# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?|([a-zA-Z0-9]+)[({[«]([a-zA-Z\s]+)[)}\]»]|[({[«]([a-zA-Z\s]+)[)}\]»]([a-zA-Z0-9]+))"
test_str = ("// i want to mark for single brackets examples below other heighlight pattren not disturb.please\n"
"(weather // i want to mark this word\n"
"weather) // i want to mark this word\n"
"(weather is good // i want to mark this word\n"
"weather is good) // i want to mark this word\n"
"weathe)r\n"
"wea(ther\n"
"and same for other brackets {,[,«\n"
"{weather // i want to mark this word\n"
"weather} // i want to mark this word\n"
"{weather is good // i want to mark this word\n"
"weather is good} // i want to mark this word\n"
"weathe}r // i want to mark this word\n"
"weathe{r // i want to mark this word\n\n"
"[weather // i want to mark this word\n"
"weather] // i want to mark this word\n"
"[weather is good // i want to mark this word\n"
"weather is good] // i want to mark this word\n"
"weathe]r // i want to mark this word\n"
"weathe[r // i want to mark this word\n"
"«weather // i want to mark this word\n"
"weather} // i want to mark this word\n"
"«weather is good // i want to mark this word\n"
"weather is good» // i want to mark this word\n"
"weathe»r // i want to mark this word\n"
"weathe»r // i want to mark this word\n\n"
"(Weather) is good. // not need to mark this beacuase this word correct word\n"
"Weath(er) is good. // mark\n"
"Weath(er is good). // mark\n"
"Weather (is) (good).\n"
"My name is Rah(eel) // mark\n"
"Best pro(duct) // mark\n"
"(Weather is good) // not need to mark this beacuase this word konown word\n"
"we(ather)\n"
"(weath)er is good. // mark\n"
"(weath)er // mark\n"
"weather(is fine)\n"
"weather is good\n"
"{weather is good} //not need to mark correct\n"
"weat{er is good} // mark\n"
"we{ather} is fine // mark\n\n"
"{weathe}r is fine // i want to mark this word\n"
"{weather is fin}e // i want to mark this word\n\n"
"[weather is good] //not need to mark correct\n"
"weat[her is good] // mark\n"
"we[ather] is fine // mark\n\n"
"[weathe]r is fine // mark\n"
"[weather is f]ine // mark\n\n"
"we[ather] is fine // mark\n\n"
"«weather is good» //not need to mark\n"
"weat«her is good» // mark\n\n"
"we«ather» is fine // mark\n\n"
"«weat»her is fine // mark\n"
"«weather is fi»ne // mark\n\n\n\n\n\n\n\n")
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