeptr = ERR18; + goto FAILED; + } continue; - case ':': /* Non-extracting bracket */ + + /* ------------------------------------------------------------ */ + case '|': /* Reset capture count for each branch */ + reset_bracount = TRUE; + /* Fall through */ + + /* ------------------------------------------------------------ */ + case ':': /* Non-capturing bracket */ bravalue = OP_BRA; ptr++; break; + + /* ------------------------------------------------------------ */ case '(': bravalue = OP_COND; /* Conditional group */ - /* A condition can be a number, referring to a numbered group, a name, - referring to a named group, 'R', referring to recursion, or an - assertion. There are two unfortunate ambiguities, caused by history. - (a) 'R' can be the recursive thing or the name 'R', and (b) a number - could be a name that consists of digits. In both cases, we look for a - name first; if not found, we try the other cases. If the first - character after (?( is a word character, we know the rest up to ) will - also be word characters because the syntax was checked in the first - pass. */ + /* A condition can be an assertion, a number (referring to a numbered + group), a name (referring to a named group), or 'R', referring to + recursion. R and R&name are also permitted for recursion tests. - if ((cd->ctypes[ptr[1]] & ctype_word) != 0) + There are several syntaxes for testing a named group: (?(name)) is used + by Python; Perl 5.10 onwards uses (?() or (?('name')). + + There are two unfortunate ambiguities, caused by history. (a) 'R' can + be the recursive thing or the name 'R' (and similarly for 'R' followed + by digits), and (b) a number could be a name that consists of digits. + In both cases, we look for a name first; if not found, we try the other + cases. */ + + /* For conditions that are assertions, check the syntax, and then exit + the switch. This will take control down to where bracketed groups, + including assertions, are processed. */ + + if (ptr[1] == '?' && (ptr[2] == '=' || ptr[2] == '!' || ptr[2] == '<')) + break; + + /* Most other conditions use OP_CREF (a couple change to OP_RREF + below), and all need to skip 3 bytes at the start of the group. */ + + code[1+LINK_SIZE] = OP_CREF; + skipbytes = 3; + refsign = -1; + + /* Check for a test for recursion in a named group. */ + + if (ptr[1] == 'R' && ptr[2] == '&') { - int i, namelen; - int condref = 0; - const uschar *name; - uschar *slot = cd->name_table; - - /* This is needed for all successful cases. */ - - skipbytes = 3; - - /* Read the name, but also get it as a number if it's all digits */ - - name = ++ptr; - while (*ptr != ')') - { - if (condref >= 0) - condref = ((digitab[*ptr] & ctype_digit) != 0)? - condref * 10 + *ptr - '0' : -1; - ptr++; - } - namelen = ptr - name; - ptr++; - - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; - slot += cd->name_entry_size; - } - - /* Found a previous named subpattern */ - - if (i < cd->names_found) - { - condref = GET2(slot, 0); - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, condref); - } - - /* Search the pattern for a forward reference */ - - else if ((i = find_named_parens(ptr, *brackets, name, namelen)) > 0) - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, i); - } - - /* Check for 'R' for recursion */ - - else if (namelen == 1 && *name == 'R') - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, CREF_RECURSE); - } - - /* Check for a subpattern number */ - - else if (condref > 0) - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, condref); + terminator = -1; + ptr += 2; + code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ } - /* Either an unidentified subpattern, or a reference to (?(0) */ + /* Check for a test for a named group's having been set, using the Perl + syntax (?() or (?('name') */ - else + else if (ptr[1] == '<') + { + terminator = '>'; + ptr++; + } + else if (ptr[1] == '\'') + { + terminator = '\''; + ptr++; + } + else + { + terminator = 0; + if (ptr[1] == '-' || ptr[1] == '+') refsign = *(++ptr); + } + + /* We now expect to read a name; any thing else is an error */ + + if ((cd->ctypes[ptr[1]] & ctype_word) == 0) + { + ptr += 1; /* To get the right offset */ + *errorcodeptr = ERR28; + goto FAILED; + } + + /* Read the name, but also get it as a number if it's all digits */ + + recno = 0; + name = ++ptr; + while ((cd->ctypes[*ptr] & ctype_word) != 0) + { + if (recno >= 0) + recno = ((digitab[*ptr] & ctype_digit) != 0)? + recno * 10 + *ptr - '0' : -1; + ptr++; + } + namelen = ptr - name; + + if ((terminator > 0 && *ptr++ != terminator) || *ptr++ != ')') + { + ptr--; /* Error offset */ + *errorcodeptr = ERR26; + goto FAILED; + } + + /* Do no further checking in the pre-compile phase. */ + + if (lengthptr != NULL) break; + + /* In the real compile we do the work of looking for the actual + reference. If the string started with "+" or "-" we require the rest to + be digits, in which case recno will be set. */ + + if (refsign > 0) + { + if (recno <= 0) { - *errorcodeptr = (condref == 0)? ERR35: ERR15; + *errorcodeptr = ERR58; goto FAILED; } + if (refsign == '-') + { + recno = cd->bracount - recno + 1; + if (recno <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + else recno += cd->bracount; + PUT2(code, 2+LINK_SIZE, recno); + break; } - /* For conditions that are assertions, we just fall through, having - set bravalue above. */ + /* Otherwise (did not start with "+" or "-"), start by looking for the + name. */ + slot = cd->name_table; + for (i = 0; i < cd->names_found; i++) + { + if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; + slot += cd->name_entry_size; + } + + /* Found a previous named subpattern */ + + if (i < cd->names_found) + { + recno = GET2(slot, 0); + PUT2(code, 2+LINK_SIZE, recno); + } + + /* Search the pattern for a forward reference */ + + else if ((i = find_parens(ptr, cd->bracount, name, namelen, + (options & PCRE_EXTENDED) != 0)) > 0) + { + PUT2(code, 2+LINK_SIZE, i); + } + + /* If terminator == 0 it means that the name followed directly after + the opening parenthesis [e.g. (?(abc)...] and in this case there are + some further alternatives to try. For the cases where terminator != 0 + [things like (?(... or (?('name')... or (?(R&name)... ] we have + now checked all the possibilities, so give an error. */ + + else if (terminator != 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + + /* Check for (?(R) for recursion. Allow digits after R to specify a + specific group number. */ + + else if (*name == 'R') + { + recno = 0; + for (i = 1; i < namelen; i++) + { + if ((digitab[name[i]] & ctype_digit) == 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + recno = recno * 10 + name[i] - '0'; + } + if (recno == 0) recno = RREF_ANY; + code[1+LINK_SIZE] = OP_RREF; /* Change test type */ + PUT2(code, 2+LINK_SIZE, recno); + } + + /* Similarly, check for the (?(DEFINE) "condition", which is always + false. */ + + else if (namelen == 6 && strncmp((char *)name, "DEFINE", 6) == 0) + { + code[1+LINK_SIZE] = OP_DEF; + skipbytes = 1; + } + + /* Check for the "name" actually being a subpattern number. */ + + else if (recno > 0) + { + PUT2(code, 2+LINK_SIZE, recno); + } + + /* Either an unidentified subpattern, or a reference to (?(0) */ + + else + { + *errorcodeptr = (recno == 0)? ERR35: ERR15; + goto FAILED; + } break; + + /* ------------------------------------------------------------ */ case '=': /* Positive lookahead */ bravalue = OP_ASSERT; ptr++; break; + + /* ------------------------------------------------------------ */ case '!': /* Negative lookahead */ bravalue = OP_ASSERT_NOT; ptr++; break; - case '<': /* Lookbehinds */ - switch (*(++ptr)) + + /* ------------------------------------------------------------ */ + case '<': /* Lookbehind or named define */ + switch (ptr[1]) { case '=': /* Positive lookbehind */ bravalue = OP_ASSERTBACK; - ptr++; + ptr += 2; break; case '!': /* Negative lookbehind */ bravalue = OP_ASSERTBACK_NOT; - ptr++; + ptr += 2; break; + + default: /* Could be name define, else bad */ + if ((cd->ctypes[ptr[1]] & ctype_word) != 0) goto DEFINE_NAME; + ptr++; /* Correct offset for error */ + *errorcodeptr = ERR24; + goto FAILED; } break; + + /* ------------------------------------------------------------ */ case '>': /* One-time brackets */ bravalue = OP_ONCE; ptr++; break; + + /* ------------------------------------------------------------ */ case 'C': /* Callout - may be followed by digits; */ previous_callout = code; /* Save for later completion */ after_manual_callout = 1; /* Skip one item before completing */ - *code++ = OP_CALLOUT; /* Already checked that the terminating */ - { /* closing parenthesis is present. */ + *code++ = OP_CALLOUT; + { int n = 0; while ((digitab[*(++ptr)] & ctype_digit) != 0) n = n * 10 + *ptr - '0'; + if (*ptr != ')') + { + *errorcodeptr = ERR39; + goto FAILED; + } if (n > 255) { *errorcodeptr = ERR38; @@ -3034,58 +4129,138 @@ for (;; ptr++) previous = NULL; continue; - case 'P': /* Named subpattern handling */ - if (*(++ptr) == '<') /* Definition */ + + /* ------------------------------------------------------------ */ + case 'P': /* Python-style named subpattern handling */ + if (*(++ptr) == '=' || *ptr == '>') /* Reference or recursion */ { - int i, namelen; - uschar *slot = cd->name_table; - const uschar *name; /* Don't amalgamate; some compilers */ - name = ++ptr; /* grumble at autoincrement in declaration */ - - while (*ptr++ != '>'); - namelen = ptr - name - 1; - - for (i = 0; i < cd->names_found; i++) - { - int crc = memcmp(name, slot+2, namelen); - if (crc == 0) - { - if (slot[2+namelen] == 0) - { - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } - } - else crc = -1; /* Current name is substring */ - } - if (crc < 0) - { - memmove(slot + cd->name_entry_size, slot, - (cd->names_found - i) * cd->name_entry_size); - break; - } - slot += cd->name_entry_size; - } - - PUT2(slot, 0, *brackets + 1); - memcpy(slot + 2, name, namelen); - slot[2+namelen] = 0; - cd->names_found++; - goto NUMBERED_GROUP; + is_recurse = *ptr == '>'; + terminator = ')'; + goto NAMED_REF_OR_RECURSE; } - - if (*ptr == '=' || *ptr == '>') /* Reference or recursion */ + else if (*ptr != '<') /* Test for Python-style definition */ { - int i, namelen; - int type = *ptr++; - const uschar *name = ptr; - uschar *slot = cd->name_table; + *errorcodeptr = ERR41; + goto FAILED; + } + /* Fall through to handle (?P< as (?< is handled */ - while (*ptr != ')') ptr++; + + /* ------------------------------------------------------------ */ + DEFINE_NAME: /* Come here from (?< handling */ + case '\'': + { + terminator = (*ptr == '<')? '>' : '\''; + name = ++ptr; + + while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; namelen = ptr - name; + /* In the pre-compile phase, just do a syntax check. */ + + if (lengthptr != NULL) + { + if (*ptr != terminator) + { + *errorcodeptr = ERR42; + goto FAILED; + } + if (cd->names_found >= MAX_NAME_COUNT) + { + *errorcodeptr = ERR49; + goto FAILED; + } + if (namelen + 3 > cd->name_entry_size) + { + cd->name_entry_size = namelen + 3; + if (namelen > MAX_NAME_SIZE) + { + *errorcodeptr = ERR48; + goto FAILED; + } + } + } + + /* In the real compile, create the entry in the table */ + + else + { + slot = cd->name_table; + for (i = 0; i < cd->names_found; i++) + { + int crc = memcmp(name, slot+2, namelen); + if (crc == 0) + { + if (slot[2+namelen] == 0) + { + if ((options & PCRE_DUPNAMES) == 0) + { + *errorcodeptr = ERR43; + goto FAILED; + } + } + else crc = -1; /* Current name is substring */ + } + if (crc < 0) + { + memmove(slot + cd->name_entry_size, slot, + (cd->names_found - i) * cd->name_entry_size); + break; + } + slot += cd->name_entry_size; + } + + PUT2(slot, 0, cd->bracount + 1); + memcpy(slot + 2, name, namelen); + slot[2+namelen] = 0; + } + } + + /* In both cases, count the number of names we've encountered. */ + + ptr++; /* Move past > or ' */ + cd->names_found++; + goto NUMBERED_GROUP; + + + /* ------------------------------------------------------------ */ + case '&': /* Perl recursion/subroutine syntax */ + terminator = ')'; + is_recurse = TRUE; + /* Fall through */ + + /* We come here from the Python syntax above that handles both + references (?P=name) and recursion (?P>name), as well as falling + through from the Perl recursion syntax (?&name). */ + + NAMED_REF_OR_RECURSE: + name = ++ptr; + while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + namelen = ptr - name; + + /* In the pre-compile phase, do a syntax check and set a dummy + reference number. */ + + if (lengthptr != NULL) + { + if (*ptr != terminator) + { + *errorcodeptr = ERR42; + goto FAILED; + } + if (namelen > MAX_NAME_SIZE) + { + *errorcodeptr = ERR48; + goto FAILED; + } + recno = 0; + } + + /* In the real compile, seek the name in the table */ + + else + { + slot = cd->name_table; for (i = 0; i < cd->names_found; i++) { if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; @@ -3097,71 +4272,124 @@ for (;; ptr++) recno = GET2(slot, 0); } else if ((recno = /* Forward back reference */ - find_named_parens(ptr, *brackets, name, namelen)) <= 0) + find_parens(ptr, cd->bracount, name, namelen, + (options & PCRE_EXTENDED) != 0)) <= 0) { *errorcodeptr = ERR15; goto FAILED; } - - if (type == '>') goto HANDLE_RECURSION; /* A few lines below */ - - /* Back reference */ - - previous = code; - *code++ = OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - continue; } - /* Should never happen */ - break; + /* In both phases, we can now go to the code than handles numerical + recursion or backreferences. */ - case 'R': /* Pattern recursion */ + if (is_recurse) goto HANDLE_RECURSION; + else goto HANDLE_REFERENCE; + + + /* ------------------------------------------------------------ */ + case 'R': /* Recursion */ ptr++; /* Same as (?0) */ /* Fall through */ - /* Recursion or "subroutine" call */ - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': + /* ------------------------------------------------------------ */ + case '-': case '+': + case '0': case '1': case '2': case '3': case '4': /* Recursion or */ + case '5': case '6': case '7': case '8': case '9': /* subroutine */ { const uschar *called; + + if ((refsign = *ptr) == '+') ptr++; + else if (refsign == '-') + { + if ((digitab[ptr[1]] & ctype_digit) == 0) + goto OTHER_CHAR_AFTER_QUERY; + ptr++; + } + recno = 0; while((digitab[*ptr] & ctype_digit) != 0) recno = recno * 10 + *ptr++ - '0'; + if (*ptr != ')') + { + *errorcodeptr = ERR29; + goto FAILED; + } + + if (refsign == '-') + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno = cd->bracount - recno + 1; + if (recno <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + else if (refsign == '+') + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno += cd->bracount; + } + /* Come here from code above that handles a named recursion */ HANDLE_RECURSION: previous = code; + called = cd->start_code; - /* Find the bracket that is being referenced. Temporarily end the - regex in case it doesn't exist. */ + /* When we are actually compiling, find the bracket that is being + referenced. Temporarily end the regex in case it doesn't exist before + this point. If we end up with a forward reference, first check that + the bracket does occur later so we can give the error (and position) + now. Then remember this forward reference in the workspace so it can + be filled in at the end. */ - *code = OP_END; - called = (recno == 0)? cd->start_code : - find_bracket(cd->start_code, utf8, recno); - if (called == NULL) + if (lengthptr == NULL) { - *errorcodeptr = ERR15; - goto FAILED; - } + *code = OP_END; + if (recno != 0) called = find_bracket(cd->start_code, utf8, recno); - /* If the subpattern is still open, this is a recursive call. We - check to see if this is a left recursion that could loop for ever, - and diagnose that case. */ + /* Forward reference */ - if (GET(called, 1) == 0 && could_be_empty(called, code, bcptr, utf8)) - { - *errorcodeptr = ERR40; - goto FAILED; + if (called == NULL) + { + if (find_parens(ptr, cd->bracount, NULL, recno, + (options & PCRE_EXTENDED) != 0) < 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + called = cd->start_code + recno; + PUTINC(cd->hwm, 0, code + 2 + LINK_SIZE - cd->start_code); + } + + /* If not a forward reference, and the subpattern is still open, + this is a recursive call. We check to see if this is a left + recursion that could loop for ever, and diagnose that case. */ + + else if (GET(called, 1) == 0 && + could_be_empty(called, code, bcptr, utf8)) + { + *errorcodeptr = ERR40; + goto FAILED; + } } /* Insert the recursion/subroutine item, automatically wrapped inside - "once" brackets. */ + "once" brackets. Set up a "previous group" length so that a + subsequent quantifier will work. */ *code = OP_ONCE; PUT(code, 1, 2 + 2*LINK_SIZE); @@ -3174,12 +4402,19 @@ for (;; ptr++) *code = OP_KET; PUT(code, 1, 2 + 2*LINK_SIZE); code += 1 + LINK_SIZE; + + length_prevgroup = 3 + 3*LINK_SIZE; } + + /* Can't determine a first byte now */ + + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; continue; - /* Character after (? not specially recognized */ - default: /* Option setting */ + /* ------------------------------------------------------------ */ + default: /* Other characters: check option setting */ + OTHER_CHAR_AFTER_QUERY: set = unset = 0; optset = &set; @@ -3189,13 +4424,21 @@ for (;; ptr++) { case '-': optset = &unset; break; + case 'J': /* Record that it changed in the external options */ + *optset |= PCRE_DUPNAMES; + cd->external_options |= PCRE_JCHANGED; + break; + case 'i': *optset |= PCRE_CASELESS; break; - case 'J': *optset |= PCRE_DUPNAMES; break; case 'm': *optset |= PCRE_MULTILINE; break; case 's': *optset |= PCRE_DOTALL; break; case 'x': *optset |= PCRE_EXTENDED; break; case 'U': *optset |= PCRE_UNGREEDY; break; case 'X': *optset |= PCRE_EXTRA; break; + + default: *errorcodeptr = ERR12; + ptr--; /* Correct the offset */ + goto FAILED; } } @@ -3204,32 +4447,54 @@ for (;; ptr++) newoptions = (options | set) & (~unset); /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. Compile - code to change the ims options if this setting actually changes any of - them. We also pass the new setting back so that it can be put at the - start of any following branches, and when this group ends (if we are in - a group), a resetting item can be compiled. + group with option changes, so the options change at this level. If this + item is right at the start of the pattern, the options can be + abstracted and made external in the pre-compile phase, and ignored in + the compile phase. This can be helpful when matching -- for instance in + caseless checking of required bytes. - Note that if this item is right at the start of the pattern, the - options will have been abstracted and made global, so there will be no - change to compile. */ + If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are + definitely *not* at the start of the pattern because something has been + compiled. In the pre-compile phase, however, the code pointer can have + that value after the start, because it gets reset as code is discarded + during the pre-compile. However, this can happen only at top level - if + we are within parentheses, the starting BRA will still be present. At + any parenthesis level, the length value can be used to test if anything + has been compiled at that level. Thus, a test for both these conditions + is necessary to ensure we correctly detect the start of the pattern in + both phases. + + If we are not at the pattern start, compile code to change the ims + options if this setting actually changes any of them. We also pass the + new setting back so that it can be put at the start of any following + branches, and when this group ends (if we are in a group), a resetting + item can be compiled. */ if (*ptr == ')') { - if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) + if (code == cd->start_code + 1 + LINK_SIZE && + (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) { - *code++ = OP_OPT; - *code++ = newoptions & PCRE_IMS; + cd->external_options = newoptions; + options = newoptions; } + else + { + if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) + { + *code++ = OP_OPT; + *code++ = newoptions & PCRE_IMS; + } - /* Change options at this level, and pass them back for use - in subsequent branches. Reset the greedy defaults and the case - value for firstbyte and reqbyte. */ + /* Change options at this level, and pass them back for use + in subsequent branches. Reset the greedy defaults and the case + value for firstbyte and reqbyte. */ - *optionsptr = options = newoptions; - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; + *optionsptr = options = newoptions; + greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); + greedy_non_default = greedy_default ^ 1; + req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; + } previous = NULL; /* This item can't be repeated */ continue; /* It is complete */ @@ -3242,58 +4507,57 @@ for (;; ptr++) bravalue = OP_BRA; ptr++; - } - } + } /* End of switch for character following (? */ + } /* End of (? handling */ - /* If PCRE_NO_AUTO_CAPTURE is set, all unadorned brackets become - non-capturing and behave like (?:...) brackets */ + /* Opening parenthesis not followed by '?'. If PCRE_NO_AUTO_CAPTURE is set, + all unadorned brackets become non-capturing and behave like (?:...) + brackets. */ else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) { bravalue = OP_BRA; } - /* Else we have a referencing group; adjust the opcode. If the bracket - number is greater than EXTRACT_BASIC_MAX, we set the opcode one higher, and - arrange for the true number to follow later, in an OP_BRANUMBER item. */ + /* Else we have a capturing group. */ else { NUMBERED_GROUP: - if (++(*brackets) > EXTRACT_BASIC_MAX) - { - bravalue = OP_BRA + EXTRACT_BASIC_MAX + 1; - code[1+LINK_SIZE] = OP_BRANUMBER; - PUT2(code, 2+LINK_SIZE, *brackets); - skipbytes = 3; - } - else bravalue = OP_BRA + *brackets; + cd->bracount += 1; + PUT2(code, 1+LINK_SIZE, cd->bracount); + skipbytes = 2; } - /* Process nested bracketed re. Assertions may not be repeated, but other - kinds can be. We copy code into a non-register variable in order to be able - to pass its address because some compilers complain otherwise. Pass in a - new setting for the ims options if they have changed. */ + /* Process nested bracketed regex. Assertions may not be repeated, but + other kinds can be. All their opcodes are >= OP_ONCE. We copy code into a + non-register variable in order to be able to pass its address because some + compilers complain otherwise. Pass in a new setting for the ims options if + they have changed. */ previous = (bravalue >= OP_ONCE)? code : NULL; *code = bravalue; tempcode = code; tempreqvary = cd->req_varyopt; /* Save value before bracket */ + length_prevgroup = 0; /* Initialize for pre-compile phase */ if (!compile_regex( newoptions, /* The complete new option state */ options & PCRE_IMS, /* The previous ims option state */ - brackets, /* Extracting bracket count */ &tempcode, /* Where to put code (updated) */ &ptr, /* Input pointer (updated) */ errorcodeptr, /* Where to put an error message */ (bravalue == OP_ASSERTBACK || bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - skipbytes, /* Skip over OP_COND/OP_BRANUMBER */ + reset_bracount, /* True if (?| group */ + skipbytes, /* Skip over bracket number */ &subfirstbyte, /* For possible first char */ &subreqbyte, /* For possible last char */ bcptr, /* Current branch chain */ - cd)) /* Tables block */ + cd, /* Tables block */ + (lengthptr == NULL)? NULL : /* Actual compile phase */ + &length_prevgroup /* Pre-compile phase */ + )) goto FAILED; /* At the end of compiling, code is still pointing to the start of the @@ -3302,9 +4566,11 @@ for (;; ptr++) is on the bracket. */ /* If this is a conditional bracket, check that there are no more than - two branches in the group. */ + two branches in the group, or just one if it's a DEFINE group. We do this + in the real compile phase, not in the pre-pass, where the whole group may + not be available. */ - else if (bravalue == OP_COND) + if (bravalue == OP_COND && lengthptr == NULL) { uschar *tc = code; int condcount = 0; @@ -3315,29 +4581,77 @@ for (;; ptr++) } while (*tc != OP_KET); - if (condcount > 2) + /* A DEFINE group is never obeyed inline (the "condition" is always + false). It must have only one branch. */ + + if (code[LINK_SIZE+1] == OP_DEF) { - *errorcodeptr = ERR27; - goto FAILED; + if (condcount > 1) + { + *errorcodeptr = ERR54; + goto FAILED; + } + bravalue = OP_DEF; /* Just a flag to suppress char handling below */ } - /* If there is just one branch, we must not make use of its firstbyte or - reqbyte, because this is equivalent to an empty second branch. */ + /* A "normal" conditional group. If there is just one branch, we must not + make use of its firstbyte or reqbyte, because this is equivalent to an + empty second branch. */ - if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; + else + { + if (condcount > 2) + { + *errorcodeptr = ERR27; + goto FAILED; + } + if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; + } } - /* Handle updating of the required and first characters. Update for normal - brackets of all kinds, and conditions with two branches (see code above). - If the bracket is followed by a quantifier with zero repeat, we have to - back off. Hence the definition of zeroreqbyte and zerofirstbyte outside the - main loop so that they can be accessed for the back off. */ + /* Error if hit end of pattern */ + + if (*ptr != ')') + { + *errorcodeptr = ERR14; + goto FAILED; + } + + /* In the pre-compile phase, update the length by the length of the nested + group, less the brackets at either end. Then reduce the compiled code to + just the brackets so that it doesn't use much memory if it is duplicated by + a quantifier. */ + + if (lengthptr != NULL) + { + *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; + code++; + PUTINC(code, 0, 1 + LINK_SIZE); + *code++ = OP_KET; + PUTINC(code, 0, 1 + LINK_SIZE); + } + + /* Otherwise update the main code pointer to the end of the group. */ + + else code = tempcode; + + /* For a DEFINE group, required and first character settings are not + relevant. */ + + if (bravalue == OP_DEF) break; + + /* Handle updating of the required and first characters for other types of + group. Update for normal brackets of all kinds, and conditions with two + branches (see code above). If the bracket is followed by a quantifier with + zero repeat, we have to back off. Hence the definition of zeroreqbyte and + zerofirstbyte outside the main loop so that they can be accessed for the + back off. */ zeroreqbyte = reqbyte; zerofirstbyte = firstbyte; groupsetfirstbyte = FALSE; - if (bravalue >= OP_BRA || bravalue == OP_ONCE || bravalue == OP_COND) + if (bravalue >= OP_ONCE) { /* If we have not yet set a firstbyte in this branch, take it from the subpattern, remembering that it was set here so that a repeat of more @@ -3378,35 +4692,22 @@ for (;; ptr++) firstbyte, looking for an asserted first char. */ else if (bravalue == OP_ASSERT && subreqbyte >= 0) reqbyte = subreqbyte; + break; /* End of processing '(' */ - /* Now update the main code pointer to the end of the group. */ - code = tempcode; - - /* Error if hit end of pattern */ - - if (*ptr != ')') - { - *errorcodeptr = ERR14; - goto FAILED; - } - break; - - /* Check \ for being a real metacharacter; if not, fall through and handle - it as a data character at the start of a string. Escape items are checked - for validity in the pre-compiling pass. */ - - case '\\': - tempptr = ptr; - c = check_escape(&ptr, errorcodeptr, *brackets, options, FALSE); - - /* Handle metacharacters introduced by \. For ones like \d, the ESC_ values + /* ===================================================================*/ + /* Handle metasequences introduced by \. For ones like \d, the ESC_ values are arranged to be the negation of the corresponding OP_values. For the back references, the values are ESC_REF plus the reference number. Only back references and those types that consume a character may be repeated. We can test for values between ESC_b and ESC_Z for the latter; this may have to change if any new ones are ever created. */ + case '\\': + tempptr = ptr; + c = check_escape(&ptr, errorcodeptr, cd->bracount, options, FALSE); + if (*errorcodeptr != 0) goto FAILED; + if (c < 0) { if (-c == ESC_Q) /* Handle start of quoted string */ @@ -3416,6 +4717,8 @@ for (;; ptr++) continue; } + if (-c == ESC_E) continue; /* Perl ignores an orphan \E */ + /* For metasequences that actually match a character, we disable the setting of a first character if it hasn't already been set. */ @@ -3427,18 +4730,34 @@ for (;; ptr++) zerofirstbyte = firstbyte; zeroreqbyte = reqbyte; - /* Back references are handled specially */ + /* \k or \k'name' is a back reference by name (Perl syntax). + We also support \k{name} (.NET syntax) */ + + if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\'' || ptr[1] == '{')) + { + is_recurse = FALSE; + terminator = (*(++ptr) == '<')? '>' : (*ptr == '\'')? '\'' : '}'; + goto NAMED_REF_OR_RECURSE; + } + + /* Back references are handled specially; must disable firstbyte if + not set to cope with cases like (?=(\w+))\1: which would otherwise set + ':' later. */ if (-c >= ESC_REF) { - int number = -c - ESC_REF; + recno = -c - ESC_REF; + + HANDLE_REFERENCE: /* Come here from named backref handling */ + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; previous = code; *code++ = OP_REF; - PUT2INC(code, 0, number); + PUT2INC(code, 0, recno); + cd->backref_map |= (recno < 32)? (1 << recno) : 1; + if (recno > cd->top_backref) cd->top_backref = recno; } - /* So are Unicode property matches, if supported. We know that get_ucp - won't fail because it was tested in the pre-pass. */ + /* So are Unicode property matches, if supported. */ #ifdef SUPPORT_UCP else if (-c == ESC_P || -c == ESC_p) @@ -3446,15 +4765,26 @@ for (;; ptr++) BOOL negated; int pdata; int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); + if (ptype < 0) goto FAILED; previous = code; *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP; *code++ = ptype; *code++ = pdata; } +#else + + /* If Unicode properties are not supported, \X, \P, and \p are not + allowed. */ + + else if (-c == ESC_X || -c == ESC_P || -c == ESC_p) + { + *errorcodeptr = ERR45; + goto FAILED; + } #endif - /* For the rest, we can obtain the OP value by negating the escape - value */ + /* For the rest (including \X when Unicode properties are supported), we + can obtain the OP value by negating the escape value. */ else { @@ -3478,9 +4808,10 @@ for (;; ptr++) mcbuffer[0] = c; mclength = 1; } - goto ONE_CHAR; + + /* ===================================================================*/ /* Handle a literal character. It is guaranteed not to be whitespace or # when the extended flag is set. If we are in UTF-8 mode, it may be a multi-byte literal character. */ @@ -3491,7 +4822,7 @@ for (;; ptr++) mcbuffer[0] = c; #ifdef SUPPORT_UTF8 - if (utf8 && (c & 0xc0) == 0xc0) + if (utf8 && c >= 0xc0) { while ((ptr[1] & 0xc0) == 0x80) mcbuffer[mclength++] = *(++ptr); @@ -3542,6 +4873,7 @@ for (;; ptr++) } } /* end of big loop */ + /* Control never reaches here by falling through, only by a goto for all the error states. Pass back the position in the pattern so that it can be displayed to the user for diagnosing the error. */ @@ -3558,35 +4890,42 @@ return FALSE; * Compile sequence of alternatives * *************************************************/ -/* On entry, ptr is pointing past the bracket character, but on return -it points to the closing bracket, or vertical bar, or end of string. -The code variable is pointing at the byte into which the BRA operator has been -stored. If the ims options are changed at the start (for a (?ims: group) or -during any branch, we need to insert an OP_OPT item at the start of every -following branch to ensure they get set correctly at run time, and also pass -the new options into every subsequent branch compile. +/* On entry, ptr is pointing past the bracket character, but on return it +points to the closing bracket, or vertical bar, or end of string. The code +variable is pointing at the byte into which the BRA operator has been stored. +If the ims options are changed at the start (for a (?ims: group) or during any +branch, we need to insert an OP_OPT item at the start of every following branch +to ensure they get set correctly at run time, and also pass the new options +into every subsequent branch compile. -Argument: +This function is used during the pre-compile phase when we are trying to find +out the amount of memory needed, as well as during the real compile phase. The +value of lengthptr distinguishes the two phases. + +Arguments: options option bits, including any changes for this subpattern oldims previous settings of ims option bits - brackets -> int containing the number of extracting brackets used codeptr -> the address of the current code pointer ptrptr -> the address of the current pattern pointer errorcodeptr -> pointer to error code variable lookbehind TRUE if this is a lookbehind assertion - skipbytes skip this many bytes at start (for OP_COND, OP_BRANUMBER) + reset_bracount TRUE to reset the count for each branch + skipbytes skip this many bytes at start (for brackets and OP_COND) firstbyteptr place to put the first required character, or a negative number reqbyteptr place to put the last required character, or a negative number bcptr pointer to the chain of currently open branches cd points to the data block with tables pointers etc. + lengthptr NULL during the real compile phase + points to length accumulator during pre-compile phase -Returns: TRUE on success +Returns: TRUE on success */ static BOOL -compile_regex(int options, int oldims, int *brackets, uschar **codeptr, - const uschar **ptrptr, int *errorcodeptr, BOOL lookbehind, int skipbytes, - int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd) +compile_regex(int options, int oldims, uschar **codeptr, const uschar **ptrptr, + int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, + int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd, + int *lengthptr) { const uschar *ptr = *ptrptr; uschar *code = *codeptr; @@ -3595,6 +4934,9 @@ uschar *start_bracket = code; uschar *reverse_count = NULL; int firstbyte, reqbyte; int branchfirstbyte, branchreqbyte; +int length; +int orig_bracount; +int max_bracount; branch_chain bc; bc.outer = bcptr; @@ -3602,6 +4944,20 @@ bc.current = code; firstbyte = reqbyte = REQ_UNSET; +/* Accumulate the length for use in the pre-compile phase. Start with the +length of the BRA and KET and any extra bytes that are required at the +beginning. We accumulate in a local variable to save frequent testing of +lenthptr for NULL. We cannot do this by looking at the value of code at the +start and end of each alternative, because compiled items are discarded during +the pre-compile phase so that the work space is not exceeded. */ + +length = 2 + 2*LINK_SIZE + skipbytes; + +/* WARNING: If the above line is changed for any reason, you must also change +the code that abstracts option settings at the start of the pattern and makes +them global. It tests the value of length for (2 + 2*LINK_SIZE) in the +pre-compile phase to find out whether anything has yet been compiled or not. */ + /* Offset is set zero to mark that this bracket is still open */ PUT(code, 1, 0); @@ -3609,14 +4965,21 @@ code += 1 + LINK_SIZE + skipbytes; /* Loop for each alternative branch */ +orig_bracount = max_bracount = cd->bracount; for (;;) { + /* For a (?| group, reset the capturing bracket count so that each branch + uses the same numbers. */ + + if (reset_bracount) cd->bracount = orig_bracount; + /* Handle a change of ims options at the start of the branch */ if ((options & PCRE_IMS) != oldims) { *code++ = OP_OPT; *code++ = options & PCRE_IMS; + length += 2; } /* Set up dummy OP_REVERSE if lookbehind assertion */ @@ -3626,95 +4989,110 @@ for (;;) *code++ = OP_REVERSE; reverse_count = code; PUTINC(code, 0, 0); + length += 1 + LINK_SIZE; } - /* Now compile the branch */ + /* Now compile the branch; in the pre-compile phase its length gets added + into the length. */ - if (!compile_branch(&options, brackets, &code, &ptr, errorcodeptr, - &branchfirstbyte, &branchreqbyte, &bc, cd)) + if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstbyte, + &branchreqbyte, &bc, cd, (lengthptr == NULL)? NULL : &length)) { *ptrptr = ptr; return FALSE; } - /* If this is the first branch, the firstbyte and reqbyte values for the - branch become the values for the regex. */ + /* Keep the highest bracket count in case (?| was used and some branch + has fewer than the rest. */ - if (*last_branch != OP_ALT) + if (cd->bracount > max_bracount) max_bracount = cd->bracount; + + /* In the real compile phase, there is some post-processing to be done. */ + + if (lengthptr == NULL) { - firstbyte = branchfirstbyte; - reqbyte = branchreqbyte; - } + /* If this is the first branch, the firstbyte and reqbyte values for the + branch become the values for the regex. */ - /* If this is not the first branch, the first char and reqbyte have to - match the values from all the previous branches, except that if the previous - value for reqbyte didn't have REQ_VARY set, it can still match, and we set - REQ_VARY for the regex. */ - - else - { - /* If we previously had a firstbyte, but it doesn't match the new branch, - we have to abandon the firstbyte for the regex, but if there was previously - no reqbyte, it takes on the value of the old firstbyte. */ - - if (firstbyte >= 0 && firstbyte != branchfirstbyte) + if (*last_branch != OP_ALT) { - if (reqbyte < 0) reqbyte = firstbyte; - firstbyte = REQ_NONE; + firstbyte = branchfirstbyte; + reqbyte = branchreqbyte; } - /* If we (now or from before) have no firstbyte, a firstbyte from the - branch becomes a reqbyte if there isn't a branch reqbyte. */ + /* If this is not the first branch, the first char and reqbyte have to + match the values from all the previous branches, except that if the + previous value for reqbyte didn't have REQ_VARY set, it can still match, + and we set REQ_VARY for the regex. */ - if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) - branchreqbyte = branchfirstbyte; - - /* Now ensure that the reqbytes match */ - - if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) - reqbyte = REQ_NONE; - else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ - } - - /* If lookbehind, check that this branch matches a fixed-length string, - and put the length into the OP_REVERSE item. Temporarily mark the end of - the branch with OP_END. */ - - if (lookbehind) - { - int length; - *code = OP_END; - length = find_fixedlength(last_branch, options); - DPRINTF(("fixed length = %d\n", length)); - if (length < 0) + else { - *errorcodeptr = (length == -2)? ERR36 : ERR25; - *ptrptr = ptr; - return FALSE; + /* If we previously had a firstbyte, but it doesn't match the new branch, + we have to abandon the firstbyte for the regex, but if there was + previously no reqbyte, it takes on the value of the old firstbyte. */ + + if (firstbyte >= 0 && firstbyte != branchfirstbyte) + { + if (reqbyte < 0) reqbyte = firstbyte; + firstbyte = REQ_NONE; + } + + /* If we (now or from before) have no firstbyte, a firstbyte from the + branch becomes a reqbyte if there isn't a branch reqbyte. */ + + if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) + branchreqbyte = branchfirstbyte; + + /* Now ensure that the reqbytes match */ + + if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) + reqbyte = REQ_NONE; + else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ + } + + /* If lookbehind, check that this branch matches a fixed-length string, and + put the length into the OP_REVERSE item. Temporarily mark the end of the + branch with OP_END. */ + + if (lookbehind) + { + int fixed_length; + *code = OP_END; + fixed_length = find_fixedlength(last_branch, options); + DPRINTF(("fixed length = %d\n", fixed_length)); + if (fixed_length < 0) + { + *errorcodeptr = (fixed_length == -2)? ERR36 : ERR25; + *ptrptr = ptr; + return FALSE; + } + PUT(reverse_count, 0, fixed_length); } - PUT(reverse_count, 0, length); } - /* Reached end of expression, either ')' or end of pattern. Go back through - the alternative branches and reverse the chain of offsets, with the field in - the BRA item now becoming an offset to the first alternative. If there are - no alternatives, it points to the end of the group. The length in the - terminating ket is always the length of the whole bracketed item. If any of - the ims options were changed inside the group, compile a resetting op-code - following, except at the very end of the pattern. Return leaving the pointer - at the terminating char. */ + /* Reached end of expression, either ')' or end of pattern. In the real + compile phase, go back through the alternative branches and reverse the chain + of offsets, with the field in the BRA item now becoming an offset to the + first alternative. If there are no alternatives, it points to the end of the + group. The length in the terminating ket is always the length of the whole + bracketed item. If any of the ims options were changed inside the group, + compile a resetting op-code following, except at the very end of the pattern. + Return leaving the pointer at the terminating char. */ if (*ptr != '|') { - int length = code - last_branch; - do + if (lengthptr == NULL) { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, length); - length = prev_length; - last_branch -= length; + int branch_length = code - last_branch; + do + { + int prev_length = GET(last_branch, 1); + PUT(last_branch, 1, branch_length); + branch_length = prev_length; + last_branch -= branch_length; + } + while (branch_length > 0); } - while (length > 0); /* Fill in the ket */ @@ -3728,26 +5106,45 @@ for (;;) { *code++ = OP_OPT; *code++ = oldims; + length += 2; } + /* Retain the highest bracket number, in case resetting was used. */ + + cd->bracount = max_bracount; + /* Set values to pass back */ *codeptr = code; *ptrptr = ptr; *firstbyteptr = firstbyte; *reqbyteptr = reqbyte; + if (lengthptr != NULL) *lengthptr += length; return TRUE; } - /* Another branch follows; insert an "or" node. Its length field points back + /* Another branch follows. In the pre-compile phase, we can move the code + pointer back to where it was for the start of the first branch. (That is, + pretend that each branch is the only one.) + + In the real compile phase, insert an ALT node. Its length field points back to the previous branch while the bracket remains open. At the end the chain is reversed. It's done like this so that the start of the bracket has a zero offset until it is closed, making it possible to detect recursion. */ - *code = OP_ALT; - PUT(code, 1, code - last_branch); - bc.current = last_branch = code; - code += 1 + LINK_SIZE; + if (lengthptr != NULL) + { + code = *codeptr + 1 + LINK_SIZE + skipbytes; + length += 1 + LINK_SIZE; + } + else + { + *code = OP_ALT; + PUT(code, 1, code - last_branch); + bc.current = last_branch = code; + code += 1 + LINK_SIZE; + } + ptr++; } /* Control never reaches here */ @@ -3799,24 +5196,29 @@ is_anchored(register const uschar *code, int *options, unsigned int bracket_map, unsigned int backref_map) { do { - const uschar *scode = - first_significant_code(code + 1+LINK_SIZE, options, PCRE_MULTILINE, FALSE); + const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], + options, PCRE_MULTILINE, FALSE); register int op = *scode; + /* Non-capturing brackets */ + + if (op == OP_BRA) + { + if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; + } + /* Capturing brackets */ - if (op > OP_BRA) + else if (op == OP_CBRA) { - int new_map; - op -= OP_BRA; - if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); - new_map = bracket_map | ((op < 32)? (1 << op) : 1); + int n = GET2(scode, 1+LINK_SIZE); + int new_map = bracket_map | ((n < 32)? (1 << n) : 1); if (!is_anchored(scode, options, new_map, backref_map)) return FALSE; } /* Other brackets */ - else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) + else if (op == OP_ASSERT || op == OP_ONCE || op == OP_COND) { if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; } @@ -3824,7 +5226,8 @@ do { /* .* is not anchored unless DOTALL is set and it isn't in brackets that are or may be referenced. */ - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR) && + else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || + op == OP_TYPEPOSSTAR) && (*options & PCRE_DOTALL) != 0) { if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; @@ -3869,30 +5272,35 @@ is_startline(const uschar *code, unsigned int bracket_map, unsigned int backref_map) { do { - const uschar *scode = first_significant_code(code + 1+LINK_SIZE, NULL, 0, - FALSE); + const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], + NULL, 0, FALSE); register int op = *scode; + /* Non-capturing brackets */ + + if (op == OP_BRA) + { + if (!is_startline(scode, bracket_map, backref_map)) return FALSE; + } + /* Capturing brackets */ - if (op > OP_BRA) + else if (op == OP_CBRA) { - int new_map; - op -= OP_BRA; - if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); - new_map = bracket_map | ((op < 32)? (1 << op) : 1); + int n = GET2(scode, 1+LINK_SIZE); + int new_map = bracket_map | ((n < 32)? (1 << n) : 1); if (!is_startline(scode, new_map, backref_map)) return FALSE; } /* Other brackets */ - else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) + else if (op == OP_ASSERT || op == OP_ONCE || op == OP_COND) { if (!is_startline(scode, bracket_map, backref_map)) return FALSE; } /* .* means "start at start or after \n" if it isn't in brackets that may be referenced. */ - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR) + else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) { if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; } @@ -3941,14 +5349,13 @@ do { first_significant_code(code + 1+LINK_SIZE, options, PCRE_CASELESS, TRUE); register int op = *scode; - if (op >= OP_BRA) op = OP_BRA; - switch(op) { default: return -1; case OP_BRA: + case OP_CBRA: case OP_ASSERT: case OP_ONCE: case OP_COND: @@ -3964,6 +5371,7 @@ do { case OP_CHARNC: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: if (!inassert) return -1; if (c < 0) { @@ -4004,7 +5412,7 @@ Returns: pointer to compiled data block, or NULL on error, with errorptr and erroroffset set */ -PCRE_DATA_SCOPE pcre * +PCRE_EXP_DEFN pcre * pcre_compile(const char *pattern, int options, const char **errorptr, int *erroroffset, const unsigned char *tables) { @@ -4012,37 +5420,36 @@ return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); } - -PCRE_DATA_SCOPE pcre * +PCRE_EXP_DEFN pcre * pcre_compile2(const char *pattern, int options, int *errorcodeptr, const char **errorptr, int *erroroffset, const unsigned char *tables) { real_pcre *re; -int length = 1 + LINK_SIZE; /* For initial BRA plus length */ -int c, firstbyte, reqbyte, newline; -int bracount = 0; -int branch_extra = 0; -int branch_newextra; -int item_count = -1; -int name_count = 0; -int max_name_size = 0; -int lastitemlength = 0; +int length = 1; /* For final END opcode */ +int firstbyte, reqbyte, newline; int errorcode = 0; #ifdef SUPPORT_UTF8 BOOL utf8; -BOOL class_utf8; #endif -BOOL inescq = FALSE; -BOOL capturing; -unsigned int brastackptr = 0; size_t size; uschar *code; const uschar *codestart; const uschar *ptr; compile_data compile_block; compile_data *cd = &compile_block; -int brastack[BRASTACK_SIZE]; -uschar bralenstack[BRASTACK_SIZE]; + +/* This space is used for "compiling" into during the first phase, when we are +computing the amount of memory that is needed. Compiled items are thrown away +as soon as possible, so that a fairly large buffer should be sufficient for +this purpose. The same space is used in the second phase for remembering where +to fill in forward references to subpatterns. */ + +uschar cworkspace[COMPILE_WORK_SIZE]; + + +/* Set this early so that early errors get offset 0. */ + +ptr = (const uschar *)pattern; /* We can't pass back an error message if errorptr is NULL; I guess the best we can do is just return NULL, but we can set a code value if there is a code @@ -4062,7 +5469,7 @@ if (errorcodeptr != NULL) *errorcodeptr = ERR0; if (erroroffset == NULL) { errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN; + goto PCRE_EARLY_ERROR_RETURN2; } *erroroffset = 0; @@ -4075,7 +5482,7 @@ if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 && (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) { errorcode = ERR44; - goto PCRE_EARLY_ERROR_RETURN; + goto PCRE_EARLY_ERROR_RETURN2; } #else if ((options & PCRE_UTF8) != 0) @@ -4099,34 +5506,49 @@ cd->fcc = tables + fcc_offset; cd->cbits = tables + cbits_offset; cd->ctypes = tables + ctypes_offset; -/* Handle different types of newline. The two bits give four cases. The current -code allows for one- or two-byte sequences. */ +/* Handle different types of newline. The three bits give seven cases. The +current code allows for fixed one- or two-byte sequences, plus "any" and +"anycrlf". */ -switch (options & PCRE_NEWLINE_CRLF) +switch (options & (PCRE_NEWLINE_CRLF | PCRE_NEWLINE_ANY)) { - default: newline = NEWLINE; break; /* Compile-time default */ + case 0: newline = NEWLINE; break; /* Compile-time default */ case PCRE_NEWLINE_CR: newline = '\r'; break; case PCRE_NEWLINE_LF: newline = '\n'; break; case PCRE_NEWLINE_CR+ PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; } -if (newline > 255) +if (newline == -2) { - cd->nllen = 2; - cd->nl[0] = (newline >> 8) & 255; - cd->nl[1] = newline & 255; + cd->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + cd->nltype = NLTYPE_ANY; } else { - cd->nllen = 1; - cd->nl[0] = newline; + cd->nltype = NLTYPE_FIXED; + if (newline > 255) + { + cd->nllen = 2; + cd->nl[0] = (newline >> 8) & 255; + cd->nl[1] = newline & 255; + } + else + { + cd->nllen = 1; + cd->nl[0] = newline; + } } -/* Maximum back reference and backref bitmap. This is updated for numeric -references during the first pass, but for named references during the actual -compile pass. The bitmap records up to 31 back references to help in deciding -whether (.*) can be treated as anchored or not. */ +/* Maximum back reference and backref bitmap. The bitmap records up to 31 back +references to help in deciding whether (.*) can be treated as anchored or not. +*/ cd->top_backref = 0; cd->backref_map = 0; @@ -4136,952 +5558,41 @@ cd->backref_map = 0; DPRINTF(("------------------------------------------------------------------\n")); DPRINTF(("%s\n", pattern)); -/* The first thing to do is to make a pass over the pattern to compute the -amount of store required to hold the compiled code. This does not have to be -perfect as long as errors are overestimates. At the same time we can detect any -flag settings right at the start, and extract them. Make an attempt to correct -for any counted white space if an "extended" flag setting appears late in the -pattern. We can't be so clever for #-comments. */ - -ptr = (const uschar *)(pattern - 1); -while ((c = *(++ptr)) != 0) - { - int min, max; - int class_optcount; - int bracket_length; - int duplength; - - /* If we are inside a \Q...\E sequence, all chars are literal */ - - if (inescq) - { - if ((options & PCRE_AUTO_CALLOUT) != 0) length += 2 + 2*LINK_SIZE; - goto NORMAL_CHAR; - } - - /* Otherwise, first check for ignored whitespace and comments */ - - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; - if (*ptr != 0) - { - ptr += cd->nllen - 1; - continue; - } - break; /* End loop at end of pattern */ - } - } - - item_count++; /* Is zero for the first non-comment item */ - - /* Allow space for auto callout before every item except quantifiers. */ - - if ((options & PCRE_AUTO_CALLOUT) != 0 && - c != '*' && c != '+' && c != '?' && - (c != '{' || !is_counted_repeat(ptr + 1))) - length += 2 + 2*LINK_SIZE; - - switch(c) - { - /* A backslashed item may be an escaped data character or it may be a - character type. */ - - case '\\': - c = check_escape(&ptr, &errorcode, bracount, options, FALSE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - lastitemlength = 1; /* Default length of last item for repeats */ - - if (c >= 0) /* Data character */ - { - length += 2; /* For a one-byte character */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - { - int i; - for (i = 0; i < _pcre_utf8_table1_size; i++) - if (c <= _pcre_utf8_table1[i]) break; - length += i; - lastitemlength += i; - } -#endif - - continue; - } - - /* If \Q, enter "literal" mode */ - - if (-c == ESC_Q) - { - inescq = TRUE; - continue; - } - - /* \X is supported only if Unicode property support is compiled */ - -#ifndef SUPPORT_UCP - if (-c == ESC_X) - { - errorcode = ERR45; - goto PCRE_ERROR_RETURN; - } -#endif - - /* \P and \p are for Unicode properties, but only when the support has - been compiled. Each item needs 3 bytes. */ - - else if (-c == ESC_P || -c == ESC_p) - { -#ifdef SUPPORT_UCP - BOOL negated; - BOOL pdata; - length += 3; - lastitemlength = 3; - if (get_ucp(&ptr, &negated, &pdata, &errorcode) < 0) - goto PCRE_ERROR_RETURN; - continue; -#else - errorcode = ERR45; - goto PCRE_ERROR_RETURN; -#endif - } - - /* Other escapes need one byte */ - - length++; - - /* A back reference needs an additional 2 bytes, plus either one or 5 - bytes for a repeat. We also need to keep the value of the highest - back reference. */ - - if (c <= -ESC_REF) - { - int refnum = -c - ESC_REF; - cd->backref_map |= (refnum < 32)? (1 << refnum) : 1; - if (refnum > cd->top_backref) - cd->top_backref = refnum; - length += 2; /* For single back reference */ - if (ptr[1] == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '?') ptr++; - } - } - continue; - - case '^': /* Single-byte metacharacters */ - case '.': - case '$': - length++; - lastitemlength = 1; - continue; - - case '*': /* These repeats won't be after brackets; */ - case '+': /* those are handled separately */ - case '?': - length++; - goto POSESSIVE; /* A few lines below */ - - /* This covers the cases of braced repeats after a single char, metachar, - class, or back reference. */ - - case '{': - if (!is_counted_repeat(ptr+1)) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - /* These special cases just insert one extra opcode */ - - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - - /* These cases might insert additional copies of a preceding character. */ - - else - { - if (min != 1) - { - length -= lastitemlength; /* Uncount the original char or metachar */ - if (min > 0) length += 3 + lastitemlength; - } - length += lastitemlength + ((max > 0)? 3 : 1); - } - - if (ptr[1] == '?') ptr++; /* Needs no extra length */ - - POSESSIVE: /* Test for possessive quantifier */ - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; /* Allow for atomic brackets */ - } - continue; - - /* An alternation contains an offset to the next branch or ket. If any ims - options changed in the previous branch(es), and/or if we are in a - lookbehind assertion, extra space will be needed at the start of the - branch. This is handled by branch_extra. */ - - case '|': - length += 1 + LINK_SIZE + branch_extra; - continue; - - /* A character class uses 33 characters provided that all the character - values are less than 256. Otherwise, it uses a bit map for low valued - characters, and individual items for others. Don't worry about character - types that aren't allowed in classes - they'll get picked up during the - compile. A character class that contains only one single-byte character - uses 2 or 3 bytes, depending on whether it is negated or not. Notice this - where we can. (In UTF-8 mode we can do this only for chars < 128.) */ - - case '[': - if (*(++ptr) == '^') - { - class_optcount = 10; /* Greater than one */ - ptr++; - } - else class_optcount = 0; - -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; -#endif - - /* Written as a "do" so that an initial ']' is taken as data */ - - if (*ptr != 0) do - { - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (*ptr != '\\' || ptr[1] != 'E') goto GET_ONE_CHARACTER; - inescq = FALSE; - ptr += 1; - continue; - } - - /* Outside \Q...\E, check for escapes */ - - if (*ptr == '\\') - { - c = check_escape(&ptr, &errorcode, bracount, options, TRUE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - /* \b is backspace inside a class; \X is literal */ - - if (-c == ESC_b) c = '\b'; - else if (-c == ESC_X) c = 'X'; - - /* \Q enters quoting mode */ - - else if (-c == ESC_Q) - { - inescq = TRUE; - continue; - } - - /* Handle escapes that turn into characters */ - - if (c >= 0) goto NON_SPECIAL_CHARACTER; - - /* Escapes that are meta-things. The normal ones just affect the - bit map, but Unicode properties require an XCLASS extended item. */ - - else - { - class_optcount = 10; /* \d, \s etc; make sure > 1 */ -#ifdef SUPPORT_UTF8 - if (-c == ESC_p || -c == ESC_P) - { - if (!class_utf8) - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } - length += 3; - } -#endif - } - } - - /* Check the syntax for POSIX stuff. The bits we actually handle are - checked during the real compile phase. */ - - else if (*ptr == '[' && - (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &ptr, cd)) - { - ptr++; - class_optcount = 10; /* Make sure > 1 */ - } - - /* Anything else increments the possible optimization count. We have to - detect ranges here so that we can compute the number of extra ranges for - caseless wide characters when UCP support is available. If there are wide - characters, we are going to have to use an XCLASS, even for single - characters. */ - - else - { - int d; - - GET_ONE_CHARACTER: - -#ifdef SUPPORT_UTF8 - if (utf8) - { - int extra = 0; - GETCHARLEN(c, ptr, extra); - ptr += extra; - } - else c = *ptr; -#else - c = *ptr; -#endif - - /* Come here from handling \ above when it escapes to a char value */ - - NON_SPECIAL_CHARACTER: - class_optcount++; - - d = -1; - if (ptr[1] == '-') - { - uschar const *hyptr = ptr++; - if (ptr[1] == '\\') - { - ptr++; - d = check_escape(&ptr, &errorcode, bracount, options, TRUE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if (-d == ESC_b) d = '\b'; /* backspace */ - else if (-d == ESC_X) d = 'X'; /* literal X in a class */ - } - else if (ptr[1] != 0 && ptr[1] != ']') - { - ptr++; -#ifdef SUPPORT_UTF8 - if (utf8) - { - int extra = 0; - GETCHARLEN(d, ptr, extra); - ptr += extra; - } - else -#endif - d = *ptr; - } - if (d < 0) ptr = hyptr; /* go back to hyphen as data */ - } - - /* If d >= 0 we have a range. In UTF-8 mode, if the end is > 255, or > - 127 for caseless matching, we will need to use an XCLASS. */ - - if (d >= 0) - { - class_optcount = 10; /* Ensure > 1 */ - if (d < c) - { - errorcode = ERR8; - goto PCRE_ERROR_RETURN; - } - -#ifdef SUPPORT_UTF8 - if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) - { - uschar buffer[6]; - if (!class_utf8) /* Allow for XCLASS overhead */ - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } - -#ifdef SUPPORT_UCP - /* If we have UCP support, find out how many extra ranges are - needed to map the other case of characters within this range. We - have to mimic the range optimization here, because extending the - range upwards might push d over a boundary that makes is use - another byte in the UTF-8 representation. */ - - if ((options & PCRE_CASELESS) != 0) - { - int occ, ocd; - int cc = c; - int origd = d; - while (get_othercase_range(&cc, origd, &occ, &ocd)) - { - if (occ >= c && ocd <= d) continue; /* Skip embedded */ - - if (occ < c && ocd >= c - 1) /* Extend the basic range */ - { /* if there is overlap, */ - c = occ; /* noting that if occ < c */ - continue; /* we can't have ocd > d */ - } /* because a subrange is */ - if (ocd > d && occ <= d + 1) /* always shorter than */ - { /* the basic range. */ - d = ocd; - continue; - } - - /* An extra item is needed */ - - length += 1 + _pcre_ord2utf8(occ, buffer) + - ((occ == ocd)? 0 : _pcre_ord2utf8(ocd, buffer)); - } - } -#endif /* SUPPORT_UCP */ - - /* The length of the (possibly extended) range */ - - length += 1 + _pcre_ord2utf8(c, buffer) + _pcre_ord2utf8(d, buffer); - } -#endif /* SUPPORT_UTF8 */ - - } - - /* We have a single character. There is nothing to be done unless we - are in UTF-8 mode. If the char is > 255, or 127 when caseless, we must - allow for an XCL_SINGLE item, doubled for caselessness if there is UCP - support. */ - - else - { -#ifdef SUPPORT_UTF8 - if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) - { - uschar buffer[6]; - class_optcount = 10; /* Ensure > 1 */ - if (!class_utf8) /* Allow for XCLASS overhead */ - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } -#ifdef SUPPORT_UCP - length += (((options & PCRE_CASELESS) != 0)? 2 : 1) * - (1 + _pcre_ord2utf8(c, buffer)); -#else /* SUPPORT_UCP */ - length += 1 + _pcre_ord2utf8(c, buffer); -#endif /* SUPPORT_UCP */ - } -#endif /* SUPPORT_UTF8 */ - } - } - } - while (*(++ptr) != 0 && (inescq || *ptr != ']')); /* Concludes "do" above */ - - if (*ptr == 0) /* Missing terminating ']' */ - { - errorcode = ERR6; - goto PCRE_ERROR_RETURN; - } - - /* We can optimize when there was only one optimizable character. Repeats - for positive and negated single one-byte chars are handled by the general - code. Here, we handle repeats for the class opcodes. */ - - if (class_optcount == 1) length += 3; else - { - length += 33; - - /* A repeat needs either 1 or 5 bytes. If it is a possessive quantifier, - we also need extra for wrapping the whole thing in a sub-pattern. */ - - if (*ptr != 0 && ptr[1] == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; - } - else if (ptr[1] == '?') ptr++; - } - } - continue; - - /* Brackets may be genuine groups or special things */ - - case '(': - branch_newextra = 0; - bracket_length = 1 + LINK_SIZE; - capturing = FALSE; - - /* Handle special forms of bracket, which all start (? */ - - if (ptr[1] == '?') - { - int set, unset; - int *optset; - - switch (c = ptr[2]) - { - /* Skip over comments entirely */ - case '#': - ptr += 3; - while (*ptr != 0 && *ptr != ')') ptr++; - if (*ptr == 0) - { - errorcode = ERR18; - goto PCRE_ERROR_RETURN; - } - continue; - - /* Non-referencing groups and lookaheads just move the pointer on, and - then behave like a non-special bracket, except that they don't increment - the count of extracting brackets. Ditto for the "once only" bracket, - which is in Perl from version 5.005. */ - - case ':': - case '=': - case '!': - case '>': - ptr += 2; - break; - - /* Named subpatterns are an extension copied from Python */ - - case 'P': - ptr += 3; - - /* Handle the definition of a named subpattern */ - - if (*ptr == '<') - { - const uschar *p; /* Don't amalgamate; some compilers */ - p = ++ptr; /* grumble at autoincrement in declaration */ - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr != '>') - { - errorcode = ERR42; - goto PCRE_ERROR_RETURN; - } - name_count++; - if (name_count > MAX_NAME_COUNT) - { - errorcode = ERR49; - goto PCRE_ERROR_RETURN; - } - if (ptr - p > max_name_size) - { - max_name_size = (ptr - p); - if (max_name_size > MAX_NAME_SIZE) - { - errorcode = ERR48; - goto PCRE_ERROR_RETURN; - } - } - capturing = TRUE; /* Named parentheses are always capturing */ - break; /* Go handle capturing parentheses */ - } - - /* Handle back references and recursive calls to named subpatterns */ - - if (*ptr == '=' || *ptr == '>') - { - length += 3 + 3*LINK_SIZE; /* Allow for the automatic "once" */ - while ((cd->ctypes[*(++ptr)] & ctype_word) != 0); - if (*ptr != ')') - { - errorcode = ERR42; - goto PCRE_ERROR_RETURN; - } - goto RECURSE_CHECK_QUANTIFIED; - } - - /* Unknown character after (?P */ - - errorcode = ERR41; - goto PCRE_ERROR_RETURN; - - /* (?R) specifies a recursive call to the regex, which is an extension - to provide the facility which can be obtained by (?p{perl-code}) in - Perl 5.6. In Perl 5.8 this has become (??{perl-code}). - - From PCRE 4.00, items such as (?3) specify subroutine-like "calls" to - the appropriate numbered brackets. This includes both recursive and - non-recursive calls. (?R) is now synonymous with (?0). */ - - case 'R': - ptr++; - - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': - ptr += 2; - if (c != 'R') - while ((digitab[*(++ptr)] & ctype_digit) != 0); - if (*ptr != ')') - { - errorcode = ERR29; - goto PCRE_ERROR_RETURN; - } - length += 3 + 3*LINK_SIZE; /* Allows for the automatic "once" */ - - /* If this item is quantified, it will get wrapped inside brackets so - as to use the code for quantified brackets. We jump down and use the - code that handles this for real brackets. Come here from code for - named recursions/subroutines. */ - - RECURSE_CHECK_QUANTIFIED: - if (ptr[1] == '+' || ptr[1] == '*' || ptr[1] == '?' || ptr[1] == '{') - { - length += 2 + 2 * LINK_SIZE; /* to make bracketed */ - duplength = 5 + 3 * LINK_SIZE; - goto HANDLE_QUANTIFIED_BRACKETS; - } - continue; - - /* (?C) is an extension which provides "callout" - to provide a bit of - the functionality of the Perl (?{...}) feature. An optional number may - follow (default is zero). */ - - case 'C': - ptr += 2; - while ((digitab[*(++ptr)] & ctype_digit) != 0); - if (*ptr != ')') - { - errorcode = ERR39; - goto PCRE_ERROR_RETURN; - } - length += 2 + 2*LINK_SIZE; - continue; - - /* Lookbehinds are in Perl from version 5.005 */ - - case '<': - ptr += 3; - if (*ptr == '=' || *ptr == '!') - { - branch_newextra = 1 + LINK_SIZE; - length += 1 + LINK_SIZE; /* For the first branch */ - break; - } - errorcode = ERR24; - goto PCRE_ERROR_RETURN; - - /* Conditionals are in Perl from version 5.005. The bracket must either - be followed by a number (for bracket reference) or by an assertion - group. PCRE extends this by allowing a name to reference a named group; - unfortunately, previously 'R' was implemented for a recursion test. - When this is compiled, we look for the named group 'R' first. At this - point we just do a basic syntax check. */ - - case '(': - if ((cd->ctypes[ptr[3]] & ctype_word) != 0) - { - ptr += 4; - length += 3; - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr != ')') - { - errorcode = ERR26; - goto PCRE_ERROR_RETURN; - } - } - else /* An assertion must follow */ - { - ptr++; /* Can treat like ':' as far as spacing is concerned */ - if (ptr[2] != '?' || - (ptr[3] != '=' && ptr[3] != '!' && ptr[3] != '<') ) - { - ptr += 2; /* To get right offset in message */ - errorcode = ERR28; - goto PCRE_ERROR_RETURN; - } - } - break; - - /* Else loop checking valid options until ) is met. Anything else is an - error. If we are without any brackets, i.e. at top level, the settings - act as if specified in the options, so massage the options immediately. - This is for backward compatibility with Perl 5.004. */ - - default: - set = unset = 0; - optset = &set; - ptr += 2; - - for (;; ptr++) - { - c = *ptr; - switch (c) - { - case 'i': - *optset |= PCRE_CASELESS; - continue; - - case 'J': - *optset |= PCRE_DUPNAMES; - options |= PCRE_JCHANGED; /* Record that it changed */ - continue; - - case 'm': - *optset |= PCRE_MULTILINE; - continue; - - case 's': - *optset |= PCRE_DOTALL; - continue; - - case 'x': - *optset |= PCRE_EXTENDED; - continue; - - case 'X': - *optset |= PCRE_EXTRA; - continue; - - case 'U': - *optset |= PCRE_UNGREEDY; - continue; - - case '-': - optset = &unset; - continue; - - /* A termination by ')' indicates an options-setting-only item; if - this is at the very start of the pattern (indicated by item_count - being zero), we use it to set the global options. This is helpful - when analyzing the pattern for first characters, etc. Otherwise - nothing is done here and it is handled during the compiling - process. - - We allow for more than one options setting at the start. If such - settings do not change the existing options, nothing is compiled. - However, we must leave space just in case something is compiled. - This can happen for pathological sequences such as (?i)(?-i) - because the global options will end up with -i set. The space is - small and not significant. (Before I did this there was a reported - bug with (?i)(?-i) in a machine-generated pattern.) - - [Historical note: Up to Perl 5.8, options settings at top level - were always global settings, wherever they appeared in the pattern. - That is, they were equivalent to an external setting. From 5.8 - onwards, they apply only to what follows (which is what you might - expect).] */ - - case ')': - if (item_count == 0) - { - options = (options | set) & (~unset); - set = unset = 0; /* To save length */ - item_count--; /* To allow for several */ - length += 2; - } - - /* Fall through */ - - /* A termination by ':' indicates the start of a nested group with - the given options set. This is again handled at compile time, but - we must allow for compiled space if any of the ims options are - set. We also have to allow for resetting space at the end of - the group, which is why 4 is added to the length and not just 2. - If there are several changes of options within the same group, this - will lead to an over-estimate on the length, but this shouldn't - matter very much. We also have to allow for resetting options at - the start of any alternations, which we do by setting - branch_newextra to 2. */ - - case ':': - if (((set|unset) & PCRE_IMS) != 0) - { - length += 4; - branch_newextra = 2; - } - goto END_OPTIONS; - - /* Unrecognized option character */ - - default: - errorcode = ERR12; - goto PCRE_ERROR_RETURN; - } - } - - /* If we hit a closing bracket, that's it - this is a freestanding - option-setting. We need to ensure that branch_extra is updated if - necessary. The only values branch_newextra can have here are 0 or 2. - If the value is 2, then branch_extra must either be 2 or 5, depending - on whether this is a lookbehind group or not. */ - - END_OPTIONS: - if (c == ')') - { - if (branch_newextra == 2 && - (branch_extra == 0 || branch_extra == 1+LINK_SIZE)) - branch_extra += branch_newextra; - continue; - } - - /* If options were terminated by ':' control comes here. This is a - non-capturing group with an options change. There is nothing more that - needs to be done because "capturing" is already set FALSE by default; - we can just fall through. */ - - } - } - - /* Ordinary parentheses, not followed by '?', are capturing unless - PCRE_NO_AUTO_CAPTURE is set. */ - - else capturing = (options & PCRE_NO_AUTO_CAPTURE) == 0; - - /* Capturing brackets must be counted so we can process escapes in a - Perlish way. If the number exceeds EXTRACT_BASIC_MAX we are going to need - an additional 3 bytes of memory per capturing bracket. */ - - if (capturing) - { - bracount++; - if (bracount > EXTRACT_BASIC_MAX) bracket_length += 3; - } - - /* Save length for computing whole length at end if there's a repeat that - requires duplication of the group. Also save the current value of - branch_extra, and start the new group with the new value. If non-zero, this - will either be 2 for a (?imsx: group, or 3 for a lookbehind assertion. */ - - if (brastackptr >= sizeof(brastack)/sizeof(int)) - { - errorcode = ERR19; - goto PCRE_ERROR_RETURN; - } - - bralenstack[brastackptr] = branch_extra; - branch_extra = branch_newextra; - - brastack[brastackptr++] = length; - length += bracket_length; - continue; - - /* Handle ket. Look for subsequent max/min; for certain sets of values we - have to replicate this bracket up to that many times. If brastackptr is - 0 this is an unmatched bracket which will generate an error, but take care - not to try to access brastack[-1] when computing the length and restoring - the branch_extra value. */ - - case ')': - length += 1 + LINK_SIZE; - if (brastackptr > 0) - { - duplength = length - brastack[--brastackptr]; - branch_extra = bralenstack[brastackptr]; - /* This is a paranoid check to stop integer overflow later on */ - if (duplength > MAX_DUPLENGTH) - { - errorcode = ERR50; - goto PCRE_ERROR_RETURN; - } - } - else duplength = 0; - - /* The following code is also used when a recursion such as (?3) is - followed by a quantifier, because in that case, it has to be wrapped inside - brackets so that the quantifier works. The value of duplength must be - set before arrival. */ - - HANDLE_QUANTIFIED_BRACKETS: - - /* Leave ptr at the final char; for read_repeat_counts this happens - automatically; for the others we need an increment. */ - - if ((c = ptr[1]) == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - } - else if (c == '*') { min = 0; max = -1; ptr++; } - else if (c == '+') { min = 1; max = -1; ptr++; } - else if (c == '?') { min = 0; max = 1; ptr++; } - else { min = 1; max = 1; } - - /* If the minimum is zero, we have to allow for an OP_BRAZERO before the - group, and if the maximum is greater than zero, we have to replicate - maxval-1 times; each replication acquires an OP_BRAZERO plus a nesting - bracket set. */ - - if (min == 0) - { - length++; - if (max > 0) length += (max - 1) * (duplength + 3 + 2*LINK_SIZE); - } - - /* When the minimum is greater than zero, we have to replicate up to - minval-1 times, with no additions required in the copies. Then, if there - is a limited maximum we have to replicate up to maxval-1 times allowing - for a BRAZERO item before each optional copy and nesting brackets for all - but one of the optional copies. */ - - else - { - length += (min - 1) * duplength; - if (max > min) /* Need this test as max=-1 means no limit */ - length += (max - min) * (duplength + 3 + 2*LINK_SIZE) - - (2 + 2*LINK_SIZE); - } - - /* Allow space for once brackets for "possessive quantifier" */ - - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; - } - continue; - - /* Non-special character. It won't be space or # in extended mode, so it is - always a genuine character. If we are in a \Q...\E sequence, check for the - end; if not, we have a literal. */ - - default: - NORMAL_CHAR: - - if (inescq && c == '\\' && ptr[1] == 'E') - { - inescq = FALSE; - ptr++; - continue; - } - - length += 2; /* For a one-byte character */ - lastitemlength = 1; /* Default length of last item for repeats */ - - /* In UTF-8 mode, check for additional bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (c & 0xc0) == 0xc0) - { - while ((ptr[1] & 0xc0) == 0x80) /* Can't flow over the end */ - { /* because the end is marked */ - lastitemlength++; /* by a zero byte. */ - length++; - ptr++; - } - } -#endif - - continue; - } - } - -length += 2 + LINK_SIZE; /* For final KET and END */ - -if ((options & PCRE_AUTO_CALLOUT) != 0) - length += 2 + 2*LINK_SIZE; /* For final callout */ +/* Pretend to compile the pattern while actually just accumulating the length +of memory required. This behaviour is triggered by passing a non-NULL final +argument to compile_regex(). We pass a block of workspace (cworkspace) for it +to compile parts of the pattern into; the compiled code is discarded when it is +no longer needed, so hopefully this workspace will never overflow, though there +is a test for its doing so. */ + +cd->bracount = 0; +cd->names_found = 0; +cd->name_entry_size = 0; +cd->name_table = NULL; +cd->start_workspace = cworkspace; +cd->start_code = cworkspace; +cd->hwm = cworkspace; +cd->start_pattern = (const uschar *)pattern; +cd->end_pattern = (const uschar *)(pattern + strlen(pattern)); +cd->req_varyopt = 0; +cd->nopartial = FALSE; +cd->external_options = options; + +/* Now do the pre-compile. On error, errorcode will be set non-zero, so we +don't need to look at the result of the function here. The initial options have +been put into the cd block so that they can be changed if an option setting is +found within the regex right at the beginning. Bringing initial option settings +outside can help speed up starting point checks. */ + +code = cworkspace; +*code = OP_BRA; +(void)compile_regex(cd->external_options, cd->external_options & PCRE_IMS, + &code, &ptr, &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, + &length); +if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; + +DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, + cd->hwm - cworkspace)); if (length > MAX_PATTERN_SIZE) { @@ -5091,9 +5602,10 @@ if (length > MAX_PATTERN_SIZE) /* Compute the size of data block needed and get it, either from malloc or externally provided function. Integer overflow should no longer be possible -because nowadays we limit the maximum value of name_count and max_name size. */ +because nowadays we limit the maximum value of cd->names_found and +cd->name_entry_size. */ -size = length + sizeof(real_pcre) + name_count * (max_name_size + 3); +size = length + sizeof(real_pcre) + cd->names_found * (cd->name_entry_size + 3); re = (real_pcre *)(pcre_malloc)(size); if (re == NULL) @@ -5102,31 +5614,37 @@ if (re == NULL) goto PCRE_EARLY_ERROR_RETURN; } -/* Put in the magic number, and save the sizes, options, and character table -pointer. NULL is used for the default character tables. The nullpad field is at -the end; it's there to help in the case when a regex compiled on a system with -4-byte pointers is run on another with 8-byte pointers. */ +/* Put in the magic number, and save the sizes, initial options, and character +table pointer. NULL is used for the default character tables. The nullpad field +is at the end; it's there to help in the case when a regex compiled on a system +with 4-byte pointers is run on another with 8-byte pointers. */ re->magic_number = MAGIC_NUMBER; re->size = size; -re->options = options; +re->options = cd->external_options; re->dummy1 = 0; +re->first_byte = 0; +re->req_byte = 0; re->name_table_offset = sizeof(real_pcre); -re->name_entry_size = max_name_size + 3; -re->name_count = name_count; +re->name_entry_size = cd->name_entry_size; +re->name_count = cd->names_found; re->ref_count = 0; re->tables = (tables == _pcre_default_tables)? NULL : tables; re->nullpad = NULL; /* The starting points of the name/number translation table and of the code are -passed around in the compile data block. */ +passed around in the compile data block. The start/end pattern and initial +options are already set from the pre-compile phase, as is the name_entry_size +field. Reset the bracket count and the names_found field. Also reset the hwm +field; this time it's used for remembering forward references to subpatterns. +*/ +cd->bracount = 0; cd->names_found = 0; -cd->name_entry_size = max_name_size + 3; cd->name_table = (uschar *)re + re->name_table_offset; codestart = cd->name_table + re->name_entry_size * re->name_count; cd->start_code = codestart; -cd->start_pattern = (const uschar *)pattern; +cd->hwm = cworkspace; cd->req_varyopt = 0; cd->nopartial = FALSE; @@ -5137,10 +5655,9 @@ of the function here. */ ptr = (const uschar *)pattern; code = (uschar *)codestart; *code = OP_BRA; -bracount = 0; -(void)compile_regex(options, options & PCRE_IMS, &bracount, &code, &ptr, - &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd); -re->top_bracket = bracount; +(void)compile_regex(re->options, re->options & PCRE_IMS, &code, &ptr, + &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); +re->top_bracket = cd->bracount; re->top_backref = cd->top_backref; if (cd->nopartial) re->options |= PCRE_NOPARTIAL; @@ -5158,19 +5675,33 @@ if debugging, leave the test till after things are printed out. */ if (code - codestart > length) errorcode = ERR23; #endif +/* Fill in any forward references that are required. */ + +while (errorcode == 0 && cd->hwm > cworkspace) + { + int offset, recno; + const uschar *groupptr; + cd->hwm -= LINK_SIZE; + offset = GET(cd->hwm, 0); + recno = GET(codestart, offset); + groupptr = find_bracket(codestart, (re->options & PCRE_UTF8) != 0, recno); + if (groupptr == NULL) errorcode = ERR53; + else PUT(((uschar *)codestart), offset, groupptr - codestart); + } + /* Give an error if there's back reference to a non-existent capturing subpattern. */ -if (re->top_backref > re->top_bracket) errorcode = ERR15; +if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; /* Failed to compile, or error while post-processing */ if (errorcode != 0) { (pcre_free)(re); - PCRE_ERROR_RETURN: - *erroroffset = ptr - (const uschar *)pattern; PCRE_EARLY_ERROR_RETURN: + *erroroffset = ptr - (const uschar *)pattern; + PCRE_EARLY_ERROR_RETURN2: *errorptr = error_texts[errorcode]; if (errorcodeptr != NULL) *errorcodeptr = errorcode; return NULL; @@ -5180,15 +5711,15 @@ if (errorcode != 0) the pattern is anchored by virtue of ^ characters or \A or anything else (such as starting with .* when DOTALL is set). -Otherwise, if we know what the first character has to be, save it, because that +Otherwise, if we know what the first byte has to be, save it, because that speeds up unanchored matches no end. If not, see if we can set the PCRE_STARTLINE flag. This is helpful for multiline matches when all branches start with ^. and also when all branches start with .* for non-DOTALL matches. */ -if ((options & PCRE_ANCHORED) == 0) +if ((re->options & PCRE_ANCHORED) == 0) { - int temp_options = options; + int temp_options = re->options; /* May get changed during these scans */ if (is_anchored(codestart, &temp_options, 0, cd->backref_map)) re->options |= PCRE_ANCHORED; else @@ -5260,7 +5791,7 @@ if ((re->options & PCRE_REQCHSET) != 0) else printf("Req char = \\x%02x%s\n", ch, caseless); } -pcre_printint(re, stdout); +pcre_printint(re, stdout, TRUE); /* This check is done here in the debugging case so that the code that was compiled can be seen. */ @@ -5273,7 +5804,7 @@ if (code - codestart > length) if (errorcodeptr != NULL) *errorcodeptr = ERR23; return NULL; } -#endif +#endif /* DEBUG */ return (pcre *)re; } diff --git a/libpcre/pcre_config.c b/libpcre/pcre_config.c index 29e6c1a35..52d259466 100644 --- a/libpcre/pcre_config.c +++ b/libpcre/pcre_config.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -58,7 +58,7 @@ Arguments: Returns: 0 if data returned, negative on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_config(int what, void *where) { switch (what) diff --git a/libpcre/pcre_dfa_exec.c b/libpcre/pcre_dfa_exec.c index 5396d633b..87f9746af 100644 --- a/libpcre/pcre_dfa_exec.c +++ b/libpcre/pcre_dfa_exec.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -39,11 +39,15 @@ POSSIBILITY OF SUCH DAMAGE. /* This module contains the external function pcre_dfa_exec(), which is an -alternative matching function that uses a DFA algorithm. This is NOT Perl- -compatible, but it has advantages in certain applications. */ +alternative matching function that uses a sort of DFA algorithm (not a true +FSM). This is NOT Perl- compatible, but it has advantages in certain +applications. */ -#define NLBLOCK md /* The block containing newline information */ +#define NLBLOCK md /* Block containing newline information */ +#define PSSTART start_subject /* Field containing processed string start */ +#define PSEND end_subject /* Field containing processed string end */ + #include "pcre_internal.h" @@ -58,24 +62,31 @@ compatible, but it has advantages in certain applications. */ *************************************************/ /* These are offsets that are used to turn the OP_TYPESTAR and friends opcodes -into others, under special conditions. A gap of 10 between the blocks should be -enough. */ +into others, under special conditions. A gap of 20 between the blocks should be +enough. The resulting opcodes don't have to be less than 256 because they are +never stored, so we push them well clear of the normal opcodes. */ -#define OP_PROP_EXTRA (EXTRACT_BASIC_MAX+1) -#define OP_EXTUNI_EXTRA (EXTRACT_BASIC_MAX+11) +#define OP_PROP_EXTRA 300 +#define OP_EXTUNI_EXTRA 320 +#define OP_ANYNL_EXTRA 340 +#define OP_HSPACE_EXTRA 360 +#define OP_VSPACE_EXTRA 380 /* This table identifies those opcodes that are followed immediately by a character that is to be tested in some way. This makes is possible to centralize the loading of these characters. In the case of Type * etc, the "character" is the opcode for \D, \d, \S, \s, \W, or \w, which will always be a -small value. */ +small value. ***NOTE*** If the start of this table is modified, the two tables +that follow must also be modified. */ static uschar coptable[] = { 0, /* End */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* \A, \G, \B, \b, \D, \d, \S, \s, \W, \w */ + 0, 0, 0, 0, 0, /* \A, \G, \K, \B, \b */ + 0, 0, 0, 0, 0, 0, /* \D, \d, \S, \s, \W, \w */ 0, 0, /* Any, Anybyte */ 0, 0, 0, /* NOTPROP, PROP, EXTUNI */ + 0, 0, 0, 0, 0, /* \R, \H, \h, \V, \v */ 0, 0, 0, 0, 0, /* \Z, \z, Opt, ^, $ */ 1, /* Char */ 1, /* Charnc */ @@ -83,12 +94,15 @@ static uschar coptable[] = { /* Positive single-char repeats */ 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ 3, 3, 3, /* upto, minupto, exact */ + 1, 1, 1, 3, /* *+, ++, ?+, upto+ */ /* Negative single-char repeats - only for chars < 256 */ 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ 3, 3, 3, /* NOT upto, minupto, exact */ + 1, 1, 1, 3, /* NOT *+, ++, ?+, updo+ */ /* Positive type repeats */ 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ 3, 3, 3, /* Type upto, minupto, exact */ + 1, 1, 1, 3, /* Type *+, ++, ?+, upto+ */ /* Character class & ref repeats */ 0, 0, 0, 0, 0, 0, /* *, *?, +, +?, ?, ?? */ 0, 0, /* CRRANGE, CRMINRANGE */ @@ -107,19 +121,19 @@ static uschar coptable[] = { 0, /* Assert behind */ 0, /* Assert behind not */ 0, /* Reverse */ - 0, /* Once */ - 0, /* COND */ + 0, 0, 0, 0, /* ONCE, BRA, CBRA, COND */ + 0, 0, 0, /* SBRA, SCBRA, SCOND */ 0, /* CREF */ - 0, 0, /* BRAZERO, BRAMINZERO */ - 0, /* BRANUMBER */ - 0 /* BRA */ + 0, /* RREF */ + 0, /* DEF */ + 0, 0 /* BRAZERO, BRAMINZERO */ }; /* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W, and \w */ static uschar toptable1[] = { - 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, ctype_digit, ctype_digit, ctype_space, ctype_space, ctype_word, ctype_word, @@ -127,7 +141,7 @@ static uschar toptable1[] = { }; static uschar toptable2[] = { - 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, ctype_digit, 0, ctype_space, 0, ctype_word, 0, @@ -278,7 +292,7 @@ stateblock *next_active_state, *next_new_state; const uschar *ctypes, *lcc, *fcc; const uschar *ptr; -const uschar *end_code; +const uschar *end_code, *first_op; int active_count, new_count, match_count; @@ -291,6 +305,8 @@ const uschar *start_code = md->start_code; #ifdef SUPPORT_UTF8 BOOL utf8 = (md->poptions & PCRE_UTF8) != 0; +#else +BOOL utf8 = FALSE; #endif rlevel++; @@ -314,6 +330,9 @@ active_states = (stateblock *)(workspace + 2); next_new_state = new_states = active_states + wscount; new_count = 0; +first_op = this_start_code + 1 + LINK_SIZE + + ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA)? 2:0); + /* The first thing in any (sub) pattern is a bracket of some sort. Push all the alternative states onto the list, and find out where the end is. This makes is possible to use this function recursively, when we want to stop at a @@ -323,7 +342,7 @@ If the first opcode in the first alternative is OP_REVERSE, we are dealing with a backward assertion. In that case, we have to find out the maximum amount to move back, and set up each alternative appropriately. */ -if (this_start_code[1+LINK_SIZE] == OP_REVERSE) +if (*first_op == OP_REVERSE) { int max_back = 0; int gone_back; @@ -405,10 +424,13 @@ else else { + int length = 1 + LINK_SIZE + + ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA)? 2:0); do { - ADD_NEW(end_code - start_code + 1 + LINK_SIZE, 0); + ADD_NEW(end_code - start_code + length, 0); end_code += GET(end_code, 1); + length = 1 + LINK_SIZE; } while (*end_code == OP_ALT); } @@ -461,7 +483,7 @@ for (;;) if (ptr < end_subject) { - clen = 1; + clen = 1; /* Number of bytes in the character */ #ifdef SUPPORT_UTF8 if (utf8) { GETCHARLEN(c, ptr, clen); } else #endif /* SUPPORT_UTF8 */ @@ -469,8 +491,8 @@ for (;;) } else { - clen = 0; /* At end subject */ - c = -1; + clen = 0; /* This indicates the end of the subject */ + c = NOTACHAR; /* This value should never actually be used */ } /* Scan up the active states and act on each one. The result of an action @@ -484,11 +506,13 @@ for (;;) const uschar *code; int state_offset = current_state->offset; int count, codevalue; +#ifdef SUPPORT_UCP int chartype, script; +#endif #ifdef DEBUG printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); - if (c < 0) printf("-1\n"); + if (clen == 0) printf("EOL\n"); else if (c > 32 && c < 127) printf("'%c'\n", c); else printf("0x%02x\n", c); #endif @@ -532,7 +556,6 @@ for (;;) code = start_code + state_offset; codevalue = *code; - if (codevalue >= OP_BRA) codevalue = OP_BRA; /* All brackets are equal */ /* If this opcode is followed by an inline character, load it. It is tempting to test for the presence of a subject character here, but that @@ -540,10 +563,10 @@ for (;;) permitted. We also use this mechanism for opcodes such as OP_TYPEPLUS that take an - argument that is not a data character - but is always one byte long. - Unfortunately, we have to take special action to deal with \P, \p, and - \X in this case. To keep the other cases fast, convert these ones to new - opcodes. */ + argument that is not a data character - but is always one byte long. We + have to take special action to deal with \P, \p, \H, \h, \V, \v and \X in + this case. To keep the other cases fast, convert these ones to new opcodes. + */ if (coptable[codevalue] > 0) { @@ -554,15 +577,25 @@ for (;;) d = code[coptable[codevalue]]; if (codevalue >= OP_TYPESTAR) { - if (d == OP_ANYBYTE) return PCRE_ERROR_DFA_UITEM; - if (d >= OP_NOTPROP) - codevalue += (d == OP_EXTUNI)? OP_EXTUNI_EXTRA : OP_PROP_EXTRA; + switch(d) + { + case OP_ANYBYTE: return PCRE_ERROR_DFA_UITEM; + case OP_NOTPROP: + case OP_PROP: codevalue += OP_PROP_EXTRA; break; + case OP_ANYNL: codevalue += OP_ANYNL_EXTRA; break; + case OP_EXTUNI: codevalue += OP_EXTUNI_EXTRA; break; + case OP_NOT_HSPACE: + case OP_HSPACE: codevalue += OP_HSPACE_EXTRA; break; + case OP_NOT_VSPACE: + case OP_VSPACE: codevalue += OP_VSPACE_EXTRA; break; + default: break; + } } } else { dlen = 0; /* Not strictly necessary, but compilers moan */ - d = -1; /* if these variables are not set. */ + d = NOTACHAR; /* if these variables are not set. */ } @@ -624,6 +657,7 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_BRA: + case OP_SBRA: do { ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); @@ -632,6 +666,18 @@ for (;;) while (*code == OP_ALT); break; + /*-----------------------------------------------------------------*/ + case OP_CBRA: + case OP_SCBRA: + ADD_ACTIVE(code - start_code + 3 + LINK_SIZE, 0); + code += GET(code, 1); + while (*code == OP_ALT) + { + ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); + code += GET(code, 1); + } + break; + /*-----------------------------------------------------------------*/ case OP_BRAZERO: case OP_BRAMINZERO: @@ -641,18 +687,12 @@ for (;;) ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); break; - /*-----------------------------------------------------------------*/ - case OP_BRANUMBER: - ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); - break; - /*-----------------------------------------------------------------*/ case OP_CIRC: if ((ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) || ((ims & PCRE_MULTILINE) != 0 && - ptr >= start_subject + md->nllen && ptr != end_subject && - IS_NEWLINE(ptr - md->nllen))) + WAS_NEWLINE(ptr))) { ADD_ACTIVE(state_offset + 1, 0); } break; @@ -686,16 +726,13 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_ANY: - if (clen > 0 && ((ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || - !IS_NEWLINE(ptr))) + if (clen > 0 && ((ims & PCRE_DOTALL) != 0 || !IS_NEWLINE(ptr))) { ADD_NEW(state_offset + 1, 0); } break; /*-----------------------------------------------------------------*/ case OP_EODN: - if (clen == 0 || - (ptr == end_subject - md->nllen && IS_NEWLINE(ptr))) + if (clen == 0 || (IS_NEWLINE(ptr) && ptr == end_subject - md->nllen)) { ADD_ACTIVE(state_offset + 1, 0); } break; @@ -704,13 +741,12 @@ for (;;) if ((md->moptions & PCRE_NOTEOL) == 0) { if (clen == 0 || - (ptr <= end_subject - md->nllen && IS_NEWLINE(ptr) && + (IS_NEWLINE(ptr) && ((ims & PCRE_MULTILINE) != 0 || ptr == end_subject - md->nllen) )) { ADD_ACTIVE(state_offset + 1, 0); } } - else if ((ims & PCRE_MULTILINE) != 0 && - ptr <= end_subject - md->nllen && IS_NEWLINE(ptr)) + else if ((ims & PCRE_MULTILINE) != 0 && IS_NEWLINE(ptr)) { ADD_ACTIVE(state_offset + 1, 0); } break; @@ -759,13 +795,12 @@ for (;;) break; -#ifdef SUPPORT_UCP - /*-----------------------------------------------------------------*/ /* Check the next character by Unicode property. We will get here only if the support is in the binary; otherwise a compile-time error occurs. */ +#ifdef SUPPORT_UCP case OP_PROP: case OP_NOTPROP: if (clen > 0) @@ -816,6 +851,7 @@ for (;;) case OP_TYPEPLUS: case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } if (clen > 0) @@ -824,11 +860,15 @@ for (;;) (c < 256 && (d != OP_ANY || (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || !IS_NEWLINE(ptr) ) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (count > 0 && codevalue == OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } count++; ADD_NEW(state_offset, count); } @@ -838,6 +878,7 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_TYPEQUERY: case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: ADD_ACTIVE(state_offset + 2, 0); if (clen > 0) { @@ -845,11 +886,15 @@ for (;;) (c < 256 && (d != OP_ANY || (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || !IS_NEWLINE(ptr) ) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (codevalue == OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } ADD_NEW(state_offset + 2, 0); } } @@ -858,6 +903,7 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_TYPESTAR: case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: ADD_ACTIVE(state_offset + 2, 0); if (clen > 0) { @@ -865,11 +911,15 @@ for (;;) (c < 256 && (d != OP_ANY || (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || !IS_NEWLINE(ptr) ) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (codevalue == OP_TYPEPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } ADD_NEW(state_offset, 0); } } @@ -877,10 +927,6 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - if (codevalue != OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 4, 0); } count = current_state->count; /* Number already matched */ if (clen > 0) { @@ -888,7 +934,6 @@ for (;;) (c < 256 && (d != OP_ANY || (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || !IS_NEWLINE(ptr) ) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) @@ -901,14 +946,45 @@ for (;;) } break; + /*-----------------------------------------------------------------*/ + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + ADD_ACTIVE(state_offset + 4, 0); + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || + (ims & PCRE_DOTALL) != 0 || + !IS_NEWLINE(ptr) + ) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (codevalue == OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + 4, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + /* ========================================================================== */ /* These are virtual opcodes that are used when something like - OP_TYPEPLUS has OP_PROP, OP_NOTPROP, or OP_EXTUNI as its argument. It - keeps the code above fast for the other cases. The argument is in the - d variable. */ + OP_TYPEPLUS has OP_PROP, OP_NOTPROP, OP_ANYNL, or OP_EXTUNI as its + argument. It keeps the code above fast for the other cases. The argument + is in the d variable. */ +#ifdef SUPPORT_UCP case OP_PROP_EXTRA + OP_TYPEPLUS: case OP_PROP_EXTRA + OP_TYPEMINPLUS: + case OP_PROP_EXTRA + OP_TYPEPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + 4, 0); } if (clen > 0) @@ -944,19 +1020,34 @@ for (;;) break; } - if (OK == (d == OP_PROP)) { count++; ADD_NEW(state_offset, count); } + if (OK == (d == OP_PROP)) + { + if (count > 0 && codevalue == OP_PROP_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } } break; /*-----------------------------------------------------------------*/ case OP_EXTUNI_EXTRA + OP_TYPEPLUS: case OP_EXTUNI_EXTRA + OP_TYPEMINPLUS: + case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) { const uschar *nptr = ptr + clen; int ncount = 0; + if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } while (nptr < end_subject) { int nd; @@ -970,15 +1061,143 @@ for (;;) ADD_NEW_DATA(-state_offset, count, ncount); } break; +#endif /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEPLUS: + case OP_ANYNL_EXTRA + OP_TYPEMINPLUS: + case OP_ANYNL_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, ncount); + break; + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEPLUS: + case OP_VSPACE_EXTRA + OP_TYPEMINPLUS: + case OP_VSPACE_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_VSPACE)) + { + if (count > 0 && codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEPLUS: + case OP_HSPACE_EXTRA + OP_TYPEMINPLUS: + case OP_HSPACE_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (count > 0 && codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ +#ifdef SUPPORT_UCP case OP_PROP_EXTRA + OP_TYPEQUERY: case OP_PROP_EXTRA + OP_TYPEMINQUERY: + case OP_PROP_EXTRA + OP_TYPEPOSQUERY: count = 4; goto QS1; case OP_PROP_EXTRA + OP_TYPESTAR: case OP_PROP_EXTRA + OP_TYPEMINSTAR: + case OP_PROP_EXTRA + OP_TYPEPOSSTAR: count = 0; QS1: @@ -1017,18 +1236,29 @@ for (;;) break; } - if (OK == (d == OP_PROP)) { ADD_NEW(state_offset + count, 0); } + if (OK == (d == OP_PROP)) + { + if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_PROP_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + count, 0); + } } break; /*-----------------------------------------------------------------*/ case OP_EXTUNI_EXTRA + OP_TYPEQUERY: case OP_EXTUNI_EXTRA + OP_TYPEMINQUERY: + case OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY: count = 2; goto QS2; case OP_EXTUNI_EXTRA + OP_TYPESTAR: case OP_EXTUNI_EXTRA + OP_TYPEMINSTAR: + case OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR: count = 0; QS2: @@ -1038,6 +1268,12 @@ for (;;) { const uschar *nptr = ptr + clen; int ncount = 0; + if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } while (nptr < end_subject) { int nd; @@ -1050,11 +1286,161 @@ for (;;) ADD_NEW_DATA(-(state_offset + count), 0, ncount); } break; +#endif /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEQUERY: + case OP_ANYNL_EXTRA + OP_TYPEMINQUERY: + case OP_ANYNL_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS3; + + case OP_ANYNL_EXTRA + OP_TYPESTAR: + case OP_ANYNL_EXTRA + OP_TYPEMINSTAR: + case OP_ANYNL_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS3: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + count), 0, ncount); + break; + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEQUERY: + case OP_VSPACE_EXTRA + OP_TYPEMINQUERY: + case OP_VSPACE_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS4; + + case OP_VSPACE_EXTRA + OP_TYPESTAR: + case OP_VSPACE_EXTRA + OP_TYPEMINSTAR: + case OP_VSPACE_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS4: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + if (OK == (d == OP_VSPACE)) + { + if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + count), 0, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEQUERY: + case OP_HSPACE_EXTRA + OP_TYPEMINQUERY: + case OP_HSPACE_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS5; + + case OP_HSPACE_EXTRA + OP_TYPESTAR: + case OP_HSPACE_EXTRA + OP_TYPEMINSTAR: + case OP_HSPACE_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS5: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + count), 0, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ +#ifdef SUPPORT_UCP case OP_PROP_EXTRA + OP_TYPEEXACT: case OP_PROP_EXTRA + OP_TYPEUPTO: case OP_PROP_EXTRA + OP_TYPEMINUPTO: + case OP_PROP_EXTRA + OP_TYPEPOSUPTO: if (codevalue != OP_PROP_EXTRA + OP_TYPEEXACT) { ADD_ACTIVE(state_offset + 6, 0); } count = current_state->count; /* Number already matched */ @@ -1093,6 +1479,11 @@ for (;;) if (OK == (d == OP_PROP)) { + if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } if (++count >= GET2(code, 1)) { ADD_NEW(state_offset + 6, 0); } else @@ -1105,6 +1496,7 @@ for (;;) case OP_EXTUNI_EXTRA + OP_TYPEEXACT: case OP_EXTUNI_EXTRA + OP_TYPEUPTO: case OP_EXTUNI_EXTRA + OP_TYPEMINUPTO: + case OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO: if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) { ADD_ACTIVE(state_offset + 4, 0); } count = current_state->count; /* Number already matched */ @@ -1112,6 +1504,11 @@ for (;;) { const uschar *nptr = ptr + clen; int ncount = 0; + if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } while (nptr < end_subject) { int nd; @@ -1127,6 +1524,142 @@ for (;;) { ADD_NEW_DATA(-state_offset, count, ncount); } } break; +#endif + + /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEEXACT: + case OP_ANYNL_EXTRA + OP_TYPEUPTO: + case OP_ANYNL_EXTRA + OP_TYPEMINUPTO: + case OP_ANYNL_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_ANYNL_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, ncount); } + else + { ADD_NEW_DATA(-state_offset, count, ncount); } + break; + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEEXACT: + case OP_VSPACE_EXTRA + OP_TYPEUPTO: + case OP_VSPACE_EXTRA + OP_TYPEMINUPTO: + case OP_VSPACE_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_VSPACE_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + OK = TRUE; + break; + + default: + OK = FALSE; + } + + if (OK == (d == OP_VSPACE)) + { + if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, 0); } + else + { ADD_NEW_DATA(-state_offset, count, 0); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEEXACT: + case OP_HSPACE_EXTRA + OP_TYPEUPTO: + case OP_HSPACE_EXTRA + OP_TYPEMINUPTO: + case OP_HSPACE_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_HSPACE_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, 0); } + else + { ADD_NEW_DATA(-state_offset, count, 0); } + } + } + break; /* ========================================================================== */ /* These opcodes are followed by a character that is usually compared @@ -1148,7 +1681,7 @@ for (;;) { if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else { - int othercase; + unsigned int othercase; if (c < 128) othercase = fcc[c]; else /* If we have Unicode property support, we can use it to test the @@ -1157,7 +1690,7 @@ for (;;) #ifdef SUPPORT_UCP othercase = _pcre_ucp_othercase(c); #else - othercase = -1; + othercase = NOTACHAR; #endif if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); } @@ -1197,6 +1730,131 @@ for (;;) break; #endif + /*-----------------------------------------------------------------*/ + /* This is a tricky like EXTUNI because it too can match more than one + character (when CR is followed by LF). In this case, set up a negative + state to wait for one character to pass before continuing. */ + + case OP_ANYNL: + if (clen > 0) switch(c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + ADD_NEW(state_offset + 1, 0); + break; + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) + { + ADD_NEW_DATA(-(state_offset + 1), 0, 1); + } + else + { + ADD_NEW(state_offset + 1, 0); + } + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_VSPACE: + if (clen > 0) switch(c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + break; + + default: + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE: + if (clen > 0) switch(c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + ADD_NEW(state_offset + 1, 0); + break; + + default: break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_HSPACE: + if (clen > 0) switch(c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + + default: + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE: + if (clen > 0) switch(c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + ADD_NEW(state_offset + 1, 0); + break; + } + break; + /*-----------------------------------------------------------------*/ /* Match a negated single character. This is only used for one-byte characters, that is, we know that d < 256. The character we are @@ -1205,7 +1863,7 @@ for (;;) case OP_NOT: if (clen > 0) { - int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d; + unsigned int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d; if (c != d && c != otherd) { ADD_NEW(state_offset + dlen + 1, 0); } } break; @@ -1213,13 +1871,15 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_NOTPLUS: case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 @@ -1234,19 +1894,30 @@ for (;;) otherd = fcc[d]; } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { count++; ADD_NEW(state_offset, count); } + { + if (count > 0 && + (codevalue == OP_POSPLUS || codevalue == OP_NOTPOSPLUS)) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } } break; /*-----------------------------------------------------------------*/ case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: case OP_NOTQUERY: case OP_NOTMINQUERY: + case OP_NOTPOSQUERY: ADD_ACTIVE(state_offset + dlen + 1, 0); if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 @@ -1261,19 +1932,28 @@ for (;;) otherd = fcc[d]; } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { ADD_NEW(state_offset + dlen + 1, 0); } + { + if (codevalue == OP_POSQUERY || codevalue == OP_NOTPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + dlen + 1, 0); + } } break; /*-----------------------------------------------------------------*/ case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_NOTSTAR: case OP_NOTMINSTAR: + case OP_NOTPOSSTAR: ADD_ACTIVE(state_offset + dlen + 1, 0); if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 @@ -1288,23 +1968,24 @@ for (;;) otherd = fcc[d]; } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { ADD_NEW(state_offset, 0); } + { + if (codevalue == OP_POSSTAR || codevalue == OP_NOTPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset, 0); + } } break; /*-----------------------------------------------------------------*/ case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: case OP_NOTEXACT: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - if (codevalue != OP_EXACT && codevalue != OP_NOTEXACT) - { ADD_ACTIVE(state_offset + dlen + 3, 0); } count = current_state->count; /* Number already matched */ if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 @@ -1328,6 +2009,46 @@ for (;;) } break; + /*-----------------------------------------------------------------*/ + case OP_UPTO: + case OP_MINUPTO: + case OP_POSUPTO: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTPOSUPTO: + ADD_ACTIVE(state_offset + dlen + 3, 0); + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + unsigned int otherd = NOTACHAR; + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = _pcre_ucp_othercase(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF8 */ + otherd = fcc[d]; + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (codevalue == OP_POSUPTO || codevalue == OP_NOTPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + dlen + 3, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + /* ========================================================================== */ /* These are the class-handling opcodes */ @@ -1448,18 +2169,31 @@ for (;;) /*-----------------------------------------------------------------*/ case OP_COND: + case OP_SCOND: { int local_offsets[1000]; int local_workspace[1000]; int condcode = code[LINK_SIZE+1]; - /* The only supported version of OP_CREF is for the value 0xffff, which - means "test if in a recursion". */ + /* Back reference conditions are not supported */ - if (condcode == OP_CREF) + if (condcode == OP_CREF) return PCRE_ERROR_DFA_UCOND; + + /* The DEFINE condition is always false */ + + if (condcode == OP_DEF) + { + ADD_ACTIVE(state_offset + GET(code, 1) + LINK_SIZE + 1, 0); + } + + /* The only supported version of OP_RREF is for the value RREF_ANY, + which means "test if in any recursion". We can't test for specifically + recursed groups. */ + + else if (condcode == OP_RREF) { int value = GET2(code, LINK_SIZE+2); - if (value != 0xffff) return PCRE_ERROR_DFA_UCOND; + if (value != RREF_ANY) return PCRE_ERROR_DFA_UCOND; if (recursing > 0) { ADD_ACTIVE(state_offset + LINK_SIZE + 4, 0); } else { ADD_ACTIVE(state_offset + GET(code, 1) + LINK_SIZE + 1, 0); } } @@ -1728,7 +2462,7 @@ is not anchored. Arguments: argument_re points to the compiled expression - extra_data points to extra data or is NULL (not currently used) + extra_data points to extra data or is NULL subject points to the subject string length length of subject string (may contain binary zeros) start_offset where to start in the subject string @@ -1744,7 +2478,7 @@ Returns: > 0 => number of match offset pairs placed in offsets < -1 => some kind of unexpected problem */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, const char *subject, int length, int start_offset, int options, int *offsets, int offsetcount, int *workspace, int wscount) @@ -1834,29 +2568,44 @@ md->end_subject = end_subject; md->moptions = options; md->poptions = re->options; -/* Handle different types of newline. The two bits give four cases. If nothing -is set at run time, whatever was used at compile time applies. */ +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ -switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & - PCRE_NEWLINE_CRLF) +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & + PCRE_NEWLINE_BITS) { - default: newline = NEWLINE; break; /* Compile-time default */ + case 0: newline = NEWLINE; break; /* Compile-time default */ case PCRE_NEWLINE_CR: newline = '\r'; break; case PCRE_NEWLINE_LF: newline = '\n'; break; case PCRE_NEWLINE_CR+ PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: return PCRE_ERROR_BADNEWLINE; } -if (newline > 255) +if (newline == -2) { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + md->nltype = NLTYPE_ANY; } else { - md->nllen = 1; - md->nl[0] = newline; + md->nltype = NLTYPE_FIXED; + if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } + else + { + md->nllen = 1; + md->nl[0] = newline; + } } /* Check a UTF-8 string if required. Unfortunately there's no way of passing @@ -1946,7 +2695,7 @@ for (;;) if (firstline) { const uschar *t = current_subject; - while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; + while (t < md->end_subject && !IS_NEWLINE(t)) t++; end_subject = t; } @@ -1965,11 +2714,19 @@ for (;;) else if (startline) { - if (current_subject > md->start_subject + md->nllen + - start_offset) + if (current_subject > md->start_subject + start_offset) { - while (current_subject <= end_subject && - !IS_NEWLINE(current_subject - md->nllen)) + while (current_subject <= end_subject && !WAS_NEWLINE(current_subject)) + current_subject++; + + /* If we have just passed a CR and the newline option is ANY or + ANYCRLF, and we are now at a LF, advance the match position by one more + character. */ + + if (current_subject[-1] == '\r' && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + current_subject < end_subject && + *current_subject == '\n') current_subject++; } } @@ -2052,15 +2809,15 @@ for (;;) rc = internal_dfa_exec( md, /* fixed match data */ md->start_code, /* this subexpression's code */ - current_subject, /* where we currently are */ - start_offset, /* start offset in subject */ - offsets, /* offset vector */ - offsetcount, /* size of same */ - workspace, /* workspace vector */ - wscount, /* size of same */ + current_subject, /* where we currently are */ + start_offset, /* start offset in subject */ + offsets, /* offset vector */ + offsetcount, /* size of same */ + workspace, /* workspace vector */ + wscount, /* size of same */ re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL), /* ims flags */ - 0, /* function recurse level */ - 0); /* regex recurse level */ + 0, /* function recurse level */ + 0); /* regex recurse level */ /* Anything other than "no match" means we are done, always; otherwise, carry on only if not anchored. */ @@ -2070,9 +2827,7 @@ for (;;) /* Advance to the next subject character unless we are at the end of a line and firstline is set. */ - if (firstline && - current_subject <= end_subject - md->nllen && - IS_NEWLINE(current_subject)) break; + if (firstline && IS_NEWLINE(current_subject)) break; current_subject++; if (utf8) { @@ -2080,7 +2835,20 @@ for (;;) current_subject++; } if (current_subject > end_subject) break; - } + + /* If we have just passed a CR and the newline option is CRLF or ANY or + ANYCRLF, and we are now at a LF, advance the match position by one more + character. */ + + if (current_subject[-1] == '\r' && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2) && + current_subject < end_subject && + *current_subject == '\n') + current_subject++; + + } /* "Bumpalong" loop */ return PCRE_ERROR_NOMATCH; } diff --git a/libpcre/pcre_exec.c b/libpcre/pcre_exec.c index 13ad9b140..a749a216e 100644 --- a/libpcre/pcre_exec.c +++ b/libpcre/pcre_exec.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,25 +42,27 @@ POSSIBILITY OF SUCH DAMAGE. pattern matching using an NFA algorithm, trying to mimic Perl as closely as possible. There are also some static supporting functions. */ -#define NLBLOCK md /* The block containing newline information */ +#define NLBLOCK md /* Block containing newline information */ +#define PSSTART start_subject /* Field containing processed string start */ +#define PSEND end_subject /* Field containing processed string end */ + #include "pcre_internal.h" +/* Undefine some potentially clashing cpp symbols */ -/* Structure for building a chain of data that actually lives on the -stack, for holding the values of the subject pointer at the start of each -subpattern, so as to detect when an empty string has been matched by a -subpattern - to break infinite loops. When NO_RECURSE is set, these blocks -are on the heap, not on the stack. */ +#undef min +#undef max -typedef struct eptrblock { - struct eptrblock *epb_prev; - USPTR epb_saved_eptr; -} eptrblock; +/* The chain of eptrblocks for tail recursions uses memory in stack workspace, +obtained at top level, the size of which is defined by EPTR_WORK_SIZE. */ + +#define EPTR_WORK_SIZE (1000) /* Flag bits for the match() function */ -#define match_condassert 0x01 /* Called to check a condition assertion */ -#define match_isgroup 0x02 /* Set if start of bracketed group */ +#define match_condassert 0x01 /* Called to check a condition assertion */ +#define match_cbegroup 0x02 /* Could-be-empty unlimited repeat group */ +#define match_tail_recursed 0x04 /* Tail recursive call */ /* Non-error returns from the match() function. Error returns are externally defined PCRE_ERROR_xxx codes, which are all negative. */ @@ -101,7 +103,7 @@ Returns: nothing static void pchars(const uschar *p, int length, BOOL is_subject, match_data *md) { -int c; +unsigned int c; if (is_subject && length > md->end_subject - p) length = md->end_subject - p; while (length-- > 0) if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c); @@ -186,20 +188,45 @@ calls by keeping local variables that need to be preserved in blocks of memory obtained from malloc() instead instead of on the stack. Macros are used to achieve this so that the actual code doesn't look very different to what it always used to. + +The original heap-recursive code used longjmp(). However, it seems that this +can be very slow on some operating systems. Following a suggestion from Stan +Switzer, the use of longjmp() has been abolished, at the cost of having to +provide a unique number for each call to RMATCH. There is no way of generating +a sequence of numbers at compile time in C. I have given them names, to make +them stand out more clearly. + +Crude tests on x86 Linux show a small speedup of around 5-8%. However, on +FreeBSD, avoiding longjmp() more than halves the time taken to run the standard +tests. Furthermore, not using longjmp() means that local dynamic variables +don't have indeterminate values; this has meant that the frame size can be +reduced because the result can be "passed back" by straight setting of the +variable instead of being passed in the frame. **************************************************************************** ***************************************************************************/ +/* Numbers for RMATCH calls */ + +enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, + RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, + RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, + RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, + RM41, RM42, RM43, RM44, RM45, RM46, RM47 }; + + /* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. */ +versions and production versions. Note that the "rw" argument of RMATCH isn't +actuall used in this definition. */ #ifndef NO_RECURSE #define REGISTER register + #ifdef DEBUG -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ { \ printf("match() called in line %d\n", __LINE__); \ - rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1); \ + rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1); \ printf("to line %d\n", __LINE__); \ } #define RRETURN(ra) \ @@ -208,43 +235,38 @@ versions and production versions. */ return ra; \ } #else -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ - rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1) +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ + rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1) #define RRETURN(ra) return ra #endif #else -/* These versions of the macros manage a private stack on the heap. Note -that the rd argument of RMATCH isn't actually used. It's the md argument of -match(), which never changes. */ +/* These versions of the macros manage a private stack on the heap. Note that +the "rd" argument of RMATCH isn't actually used in this definition. It's the md +argument of match(), which never changes. */ #define REGISTER -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg)\ +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw)\ {\ heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ - if (setjmp(frame->Xwhere) == 0)\ - {\ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xoffset_top = rc;\ - newframe->Xims = re;\ - newframe->Xeptrb = rf;\ - newframe->Xflags = rg;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - }\ - else\ - {\ - DPRINTF(("longjumped back to line %d\n", __LINE__));\ - frame = md->thisframe;\ - rx = frame->Xresult;\ - }\ + frame->Xwhere = rw; \ + newframe->Xeptr = ra;\ + newframe->Xecode = rb;\ + newframe->Xmstart = mstart;\ + newframe->Xoffset_top = rc;\ + newframe->Xims = re;\ + newframe->Xeptrb = rf;\ + newframe->Xflags = rg;\ + newframe->Xrdepth = frame->Xrdepth + 1;\ + newframe->Xprevframe = frame;\ + frame = newframe;\ + DPRINTF(("restarting from line %d\n", __LINE__));\ + goto HEAP_RECURSE;\ + L_##rw:\ + DPRINTF(("jumped back to line %d\n", __LINE__));\ } #define RRETURN(ra)\ @@ -254,9 +276,8 @@ match(), which never changes. */ (pcre_stack_free)(newframe);\ if (frame != NULL)\ {\ - frame->Xresult = ra;\ - md->thisframe = frame;\ - longjmp(frame->Xwhere, 1);\ + rrc = ra;\ + goto HEAP_RETURN;\ }\ return ra;\ } @@ -271,6 +292,7 @@ typedef struct heapframe { const uschar *Xeptr; const uschar *Xecode; + const uschar *Xmstart; int Xoffset_top; long int Xims; eptrblock *Xeptrb; @@ -291,7 +313,6 @@ typedef struct heapframe { BOOL Xcur_is_word; BOOL Xcondition; - BOOL Xminimize; BOOL Xprev_is_word; unsigned long int Xoriginal_ims; @@ -303,11 +324,12 @@ typedef struct heapframe { int Xprop_category; int Xprop_chartype; int Xprop_script; - int *Xprop_test_variable; + int Xoclength; + uschar Xocchars[8]; #endif int Xctype; - int Xfc; + unsigned int Xfc; int Xfi; int Xlength; int Xmax; @@ -321,10 +343,9 @@ typedef struct heapframe { eptrblock Xnewptrb; - /* Place to pass back result, and where to jump back to */ + /* Where to jump back to */ - int Xresult; - jmp_buf Xwhere; + int Xwhere; } heapframe; @@ -340,10 +361,7 @@ typedef struct heapframe { * Match from current position * *************************************************/ -/* On entry ecode points to the first opcode, and eptr to the first character -in the subject string, while eptrb holds the value of eptr at the start of the -last bracketed group - used for breaking infinite loops matching zero-length -strings. This function is called recursively in many circumstances. Whenever it +/* This function is called recursively in many circumstances. Whenever it returns a negative (error) response, the outer incarnation must also return the same response. @@ -353,8 +371,10 @@ performance. Tests using gcc on a SPARC disproved this; in the first case, it made performance worse. Arguments: - eptr pointer in subject - ecode position in code + eptr pointer to current character in subject + ecode pointer to current position in compiled code + mstart pointer to the current match start position (can be modified + by encountering \K) offset_top current top pointer md pointer to "static" info for the match ims current /i, /m, and /s options @@ -362,7 +382,9 @@ Arguments: brackets - for testing for empty matches flags can contain match_condassert - this is an assertion condition - match_isgroup - this is the start of a bracketed group + match_cbegroup - this is the start of an unlimited repeat + group that can match an empty string + match_tail_recursed - this is a tail_recursed group rdepth the recursion depth Returns: MATCH_MATCH if matched ) these values are >= 0 @@ -372,18 +394,20 @@ Returns: MATCH_MATCH if matched ) these values are >= 0 */ static int -match(REGISTER USPTR eptr, REGISTER const uschar *ecode, +match(REGISTER USPTR eptr, REGISTER const uschar *ecode, const uschar *mstart, int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, int flags, unsigned int rdepth) { /* These variables do not need to be preserved over recursion in this function, -so they can be ordinary variables in all cases. Mark them with "register" -because they are used a lot in loops. */ +so they can be ordinary variables in all cases. Mark some of them with +"register" because they are used a lot in loops. */ -register int rrc; /* Returns from recursive calls */ -register int i; /* Used for loops not involving calls to RMATCH() */ -register unsigned int c; /* Character values not kept over RMATCH() calls */ -register BOOL utf8; /* Local copy of UTF-8 flag for speed */ +register int rrc; /* Returns from recursive calls */ +register int i; /* Used for loops not involving calls to RMATCH() */ +register unsigned int c; /* Character values not kept over RMATCH() calls */ +register BOOL utf8; /* Local copy of UTF-8 flag for speed */ + +BOOL minimize, possessive; /* Quantifier options */ /* When recursion is not being used, all "local" variables that have to be preserved over calls to RMATCH() are part of a "frame" which is obtained from @@ -398,6 +422,7 @@ frame->Xprevframe = NULL; /* Marks the top level */ frame->Xeptr = eptr; frame->Xecode = ecode; +frame->Xmstart = mstart; frame->Xoffset_top = offset_top; frame->Xims = ims; frame->Xeptrb = eptrb; @@ -412,6 +437,7 @@ HEAP_RECURSE: #define eptr frame->Xeptr #define ecode frame->Xecode +#define mstart frame->Xmstart #define offset_top frame->Xoffset_top #define ims frame->Xims #define eptrb frame->Xeptrb @@ -434,7 +460,6 @@ HEAP_RECURSE: #define cur_is_word frame->Xcur_is_word #define condition frame->Xcondition -#define minimize frame->Xminimize #define prev_is_word frame->Xprev_is_word #define original_ims frame->Xoriginal_ims @@ -446,7 +471,8 @@ HEAP_RECURSE: #define prop_category frame->Xprop_category #define prop_chartype frame->Xprop_chartype #define prop_script frame->Xprop_script -#define prop_test_variable frame->Xprop_test_variable +#define oclength frame->Xoclength +#define occhars frame->Xocchars #endif #define ctype frame->Xctype @@ -470,17 +496,17 @@ HEAP_RECURSE: get preserved during recursion in the normal way. In this environment, fi and i, and fc and c, can be the same variables. */ -#else +#else /* NO_RECURSE not defined */ #define fi i #define fc c #ifdef SUPPORT_UTF8 /* Many of these variables are used only */ const uschar *charptr; /* in small blocks of the code. My normal */ -#endif /* style of coding would have declared */ -const uschar *callpat; /* them within each of those blocks. */ -const uschar *data; /* However, in order to accommodate the */ -const uschar *next; /* version of this code that uses an */ +#endif /* style of coding would have declared */ +const uschar *callpat; /* them within each of those blocks. */ +const uschar *data; /* However, in order to accommodate the */ +const uschar *next; /* version of this code that uses an */ USPTR pp; /* external "stack" implemented on the */ const uschar *prev; /* heap, it is easier to declare them all */ USPTR saved_eptr; /* here, so the declarations can be cut */ @@ -489,7 +515,6 @@ recursion_info new_recursive; /* within blocks below are for variables */ /* that do not have to be preserved over */ BOOL cur_is_word; /* a recursive call to RMATCH(). */ BOOL condition; -BOOL minimize; BOOL prev_is_word; unsigned long int original_ims; @@ -501,7 +526,8 @@ int prop_fail_result; int prop_category; int prop_chartype; int prop_script; -int *prop_test_variable; +int oclength; +uschar occhars[8]; #endif int ctype; @@ -516,7 +542,7 @@ int save_offset1, save_offset2, save_offset3; int stacksave[REC_STACK_SAVE_MAX]; eptrblock newptrb; -#endif +#endif /* NO_RECURSE */ /* These statements are here to stop the compiler complaining about unitialized variables. */ @@ -524,9 +550,9 @@ variables. */ #ifdef SUPPORT_UCP prop_value = 0; prop_fail_result = 0; -prop_test_variable = NULL; #endif + /* This label is used for tail recursion, which is used in a few cases even when NO_RECURSE is not defined, in order to reduce the amount of stack that is used. Thanks to Ian Taylor for noticing this possibility and sending the @@ -542,6 +568,12 @@ defined). However, RMATCH isn't like a function call because it's quite a complicated macro. It has to be used in one particular way. This shouldn't, however, impact performance when true recursion is being used. */ +#ifdef SUPPORT_UTF8 +utf8 = md->utf8; /* Local copy of the flag */ +#else +utf8 = FALSE; +#endif + /* First check that we haven't called match() too many times, or that we haven't exceeded the recursive call limit. */ @@ -550,66 +582,67 @@ if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); original_ims = ims; /* Save for resetting on ')' */ -#ifdef SUPPORT_UTF8 -utf8 = md->utf8; /* Local copy of the flag */ -#else -utf8 = FALSE; -#endif +/* At the start of a group with an unlimited repeat that may match an empty +string, the match_cbegroup flag is set. When this is the case, add the current +subject pointer to the chain of such remembered pointers, to be checked when we +hit the closing ket, in order to break infinite loops that match no characters. +When match() is called in other circumstances, don't add to the chain. If this +is a tail recursion, use a block from the workspace, as the one on the stack is +already used. */ -/* At the start of a bracketed group, add the current subject pointer to the -stack of such pointers, to be re-instated at the end of the group when we hit -the closing ket. When match() is called in other circumstances, we don't add to -this stack. */ - -if ((flags & match_isgroup) != 0) +if ((flags & match_cbegroup) != 0) { - newptrb.epb_prev = eptrb; - newptrb.epb_saved_eptr = eptr; - eptrb = &newptrb; + eptrblock *p; + if ((flags & match_tail_recursed) != 0) + { + if (md->eptrn >= EPTR_WORK_SIZE) RRETURN(PCRE_ERROR_NULLWSLIMIT); + p = md->eptrchain + md->eptrn++; + } + else p = &newptrb; + p->epb_saved_eptr = eptr; + p->epb_prev = eptrb; + eptrb = p; } -/* Now start processing the operations. */ +/* Now start processing the opcodes. */ for (;;) { + minimize = possessive = FALSE; op = *ecode; - minimize = FALSE; /* For partial matching, remember if we ever hit the end of the subject after matching at least one subject character. */ if (md->partial && eptr >= md->end_subject && - eptr > md->start_match) + eptr > mstart) md->hitend = TRUE; - /* Opening capturing bracket. If there is space in the offset vector, save - the current subject position in the working slot at the top of the vector. We - mustn't change the current values of the data slot, because they may be set - from a previous iteration of this group, and be referred to by a reference - inside the group. - - If the bracket fails to match, we need to restore this value and also the - values of the final offsets, in case they were set by a previous iteration of - the same bracket. - - If there isn't enough space in the offset vector, treat this as if it were a - non-capturing bracket. Don't worry about setting the flag for the error case - here; that is handled in the code for KET. */ - - if (op > OP_BRA) + switch(op) { - number = op - OP_BRA; + /* Handle a capturing bracket. If there is space in the offset vector, save + the current subject position in the working slot at the top of the vector. + We mustn't change the current values of the data slot, because they may be + set from a previous iteration of this group, and be referred to by a + reference inside the group. - /* For extended extraction brackets (large number), we have to fish out the - number from a dummy opcode at the start. */ + If the bracket fails to match, we need to restore this value and also the + values of the final offsets, in case they were set by a previous iteration + of the same bracket. - if (number > EXTRACT_BASIC_MAX) - number = GET2(ecode, 2+LINK_SIZE); + If there isn't enough space in the offset vector, treat this as if it were + a non-capturing bracket. Don't worry about setting the flag for the error + case here; that is handled in the code for KET. */ + + case OP_CBRA: + case OP_SCBRA: + number = GET2(ecode, 1+LINK_SIZE); offset = number << 1; #ifdef DEBUG - printf("start bracket %d subject=", number); + printf("start bracket %d\n", number); + printf("subject="); pchars(eptr, 16, TRUE, md); printf("\n"); #endif @@ -624,10 +657,11 @@ for (;;) DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); md->offset_vector[md->offset_end - number] = eptr - md->start_subject; + flags = (op == OP_SCBRA)? match_cbegroup : 0; do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM1); if (rrc != MATCH_NOMATCH) RRETURN(rrc); md->capture_last = save_capture_last; ecode += GET(ecode, 1); @@ -643,39 +677,35 @@ for (;;) RRETURN(MATCH_NOMATCH); } - /* Insufficient room for saving captured contents */ + /* Insufficient room for saving captured contents. Treat as a non-capturing + bracket. */ - else op = OP_BRA; - } + DPRINTF(("insufficient capture room: treat as non-capturing\n")); - /* Other types of node can be handled by a switch */ - - switch(op) - { - case OP_BRA: /* Non-capturing bracket: optimized */ - DPRINTF(("start bracket 0\n")); - - /* Loop for all the alternatives */ + /* Non-capturing bracket. Loop for all the alternatives. When we get to the + final alternative within the brackets, we would return the result of a + recursive call to match() whatever happened. We can reduce stack usage by + turning this into a tail recursion. */ + case OP_BRA: + case OP_SBRA: + DPRINTF(("start non-capturing bracket\n")); + flags = (op >= OP_SBRA)? match_cbegroup : 0; for (;;) { - /* When we get to the final alternative within the brackets, we would - return the result of a recursive call to match() whatever happened. We - can reduce stack usage by turning this into a tail recursion. */ - if (ecode[GET(ecode, 1)] != OP_ALT) - { - ecode += 1 + LINK_SIZE; - flags = match_isgroup; - DPRINTF(("bracket 0 tail recursion\n")); - goto TAIL_RECURSE; - } + { + ecode += _pcre_OP_lengths[*ecode]; + flags |= match_tail_recursed; + DPRINTF(("bracket 0 tail recursion\n")); + goto TAIL_RECURSE; + } /* For non-final alternatives, continue the loop for a NOMATCH result; otherwise return. */ - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, + eptrb, flags, RM2); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode, 1); } @@ -688,54 +718,72 @@ for (;;) obeyed, we can use tail recursion to avoid using another stack frame. */ case OP_COND: - if (ecode[LINK_SIZE+1] == OP_CREF) /* Condition extract or recurse test */ + case OP_SCOND: + if (ecode[LINK_SIZE+1] == OP_RREF) /* Recursion test */ + { + offset = GET2(ecode, LINK_SIZE + 2); /* Recursion group number*/ + condition = md->recursive != NULL && + (offset == RREF_ANY || offset == md->recursive->group_num); + ecode += condition? 3 : GET(ecode, 1); + } + + else if (ecode[LINK_SIZE+1] == OP_CREF) /* Group used test */ { offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */ - condition = (offset == CREF_RECURSE * 2)? - (md->recursive != NULL) : - (offset < offset_top && md->offset_vector[offset] >= 0); - ecode += condition? (LINK_SIZE + 4) : (LINK_SIZE + 1 + GET(ecode, 1)); - flags = match_isgroup; - goto TAIL_RECURSE; + condition = offset < offset_top && md->offset_vector[offset] >= 0; + ecode += condition? 3 : GET(ecode, 1); + } + + else if (ecode[LINK_SIZE+1] == OP_DEF) /* DEFINE - always false */ + { + condition = FALSE; + ecode += GET(ecode, 1); } /* The condition is an assertion. Call match() to evaluate it - setting - the final argument TRUE causes it to stop at the end of an assertion. */ + the final argument match_condassert causes it to stop at the end of an + assertion. */ else { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_condassert | match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, + match_condassert, RM3); if (rrc == MATCH_MATCH) { - ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE+2); + condition = TRUE; + ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2); while (*ecode == OP_ALT) ecode += GET(ecode, 1); } else if (rrc != MATCH_NOMATCH) { RRETURN(rrc); /* Need braces because of following else */ } - else ecode += GET(ecode, 1); + else + { + condition = FALSE; + ecode += GET(ecode, 1); + } + } - /* We are now at the branch that is to be obeyed. As there is only one, - we can use tail recursion to avoid using another stack frame. */ + /* We are now at the branch that is to be obeyed. As there is only one, + we can use tail recursion to avoid using another stack frame. If the second + alternative doesn't exist, we can just plough on. */ + if (condition || *ecode == OP_ALT) + { ecode += 1 + LINK_SIZE; - flags = match_isgroup; + flags = match_tail_recursed | ((op == OP_SCOND)? match_cbegroup : 0); goto TAIL_RECURSE; } - /* Control never reaches here */ - - /* Skip over conditional reference or large extraction number data if - encountered. */ - - case OP_CREF: - case OP_BRANUMBER: - ecode += 3; + else + { + ecode += 1 + LINK_SIZE; + } break; - /* End of the pattern. If we are in a recursion, we should restore the - offsets appropriately and continue from after the call. */ + + /* End of the pattern. If we are in a top-level recursion, we should + restore the offsets appropriately and continue from after the call. */ case OP_END: if (md->recursive != NULL && md->recursive->group_num == 0) @@ -745,7 +793,7 @@ for (;;) md->recursive = rec->prevrec; memmove(md->offset_vector, rec->offset_save, rec->saved_max * sizeof(int)); - md->start_match = rec->save_start; + mstart = rec->save_start; ims = original_ims; ecode = rec->after_call; break; @@ -754,9 +802,10 @@ for (;;) /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty string - backtracking will then try other alternatives, if any. */ - if (md->notempty && eptr == md->start_match) RRETURN(MATCH_NOMATCH); - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ + if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); + md->end_match_ptr = eptr; /* Record where we ended */ + md->end_offset_top = offset_top; /* and how many extracts were taken */ + md->start_match_ptr = mstart; /* and the start (\K can modify) */ RRETURN(MATCH_MATCH); /* Change option settings */ @@ -777,8 +826,8 @@ for (;;) case OP_ASSERTBACK: do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, + RM4); if (rrc == MATCH_MATCH) break; if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode, 1); @@ -804,8 +853,8 @@ for (;;) case OP_ASSERTBACK_NOT: do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, + RM5); if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode,1); @@ -826,8 +875,8 @@ for (;;) #ifdef SUPPORT_UTF8 if (utf8) { - c = GET(ecode,1); - for (i = 0; i < c; i++) + i = GET(ecode, 1); + while (i-- > 0) { eptr--; if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); @@ -840,7 +889,7 @@ for (;;) /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ { - eptr -= GET(ecode,1); + eptr -= GET(ecode, 1); if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); } @@ -862,7 +911,7 @@ for (;;) cb.offset_vector = md->offset_vector; cb.subject = (PCRE_SPTR)md->start_subject; cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = md->start_match - md->start_subject; + cb.start_match = mstart - md->start_subject; cb.current_position = eptr - md->start_subject; cb.pattern_position = GET(ecode, 2); cb.next_item_length = GET(ecode, 2 + LINK_SIZE); @@ -897,13 +946,8 @@ for (;;) case OP_RECURSE: { callpat = md->start_code + GET(ecode, 1); - new_recursive.group_num = *callpat - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out - the number from a dummy opcode at the start. */ - - if (new_recursive.group_num > EXTRACT_BASIC_MAX) - new_recursive.group_num = GET2(callpat, 2+LINK_SIZE); + new_recursive.group_num = (callpat == md->start_code)? 0 : + GET2(callpat, 1 + LINK_SIZE); /* Add to "recursing stack" */ @@ -929,17 +973,18 @@ for (;;) memcpy(new_recursive.offset_save, md->offset_vector, new_recursive.saved_max * sizeof(int)); - new_recursive.save_start = md->start_match; - md->start_match = eptr; + new_recursive.save_start = mstart; + mstart = eptr; /* OK, now we can do the recursion. For each top-level alternative we restore the offset and recursion data. */ DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); + flags = (*callpat >= OP_SBRA)? match_cbegroup : 0; do { - RMATCH(rrc, eptr, callpat + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, match_isgroup); + RMATCH(eptr, callpat + _pcre_OP_lengths[*callpat], offset_top, + md, ims, eptrb, flags, RM6); if (rrc == MATCH_MATCH) { DPRINTF(("Recursion matched\n")); @@ -977,69 +1022,70 @@ for (;;) the end of a normal bracket, leaving the subject pointer. */ case OP_ONCE: - prev = ecode; - saved_eptr = eptr; + prev = ecode; + saved_eptr = eptr; - do - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, match_isgroup); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); + do + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, + eptrb, 0, RM7); + if (rrc == MATCH_MATCH) break; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode,1); + } + while (*ecode == OP_ALT); - /* If hit the end of the group (which could be repeated), fail */ + /* If hit the end of the group (which could be repeated), fail */ - if (*ecode != OP_ONCE && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); + if (*ecode != OP_ONCE && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); - /* Continue as from after the assertion, updating the offsets high water - mark, since extracts may have been taken. */ + /* Continue as from after the assertion, updating the offsets high water + mark, since extracts may have been taken. */ - do ecode += GET(ecode,1); while (*ecode == OP_ALT); + do ecode += GET(ecode, 1); while (*ecode == OP_ALT); - offset_top = md->end_offset_top; - eptr = md->end_match_ptr; + offset_top = md->end_offset_top; + eptr = md->end_match_ptr; - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ + /* For a non-repeating ket, just continue at this level. This also + happens for a repeating ket if no characters were matched in the group. + This is the forcible breaking of infinite loops as implemented in Perl + 5.005. If there is an options reset, it will get obeyed in the normal + course of events. */ - if (*ecode == OP_KET || eptr == saved_eptr) - { - ecode += 1+LINK_SIZE; - break; - } + if (*ecode == OP_KET || eptr == saved_eptr) + { + ecode += 1+LINK_SIZE; + break; + } - /* The repeating kets try the rest of the pattern or restart from the + /* The repeating kets try the rest of the pattern or restart from the preceding bracket, in the appropriate order. The second "call" of match() uses tail recursion, to avoid using another stack frame. We need to reset any options that changed within the bracket before re-running it, so check the next opcode. */ - if (ecode[1+LINK_SIZE] == OP_OPT) - { - ims = (ims & ~PCRE_IMS) | ecode[4]; - DPRINTF(("ims set to %02lx at group repeat\n", ims)); - } + if (ecode[1+LINK_SIZE] == OP_OPT) + { + ims = (ims & ~PCRE_IMS) | ecode[4]; + DPRINTF(("ims set to %02lx at group repeat\n", ims)); + } - if (*ecode == OP_KETRMIN) - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (*ecode == OP_KETRMIN) + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, + RM8); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode = prev; - flags = match_isgroup; + flags = match_tail_recursed; goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + else /* OP_KETRMAX */ + { + RMATCH(eptr, prev, offset_top, md, ims, eptrb, match_cbegroup, RM9); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += 1 + LINK_SIZE; - flags = 0; + flags = match_tail_recursed; goto TAIL_RECURSE; } /* Control never gets here */ @@ -1060,137 +1106,135 @@ for (;;) case OP_BRAZERO: { next = ecode+1; - RMATCH(rrc, eptr, next, offset_top, md, ims, eptrb, match_isgroup); + RMATCH(eptr, next, offset_top, md, ims, eptrb, 0, RM10); if (rrc != MATCH_NOMATCH) RRETURN(rrc); do next += GET(next,1); while (*next == OP_ALT); - ecode = next + 1+LINK_SIZE; + ecode = next + 1 + LINK_SIZE; } break; case OP_BRAMINZERO: { next = ecode+1; - do next += GET(next,1); while (*next == OP_ALT); - RMATCH(rrc, eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); + do next += GET(next, 1); while (*next == OP_ALT); + RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, RM11); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode++; } break; - /* End of a group, repeated or non-repeating. If we are at the end of - an assertion "group", stop matching and return MATCH_MATCH, but record the - current high water mark for use by positive assertions. Do this also - for the "once" (not-backup up) groups. */ + /* End of a group, repeated or non-repeating. */ case OP_KET: case OP_KETRMIN: case OP_KETRMAX: - prev = ecode - GET(ecode, 1); - saved_eptr = eptrb->epb_saved_eptr; + prev = ecode - GET(ecode, 1); - /* Back up the stack of bracket start pointers. */ + /* If this was a group that remembered the subject start, in order to break + infinite repeats of empty string matches, retrieve the subject start from + the chain. Otherwise, set it NULL. */ - eptrb = eptrb->epb_prev; + if (*prev >= OP_SBRA) + { + saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */ + eptrb = eptrb->epb_prev; /* Backup to previous group */ + } + else saved_eptr = NULL; - if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || - *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || - *prev == OP_ONCE) - { - md->end_match_ptr = eptr; /* For ONCE */ - md->end_offset_top = offset_top; - RRETURN(MATCH_MATCH); - } + /* If we are at the end of an assertion group, stop matching and return + MATCH_MATCH, but record the current high water mark for use by positive + assertions. Do this also for the "once" (atomic) groups. */ - /* In all other cases except a conditional group we have to check the - group number back at the start and if necessary complete handling an - extraction by setting the offsets and bumping the high water mark. */ + if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || + *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || + *prev == OP_ONCE) + { + md->end_match_ptr = eptr; /* For ONCE */ + md->end_offset_top = offset_top; + RRETURN(MATCH_MATCH); + } - if (*prev != OP_COND) - { - number = *prev - OP_BRA; + /* For capturing groups we have to check the group number back at the start + and if necessary complete handling an extraction by setting the offsets and + bumping the high water mark. Note that whole-pattern recursion is coded as + a recurse into group 0, so it won't be picked up here. Instead, we catch it + when the OP_END is reached. Other recursion is handled here. */ - /* For extended extraction brackets (large number), we have to fish out - the number from a dummy opcode at the start. */ - - if (number > EXTRACT_BASIC_MAX) number = GET2(prev, 2+LINK_SIZE); - offset = number << 1; + if (*prev == OP_CBRA || *prev == OP_SCBRA) + { + number = GET2(prev, 1+LINK_SIZE); + offset = number << 1; #ifdef DEBUG - printf("end bracket %d", number); - printf("\n"); + printf("end bracket %d", number); + printf("\n"); #endif - /* Test for a numbered group. This includes groups called as a result - of recursion. Note that whole-pattern recursion is coded as a recurse - into group 0, so it won't be picked up here. Instead, we catch it when - the OP_END is reached. */ - - if (number > 0) - { - md->capture_last = number; - if (offset >= md->offset_max) md->offset_overflow = TRUE; else - { - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = eptr - md->start_subject; - if (offset_top <= offset) offset_top = offset + 2; - } - - /* Handle a recursively called group. Restore the offsets - appropriately and continue from after the call. */ - - if (md->recursive != NULL && md->recursive->group_num == number) - { - recursion_info *rec = md->recursive; - DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); - md->recursive = rec->prevrec; - md->start_match = rec->save_start; - memcpy(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - ecode = rec->after_call; - ims = original_ims; - break; - } - } + md->capture_last = number; + if (offset >= md->offset_max) md->offset_overflow = TRUE; else + { + md->offset_vector[offset] = + md->offset_vector[md->offset_end - number]; + md->offset_vector[offset+1] = eptr - md->start_subject; + if (offset_top <= offset) offset_top = offset + 2; } - /* Reset the value of the ims flags, in case they got changed during - the group. */ + /* Handle a recursively called group. Restore the offsets + appropriately and continue from after the call. */ - ims = original_ims; - DPRINTF(("ims reset to %02lx\n", ims)); - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == saved_eptr) + if (md->recursive != NULL && md->recursive->group_num == number) { - ecode += 1 + LINK_SIZE; + recursion_info *rec = md->recursive; + DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); + md->recursive = rec->prevrec; + mstart = rec->save_start; + memcpy(md->offset_vector, rec->offset_save, + rec->saved_max * sizeof(int)); + ecode = rec->after_call; + ims = original_ims; break; } + } - /* The repeating kets try the rest of the pattern or restart from the + /* For both capturing and non-capturing groups, reset the value of the ims + flags, in case they got changed during the group. */ + + ims = original_ims; + DPRINTF(("ims reset to %02lx\n", ims)); + + /* For a non-repeating ket, just continue at this level. This also + happens for a repeating ket if no characters were matched in the group. + This is the forcible breaking of infinite loops as implemented in Perl + 5.005. If there is an options reset, it will get obeyed in the normal + course of events. */ + + if (*ecode == OP_KET || eptr == saved_eptr) + { + ecode += 1 + LINK_SIZE; + break; + } + + /* The repeating kets try the rest of the pattern or restart from the preceding bracket, in the appropriate order. In the second case, we can use tail recursion to avoid using another stack frame. */ - if (*ecode == OP_KETRMIN) - { - RMATCH(rrc, eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + flags = (*prev >= OP_SBRA)? match_cbegroup : 0; + + if (*ecode == OP_KETRMIN) + { + RMATCH(eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, + RM12); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode = prev; - flags = match_isgroup; + flags |= match_tail_recursed; goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + else /* OP_KETRMAX */ + { + RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM13); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += 1 + LINK_SIZE; - flags = 0; + flags = match_tail_recursed; goto TAIL_RECURSE; } /* Control never gets here */ @@ -1202,9 +1246,7 @@ for (;;) if ((ims & PCRE_MULTILINE) != 0) { if (eptr != md->start_subject && - (eptr == md->end_subject || - eptr < md->start_subject + md->nllen || - !IS_NEWLINE(eptr - md->nllen))) + (eptr == md->end_subject || !WAS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); ecode++; break; @@ -1225,6 +1267,13 @@ for (;;) ecode++; break; + /* Reset the start of match point */ + + case OP_SET_SOM: + mstart = eptr; + ecode++; + break; + /* Assert before internal newline if multiline, or before a terminating newline unless endonly is set, else end of subject unless noteol is set. */ @@ -1244,7 +1293,7 @@ for (;;) if (!md->endonly) { if (eptr != md->end_subject && - (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) + (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) RRETURN(MATCH_NOMATCH); ecode++; break; @@ -1263,7 +1312,7 @@ for (;;) case OP_EODN: if (eptr != md->end_subject && - (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) + (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) RRETURN(MATCH_NOMATCH); ecode++; break; @@ -1319,8 +1368,7 @@ for (;;) case OP_ANY: if ((ims & PCRE_DOTALL) == 0) { - if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); } if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); if (utf8) @@ -1414,6 +1462,122 @@ for (;;) ecode++; break; + case OP_ANYNL: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + break; + } + ecode++; + break; + + case OP_NOT_HSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_HSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + ecode++; + break; + + case OP_NOT_VSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_VSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + ecode++; + break; + #ifdef SUPPORT_UCP /* Check the next character by Unicode property. We will get here only if the support is in the binary; otherwise a compile-time error occurs. */ @@ -1456,7 +1620,6 @@ for (;;) default: RRETURN(PCRE_ERROR_INTERNAL); - break; } ecode += 3; @@ -1570,7 +1733,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM14); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || !match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); @@ -1591,7 +1754,7 @@ for (;;) } while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM15); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr -= length; } @@ -1696,7 +1859,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM16); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -1716,7 +1879,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM17); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); c = *eptr++; @@ -1753,7 +1916,7 @@ for (;;) } for (;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM18); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -1772,7 +1935,7 @@ for (;;) } while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM19); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -1843,7 +2006,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM20); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -1867,7 +2030,7 @@ for (;;) } for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr) @@ -1926,7 +2089,7 @@ for (;;) else { - int dc; + unsigned int dc; GETCHARINC(dc, eptr); ecode += length; @@ -1953,13 +2116,17 @@ for (;;) } break; - /* Match a single character repeatedly; different opcodes share code. */ + /* Match a single character repeatedly. */ case OP_EXACT: min = max = GET2(ecode, 1); ecode += 3; goto REPEATCHAR; + case OP_POSUPTO: + possessive = TRUE; + /* Fall through */ + case OP_UPTO: case OP_MINUPTO: min = 0; @@ -1968,6 +2135,27 @@ for (;;) ecode += 3; goto REPEATCHAR; + case OP_POSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATCHAR; + + case OP_POSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATCHAR; + + case OP_POSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATCHAR; + case OP_STAR: case OP_MINSTAR: case OP_PLUS: @@ -1999,20 +2187,18 @@ for (;;) if (length > 1) { - int oclength = 0; - uschar occhars[8]; - #ifdef SUPPORT_UCP - int othercase; + unsigned int othercase; if ((ims & PCRE_CASELESS) != 0 && - (othercase = _pcre_ucp_othercase(fc)) >= 0 && - othercase >= 0) + (othercase = _pcre_ucp_othercase(fc)) != NOTACHAR) oclength = _pcre_ord2utf8(othercase, occhars); + else oclength = 0; #endif /* SUPPORT_UCP */ for (i = 1; i <= min; i++) { if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP /* Need braces because of following else */ else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } else @@ -2020,6 +2206,9 @@ for (;;) if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); eptr += oclength; } +#else /* without SUPPORT_UCP */ + else { RRETURN(MATCH_NOMATCH); } +#endif /* SUPPORT_UCP */ } if (min == max) continue; @@ -2028,10 +2217,11 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM22); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP /* Need braces because of following else */ else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } else @@ -2039,30 +2229,45 @@ for (;;) if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); eptr += oclength; } +#else /* without SUPPORT_UCP */ + else { RRETURN (MATCH_NOMATCH); } +#endif /* SUPPORT_UCP */ } /* Control never gets here */ } - else + + else /* Maximize */ { pp = eptr; for (i = min; i < max; i++) { if (eptr > md->end_subject - length) break; if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP else if (oclength == 0) break; else { if (memcmp(eptr, occhars, oclength) != 0) break; eptr += oclength; } +#else /* without SUPPORT_UCP */ + else break; +#endif /* SUPPORT_UCP */ } - while (eptr >= pp) + + if (possessive) continue; + for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM23); if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr == pp) RRETURN(MATCH_NOMATCH); +#ifdef SUPPORT_UCP + eptr--; + BACKCHAR(eptr); +#else /* without SUPPORT_UCP */ eptr -= length; +#endif /* SUPPORT_UCP */ } - RRETURN(MATCH_NOMATCH); } /* Control never gets here */ } @@ -2102,7 +2307,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM24); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc != md->lcc[*eptr++]) @@ -2110,7 +2315,7 @@ for (;;) } /* Control never gets here */ } - else + else /* Maximize */ { pp = eptr; for (i = min; i < max; i++) @@ -2118,9 +2323,10 @@ for (;;) if (eptr >= md->end_subject || fc != md->lcc[*eptr]) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM25); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -2139,14 +2345,14 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM26); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc != *eptr++) RRETURN(MATCH_NOMATCH); } /* Control never gets here */ } - else + else /* Maximize */ { pp = eptr; for (i = min; i < max; i++) @@ -2154,9 +2360,10 @@ for (;;) if (eptr >= md->end_subject || fc != *eptr) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM27); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -2206,6 +2413,34 @@ for (;;) ecode += 3; goto REPEATNOTCHAR; + case OP_NOTPOSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSUPTO: + possessive = TRUE; + min = 0; + max = GET2(ecode, 1); + ecode += 3; + goto REPEATNOTCHAR; + case OP_NOTSTAR: case OP_NOTMINSTAR: case OP_NOTPLUS: @@ -2245,7 +2480,7 @@ for (;;) /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = 1; i <= min; i++) { GETCHARINC(d, eptr); @@ -2270,10 +2505,10 @@ for (;;) /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28); if (rrc != MATCH_NOMATCH) RRETURN(rrc); GETCHARINC(d, eptr); if (d < 256) d = md->lcc[d]; @@ -2287,7 +2522,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM29); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); @@ -2306,7 +2541,7 @@ for (;;) /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = min; i < max; i++) { int len = 1; @@ -2316,9 +2551,10 @@ for (;;) if (fc == d) break; eptr += len; } - for(;;) + if (possessive) continue; + for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM30); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -2333,9 +2569,10 @@ for (;;) if (eptr >= md->end_subject || fc == md->lcc[*eptr]) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM31); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -2354,7 +2591,7 @@ for (;;) /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = 1; i <= min; i++) { GETCHARINC(d, eptr); @@ -2377,10 +2614,10 @@ for (;;) /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32); if (rrc != MATCH_NOMATCH) RRETURN(rrc); GETCHARINC(d, eptr); if (fi >= max || eptr >= md->end_subject || fc == d) @@ -2393,7 +2630,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM33); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc == *eptr++) RRETURN(MATCH_NOMATCH); @@ -2412,7 +2649,7 @@ for (;;) /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = min; i < max; i++) { int len = 1; @@ -2421,9 +2658,10 @@ for (;;) if (fc == d) break; eptr += len; } + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM34); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -2438,9 +2676,10 @@ for (;;) if (eptr >= md->end_subject || fc == *eptr) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM35); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -2469,6 +2708,34 @@ for (;;) ecode += 3; goto REPEATTYPE; + case OP_TYPEPOSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSUPTO: + possessive = TRUE; + min = 0; + max = GET2(ecode, 1); + ecode += 3; + goto REPEATTYPE; + case OP_TYPESTAR: case OP_TYPEMINSTAR: case OP_TYPEPLUS: @@ -2516,10 +2783,10 @@ for (;;) { case PT_ANY: if (prop_fail_result) RRETURN(MATCH_NOMATCH); - for (i = 1; i <= min; i++) - { + for (i = 1; i <= min; i++) + { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); } break; @@ -2527,7 +2794,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_chartype == ucp_Lu || prop_chartype == ucp_Ll || @@ -2540,18 +2807,18 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } + RRETURN(MATCH_NOMATCH); + } break; case PT_PC: for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_chartype == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); @@ -2562,7 +2829,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_script == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); @@ -2571,7 +2838,6 @@ for (;;) default: RRETURN(PCRE_ERROR_INTERNAL); - break; } } @@ -2611,9 +2877,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && - IS_NEWLINE(eptr))) + ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); eptr++; while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; @@ -2624,6 +2888,132 @@ for (;;) eptr += min; break; + case OP_ANYNL: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + break; + } + } + break; + + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + } + break; + case OP_NOT_DIGIT: for (i = 1; i <= min; i++) { @@ -2692,7 +3082,8 @@ for (;;) #endif /* SUPPORT_UTF8 */ /* Code for the non-UTF-8 case for minimum matching of operators other - than OP_PROP and OP_NOTPROP. */ + than OP_PROP and OP_NOTPROP. We can assume that there are the minimum + number of bytes present, as this was tested above. */ switch(ctype) { @@ -2701,8 +3092,7 @@ for (;;) { for (i = 1; i <= min; i++) { - if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); eptr++; } } @@ -2713,6 +3103,92 @@ for (;;) eptr += min; break; + /* Because of the CRLF case, we can't assume the minimum number of + bytes are present in this case. */ + + case OP_ANYNL: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + break; + } + } + break; + + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + break; + } + } + break; + case OP_NOT_DIGIT: for (i = 1; i <= min; i++) if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); @@ -2768,18 +3244,18 @@ for (;;) case PT_ANY: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM36); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); if (prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_LAMP: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM37); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2789,12 +3265,12 @@ for (;;) prop_chartype == ucp_Lt) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_GC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM38); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2802,12 +3278,12 @@ for (;;) if ((prop_category == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_PC: for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + { + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM39); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2815,24 +3291,23 @@ for (;;) if ((prop_chartype == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_SC: - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM40); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ default: RRETURN(PCRE_ERROR_INTERNAL); - break; } } @@ -2843,7 +3318,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM41); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINCTEST(c, eptr); @@ -2872,11 +3347,11 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + IS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2888,6 +3363,107 @@ for (;;) case OP_ANYBYTE: break; + case OP_ANYNL: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + break; + } + break; + + case OP_NOT_HSPACE: + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + break; + case OP_NOT_DIGIT: if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); @@ -2929,11 +3505,10 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); c = *eptr++; @@ -2945,6 +3520,69 @@ for (;;) case OP_ANYBYTE: break; + case OP_ANYNL: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + case 0x000b: + case 0x000c: + case 0x0085: + break; + } + break; + + case OP_NOT_HSPACE: + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + break; + } + break; + case OP_NOT_DIGIT: if ((md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); break; @@ -2977,7 +3615,7 @@ for (;;) /* Control never gets here */ } - /* If maximizing it is worth using inline code for speed, doing the type + /* If maximizing, it is worth using inline code for speed, doing the type test once at the start (i.e. keep it out of the loop). Again, keep the UTF-8 and UCP stuff separate. */ @@ -3030,16 +3668,16 @@ for (;;) break; case PT_PC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_chartype == prop_value) == prop_fail_result) - break; - eptr+= len; - } + break; + eptr+= len; + } break; case PT_SC: @@ -3058,9 +3696,10 @@ for (;;) /* eptr is now past the end of the maximum run */ + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -3093,9 +3732,10 @@ for (;;) /* eptr is now past the end of the maximum run */ + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM45); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ for (;;) /* Move back over one extended */ @@ -3135,9 +3775,7 @@ for (;;) { for (i = min; i < max; i++) { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; eptr++; while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; } @@ -3161,9 +3799,7 @@ for (;;) { for (i = min; i < max; i++) { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; eptr++; } break; @@ -3171,7 +3807,8 @@ for (;;) else { c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; + if (c > (unsigned int)(md->end_subject - eptr)) + c = md->end_subject - eptr; eptr += c; } } @@ -3181,10 +3818,96 @@ for (;;) case OP_ANYBYTE: c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; + if (c > (unsigned int)(md->end_subject - eptr)) + c = md->end_subject - eptr; eptr += c; break; + case OP_ANYNL: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c == 0x000d) + { + if (++eptr >= md->end_subject) break; + if (*eptr == 0x000a) eptr++; + } + else + { + if (c != 0x000a && c != 0x000b && c != 0x000c && + c != 0x0085 && c != 0x2028 && c != 0x2029) + break; + eptr += len; + } + } + break; + + case OP_NOT_HSPACE: + case OP_HSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + switch(c) + { + default: gotspace = FALSE; break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + gotspace = TRUE; + break; + } + if (gotspace == (ctype == OP_NOT_HSPACE)) break; + eptr += len; + } + break; + + case OP_NOT_VSPACE: + case OP_VSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + switch(c) + { + default: gotspace = FALSE; break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + gotspace = TRUE; + break; + } + if (gotspace == (ctype == OP_NOT_VSPACE)) break; + eptr += len; + } + break; + case OP_NOT_DIGIT: for (i = min; i < max; i++) { @@ -3257,9 +3980,10 @@ for (;;) /* eptr is now past the end of the maximum run */ + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM46); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -3277,9 +4001,7 @@ for (;;) { for (i = min; i < max; i++) { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; eptr++; } break; @@ -3288,10 +4010,72 @@ for (;;) case OP_ANYBYTE: c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; + if (c > (unsigned int)(md->end_subject - eptr)) + c = md->end_subject - eptr; eptr += c; break; + case OP_ANYNL: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x000d) + { + if (++eptr >= md->end_subject) break; + if (*eptr == 0x000a) eptr++; + } + else + { + if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085) + break; + eptr++; + } + } + break; + + case OP_NOT_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x09 || c == 0x20 || c == 0xa0) break; + eptr++; + } + break; + + case OP_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c != 0x09 && c != 0x20 && c != 0xa0) break; + eptr++; + } + break; + + case OP_NOT_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x0a || c == 0x0b || c == 0x0c || c == 0x0d || c == 0x85) + break; + eptr++; + } + break; + + case OP_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c != 0x0a && c != 0x0b && c != 0x0c && c != 0x0d && c != 0x85) + break; + eptr++; + } + break; + case OP_NOT_DIGIT: for (i = min; i < max; i++) { @@ -3352,9 +4136,10 @@ for (;;) /* eptr is now past the end of the maximum run */ + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM47); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -3366,14 +4151,12 @@ for (;;) } /* Control never gets here */ - /* There's been some horrible disaster. Since all codes > OP_BRA are - for capturing brackets, and there shouldn't be any gaps between 0 and - OP_BRA, arrival here can only mean there is something seriously wrong - in the code above or the OP_xxx definitions. */ + /* There's been some horrible disaster. Arrival here can only mean there is + something seriously wrong in the code above or the OP_xxx definitions. */ default: DPRINTF(("Unknown opcode %d\n", *ecode)); - RRETURN(PCRE_ERROR_UNKNOWN_NODE); + RRETURN(PCRE_ERROR_UNKNOWN_OPCODE); } /* Do not stick any code in here without much thought; it is assumed @@ -3382,6 +4165,29 @@ for (;;) } /* End of main loop */ /* Control never reaches here */ + + +/* When compiling to use the heap rather than the stack for recursive calls to +match(), the RRETURN() macro jumps here. The number that is saved in +frame->Xwhere indicates which label we actually want to return to. */ + +#ifdef NO_RECURSE +#define LBL(val) case val: goto L_RM##val; +HEAP_RETURN: +switch (frame->Xwhere) + { + LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) + LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16) + LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24) + LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32) + LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) + LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) + default: + DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); + return PCRE_ERROR_INTERNAL; + } +#undef LBL +#endif /* NO_RECURSE */ } @@ -3394,6 +4200,7 @@ Undefine all the macros that were defined above to handle this. */ #ifdef NO_RECURSE #undef eptr #undef ecode +#undef mstart #undef offset_top #undef ims #undef eptrb @@ -3411,7 +4218,6 @@ Undefine all the macros that were defined above to handle this. */ #undef cur_is_word #undef condition -#undef minimize #undef prev_is_word #undef original_ims @@ -3467,7 +4273,7 @@ Returns: > 0 => success; value is the number of elements filled in < -1 => some kind of unexpected problem */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, int offsetcount) @@ -3484,6 +4290,7 @@ BOOL startline; BOOL firstline; BOOL first_byte_caseless = FALSE; BOOL req_byte_caseless = FALSE; +BOOL utf8; match_data match_block; match_data *md = &match_block; const uschar *tables; @@ -3491,6 +4298,7 @@ const uschar *start_bits = NULL; USPTR start_match = (USPTR)subject + start_offset; USPTR end_subject; USPTR req_byte_ptr = start_match - 1; +eptrblock eptrchain[EPTR_WORK_SIZE]; pcre_study_data internal_study; const pcre_study_data *study; @@ -3567,7 +4375,7 @@ md->end_subject = md->start_subject + length; end_subject = md->end_subject; md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; -md->utf8 = (re->options & PCRE_UTF8) != 0; +utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0; md->notbol = (options & PCRE_NOTBOL) != 0; md->noteol = (options & PCRE_NOTEOL) != 0; @@ -3576,33 +4384,49 @@ md->partial = (options & PCRE_PARTIAL) != 0; md->hitend = FALSE; md->recursive = NULL; /* No recursion at top level */ +md->eptrchain = eptrchain; /* Make workspace generally available */ md->lcc = tables + lcc_offset; md->ctypes = tables + ctypes_offset; -/* Handle different types of newline. The two bits give four cases. If nothing -is set at run time, whatever was used at compile time applies. */ +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ -switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & - PCRE_NEWLINE_CRLF) +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & + PCRE_NEWLINE_BITS) { - default: newline = NEWLINE; break; /* Compile-time default */ + case 0: newline = NEWLINE; break; /* Compile-time default */ case PCRE_NEWLINE_CR: newline = '\r'; break; case PCRE_NEWLINE_LF: newline = '\n'; break; case PCRE_NEWLINE_CR+ PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: return PCRE_ERROR_BADNEWLINE; } -if (newline > 255) +if (newline == -2) { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + md->nltype = NLTYPE_ANY; } else { - md->nllen = 1; - md->nl[0] = newline; + md->nltype = NLTYPE_FIXED; + if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } + else + { + md->nllen = 1; + md->nl[0] = newline; + } } /* Partial matching is supported only for a restricted set of regexes at the @@ -3615,7 +4439,7 @@ if (md->partial && (re->options & PCRE_NOPARTIAL) != 0) back the character offset. */ #ifdef SUPPORT_UTF8 -if (md->utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) +if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) { if (_pcre_valid_utf8((uschar *)subject, length) >= 0) return PCRE_ERROR_BADUTF8; @@ -3707,10 +4531,13 @@ if ((re->options & PCRE_REQCHSET) != 0) req_byte2 = (tables + fcc_offset)[req_byte]; /* case flipped */ } + +/* ==========================================================================*/ + /* Loop for handling unanchored repeated matching attempts; for anchored regexs the loop runs just once. */ -do +for(;;) { USPTR save_end_subject = end_subject; @@ -3725,14 +4552,14 @@ do /* Advance to a unique first char if possible. If firstline is TRUE, the start of the match is constrained to the first line of a multiline string. - Implement this by temporarily adjusting end_subject so that we stop scanning - at a newline. If the match fails at the newline, later code breaks this loop. - */ + That is, the match must be before or at the first newline. Implement this by + temporarily adjusting end_subject so that we stop scanning at a newline. If + the match fails at the newline, later code breaks this loop. */ if (firstline) { USPTR t = start_match; - while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; + while (t < md->end_subject && !IS_NEWLINE(t)) t++; end_subject = t; } @@ -3753,11 +4580,19 @@ do else if (startline) { - if (start_match >= md->start_subject + md->nllen + - start_offset) + if (start_match > md->start_subject + start_offset) { - while (start_match <= end_subject && - !IS_NEWLINE(start_match - md->nllen)) + while (start_match <= end_subject && !WAS_NEWLINE(start_match)) + start_match++; + + /* If we have just passed a CR and the newline option is ANY or ANYCRLF, + and we are now at a LF, advance the match position by one more character. + */ + + if (start_match[-1] == '\r' && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + start_match < end_subject && + *start_match == '\n') start_match++; } } @@ -3793,8 +4628,8 @@ do HOWEVER: when the subject string is very, very long, searching to its end can take a long time, and give bad performance on quite ordinary patterns. This - showed up when somebody was matching /^C/ on a 32-megabyte string... so we - don't do this when the string is sufficiently long. + showed up when somebody was matching something like /^\d+C/ on a 32-megabyte + string... so we don't do this when the string is sufficiently long. ALSO: this processing is disabled when partial matching is requested. */ @@ -3826,9 +4661,14 @@ do } } - /* If we can't find the required character, break the matching loop */ + /* If we can't find the required character, break the matching loop, + forcing a match failure. */ - if (p >= end_subject) break; + if (p >= end_subject) + { + rc = MATCH_NOMATCH; + break; + } /* If we have found the required character, save the point where we found it, so that we don't search again next time round the loop if @@ -3838,49 +4678,74 @@ do } } - /* When a match occurs, substrings will be set for all internal extractions; - we just need to set up the whole thing as substring 0 before returning. If - there were too many extractions, set the return code to zero. In the case - where we had to get some local store to hold offsets for backreferences, copy - those back references that we can. In this case there need not be overflow - if certain parts of the pattern were not used. */ + /* OK, we can now run the match. */ - md->start_match = start_match; + md->start_match_ptr = start_match; /* Insurance */ md->match_call_count = 0; + md->eptrn = 0; /* Next free eptrchain slot */ + rc = match(start_match, md->start_code, start_match, 2, md, + ims, NULL, 0, 0); - rc = match(start_match, md->start_code, 2, md, ims, NULL, match_isgroup, 0); + /* Any return other than MATCH_NOMATCH breaks the loop. */ - /* When the result is no match, if the subject's first character was a - newline and the PCRE_FIRSTLINE option is set, break (which will return - PCRE_ERROR_NOMATCH). The option requests that a match occur before the first - newline in the subject. Otherwise, advance the pointer to the next character - and continue - but the continuation will actually happen only when the - pattern is not anchored. */ + if (rc != MATCH_NOMATCH) break; - if (rc == MATCH_NOMATCH) - { - if (firstline && - start_match <= md->end_subject - md->nllen && - IS_NEWLINE(start_match)) - break; - start_match++; + /* If PCRE_FIRSTLINE is set, the match must happen before or at the first + newline in the subject (though it may continue over the newline). Therefore, + if we have just failed to match, starting at a newline, do not continue. */ + + if (firstline && IS_NEWLINE(start_match)) break; + + /* Advance the match position by one character. */ + + start_match++; #ifdef SUPPORT_UTF8 - if (md->utf8) - while(start_match < end_subject && (*start_match & 0xc0) == 0x80) - start_match++; + if (utf8) + while(start_match < end_subject && (*start_match & 0xc0) == 0x80) + start_match++; #endif - continue; - } - if (rc != MATCH_MATCH) - { - DPRINTF((">>>> error: returning %d\n", rc)); - return rc; - } + /* Break the loop if the pattern is anchored or if we have passed the end of + the subject. */ - /* We have a match! Copy the offset information from temporary store if - necessary */ + if (anchored || start_match > end_subject) break; + /* If we have just passed a CR and the newline option is CRLF or ANY or + ANYCRLF, and we are now at a LF, advance the match position by one more + character. */ + + if (start_match[-1] == '\r' && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2) && + start_match < end_subject && + *start_match == '\n') + start_match++; + + } /* End of for(;;) "bumpalong" loop */ + +/* ==========================================================================*/ + +/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping +conditions is true: + +(1) The pattern is anchored; + +(2) We are past the end of the subject; + +(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because + this option requests that a match occur at or before the first newline in + the subject. + +When we have a match and the offset vector is big enough to deal with any +backreferences, captured substring offsets will already be set up. In the case +where we had to get some local store to hold offsets for backreference +processing, copy those that we can. In this case there need not be overflow if +certain parts of the pattern were not used, even though there are more +capturing parentheses than vector slots. */ + +if (rc == MATCH_MATCH) + { if (using_temporary_offsets) { if (offsetcount >= 4) @@ -3889,18 +4754,23 @@ do (offsetcount - 2) * sizeof(int)); DPRINTF(("Copied offsets from temporary memory\n")); } - if (md->end_offset_top > offsetcount) - md->offset_overflow = TRUE; - + if (md->end_offset_top > offsetcount) md->offset_overflow = TRUE; DPRINTF(("Freeing temporary memory\n")); (pcre_free)(md->offset_vector); } + /* Set the return code to the number of captured strings, or 0 if there are + too many to fit into the vector. */ + rc = md->offset_overflow? 0 : md->end_offset_top/2; + /* If there is space, set up the whole thing as substring 0. The value of + md->start_match_ptr might be modified if \K was encountered on the success + matching path. */ + if (offsetcount < 2) rc = 0; else { - offsets[0] = start_match - md->start_subject; + offsets[0] = md->start_match_ptr - md->start_subject; offsets[1] = md->end_match_ptr - md->start_subject; } @@ -3908,9 +4778,8 @@ do return rc; } -/* This "while" is the end of the "do" above */ - -while (!anchored && start_match <= end_subject); +/* Control gets here if there has been an error, or if the overall match +attempt has failed at all permitted starting positions. */ if (using_temporary_offsets) { @@ -3918,7 +4787,12 @@ if (using_temporary_offsets) (pcre_free)(md->offset_vector); } -if (md->partial && md->hitend) +if (rc != MATCH_NOMATCH) + { + DPRINTF((">>>> error: returning %d\n", rc)); + return rc; + } +else if (md->partial && md->hitend) { DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); return PCRE_ERROR_PARTIAL; diff --git a/libpcre/pcre_fullinfo.c b/libpcre/pcre_fullinfo.c index 4a8edc6f4..797eddecf 100644 --- a/libpcre/pcre_fullinfo.c +++ b/libpcre/pcre_fullinfo.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -61,7 +61,7 @@ Arguments: Returns: 0 if data returned, negative on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, void *where) { @@ -140,6 +140,14 @@ switch (what) *((const uschar **)where) = (const uschar *)(_pcre_default_tables); break; + case PCRE_INFO_OKPARTIAL: + *((int *)where) = (re->options & PCRE_NOPARTIAL) == 0; + break; + + case PCRE_INFO_JCHANGED: + *((int *)where) = (re->options & PCRE_JCHANGED) != 0; + break; + default: return PCRE_ERROR_BADOPTION; } diff --git a/libpcre/pcre_get.c b/libpcre/pcre_get.c index 0588c61a7..ba0c8cb21 100644 --- a/libpcre/pcre_get.c +++ b/libpcre/pcre_get.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -436,7 +436,6 @@ pcre_get_named_substring(const pcre *code, const char *subject, int *ovector, int n = get_first_set(code, stringname, ovector); if (n <= 0) return n; return pcre_get_substring(subject, ovector, stringcount, n, stringptr); - } diff --git a/libpcre/pcre_globals.c b/libpcre/pcre_globals.c index f829acfb1..dbde57e02 100644 --- a/libpcre/pcre_globals.c +++ b/libpcre/pcre_globals.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -46,24 +46,14 @@ indirection. These values can be changed by the caller, but are shared between all threads. However, when compiling for Virtual Pascal, things are done differently, and global variables are not used (see pcre.in). */ - #include "pcre_internal.h" - #ifndef VPCOMPAT -#ifdef __cplusplus -extern "C" void *(*pcre_malloc)(size_t) = malloc; -extern "C" void (*pcre_free)(void *) = free; -extern "C" void *(*pcre_stack_malloc)(size_t) = malloc; -extern "C" void (*pcre_stack_free)(void *) = free; -extern "C" int (*pcre_callout)(pcre_callout_block *) = NULL; -#else -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; -void *(*pcre_stack_malloc)(size_t) = malloc; -void (*pcre_stack_free)(void *) = free; -int (*pcre_callout)(pcre_callout_block *) = NULL; -#endif +PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*pcre_free)(void *) = free; +PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*pcre_stack_free)(void *) = free; +PCRE_EXP_DATA_DEFN int (*pcre_callout)(pcre_callout_block *) = NULL; #endif /* End of pcre_globals.c */ diff --git a/libpcre/pcre_info.c b/libpcre/pcre_info.c index b318b93ea..52ac23f70 100644 --- a/libpcre/pcre_info.c +++ b/libpcre/pcre_info.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -68,7 +68,7 @@ Returns: number of capturing subpatterns or negative values on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_info(const pcre *argument_re, int *optptr, int *first_byte) { real_pcre internal_re; diff --git a/libpcre/pcre_internal.h b/libpcre/pcre_internal.h index b13a4abcb..6ef019bb1 100644 --- a/libpcre/pcre_internal.h +++ b/libpcre/pcre_internal.h @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,18 +42,9 @@ POSSIBILITY OF SUCH DAMAGE. modules, but which are not relevant to the exported API. This includes some functions whose names all begin with "_pcre_". */ -/* Get the definitions provided by running "configure" */ - #ifndef PCRE_INTERNAL_H #define PCRE_INTERNAL_H - -#ifndef WIN32 -#include "config.h" -#else -#include "pcre_winconfig.h" -#endif - /* Define DEBUG to get debugging output on stdout. */ #if 0 @@ -63,15 +54,25 @@ functions whose names all begin with "_pcre_". */ /* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef inline, and there are *still* stupid compilers about that don't like indented pre-processor statements, or at least there were when I first wrote this. After -all, it had only been about 10 years then... */ +all, it had only been about 10 years then... + +It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so +be absolutely sure we get our version. */ + +#undef DPRINTF +#ifdef DEBUG +#define DPRINTF(p) printf p +#else +#define DPRINTF(p) /* Nothing */ +#endif /* Get the definitions provided by running "configure" */ -#ifdef DEBUG -#define DPRINTF(p) printf p +#ifdef WIN32 +#include "pcre_winconfig.h" #else -#define DPRINTF(p) /*nothing*/ +#include "config.h" #endif /* Standard C headers plus the external interface definition. The only time @@ -86,8 +87,62 @@ setjmp and stdarg are used is when NO_RECURSE is set. */ #include #include -#ifndef PCRE_SPY -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ +/* When compiling a DLL for Windows, the exported symbols have to be declared +using some MS magic. I found some useful information on this web page: +http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the +information there, using __declspec(dllexport) without "extern" we have a +definition; with "extern" we have a declaration. The settings here override the +setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, +which is all that is needed for applications (they just import the symbols). We +use: + + PCRE_EXP_DECL for declarations + PCRE_EXP_DEFN for definitions of exported functions + PCRE_EXP_DATA_DEFN for definitions of exported variables + +The reason for the two DEFN macros is that in non-Windows environments, one +does not want to have "extern" before variable definitions because it leads to +compiler warnings. So we distinguish between functions and variables. In +Windows, the two should always be the same. + +The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, +which is an application, but needs to import this file in order to "peek" at +internals, can #include pcre.h first to get an application's-eye view. + +In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, +special-purpose environments) might want to stick other stuff in front of +exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and +PCRE_EXP_DATA_DEFN only if they are not already set. */ + +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 +/* COMMENTED OUT AS IT'S COMPILED STATICALLY +# ifdef DLL_EXPORT +# define PCRE_EXP_DECL extern __declspec(dllexport) +# define PCRE_EXP_DEFN __declspec(dllexport) +# define PCRE_EXP_DATA_DEFN __declspec(dllexport) +# else +*/ +# define PCRE_EXP_DECL extern +# define PCRE_EXP_DEFN +# define PCRE_EXP_DATA_DEFN +/* +# endif +*/ +# +# else +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +# ifndef PCRE_EXP_DEFN +# define PCRE_EXP_DEFN PCRE_EXP_DECL +# endif +# ifndef PCRE_EXP_DATA_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# endif #endif /* We need to have types that specify unsigned 16-bit and 32-bit integers. We @@ -121,22 +176,57 @@ Unix, where it is defined in sys/types, so use "uschar" instead. */ typedef unsigned char uschar; -/* PCRE is able to support 3 different kinds of newline (CR, LF, CRLF). The -following macro is used to package up testing for newlines. NLBLOCK is defined -in the various modules to indicate in which datablock the parameters exist. */ +/* This is an unsigned int value that no character can ever have. UTF-8 +characters only go up to 0x7fffffff (though Unicode doesn't go beyond +0x0010ffff). */ + +#define NOTACHAR 0xffffffff + +/* PCRE is able to support several different kinds of newline (CR, LF, CRLF, +"any" and "anycrlf" at present). The following macros are used to package up +testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various +modules to indicate in which datablock the parameters exist, and what the +start/end of string field names are. */ + +#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ +#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ + +/* This macro checks for a newline at the given position */ #define IS_NEWLINE(p) \ - ((p)[0] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1])) + ((NLBLOCK->nltype != NLTYPE_FIXED)? \ + ((p) < NLBLOCK->PSEND && \ + _pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\ + utf8)) \ + : \ + ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ + (p)[0] == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1]) \ + ) \ + ) -/* When PCRE is compiled as a C++ library, the subject pointer can be -replaced with a custom type. This makes it possible, for example, to -allow pcre_exec() to process subject strings that are discontinuous by -using a smart pointer class. It must always be possible to inspect all -of the subject string in pcre_exec() because of the way it -backtracks. Two macros are required in the normal case, for -sign-unspecified and unsigned char pointers. The former is used for -the external interface and appears in pcre.h, which is why its name +/* This macro checks for a newline immediately preceding the given position */ + +#define WAS_NEWLINE(p) \ + ((NLBLOCK->nltype != NLTYPE_FIXED)? \ + ((p) > NLBLOCK->PSSTART && \ + _pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ + &(NLBLOCK->nllen), utf8)) \ + : \ + ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ + (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || (p)[-NLBLOCK->nllen+1] == NLBLOCK->nl[1]) \ + ) \ + ) + +/* When PCRE is compiled as a C++ library, the subject pointer can be replaced +with a custom type. This makes it possible, for example, to allow pcre_exec() +to process subject strings that are discontinuous by using a smart pointer +class. It must always be possible to inspect all of the subject string in +pcre_exec() because of the way it backtracks. Two macros are required in the +normal case, for sign-unspecified and unsigned char pointers. The former is +used for the external interface and appears in pcre.h, which is why its name must begin with PCRE_. */ #ifdef CUSTOM_SUBJECT_PTR @@ -147,24 +237,22 @@ must begin with PCRE_. */ #define USPTR const unsigned char * #endif -/* Include the public PCRE header and the definitions of UCP character - property values. */ + + +/* Include the public PCRE header and the definitions of UCP character property +values. */ #include "pcre.h" #include "ucp.h" - -/* Include the (copy of) the public ucp header, changing the external name into a private one. This does no harm, even if we aren't compiling UCP support. */ - -#define ucp_findchar _pcre_ucp_findchar -#include "ucp.h" - /* When compiling for use with the Virtual Pascal compiler, these functions need to have their names changed. PCRE must be compiled with the -DVPCOMPAT option on the command line. */ #ifdef VPCOMPAT +#define strlen(s) _strlen(s) #define strncmp(s1,s2,m) _strncmp(s1,s2,m) +#define memcmp(s,c,n) _memcmp(s,c,n) #define memcpy(d,s,n) _memcpy(d,s,n) #define memmove(d,s,n) _memmove(d,s,n) #define memset(s,c,n) _memset(s,c,n) @@ -173,23 +261,31 @@ option on the command line. */ /* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY is set. Otherwise, include an emulating function for those systems that have -neither (there some non-Unix environments where this is the case). This assumes -that all calls to memmove are moving strings upwards in store, which is the -case in PCRE. */ +neither (there some non-Unix environments where this is the case). */ -#if ! HAVE_MEMMOVE +#ifndef HAVE_MEMMOVE #undef memmove /* some systems may have a macro */ -#if HAVE_BCOPY +#ifdef HAVE_BCOPY #define memmove(a, b, c) bcopy(b, a, c) #else /* HAVE_BCOPY */ static void * -pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) +pcre_memmove(void *d, const void *s, size_t n) { size_t i; -dest += n; -src += n; -for (i = 0; i < n; ++i) *(--dest) = *(--src); -return dest; +unsigned char *dest = (unsigned char *)d; +const unsigned char *src = (const unsigned char *)s; +if (dest > src) + { + dest += n; + src += n; + for (i = 0; i < n; ++i) *(--dest) = *(--src); + return (void *)dest; + } +else + { + for (i = 0; i < n; ++i) *dest++ = *src++; + return (void *)(dest - n); + } } #define memmove(a, b, c) pcre_memmove(a, b, c) #endif /* not HAVE_BCOPY */ @@ -292,7 +388,7 @@ we know we are in UTF-8 mode. */ #define GETCHAR(c, eptr) \ c = *eptr; \ - if ((c & 0xc0) == 0xc0) \ + if (c >= 0xc0) \ { \ int gcii; \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ @@ -310,7 +406,7 @@ pointer. */ #define GETCHARTEST(c, eptr) \ c = *eptr; \ - if (utf8 && (c & 0xc0) == 0xc0) \ + if (utf8 && c >= 0xc0) \ { \ int gcii; \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ @@ -328,7 +424,7 @@ know we are in UTF-8 mode. */ #define GETCHARINC(c, eptr) \ c = *eptr++; \ - if ((c & 0xc0) == 0xc0) \ + if (c >= 0xc0) \ { \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ int gcss = 6*gcaa; \ @@ -344,7 +440,7 @@ know we are in UTF-8 mode. */ #define GETCHARINCTEST(c, eptr) \ c = *eptr++; \ - if (utf8 && (c & 0xc0) == 0xc0) \ + if (utf8 && c >= 0xc0) \ { \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ int gcss = 6*gcaa; \ @@ -361,7 +457,7 @@ if there are extra bytes. This is called when we know we are in UTF-8 mode. */ #define GETCHARLEN(c, eptr, len) \ c = *eptr; \ - if ((c & 0xc0) == 0xc0) \ + if (c >= 0xc0) \ { \ int gcii; \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ @@ -414,20 +510,22 @@ bits. */ /* Masks for identifying the public options that are permitted at compile time, run time, or study time, respectively. */ +#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ + PCRE_NEWLINE_ANYCRLF) + #define PUBLIC_OPTIONS \ (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) + PCRE_DUPNAMES|PCRE_NEWLINE_BITS) #define PUBLIC_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) + PCRE_PARTIAL|PCRE_NEWLINE_BITS) #define PUBLIC_DFA_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_CR| \ - PCRE_NEWLINE_LF) + PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS) #define PUBLIC_STUDY_OPTIONS 0 /* None defined */ @@ -459,9 +557,7 @@ typedef int BOOL; #define FALSE 0 #define TRUE 1 -/* Escape items that are just an encoding of a particular data value. Note that -ESC_n is defined as yet another macro, which is set in config.h to either \n -(the default) or \r (which some people want). */ +/* Escape items that are just an encoding of a particular data value. */ #ifndef ESC_e #define ESC_e 27 @@ -472,7 +568,7 @@ ESC_n is defined as yet another macro, which is set in config.h to either \n #endif #ifndef ESC_n -#define ESC_n NEWLINE +#define ESC_n '\n' #endif #ifndef ESC_r @@ -511,21 +607,28 @@ value such as \n. They must have non-zero values, as check_escape() returns their negation. Also, they must appear in the same order as in the opcode definitions below, up to ESC_z. There's a dummy for OP_ANY because it corresponds to "." rather than an escape sequence. The final one must be -ESC_REF as subsequent values are used for \1, \2, \3, etc. There is are two -tests in the code for an escape greater than ESC_b and less than ESC_Z to -detect the types that may be repeated. These are the types that consume -characters. If any new escapes are put in between that don't consume a +ESC_REF as subsequent values are used for backreferences (\1, \2, \3, etc). +There are two tests in the code for an escape greater than ESC_b and less than +ESC_Z to detect the types that may be repeated. These are the types that +consume characters. If any new escapes are put in between that don't consume a character, that code will have to change. */ -enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, - ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E, - ESC_Q, ESC_REF }; +enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, + ESC_W, ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, ESC_h, + ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_k, ESC_REF }; + /* Opcode table: OP_BRA must be last, as all values >= it are used for brackets that extract substrings. Starting from 1 (i.e. after OP_END), the values up to OP_EOD must correspond in order to the list of escapes immediately above. -Note that whenever this list is updated, the two macro definitions that follow -must also be updated to match. */ + +To keep stored, compiled patterns compatible, new opcodes should be added +immediately before OP_BRA, where (since release 7.0) a gap is left for this +purpose. + +*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions +that follow must also be updated to match. There is also a table called +"coptable" in pcre_dfa_exec.c that must be updated. */ enum { OP_END, /* 0 End of pattern */ @@ -534,141 +637,162 @@ enum { OP_SOD, /* 1 Start of data: \A */ OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_NOT_WORD_BOUNDARY, /* 3 \B */ - OP_WORD_BOUNDARY, /* 4 \b */ - OP_NOT_DIGIT, /* 5 \D */ - OP_DIGIT, /* 6 \d */ - OP_NOT_WHITESPACE, /* 7 \S */ - OP_WHITESPACE, /* 8 \s */ - OP_NOT_WORDCHAR, /* 9 \W */ - OP_WORDCHAR, /* 10 \w */ - OP_ANY, /* 11 Match any character */ - OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 13 \P (not Unicode property) */ - OP_PROP, /* 14 \p (Unicode property) */ - OP_EXTUNI, /* 15 \X (extended Unicode sequence */ - OP_EODN, /* 16 End of data or \n at end of data: \Z. */ - OP_EOD, /* 17 End of data: \z */ + OP_SET_SOM, /* 3 Set start of match (\K) */ + OP_NOT_WORD_BOUNDARY, /* 4 \B */ + OP_WORD_BOUNDARY, /* 5 \b */ + OP_NOT_DIGIT, /* 6 \D */ + OP_DIGIT, /* 7 \d */ + OP_NOT_WHITESPACE, /* 8 \S */ + OP_WHITESPACE, /* 9 \s */ + OP_NOT_WORDCHAR, /* 10 \W */ + OP_WORDCHAR, /* 11 \w */ + OP_ANY, /* 12 Match any character */ + OP_ANYBYTE, /* 13 Match any byte (\C); different to OP_ANY for UTF-8 */ + OP_NOTPROP, /* 14 \P (not Unicode property) */ + OP_PROP, /* 15 \p (Unicode property) */ + OP_ANYNL, /* 16 \R (any newline sequence) */ + OP_NOT_HSPACE, /* 17 \H (not horizontal whitespace) */ + OP_HSPACE, /* 18 \h (horizontal whitespace) */ + OP_NOT_VSPACE, /* 19 \V (not vertical whitespace) */ + OP_VSPACE, /* 20 \v (vertical whitespace) */ + OP_EXTUNI, /* 21 \X (extended Unicode sequence */ + OP_EODN, /* 22 End of data or \n at end of data: \Z. */ + OP_EOD, /* 23 End of data: \z */ - OP_OPT, /* 18 Set runtime options */ - OP_CIRC, /* 19 Start of line - varies with multiline switch */ - OP_DOLL, /* 20 End of line - varies with multiline switch */ - OP_CHAR, /* 21 Match one character, casefully */ - OP_CHARNC, /* 22 Match one character, caselessly */ - OP_NOT, /* 23 Match one character, not the following one */ + OP_OPT, /* 24 Set runtime options */ + OP_CIRC, /* 25 Start of line - varies with multiline switch */ + OP_DOLL, /* 26 End of line - varies with multiline switch */ + OP_CHAR, /* 27 Match one character, casefully */ + OP_CHARNC, /* 28 Match one character, caselessly */ + OP_NOT, /* 29 Match one character, not the following one */ - OP_STAR, /* 24 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 25 all these opcodes must come in pairs, with */ - OP_PLUS, /* 26 the minimizing one second. */ - OP_MINPLUS, /* 27 This first set applies to single characters */ - OP_QUERY, /* 28 */ - OP_MINQUERY, /* 29 */ - OP_UPTO, /* 30 From 0 to n matches */ - OP_MINUPTO, /* 31 */ - OP_EXACT, /* 32 Exactly n matches */ + OP_STAR, /* 30 The maximizing and minimizing versions of */ + OP_MINSTAR, /* 31 these six opcodes must come in pairs, with */ + OP_PLUS, /* 32 the minimizing one second. */ + OP_MINPLUS, /* 33 This first set applies to single characters.*/ + OP_QUERY, /* 34 */ + OP_MINQUERY, /* 35 */ - OP_NOTSTAR, /* 33 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 34 all these opcodes must come in pairs, with */ - OP_NOTPLUS, /* 35 the minimizing one second. */ - OP_NOTMINPLUS, /* 36 This set applies to "not" single characters */ - OP_NOTQUERY, /* 37 */ - OP_NOTMINQUERY, /* 38 */ - OP_NOTUPTO, /* 39 From 0 to n matches */ - OP_NOTMINUPTO, /* 40 */ - OP_NOTEXACT, /* 41 Exactly n matches */ + OP_UPTO, /* 36 From 0 to n matches */ + OP_MINUPTO, /* 37 */ + OP_EXACT, /* 38 Exactly n matches */ - OP_TYPESTAR, /* 42 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 43 all these opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 44 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 45 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 46 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 47 */ - OP_TYPEUPTO, /* 48 From 0 to n matches */ - OP_TYPEMINUPTO, /* 49 */ - OP_TYPEEXACT, /* 50 Exactly n matches */ + OP_POSSTAR, /* 39 Possessified star */ + OP_POSPLUS, /* 40 Possessified plus */ + OP_POSQUERY, /* 41 Posesssified query */ + OP_POSUPTO, /* 42 Possessified upto */ - OP_CRSTAR, /* 51 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 52 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 53 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 54 be in exactly the same order as those above. */ - OP_CRQUERY, /* 55 These are for character classes and back refs */ - OP_CRMINQUERY, /* 56 */ - OP_CRRANGE, /* 57 These are different to the three sets above. */ - OP_CRMINRANGE, /* 58 */ + OP_NOTSTAR, /* 43 The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* 44 these six opcodes must come in pairs, with */ + OP_NOTPLUS, /* 45 the minimizing one second. They must be in */ + OP_NOTMINPLUS, /* 46 exactly the same order as those above. */ + OP_NOTQUERY, /* 47 This set applies to "not" single characters. */ + OP_NOTMINQUERY, /* 48 */ - OP_CLASS, /* 59 Match a character class, chars < 256 only */ - OP_NCLASS, /* 60 Same, but the bitmap was created from a negative + OP_NOTUPTO, /* 49 From 0 to n matches */ + OP_NOTMINUPTO, /* 50 */ + OP_NOTEXACT, /* 51 Exactly n matches */ + + OP_NOTPOSSTAR, /* 52 Possessified versions */ + OP_NOTPOSPLUS, /* 53 */ + OP_NOTPOSQUERY, /* 54 */ + OP_NOTPOSUPTO, /* 55 */ + + OP_TYPESTAR, /* 56 The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* 57 these six opcodes must come in pairs, with */ + OP_TYPEPLUS, /* 58 the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* 59 be in exactly the same order as those above. */ + OP_TYPEQUERY, /* 60 This set applies to character types such as \d */ + OP_TYPEMINQUERY, /* 61 */ + + OP_TYPEUPTO, /* 62 From 0 to n matches */ + OP_TYPEMINUPTO, /* 63 */ + OP_TYPEEXACT, /* 64 Exactly n matches */ + + OP_TYPEPOSSTAR, /* 65 Possessified versions */ + OP_TYPEPOSPLUS, /* 66 */ + OP_TYPEPOSQUERY, /* 67 */ + OP_TYPEPOSUPTO, /* 68 */ + + OP_CRSTAR, /* 69 The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* 70 all these opcodes must come in pairs, with */ + OP_CRPLUS, /* 71 the minimizing one second. These codes must */ + OP_CRMINPLUS, /* 72 be in exactly the same order as those above. */ + OP_CRQUERY, /* 73 These are for character classes and back refs */ + OP_CRMINQUERY, /* 74 */ + OP_CRRANGE, /* 75 These are different to the three sets above. */ + OP_CRMINRANGE, /* 76 */ + + OP_CLASS, /* 77 Match a character class, chars < 256 only */ + OP_NCLASS, /* 78 Same, but the bitmap was created from a negative class - the difference is relevant only when a UTF-8 character > 255 is encountered. */ - OP_XCLASS, /* 61 Extended class for handling UTF-8 chars within the + OP_XCLASS, /* 79 Extended class for handling UTF-8 chars within the class. This does both positive and negative. */ - OP_REF, /* 62 Match a back reference */ - OP_RECURSE, /* 63 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 64 Call out to external function if provided */ + OP_REF, /* 80 Match a back reference */ + OP_RECURSE, /* 81 Match a numbered subpattern (possibly recursive) */ + OP_CALLOUT, /* 82 Call out to external function if provided */ - OP_ALT, /* 65 Start of alternation */ - OP_KET, /* 66 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 67 These two must remain together and in this */ - OP_KETRMIN, /* 68 order. They are for groups the repeat for ever. */ + OP_ALT, /* 83 Start of alternation */ + OP_KET, /* 84 End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* 85 These two must remain together and in this */ + OP_KETRMIN, /* 86 order. They are for groups the repeat for ever. */ - /* The assertions must come before ONCE and COND */ + /* The assertions must come before BRA, CBRA, ONCE, and COND.*/ - OP_ASSERT, /* 69 Positive lookahead */ - OP_ASSERT_NOT, /* 70 Negative lookahead */ - OP_ASSERTBACK, /* 71 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */ - OP_REVERSE, /* 73 Move pointer back - used in lookbehind assertions */ + OP_ASSERT, /* 87 Positive lookahead */ + OP_ASSERT_NOT, /* 88 Negative lookahead */ + OP_ASSERTBACK, /* 89 Positive lookbehind */ + OP_ASSERTBACK_NOT, /* 90 Negative lookbehind */ + OP_REVERSE, /* 91 Move pointer back - used in lookbehind assertions */ - /* ONCE and COND must come after the assertions, with ONCE first, as there's - a test for >= ONCE for a subpattern that isn't an assertion. */ + /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first, + as there's a test for >= ONCE for a subpattern that isn't an assertion. */ - OP_ONCE, /* 74 Once matched, don't back up into the subpattern */ - OP_COND, /* 75 Conditional group */ - OP_CREF, /* 76 Used to hold an extraction string number (cond ref) */ + OP_ONCE, /* 92 Atomic group */ + OP_BRA, /* 83 Start of non-capturing bracket */ + OP_CBRA, /* 94 Start of capturing bracket */ + OP_COND, /* 95 Conditional group */ - OP_BRAZERO, /* 77 These two must remain together and in this */ - OP_BRAMINZERO, /* 78 order. */ + /* These three must follow the previous three, in the same order. There's a + check for >= SBRA to distinguish the two sets. */ - OP_BRANUMBER, /* 79 Used for extracting brackets whose number is greater - than can fit into an opcode. */ + OP_SBRA, /* 96 Start of non-capturing bracket, check empty */ + OP_SCBRA, /* 97 Start of capturing bracket, check empty */ + OP_SCOND, /* 98 Conditional group, check empty */ - OP_BRA /* 80 This and greater values are used for brackets that - extract substrings up to EXTRACT_BASIC_MAX. After - that, use is made of OP_BRANUMBER. */ + OP_CREF, /* 99 Used to hold a capture number as condition */ + OP_RREF, /* 100 Used to hold a recursion number as condition */ + OP_DEF, /* 101 The DEFINE condition */ + + OP_BRAZERO, /* 102 These two must remain together and in this */ + OP_BRAMINZERO /* 103 order. */ }; -/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and -study.c that all opcodes are less than 128 in value. This makes handling UTF-8 -character sequences easier. */ - -/* The highest extraction number before we have to start using additional -bytes. (Originally PCRE didn't have support for extraction counts highter than -this number.) The value is limited by the number of opcodes left after OP_BRA, -i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional -opcodes. */ - -#define EXTRACT_BASIC_MAX 100 - /* This macro defines textual names for all the opcodes. These are used only for debugging. The macro is referenced only in pcre_printint.c. */ #define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ + "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "extuni", \ - "\\Z", "\\z", \ + "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ + "extuni", "\\Z", "\\z", \ "Opt", "^", "$", "char", "charnc", "not", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ "*", "*?", "+", "+?", "?", "??", "{", "{", \ "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ - "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\ - "Brazero", "Braminzero", "Branumber", "Bra" + "AssertB", "AssertB not", "Reverse", \ + "Once", "Bra 0", "Bra", "Cond", "SBra 0", "SBra", "SCond", \ + "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero" /* This macro defines the length of fixed length operations in the compiled @@ -682,9 +806,11 @@ in UTF-8 mode. The code that uses this table must know about such things. */ #define OP_LENGTHS \ 1, /* End */ \ - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ + 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ + 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ 1, 1, /* Any, Anybyte */ \ 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ + 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ 2, /* Char - the minimum length */ \ 2, /* Charnc - the minimum length */ \ @@ -692,12 +818,15 @@ in UTF-8 mode. The code that uses this table must know about such things. */ /* Positive single-char repeats ** These are */ \ 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ + 2, 2, 2, 4, /* *+, ++, ?+, upto+ */ \ /* Negative single-char repeats - only for chars < 256 */ \ 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ 4, 4, 4, /* NOT upto, minupto, exact */ \ + 2, 2, 2, 4, /* Possessive *, +, ?, upto */ \ /* Positive type repeats */ \ 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ 4, 4, 4, /* Type upto, minupto, exact */ \ + 2, 2, 2, 4, /* Possessive *+, ++, ?+, upto+ */ \ /* Character class & ref repeats */ \ 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ 5, 5, /* CRRANGE, CRMINRANGE */ \ @@ -716,17 +845,22 @@ in UTF-8 mode. The code that uses this table must know about such things. */ 1+LINK_SIZE, /* Assert behind */ \ 1+LINK_SIZE, /* Assert behind not */ \ 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* Once */ \ + 1+LINK_SIZE, /* ONCE */ \ + 1+LINK_SIZE, /* BRA */ \ + 3+LINK_SIZE, /* CBRA */ \ 1+LINK_SIZE, /* COND */ \ + 1+LINK_SIZE, /* SBRA */ \ + 3+LINK_SIZE, /* SCBRA */ \ + 1+LINK_SIZE, /* SCOND */ \ 3, /* CREF */ \ + 3, /* RREF */ \ + 1, /* DEF */ \ 1, 1, /* BRAZERO, BRAMINZERO */ \ - 3, /* BRANUMBER */ \ - 1+LINK_SIZE /* BRA */ \ -/* A magic value for OP_CREF to indicate the "in recursion" condition. */ +/* A magic value for OP_RREF to indicate the "any recursion" condition. */ -#define CREF_RECURSE 0xffff +#define RREF_ANY 0xffff /* Error code numbers. They are given names so that they can more easily be tracked. */ @@ -736,7 +870,7 @@ enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51 }; + ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58 }; /* The real format of the start of the pcre block; the index of names and the code vector run on as long as necessary after the end. We store an explicit @@ -791,17 +925,23 @@ typedef struct compile_data { const uschar *fcc; /* Points to case-flipping table */ const uschar *cbits; /* Points to character type table */ const uschar *ctypes; /* Points to table of type maps */ + const uschar *start_workspace;/* The start of working space */ const uschar *start_code; /* The start of the compiled code */ const uschar *start_pattern; /* The start of the pattern */ + const uschar *end_pattern; /* The end of the pattern */ + uschar *hwm; /* High watermark of workspace */ uschar *name_table; /* The name/number table */ int names_found; /* Number of entries so far */ int name_entry_size; /* Size of each entry */ + int bracount; /* Count of capturing parens */ int top_backref; /* Maximum back reference */ unsigned int backref_map; /* Bitmap of low back refs */ + int external_options; /* External (initial) options */ int req_varyopt; /* "After variable item" flag for reqbyte */ BOOL nopartial; /* Set TRUE if partial won't work */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + uschar nl[4]; /* Newline string when fixed length */ } compile_data; /* Structure for maintaining a chain of pointers to the currently incomplete @@ -819,33 +959,34 @@ typedef struct recursion_info { struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ int group_num; /* Number of group that was called */ const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of md->start_match */ + USPTR save_start; /* Old value of mstart */ int *offset_save; /* Pointer to start of saved offsets */ int saved_max; /* Number of saved offsets */ } recursion_info; -/* When compiling in a mode that doesn't use recursive calls to match(), -a structure is used to remember local variables on the heap. It is defined in -pcre_exec.c, close to the match() function, so that it is easy to keep it in -step with any changes of local variable. However, the pointer to the current -frame must be saved in some "static" place over a longjmp(). We declare the -structure here so that we can put a pointer in the match_data structure. NOTE: -This isn't used for a "normal" compilation of pcre. */ +/* Structure for building a chain of data for holding the values of the subject +pointer at the start of each subpattern, so as to detect when an empty string +has been matched by a subpattern - to break infinite loops. */ + +typedef struct eptrblock { + struct eptrblock *epb_prev; + USPTR epb_saved_eptr; +} eptrblock; -struct heapframe; /* Structure for passing "static" information around between the functions doing traditional NFA matching, so that they are thread-safe. */ typedef struct match_data { - unsigned long int match_call_count; /* As it says */ + unsigned long int match_call_count; /* As it says */ unsigned long int match_limit; /* As it says */ unsigned long int match_limit_recursion; /* As it says */ int *offset_vector; /* Offset vector */ int offset_end; /* One past the end */ int offset_max; /* The maximum usable for return data */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + uschar nl[4]; /* Newline string when fixed */ const uschar *lcc; /* Points to lower casing table */ const uschar *ctypes; /* Points to table of type maps */ BOOL offset_overflow; /* Set if too many extractions */ @@ -859,14 +1000,15 @@ typedef struct match_data { const uschar *start_code; /* For use when recursing */ USPTR start_subject; /* Start of the subject string */ USPTR end_subject; /* End of the subject string */ - USPTR start_match; /* Start of this match attempt */ + USPTR start_match_ptr; /* Start of matched string */ USPTR end_match_ptr; /* Subject position at end match */ int end_offset_top; /* Highwater mark at end of match */ int capture_last; /* Most recent capture number */ int start_offset; /* The start offset value */ + eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */ + int eptrn; /* Next free eptrblock */ recursion_info *recursive; /* Linked list of recursion data */ void *callout_data; /* To pass back to callouts */ - struct heapframe *thisframe; /* Used only when compiling for no recursion */ } match_data; /* A similar structure is used for the same purpose by the DFA matching @@ -879,8 +1021,9 @@ typedef struct dfa_match_data { const uschar *tables; /* Character tables */ int moptions; /* Match options */ int poptions; /* Pattern options */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + uschar nl[4]; /* Newline string when fixed */ void *callout_data; /* To pass back to callouts */ } dfa_match_data; @@ -951,13 +1094,17 @@ extern const uschar _pcre_OP_lengths[]; one of the exported public functions. They have to be "external" in the C sense, but are not part of the PCRE public API. */ -extern int _pcre_ord2utf8(int, uschar *); -extern real_pcre * _pcre_try_flipped(const real_pcre *, real_pcre *, - const pcre_study_data *, pcre_study_data *); -extern int _pcre_ucp_findprop(const unsigned int, int *, int *); -extern int _pcre_ucp_othercase(const int); -extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_xclass(int, const uschar *); +extern BOOL _pcre_is_newline(const uschar *, int, const uschar *, + int *, BOOL); +extern int _pcre_ord2utf8(int, uschar *); +extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *, + const pcre_study_data *, pcre_study_data *); +extern int _pcre_ucp_findprop(const unsigned int, int *, int *); +extern unsigned int _pcre_ucp_othercase(const unsigned int); +extern int _pcre_valid_utf8(const uschar *, int); +extern BOOL _pcre_was_newline(const uschar *, int, const uschar *, + int *, BOOL); +extern BOOL _pcre_xclass(int, const uschar *); #endif diff --git a/libpcre/pcre_maketables.c b/libpcre/pcre_maketables.c index afe63d1b1..9963e13fb 100644 --- a/libpcre/pcre_maketables.c +++ b/libpcre/pcre_maketables.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -130,7 +130,7 @@ for (i = 0; i < 256; i++) meta-character, which in this sense is any character that terminates a run of data characters. */ - if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; + if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta; *p++ = x; } diff --git a/libpcre/pcre_newline.c b/libpcre/pcre_newline.c new file mode 100644 index 000000000..ae66c730f --- /dev/null +++ b/libpcre/pcre_newline.c @@ -0,0 +1,156 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2007 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains internal functions for testing newlines when more than +one kind of newline is to be recognized. When a newline is found, its length is +returned. In principle, we could implement several newline "types", each +referring to a different set of newline characters. At present, PCRE supports +only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, +and NLTYPE_ANY. The full list of Unicode newline characters is taken from +http://unicode.org/unicode/reports/tr18/. */ + + +#include "pcre_internal.h" + + + +/************************************************* +* Check for newline at given position * +*************************************************/ + +/* It is guaranteed that the initial value of ptr is less than the end of the +string that is being processed. + +Arguments: + ptr pointer to possible newline + type the newline type + endptr pointer to the end of the string + lenptr where to return the length + utf8 TRUE if in utf8 mode + +Returns: TRUE or FALSE +*/ + +BOOL +_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr, + int *lenptr, BOOL utf8) +{ +int c; +if (utf8) { GETCHAR(c, ptr); } else c = *ptr; + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case 0x000a: *lenptr = 1; return TRUE; /* LF */ + case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; + return TRUE; /* CR */ + default: return FALSE; + } + +/* NLTYPE_ANY */ + +else switch(c) + { + case 0x000a: /* LF */ + case 0x000b: /* VT */ + case 0x000c: *lenptr = 1; return TRUE; /* FF */ + case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; + return TRUE; /* CR */ + case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ + case 0x2028: /* LS */ + case 0x2029: *lenptr = 3; return TRUE; /* PS */ + default: return FALSE; + } +} + + + +/************************************************* +* Check for newline at previous position * +*************************************************/ + +/* It is guaranteed that the initial value of ptr is greater than the start of +the string that is being processed. + +Arguments: + ptr pointer to possible newline + type the newline type + startptr pointer to the start of the string + lenptr where to return the length + utf8 TRUE if in utf8 mode + +Returns: TRUE or FALSE +*/ + +BOOL +_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr, + int *lenptr, BOOL utf8) +{ +int c; +ptr--; +if (utf8) + { + BACKCHAR(ptr); + GETCHAR(c, ptr); + } +else c = *ptr; + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; + return TRUE; /* LF */ + case 0x000d: *lenptr = 1; return TRUE; /* CR */ + default: return FALSE; + } + +else switch(c) + { + case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; + return TRUE; /* LF */ + case 0x000b: /* VT */ + case 0x000c: /* FF */ + case 0x000d: *lenptr = 1; return TRUE; /* CR */ + case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ + case 0x2028: /* LS */ + case 0x2029: *lenptr = 3; return TRUE; /* PS */ + default: return FALSE; + } +} + +/* End of pcre_newline.c */ diff --git a/libpcre/pcre_ord2utf8.c b/libpcre/pcre_ord2utf8.c new file mode 100644 index 000000000..a72761285 --- /dev/null +++ b/libpcre/pcre_ord2utf8.c @@ -0,0 +1,82 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2007 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This file contains a private PCRE function that converts an ordinal +character value into a UTF8 string. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Convert character value to UTF-8 * +*************************************************/ + +/* This function takes an integer value in the range 0 - 0x7fffffff +and encodes it as a UTF-8 character in 0 to 6 bytes. + +Arguments: + cvalue the character value + buffer pointer to buffer for result - at least 6 bytes long + +Returns: number of characters placed in the buffer +*/ + +int +_pcre_ord2utf8(int cvalue, uschar *buffer) +{ +#ifdef SUPPORT_UTF8 +register int i, j; +for (i = 0; i < _pcre_utf8_table1_size; i++) + if (cvalue <= _pcre_utf8_table1[i]) break; +buffer += i; +for (j = i; j > 0; j--) + { + *buffer-- = 0x80 | (cvalue & 0x3f); + cvalue >>= 6; + } +*buffer = _pcre_utf8_table2[i] | cvalue; +return i + 1; +#else +return 0; /* Keep compiler happy; this function won't ever be */ +#endif /* called when SUPPORT_UTF8 is not defined. */ +} + +/* End of pcre_ord2utf8.c */ diff --git a/libpcre/pcre_refcount.c b/libpcre/pcre_refcount.c index e6965812e..8339019db 100644 --- a/libpcre/pcre_refcount.c +++ b/libpcre/pcre_refcount.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -63,7 +63,7 @@ Returns: the (possibly updated) count value (a non-negative number), or a negative error number */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_refcount(pcre *argument_re, int adjust) { real_pcre *re = (real_pcre *)argument_re; diff --git a/libpcre/pcre_study.c b/libpcre/pcre_study.c index 5091324ae..3cf5b5954 100644 --- a/libpcre/pcre_study.c +++ b/libpcre/pcre_study.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -45,6 +45,11 @@ supporting functions. */ #include "pcre_internal.h" +/* Returns from set_start_bits() */ + +enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE }; + + /************************************************* * Set a bit and maybe its alternate case * *************************************************/ @@ -72,12 +77,16 @@ if (caseless && (cd->ctypes[c] & ctype_letter) != 0) /************************************************* -* Create bitmap of starting chars * +* Create bitmap of starting bytes * *************************************************/ -/* This function scans a compiled unanchored expression and attempts to build a -bitmap of the set of initial characters. If it can't, it returns FALSE. As time -goes by, we may be able to get more clever at doing this. +/* This function scans a compiled unanchored expression recursively and +attempts to build a bitmap of the set of possible starting bytes. As time goes +by, we may be able to get more clever at doing this. The SSB_CONTINUE return is +useful for parenthesized groups in patterns such as (a*)b where the group +provides some optional starting bytes but scanning must continue at the outer +level to find at least one mandatory byte. At the outermost level, this +function fails unless the result is SSB_DONE. Arguments: code points to an expression @@ -86,14 +95,17 @@ Arguments: utf8 TRUE if in UTF-8 mode cd the block with char table pointers -Returns: TRUE if table built, FALSE otherwise +Returns: SSB_FAIL => Failed to find any starting bytes + SSB_DONE => Found mandatory starting bytes + SSB_CONTINUE => Found optional starting bytes */ -static BOOL +static int set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, BOOL utf8, compile_data *cd) { register int c; +int yield = SSB_DONE; #if 0 /* ========================================================================= */ @@ -114,25 +126,55 @@ volatile int dummy; do { - const uschar *tcode = code + 1 + LINK_SIZE; + const uschar *tcode = code + (((int)*code == OP_CBRA)? 3:1) + LINK_SIZE; BOOL try_next = TRUE; - while (try_next) + while (try_next) /* Loop for items in this branch */ { - /* If a branch starts with a bracket or a positive lookahead assertion, - recurse to set bits from within them. That's all for this branch. */ - - if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT) + int rc; + switch(*tcode) { - if (!set_start_bits(tcode, start_bits, caseless, utf8, cd)) - return FALSE; - try_next = FALSE; - } + /* Fail if we reach something we don't understand */ - else switch(*tcode) - { default: - return FALSE; + return SSB_FAIL; + + /* If we hit a bracket or a positive lookahead assertion, recurse to set + bits from within the subpattern. If it can't find anything, we have to + give up. If it finds some mandatory character(s), we are done for this + branch. Otherwise, carry on scanning after the subpattern. */ + + case OP_BRA: + case OP_SBRA: + case OP_CBRA: + case OP_SCBRA: + case OP_ONCE: + case OP_ASSERT: + rc = set_start_bits(tcode, start_bits, caseless, utf8, cd); + if (rc == SSB_FAIL) return SSB_FAIL; + if (rc == SSB_DONE) try_next = FALSE; else + { + do tcode += GET(tcode, 1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; + } + break; + + /* If we hit ALT or KET, it means we haven't found anything mandatory in + this branch, though we might have found something optional. For ALT, we + continue with the next alternative, but we have to arrange that the final + result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET, + return SSB_CONTINUE: if this is the top level, that indicates failure, + but after a nested subpattern, it causes scanning to continue. */ + + case OP_ALT: + yield = SSB_CONTINUE; + try_next = FALSE; + break; + + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + return SSB_CONTINUE; /* Skip over callout */ @@ -140,19 +182,13 @@ do tcode += 2 + 2*LINK_SIZE; break; - /* Skip over extended extraction bracket number */ - - case OP_BRANUMBER: - tcode += 3; - break; - /* Skip over lookbehind and negative lookahead assertions */ case OP_ASSERT_NOT: case OP_ASSERTBACK: case OP_ASSERTBACK_NOT: do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1+LINK_SIZE; + tcode += 1 + LINK_SIZE; break; /* Skip over an option setting, changing the caseless flag */ @@ -166,27 +202,30 @@ do case OP_BRAZERO: case OP_BRAMINZERO: - if (!set_start_bits(++tcode, start_bits, caseless, utf8, cd)) - return FALSE; + if (set_start_bits(++tcode, start_bits, caseless, utf8, cd) == SSB_FAIL) + return SSB_FAIL; /* ========================================================================= See the comment at the head of this function concerning the next line, which was an old fudge for the benefit of OS/2. dummy = 1; ========================================================================= */ do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1+LINK_SIZE; + tcode += 1 + LINK_SIZE; break; /* Single-char * or ? sets the bit and tries the next item */ case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: set_bit(start_bits, tcode[1], caseless, cd); tcode += 2; #ifdef SUPPORT_UTF8 - if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; + if (utf8 && tcode[-1] >= 0xc0) + tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; #endif break; @@ -194,10 +233,12 @@ do case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: set_bit(start_bits, tcode[3], caseless, cd); tcode += 4; #ifdef SUPPORT_UTF8 - if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; + if (utf8 && tcode[-1] >= 0xc0) + tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; #endif break; @@ -210,6 +251,7 @@ do case OP_CHARNC: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: set_bit(start_bits, tcode[1], caseless, cd); try_next = FALSE; break; @@ -283,16 +325,19 @@ do case OP_TYPEUPTO: case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: tcode += 2; /* Fall through */ case OP_TYPESTAR: case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: case OP_TYPEQUERY: case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: switch(tcode[1]) { case OP_ANY: - return FALSE; + return SSB_FAIL; case OP_NOT_DIGIT: for (c = 0; c < 32; c++) @@ -349,11 +394,13 @@ do character with a value > 255. */ case OP_NCLASS: +#ifdef SUPPORT_UTF8 if (utf8) { start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ } +#endif /* Fall through */ case OP_CLASS: @@ -366,6 +413,7 @@ do value is > 127. In fact, there are only two possible starting bytes for characters in the range 128 - 255. */ +#ifdef SUPPORT_UTF8 if (utf8) { for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; @@ -383,6 +431,7 @@ do /* In non-UTF-8 mode, the two bit maps are completely compatible. */ else +#endif { for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; } @@ -418,7 +467,7 @@ do code += GET(code, 1); /* Advance to next branch */ } while (*code == OP_ALT); -return TRUE; +return yield; } @@ -442,7 +491,7 @@ Returns: pointer to a pcre_extra block, with study_data filled in and the NULL on error or if no optimization possible */ -PCRE_DATA_SCOPE pcre_extra * +PCRE_EXP_DEFN pcre_extra * pcre_study(const pcre *external_re, int options, const char **errorptr) { uschar start_bits[32]; @@ -492,8 +541,8 @@ compile_block.ctypes = tables + ctypes_offset; /* See if we can find a fixed set of initial characters for the pattern. */ memset(start_bits, 0, 32 * sizeof(uschar)); -if (!set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, - (re->options & PCRE_UTF8) != 0, &compile_block)) return NULL; +if (set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, + (re->options & PCRE_UTF8) != 0, &compile_block) != SSB_DONE) return NULL; /* Get a pcre_extra block and a pcre_study_data block. The study data is put in the latter, which is pointed to by the former, which may also get additional diff --git a/libpcre/pcre_tables.c b/libpcre/pcre_tables.c index 480257cab..3e36c931a 100644 --- a/libpcre/pcre_tables.c +++ b/libpcre/pcre_tables.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -61,6 +61,8 @@ const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; /* These are the breakpoints for different numbers of bytes in a UTF-8 character. */ +#ifdef SUPPORT_UTF8 + const int _pcre_utf8_table1[] = { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; @@ -72,9 +74,8 @@ first byte of a character, indexed by the number of additional bytes. */ const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; -/* Table of the number of extra characters, indexed by the first character -masked with 0x3f. The highest number for a valid UTF-8 character is in fact -0x3d. */ +/* Table of the number of extra bytes, indexed by the first byte masked with +0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ const uschar _pcre_utf8_table4[] = { 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, @@ -89,6 +90,7 @@ const ucp_type_table _pcre_utt[] = { { "Any", PT_ANY, 0 }, { "Arabic", PT_SC, ucp_Arabic }, { "Armenian", PT_SC, ucp_Armenian }, + { "Balinese", PT_SC, ucp_Balinese }, { "Bengali", PT_SC, ucp_Bengali }, { "Bopomofo", PT_SC, ucp_Bopomofo }, { "Braille", PT_SC, ucp_Braille }, @@ -104,6 +106,7 @@ const ucp_type_table _pcre_utt[] = { { "Common", PT_SC, ucp_Common }, { "Coptic", PT_SC, ucp_Coptic }, { "Cs", PT_PC, ucp_Cs }, + { "Cuneiform", PT_SC, ucp_Cuneiform }, { "Cypriot", PT_SC, ucp_Cypriot }, { "Cyrillic", PT_SC, ucp_Cyrillic }, { "Deseret", PT_SC, ucp_Deseret }, @@ -146,6 +149,7 @@ const ucp_type_table _pcre_utt[] = { { "N", PT_GC, ucp_N }, { "Nd", PT_PC, ucp_Nd }, { "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue }, + { "Nko", PT_SC, ucp_Nko }, { "Nl", PT_PC, ucp_Nl }, { "No", PT_PC, ucp_No }, { "Ogham", PT_SC, ucp_Ogham }, @@ -158,6 +162,8 @@ const ucp_type_table _pcre_utt[] = { { "Pd", PT_PC, ucp_Pd }, { "Pe", PT_PC, ucp_Pe }, { "Pf", PT_PC, ucp_Pf }, + { "Phags_Pa", PT_SC, ucp_Phags_Pa }, + { "Phoenician", PT_SC, ucp_Phoenician }, { "Pi", PT_PC, ucp_Pi }, { "Po", PT_PC, ucp_Po }, { "Ps", PT_PC, ucp_Ps }, @@ -190,4 +196,6 @@ const ucp_type_table _pcre_utt[] = { const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); +#endif /* SUPPORT_UTF8 */ + /* End of pcre_tables.c */ diff --git a/libpcre/pcre_try_flipped.c b/libpcre/pcre_try_flipped.c index 00c94fccf..cd45968a4 100644 --- a/libpcre/pcre_try_flipped.c +++ b/libpcre/pcre_try_flipped.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without diff --git a/libpcre/pcre_ucp_searchfuncs.c b/libpcre/pcre_ucp_searchfuncs.c new file mode 100644 index 000000000..5ecba6b1f --- /dev/null +++ b/libpcre/pcre_ucp_searchfuncs.c @@ -0,0 +1,175 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2007 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains code for searching the table of Unicode character +properties. */ + +#include "pcre_internal.h" + +#include "ucp.h" /* Category definitions */ +#include "ucpinternal.h" /* Internal table details */ +#include "ucptable.h" /* The table itself */ + + +/* Table to translate from particular type value to the general value. */ + +static const int ucp_gentype[] = { + ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ + ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ + ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ + ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ + ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ + ucp_P, ucp_P, /* Ps, Po */ + ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ + ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ +}; + + + +/************************************************* +* Search table and return type * +*************************************************/ + +/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed +character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc. + +Arguments: + c the character value + type_ptr the detailed character type is returned here + script_ptr the script is returned here + +Returns: the character type category +*/ + +int +_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr) +{ +int bot = 0; +int top = sizeof(ucp_table)/sizeof(cnode); +int mid; + +/* The table is searched using a binary chop. You might think that using +intermediate variables to hold some of the common expressions would speed +things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it +makes things a lot slower. */ + +for (;;) + { + if (top <= bot) + { + *type_ptr = ucp_Cn; + *script_ptr = ucp_Common; + return ucp_C; + } + mid = (bot + top) >> 1; + if (c == (ucp_table[mid].f0 & f0_charmask)) break; + if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; + else + { + if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && + c <= (ucp_table[mid].f0 & f0_charmask) + + (ucp_table[mid].f1 & f1_rangemask)) break; + bot = mid + 1; + } + } + +/* Found an entry in the table. Set the script and detailed type values, and +return the general type. */ + +*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift; +*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift; + +return ucp_gentype[*type_ptr]; +} + + + +/************************************************* +* Search table and return other case * +*************************************************/ + +/* If the given character is a letter, and there is another case for the +letter, return the other case. Otherwise, return -1. + +Arguments: + c the character value + +Returns: the other case or NOTACHAR if none +*/ + +unsigned int +_pcre_ucp_othercase(const unsigned int c) +{ +int bot = 0; +int top = sizeof(ucp_table)/sizeof(cnode); +int mid, offset; + +/* The table is searched using a binary chop. You might think that using +intermediate variables to hold some of the common expressions would speed +things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it +makes things a lot slower. */ + +for (;;) + { + if (top <= bot) return -1; + mid = (bot + top) >> 1; + if (c == (ucp_table[mid].f0 & f0_charmask)) break; + if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; + else + { + if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && + c <= (ucp_table[mid].f0 & f0_charmask) + + (ucp_table[mid].f1 & f1_rangemask)) break; + bot = mid + 1; + } + } + +/* Found an entry in the table. Return NOTACHAR for a range entry. Otherwise +return the other case if there is one, else NOTACHAR. */ + +if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return NOTACHAR; + +offset = ucp_table[mid].f1 & f1_casemask; +if ((offset & f1_caseneg) != 0) offset |= f1_caseneg; +return (offset == 0)? NOTACHAR : c + offset; +} + + +/* End of pcre_ucp_searchfuncs.c */ diff --git a/libpcre/pcre_valid_utf8.c b/libpcre/pcre_valid_utf8.c new file mode 100644 index 000000000..9a35a202e --- /dev/null +++ b/libpcre/pcre_valid_utf8.c @@ -0,0 +1,132 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2007 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function for validating UTF-8 character +strings. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Validate a UTF-8 string * +*************************************************/ + +/* This function is called (optionally) at the start of compile or match, to +validate that a supposed UTF-8 string is actually valid. The early check means +that subsequent code can assume it is dealing with a valid string. The check +can be turned off for maximum performance, but the consequences of supplying +an invalid string are then undefined. + +Arguments: + string points to the string + length length of string, or -1 if the string is zero-terminated + +Returns: < 0 if the string is a valid UTF-8 string + >= 0 otherwise; the value is the offset of the bad byte +*/ + +int +_pcre_valid_utf8(const uschar *string, int length) +{ +#ifdef SUPPORT_UTF8 +register const uschar *p; + +if (length < 0) + { + for (p = string; *p != 0; p++); + length = p - string; + } + +for (p = string; length-- > 0; p++) + { + register int ab; + register int c = *p; + if (c < 128) continue; + if (c < 0xc0) return p - string; + ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ + if (length < ab) return p - string; + length -= ab; + + /* Check top bits in the second byte */ + if ((*(++p) & 0xc0) != 0x80) return p - string; + + /* Check for overlong sequences for each different length */ + switch (ab) + { + /* Check for xx00 000x */ + case 1: + if ((c & 0x3e) == 0) return p - string; + continue; /* We know there aren't any more bytes to check */ + + /* Check for 1110 0000, xx0x xxxx */ + case 2: + if (c == 0xe0 && (*p & 0x20) == 0) return p - string; + break; + + /* Check for 1111 0000, xx00 xxxx */ + case 3: + if (c == 0xf0 && (*p & 0x30) == 0) return p - string; + break; + + /* Check for 1111 1000, xx00 0xxx */ + case 4: + if (c == 0xf8 && (*p & 0x38) == 0) return p - string; + break; + + /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */ + case 5: + if (c == 0xfe || c == 0xff || + (c == 0xfc && (*p & 0x3c) == 0)) return p - string; + break; + } + + /* Check for valid bytes after the 2nd, if any; all must start 10 */ + while (--ab > 0) + { + if ((*(++p) & 0xc0) != 0x80) return p - string; + } + } +#endif + +return -1; +} + +/* End of pcre_valid_utf8.c */ diff --git a/libpcre/pcre_version.c b/libpcre/pcre_version.c index c2aad4da0..1a9ecb2c5 100644 --- a/libpcre/pcre_version.c +++ b/libpcre/pcre_version.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -49,16 +49,38 @@ string that identifies the PCRE version that is in use. */ * Return version string * *************************************************/ +/* These macros are the standard way of turning unquoted text into C strings. +They allow macros like PCRE_MAJOR to be defined without quotes, which is +convenient for user programs that want to test its value. */ + #define STRING(a) # a #define XSTRING(s) STRING(s) -PCRE_DATA_SCOPE const char * +/* A problem turned up with PCRE_PRERELEASE, which is defined empty for +production releases. Originally, it was used naively in this code: + + return XSTRING(PCRE_MAJOR) + "." XSTRING(PCRE_MINOR) + XSTRING(PCRE_PRERELEASE) + " " XSTRING(PCRE_DATE); + +However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of +STRING(). The C standard states: "If (before argument substitution) any +argument consists of no preprocessing tokens, the behavior is undefined." It +turns out the gcc treats this case as a single empty string - which is what we +really want - but Visual C grumbles about the lack of an argument for the +macro. Unfortunately, both are within their rights. To cope with both ways of +handling this, I had resort to some messy hackery that does a test at run time. +I could find no way of detecting that a macro is defined as an empty string at +pre-processor time. This hack uses a standard trick for avoiding calling +the STRING macro with an empty argument when doing the test. */ + +PCRE_EXP_DEFN const char * pcre_version(void) { -return XSTRING(PCRE_MAJOR) - "." XSTRING(PCRE_MINOR) - XSTRING(PCRE_PRERELEASE) - " " XSTRING(PCRE_DATE); +return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? + XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) : + XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE); } /* End of pcre_version.c */ diff --git a/libpcre/pcre_xclass.c b/libpcre/pcre_xclass.c index 57c514b78..0b333515f 100644 --- a/libpcre/pcre_xclass.c +++ b/libpcre/pcre_xclass.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without diff --git a/libpcre/pcreposix.c b/libpcre/pcreposix.c index 79397f029..8582fba09 100644 --- a/libpcre/pcreposix.c +++ b/libpcre/pcreposix.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -78,9 +78,9 @@ static const int eint[] = { REG_BADPAT, /* unrecognized character after (?< */ REG_BADPAT, /* lookbehind assertion is not fixed length */ REG_BADPAT, /* malformed number or name after (?( */ - REG_BADPAT, /* conditional group containe more than two branches */ + REG_BADPAT, /* conditional group contains more than two branches */ REG_BADPAT, /* assertion expected after (?( */ - REG_BADPAT, /* (?R or (?digits must be followed by ) */ + REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */ REG_ECTYPE, /* unknown POSIX class name */ REG_BADPAT, /* POSIX collating elements are not supported */ REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ @@ -93,7 +93,7 @@ static const int eint[] = { REG_BADPAT, /* closing ) for (?C expected */ REG_BADPAT, /* recursive call could loop indefinitely */ REG_BADPAT, /* unrecognized character after (?P */ - REG_BADPAT, /* syntax error after (?P */ + REG_BADPAT, /* syntax error in subpattern name (missing terminator) */ REG_BADPAT, /* two named subpatterns have the same name */ REG_BADPAT, /* invalid UTF-8 string */ REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ @@ -102,7 +102,14 @@ static const int eint[] = { REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ REG_BADPAT, /* repeated subpattern is too long */ - REG_BADPAT /* octal value is greater than \377 (not in UTF-8 mode) */ + REG_BADPAT, /* octal value is greater than \377 (not in UTF-8 mode) */ + REG_BADPAT, /* internal error: overran compiling workspace */ + REG_BADPAT, /* internal error: previously-checked referenced subpattern not found */ + REG_BADPAT, /* DEFINE group contains more than one branch */ + REG_BADPAT, /* repeating a DEFINE group is not allowed */ + REG_INVARG, /* inconsistent NEWLINE options */ + REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ + REG_BADPAT /* (?+ or (?- must be followed by a non-zero number */ }; /* Table of texts corresponding to POSIX error codes */ @@ -135,7 +142,7 @@ static const char *const pstring[] = { * Translate error code to string * *************************************************/ -PCRE_DATA_SCOPE size_t +PCREPOSIX_EXP_DEFN size_t regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) { const char *message, *addmessage; @@ -170,7 +177,7 @@ return length + addlength; * Free store held by a regex * *************************************************/ -PCRE_DATA_SCOPE void +PCREPOSIX_EXP_DEFN void regfree(regex_t *preg) { (pcre_free)(preg->re_pcre); @@ -193,7 +200,7 @@ Returns: 0 on success various non-zero codes on failure */ -PCRE_DATA_SCOPE int +PCREPOSIX_EXP_DEFN int regcomp(regex_t *preg, const char *pattern, int cflags) { const char *errorptr; @@ -201,9 +208,9 @@ int erroffset; int errorcode; int options = 0; -if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; +if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; -if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; +if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; if ((cflags & REG_NOSUB) != 0) options |= PCRE_NO_AUTO_CAPTURE; if ((cflags & REG_UTF8) != 0) options |= PCRE_UTF8; @@ -235,7 +242,7 @@ If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will be set. When this is the case, the nmatch and pmatch arguments are ignored, and the only result is yes/no/error. */ -PCRE_DATA_SCOPE int +PCREPOSIX_EXP_DEFN int regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags) { @@ -282,13 +289,13 @@ if (rc >= 0) size_t i; if (!nosub) { - for (i = 0; i < (size_t)rc; i++) - { - pmatch[i].rm_so = ovector[i*2]; - pmatch[i].rm_eo = ovector[i*2+1]; - } - if (allocated_ovector) free(ovector); - for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; + for (i = 0; i < (size_t)rc; i++) + { + pmatch[i].rm_so = ovector[i*2]; + pmatch[i].rm_eo = ovector[i*2+1]; + } + if (allocated_ovector) free(ovector); + for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; } return 0; } diff --git a/libpcre/pcreposix.h b/libpcre/pcreposix.h index 31ee03749..1a7de125f 100644 --- a/libpcre/pcreposix.h +++ b/libpcre/pcreposix.h @@ -9,7 +9,7 @@ Compatible Regular Expression library. It defines the things POSIX says should be there. I hope. - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -105,40 +105,38 @@ typedef struct { regoff_t rm_eo; } regmatch_t; -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. */ +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export settings are needed. */ -#ifndef PCRE_DATA_SCOPE +/* #ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else -# ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) -# endif +# ifndef PCREPOSIX_STATIC +# define PCREPOSIX_EXP_DECL extern __declspec(dllimport) +# define PCREPOSIX_EXP_DEFN __declspec(dllimport) # endif #endif -#endif +*/ -/* Otherwise, we use the standard "extern". */ +/* By default, we use the standard "extern" declarations. */ -#ifndef PCRE_DATA_SCOPE +#ifndef PCREPOSIX_EXP_DECL # ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" +# define PCREPOSIX_EXP_DECL extern "C" +# define PCREPOSIX_EXP_DEFN extern "C" # else -# define PCRE_DATA_SCOPE extern +# define PCREPOSIX_EXP_DECL extern +# define PCREPOSIX_EXP_DEFN extern # endif #endif /* The functions */ -PCRE_DATA_SCOPE int regcomp(regex_t *, const char *, int); -PCRE_DATA_SCOPE int regexec(const regex_t *, const char *, size_t, - regmatch_t *, int); -PCRE_DATA_SCOPE size_t regerror(int, const regex_t *, char *, size_t); -PCRE_DATA_SCOPE void regfree(regex_t *); +PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int); +PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, + regmatch_t *, int); +PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); +PCREPOSIX_EXP_DECL void regfree(regex_t *); #ifdef __cplusplus } /* extern "C" */ diff --git a/libpcre/ucp.h b/libpcre/ucp.h index 1ca23c9c1..3a4179b76 100644 --- a/libpcre/ucp.h +++ b/libpcre/ucp.h @@ -6,7 +6,9 @@ #define _UCP_H /* This file contains definitions of the property values that are returned by -the function _pcre_ucp_findprop(). */ +the function _pcre_ucp_findprop(). New values that are added for new releases +of Unicode should always be at the end of each enum, for backwards +compatibility. */ /* These are the general character categories. */ @@ -118,7 +120,12 @@ enum { ucp_Tibetan, ucp_Tifinagh, ucp_Ugaritic, - ucp_Yi + ucp_Yi, + ucp_Balinese, /* New for Unicode 5.0.0 */ + ucp_Cuneiform, /* New for Unicode 5.0.0 */ + ucp_Nko, /* New for Unicode 5.0.0 */ + ucp_Phags_Pa, /* New for Unicode 5.0.0 */ + ucp_Phoenician /* New for Unicode 5.0.0 */ }; #endif diff --git a/libpcre/ucpinternal.h b/libpcre/ucpinternal.h new file mode 100644 index 000000000..811a373c8 --- /dev/null +++ b/libpcre/ucpinternal.h @@ -0,0 +1,92 @@ +/************************************************* +* Unicode Property Table handler * +*************************************************/ + +#ifndef _UCPINTERNAL_H +#define _UCPINTERNAL_H + +/* Internal header file defining the layout of the bits in each pair of 32-bit +words that form a data item in the table. */ + +typedef struct cnode { + pcre_uint32 f0; + pcre_uint32 f1; +} cnode; + +/* Things for the f0 field */ + +#define f0_scriptmask 0xff000000 /* Mask for script field */ +#define f0_scriptshift 24 /* Shift for script value */ +#define f0_rangeflag 0x00f00000 /* Flag for a range item */ +#define f0_charmask 0x001fffff /* Mask for code point value */ + +/* Things for the f1 field */ + +#define f1_typemask 0xfc000000 /* Mask for char type field */ +#define f1_typeshift 26 /* Shift for the type field */ +#define f1_rangemask 0x0000ffff /* Mask for a range offset */ +#define f1_casemask 0x0000ffff /* Mask for a case offset */ +#define f1_caseneg 0xffff8000 /* Bits for negation */ + +/* The data consists of a vector of structures of type cnode. The two unsigned +32-bit integers are used as follows: + +(f0) (1) The most significant byte holds the script number. The numbers are + defined by the enum in ucp.h. + + (2) The 0x00800000 bit is set if this entry defines a range of characters. + It is not set if this entry defines a single character + + (3) The 0x00600000 bits are spare. + + (4) The 0x001fffff bits contain the code point. No Unicode code point will + ever be greater than 0x0010ffff, so this should be OK for ever. + +(f1) (1) The 0xfc000000 bits contain the character type number. The numbers are + defined by an enum in ucp.h. + + (2) The 0x03ff0000 bits are spare. + + (3) The 0x0000ffff bits contain EITHER the unsigned offset to the top of + range if this entry defines a range, OR the *signed* offset to the + character's "other case" partner if this entry defines a single + character. There is no partner if the value is zero. + +------------------------------------------------------------------------------- +| script (8) |.|.|.| codepoint (21) || type (6) |.|.| spare (8) | offset (16) | +------------------------------------------------------------------------------- + | | | | | + | | |-> spare | |-> spare + | | | + | |-> spare |-> spare + | + |-> range flag + +The upper/lower casing information is set only for characters that come in +pairs. The non-one-to-one mappings in the Unicode data are ignored. + +When searching the data, proceed as follows: + +(1) Set up for a binary chop search. + +(2) If the top is not greater than the bottom, the character is not in the + table. Its type must therefore be "Cn" ("Undefined"). + +(3) Find the middle vector element. + +(4) Extract the code point and compare. If equal, we are done. + +(5) If the test character is smaller, set the top to the current point, and + goto (2). + +(6) If the current entry defines a range, compute the last character by adding + the offset, and see if the test character is within the range. If it is, + we are done. + +(7) Otherwise, set the bottom to one element past the current point and goto + (2). +*/ + +#endif /* _UCPINTERNAL_H */ + +/* End of ucpinternal.h */ diff --git a/libpcre/ucptable.h b/libpcre/ucptable.h new file mode 100644 index 000000000..07eaced8f --- /dev/null +++ b/libpcre/ucptable.h @@ -0,0 +1,3068 @@ +/* This source module is automatically generated from the Unicode +property table. See ucpinternal.h for a description of the layout. +This version was made from the Unicode 5.0.0 tables. */ + +static const cnode ucp_table[] = { + { 0x09800000, 0x0000001f }, + { 0x09000020, 0x74000000 }, + { 0x09800021, 0x54000002 }, + { 0x09000024, 0x5c000000 }, + { 0x09800025, 0x54000002 }, + { 0x09000028, 0x58000000 }, + { 0x09000029, 0x48000000 }, + { 0x0900002a, 0x54000000 }, + { 0x0900002b, 0x64000000 }, + { 0x0900002c, 0x54000000 }, + { 0x0900002d, 0x44000000 }, + { 0x0980002e, 0x54000001 }, + { 0x09800030, 0x34000009 }, + { 0x0980003a, 0x54000001 }, + { 0x0980003c, 0x64000002 }, + { 0x0980003f, 0x54000001 }, + { 0x21000041, 0x24000020 }, + { 0x21000042, 0x24000020 }, + { 0x21000043, 0x24000020 }, + { 0x21000044, 0x24000020 }, + { 0x21000045, 0x24000020 }, + { 0x21000046, 0x24000020 }, + { 0x21000047, 0x24000020 }, + { 0x21000048, 0x24000020 }, + { 0x21000049, 0x24000020 }, + { 0x2100004a, 0x24000020 }, + { 0x2100004b, 0x24000020 }, + { 0x2100004c, 0x24000020 }, + { 0x2100004d, 0x24000020 }, + { 0x2100004e, 0x24000020 }, + { 0x2100004f, 0x24000020 }, + { 0x21000050, 0x24000020 }, + { 0x21000051, 0x24000020 }, + { 0x21000052, 0x24000020 }, + { 0x21000053, 0x24000020 }, + { 0x21000054, 0x24000020 }, + { 0x21000055, 0x24000020 }, + { 0x21000056, 0x24000020 }, + { 0x21000057, 0x24000020 }, + { 0x21000058, 0x24000020 }, + { 0x21000059, 0x24000020 }, + { 0x2100005a, 0x24000020 }, + { 0x0900005b, 0x58000000 }, + { 0x0900005c, 0x54000000 }, + { 0x0900005d, 0x48000000 }, + { 0x0900005e, 0x60000000 }, + { 0x0900005f, 0x40000000 }, + { 0x09000060, 0x60000000 }, + { 0x21000061, 0x1400ffe0 }, + { 0x21000062, 0x1400ffe0 }, + { 0x21000063, 0x1400ffe0 }, + { 0x21000064, 0x1400ffe0 }, + { 0x21000065, 0x1400ffe0 }, + { 0x21000066, 0x1400ffe0 }, + { 0x21000067, 0x1400ffe0 }, + { 0x21000068, 0x1400ffe0 }, + { 0x21000069, 0x1400ffe0 }, + { 0x2100006a, 0x1400ffe0 }, + { 0x2100006b, 0x1400ffe0 }, + { 0x2100006c, 0x1400ffe0 }, + { 0x2100006d, 0x1400ffe0 }, + { 0x2100006e, 0x1400ffe0 }, + { 0x2100006f, 0x1400ffe0 }, + { 0x21000070, 0x1400ffe0 }, + { 0x21000071, 0x1400ffe0 }, + { 0x21000072, 0x1400ffe0 }, + { 0x21000073, 0x1400ffe0 }, + { 0x21000074, 0x1400ffe0 }, + { 0x21000075, 0x1400ffe0 }, + { 0x21000076, 0x1400ffe0 }, + { 0x21000077, 0x1400ffe0 }, + { 0x21000078, 0x1400ffe0 }, + { 0x21000079, 0x1400ffe0 }, + { 0x2100007a, 0x1400ffe0 }, + { 0x0900007b, 0x58000000 }, + { 0x0900007c, 0x64000000 }, + { 0x0900007d, 0x48000000 }, + { 0x0900007e, 0x64000000 }, + { 0x0980007f, 0x00000020 }, + { 0x090000a0, 0x74000000 }, + { 0x090000a1, 0x54000000 }, + { 0x098000a2, 0x5c000003 }, + { 0x098000a6, 0x68000001 }, + { 0x090000a8, 0x60000000 }, + { 0x090000a9, 0x68000000 }, + { 0x210000aa, 0x14000000 }, + { 0x090000ab, 0x50000000 }, + { 0x090000ac, 0x64000000 }, + { 0x090000ad, 0x04000000 }, + { 0x090000ae, 0x68000000 }, + { 0x090000af, 0x60000000 }, + { 0x090000b0, 0x68000000 }, + { 0x090000b1, 0x64000000 }, + { 0x098000b2, 0x3c000001 }, + { 0x090000b4, 0x60000000 }, + { 0x090000b5, 0x140002e7 }, + { 0x090000b6, 0x68000000 }, + { 0x090000b7, 0x54000000 }, + { 0x090000b8, 0x60000000 }, + { 0x090000b9, 0x3c000000 }, + { 0x210000ba, 0x14000000 }, + { 0x090000bb, 0x4c000000 }, + { 0x098000bc, 0x3c000002 }, + { 0x090000bf, 0x54000000 }, + { 0x210000c0, 0x24000020 }, + { 0x210000c1, 0x24000020 }, + { 0x210000c2, 0x24000020 }, + { 0x210000c3, 0x24000020 }, + { 0x210000c4, 0x24000020 }, + { 0x210000c5, 0x24000020 }, + { 0x210000c6, 0x24000020 }, + { 0x210000c7, 0x24000020 }, + { 0x210000c8, 0x24000020 }, + { 0x210000c9, 0x24000020 }, + { 0x210000ca, 0x24000020 }, + { 0x210000cb, 0x24000020 }, + { 0x210000cc, 0x24000020 }, + { 0x210000cd, 0x24000020 }, + { 0x210000ce, 0x24000020 }, + { 0x210000cf, 0x24000020 }, + { 0x210000d0, 0x24000020 }, + { 0x210000d1, 0x24000020 }, + { 0x210000d2, 0x24000020 }, + { 0x210000d3, 0x24000020 }, + { 0x210000d4, 0x24000020 }, + { 0x210000d5, 0x24000020 }, + { 0x210000d6, 0x24000020 }, + { 0x090000d7, 0x64000000 }, + { 0x210000d8, 0x24000020 }, + { 0x210000d9, 0x24000020 }, + { 0x210000da, 0x24000020 }, + { 0x210000db, 0x24000020 }, + { 0x210000dc, 0x24000020 }, + { 0x210000dd, 0x24000020 }, + { 0x210000de, 0x24000020 }, + { 0x210000df, 0x14000000 }, + { 0x210000e0, 0x1400ffe0 }, + { 0x210000e1, 0x1400ffe0 }, + { 0x210000e2, 0x1400ffe0 }, + { 0x210000e3, 0x1400ffe0 }, + { 0x210000e4, 0x1400ffe0 }, + { 0x210000e5, 0x1400ffe0 }, + { 0x210000e6, 0x1400ffe0 }, + { 0x210000e7, 0x1400ffe0 }, + { 0x210000e8, 0x1400ffe0 }, + { 0x210000e9, 0x1400ffe0 }, + { 0x210000ea, 0x1400ffe0 }, + { 0x210000eb, 0x1400ffe0 }, + { 0x210000ec, 0x1400ffe0 }, + { 0x210000ed, 0x1400ffe0 }, + { 0x210000ee, 0x1400ffe0 }, + { 0x210000ef, 0x1400ffe0 }, + { 0x210000f0, 0x1400ffe0 }, + { 0x210000f1, 0x1400ffe0 }, + { 0x210000f2, 0x1400ffe0 }, + { 0x210000f3, 0x1400ffe0 }, + { 0x210000f4, 0x1400ffe0 }, + { 0x210000f5, 0x1400ffe0 }, + { 0x210000f6, 0x1400ffe0 }, + { 0x090000f7, 0x64000000 }, + { 0x210000f8, 0x1400ffe0 }, + { 0x210000f9, 0x1400ffe0 }, + { 0x210000fa, 0x1400ffe0 }, + { 0x210000fb, 0x1400ffe0 }, + { 0x210000fc, 0x1400ffe0 }, + { 0x210000fd, 0x1400ffe0 }, + { 0x210000fe, 0x1400ffe0 }, + { 0x210000ff, 0x14000079 }, + { 0x21000100, 0x24000001 }, + { 0x21000101, 0x1400ffff }, + { 0x21000102, 0x24000001 }, + { 0x21000103, 0x1400ffff }, + { 0x21000104, 0x24000001 }, + { 0x21000105, 0x1400ffff }, + { 0x21000106, 0x24000001 }, + { 0x21000107, 0x1400ffff }, + { 0x21000108, 0x24000001 }, + { 0x21000109, 0x1400ffff }, + { 0x2100010a, 0x24000001 }, + { 0x2100010b, 0x1400ffff }, + { 0x2100010c, 0x24000001 }, + { 0x2100010d, 0x1400ffff }, + { 0x2100010e, 0x24000001 }, + { 0x2100010f, 0x1400ffff }, + { 0x21000110, 0x24000001 }, + { 0x21000111, 0x1400ffff }, + { 0x21000112, 0x24000001 }, + { 0x21000113, 0x1400ffff }, + { 0x21000114, 0x24000001 }, + { 0x21000115, 0x1400ffff }, + { 0x21000116, 0x24000001 }, + { 0x21000117, 0x1400ffff }, + { 0x21000118, 0x24000001 }, + { 0x21000119, 0x1400ffff }, + { 0x2100011a, 0x24000001 }, + { 0x2100011b, 0x1400ffff }, + { 0x2100011c, 0x24000001 }, + { 0x2100011d, 0x1400ffff }, + { 0x2100011e, 0x24000001 }, + { 0x2100011f, 0x1400ffff }, + { 0x21000120, 0x24000001 }, + { 0x21000121, 0x1400ffff }, + { 0x21000122, 0x24000001 }, + { 0x21000123, 0x1400ffff }, + { 0x21000124, 0x24000001 }, + { 0x21000125, 0x1400ffff }, + { 0x21000126, 0x24000001 }, + { 0x21000127, 0x1400ffff }, + { 0x21000128, 0x24000001 }, + { 0x21000129, 0x1400ffff }, + { 0x2100012a, 0x24000001 }, + { 0x2100012b, 0x1400ffff }, + { 0x2100012c, 0x24000001 }, + { 0x2100012d, 0x1400ffff }, + { 0x2100012e, 0x24000001 }, + { 0x2100012f, 0x1400ffff }, + { 0x21000130, 0x2400ff39 }, + { 0x21000131, 0x1400ff18 }, + { 0x21000132, 0x24000001 }, + { 0x21000133, 0x1400ffff }, + { 0x21000134, 0x24000001 }, + { 0x21000135, 0x1400ffff }, + { 0x21000136, 0x24000001 }, + { 0x21000137, 0x1400ffff }, + { 0x21000138, 0x14000000 }, + { 0x21000139, 0x24000001 }, + { 0x2100013a, 0x1400ffff }, + { 0x2100013b, 0x24000001 }, + { 0x2100013c, 0x1400ffff }, + { 0x2100013d, 0x24000001 }, + { 0x2100013e, 0x1400ffff }, + { 0x2100013f, 0x24000001 }, + { 0x21000140, 0x1400ffff }, + { 0x21000141, 0x24000001 }, + { 0x21000142, 0x1400ffff }, + { 0x21000143, 0x24000001 }, + { 0x21000144, 0x1400ffff }, + { 0x21000145, 0x24000001 }, + { 0x21000146, 0x1400ffff }, + { 0x21000147, 0x24000001 }, + { 0x21000148, 0x1400ffff }, + { 0x21000149, 0x14000000 }, + { 0x2100014a, 0x24000001 }, + { 0x2100014b, 0x1400ffff }, + { 0x2100014c, 0x24000001 }, + { 0x2100014d, 0x1400ffff }, + { 0x2100014e, 0x24000001 }, + { 0x2100014f, 0x1400ffff }, + { 0x21000150, 0x24000001 }, + { 0x21000151, 0x1400ffff }, + { 0x21000152, 0x24000001 }, + { 0x21000153, 0x1400ffff }, + { 0x21000154, 0x24000001 }, + { 0x21000155, 0x1400ffff }, + { 0x21000156, 0x24000001 }, + { 0x21000157, 0x1400ffff }, + { 0x21000158, 0x24000001 }, + { 0x21000159, 0x1400ffff }, + { 0x2100015a, 0x24000001 }, + { 0x2100015b, 0x1400ffff }, + { 0x2100015c, 0x24000001 }, + { 0x2100015d, 0x1400ffff }, + { 0x2100015e, 0x24000001 }, + { 0x2100015f, 0x1400ffff }, + { 0x21000160, 0x24000001 }, + { 0x21000161, 0x1400ffff }, + { 0x21000162, 0x24000001 }, + { 0x21000163, 0x1400ffff }, + { 0x21000164, 0x24000001 }, + { 0x21000165, 0x1400ffff }, + { 0x21000166, 0x24000001 }, + { 0x21000167, 0x1400ffff }, + { 0x21000168, 0x24000001 }, + { 0x21000169, 0x1400ffff }, + { 0x2100016a, 0x24000001 }, + { 0x2100016b, 0x1400ffff }, + { 0x2100016c, 0x24000001 }, + { 0x2100016d, 0x1400ffff }, + { 0x2100016e, 0x24000001 }, + { 0x2100016f, 0x1400ffff }, + { 0x21000170, 0x24000001 }, + { 0x21000171, 0x1400ffff }, + { 0x21000172, 0x24000001 }, + { 0x21000173, 0x1400ffff }, + { 0x21000174, 0x24000001 }, + { 0x21000175, 0x1400ffff }, + { 0x21000176, 0x24000001 }, + { 0x21000177, 0x1400ffff }, + { 0x21000178, 0x2400ff87 }, + { 0x21000179, 0x24000001 }, + { 0x2100017a, 0x1400ffff }, + { 0x2100017b, 0x24000001 }, + { 0x2100017c, 0x1400ffff }, + { 0x2100017d, 0x24000001 }, + { 0x2100017e, 0x1400ffff }, + { 0x2100017f, 0x1400fed4 }, + { 0x21000180, 0x140000c3 }, + { 0x21000181, 0x240000d2 }, + { 0x21000182, 0x24000001 }, + { 0x21000183, 0x1400ffff }, + { 0x21000184, 0x24000001 }, + { 0x21000185, 0x1400ffff }, + { 0x21000186, 0x240000ce }, + { 0x21000187, 0x24000001 }, + { 0x21000188, 0x1400ffff }, + { 0x21000189, 0x240000cd }, + { 0x2100018a, 0x240000cd }, + { 0x2100018b, 0x24000001 }, + { 0x2100018c, 0x1400ffff }, + { 0x2100018d, 0x14000000 }, + { 0x2100018e, 0x2400004f }, + { 0x2100018f, 0x240000ca }, + { 0x21000190, 0x240000cb }, + { 0x21000191, 0x24000001 }, + { 0x21000192, 0x1400ffff }, + { 0x21000193, 0x240000cd }, + { 0x21000194, 0x240000cf }, + { 0x21000195, 0x14000061 }, + { 0x21000196, 0x240000d3 }, + { 0x21000197, 0x240000d1 }, + { 0x21000198, 0x24000001 }, + { 0x21000199, 0x1400ffff }, + { 0x2100019a, 0x140000a3 }, + { 0x2100019b, 0x14000000 }, + { 0x2100019c, 0x240000d3 }, + { 0x2100019d, 0x240000d5 }, + { 0x2100019e, 0x14000082 }, + { 0x2100019f, 0x240000d6 }, + { 0x210001a0, 0x24000001 }, + { 0x210001a1, 0x1400ffff }, + { 0x210001a2, 0x24000001 }, + { 0x210001a3, 0x1400ffff }, + { 0x210001a4, 0x24000001 }, + { 0x210001a5, 0x1400ffff }, + { 0x210001a6, 0x240000da }, + { 0x210001a7, 0x24000001 }, + { 0x210001a8, 0x1400ffff }, + { 0x210001a9, 0x240000da }, + { 0x218001aa, 0x14000001 }, + { 0x210001ac, 0x24000001 }, + { 0x210001ad, 0x1400ffff }, + { 0x210001ae, 0x240000da }, + { 0x210001af, 0x24000001 }, + { 0x210001b0, 0x1400ffff }, + { 0x210001b1, 0x240000d9 }, + { 0x210001b2, 0x240000d9 }, + { 0x210001b3, 0x24000001 }, + { 0x210001b4, 0x1400ffff }, + { 0x210001b5, 0x24000001 }, + { 0x210001b6, 0x1400ffff }, + { 0x210001b7, 0x240000db }, + { 0x210001b8, 0x24000001 }, + { 0x210001b9, 0x1400ffff }, + { 0x210001ba, 0x14000000 }, + { 0x210001bb, 0x1c000000 }, + { 0x210001bc, 0x24000001 }, + { 0x210001bd, 0x1400ffff }, + { 0x210001be, 0x14000000 }, + { 0x210001bf, 0x14000038 }, + { 0x218001c0, 0x1c000003 }, + { 0x210001c4, 0x24000002 }, + { 0x210001c5, 0x2000ffff }, + { 0x210001c6, 0x1400fffe }, + { 0x210001c7, 0x24000002 }, + { 0x210001c8, 0x2000ffff }, + { 0x210001c9, 0x1400fffe }, + { 0x210001ca, 0x24000002 }, + { 0x210001cb, 0x2000ffff }, + { 0x210001cc, 0x1400fffe }, + { 0x210001cd, 0x24000001 }, + { 0x210001ce, 0x1400ffff }, + { 0x210001cf, 0x24000001 }, + { 0x210001d0, 0x1400ffff }, + { 0x210001d1, 0x24000001 }, + { 0x210001d2, 0x1400ffff }, + { 0x210001d3, 0x24000001 }, + { 0x210001d4, 0x1400ffff }, + { 0x210001d5, 0x24000001 }, + { 0x210001d6, 0x1400ffff }, + { 0x210001d7, 0x24000001 }, + { 0x210001d8, 0x1400ffff }, + { 0x210001d9, 0x24000001 }, + { 0x210001da, 0x1400ffff }, + { 0x210001db, 0x24000001 }, + { 0x210001dc, 0x1400ffff }, + { 0x210001dd, 0x1400ffb1 }, + { 0x210001de, 0x24000001 }, + { 0x210001df, 0x1400ffff }, + { 0x210001e0, 0x24000001 }, + { 0x210001e1, 0x1400ffff }, + { 0x210001e2, 0x24000001 }, + { 0x210001e3, 0x1400ffff }, + { 0x210001e4, 0x24000001 }, + { 0x210001e5, 0x1400ffff }, + { 0x210001e6, 0x24000001 }, + { 0x210001e7, 0x1400ffff }, + { 0x210001e8, 0x24000001 }, + { 0x210001e9, 0x1400ffff }, + { 0x210001ea, 0x24000001 }, + { 0x210001eb, 0x1400ffff }, + { 0x210001ec, 0x24000001 }, + { 0x210001ed, 0x1400ffff }, + { 0x210001ee, 0x24000001 }, + { 0x210001ef, 0x1400ffff }, + { 0x210001f0, 0x14000000 }, + { 0x210001f1, 0x24000002 }, + { 0x210001f2, 0x2000ffff }, + { 0x210001f3, 0x1400fffe }, + { 0x210001f4, 0x24000001 }, + { 0x210001f5, 0x1400ffff }, + { 0x210001f6, 0x2400ff9f }, + { 0x210001f7, 0x2400ffc8 }, + { 0x210001f8, 0x24000001 }, + { 0x210001f9, 0x1400ffff }, + { 0x210001fa, 0x24000001 }, + { 0x210001fb, 0x1400ffff }, + { 0x210001fc, 0x24000001 }, + { 0x210001fd, 0x1400ffff }, + { 0x210001fe, 0x24000001 }, + { 0x210001ff, 0x1400ffff }, + { 0x21000200, 0x24000001 }, + { 0x21000201, 0x1400ffff }, + { 0x21000202, 0x24000001 }, + { 0x21000203, 0x1400ffff }, + { 0x21000204, 0x24000001 }, + { 0x21000205, 0x1400ffff }, + { 0x21000206, 0x24000001 }, + { 0x21000207, 0x1400ffff }, + { 0x21000208, 0x24000001 }, + { 0x21000209, 0x1400ffff }, + { 0x2100020a, 0x24000001 }, + { 0x2100020b, 0x1400ffff }, + { 0x2100020c, 0x24000001 }, + { 0x2100020d, 0x1400ffff }, + { 0x2100020e, 0x24000001 }, + { 0x2100020f, 0x1400ffff }, + { 0x21000210, 0x24000001 }, + { 0x21000211, 0x1400ffff }, + { 0x21000212, 0x24000001 }, + { 0x21000213, 0x1400ffff }, + { 0x21000214, 0x24000001 }, + { 0x21000215, 0x1400ffff }, + { 0x21000216, 0x24000001 }, + { 0x21000217, 0x1400ffff }, + { 0x21000218, 0x24000001 }, + { 0x21000219, 0x1400ffff }, + { 0x2100021a, 0x24000001 }, + { 0x2100021b, 0x1400ffff }, + { 0x2100021c, 0x24000001 }, + { 0x2100021d, 0x1400ffff }, + { 0x2100021e, 0x24000001 }, + { 0x2100021f, 0x1400ffff }, + { 0x21000220, 0x2400ff7e }, + { 0x21000221, 0x14000000 }, + { 0x21000222, 0x24000001 }, + { 0x21000223, 0x1400ffff }, + { 0x21000224, 0x24000001 }, + { 0x21000225, 0x1400ffff }, + { 0x21000226, 0x24000001 }, + { 0x21000227, 0x1400ffff }, + { 0x21000228, 0x24000001 }, + { 0x21000229, 0x1400ffff }, + { 0x2100022a, 0x24000001 }, + { 0x2100022b, 0x1400ffff }, + { 0x2100022c, 0x24000001 }, + { 0x2100022d, 0x1400ffff }, + { 0x2100022e, 0x24000001 }, + { 0x2100022f, 0x1400ffff }, + { 0x21000230, 0x24000001 }, + { 0x21000231, 0x1400ffff }, + { 0x21000232, 0x24000001 }, + { 0x21000233, 0x1400ffff }, + { 0x21800234, 0x14000005 }, + { 0x2100023a, 0x24002a2b }, + { 0x2100023b, 0x24000001 }, + { 0x2100023c, 0x1400ffff }, + { 0x2100023d, 0x2400ff5d }, + { 0x2100023e, 0x24002a28 }, + { 0x2180023f, 0x14000001 }, + { 0x21000241, 0x24000001 }, + { 0x21000242, 0x1400ffff }, + { 0x21000243, 0x2400ff3d }, + { 0x21000244, 0x24000045 }, + { 0x21000245, 0x24000047 }, + { 0x21000246, 0x24000001 }, + { 0x21000247, 0x1400ffff }, + { 0x21000248, 0x24000001 }, + { 0x21000249, 0x1400ffff }, + { 0x2100024a, 0x24000001 }, + { 0x2100024b, 0x1400ffff }, + { 0x2100024c, 0x24000001 }, + { 0x2100024d, 0x1400ffff }, + { 0x2100024e, 0x24000001 }, + { 0x2100024f, 0x1400ffff }, + { 0x21800250, 0x14000002 }, + { 0x21000253, 0x1400ff2e }, + { 0x21000254, 0x1400ff32 }, + { 0x21000255, 0x14000000 }, + { 0x21000256, 0x1400ff33 }, + { 0x21000257, 0x1400ff33 }, + { 0x21000258, 0x14000000 }, + { 0x21000259, 0x1400ff36 }, + { 0x2100025a, 0x14000000 }, + { 0x2100025b, 0x1400ff35 }, + { 0x2180025c, 0x14000003 }, + { 0x21000260, 0x1400ff33 }, + { 0x21800261, 0x14000001 }, + { 0x21000263, 0x1400ff31 }, + { 0x21800264, 0x14000003 }, + { 0x21000268, 0x1400ff2f }, + { 0x21000269, 0x1400ff2d }, + { 0x2100026a, 0x14000000 }, + { 0x2100026b, 0x140029f7 }, + { 0x2180026c, 0x14000002 }, + { 0x2100026f, 0x1400ff2d }, + { 0x21800270, 0x14000001 }, + { 0x21000272, 0x1400ff2b }, + { 0x21800273, 0x14000001 }, + { 0x21000275, 0x1400ff2a }, + { 0x21800276, 0x14000006 }, + { 0x2100027d, 0x140029e7 }, + { 0x2180027e, 0x14000001 }, + { 0x21000280, 0x1400ff26 }, + { 0x21800281, 0x14000001 }, + { 0x21000283, 0x1400ff26 }, + { 0x21800284, 0x14000003 }, + { 0x21000288, 0x1400ff26 }, + { 0x21000289, 0x1400ffbb }, + { 0x2100028a, 0x1400ff27 }, + { 0x2100028b, 0x1400ff27 }, + { 0x2100028c, 0x1400ffb9 }, + { 0x2180028d, 0x14000004 }, + { 0x21000292, 0x1400ff25 }, + { 0x21000293, 0x14000000 }, + { 0x21000294, 0x1c000000 }, + { 0x21800295, 0x1400001a }, + { 0x218002b0, 0x18000011 }, + { 0x098002c2, 0x60000003 }, + { 0x098002c6, 0x1800000b }, + { 0x098002d2, 0x6000000d }, + { 0x218002e0, 0x18000004 }, + { 0x098002e5, 0x60000008 }, + { 0x090002ee, 0x18000000 }, + { 0x098002ef, 0x60000010 }, + { 0x1b800300, 0x30000044 }, + { 0x1b000345, 0x30000054 }, + { 0x1b800346, 0x30000029 }, + { 0x13800374, 0x60000001 }, + { 0x1300037a, 0x18000000 }, + { 0x1300037b, 0x14000082 }, + { 0x1300037c, 0x14000082 }, + { 0x1300037d, 0x14000082 }, + { 0x0900037e, 0x54000000 }, + { 0x13800384, 0x60000001 }, + { 0x13000386, 0x24000026 }, + { 0x09000387, 0x54000000 }, + { 0x13000388, 0x24000025 }, + { 0x13000389, 0x24000025 }, + { 0x1300038a, 0x24000025 }, + { 0x1300038c, 0x24000040 }, + { 0x1300038e, 0x2400003f }, + { 0x1300038f, 0x2400003f }, + { 0x13000390, 0x14000000 }, + { 0x13000391, 0x24000020 }, + { 0x13000392, 0x24000020 }, + { 0x13000393, 0x24000020 }, + { 0x13000394, 0x24000020 }, + { 0x13000395, 0x24000020 }, + { 0x13000396, 0x24000020 }, + { 0x13000397, 0x24000020 }, + { 0x13000398, 0x24000020 }, + { 0x13000399, 0x24000020 }, + { 0x1300039a, 0x24000020 }, + { 0x1300039b, 0x24000020 }, + { 0x1300039c, 0x24000020 }, + { 0x1300039d, 0x24000020 }, + { 0x1300039e, 0x24000020 }, + { 0x1300039f, 0x24000020 }, + { 0x130003a0, 0x24000020 }, + { 0x130003a1, 0x24000020 }, + { 0x130003a3, 0x24000020 }, + { 0x130003a4, 0x24000020 }, + { 0x130003a5, 0x24000020 }, + { 0x130003a6, 0x24000020 }, + { 0x130003a7, 0x24000020 }, + { 0x130003a8, 0x24000020 }, + { 0x130003a9, 0x24000020 }, + { 0x130003aa, 0x24000020 }, + { 0x130003ab, 0x24000020 }, + { 0x130003ac, 0x1400ffda }, + { 0x130003ad, 0x1400ffdb }, + { 0x130003ae, 0x1400ffdb }, + { 0x130003af, 0x1400ffdb }, + { 0x130003b0, 0x14000000 }, + { 0x130003b1, 0x1400ffe0 }, + { 0x130003b2, 0x1400ffe0 }, + { 0x130003b3, 0x1400ffe0 }, + { 0x130003b4, 0x1400ffe0 }, + { 0x130003b5, 0x1400ffe0 }, + { 0x130003b6, 0x1400ffe0 }, + { 0x130003b7, 0x1400ffe0 }, + { 0x130003b8, 0x1400ffe0 }, + { 0x130003b9, 0x1400ffe0 }, + { 0x130003ba, 0x1400ffe0 }, + { 0x130003bb, 0x1400ffe0 }, + { 0x130003bc, 0x1400ffe0 }, + { 0x130003bd, 0x1400ffe0 }, + { 0x130003be, 0x1400ffe0 }, + { 0x130003bf, 0x1400ffe0 }, + { 0x130003c0, 0x1400ffe0 }, + { 0x130003c1, 0x1400ffe0 }, + { 0x130003c2, 0x1400ffe1 }, + { 0x130003c3, 0x1400ffe0 }, + { 0x130003c4, 0x1400ffe0 }, + { 0x130003c5, 0x1400ffe0 }, + { 0x130003c6, 0x1400ffe0 }, + { 0x130003c7, 0x1400ffe0 }, + { 0x130003c8, 0x1400ffe0 }, + { 0x130003c9, 0x1400ffe0 }, + { 0x130003ca, 0x1400ffe0 }, + { 0x130003cb, 0x1400ffe0 }, + { 0x130003cc, 0x1400ffc0 }, + { 0x130003cd, 0x1400ffc1 }, + { 0x130003ce, 0x1400ffc1 }, + { 0x130003d0, 0x1400ffc2 }, + { 0x130003d1, 0x1400ffc7 }, + { 0x138003d2, 0x24000002 }, + { 0x130003d5, 0x1400ffd1 }, + { 0x130003d6, 0x1400ffca }, + { 0x130003d7, 0x14000000 }, + { 0x130003d8, 0x24000001 }, + { 0x130003d9, 0x1400ffff }, + { 0x130003da, 0x24000001 }, + { 0x130003db, 0x1400ffff }, + { 0x130003dc, 0x24000001 }, + { 0x130003dd, 0x1400ffff }, + { 0x130003de, 0x24000001 }, + { 0x130003df, 0x1400ffff }, + { 0x130003e0, 0x24000001 }, + { 0x130003e1, 0x1400ffff }, + { 0x0a0003e2, 0x24000001 }, + { 0x0a0003e3, 0x1400ffff }, + { 0x0a0003e4, 0x24000001 }, + { 0x0a0003e5, 0x1400ffff }, + { 0x0a0003e6, 0x24000001 }, + { 0x0a0003e7, 0x1400ffff }, + { 0x0a0003e8, 0x24000001 }, + { 0x0a0003e9, 0x1400ffff }, + { 0x0a0003ea, 0x24000001 }, + { 0x0a0003eb, 0x1400ffff }, + { 0x0a0003ec, 0x24000001 }, + { 0x0a0003ed, 0x1400ffff }, + { 0x0a0003ee, 0x24000001 }, + { 0x0a0003ef, 0x1400ffff }, + { 0x130003f0, 0x1400ffaa }, + { 0x130003f1, 0x1400ffb0 }, + { 0x130003f2, 0x14000007 }, + { 0x130003f3, 0x14000000 }, + { 0x130003f4, 0x2400ffc4 }, + { 0x130003f5, 0x1400ffa0 }, + { 0x130003f6, 0x64000000 }, + { 0x130003f7, 0x24000001 }, + { 0x130003f8, 0x1400ffff }, + { 0x130003f9, 0x2400fff9 }, + { 0x130003fa, 0x24000001 }, + { 0x130003fb, 0x1400ffff }, + { 0x130003fc, 0x14000000 }, + { 0x130003fd, 0x2400ff7e }, + { 0x130003fe, 0x2400ff7e }, + { 0x130003ff, 0x2400ff7e }, + { 0x0c000400, 0x24000050 }, + { 0x0c000401, 0x24000050 }, + { 0x0c000402, 0x24000050 }, + { 0x0c000403, 0x24000050 }, + { 0x0c000404, 0x24000050 }, + { 0x0c000405, 0x24000050 }, + { 0x0c000406, 0x24000050 }, + { 0x0c000407, 0x24000050 }, + { 0x0c000408, 0x24000050 }, + { 0x0c000409, 0x24000050 }, + { 0x0c00040a, 0x24000050 }, + { 0x0c00040b, 0x24000050 }, + { 0x0c00040c, 0x24000050 }, + { 0x0c00040d, 0x24000050 }, + { 0x0c00040e, 0x24000050 }, + { 0x0c00040f, 0x24000050 }, + { 0x0c000410, 0x24000020 }, + { 0x0c000411, 0x24000020 }, + { 0x0c000412, 0x24000020 }, + { 0x0c000413, 0x24000020 }, + { 0x0c000414, 0x24000020 }, + { 0x0c000415, 0x24000020 }, + { 0x0c000416, 0x24000020 }, + { 0x0c000417, 0x24000020 }, + { 0x0c000418, 0x24000020 }, + { 0x0c000419, 0x24000020 }, + { 0x0c00041a, 0x24000020 }, + { 0x0c00041b, 0x24000020 }, + { 0x0c00041c, 0x24000020 }, + { 0x0c00041d, 0x24000020 }, + { 0x0c00041e, 0x24000020 }, + { 0x0c00041f, 0x24000020 }, + { 0x0c000420, 0x24000020 }, + { 0x0c000421, 0x24000020 }, + { 0x0c000422, 0x24000020 }, + { 0x0c000423, 0x24000020 }, + { 0x0c000424, 0x24000020 }, + { 0x0c000425, 0x24000020 }, + { 0x0c000426, 0x24000020 }, + { 0x0c000427, 0x24000020 }, + { 0x0c000428, 0x24000020 }, + { 0x0c000429, 0x24000020 }, + { 0x0c00042a, 0x24000020 }, + { 0x0c00042b, 0x24000020 }, + { 0x0c00042c, 0x24000020 }, + { 0x0c00042d, 0x24000020 }, + { 0x0c00042e, 0x24000020 }, + { 0x0c00042f, 0x24000020 }, + { 0x0c000430, 0x1400ffe0 }, + { 0x0c000431, 0x1400ffe0 }, + { 0x0c000432, 0x1400ffe0 }, + { 0x0c000433, 0x1400ffe0 }, + { 0x0c000434, 0x1400ffe0 }, + { 0x0c000435, 0x1400ffe0 }, + { 0x0c000436, 0x1400ffe0 }, + { 0x0c000437, 0x1400ffe0 }, + { 0x0c000438, 0x1400ffe0 }, + { 0x0c000439, 0x1400ffe0 }, + { 0x0c00043a, 0x1400ffe0 }, + { 0x0c00043b, 0x1400ffe0 }, + { 0x0c00043c, 0x1400ffe0 }, + { 0x0c00043d, 0x1400ffe0 }, + { 0x0c00043e, 0x1400ffe0 }, + { 0x0c00043f, 0x1400ffe0 }, + { 0x0c000440, 0x1400ffe0 }, + { 0x0c000441, 0x1400ffe0 }, + { 0x0c000442, 0x1400ffe0 }, + { 0x0c000443, 0x1400ffe0 }, + { 0x0c000444, 0x1400ffe0 }, + { 0x0c000445, 0x1400ffe0 }, + { 0x0c000446, 0x1400ffe0 }, + { 0x0c000447, 0x1400ffe0 }, + { 0x0c000448, 0x1400ffe0 }, + { 0x0c000449, 0x1400ffe0 }, + { 0x0c00044a, 0x1400ffe0 }, + { 0x0c00044b, 0x1400ffe0 }, + { 0x0c00044c, 0x1400ffe0 }, + { 0x0c00044d, 0x1400ffe0 }, + { 0x0c00044e, 0x1400ffe0 }, + { 0x0c00044f, 0x1400ffe0 }, + { 0x0c000450, 0x1400ffb0 }, + { 0x0c000451, 0x1400ffb0 }, + { 0x0c000452, 0x1400ffb0 }, + { 0x0c000453, 0x1400ffb0 }, + { 0x0c000454, 0x1400ffb0 }, + { 0x0c000455, 0x1400ffb0 }, + { 0x0c000456, 0x1400ffb0 }, + { 0x0c000457, 0x1400ffb0 }, + { 0x0c000458, 0x1400ffb0 }, + { 0x0c000459, 0x1400ffb0 }, + { 0x0c00045a, 0x1400ffb0 }, + { 0x0c00045b, 0x1400ffb0 }, + { 0x0c00045c, 0x1400ffb0 }, + { 0x0c00045d, 0x1400ffb0 }, + { 0x0c00045e, 0x1400ffb0 }, + { 0x0c00045f, 0x1400ffb0 }, + { 0x0c000460, 0x24000001 }, + { 0x0c000461, 0x1400ffff }, + { 0x0c000462, 0x24000001 }, + { 0x0c000463, 0x1400ffff }, + { 0x0c000464, 0x24000001 }, + { 0x0c000465, 0x1400ffff }, + { 0x0c000466, 0x24000001 }, + { 0x0c000467, 0x1400ffff }, + { 0x0c000468, 0x24000001 }, + { 0x0c000469, 0x1400ffff }, + { 0x0c00046a, 0x24000001 }, + { 0x0c00046b, 0x1400ffff }, + { 0x0c00046c, 0x24000001 }, + { 0x0c00046d, 0x1400ffff }, + { 0x0c00046e, 0x24000001 }, + { 0x0c00046f, 0x1400ffff }, + { 0x0c000470, 0x24000001 }, + { 0x0c000471, 0x1400ffff }, + { 0x0c000472, 0x24000001 }, + { 0x0c000473, 0x1400ffff }, + { 0x0c000474, 0x24000001 }, + { 0x0c000475, 0x1400ffff }, + { 0x0c000476, 0x24000001 }, + { 0x0c000477, 0x1400ffff }, + { 0x0c000478, 0x24000001 }, + { 0x0c000479, 0x1400ffff }, + { 0x0c00047a, 0x24000001 }, + { 0x0c00047b, 0x1400ffff }, + { 0x0c00047c, 0x24000001 }, + { 0x0c00047d, 0x1400ffff }, + { 0x0c00047e, 0x24000001 }, + { 0x0c00047f, 0x1400ffff }, + { 0x0c000480, 0x24000001 }, + { 0x0c000481, 0x1400ffff }, + { 0x0c000482, 0x68000000 }, + { 0x0c800483, 0x30000003 }, + { 0x0c800488, 0x2c000001 }, + { 0x0c00048a, 0x24000001 }, + { 0x0c00048b, 0x1400ffff }, + { 0x0c00048c, 0x24000001 }, + { 0x0c00048d, 0x1400ffff }, + { 0x0c00048e, 0x24000001 }, + { 0x0c00048f, 0x1400ffff }, + { 0x0c000490, 0x24000001 }, + { 0x0c000491, 0x1400ffff }, + { 0x0c000492, 0x24000001 }, + { 0x0c000493, 0x1400ffff }, + { 0x0c000494, 0x24000001 }, + { 0x0c000495, 0x1400ffff }, + { 0x0c000496, 0x24000001 }, + { 0x0c000497, 0x1400ffff }, + { 0x0c000498, 0x24000001 }, + { 0x0c000499, 0x1400ffff }, + { 0x0c00049a, 0x24000001 }, + { 0x0c00049b, 0x1400ffff }, + { 0x0c00049c, 0x24000001 }, + { 0x0c00049d, 0x1400ffff }, + { 0x0c00049e, 0x24000001 }, + { 0x0c00049f, 0x1400ffff }, + { 0x0c0004a0, 0x24000001 }, + { 0x0c0004a1, 0x1400ffff }, + { 0x0c0004a2, 0x24000001 }, + { 0x0c0004a3, 0x1400ffff }, + { 0x0c0004a4, 0x24000001 }, + { 0x0c0004a5, 0x1400ffff }, + { 0x0c0004a6, 0x24000001 }, + { 0x0c0004a7, 0x1400ffff }, + { 0x0c0004a8, 0x24000001 }, + { 0x0c0004a9, 0x1400ffff }, + { 0x0c0004aa, 0x24000001 }, + { 0x0c0004ab, 0x1400ffff }, + { 0x0c0004ac, 0x24000001 }, + { 0x0c0004ad, 0x1400ffff }, + { 0x0c0004ae, 0x24000001 }, + { 0x0c0004af, 0x1400ffff }, + { 0x0c0004b0, 0x24000001 }, + { 0x0c0004b1, 0x1400ffff }, + { 0x0c0004b2, 0x24000001 }, + { 0x0c0004b3, 0x1400ffff }, + { 0x0c0004b4, 0x24000001 }, + { 0x0c0004b5, 0x1400ffff }, + { 0x0c0004b6, 0x24000001 }, + { 0x0c0004b7, 0x1400ffff }, + { 0x0c0004b8, 0x24000001 }, + { 0x0c0004b9, 0x1400ffff }, + { 0x0c0004ba, 0x24000001 }, + { 0x0c0004bb, 0x1400ffff }, + { 0x0c0004bc, 0x24000001 }, + { 0x0c0004bd, 0x1400ffff }, + { 0x0c0004be, 0x24000001 }, + { 0x0c0004bf, 0x1400ffff }, + { 0x0c0004c0, 0x2400000f }, + { 0x0c0004c1, 0x24000001 }, + { 0x0c0004c2, 0x1400ffff }, + { 0x0c0004c3, 0x24000001 }, + { 0x0c0004c4, 0x1400ffff }, + { 0x0c0004c5, 0x24000001 }, + { 0x0c0004c6, 0x1400ffff }, + { 0x0c0004c7, 0x24000001 }, + { 0x0c0004c8, 0x1400ffff }, + { 0x0c0004c9, 0x24000001 }, + { 0x0c0004ca, 0x1400ffff }, + { 0x0c0004cb, 0x24000001 }, + { 0x0c0004cc, 0x1400ffff }, + { 0x0c0004cd, 0x24000001 }, + { 0x0c0004ce, 0x1400ffff }, + { 0x0c0004cf, 0x1400fff1 }, + { 0x0c0004d0, 0x24000001 }, + { 0x0c0004d1, 0x1400ffff }, + { 0x0c0004d2, 0x24000001 }, + { 0x0c0004d3, 0x1400ffff }, + { 0x0c0004d4, 0x24000001 }, + { 0x0c0004d5, 0x1400ffff }, + { 0x0c0004d6, 0x24000001 }, + { 0x0c0004d7, 0x1400ffff }, + { 0x0c0004d8, 0x24000001 }, + { 0x0c0004d9, 0x1400ffff }, + { 0x0c0004da, 0x24000001 }, + { 0x0c0004db, 0x1400ffff }, + { 0x0c0004dc, 0x24000001 }, + { 0x0c0004dd, 0x1400ffff }, + { 0x0c0004de, 0x24000001 }, + { 0x0c0004df, 0x1400ffff }, + { 0x0c0004e0, 0x24000001 }, + { 0x0c0004e1, 0x1400ffff }, + { 0x0c0004e2, 0x24000001 }, + { 0x0c0004e3, 0x1400ffff }, + { 0x0c0004e4, 0x24000001 }, + { 0x0c0004e5, 0x1400ffff }, + { 0x0c0004e6, 0x24000001 }, + { 0x0c0004e7, 0x1400ffff }, + { 0x0c0004e8, 0x24000001 }, + { 0x0c0004e9, 0x1400ffff }, + { 0x0c0004ea, 0x24000001 }, + { 0x0c0004eb, 0x1400ffff }, + { 0x0c0004ec, 0x24000001 }, + { 0x0c0004ed, 0x1400ffff }, + { 0x0c0004ee, 0x24000001 }, + { 0x0c0004ef, 0x1400ffff }, + { 0x0c0004f0, 0x24000001 }, + { 0x0c0004f1, 0x1400ffff }, + { 0x0c0004f2, 0x24000001 }, + { 0x0c0004f3, 0x1400ffff }, + { 0x0c0004f4, 0x24000001 }, + { 0x0c0004f5, 0x1400ffff }, + { 0x0c0004f6, 0x24000001 }, + { 0x0c0004f7, 0x1400ffff }, + { 0x0c0004f8, 0x24000001 }, + { 0x0c0004f9, 0x1400ffff }, + { 0x0c0004fa, 0x24000001 }, + { 0x0c0004fb, 0x1400ffff }, + { 0x0c0004fc, 0x24000001 }, + { 0x0c0004fd, 0x1400ffff }, + { 0x0c0004fe, 0x24000001 }, + { 0x0c0004ff, 0x1400ffff }, + { 0x0c000500, 0x24000001 }, + { 0x0c000501, 0x1400ffff }, + { 0x0c000502, 0x24000001 }, + { 0x0c000503, 0x1400ffff }, + { 0x0c000504, 0x24000001 }, + { 0x0c000505, 0x1400ffff }, + { 0x0c000506, 0x24000001 }, + { 0x0c000507, 0x1400ffff }, + { 0x0c000508, 0x24000001 }, + { 0x0c000509, 0x1400ffff }, + { 0x0c00050a, 0x24000001 }, + { 0x0c00050b, 0x1400ffff }, + { 0x0c00050c, 0x24000001 }, + { 0x0c00050d, 0x1400ffff }, + { 0x0c00050e, 0x24000001 }, + { 0x0c00050f, 0x1400ffff }, + { 0x0c000510, 0x24000001 }, + { 0x0c000511, 0x1400ffff }, + { 0x0c000512, 0x24000001 }, + { 0x0c000513, 0x1400ffff }, + { 0x01000531, 0x24000030 }, + { 0x01000532, 0x24000030 }, + { 0x01000533, 0x24000030 }, + { 0x01000534, 0x24000030 }, + { 0x01000535, 0x24000030 }, + { 0x01000536, 0x24000030 }, + { 0x01000537, 0x24000030 }, + { 0x01000538, 0x24000030 }, + { 0x01000539, 0x24000030 }, + { 0x0100053a, 0x24000030 }, + { 0x0100053b, 0x24000030 }, + { 0x0100053c, 0x24000030 }, + { 0x0100053d, 0x24000030 }, + { 0x0100053e, 0x24000030 }, + { 0x0100053f, 0x24000030 }, + { 0x01000540, 0x24000030 }, + { 0x01000541, 0x24000030 }, + { 0x01000542, 0x24000030 }, + { 0x01000543, 0x24000030 }, + { 0x01000544, 0x24000030 }, + { 0x01000545, 0x24000030 }, + { 0x01000546, 0x24000030 }, + { 0x01000547, 0x24000030 }, + { 0x01000548, 0x24000030 }, + { 0x01000549, 0x24000030 }, + { 0x0100054a, 0x24000030 }, + { 0x0100054b, 0x24000030 }, + { 0x0100054c, 0x24000030 }, + { 0x0100054d, 0x24000030 }, + { 0x0100054e, 0x24000030 }, + { 0x0100054f, 0x24000030 }, + { 0x01000550, 0x24000030 }, + { 0x01000551, 0x24000030 }, + { 0x01000552, 0x24000030 }, + { 0x01000553, 0x24000030 }, + { 0x01000554, 0x24000030 }, + { 0x01000555, 0x24000030 }, + { 0x01000556, 0x24000030 }, + { 0x01000559, 0x18000000 }, + { 0x0180055a, 0x54000005 }, + { 0x01000561, 0x1400ffd0 }, + { 0x01000562, 0x1400ffd0 }, + { 0x01000563, 0x1400ffd0 }, + { 0x01000564, 0x1400ffd0 }, + { 0x01000565, 0x1400ffd0 }, + { 0x01000566, 0x1400ffd0 }, + { 0x01000567, 0x1400ffd0 }, + { 0x01000568, 0x1400ffd0 }, + { 0x01000569, 0x1400ffd0 }, + { 0x0100056a, 0x1400ffd0 }, + { 0x0100056b, 0x1400ffd0 }, + { 0x0100056c, 0x1400ffd0 }, + { 0x0100056d, 0x1400ffd0 }, + { 0x0100056e, 0x1400ffd0 }, + { 0x0100056f, 0x1400ffd0 }, + { 0x01000570, 0x1400ffd0 }, + { 0x01000571, 0x1400ffd0 }, + { 0x01000572, 0x1400ffd0 }, + { 0x01000573, 0x1400ffd0 }, + { 0x01000574, 0x1400ffd0 }, + { 0x01000575, 0x1400ffd0 }, + { 0x01000576, 0x1400ffd0 }, + { 0x01000577, 0x1400ffd0 }, + { 0x01000578, 0x1400ffd0 }, + { 0x01000579, 0x1400ffd0 }, + { 0x0100057a, 0x1400ffd0 }, + { 0x0100057b, 0x1400ffd0 }, + { 0x0100057c, 0x1400ffd0 }, + { 0x0100057d, 0x1400ffd0 }, + { 0x0100057e, 0x1400ffd0 }, + { 0x0100057f, 0x1400ffd0 }, + { 0x01000580, 0x1400ffd0 }, + { 0x01000581, 0x1400ffd0 }, + { 0x01000582, 0x1400ffd0 }, + { 0x01000583, 0x1400ffd0 }, + { 0x01000584, 0x1400ffd0 }, + { 0x01000585, 0x1400ffd0 }, + { 0x01000586, 0x1400ffd0 }, + { 0x01000587, 0x14000000 }, + { 0x09000589, 0x54000000 }, + { 0x0100058a, 0x44000000 }, + { 0x19800591, 0x3000002c }, + { 0x190005be, 0x54000000 }, + { 0x190005bf, 0x30000000 }, + { 0x190005c0, 0x54000000 }, + { 0x198005c1, 0x30000001 }, + { 0x190005c3, 0x54000000 }, + { 0x198005c4, 0x30000001 }, + { 0x190005c6, 0x54000000 }, + { 0x190005c7, 0x30000000 }, + { 0x198005d0, 0x1c00001a }, + { 0x198005f0, 0x1c000002 }, + { 0x198005f3, 0x54000001 }, + { 0x09800600, 0x04000003 }, + { 0x0000060b, 0x5c000000 }, + { 0x0980060c, 0x54000001 }, + { 0x0080060e, 0x68000001 }, + { 0x00800610, 0x30000005 }, + { 0x0900061b, 0x54000000 }, + { 0x0080061e, 0x54000001 }, + { 0x00800621, 0x1c000019 }, + { 0x09000640, 0x18000000 }, + { 0x00800641, 0x1c000009 }, + { 0x1b80064b, 0x30000013 }, + { 0x09800660, 0x34000009 }, + { 0x0080066a, 0x54000003 }, + { 0x0080066e, 0x1c000001 }, + { 0x1b000670, 0x30000000 }, + { 0x00800671, 0x1c000062 }, + { 0x000006d4, 0x54000000 }, + { 0x000006d5, 0x1c000000 }, + { 0x008006d6, 0x30000006 }, + { 0x090006dd, 0x04000000 }, + { 0x000006de, 0x2c000000 }, + { 0x008006df, 0x30000005 }, + { 0x008006e5, 0x18000001 }, + { 0x008006e7, 0x30000001 }, + { 0x000006e9, 0x68000000 }, + { 0x008006ea, 0x30000003 }, + { 0x008006ee, 0x1c000001 }, + { 0x008006f0, 0x34000009 }, + { 0x008006fa, 0x1c000002 }, + { 0x008006fd, 0x68000001 }, + { 0x000006ff, 0x1c000000 }, + { 0x31800700, 0x5400000d }, + { 0x3100070f, 0x04000000 }, + { 0x31000710, 0x1c000000 }, + { 0x31000711, 0x30000000 }, + { 0x31800712, 0x1c00001d }, + { 0x31800730, 0x3000001a }, + { 0x3180074d, 0x1c000020 }, + { 0x37800780, 0x1c000025 }, + { 0x378007a6, 0x3000000a }, + { 0x370007b1, 0x1c000000 }, + { 0x3f8007c0, 0x34000009 }, + { 0x3f8007ca, 0x1c000020 }, + { 0x3f8007eb, 0x30000008 }, + { 0x3f8007f4, 0x18000001 }, + { 0x3f0007f6, 0x68000000 }, + { 0x3f8007f7, 0x54000002 }, + { 0x3f0007fa, 0x18000000 }, + { 0x0e800901, 0x30000001 }, + { 0x0e000903, 0x28000000 }, + { 0x0e800904, 0x1c000035 }, + { 0x0e00093c, 0x30000000 }, + { 0x0e00093d, 0x1c000000 }, + { 0x0e80093e, 0x28000002 }, + { 0x0e800941, 0x30000007 }, + { 0x0e800949, 0x28000003 }, + { 0x0e00094d, 0x30000000 }, + { 0x0e000950, 0x1c000000 }, + { 0x0e800951, 0x30000003 }, + { 0x0e800958, 0x1c000009 }, + { 0x0e800962, 0x30000001 }, + { 0x09800964, 0x54000001 }, + { 0x0e800966, 0x34000009 }, + { 0x09000970, 0x54000000 }, + { 0x0e80097b, 0x1c000004 }, + { 0x02000981, 0x30000000 }, + { 0x02800982, 0x28000001 }, + { 0x02800985, 0x1c000007 }, + { 0x0280098f, 0x1c000001 }, + { 0x02800993, 0x1c000015 }, + { 0x028009aa, 0x1c000006 }, + { 0x020009b2, 0x1c000000 }, + { 0x028009b6, 0x1c000003 }, + { 0x020009bc, 0x30000000 }, + { 0x020009bd, 0x1c000000 }, + { 0x028009be, 0x28000002 }, + { 0x028009c1, 0x30000003 }, + { 0x028009c7, 0x28000001 }, + { 0x028009cb, 0x28000001 }, + { 0x020009cd, 0x30000000 }, + { 0x020009ce, 0x1c000000 }, + { 0x020009d7, 0x28000000 }, + { 0x028009dc, 0x1c000001 }, + { 0x028009df, 0x1c000002 }, + { 0x028009e2, 0x30000001 }, + { 0x028009e6, 0x34000009 }, + { 0x028009f0, 0x1c000001 }, + { 0x028009f2, 0x5c000001 }, + { 0x028009f4, 0x3c000005 }, + { 0x020009fa, 0x68000000 }, + { 0x15800a01, 0x30000001 }, + { 0x15000a03, 0x28000000 }, + { 0x15800a05, 0x1c000005 }, + { 0x15800a0f, 0x1c000001 }, + { 0x15800a13, 0x1c000015 }, + { 0x15800a2a, 0x1c000006 }, + { 0x15800a32, 0x1c000001 }, + { 0x15800a35, 0x1c000001 }, + { 0x15800a38, 0x1c000001 }, + { 0x15000a3c, 0x30000000 }, + { 0x15800a3e, 0x28000002 }, + { 0x15800a41, 0x30000001 }, + { 0x15800a47, 0x30000001 }, + { 0x15800a4b, 0x30000002 }, + { 0x15800a59, 0x1c000003 }, + { 0x15000a5e, 0x1c000000 }, + { 0x15800a66, 0x34000009 }, + { 0x15800a70, 0x30000001 }, + { 0x15800a72, 0x1c000002 }, + { 0x14800a81, 0x30000001 }, + { 0x14000a83, 0x28000000 }, + { 0x14800a85, 0x1c000008 }, + { 0x14800a8f, 0x1c000002 }, + { 0x14800a93, 0x1c000015 }, + { 0x14800aaa, 0x1c000006 }, + { 0x14800ab2, 0x1c000001 }, + { 0x14800ab5, 0x1c000004 }, + { 0x14000abc, 0x30000000 }, + { 0x14000abd, 0x1c000000 }, + { 0x14800abe, 0x28000002 }, + { 0x14800ac1, 0x30000004 }, + { 0x14800ac7, 0x30000001 }, + { 0x14000ac9, 0x28000000 }, + { 0x14800acb, 0x28000001 }, + { 0x14000acd, 0x30000000 }, + { 0x14000ad0, 0x1c000000 }, + { 0x14800ae0, 0x1c000001 }, + { 0x14800ae2, 0x30000001 }, + { 0x14800ae6, 0x34000009 }, + { 0x14000af1, 0x5c000000 }, + { 0x2b000b01, 0x30000000 }, + { 0x2b800b02, 0x28000001 }, + { 0x2b800b05, 0x1c000007 }, + { 0x2b800b0f, 0x1c000001 }, + { 0x2b800b13, 0x1c000015 }, + { 0x2b800b2a, 0x1c000006 }, + { 0x2b800b32, 0x1c000001 }, + { 0x2b800b35, 0x1c000004 }, + { 0x2b000b3c, 0x30000000 }, + { 0x2b000b3d, 0x1c000000 }, + { 0x2b000b3e, 0x28000000 }, + { 0x2b000b3f, 0x30000000 }, + { 0x2b000b40, 0x28000000 }, + { 0x2b800b41, 0x30000002 }, + { 0x2b800b47, 0x28000001 }, + { 0x2b800b4b, 0x28000001 }, + { 0x2b000b4d, 0x30000000 }, + { 0x2b000b56, 0x30000000 }, + { 0x2b000b57, 0x28000000 }, + { 0x2b800b5c, 0x1c000001 }, + { 0x2b800b5f, 0x1c000002 }, + { 0x2b800b66, 0x34000009 }, + { 0x2b000b70, 0x68000000 }, + { 0x2b000b71, 0x1c000000 }, + { 0x35000b82, 0x30000000 }, + { 0x35000b83, 0x1c000000 }, + { 0x35800b85, 0x1c000005 }, + { 0x35800b8e, 0x1c000002 }, + { 0x35800b92, 0x1c000003 }, + { 0x35800b99, 0x1c000001 }, + { 0x35000b9c, 0x1c000000 }, + { 0x35800b9e, 0x1c000001 }, + { 0x35800ba3, 0x1c000001 }, + { 0x35800ba8, 0x1c000002 }, + { 0x35800bae, 0x1c00000b }, + { 0x35800bbe, 0x28000001 }, + { 0x35000bc0, 0x30000000 }, + { 0x35800bc1, 0x28000001 }, + { 0x35800bc6, 0x28000002 }, + { 0x35800bca, 0x28000002 }, + { 0x35000bcd, 0x30000000 }, + { 0x35000bd7, 0x28000000 }, + { 0x35800be6, 0x34000009 }, + { 0x35800bf0, 0x3c000002 }, + { 0x35800bf3, 0x68000005 }, + { 0x35000bf9, 0x5c000000 }, + { 0x35000bfa, 0x68000000 }, + { 0x36800c01, 0x28000002 }, + { 0x36800c05, 0x1c000007 }, + { 0x36800c0e, 0x1c000002 }, + { 0x36800c12, 0x1c000016 }, + { 0x36800c2a, 0x1c000009 }, + { 0x36800c35, 0x1c000004 }, + { 0x36800c3e, 0x30000002 }, + { 0x36800c41, 0x28000003 }, + { 0x36800c46, 0x30000002 }, + { 0x36800c4a, 0x30000003 }, + { 0x36800c55, 0x30000001 }, + { 0x36800c60, 0x1c000001 }, + { 0x36800c66, 0x34000009 }, + { 0x1c800c82, 0x28000001 }, + { 0x1c800c85, 0x1c000007 }, + { 0x1c800c8e, 0x1c000002 }, + { 0x1c800c92, 0x1c000016 }, + { 0x1c800caa, 0x1c000009 }, + { 0x1c800cb5, 0x1c000004 }, + { 0x1c000cbc, 0x30000000 }, + { 0x1c000cbd, 0x1c000000 }, + { 0x1c000cbe, 0x28000000 }, + { 0x1c000cbf, 0x30000000 }, + { 0x1c800cc0, 0x28000004 }, + { 0x1c000cc6, 0x30000000 }, + { 0x1c800cc7, 0x28000001 }, + { 0x1c800cca, 0x28000001 }, + { 0x1c800ccc, 0x30000001 }, + { 0x1c800cd5, 0x28000001 }, + { 0x1c000cde, 0x1c000000 }, + { 0x1c800ce0, 0x1c000001 }, + { 0x1c800ce2, 0x30000001 }, + { 0x1c800ce6, 0x34000009 }, + { 0x1c800cf1, 0x68000001 }, + { 0x24800d02, 0x28000001 }, + { 0x24800d05, 0x1c000007 }, + { 0x24800d0e, 0x1c000002 }, + { 0x24800d12, 0x1c000016 }, + { 0x24800d2a, 0x1c00000f }, + { 0x24800d3e, 0x28000002 }, + { 0x24800d41, 0x30000002 }, + { 0x24800d46, 0x28000002 }, + { 0x24800d4a, 0x28000002 }, + { 0x24000d4d, 0x30000000 }, + { 0x24000d57, 0x28000000 }, + { 0x24800d60, 0x1c000001 }, + { 0x24800d66, 0x34000009 }, + { 0x2f800d82, 0x28000001 }, + { 0x2f800d85, 0x1c000011 }, + { 0x2f800d9a, 0x1c000017 }, + { 0x2f800db3, 0x1c000008 }, + { 0x2f000dbd, 0x1c000000 }, + { 0x2f800dc0, 0x1c000006 }, + { 0x2f000dca, 0x30000000 }, + { 0x2f800dcf, 0x28000002 }, + { 0x2f800dd2, 0x30000002 }, + { 0x2f000dd6, 0x30000000 }, + { 0x2f800dd8, 0x28000007 }, + { 0x2f800df2, 0x28000001 }, + { 0x2f000df4, 0x54000000 }, + { 0x38800e01, 0x1c00002f }, + { 0x38000e31, 0x30000000 }, + { 0x38800e32, 0x1c000001 }, + { 0x38800e34, 0x30000006 }, + { 0x09000e3f, 0x5c000000 }, + { 0x38800e40, 0x1c000005 }, + { 0x38000e46, 0x18000000 }, + { 0x38800e47, 0x30000007 }, + { 0x38000e4f, 0x54000000 }, + { 0x38800e50, 0x34000009 }, + { 0x38800e5a, 0x54000001 }, + { 0x20800e81, 0x1c000001 }, + { 0x20000e84, 0x1c000000 }, + { 0x20800e87, 0x1c000001 }, + { 0x20000e8a, 0x1c000000 }, + { 0x20000e8d, 0x1c000000 }, + { 0x20800e94, 0x1c000003 }, + { 0x20800e99, 0x1c000006 }, + { 0x20800ea1, 0x1c000002 }, + { 0x20000ea5, 0x1c000000 }, + { 0x20000ea7, 0x1c000000 }, + { 0x20800eaa, 0x1c000001 }, + { 0x20800ead, 0x1c000003 }, + { 0x20000eb1, 0x30000000 }, + { 0x20800eb2, 0x1c000001 }, + { 0x20800eb4, 0x30000005 }, + { 0x20800ebb, 0x30000001 }, + { 0x20000ebd, 0x1c000000 }, + { 0x20800ec0, 0x1c000004 }, + { 0x20000ec6, 0x18000000 }, + { 0x20800ec8, 0x30000005 }, + { 0x20800ed0, 0x34000009 }, + { 0x20800edc, 0x1c000001 }, + { 0x39000f00, 0x1c000000 }, + { 0x39800f01, 0x68000002 }, + { 0x39800f04, 0x5400000e }, + { 0x39800f13, 0x68000004 }, + { 0x39800f18, 0x30000001 }, + { 0x39800f1a, 0x68000005 }, + { 0x39800f20, 0x34000009 }, + { 0x39800f2a, 0x3c000009 }, + { 0x39000f34, 0x68000000 }, + { 0x39000f35, 0x30000000 }, + { 0x39000f36, 0x68000000 }, + { 0x39000f37, 0x30000000 }, + { 0x39000f38, 0x68000000 }, + { 0x39000f39, 0x30000000 }, + { 0x39000f3a, 0x58000000 }, + { 0x39000f3b, 0x48000000 }, + { 0x39000f3c, 0x58000000 }, + { 0x39000f3d, 0x48000000 }, + { 0x39800f3e, 0x28000001 }, + { 0x39800f40, 0x1c000007 }, + { 0x39800f49, 0x1c000021 }, + { 0x39800f71, 0x3000000d }, + { 0x39000f7f, 0x28000000 }, + { 0x39800f80, 0x30000004 }, + { 0x39000f85, 0x54000000 }, + { 0x39800f86, 0x30000001 }, + { 0x39800f88, 0x1c000003 }, + { 0x39800f90, 0x30000007 }, + { 0x39800f99, 0x30000023 }, + { 0x39800fbe, 0x68000007 }, + { 0x39000fc6, 0x30000000 }, + { 0x39800fc7, 0x68000005 }, + { 0x39000fcf, 0x68000000 }, + { 0x39800fd0, 0x54000001 }, + { 0x26801000, 0x1c000021 }, + { 0x26801023, 0x1c000004 }, + { 0x26801029, 0x1c000001 }, + { 0x2600102c, 0x28000000 }, + { 0x2680102d, 0x30000003 }, + { 0x26001031, 0x28000000 }, + { 0x26001032, 0x30000000 }, + { 0x26801036, 0x30000001 }, + { 0x26001038, 0x28000000 }, + { 0x26001039, 0x30000000 }, + { 0x26801040, 0x34000009 }, + { 0x2680104a, 0x54000005 }, + { 0x26801050, 0x1c000005 }, + { 0x26801056, 0x28000001 }, + { 0x26801058, 0x30000001 }, + { 0x100010a0, 0x24001c60 }, + { 0x100010a1, 0x24001c60 }, + { 0x100010a2, 0x24001c60 }, + { 0x100010a3, 0x24001c60 }, + { 0x100010a4, 0x24001c60 }, + { 0x100010a5, 0x24001c60 }, + { 0x100010a6, 0x24001c60 }, + { 0x100010a7, 0x24001c60 }, + { 0x100010a8, 0x24001c60 }, + { 0x100010a9, 0x24001c60 }, + { 0x100010aa, 0x24001c60 }, + { 0x100010ab, 0x24001c60 }, + { 0x100010ac, 0x24001c60 }, + { 0x100010ad, 0x24001c60 }, + { 0x100010ae, 0x24001c60 }, + { 0x100010af, 0x24001c60 }, + { 0x100010b0, 0x24001c60 }, + { 0x100010b1, 0x24001c60 }, + { 0x100010b2, 0x24001c60 }, + { 0x100010b3, 0x24001c60 }, + { 0x100010b4, 0x24001c60 }, + { 0x100010b5, 0x24001c60 }, + { 0x100010b6, 0x24001c60 }, + { 0x100010b7, 0x24001c60 }, + { 0x100010b8, 0x24001c60 }, + { 0x100010b9, 0x24001c60 }, + { 0x100010ba, 0x24001c60 }, + { 0x100010bb, 0x24001c60 }, + { 0x100010bc, 0x24001c60 }, + { 0x100010bd, 0x24001c60 }, + { 0x100010be, 0x24001c60 }, + { 0x100010bf, 0x24001c60 }, + { 0x100010c0, 0x24001c60 }, + { 0x100010c1, 0x24001c60 }, + { 0x100010c2, 0x24001c60 }, + { 0x100010c3, 0x24001c60 }, + { 0x100010c4, 0x24001c60 }, + { 0x100010c5, 0x24001c60 }, + { 0x108010d0, 0x1c00002a }, + { 0x090010fb, 0x54000000 }, + { 0x100010fc, 0x18000000 }, + { 0x17801100, 0x1c000059 }, + { 0x1780115f, 0x1c000043 }, + { 0x178011a8, 0x1c000051 }, + { 0x0f801200, 0x1c000048 }, + { 0x0f80124a, 0x1c000003 }, + { 0x0f801250, 0x1c000006 }, + { 0x0f001258, 0x1c000000 }, + { 0x0f80125a, 0x1c000003 }, + { 0x0f801260, 0x1c000028 }, + { 0x0f80128a, 0x1c000003 }, + { 0x0f801290, 0x1c000020 }, + { 0x0f8012b2, 0x1c000003 }, + { 0x0f8012b8, 0x1c000006 }, + { 0x0f0012c0, 0x1c000000 }, + { 0x0f8012c2, 0x1c000003 }, + { 0x0f8012c8, 0x1c00000e }, + { 0x0f8012d8, 0x1c000038 }, + { 0x0f801312, 0x1c000003 }, + { 0x0f801318, 0x1c000042 }, + { 0x0f00135f, 0x30000000 }, + { 0x0f001360, 0x68000000 }, + { 0x0f801361, 0x54000007 }, + { 0x0f801369, 0x3c000013 }, + { 0x0f801380, 0x1c00000f }, + { 0x0f801390, 0x68000009 }, + { 0x088013a0, 0x1c000054 }, + { 0x07801401, 0x1c00026b }, + { 0x0780166d, 0x54000001 }, + { 0x0780166f, 0x1c000007 }, + { 0x28001680, 0x74000000 }, + { 0x28801681, 0x1c000019 }, + { 0x2800169b, 0x58000000 }, + { 0x2800169c, 0x48000000 }, + { 0x2d8016a0, 0x1c00004a }, + { 0x098016eb, 0x54000002 }, + { 0x2d8016ee, 0x38000002 }, + { 0x32801700, 0x1c00000c }, + { 0x3280170e, 0x1c000003 }, + { 0x32801712, 0x30000002 }, + { 0x18801720, 0x1c000011 }, + { 0x18801732, 0x30000002 }, + { 0x09801735, 0x54000001 }, + { 0x06801740, 0x1c000011 }, + { 0x06801752, 0x30000001 }, + { 0x33801760, 0x1c00000c }, + { 0x3380176e, 0x1c000002 }, + { 0x33801772, 0x30000001 }, + { 0x1f801780, 0x1c000033 }, + { 0x1f8017b4, 0x04000001 }, + { 0x1f0017b6, 0x28000000 }, + { 0x1f8017b7, 0x30000006 }, + { 0x1f8017be, 0x28000007 }, + { 0x1f0017c6, 0x30000000 }, + { 0x1f8017c7, 0x28000001 }, + { 0x1f8017c9, 0x3000000a }, + { 0x1f8017d4, 0x54000002 }, + { 0x1f0017d7, 0x18000000 }, + { 0x1f8017d8, 0x54000002 }, + { 0x1f0017db, 0x5c000000 }, + { 0x1f0017dc, 0x1c000000 }, + { 0x1f0017dd, 0x30000000 }, + { 0x1f8017e0, 0x34000009 }, + { 0x1f8017f0, 0x3c000009 }, + { 0x25801800, 0x54000005 }, + { 0x25001806, 0x44000000 }, + { 0x25801807, 0x54000003 }, + { 0x2580180b, 0x30000002 }, + { 0x2500180e, 0x74000000 }, + { 0x25801810, 0x34000009 }, + { 0x25801820, 0x1c000022 }, + { 0x25001843, 0x18000000 }, + { 0x25801844, 0x1c000033 }, + { 0x25801880, 0x1c000028 }, + { 0x250018a9, 0x30000000 }, + { 0x22801900, 0x1c00001c }, + { 0x22801920, 0x30000002 }, + { 0x22801923, 0x28000003 }, + { 0x22801927, 0x30000001 }, + { 0x22801929, 0x28000002 }, + { 0x22801930, 0x28000001 }, + { 0x22001932, 0x30000000 }, + { 0x22801933, 0x28000005 }, + { 0x22801939, 0x30000002 }, + { 0x22001940, 0x68000000 }, + { 0x22801944, 0x54000001 }, + { 0x22801946, 0x34000009 }, + { 0x34801950, 0x1c00001d }, + { 0x34801970, 0x1c000004 }, + { 0x27801980, 0x1c000029 }, + { 0x278019b0, 0x28000010 }, + { 0x278019c1, 0x1c000006 }, + { 0x278019c8, 0x28000001 }, + { 0x278019d0, 0x34000009 }, + { 0x278019de, 0x54000001 }, + { 0x1f8019e0, 0x6800001f }, + { 0x05801a00, 0x1c000016 }, + { 0x05801a17, 0x30000001 }, + { 0x05801a19, 0x28000002 }, + { 0x05801a1e, 0x54000001 }, + { 0x3d801b00, 0x30000003 }, + { 0x3d001b04, 0x28000000 }, + { 0x3d801b05, 0x1c00002e }, + { 0x3d001b34, 0x30000000 }, + { 0x3d001b35, 0x28000000 }, + { 0x3d801b36, 0x30000004 }, + { 0x3d001b3b, 0x28000000 }, + { 0x3d001b3c, 0x30000000 }, + { 0x3d801b3d, 0x28000004 }, + { 0x3d001b42, 0x30000000 }, + { 0x3d801b43, 0x28000001 }, + { 0x3d801b45, 0x1c000006 }, + { 0x3d801b50, 0x34000009 }, + { 0x3d801b5a, 0x54000006 }, + { 0x3d801b61, 0x68000009 }, + { 0x3d801b6b, 0x30000008 }, + { 0x3d801b74, 0x68000008 }, + { 0x21801d00, 0x1400002b }, + { 0x21801d2c, 0x18000035 }, + { 0x21801d62, 0x14000015 }, + { 0x0c001d78, 0x18000000 }, + { 0x21801d79, 0x14000003 }, + { 0x21001d7d, 0x14000ee6 }, + { 0x21801d7e, 0x1400001c }, + { 0x21801d9b, 0x18000024 }, + { 0x1b801dc0, 0x3000000a }, + { 0x1b801dfe, 0x30000001 }, + { 0x21001e00, 0x24000001 }, + { 0x21001e01, 0x1400ffff }, + { 0x21001e02, 0x24000001 }, + { 0x21001e03, 0x1400ffff }, + { 0x21001e04, 0x24000001 }, + { 0x21001e05, 0x1400ffff }, + { 0x21001e06, 0x24000001 }, + { 0x21001e07, 0x1400ffff }, + { 0x21001e08, 0x24000001 }, + { 0x21001e09, 0x1400ffff }, + { 0x21001e0a, 0x24000001 }, + { 0x21001e0b, 0x1400ffff }, + { 0x21001e0c, 0x24000001 }, + { 0x21001e0d, 0x1400ffff }, + { 0x21001e0e, 0x24000001 }, + { 0x21001e0f, 0x1400ffff }, + { 0x21001e10, 0x24000001 }, + { 0x21001e11, 0x1400ffff }, + { 0x21001e12, 0x24000001 }, + { 0x21001e13, 0x1400ffff }, + { 0x21001e14, 0x24000001 }, + { 0x21001e15, 0x1400ffff }, + { 0x21001e16, 0x24000001 }, + { 0x21001e17, 0x1400ffff }, + { 0x21001e18, 0x24000001 }, + { 0x21001e19, 0x1400ffff }, + { 0x21001e1a, 0x24000001 }, + { 0x21001e1b, 0x1400ffff }, + { 0x21001e1c, 0x24000001 }, + { 0x21001e1d, 0x1400ffff }, + { 0x21001e1e, 0x24000001 }, + { 0x21001e1f, 0x1400ffff }, + { 0x21001e20, 0x24000001 }, + { 0x21001e21, 0x1400ffff }, + { 0x21001e22, 0x24000001 }, + { 0x21001e23, 0x1400ffff }, + { 0x21001e24, 0x24000001 }, + { 0x21001e25, 0x1400ffff }, + { 0x21001e26, 0x24000001 }, + { 0x21001e27, 0x1400ffff }, + { 0x21001e28, 0x24000001 }, + { 0x21001e29, 0x1400ffff }, + { 0x21001e2a, 0x24000001 }, + { 0x21001e2b, 0x1400ffff }, + { 0x21001e2c, 0x24000001 }, + { 0x21001e2d, 0x1400ffff }, + { 0x21001e2e, 0x24000001 }, + { 0x21001e2f, 0x1400ffff }, + { 0x21001e30, 0x24000001 }, + { 0x21001e31, 0x1400ffff }, + { 0x21001e32, 0x24000001 }, + { 0x21001e33, 0x1400ffff }, + { 0x21001e34, 0x24000001 }, + { 0x21001e35, 0x1400ffff }, + { 0x21001e36, 0x24000001 }, + { 0x21001e37, 0x1400ffff }, + { 0x21001e38, 0x24000001 }, + { 0x21001e39, 0x1400ffff }, + { 0x21001e3a, 0x24000001 }, + { 0x21001e3b, 0x1400ffff }, + { 0x21001e3c, 0x24000001 }, + { 0x21001e3d, 0x1400ffff }, + { 0x21001e3e, 0x24000001 }, + { 0x21001e3f, 0x1400ffff }, + { 0x21001e40, 0x24000001 }, + { 0x21001e41, 0x1400ffff }, + { 0x21001e42, 0x24000001 }, + { 0x21001e43, 0x1400ffff }, + { 0x21001e44, 0x24000001 }, + { 0x21001e45, 0x1400ffff }, + { 0x21001e46, 0x24000001 }, + { 0x21001e47, 0x1400ffff }, + { 0x21001e48, 0x24000001 }, + { 0x21001e49, 0x1400ffff }, + { 0x21001e4a, 0x24000001 }, + { 0x21001e4b, 0x1400ffff }, + { 0x21001e4c, 0x24000001 }, + { 0x21001e4d, 0x1400ffff }, + { 0x21001e4e, 0x24000001 }, + { 0x21001e4f, 0x1400ffff }, + { 0x21001e50, 0x24000001 }, + { 0x21001e51, 0x1400ffff }, + { 0x21001e52, 0x24000001 }, + { 0x21001e53, 0x1400ffff }, + { 0x21001e54, 0x24000001 }, + { 0x21001e55, 0x1400ffff }, + { 0x21001e56, 0x24000001 }, + { 0x21001e57, 0x1400ffff }, + { 0x21001e58, 0x24000001 }, + { 0x21001e59, 0x1400ffff }, + { 0x21001e5a, 0x24000001 }, + { 0x21001e5b, 0x1400ffff }, + { 0x21001e5c, 0x24000001 }, + { 0x21001e5d, 0x1400ffff }, + { 0x21001e5e, 0x24000001 }, + { 0x21001e5f, 0x1400ffff }, + { 0x21001e60, 0x24000001 }, + { 0x21001e61, 0x1400ffff }, + { 0x21001e62, 0x24000001 }, + { 0x21001e63, 0x1400ffff }, + { 0x21001e64, 0x24000001 }, + { 0x21001e65, 0x1400ffff }, + { 0x21001e66, 0x24000001 }, + { 0x21001e67, 0x1400ffff }, + { 0x21001e68, 0x24000001 }, + { 0x21001e69, 0x1400ffff }, + { 0x21001e6a, 0x24000001 }, + { 0x21001e6b, 0x1400ffff }, + { 0x21001e6c, 0x24000001 }, + { 0x21001e6d, 0x1400ffff }, + { 0x21001e6e, 0x24000001 }, + { 0x21001e6f, 0x1400ffff }, + { 0x21001e70, 0x24000001 }, + { 0x21001e71, 0x1400ffff }, + { 0x21001e72, 0x24000001 }, + { 0x21001e73, 0x1400ffff }, + { 0x21001e74, 0x24000001 }, + { 0x21001e75, 0x1400ffff }, + { 0x21001e76, 0x24000001 }, + { 0x21001e77, 0x1400ffff }, + { 0x21001e78, 0x24000001 }, + { 0x21001e79, 0x1400ffff }, + { 0x21001e7a, 0x24000001 }, + { 0x21001e7b, 0x1400ffff }, + { 0x21001e7c, 0x24000001 }, + { 0x21001e7d, 0x1400ffff }, + { 0x21001e7e, 0x24000001 }, + { 0x21001e7f, 0x1400ffff }, + { 0x21001e80, 0x24000001 }, + { 0x21001e81, 0x1400ffff }, + { 0x21001e82, 0x24000001 }, + { 0x21001e83, 0x1400ffff }, + { 0x21001e84, 0x24000001 }, + { 0x21001e85, 0x1400ffff }, + { 0x21001e86, 0x24000001 }, + { 0x21001e87, 0x1400ffff }, + { 0x21001e88, 0x24000001 }, + { 0x21001e89, 0x1400ffff }, + { 0x21001e8a, 0x24000001 }, + { 0x21001e8b, 0x1400ffff }, + { 0x21001e8c, 0x24000001 }, + { 0x21001e8d, 0x1400ffff }, + { 0x21001e8e, 0x24000001 }, + { 0x21001e8f, 0x1400ffff }, + { 0x21001e90, 0x24000001 }, + { 0x21001e91, 0x1400ffff }, + { 0x21001e92, 0x24000001 }, + { 0x21001e93, 0x1400ffff }, + { 0x21001e94, 0x24000001 }, + { 0x21001e95, 0x1400ffff }, + { 0x21801e96, 0x14000004 }, + { 0x21001e9b, 0x1400ffc5 }, + { 0x21001ea0, 0x24000001 }, + { 0x21001ea1, 0x1400ffff }, + { 0x21001ea2, 0x24000001 }, + { 0x21001ea3, 0x1400ffff }, + { 0x21001ea4, 0x24000001 }, + { 0x21001ea5, 0x1400ffff }, + { 0x21001ea6, 0x24000001 }, + { 0x21001ea7, 0x1400ffff }, + { 0x21001ea8, 0x24000001 }, + { 0x21001ea9, 0x1400ffff }, + { 0x21001eaa, 0x24000001 }, + { 0x21001eab, 0x1400ffff }, + { 0x21001eac, 0x24000001 }, + { 0x21001ead, 0x1400ffff }, + { 0x21001eae, 0x24000001 }, + { 0x21001eaf, 0x1400ffff }, + { 0x21001eb0, 0x24000001 }, + { 0x21001eb1, 0x1400ffff }, + { 0x21001eb2, 0x24000001 }, + { 0x21001eb3, 0x1400ffff }, + { 0x21001eb4, 0x24000001 }, + { 0x21001eb5, 0x1400ffff }, + { 0x21001eb6, 0x24000001 }, + { 0x21001eb7, 0x1400ffff }, + { 0x21001eb8, 0x24000001 }, + { 0x21001eb9, 0x1400ffff }, + { 0x21001eba, 0x24000001 }, + { 0x21001ebb, 0x1400ffff }, + { 0x21001ebc, 0x24000001 }, + { 0x21001ebd, 0x1400ffff }, + { 0x21001ebe, 0x24000001 }, + { 0x21001ebf, 0x1400ffff }, + { 0x21001ec0, 0x24000001 }, + { 0x21001ec1, 0x1400ffff }, + { 0x21001ec2, 0x24000001 }, + { 0x21001ec3, 0x1400ffff }, + { 0x21001ec4, 0x24000001 }, + { 0x21001ec5, 0x1400ffff }, + { 0x21001ec6, 0x24000001 }, + { 0x21001ec7, 0x1400ffff }, + { 0x21001ec8, 0x24000001 }, + { 0x21001ec9, 0x1400ffff }, + { 0x21001eca, 0x24000001 }, + { 0x21001ecb, 0x1400ffff }, + { 0x21001ecc, 0x24000001 }, + { 0x21001ecd, 0x1400ffff }, + { 0x21001ece, 0x24000001 }, + { 0x21001ecf, 0x1400ffff }, + { 0x21001ed0, 0x24000001 }, + { 0x21001ed1, 0x1400ffff }, + { 0x21001ed2, 0x24000001 }, + { 0x21001ed3, 0x1400ffff }, + { 0x21001ed4, 0x24000001 }, + { 0x21001ed5, 0x1400ffff }, + { 0x21001ed6, 0x24000001 }, + { 0x21001ed7, 0x1400ffff }, + { 0x21001ed8, 0x24000001 }, + { 0x21001ed9, 0x1400ffff }, + { 0x21001eda, 0x24000001 }, + { 0x21001edb, 0x1400ffff }, + { 0x21001edc, 0x24000001 }, + { 0x21001edd, 0x1400ffff }, + { 0x21001ede, 0x24000001 }, + { 0x21001edf, 0x1400ffff }, + { 0x21001ee0, 0x24000001 }, + { 0x21001ee1, 0x1400ffff }, + { 0x21001ee2, 0x24000001 }, + { 0x21001ee3, 0x1400ffff }, + { 0x21001ee4, 0x24000001 }, + { 0x21001ee5, 0x1400ffff }, + { 0x21001ee6, 0x24000001 }, + { 0x21001ee7, 0x1400ffff }, + { 0x21001ee8, 0x24000001 }, + { 0x21001ee9, 0x1400ffff }, + { 0x21001eea, 0x24000001 }, + { 0x21001eeb, 0x1400ffff }, + { 0x21001eec, 0x24000001 }, + { 0x21001eed, 0x1400ffff }, + { 0x21001eee, 0x24000001 }, + { 0x21001eef, 0x1400ffff }, + { 0x21001ef0, 0x24000001 }, + { 0x21001ef1, 0x1400ffff }, + { 0x21001ef2, 0x24000001 }, + { 0x21001ef3, 0x1400ffff }, + { 0x21001ef4, 0x24000001 }, + { 0x21001ef5, 0x1400ffff }, + { 0x21001ef6, 0x24000001 }, + { 0x21001ef7, 0x1400ffff }, + { 0x21001ef8, 0x24000001 }, + { 0x21001ef9, 0x1400ffff }, + { 0x13001f00, 0x14000008 }, + { 0x13001f01, 0x14000008 }, + { 0x13001f02, 0x14000008 }, + { 0x13001f03, 0x14000008 }, + { 0x13001f04, 0x14000008 }, + { 0x13001f05, 0x14000008 }, + { 0x13001f06, 0x14000008 }, + { 0x13001f07, 0x14000008 }, + { 0x13001f08, 0x2400fff8 }, + { 0x13001f09, 0x2400fff8 }, + { 0x13001f0a, 0x2400fff8 }, + { 0x13001f0b, 0x2400fff8 }, + { 0x13001f0c, 0x2400fff8 }, + { 0x13001f0d, 0x2400fff8 }, + { 0x13001f0e, 0x2400fff8 }, + { 0x13001f0f, 0x2400fff8 }, + { 0x13001f10, 0x14000008 }, + { 0x13001f11, 0x14000008 }, + { 0x13001f12, 0x14000008 }, + { 0x13001f13, 0x14000008 }, + { 0x13001f14, 0x14000008 }, + { 0x13001f15, 0x14000008 }, + { 0x13001f18, 0x2400fff8 }, + { 0x13001f19, 0x2400fff8 }, + { 0x13001f1a, 0x2400fff8 }, + { 0x13001f1b, 0x2400fff8 }, + { 0x13001f1c, 0x2400fff8 }, + { 0x13001f1d, 0x2400fff8 }, + { 0x13001f20, 0x14000008 }, + { 0x13001f21, 0x14000008 }, + { 0x13001f22, 0x14000008 }, + { 0x13001f23, 0x14000008 }, + { 0x13001f24, 0x14000008 }, + { 0x13001f25, 0x14000008 }, + { 0x13001f26, 0x14000008 }, + { 0x13001f27, 0x14000008 }, + { 0x13001f28, 0x2400fff8 }, + { 0x13001f29, 0x2400fff8 }, + { 0x13001f2a, 0x2400fff8 }, + { 0x13001f2b, 0x2400fff8 }, + { 0x13001f2c, 0x2400fff8 }, + { 0x13001f2d, 0x2400fff8 }, + { 0x13001f2e, 0x2400fff8 }, + { 0x13001f2f, 0x2400fff8 }, + { 0x13001f30, 0x14000008 }, + { 0x13001f31, 0x14000008 }, + { 0x13001f32, 0x14000008 }, + { 0x13001f33, 0x14000008 }, + { 0x13001f34, 0x14000008 }, + { 0x13001f35, 0x14000008 }, + { 0x13001f36, 0x14000008 }, + { 0x13001f37, 0x14000008 }, + { 0x13001f38, 0x2400fff8 }, + { 0x13001f39, 0x2400fff8 }, + { 0x13001f3a, 0x2400fff8 }, + { 0x13001f3b, 0x2400fff8 }, + { 0x13001f3c, 0x2400fff8 }, + { 0x13001f3d, 0x2400fff8 }, + { 0x13001f3e, 0x2400fff8 }, + { 0x13001f3f, 0x2400fff8 }, + { 0x13001f40, 0x14000008 }, + { 0x13001f41, 0x14000008 }, + { 0x13001f42, 0x14000008 }, + { 0x13001f43, 0x14000008 }, + { 0x13001f44, 0x14000008 }, + { 0x13001f45, 0x14000008 }, + { 0x13001f48, 0x2400fff8 }, + { 0x13001f49, 0x2400fff8 }, + { 0x13001f4a, 0x2400fff8 }, + { 0x13001f4b, 0x2400fff8 }, + { 0x13001f4c, 0x2400fff8 }, + { 0x13001f4d, 0x2400fff8 }, + { 0x13001f50, 0x14000000 }, + { 0x13001f51, 0x14000008 }, + { 0x13001f52, 0x14000000 }, + { 0x13001f53, 0x14000008 }, + { 0x13001f54, 0x14000000 }, + { 0x13001f55, 0x14000008 }, + { 0x13001f56, 0x14000000 }, + { 0x13001f57, 0x14000008 }, + { 0x13001f59, 0x2400fff8 }, + { 0x13001f5b, 0x2400fff8 }, + { 0x13001f5d, 0x2400fff8 }, + { 0x13001f5f, 0x2400fff8 }, + { 0x13001f60, 0x14000008 }, + { 0x13001f61, 0x14000008 }, + { 0x13001f62, 0x14000008 }, + { 0x13001f63, 0x14000008 }, + { 0x13001f64, 0x14000008 }, + { 0x13001f65, 0x14000008 }, + { 0x13001f66, 0x14000008 }, + { 0x13001f67, 0x14000008 }, + { 0x13001f68, 0x2400fff8 }, + { 0x13001f69, 0x2400fff8 }, + { 0x13001f6a, 0x2400fff8 }, + { 0x13001f6b, 0x2400fff8 }, + { 0x13001f6c, 0x2400fff8 }, + { 0x13001f6d, 0x2400fff8 }, + { 0x13001f6e, 0x2400fff8 }, + { 0x13001f6f, 0x2400fff8 }, + { 0x13001f70, 0x1400004a }, + { 0x13001f71, 0x1400004a }, + { 0x13001f72, 0x14000056 }, + { 0x13001f73, 0x14000056 }, + { 0x13001f74, 0x14000056 }, + { 0x13001f75, 0x14000056 }, + { 0x13001f76, 0x14000064 }, + { 0x13001f77, 0x14000064 }, + { 0x13001f78, 0x14000080 }, + { 0x13001f79, 0x14000080 }, + { 0x13001f7a, 0x14000070 }, + { 0x13001f7b, 0x14000070 }, + { 0x13001f7c, 0x1400007e }, + { 0x13001f7d, 0x1400007e }, + { 0x13001f80, 0x14000008 }, + { 0x13001f81, 0x14000008 }, + { 0x13001f82, 0x14000008 }, + { 0x13001f83, 0x14000008 }, + { 0x13001f84, 0x14000008 }, + { 0x13001f85, 0x14000008 }, + { 0x13001f86, 0x14000008 }, + { 0x13001f87, 0x14000008 }, + { 0x13001f88, 0x2000fff8 }, + { 0x13001f89, 0x2000fff8 }, + { 0x13001f8a, 0x2000fff8 }, + { 0x13001f8b, 0x2000fff8 }, + { 0x13001f8c, 0x2000fff8 }, + { 0x13001f8d, 0x2000fff8 }, + { 0x13001f8e, 0x2000fff8 }, + { 0x13001f8f, 0x2000fff8 }, + { 0x13001f90, 0x14000008 }, + { 0x13001f91, 0x14000008 }, + { 0x13001f92, 0x14000008 }, + { 0x13001f93, 0x14000008 }, + { 0x13001f94, 0x14000008 }, + { 0x13001f95, 0x14000008 }, + { 0x13001f96, 0x14000008 }, + { 0x13001f97, 0x14000008 }, + { 0x13001f98, 0x2000fff8 }, + { 0x13001f99, 0x2000fff8 }, + { 0x13001f9a, 0x2000fff8 }, + { 0x13001f9b, 0x2000fff8 }, + { 0x13001f9c, 0x2000fff8 }, + { 0x13001f9d, 0x2000fff8 }, + { 0x13001f9e, 0x2000fff8 }, + { 0x13001f9f, 0x2000fff8 }, + { 0x13001fa0, 0x14000008 }, + { 0x13001fa1, 0x14000008 }, + { 0x13001fa2, 0x14000008 }, + { 0x13001fa3, 0x14000008 }, + { 0x13001fa4, 0x14000008 }, + { 0x13001fa5, 0x14000008 }, + { 0x13001fa6, 0x14000008 }, + { 0x13001fa7, 0x14000008 }, + { 0x13001fa8, 0x2000fff8 }, + { 0x13001fa9, 0x2000fff8 }, + { 0x13001faa, 0x2000fff8 }, + { 0x13001fab, 0x2000fff8 }, + { 0x13001fac, 0x2000fff8 }, + { 0x13001fad, 0x2000fff8 }, + { 0x13001fae, 0x2000fff8 }, + { 0x13001faf, 0x2000fff8 }, + { 0x13001fb0, 0x14000008 }, + { 0x13001fb1, 0x14000008 }, + { 0x13001fb2, 0x14000000 }, + { 0x13001fb3, 0x14000009 }, + { 0x13001fb4, 0x14000000 }, + { 0x13801fb6, 0x14000001 }, + { 0x13001fb8, 0x2400fff8 }, + { 0x13001fb9, 0x2400fff8 }, + { 0x13001fba, 0x2400ffb6 }, + { 0x13001fbb, 0x2400ffb6 }, + { 0x13001fbc, 0x2000fff7 }, + { 0x13001fbd, 0x60000000 }, + { 0x13001fbe, 0x1400e3db }, + { 0x13801fbf, 0x60000002 }, + { 0x13001fc2, 0x14000000 }, + { 0x13001fc3, 0x14000009 }, + { 0x13001fc4, 0x14000000 }, + { 0x13801fc6, 0x14000001 }, + { 0x13001fc8, 0x2400ffaa }, + { 0x13001fc9, 0x2400ffaa }, + { 0x13001fca, 0x2400ffaa }, + { 0x13001fcb, 0x2400ffaa }, + { 0x13001fcc, 0x2000fff7 }, + { 0x13801fcd, 0x60000002 }, + { 0x13001fd0, 0x14000008 }, + { 0x13001fd1, 0x14000008 }, + { 0x13801fd2, 0x14000001 }, + { 0x13801fd6, 0x14000001 }, + { 0x13001fd8, 0x2400fff8 }, + { 0x13001fd9, 0x2400fff8 }, + { 0x13001fda, 0x2400ff9c }, + { 0x13001fdb, 0x2400ff9c }, + { 0x13801fdd, 0x60000002 }, + { 0x13001fe0, 0x14000008 }, + { 0x13001fe1, 0x14000008 }, + { 0x13801fe2, 0x14000002 }, + { 0x13001fe5, 0x14000007 }, + { 0x13801fe6, 0x14000001 }, + { 0x13001fe8, 0x2400fff8 }, + { 0x13001fe9, 0x2400fff8 }, + { 0x13001fea, 0x2400ff90 }, + { 0x13001feb, 0x2400ff90 }, + { 0x13001fec, 0x2400fff9 }, + { 0x13801fed, 0x60000002 }, + { 0x13001ff2, 0x14000000 }, + { 0x13001ff3, 0x14000009 }, + { 0x13001ff4, 0x14000000 }, + { 0x13801ff6, 0x14000001 }, + { 0x13001ff8, 0x2400ff80 }, + { 0x13001ff9, 0x2400ff80 }, + { 0x13001ffa, 0x2400ff82 }, + { 0x13001ffb, 0x2400ff82 }, + { 0x13001ffc, 0x2000fff7 }, + { 0x13801ffd, 0x60000001 }, + { 0x09802000, 0x7400000a }, + { 0x0980200b, 0x04000004 }, + { 0x09802010, 0x44000005 }, + { 0x09802016, 0x54000001 }, + { 0x09002018, 0x50000000 }, + { 0x09002019, 0x4c000000 }, + { 0x0900201a, 0x58000000 }, + { 0x0980201b, 0x50000001 }, + { 0x0900201d, 0x4c000000 }, + { 0x0900201e, 0x58000000 }, + { 0x0900201f, 0x50000000 }, + { 0x09802020, 0x54000007 }, + { 0x09002028, 0x6c000000 }, + { 0x09002029, 0x70000000 }, + { 0x0980202a, 0x04000004 }, + { 0x0900202f, 0x74000000 }, + { 0x09802030, 0x54000008 }, + { 0x09002039, 0x50000000 }, + { 0x0900203a, 0x4c000000 }, + { 0x0980203b, 0x54000003 }, + { 0x0980203f, 0x40000001 }, + { 0x09802041, 0x54000002 }, + { 0x09002044, 0x64000000 }, + { 0x09002045, 0x58000000 }, + { 0x09002046, 0x48000000 }, + { 0x09802047, 0x5400000a }, + { 0x09002052, 0x64000000 }, + { 0x09002053, 0x54000000 }, + { 0x09002054, 0x40000000 }, + { 0x09802055, 0x54000009 }, + { 0x0900205f, 0x74000000 }, + { 0x09802060, 0x04000003 }, + { 0x0980206a, 0x04000005 }, + { 0x09002070, 0x3c000000 }, + { 0x21002071, 0x14000000 }, + { 0x09802074, 0x3c000005 }, + { 0x0980207a, 0x64000002 }, + { 0x0900207d, 0x58000000 }, + { 0x0900207e, 0x48000000 }, + { 0x2100207f, 0x14000000 }, + { 0x09802080, 0x3c000009 }, + { 0x0980208a, 0x64000002 }, + { 0x0900208d, 0x58000000 }, + { 0x0900208e, 0x48000000 }, + { 0x21802090, 0x18000004 }, + { 0x098020a0, 0x5c000015 }, + { 0x1b8020d0, 0x3000000c }, + { 0x1b8020dd, 0x2c000003 }, + { 0x1b0020e1, 0x30000000 }, + { 0x1b8020e2, 0x2c000002 }, + { 0x1b8020e5, 0x3000000a }, + { 0x09802100, 0x68000001 }, + { 0x09002102, 0x24000000 }, + { 0x09802103, 0x68000003 }, + { 0x09002107, 0x24000000 }, + { 0x09802108, 0x68000001 }, + { 0x0900210a, 0x14000000 }, + { 0x0980210b, 0x24000002 }, + { 0x0980210e, 0x14000001 }, + { 0x09802110, 0x24000002 }, + { 0x09002113, 0x14000000 }, + { 0x09002114, 0x68000000 }, + { 0x09002115, 0x24000000 }, + { 0x09802116, 0x68000002 }, + { 0x09802119, 0x24000004 }, + { 0x0980211e, 0x68000005 }, + { 0x09002124, 0x24000000 }, + { 0x09002125, 0x68000000 }, + { 0x13002126, 0x2400e2a3 }, + { 0x09002127, 0x68000000 }, + { 0x09002128, 0x24000000 }, + { 0x09002129, 0x68000000 }, + { 0x2100212a, 0x2400df41 }, + { 0x2100212b, 0x2400dfba }, + { 0x0980212c, 0x24000001 }, + { 0x0900212e, 0x68000000 }, + { 0x0900212f, 0x14000000 }, + { 0x09802130, 0x24000001 }, + { 0x21002132, 0x2400001c }, + { 0x09002133, 0x24000000 }, + { 0x09002134, 0x14000000 }, + { 0x09802135, 0x1c000003 }, + { 0x09002139, 0x14000000 }, + { 0x0980213a, 0x68000001 }, + { 0x0980213c, 0x14000001 }, + { 0x0980213e, 0x24000001 }, + { 0x09802140, 0x64000004 }, + { 0x09002145, 0x24000000 }, + { 0x09802146, 0x14000003 }, + { 0x0900214a, 0x68000000 }, + { 0x0900214b, 0x64000000 }, + { 0x0980214c, 0x68000001 }, + { 0x2100214e, 0x1400ffe4 }, + { 0x09802153, 0x3c00000c }, + { 0x09002160, 0x38000010 }, + { 0x09002161, 0x38000010 }, + { 0x09002162, 0x38000010 }, + { 0x09002163, 0x38000010 }, + { 0x09002164, 0x38000010 }, + { 0x09002165, 0x38000010 }, + { 0x09002166, 0x38000010 }, + { 0x09002167, 0x38000010 }, + { 0x09002168, 0x38000010 }, + { 0x09002169, 0x38000010 }, + { 0x0900216a, 0x38000010 }, + { 0x0900216b, 0x38000010 }, + { 0x0900216c, 0x38000010 }, + { 0x0900216d, 0x38000010 }, + { 0x0900216e, 0x38000010 }, + { 0x0900216f, 0x38000010 }, + { 0x09002170, 0x3800fff0 }, + { 0x09002171, 0x3800fff0 }, + { 0x09002172, 0x3800fff0 }, + { 0x09002173, 0x3800fff0 }, + { 0x09002174, 0x3800fff0 }, + { 0x09002175, 0x3800fff0 }, + { 0x09002176, 0x3800fff0 }, + { 0x09002177, 0x3800fff0 }, + { 0x09002178, 0x3800fff0 }, + { 0x09002179, 0x3800fff0 }, + { 0x0900217a, 0x3800fff0 }, + { 0x0900217b, 0x3800fff0 }, + { 0x0900217c, 0x3800fff0 }, + { 0x0900217d, 0x3800fff0 }, + { 0x0900217e, 0x3800fff0 }, + { 0x0900217f, 0x3800fff0 }, + { 0x09802180, 0x38000002 }, + { 0x09002183, 0x24000001 }, + { 0x21002184, 0x1400ffff }, + { 0x09802190, 0x64000004 }, + { 0x09802195, 0x68000004 }, + { 0x0980219a, 0x64000001 }, + { 0x0980219c, 0x68000003 }, + { 0x090021a0, 0x64000000 }, + { 0x098021a1, 0x68000001 }, + { 0x090021a3, 0x64000000 }, + { 0x098021a4, 0x68000001 }, + { 0x090021a6, 0x64000000 }, + { 0x098021a7, 0x68000006 }, + { 0x090021ae, 0x64000000 }, + { 0x098021af, 0x6800001e }, + { 0x098021ce, 0x64000001 }, + { 0x098021d0, 0x68000001 }, + { 0x090021d2, 0x64000000 }, + { 0x090021d3, 0x68000000 }, + { 0x090021d4, 0x64000000 }, + { 0x098021d5, 0x6800001e }, + { 0x098021f4, 0x6400010b }, + { 0x09802300, 0x68000007 }, + { 0x09802308, 0x64000003 }, + { 0x0980230c, 0x68000013 }, + { 0x09802320, 0x64000001 }, + { 0x09802322, 0x68000006 }, + { 0x09002329, 0x58000000 }, + { 0x0900232a, 0x48000000 }, + { 0x0980232b, 0x68000050 }, + { 0x0900237c, 0x64000000 }, + { 0x0980237d, 0x6800001d }, + { 0x0980239b, 0x64000018 }, + { 0x098023b4, 0x68000027 }, + { 0x098023dc, 0x64000005 }, + { 0x098023e2, 0x68000005 }, + { 0x09802400, 0x68000026 }, + { 0x09802440, 0x6800000a }, + { 0x09802460, 0x3c00003b }, + { 0x0980249c, 0x68000019 }, + { 0x090024b6, 0x6800001a }, + { 0x090024b7, 0x6800001a }, + { 0x090024b8, 0x6800001a }, + { 0x090024b9, 0x6800001a }, + { 0x090024ba, 0x6800001a }, + { 0x090024bb, 0x6800001a }, + { 0x090024bc, 0x6800001a }, + { 0x090024bd, 0x6800001a }, + { 0x090024be, 0x6800001a }, + { 0x090024bf, 0x6800001a }, + { 0x090024c0, 0x6800001a }, + { 0x090024c1, 0x6800001a }, + { 0x090024c2, 0x6800001a }, + { 0x090024c3, 0x6800001a }, + { 0x090024c4, 0x6800001a }, + { 0x090024c5, 0x6800001a }, + { 0x090024c6, 0x6800001a }, + { 0x090024c7, 0x6800001a }, + { 0x090024c8, 0x6800001a }, + { 0x090024c9, 0x6800001a }, + { 0x090024ca, 0x6800001a }, + { 0x090024cb, 0x6800001a }, + { 0x090024cc, 0x6800001a }, + { 0x090024cd, 0x6800001a }, + { 0x090024ce, 0x6800001a }, + { 0x090024cf, 0x6800001a }, + { 0x090024d0, 0x6800ffe6 }, + { 0x090024d1, 0x6800ffe6 }, + { 0x090024d2, 0x6800ffe6 }, + { 0x090024d3, 0x6800ffe6 }, + { 0x090024d4, 0x6800ffe6 }, + { 0x090024d5, 0x6800ffe6 }, + { 0x090024d6, 0x6800ffe6 }, + { 0x090024d7, 0x6800ffe6 }, + { 0x090024d8, 0x6800ffe6 }, + { 0x090024d9, 0x6800ffe6 }, + { 0x090024da, 0x6800ffe6 }, + { 0x090024db, 0x6800ffe6 }, + { 0x090024dc, 0x6800ffe6 }, + { 0x090024dd, 0x6800ffe6 }, + { 0x090024de, 0x6800ffe6 }, + { 0x090024df, 0x6800ffe6 }, + { 0x090024e0, 0x6800ffe6 }, + { 0x090024e1, 0x6800ffe6 }, + { 0x090024e2, 0x6800ffe6 }, + { 0x090024e3, 0x6800ffe6 }, + { 0x090024e4, 0x6800ffe6 }, + { 0x090024e5, 0x6800ffe6 }, + { 0x090024e6, 0x6800ffe6 }, + { 0x090024e7, 0x6800ffe6 }, + { 0x090024e8, 0x6800ffe6 }, + { 0x090024e9, 0x6800ffe6 }, + { 0x098024ea, 0x3c000015 }, + { 0x09802500, 0x680000b6 }, + { 0x090025b7, 0x64000000 }, + { 0x098025b8, 0x68000008 }, + { 0x090025c1, 0x64000000 }, + { 0x098025c2, 0x68000035 }, + { 0x098025f8, 0x64000007 }, + { 0x09802600, 0x6800006e }, + { 0x0900266f, 0x64000000 }, + { 0x09802670, 0x6800002c }, + { 0x098026a0, 0x68000012 }, + { 0x09802701, 0x68000003 }, + { 0x09802706, 0x68000003 }, + { 0x0980270c, 0x6800001b }, + { 0x09802729, 0x68000022 }, + { 0x0900274d, 0x68000000 }, + { 0x0980274f, 0x68000003 }, + { 0x09002756, 0x68000000 }, + { 0x09802758, 0x68000006 }, + { 0x09802761, 0x68000006 }, + { 0x09002768, 0x58000000 }, + { 0x09002769, 0x48000000 }, + { 0x0900276a, 0x58000000 }, + { 0x0900276b, 0x48000000 }, + { 0x0900276c, 0x58000000 }, + { 0x0900276d, 0x48000000 }, + { 0x0900276e, 0x58000000 }, + { 0x0900276f, 0x48000000 }, + { 0x09002770, 0x58000000 }, + { 0x09002771, 0x48000000 }, + { 0x09002772, 0x58000000 }, + { 0x09002773, 0x48000000 }, + { 0x09002774, 0x58000000 }, + { 0x09002775, 0x48000000 }, + { 0x09802776, 0x3c00001d }, + { 0x09002794, 0x68000000 }, + { 0x09802798, 0x68000017 }, + { 0x098027b1, 0x6800000d }, + { 0x098027c0, 0x64000004 }, + { 0x090027c5, 0x58000000 }, + { 0x090027c6, 0x48000000 }, + { 0x098027c7, 0x64000003 }, + { 0x098027d0, 0x64000015 }, + { 0x090027e6, 0x58000000 }, + { 0x090027e7, 0x48000000 }, + { 0x090027e8, 0x58000000 }, + { 0x090027e9, 0x48000000 }, + { 0x090027ea, 0x58000000 }, + { 0x090027eb, 0x48000000 }, + { 0x098027f0, 0x6400000f }, + { 0x04802800, 0x680000ff }, + { 0x09802900, 0x64000082 }, + { 0x09002983, 0x58000000 }, + { 0x09002984, 0x48000000 }, + { 0x09002985, 0x58000000 }, + { 0x09002986, 0x48000000 }, + { 0x09002987, 0x58000000 }, + { 0x09002988, 0x48000000 }, + { 0x09002989, 0x58000000 }, + { 0x0900298a, 0x48000000 }, + { 0x0900298b, 0x58000000 }, + { 0x0900298c, 0x48000000 }, + { 0x0900298d, 0x58000000 }, + { 0x0900298e, 0x48000000 }, + { 0x0900298f, 0x58000000 }, + { 0x09002990, 0x48000000 }, + { 0x09002991, 0x58000000 }, + { 0x09002992, 0x48000000 }, + { 0x09002993, 0x58000000 }, + { 0x09002994, 0x48000000 }, + { 0x09002995, 0x58000000 }, + { 0x09002996, 0x48000000 }, + { 0x09002997, 0x58000000 }, + { 0x09002998, 0x48000000 }, + { 0x09802999, 0x6400003e }, + { 0x090029d8, 0x58000000 }, + { 0x090029d9, 0x48000000 }, + { 0x090029da, 0x58000000 }, + { 0x090029db, 0x48000000 }, + { 0x098029dc, 0x6400001f }, + { 0x090029fc, 0x58000000 }, + { 0x090029fd, 0x48000000 }, + { 0x098029fe, 0x64000101 }, + { 0x09802b00, 0x6800001a }, + { 0x09802b20, 0x68000003 }, + { 0x11002c00, 0x24000030 }, + { 0x11002c01, 0x24000030 }, + { 0x11002c02, 0x24000030 }, + { 0x11002c03, 0x24000030 }, + { 0x11002c04, 0x24000030 }, + { 0x11002c05, 0x24000030 }, + { 0x11002c06, 0x24000030 }, + { 0x11002c07, 0x24000030 }, + { 0x11002c08, 0x24000030 }, + { 0x11002c09, 0x24000030 }, + { 0x11002c0a, 0x24000030 }, + { 0x11002c0b, 0x24000030 }, + { 0x11002c0c, 0x24000030 }, + { 0x11002c0d, 0x24000030 }, + { 0x11002c0e, 0x24000030 }, + { 0x11002c0f, 0x24000030 }, + { 0x11002c10, 0x24000030 }, + { 0x11002c11, 0x24000030 }, + { 0x11002c12, 0x24000030 }, + { 0x11002c13, 0x24000030 }, + { 0x11002c14, 0x24000030 }, + { 0x11002c15, 0x24000030 }, + { 0x11002c16, 0x24000030 }, + { 0x11002c17, 0x24000030 }, + { 0x11002c18, 0x24000030 }, + { 0x11002c19, 0x24000030 }, + { 0x11002c1a, 0x24000030 }, + { 0x11002c1b, 0x24000030 }, + { 0x11002c1c, 0x24000030 }, + { 0x11002c1d, 0x24000030 }, + { 0x11002c1e, 0x24000030 }, + { 0x11002c1f, 0x24000030 }, + { 0x11002c20, 0x24000030 }, + { 0x11002c21, 0x24000030 }, + { 0x11002c22, 0x24000030 }, + { 0x11002c23, 0x24000030 }, + { 0x11002c24, 0x24000030 }, + { 0x11002c25, 0x24000030 }, + { 0x11002c26, 0x24000030 }, + { 0x11002c27, 0x24000030 }, + { 0x11002c28, 0x24000030 }, + { 0x11002c29, 0x24000030 }, + { 0x11002c2a, 0x24000030 }, + { 0x11002c2b, 0x24000030 }, + { 0x11002c2c, 0x24000030 }, + { 0x11002c2d, 0x24000030 }, + { 0x11002c2e, 0x24000030 }, + { 0x11002c30, 0x1400ffd0 }, + { 0x11002c31, 0x1400ffd0 }, + { 0x11002c32, 0x1400ffd0 }, + { 0x11002c33, 0x1400ffd0 }, + { 0x11002c34, 0x1400ffd0 }, + { 0x11002c35, 0x1400ffd0 }, + { 0x11002c36, 0x1400ffd0 }, + { 0x11002c37, 0x1400ffd0 }, + { 0x11002c38, 0x1400ffd0 }, + { 0x11002c39, 0x1400ffd0 }, + { 0x11002c3a, 0x1400ffd0 }, + { 0x11002c3b, 0x1400ffd0 }, + { 0x11002c3c, 0x1400ffd0 }, + { 0x11002c3d, 0x1400ffd0 }, + { 0x11002c3e, 0x1400ffd0 }, + { 0x11002c3f, 0x1400ffd0 }, + { 0x11002c40, 0x1400ffd0 }, + { 0x11002c41, 0x1400ffd0 }, + { 0x11002c42, 0x1400ffd0 }, + { 0x11002c43, 0x1400ffd0 }, + { 0x11002c44, 0x1400ffd0 }, + { 0x11002c45, 0x1400ffd0 }, + { 0x11002c46, 0x1400ffd0 }, + { 0x11002c47, 0x1400ffd0 }, + { 0x11002c48, 0x1400ffd0 }, + { 0x11002c49, 0x1400ffd0 }, + { 0x11002c4a, 0x1400ffd0 }, + { 0x11002c4b, 0x1400ffd0 }, + { 0x11002c4c, 0x1400ffd0 }, + { 0x11002c4d, 0x1400ffd0 }, + { 0x11002c4e, 0x1400ffd0 }, + { 0x11002c4f, 0x1400ffd0 }, + { 0x11002c50, 0x1400ffd0 }, + { 0x11002c51, 0x1400ffd0 }, + { 0x11002c52, 0x1400ffd0 }, + { 0x11002c53, 0x1400ffd0 }, + { 0x11002c54, 0x1400ffd0 }, + { 0x11002c55, 0x1400ffd0 }, + { 0x11002c56, 0x1400ffd0 }, + { 0x11002c57, 0x1400ffd0 }, + { 0x11002c58, 0x1400ffd0 }, + { 0x11002c59, 0x1400ffd0 }, + { 0x11002c5a, 0x1400ffd0 }, + { 0x11002c5b, 0x1400ffd0 }, + { 0x11002c5c, 0x1400ffd0 }, + { 0x11002c5d, 0x1400ffd0 }, + { 0x11002c5e, 0x1400ffd0 }, + { 0x21002c60, 0x24000001 }, + { 0x21002c61, 0x1400ffff }, + { 0x21002c62, 0x2400d609 }, + { 0x21002c63, 0x2400f11a }, + { 0x21002c64, 0x2400d619 }, + { 0x21002c65, 0x1400d5d5 }, + { 0x21002c66, 0x1400d5d8 }, + { 0x21002c67, 0x24000001 }, + { 0x21002c68, 0x1400ffff }, + { 0x21002c69, 0x24000001 }, + { 0x21002c6a, 0x1400ffff }, + { 0x21002c6b, 0x24000001 }, + { 0x21002c6c, 0x1400ffff }, + { 0x21002c74, 0x14000000 }, + { 0x21002c75, 0x24000001 }, + { 0x21002c76, 0x1400ffff }, + { 0x21002c77, 0x14000000 }, + { 0x0a002c80, 0x24000001 }, + { 0x0a002c81, 0x1400ffff }, + { 0x0a002c82, 0x24000001 }, + { 0x0a002c83, 0x1400ffff }, + { 0x0a002c84, 0x24000001 }, + { 0x0a002c85, 0x1400ffff }, + { 0x0a002c86, 0x24000001 }, + { 0x0a002c87, 0x1400ffff }, + { 0x0a002c88, 0x24000001 }, + { 0x0a002c89, 0x1400ffff }, + { 0x0a002c8a, 0x24000001 }, + { 0x0a002c8b, 0x1400ffff }, + { 0x0a002c8c, 0x24000001 }, + { 0x0a002c8d, 0x1400ffff }, + { 0x0a002c8e, 0x24000001 }, + { 0x0a002c8f, 0x1400ffff }, + { 0x0a002c90, 0x24000001 }, + { 0x0a002c91, 0x1400ffff }, + { 0x0a002c92, 0x24000001 }, + { 0x0a002c93, 0x1400ffff }, + { 0x0a002c94, 0x24000001 }, + { 0x0a002c95, 0x1400ffff }, + { 0x0a002c96, 0x24000001 }, + { 0x0a002c97, 0x1400ffff }, + { 0x0a002c98, 0x24000001 }, + { 0x0a002c99, 0x1400ffff }, + { 0x0a002c9a, 0x24000001 }, + { 0x0a002c9b, 0x1400ffff }, + { 0x0a002c9c, 0x24000001 }, + { 0x0a002c9d, 0x1400ffff }, + { 0x0a002c9e, 0x24000001 }, + { 0x0a002c9f, 0x1400ffff }, + { 0x0a002ca0, 0x24000001 }, + { 0x0a002ca1, 0x1400ffff }, + { 0x0a002ca2, 0x24000001 }, + { 0x0a002ca3, 0x1400ffff }, + { 0x0a002ca4, 0x24000001 }, + { 0x0a002ca5, 0x1400ffff }, + { 0x0a002ca6, 0x24000001 }, + { 0x0a002ca7, 0x1400ffff }, + { 0x0a002ca8, 0x24000001 }, + { 0x0a002ca9, 0x1400ffff }, + { 0x0a002caa, 0x24000001 }, + { 0x0a002cab, 0x1400ffff }, + { 0x0a002cac, 0x24000001 }, + { 0x0a002cad, 0x1400ffff }, + { 0x0a002cae, 0x24000001 }, + { 0x0a002caf, 0x1400ffff }, + { 0x0a002cb0, 0x24000001 }, + { 0x0a002cb1, 0x1400ffff }, + { 0x0a002cb2, 0x24000001 }, + { 0x0a002cb3, 0x1400ffff }, + { 0x0a002cb4, 0x24000001 }, + { 0x0a002cb5, 0x1400ffff }, + { 0x0a002cb6, 0x24000001 }, + { 0x0a002cb7, 0x1400ffff }, + { 0x0a002cb8, 0x24000001 }, + { 0x0a002cb9, 0x1400ffff }, + { 0x0a002cba, 0x24000001 }, + { 0x0a002cbb, 0x1400ffff }, + { 0x0a002cbc, 0x24000001 }, + { 0x0a002cbd, 0x1400ffff }, + { 0x0a002cbe, 0x24000001 }, + { 0x0a002cbf, 0x1400ffff }, + { 0x0a002cc0, 0x24000001 }, + { 0x0a002cc1, 0x1400ffff }, + { 0x0a002cc2, 0x24000001 }, + { 0x0a002cc3, 0x1400ffff }, + { 0x0a002cc4, 0x24000001 }, + { 0x0a002cc5, 0x1400ffff }, + { 0x0a002cc6, 0x24000001 }, + { 0x0a002cc7, 0x1400ffff }, + { 0x0a002cc8, 0x24000001 }, + { 0x0a002cc9, 0x1400ffff }, + { 0x0a002cca, 0x24000001 }, + { 0x0a002ccb, 0x1400ffff }, + { 0x0a002ccc, 0x24000001 }, + { 0x0a002ccd, 0x1400ffff }, + { 0x0a002cce, 0x24000001 }, + { 0x0a002ccf, 0x1400ffff }, + { 0x0a002cd0, 0x24000001 }, + { 0x0a002cd1, 0x1400ffff }, + { 0x0a002cd2, 0x24000001 }, + { 0x0a002cd3, 0x1400ffff }, + { 0x0a002cd4, 0x24000001 }, + { 0x0a002cd5, 0x1400ffff }, + { 0x0a002cd6, 0x24000001 }, + { 0x0a002cd7, 0x1400ffff }, + { 0x0a002cd8, 0x24000001 }, + { 0x0a002cd9, 0x1400ffff }, + { 0x0a002cda, 0x24000001 }, + { 0x0a002cdb, 0x1400ffff }, + { 0x0a002cdc, 0x24000001 }, + { 0x0a002cdd, 0x1400ffff }, + { 0x0a002cde, 0x24000001 }, + { 0x0a002cdf, 0x1400ffff }, + { 0x0a002ce0, 0x24000001 }, + { 0x0a002ce1, 0x1400ffff }, + { 0x0a002ce2, 0x24000001 }, + { 0x0a002ce3, 0x1400ffff }, + { 0x0a002ce4, 0x14000000 }, + { 0x0a802ce5, 0x68000005 }, + { 0x0a802cf9, 0x54000003 }, + { 0x0a002cfd, 0x3c000000 }, + { 0x0a802cfe, 0x54000001 }, + { 0x10002d00, 0x1400e3a0 }, + { 0x10002d01, 0x1400e3a0 }, + { 0x10002d02, 0x1400e3a0 }, + { 0x10002d03, 0x1400e3a0 }, + { 0x10002d04, 0x1400e3a0 }, + { 0x10002d05, 0x1400e3a0 }, + { 0x10002d06, 0x1400e3a0 }, + { 0x10002d07, 0x1400e3a0 }, + { 0x10002d08, 0x1400e3a0 }, + { 0x10002d09, 0x1400e3a0 }, + { 0x10002d0a, 0x1400e3a0 }, + { 0x10002d0b, 0x1400e3a0 }, + { 0x10002d0c, 0x1400e3a0 }, + { 0x10002d0d, 0x1400e3a0 }, + { 0x10002d0e, 0x1400e3a0 }, + { 0x10002d0f, 0x1400e3a0 }, + { 0x10002d10, 0x1400e3a0 }, + { 0x10002d11, 0x1400e3a0 }, + { 0x10002d12, 0x1400e3a0 }, + { 0x10002d13, 0x1400e3a0 }, + { 0x10002d14, 0x1400e3a0 }, + { 0x10002d15, 0x1400e3a0 }, + { 0x10002d16, 0x1400e3a0 }, + { 0x10002d17, 0x1400e3a0 }, + { 0x10002d18, 0x1400e3a0 }, + { 0x10002d19, 0x1400e3a0 }, + { 0x10002d1a, 0x1400e3a0 }, + { 0x10002d1b, 0x1400e3a0 }, + { 0x10002d1c, 0x1400e3a0 }, + { 0x10002d1d, 0x1400e3a0 }, + { 0x10002d1e, 0x1400e3a0 }, + { 0x10002d1f, 0x1400e3a0 }, + { 0x10002d20, 0x1400e3a0 }, + { 0x10002d21, 0x1400e3a0 }, + { 0x10002d22, 0x1400e3a0 }, + { 0x10002d23, 0x1400e3a0 }, + { 0x10002d24, 0x1400e3a0 }, + { 0x10002d25, 0x1400e3a0 }, + { 0x3a802d30, 0x1c000035 }, + { 0x3a002d6f, 0x18000000 }, + { 0x0f802d80, 0x1c000016 }, + { 0x0f802da0, 0x1c000006 }, + { 0x0f802da8, 0x1c000006 }, + { 0x0f802db0, 0x1c000006 }, + { 0x0f802db8, 0x1c000006 }, + { 0x0f802dc0, 0x1c000006 }, + { 0x0f802dc8, 0x1c000006 }, + { 0x0f802dd0, 0x1c000006 }, + { 0x0f802dd8, 0x1c000006 }, + { 0x09802e00, 0x54000001 }, + { 0x09002e02, 0x50000000 }, + { 0x09002e03, 0x4c000000 }, + { 0x09002e04, 0x50000000 }, + { 0x09002e05, 0x4c000000 }, + { 0x09802e06, 0x54000002 }, + { 0x09002e09, 0x50000000 }, + { 0x09002e0a, 0x4c000000 }, + { 0x09002e0b, 0x54000000 }, + { 0x09002e0c, 0x50000000 }, + { 0x09002e0d, 0x4c000000 }, + { 0x09802e0e, 0x54000008 }, + { 0x09002e17, 0x44000000 }, + { 0x09002e1c, 0x50000000 }, + { 0x09002e1d, 0x4c000000 }, + { 0x16802e80, 0x68000019 }, + { 0x16802e9b, 0x68000058 }, + { 0x16802f00, 0x680000d5 }, + { 0x09802ff0, 0x6800000b }, + { 0x09003000, 0x74000000 }, + { 0x09803001, 0x54000002 }, + { 0x09003004, 0x68000000 }, + { 0x16003005, 0x18000000 }, + { 0x09003006, 0x1c000000 }, + { 0x16003007, 0x38000000 }, + { 0x09003008, 0x58000000 }, + { 0x09003009, 0x48000000 }, + { 0x0900300a, 0x58000000 }, + { 0x0900300b, 0x48000000 }, + { 0x0900300c, 0x58000000 }, + { 0x0900300d, 0x48000000 }, + { 0x0900300e, 0x58000000 }, + { 0x0900300f, 0x48000000 }, + { 0x09003010, 0x58000000 }, + { 0x09003011, 0x48000000 }, + { 0x09803012, 0x68000001 }, + { 0x09003014, 0x58000000 }, + { 0x09003015, 0x48000000 }, + { 0x09003016, 0x58000000 }, + { 0x09003017, 0x48000000 }, + { 0x09003018, 0x58000000 }, + { 0x09003019, 0x48000000 }, + { 0x0900301a, 0x58000000 }, + { 0x0900301b, 0x48000000 }, + { 0x0900301c, 0x44000000 }, + { 0x0900301d, 0x58000000 }, + { 0x0980301e, 0x48000001 }, + { 0x09003020, 0x68000000 }, + { 0x16803021, 0x38000008 }, + { 0x1b80302a, 0x30000005 }, + { 0x09003030, 0x44000000 }, + { 0x09803031, 0x18000004 }, + { 0x09803036, 0x68000001 }, + { 0x16803038, 0x38000002 }, + { 0x1600303b, 0x18000000 }, + { 0x0900303c, 0x1c000000 }, + { 0x0900303d, 0x54000000 }, + { 0x0980303e, 0x68000001 }, + { 0x1a803041, 0x1c000055 }, + { 0x1b803099, 0x30000001 }, + { 0x0980309b, 0x60000001 }, + { 0x1a80309d, 0x18000001 }, + { 0x1a00309f, 0x1c000000 }, + { 0x090030a0, 0x44000000 }, + { 0x1d8030a1, 0x1c000059 }, + { 0x090030fb, 0x54000000 }, + { 0x098030fc, 0x18000002 }, + { 0x1d0030ff, 0x1c000000 }, + { 0x03803105, 0x1c000027 }, + { 0x17803131, 0x1c00005d }, + { 0x09803190, 0x68000001 }, + { 0x09803192, 0x3c000003 }, + { 0x09803196, 0x68000009 }, + { 0x038031a0, 0x1c000017 }, + { 0x098031c0, 0x6800000f }, + { 0x1d8031f0, 0x1c00000f }, + { 0x17803200, 0x6800001e }, + { 0x09803220, 0x3c000009 }, + { 0x0980322a, 0x68000019 }, + { 0x09003250, 0x68000000 }, + { 0x09803251, 0x3c00000e }, + { 0x17803260, 0x6800001f }, + { 0x09803280, 0x3c000009 }, + { 0x0980328a, 0x68000026 }, + { 0x098032b1, 0x3c00000e }, + { 0x098032c0, 0x6800003e }, + { 0x09803300, 0x680000ff }, + { 0x16803400, 0x1c0019b5 }, + { 0x09804dc0, 0x6800003f }, + { 0x16804e00, 0x1c0051bb }, + { 0x3c80a000, 0x1c000014 }, + { 0x3c00a015, 0x18000000 }, + { 0x3c80a016, 0x1c000476 }, + { 0x3c80a490, 0x68000036 }, + { 0x0980a700, 0x60000016 }, + { 0x0980a717, 0x18000003 }, + { 0x0980a720, 0x60000001 }, + { 0x3080a800, 0x1c000001 }, + { 0x3000a802, 0x28000000 }, + { 0x3080a803, 0x1c000002 }, + { 0x3000a806, 0x30000000 }, + { 0x3080a807, 0x1c000003 }, + { 0x3000a80b, 0x30000000 }, + { 0x3080a80c, 0x1c000016 }, + { 0x3080a823, 0x28000001 }, + { 0x3080a825, 0x30000001 }, + { 0x3000a827, 0x28000000 }, + { 0x3080a828, 0x68000003 }, + { 0x4080a840, 0x1c000033 }, + { 0x4080a874, 0x54000003 }, + { 0x1780ac00, 0x1c002ba3 }, + { 0x0980d800, 0x1000037f }, + { 0x0980db80, 0x1000007f }, + { 0x0980dc00, 0x100003ff }, + { 0x0980e000, 0x0c0018ff }, + { 0x1680f900, 0x1c00012d }, + { 0x1680fa30, 0x1c00003a }, + { 0x1680fa70, 0x1c000069 }, + { 0x2180fb00, 0x14000006 }, + { 0x0180fb13, 0x14000004 }, + { 0x1900fb1d, 0x1c000000 }, + { 0x1900fb1e, 0x30000000 }, + { 0x1980fb1f, 0x1c000009 }, + { 0x1900fb29, 0x64000000 }, + { 0x1980fb2a, 0x1c00000c }, + { 0x1980fb38, 0x1c000004 }, + { 0x1900fb3e, 0x1c000000 }, + { 0x1980fb40, 0x1c000001 }, + { 0x1980fb43, 0x1c000001 }, + { 0x1980fb46, 0x1c00006b }, + { 0x0080fbd3, 0x1c00016a }, + { 0x0900fd3e, 0x58000000 }, + { 0x0900fd3f, 0x48000000 }, + { 0x0080fd50, 0x1c00003f }, + { 0x0080fd92, 0x1c000035 }, + { 0x0080fdf0, 0x1c00000b }, + { 0x0000fdfc, 0x5c000000 }, + { 0x0900fdfd, 0x68000000 }, + { 0x1b80fe00, 0x3000000f }, + { 0x0980fe10, 0x54000006 }, + { 0x0900fe17, 0x58000000 }, + { 0x0900fe18, 0x48000000 }, + { 0x0900fe19, 0x54000000 }, + { 0x1b80fe20, 0x30000003 }, + { 0x0900fe30, 0x54000000 }, + { 0x0980fe31, 0x44000001 }, + { 0x0980fe33, 0x40000001 }, + { 0x0900fe35, 0x58000000 }, + { 0x0900fe36, 0x48000000 }, + { 0x0900fe37, 0x58000000 }, + { 0x0900fe38, 0x48000000 }, + { 0x0900fe39, 0x58000000 }, + { 0x0900fe3a, 0x48000000 }, + { 0x0900fe3b, 0x58000000 }, + { 0x0900fe3c, 0x48000000 }, + { 0x0900fe3d, 0x58000000 }, + { 0x0900fe3e, 0x48000000 }, + { 0x0900fe3f, 0x58000000 }, + { 0x0900fe40, 0x48000000 }, + { 0x0900fe41, 0x58000000 }, + { 0x0900fe42, 0x48000000 }, + { 0x0900fe43, 0x58000000 }, + { 0x0900fe44, 0x48000000 }, + { 0x0980fe45, 0x54000001 }, + { 0x0900fe47, 0x58000000 }, + { 0x0900fe48, 0x48000000 }, + { 0x0980fe49, 0x54000003 }, + { 0x0980fe4d, 0x40000002 }, + { 0x0980fe50, 0x54000002 }, + { 0x0980fe54, 0x54000003 }, + { 0x0900fe58, 0x44000000 }, + { 0x0900fe59, 0x58000000 }, + { 0x0900fe5a, 0x48000000 }, + { 0x0900fe5b, 0x58000000 }, + { 0x0900fe5c, 0x48000000 }, + { 0x0900fe5d, 0x58000000 }, + { 0x0900fe5e, 0x48000000 }, + { 0x0980fe5f, 0x54000002 }, + { 0x0900fe62, 0x64000000 }, + { 0x0900fe63, 0x44000000 }, + { 0x0980fe64, 0x64000002 }, + { 0x0900fe68, 0x54000000 }, + { 0x0900fe69, 0x5c000000 }, + { 0x0980fe6a, 0x54000001 }, + { 0x0080fe70, 0x1c000004 }, + { 0x0080fe76, 0x1c000086 }, + { 0x0900feff, 0x04000000 }, + { 0x0980ff01, 0x54000002 }, + { 0x0900ff04, 0x5c000000 }, + { 0x0980ff05, 0x54000002 }, + { 0x0900ff08, 0x58000000 }, + { 0x0900ff09, 0x48000000 }, + { 0x0900ff0a, 0x54000000 }, + { 0x0900ff0b, 0x64000000 }, + { 0x0900ff0c, 0x54000000 }, + { 0x0900ff0d, 0x44000000 }, + { 0x0980ff0e, 0x54000001 }, + { 0x0980ff10, 0x34000009 }, + { 0x0980ff1a, 0x54000001 }, + { 0x0980ff1c, 0x64000002 }, + { 0x0980ff1f, 0x54000001 }, + { 0x2100ff21, 0x24000020 }, + { 0x2100ff22, 0x24000020 }, + { 0x2100ff23, 0x24000020 }, + { 0x2100ff24, 0x24000020 }, + { 0x2100ff25, 0x24000020 }, + { 0x2100ff26, 0x24000020 }, + { 0x2100ff27, 0x24000020 }, + { 0x2100ff28, 0x24000020 }, + { 0x2100ff29, 0x24000020 }, + { 0x2100ff2a, 0x24000020 }, + { 0x2100ff2b, 0x24000020 }, + { 0x2100ff2c, 0x24000020 }, + { 0x2100ff2d, 0x24000020 }, + { 0x2100ff2e, 0x24000020 }, + { 0x2100ff2f, 0x24000020 }, + { 0x2100ff30, 0x24000020 }, + { 0x2100ff31, 0x24000020 }, + { 0x2100ff32, 0x24000020 }, + { 0x2100ff33, 0x24000020 }, + { 0x2100ff34, 0x24000020 }, + { 0x2100ff35, 0x24000020 }, + { 0x2100ff36, 0x24000020 }, + { 0x2100ff37, 0x24000020 }, + { 0x2100ff38, 0x24000020 }, + { 0x2100ff39, 0x24000020 }, + { 0x2100ff3a, 0x24000020 }, + { 0x0900ff3b, 0x58000000 }, + { 0x0900ff3c, 0x54000000 }, + { 0x0900ff3d, 0x48000000 }, + { 0x0900ff3e, 0x60000000 }, + { 0x0900ff3f, 0x40000000 }, + { 0x0900ff40, 0x60000000 }, + { 0x2100ff41, 0x1400ffe0 }, + { 0x2100ff42, 0x1400ffe0 }, + { 0x2100ff43, 0x1400ffe0 }, + { 0x2100ff44, 0x1400ffe0 }, + { 0x2100ff45, 0x1400ffe0 }, + { 0x2100ff46, 0x1400ffe0 }, + { 0x2100ff47, 0x1400ffe0 }, + { 0x2100ff48, 0x1400ffe0 }, + { 0x2100ff49, 0x1400ffe0 }, + { 0x2100ff4a, 0x1400ffe0 }, + { 0x2100ff4b, 0x1400ffe0 }, + { 0x2100ff4c, 0x1400ffe0 }, + { 0x2100ff4d, 0x1400ffe0 }, + { 0x2100ff4e, 0x1400ffe0 }, + { 0x2100ff4f, 0x1400ffe0 }, + { 0x2100ff50, 0x1400ffe0 }, + { 0x2100ff51, 0x1400ffe0 }, + { 0x2100ff52, 0x1400ffe0 }, + { 0x2100ff53, 0x1400ffe0 }, + { 0x2100ff54, 0x1400ffe0 }, + { 0x2100ff55, 0x1400ffe0 }, + { 0x2100ff56, 0x1400ffe0 }, + { 0x2100ff57, 0x1400ffe0 }, + { 0x2100ff58, 0x1400ffe0 }, + { 0x2100ff59, 0x1400ffe0 }, + { 0x2100ff5a, 0x1400ffe0 }, + { 0x0900ff5b, 0x58000000 }, + { 0x0900ff5c, 0x64000000 }, + { 0x0900ff5d, 0x48000000 }, + { 0x0900ff5e, 0x64000000 }, + { 0x0900ff5f, 0x58000000 }, + { 0x0900ff60, 0x48000000 }, + { 0x0900ff61, 0x54000000 }, + { 0x0900ff62, 0x58000000 }, + { 0x0900ff63, 0x48000000 }, + { 0x0980ff64, 0x54000001 }, + { 0x1d80ff66, 0x1c000009 }, + { 0x0900ff70, 0x18000000 }, + { 0x1d80ff71, 0x1c00002c }, + { 0x0980ff9e, 0x18000001 }, + { 0x1780ffa0, 0x1c00001e }, + { 0x1780ffc2, 0x1c000005 }, + { 0x1780ffca, 0x1c000005 }, + { 0x1780ffd2, 0x1c000005 }, + { 0x1780ffda, 0x1c000002 }, + { 0x0980ffe0, 0x5c000001 }, + { 0x0900ffe2, 0x64000000 }, + { 0x0900ffe3, 0x60000000 }, + { 0x0900ffe4, 0x68000000 }, + { 0x0980ffe5, 0x5c000001 }, + { 0x0900ffe8, 0x68000000 }, + { 0x0980ffe9, 0x64000003 }, + { 0x0980ffed, 0x68000001 }, + { 0x0980fff9, 0x04000002 }, + { 0x0980fffc, 0x68000001 }, + { 0x23810000, 0x1c00000b }, + { 0x2381000d, 0x1c000019 }, + { 0x23810028, 0x1c000012 }, + { 0x2381003c, 0x1c000001 }, + { 0x2381003f, 0x1c00000e }, + { 0x23810050, 0x1c00000d }, + { 0x23810080, 0x1c00007a }, + { 0x09810100, 0x54000001 }, + { 0x09010102, 0x68000000 }, + { 0x09810107, 0x3c00002c }, + { 0x09810137, 0x68000008 }, + { 0x13810140, 0x38000034 }, + { 0x13810175, 0x3c000003 }, + { 0x13810179, 0x68000010 }, + { 0x1301018a, 0x3c000000 }, + { 0x29810300, 0x1c00001e }, + { 0x29810320, 0x3c000003 }, + { 0x12810330, 0x1c000010 }, + { 0x12010341, 0x38000000 }, + { 0x12810342, 0x1c000007 }, + { 0x1201034a, 0x38000000 }, + { 0x3b810380, 0x1c00001d }, + { 0x3b01039f, 0x54000000 }, + { 0x2a8103a0, 0x1c000023 }, + { 0x2a8103c8, 0x1c000007 }, + { 0x2a0103d0, 0x54000000 }, + { 0x2a8103d1, 0x38000004 }, + { 0x0d010400, 0x24000028 }, + { 0x0d010401, 0x24000028 }, + { 0x0d010402, 0x24000028 }, + { 0x0d010403, 0x24000028 }, + { 0x0d010404, 0x24000028 }, + { 0x0d010405, 0x24000028 }, + { 0x0d010406, 0x24000028 }, + { 0x0d010407, 0x24000028 }, + { 0x0d010408, 0x24000028 }, + { 0x0d010409, 0x24000028 }, + { 0x0d01040a, 0x24000028 }, + { 0x0d01040b, 0x24000028 }, + { 0x0d01040c, 0x24000028 }, + { 0x0d01040d, 0x24000028 }, + { 0x0d01040e, 0x24000028 }, + { 0x0d01040f, 0x24000028 }, + { 0x0d010410, 0x24000028 }, + { 0x0d010411, 0x24000028 }, + { 0x0d010412, 0x24000028 }, + { 0x0d010413, 0x24000028 }, + { 0x0d010414, 0x24000028 }, + { 0x0d010415, 0x24000028 }, + { 0x0d010416, 0x24000028 }, + { 0x0d010417, 0x24000028 }, + { 0x0d010418, 0x24000028 }, + { 0x0d010419, 0x24000028 }, + { 0x0d01041a, 0x24000028 }, + { 0x0d01041b, 0x24000028 }, + { 0x0d01041c, 0x24000028 }, + { 0x0d01041d, 0x24000028 }, + { 0x0d01041e, 0x24000028 }, + { 0x0d01041f, 0x24000028 }, + { 0x0d010420, 0x24000028 }, + { 0x0d010421, 0x24000028 }, + { 0x0d010422, 0x24000028 }, + { 0x0d010423, 0x24000028 }, + { 0x0d010424, 0x24000028 }, + { 0x0d010425, 0x24000028 }, + { 0x0d010426, 0x24000028 }, + { 0x0d010427, 0x24000028 }, + { 0x0d010428, 0x1400ffd8 }, + { 0x0d010429, 0x1400ffd8 }, + { 0x0d01042a, 0x1400ffd8 }, + { 0x0d01042b, 0x1400ffd8 }, + { 0x0d01042c, 0x1400ffd8 }, + { 0x0d01042d, 0x1400ffd8 }, + { 0x0d01042e, 0x1400ffd8 }, + { 0x0d01042f, 0x1400ffd8 }, + { 0x0d010430, 0x1400ffd8 }, + { 0x0d010431, 0x1400ffd8 }, + { 0x0d010432, 0x1400ffd8 }, + { 0x0d010433, 0x1400ffd8 }, + { 0x0d010434, 0x1400ffd8 }, + { 0x0d010435, 0x1400ffd8 }, + { 0x0d010436, 0x1400ffd8 }, + { 0x0d010437, 0x1400ffd8 }, + { 0x0d010438, 0x1400ffd8 }, + { 0x0d010439, 0x1400ffd8 }, + { 0x0d01043a, 0x1400ffd8 }, + { 0x0d01043b, 0x1400ffd8 }, + { 0x0d01043c, 0x1400ffd8 }, + { 0x0d01043d, 0x1400ffd8 }, + { 0x0d01043e, 0x1400ffd8 }, + { 0x0d01043f, 0x1400ffd8 }, + { 0x0d010440, 0x1400ffd8 }, + { 0x0d010441, 0x1400ffd8 }, + { 0x0d010442, 0x1400ffd8 }, + { 0x0d010443, 0x1400ffd8 }, + { 0x0d010444, 0x1400ffd8 }, + { 0x0d010445, 0x1400ffd8 }, + { 0x0d010446, 0x1400ffd8 }, + { 0x0d010447, 0x1400ffd8 }, + { 0x0d010448, 0x1400ffd8 }, + { 0x0d010449, 0x1400ffd8 }, + { 0x0d01044a, 0x1400ffd8 }, + { 0x0d01044b, 0x1400ffd8 }, + { 0x0d01044c, 0x1400ffd8 }, + { 0x0d01044d, 0x1400ffd8 }, + { 0x0d01044e, 0x1400ffd8 }, + { 0x0d01044f, 0x1400ffd8 }, + { 0x2e810450, 0x1c00004d }, + { 0x2c8104a0, 0x34000009 }, + { 0x0b810800, 0x1c000005 }, + { 0x0b010808, 0x1c000000 }, + { 0x0b81080a, 0x1c00002b }, + { 0x0b810837, 0x1c000001 }, + { 0x0b01083c, 0x1c000000 }, + { 0x0b01083f, 0x1c000000 }, + { 0x41810900, 0x1c000015 }, + { 0x41810916, 0x3c000003 }, + { 0x4101091f, 0x54000000 }, + { 0x1e010a00, 0x1c000000 }, + { 0x1e810a01, 0x30000002 }, + { 0x1e810a05, 0x30000001 }, + { 0x1e810a0c, 0x30000003 }, + { 0x1e810a10, 0x1c000003 }, + { 0x1e810a15, 0x1c000002 }, + { 0x1e810a19, 0x1c00001a }, + { 0x1e810a38, 0x30000002 }, + { 0x1e010a3f, 0x30000000 }, + { 0x1e810a40, 0x3c000007 }, + { 0x1e810a50, 0x54000008 }, + { 0x3e812000, 0x1c00036e }, + { 0x3e812400, 0x38000062 }, + { 0x3e812470, 0x54000003 }, + { 0x0981d000, 0x680000f5 }, + { 0x0981d100, 0x68000026 }, + { 0x0981d12a, 0x6800003a }, + { 0x0981d165, 0x28000001 }, + { 0x1b81d167, 0x30000002 }, + { 0x0981d16a, 0x68000002 }, + { 0x0981d16d, 0x28000005 }, + { 0x0981d173, 0x04000007 }, + { 0x1b81d17b, 0x30000007 }, + { 0x0981d183, 0x68000001 }, + { 0x1b81d185, 0x30000006 }, + { 0x0981d18c, 0x6800001d }, + { 0x1b81d1aa, 0x30000003 }, + { 0x0981d1ae, 0x6800002f }, + { 0x1381d200, 0x68000041 }, + { 0x1381d242, 0x30000002 }, + { 0x1301d245, 0x68000000 }, + { 0x0981d300, 0x68000056 }, + { 0x0981d360, 0x3c000011 }, + { 0x0981d400, 0x24000019 }, + { 0x0981d41a, 0x14000019 }, + { 0x0981d434, 0x24000019 }, + { 0x0981d44e, 0x14000006 }, + { 0x0981d456, 0x14000011 }, + { 0x0981d468, 0x24000019 }, + { 0x0981d482, 0x14000019 }, + { 0x0901d49c, 0x24000000 }, + { 0x0981d49e, 0x24000001 }, + { 0x0901d4a2, 0x24000000 }, + { 0x0981d4a5, 0x24000001 }, + { 0x0981d4a9, 0x24000003 }, + { 0x0981d4ae, 0x24000007 }, + { 0x0981d4b6, 0x14000003 }, + { 0x0901d4bb, 0x14000000 }, + { 0x0981d4bd, 0x14000006 }, + { 0x0981d4c5, 0x1400000a }, + { 0x0981d4d0, 0x24000019 }, + { 0x0981d4ea, 0x14000019 }, + { 0x0981d504, 0x24000001 }, + { 0x0981d507, 0x24000003 }, + { 0x0981d50d, 0x24000007 }, + { 0x0981d516, 0x24000006 }, + { 0x0981d51e, 0x14000019 }, + { 0x0981d538, 0x24000001 }, + { 0x0981d53b, 0x24000003 }, + { 0x0981d540, 0x24000004 }, + { 0x0901d546, 0x24000000 }, + { 0x0981d54a, 0x24000006 }, + { 0x0981d552, 0x14000019 }, + { 0x0981d56c, 0x24000019 }, + { 0x0981d586, 0x14000019 }, + { 0x0981d5a0, 0x24000019 }, + { 0x0981d5ba, 0x14000019 }, + { 0x0981d5d4, 0x24000019 }, + { 0x0981d5ee, 0x14000019 }, + { 0x0981d608, 0x24000019 }, + { 0x0981d622, 0x14000019 }, + { 0x0981d63c, 0x24000019 }, + { 0x0981d656, 0x14000019 }, + { 0x0981d670, 0x24000019 }, + { 0x0981d68a, 0x1400001b }, + { 0x0981d6a8, 0x24000018 }, + { 0x0901d6c1, 0x64000000 }, + { 0x0981d6c2, 0x14000018 }, + { 0x0901d6db, 0x64000000 }, + { 0x0981d6dc, 0x14000005 }, + { 0x0981d6e2, 0x24000018 }, + { 0x0901d6fb, 0x64000000 }, + { 0x0981d6fc, 0x14000018 }, + { 0x0901d715, 0x64000000 }, + { 0x0981d716, 0x14000005 }, + { 0x0981d71c, 0x24000018 }, + { 0x0901d735, 0x64000000 }, + { 0x0981d736, 0x14000018 }, + { 0x0901d74f, 0x64000000 }, + { 0x0981d750, 0x14000005 }, + { 0x0981d756, 0x24000018 }, + { 0x0901d76f, 0x64000000 }, + { 0x0981d770, 0x14000018 }, + { 0x0901d789, 0x64000000 }, + { 0x0981d78a, 0x14000005 }, + { 0x0981d790, 0x24000018 }, + { 0x0901d7a9, 0x64000000 }, + { 0x0981d7aa, 0x14000018 }, + { 0x0901d7c3, 0x64000000 }, + { 0x0981d7c4, 0x14000005 }, + { 0x0901d7ca, 0x24000000 }, + { 0x0901d7cb, 0x14000000 }, + { 0x0981d7ce, 0x34000031 }, + { 0x16820000, 0x1c00a6d6 }, + { 0x1682f800, 0x1c00021d }, + { 0x090e0001, 0x04000000 }, + { 0x098e0020, 0x0400005f }, + { 0x1b8e0100, 0x300000ef }, + { 0x098f0000, 0x0c00fffd }, + { 0x09900000, 0x0c00fffd }, +};