# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = (r"(((?# FIRST TYPE OF ARGS\\n"
r")(?#start arg)(\"|'|`)(?#\\n"
r")(?#arg)(?<arg>(?# whole repeat pattern)((?!\3)(?(?!\\).|..))*)(?#\\n"
r")(?#end arg)\3(?#\\n"
r"))|((?# SECOND TYPE OF ARGS\\n"
r")(?#start arg)(^|\s+)(?#\\n"
r")(?#arg)(?<arg_>(?#whole repeat pattern)((?!\s|$)(?(?!\\).|..))+)(?#\\n"
r")))(?#\\n"
r"skipping trailing whitespaces)(\s|^|$)*(?=(\s|^|$|\"|'|`))")
test_str = (" arg0\\ \\ \\\\ \"arg1\\\"\\\"\" \"arg2\\\"\\\\\"\"arg3 \\\"\" 'arg4\"arg4\"' arg5 arg6 \n\n"
" space_bef_and_aft_even_arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8 arg9 \n"
" space_bef_and_aft_odd__arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8 \n"
"space_aft_even__________arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8 arg9 \n"
"space_aft_odd___________arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8 \n"
" space_bef_even_________arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8 arg9\n"
" space_bef_odd__________arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8\n"
"nospace_even____________arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8 arg9\n"
"nospace_odd_____________arg0 arg1 arg2 arg3 arg4 arg5 arg6 arg7 arg8\n\n"
" multispace______________arg0 arg1 arg2 arg3 arg4 \n\n\n"
" pbm0 pbm1 pbm2 \n"
"\"pbm0 pbm0\" pbm1 \n"
"\"pbm0 pbm0\" pbm1 \n\n"
" C:\\ProgramData\\Anaconda3\\python.exe C:\\ProgramData\\Anaconda3\\cwp.py C:\\ProgramData\\Anaconda3 C:\\ProgramData\\Anaconda3\\python.exe C:\\ProgramData\\Anaconda3\\Scripts\\jupyter-notebook-script.py \"%USERPROFILE%/\" \n\n"
" (?(?=\\2)(?(?=($|^))true|false)|false) . \n\n\n\n\n"
"(?:(?(?!\\3|\\\\).|(?=\\\\)..))*\n\n"
"((?!\\s|$)(?(?!\\\\).|..))*)")
matches = re.finditer(regex, test_str, re.MULTILINE)
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