# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^#start of line
(?![^\n!]*!{2,})
(?=[^_\n]*_[^_]*) #if _ exists, then:
([^_:]+) #mandatory group 1
((?=:[^:\n]):[^:_(\n]+|) #optional group 2
(_(?!_)) #group 3 mandatory
([^_\-(\n]+) # group 4 mandatory
\( #mandatory (
([^()\n]+) # group 5 mandatory
\) #mandatory )
((?=!)!|) # group 6 optional
((?=:[^!:@\n]):[^!:@\n]+|) # group 7 optional
((?=::[^!:@\n])::[^!:@\n]+|) #group 8 optional
((?=@[^!:@\n])@[^!:@\n]+|) #group 9 optional
$ #end of line
"""
test_str = ("# OK - Matches all components if all are provided\n"
"contextClassName:pc_ruleName(param_One paramTwo)!:pc::pe@media\n\n"
"# OK - Return group 2 blank when no : exists before _ which is group 3\n"
"contextClassName_ruleName(param_One paramTwo)!:pc::pe@media\n\n"
"# OK - When ! is not provided return group 6 blank\n"
"contextClassName_ruleName(param_One paramTwo):pc::pe@media\n\n"
"# NOTOK - More than one consecutive !\n"
"contextClassName_ruleName(param_One paramTwo)!!:pc::pe@media\n\n"
"# NOTOK - 3 More than two : at instruction tail\n"
"contextClassName_ruleName(param_One paramTwo):::pe@media\n\n"
"# OK - 2 At instruction tail :: is resolved to group 8 \n"
"contextClassName_ruleName(param_One paramTwo)::pe@media\n\n"
"# OK - 1 At instruction tail : is resolved to group 7 \n"
"contextClassName_ruleName(param_One paramTwo):pe@media\n\n"
"# OK - At instruction start : followed by chars\n"
"contextClassName:pc_ruleName(param_One paramTwo):pe@media\n\n"
"# NOTOK - At instruction start : not followed by chars\n"
"contextClassName:_ruleName(param_One paramTwo):pe@media\n\n"
"# NOTOK - At instruction start :: followed by chars\n"
"contextClassName::pc_ruleName(param_One paramTwo):pe@media\n\n"
"# OK - Whole instruction tail is optional \n"
"contextClassName:pc_ruleName(param_One paramTwo)\n\n"
"# OK - Parameter value can contain anything\n"
"contextClassName:pc_ruleName(param_One param#$^Two)")
matches = re.finditer(regex, test_str, re.MULTILINE | 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