# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
\? # match the literal characters 'text'
(?= # start lookahead
[^"']* # match any number of non-quote characters
(?: # start non-capturing group, repeated zero or more times
("|')[^\1]*\1 # one quoted portion of text
[^"']* # any number of non-quote characters
)* # end non-capturing group
$ # match end of the string
) # end lookahead
"""
test_str = ("test ? query\n"
"query ? test \"text ? text\" test ? id\n"
"query ? test 'text ? text' test ? eee\n\n"
"SELECT * FROM table1 WHERE id = ?\n"
"SELECT * FROM table1 WHERE (id IN (?)) AND (path = 'test?text')\n"
"SELECT * FROM table1 WHERE (id IN (?)) AND (path = \"test?text\")")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | 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