# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([\"'])\s*(SELECT)(?:\s+(?:(?!\1).)*)?\s+(FROM)(?:\s+(?:(?!\1).)*)?\1(?:[^\w]|$)"
test_str = (" SELECT * FROM tbl -- no match - not in a string\n"
" \"SELECT * FROM tbl\" -- matches - in a double-quoted string\n"
" 'SELECT * FROM tbl;' -- matches - in a single-quoted string\n"
" 'SELECT * FROM it's -- no match - letter after end quote\n"
" \"SELECT * FROM tbl' -- no match - quotation marks don't match\n"
" 'SELECT * FROM tbl\" -- no match - quotation marks don't match\n"
" \"select * from tbl\" -- no match - keywords not upper case\n"
" 'Select * From tbl' -- no match - still not all upper case\n"
" \"SELECT col1 FROM\" -- matches - even though no table name\n"
" ' SELECT col1 FROM ' -- matches - as above with more whitespace\n"
" 'SELECT col1, col2 FROM' -- matches - with multiple columns\n"
" \"SELECT 'c' FROM 'tbl'\" -- matches - with identifier names quoted\n"
" \"SELECT \"c\" FROM\" -- no match - same quotation marks for identifier\n"
" \"SELECT * FROM\" \"quoted\" -- matches - with another unmatched quoted string\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