# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\A(?:(?P<type>[^\(!:]+)(?:\((?P<scope>[^\)]+)\))?(?P<breaking>!)?: (?P<description>.+))(?:(?!(?:\n{2}^(?:BREAKING[ -]CHANGE|[a-zA-Z0-9_\-]+)(?:: | #\b)[^\n:]+(\n*\b)?)+)\n{2}(?P<body>(?:(?!\n{2}(?:^(?:BREAKING[ -]CHANGE|[a-zA-Z0-9_\-]+)(?:: | #\b)[^\n:]+(\n*\b)?)+).|\n+?)+?))?(?:\n{2}(?P<footers>(?:^(?:BREAKING[ -]CHANGE|[a-zA-Z0-9_\-]+)(?:: | #\b)[^\n:]+(\n*\b)?)+))?(?:\n*)\Z"
test_str = ("feat(foo): add a nice RegEx to check and parse a commit message that folows https://www.conventionalcommits.org/en/v1.0.0\n\n"
"Hello, \n\n"
"This is an\n"
"multiline example and very nice\n\n"
"This may also include colons as long as they are not after a word boundary followed after two line brakes\n"
"Example: foo\n\n"
" Other example: xyz\n\n"
"Refs: #42\n"
"BREAKING-CHANGE: Brakes wood\n"
"something #mentions a commit")
matches = re.search(regex, test_str, re.MULTILINE)
if matches:
print ("Match was found at {start}-{end}: {match}".format(start = matches.start(), end = matches.end(), match = matches.group()))
for groupNum in range(0, len(matches.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = matches.start(groupNum), end = matches.end(groupNum), group = matches.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