# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:[\s,:!&@$%^.]|\\n|(?<!\w)'|'(?: |$))+"
test_str = ("word\n"
"one of each\n"
"one fish two fish red fish blue fish\n"
"one,two,three\n"
"one,\\ntwo,\\nthree\n"
"car : carpet as java : javascript!!&@$%^&\n"
"testing, 1, 2 testing\n"
"go Go GO Stop stop\n"
"First: don't laugh. Then: don't cry.\n"
"Joe can't tell between app, apple and a.\n"
"Joe can't tell between 'large' and large.\n"
" multiple whitespaces\n"
",\\n,one,\\n ,two \\n 'three'")
matches = re.finditer(regex, test_str, re.MULTILINE | re.UNICODE)
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