# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=((?<=[\s,.:;\"']|^)[\"']))(?:(?=(\\?))\2.)*?(?=\1)"
test_str = ("Hello world \"This is a test\"\n"
"\"This is also an NL test\"\n"
"'And this has an escaped quote don\\'t in it ' Blue Boy\n"
"\"This has a single quote ' but doesn\\' end the quote as it started with double quotes\"\n\n"
"\" Lorem ipsum dolor\\\" sit 'amet' \"\n\n"
"\"你好\" \"こんにちは\" \"Привет\" \"हैलो\"\n"
"\"Foo Bar\" \"Another Value\" \"HELLO WORLD\"")
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