# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^(?!.*THIRD.*(?:SECOND|FIRST)) # SECOND or FIRST cannot appear after THIRD
(?!.*SECOND.*FIRST) # SECOND cannot appear before FIRST
(?!.*THIRD.*THIRD)
(?!.*SECOND.*SECOND)
(?!.*FIRST.*FIRST)
(?=.*FIRST).*
"""
test_str = ("FIRST\n"
"FIRST SECOND\n"
"FIRST SECOND THIRD\n"
"SECOND THIRD FIRST\n"
"SECOND FIRST THIRD\n"
"THIRD SECOND FIRST\n"
"FIRST FIRST\n"
" SECOND FIRST THIRD\n"
"FIRST SECOND SECOND\n"
"The word FIRST is mandatory ; it can appear only once\n"
"The word SECOND can appear zero or one time\n"
"The word THIRD can appear zero or one time\n"
"Order: FIRST, then SECOND then THIRD")
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