# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?m)^(?:--|[[:space:]]+).+"
test_str = ("-- Query taken from:\n"
"-- https://stackoverflow.com/a/12467388/1655567\n"
"SELECT country.name as country, country.headofstate\n"
"from country\n"
" -- Worst place to add comment ever\n"
" -- Here is even uglier\n"
"inner join city on city.id = country.capital\n"
"where city.population > 100000\n"
"-- this comment makes no sense here and would break sql parser buyt hey\n"
"and country.headofstate like 'A%'\n"
"-- WOW!")
matches = re.finditer(regex, test_str)
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