# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=begin{DoxyCode})([\s\S]+?[^\\])([_%])([\s\S]+?)(?=end{DoxyCode})"
test_str = ("\\begin{DoxyCode}\n"
"17 This is some code that contains an_undersc_ore and \n"
"18 an escaped\\_underscore. Plus another unescaped_unders_core \n"
"19 for good measure. \n"
"20 As if that was not \"bad\" enough, it also contains a %percent sign\n"
"21 that is unescaped.\n"
"\\end{DoxyCode}\n\n"
"Here is some other stuff that may contain \\index{things_not_to_be_escaped}.\n\n"
"\\begin{DoxyCode}\n"
"17 This is some code that contains an_underscore and \n"
"18 an escaped\\_underscore. Plus another unescaped_underscore \n"
"19 for good measure. \n"
"20 As if that was not \"bad\" enough, it also contains a \\%percent sign\n"
"21 that is escaped.\n"
"\\end{DoxyCode}")
matches = re.finditer(regex, test_str)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html