# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?>(?:\"\"[^\"\"\n]*\"\"|[^;\"\"\n]+)*)\"\"?[^\"\";\n]*(;.*)"
test_str = ("Peekaboo ; A comment starts with a semicolon and continues until the EOL\n"
"...unless the semicolon is surrounded by unescaped dquotes \"Don’t do it ; here\" ;but match me; once\n"
"Im not surrounded \"so pay attention to me\" ; \"peekaboo\"\n"
"Im not surrounded \"so pay attention\" to;me\" ; \"peekaboo\"\n"
"Im not surrounded \"so pay attention to me ; peekaboo\n"
"Dquote escapes a dquote so \"dont pay attention to \"\"me;here\"\" buster\" do it ; here\n"
"Don’t pay attention to \"\"\"me;here\"\"\" but do \"\"it;here\"\"\n"
"and \"dont do \"\"it;here\"\"\" either ;peekaboo\n"
"but \"pay attention to \"it;here\"\" ;not here though\n"
"Simon said \"I like goats\" then he added \"and sheep;\" ;a good comment is \"here\n"
"Simon said \"I like goats\" then he added \"and sheep;\" dont do it here\n"
"Simon said \"\"I like goats;\"peekaboo\n"
"Simon said \"I like goats;\"\"peekaboo")
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