# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:\"(?:(?<=\"(?=[^\n]))[^\n]+?(?=(?<!\\))(?=\"))?\")|(\B'(?:(?<='(?=[^\n]))[^\n]+?(?=(?<!\\))(?='))?')"
test_str = ("\n"
"1. Valid double-quoted strings:\n"
" - \"Hello\"\n"
" - \"This is a test\"\n"
" - \"123\"\n"
" - \"Special characters: @#$%^&*()_+\"\n"
" - \"Escape sequence: \\n\"\n\n"
"2. Valid double-quoted strings with additional characters or variables:\n"
" - \" test aaaaa \\\" \" + asdf\n"
" - \" test \" + ( \"aaaaa\" ) + gdf\n"
" - \" test \\\" \" + `\" aaaa \" + dfg\n"
" - \" test ' aaaaa \\\" \" + dfg\n"
" - \"\"\n\n"
"3. Valid double-quoted strings with special characters:\n"
" - \"sas''as\\\"a1\\'2 ! -_?:sa\"\n"
" - \"''\"\n"
" - \"\\abnb\\ajhgf\\crt098& \\\"'\"\n\n"
"4. Invalid double-quoted strings:\n"
" - \" test \" + ( \"aaaaa\" ) \\\" saf\n"
" - \"\\\\ + \\* test \" \\$ \\. dsdfs\n"
" - (\\\" test \\\" \" + \" aaaa \" sfgd\n"
" - ' test ' + aas ( \"aaaaa\" ) + '\\ sd\n"
" - '\\\\ + \\* test ' \\$ \\. trace\n"
" - (' test ' as ' + ' aaaa '\n"
" - '\"\"'\n"
" - '\"sas'\n"
" - 'ads'\n"
" - 'asdasd\\\"asdsa'\n"
" - \"klkl\"klkl\n"
" - \"asa\\'sasa\\\\\"\n"
" - \\'\\\\\\'\n"
" - \"hhhh\"klkl\"\n"
" - 'jkjkjk'klklk'\n"
" - '\\\"\\\\\\\"'\n"
" - ''\n"
" - '\\\"asa\\'sasa\\\\\\\"'\n"
" - \"sasasasa\\\\\\\\\\\\\"\n\n\n\n"
"1. Valid single-quoted strings:\n"
" - 'Hello'\n"
" - 'This is a test'\n"
" - '123'\n"
" - 'Special characters: @#$%^&*()_+'\n"
" - 'Escape sequence: \\n'\n\n"
"2. Valid single-quoted strings with additional characters or variables:\n"
" - ' test aaaaa \\' ' + asdf\n"
" - ' test ' + ( 'aaaaa' ) + gdf\n"
" - ' test \\' ' + ' aaaa' + dfg\n"
" - ' test \" aaaaa \\' ' + dfg\n"
" - ''\n\n"
"3. Valid single-quoted strings with special characters:\n"
" - 'sas\"\"as\\'a1\\\"2 ! -_?:sa'\n"
" - '\"\"'\n"
" - '\\abnb\\ajhgf\\crt098& \\'\"\"'\n\n"
"4. Invalid single-quoted strings:\n"
" - ' test ' + ( 'aaaaa' ) \\' saf\n"
" - '\\\\ + \\* test ' \\$ \\. dsdfs\n"
" - (\\' test \\' + ' aaaa ' sfgd\n"
" - \" test \\\" \" + \" aaaa \" sfgd\n"
" - ' test ' + aas ( 'aaaaa' ) + '\\ sd\n"
" - '\\\\ + \\* test ' \\$ \\. trace\n"
" - (' test ' as ' + ' aaaa '\n"
" - \"''\"\n"
" - 'sas\"\n"
" - \"ads'\n"
" - 'asdasd\\'asdsa'\n"
" - \"klkl\"klkl\n"
" - \"asa\\'sasa\\\\\"\n"
" - \\'\\\\\\'\n"
" - 'hhhh\"klkl\\'\\\n"
" - \\'jkjkjk\"klklk'\n"
" - \"\\'\\\\\\'\"\n"
" - ''\n"
" - '\\\"asa\\'sasa\\\\\\\"'\n"
" - 'sasasasa\\\\\\\\\\\\'\n")
matches = re.finditer(regex, test_str, re.MULTILINE)
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