# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?P<str_lit>(?P<begin_quote>(?P<single_quote>')|\")(?:(?(single_quote)\"|')|\\[\"']|\\[^\r\n ]|[^\"'\\\r\n])*?(?P=begin_quote))$"
test_str = ("\"double-quoted string\"\n"
"'single-quoted string'\n"
"\"unexpected EOL\n"
"'unexpected EOL\n"
"\"unclosed backslash escape: \\\"\n"
"\"properly doubled backslash: \\\\\"\n"
"\"escaped ' quotes and backslash escapes \\' are \\\" \\n allowed\"\n"
"\"\\t\\tindented code\\r\\n\"\n"
"\"invalid escape \\%\"\n"
"\"'\"\n"
"\"space is not a valid backslash escape: \\ \"\n"
"\"or newline either: \\\n"
"\"hopefully there aren't any edge-cases I didn't think of\"\n"
"\"\"\"oh, and single-line docstrings count as three string literals, so you would have to repeat the same expression multiple times to match it\"\"\"\n"
"\"\"\"and multi-line docstrings won't match even if you repeat the expression multiple times")
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