# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?(DEFINE)
(?<nestedBrackets> \[ [^][]* (?:\g<nestedBrackets>[^][]*)*+ ] )
)
(?: # two possible entry points
\G(?!\A) # 1. contiguous to a previous match
| # OR
[^[]* \[ # 2. all characters until an opening bracket
)
# all possible characters until "," or the closing bracket:
[^]["]* # all that is not ] [ or "
(?:
\g<nestedBrackets> [^]["]* # possible nested brackets
| # OR
"(?!,") [^]["]* # a quote not followed by ,"
)*+ # repeat as needed
\K # remove all on the left from match result
(?:
"," # match the target
|
] (*SKIP)(*F) # closing bracket: break the contiguity
)
"""
test_str = "[word:\"pla pla\",\"pla pla\",\"[other_word:\"pla pla\",\"[word:\"pla\",\"pla\"end word]\",\"pla pla\"end other_word]\",\"pla pla\",\"[word:\"pla\",\"pla\"end word]\"end word]\",\""
subst = "|,|"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.VERBOSE)
if result:
print (result)
# 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