# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?>^|\s+|\W)
(
(?>[a-z]\d*|\d+[a-z]?
(?>\(
([a-z]\d*|\d+[a-z]?)
\)[a-z]?
)?)
(?>\.(?>[a-z]|\d+[a-z]?))*
|
(?>M{0,4}(?>CM|CD|D?C{0,3})(?>XC|XL|L?X{0,3})(?>IX|IV|V?I{0,3}))
)
(?>\s+|\W|$)
"""
test_str = ("Appendix 1\n"
"6.48\n"
"CP 198\n"
"3.2.4 G\n"
"2\n"
"1.\n"
"B.\n"
"Appendix 1\n"
"Annex A\n"
"4A.10.1 and 4A.15\n"
"4A.21.10\n"
"Annex ii\n"
"A)\n"
"SECTION IV\n"
"52.19A\n"
"PRACTICE DIRECTION 83—\n"
"RSC ORDER 109\n"
"Rule 4\n"
"ADMINISTRATIVE COURT GUIDANCE\n"
"PRACTICE STATEMENT\n"
"THE PROTOCOL\n"
"C.6\n"
"Draft modules\n"
"CIS11:\n"
"Appendix 13(2)e\n"
"2002 no.\n"
"(a)\n"
"L7.3.1.R\n"
"(iii)\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | re.VERBOSE)
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