# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<![\p{L}\p{N}_])(?=[\p{L}\p{N}_])|(?<=[\p{L}\p{N}_])(?![\p{L}\p{N}_])"
test_str = ("To achieve this, I am using the regular expression /\\bsea/gmi, which works perfectly with English characters. However, it fails to produce the desired results when applied to Swedish characters, like 'ä', 'å', and 'ö'. For example, if the search word is 'gen', the postfix 'gen' in the word 'vägen' is incorrectly highlighted. It seems that the regular expression treats these characters as special characters or something similar. I even tried adding unicode modifier u but that didt't help either.\n\n"
"gen\n"
"gena\n"
"agen\n"
"ägen\n"
"genä\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.UNICODE)
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