Bug fix (CFM tends to HTML encode non-alphanumeric chars in error reports - paths weren't recognized)

This commit is contained in:
Miroslav Stampar
2019-02-21 02:50:11 +01:00
parent daeb281e91
commit 1248fe5eee
3 changed files with 31 additions and 34 deletions

View File

@@ -19,7 +19,7 @@ from lib.core.enums import DBMS_DIRECTORY_NAME
from lib.core.enums import OS
# sqlmap version (<major>.<minor>.<month>.<monthly commit>)
VERSION = "1.3.2.26"
VERSION = "1.3.2.27"
TYPE = "dev" if VERSION.count('.') > 2 and VERSION.split('.')[-1] != '0' else "stable"
TYPE_COLORS = {"dev": 33, "stable": 90, "pip": 34}
VERSION_STRING = "sqlmap/%s#%s" % ('.'.join(VERSION.split('.')[:-1]) if VERSION.count('.') > 2 and VERSION.split('.')[-1] == '0' else VERSION, TYPE)
@@ -330,7 +330,7 @@ CURRENT_DB = "CD"
SESSION_SQLITE_FILE = "session.sqlite"
# Regular expressions used for finding file paths in error messages
FILE_PATH_REGEXES = (r"<b>(?P<result>[^<>]+?)</b> on line \d+", r"in (?P<result>[^<>'\"]+?)['\"]? on line \d+", r"(?:[>(\[\s])(?P<result>[A-Za-z]:[\\/][\w. \\/-]*)", r"(?:[>(\[\s])(?P<result>/\w[/\w.~-]+)", r"href=['\"]file://(?P<result>/[^'\"]+)")
FILE_PATH_REGEXES = (r"<b>(?P<result>[^<>]+?)</b> on line \d+", r"\bin (?P<result>[^<>'\"]+?)['\"]? on line \d+", r"(?:[>(\[\s])(?P<result>[A-Za-z]:[\\/][\w. \\/-]*)", r"(?:[>(\[\s])(?P<result>/\w[/\w.~-]+)", r"\bhref=['\"]file://(?P<result>/[^'\"]+)", r"\bin <b>(?P<result>[^<]+): line \d+")
# Regular expressions used for parsing error messages (--parse-errors)
ERROR_PARSING_REGEXES = (

View File

@@ -313,43 +313,40 @@ def decodePage(page, contentEncoding, contentType):
# can't do for all responses because we need to support binary files too
if not isinstance(page, unicode) and "text/" in contentType:
if kb.heuristicMode:
kb.pageEncoding = kb.pageEncoding or checkCharEncoding(getHeuristicCharEncoding(page))
page = getUnicode(page, kb.pageEncoding)
else:
# e.g. &#195;&#235;&#224;&#226;&#224;
if "&#" in page:
page = re.sub(r"&#(\d{1,3});", lambda _: chr(int(_.group(1))) if int(_.group(1)) < 256 else _.group(0), page)
# e.g. &#x9;&#195;&#235;&#224;&#226;&#224;
if "&#" in page:
page = re.sub(r"&#x([0-9a-f]{1,2});", lambda _: (_.group(1) if len(_.group(1)) == 2 else "0%s" % _.group(1)).decode("hex"), page)
page = re.sub(r"&#(\d{1,3});", lambda _: chr(int(_.group(1))) if int(_.group(1)) < 256 else _.group(0), page)
# e.g. %20%28%29
if "%" in page:
page = re.sub(r"%([0-9a-fA-F]{2})", lambda _: _.group(1).decode("hex"), page)
# e.g. %20%28%29
if "%" in page:
page = re.sub(r"%([0-9a-fA-F]{2})", lambda _: _.group(1).decode("hex"), page)
# e.g. &amp;
page = re.sub(r"&([^;]+);", lambda _: chr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 256) < 256 else _.group(0), page)
# e.g. &amp;
page = re.sub(r"&([^;]+);", lambda _: chr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 256) < 256 else _.group(0), page)
kb.pageEncoding = kb.pageEncoding or checkCharEncoding(getHeuristicCharEncoding(page))
kb.pageEncoding = kb.pageEncoding or checkCharEncoding(getHeuristicCharEncoding(page))
if (kb.pageEncoding or "").lower() == "utf-8-sig":
kb.pageEncoding = "utf-8"
if page and page.startswith("\xef\xbb\xbf"): # Reference: https://docs.python.org/2/library/codecs.html (Note: noticed problems when "utf-8-sig" is left to Python for handling)
page = page[3:]
if (kb.pageEncoding or "").lower() == "utf-8-sig":
kb.pageEncoding = "utf-8"
if page and page.startswith("\xef\xbb\xbf"): # Reference: https://docs.python.org/2/library/codecs.html (Note: noticed problems when "utf-8-sig" is left to Python for handling)
page = page[3:]
page = getUnicode(page, kb.pageEncoding)
page = getUnicode(page, kb.pageEncoding)
# e.g. &#8217;&#8230;&#8482;
if "&#" in page:
def _(match):
retVal = match.group(0)
try:
retVal = unichr(int(match.group(1)))
except (ValueError, OverflowError):
pass
return retVal
page = re.sub(r"&#(\d+);", _, page)
# e.g. &#8217;&#8230;&#8482;
if "&#" in page:
def _(match):
retVal = match.group(0)
try:
retVal = unichr(int(match.group(1)))
except (ValueError, OverflowError):
pass
return retVal
page = re.sub(r"&#(\d+);", _, page)
# e.g. &zeta;
page = re.sub(r"&([^;]+);", lambda _: unichr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 0) > 255 else _.group(0), page)
# e.g. &zeta;
page = re.sub(r"&([^;]+);", lambda _: unichr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 0) > 255 else _.group(0), page)
return page