# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(([0-9]{1,2}|[a-z]{1,3})-([0-9]{2,3}|[a-z]{2,3})-([0-9]{1,2}|[a-z]{1,2}))"
test_str = ("XX-99-99\n"
"2 1965 99-99-XX \n"
"3 1973 99-XX-99\n"
"4 1978 XX-99-XX \n"
"5 1991 XX-XX-99 \n"
"6 1999 99-XX-XX \n"
"7 2005 99-XXX-9\n"
"8 2009 9-XXX-99\n"
"9 2006 XX-999-X \n"
"10 2008 X-999-XX \n"
"11 2015 XXX-99-X")
matches = re.finditer(regex, test_str, re.IGNORECASE)
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