# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = (r"(?ix) \n"
r"(\w+)\ (semaine|jours)?\n"
r"|\n"
r"(demain|ce soir|aujourd'hui|\n"
r"(next|this)[\ \b](matin|après-midi|soir|Lundi|Mardi|Mercredi|Jeudi|Vendredi|Samedi|Dimanche)\n"
r")|(Lundi|Mardi|Mercredi|Jeudi|Vendredi|Samedi|Dimanche)\n"
r"|\n"
r"(janvier|février|Mars|Avril|Mai|Juin|Juillet|Août|Septembre|Octobre|Novembre|Décembre)\ (\w+)((\s|\-)?\w*)\n")
test_str = ("quelle sera la température dans cinq jours\n"
"c'est quoi la température pour aujourd'hui\n"
"Comment fera-t-il lundi prochain?\n"
"quelle est la température ce soir?\n"
"donne-moi la température pour demain matin\n"
"quelle sera la température dans 8 semaines\n"
"température cet après-midi\n"
"température lundi prochain\n"
"What is the weather for march 8\n"
"What is the weather for march twenty-second")
matches = re.finditer(regex, test_str)
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