# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^(Prefeitura|Pref\.|P\.)\s(Municipal\s?|Mun.\s?|M.\s?)?(de\s)?(S[aã]o\sPaulo|S.\sP.|S.\sPaulo|S.P.|SP)$
"""
test_str = ("Prefeitura Municipal de São Paulo\n"
"Prefeitura Municipal de Sao Paulo\n"
"Prefeitura de São Paulo\n"
"Prefeitura de Sao Paulo\n"
"Prefeitura Mun. de São Paulo\n"
"Pref. Mun. de São Paulo\n"
"Pref. Mun. de S. P.\n"
"Pref. de São Paulo\n"
"Pref. de S. Paulo\n"
"Pref. M. de São Paulo\n"
"P. M. de Sao Paulo\n"
"Prefeitura São Paulo\n"
"Pref. Mun. São Paulo\n"
"Pref. Mun. S. Paulo\n"
"Prefeitura de S.P.\n"
"Prefeitura de SP")
matches = re.finditer(regex, test_str, re.MULTILINE | 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