# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?<=^|\v)
\h*+\*\h*+
(?:
(?:
(?P<annotation>
@(?P<name>\w++)
(?:
(?<=@param)\h++(?P<type>\w++(?:\[\])?)\h++\$(?P<variable>\w++)
|(?<=@return)\h++(?P<type>\w++(?:\[\])?)
|(?<=@throws)\h++(?P<class>\w++)
|(?<=@cache)\h++(?P<time>\d++)
|(?<=@roles)\h++(?P<roles>\w++(?:\h*+,\h*+\w++)*)
)?
)
)
(?P<comment>\h++[^\v]++)?
(?:(?P<comment>\v)\h*+\*\h*+(?P<comment>[^\v@\h\*][^\v]++))*+
|(?P<description>(?:[^\v@\h\*][^\v]++)
(?:
\v\h*+\*\h*+[^\v@\h\*][^\v]++
)*+
)
)
"""
test_str = ("/**\n"
" * bla bla \n"
" *bla2 @ bla2 @\n"
" *\n"
" * bla bla 3\n"
" *\n"
" * @olivier voila\n"
" * @param string $sku1 bidule\n"
" *\n"
" * @param string[] $sku2\n"
" *\n"
" * @param string $sku3 toto bidule @\n"
" * machin truc\n"
" *\n"
" * @param string $sku4\n"
" * machin truc\n"
" *\n"
" * @deprecated\n"
" *\n"
" * @deprecated toto\n"
" *\n"
" * @throws Exception\n"
" * @throws Exception\n"
" * machin\n"
" * @return Cfe_Type_Product\n"
" * @cache 3600\n"
" * @roles toto, titi,truc , machin\n"
" */")
matches = re.finditer(regex, test_str, re.VERBOSE | re.DOTALL)
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