import re
regex = re.compile(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|$)
""", flags=re.MULTILINE | re.IGNORECASE | re.VERBOSE)
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 = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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