From: Nathan TeBlunthuis Date: Thu, 10 Mar 2022 23:07:27 +0000 (-0800) Subject: add a minor comment on the source of the redirect regex X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/commitdiff_plain/32283aa4da2eb256af9bec2e2d42481a1ca19d0b add a minor comment on the source of the redirect regex --- diff --git a/wikiq b/wikiq index 6d2e7fa..a9b8f2e 100755 --- a/wikiq +++ b/wikiq @@ -389,6 +389,8 @@ class WikiqParser(): redirect_aliases = chain(* map(lambda obj: obj.get("aliases"), redirect_config)) redirect_aliases = list(map(lambda s: s.lstrip('#'), redirect_aliases)) redirect_aliases.append('REDIRECT') # just in case + + # this regular expression is copied from pywikibot pattern = '(?:' + '|'.join(redirect_aliases) + ')' redirect_regex = re.compile(r'\s*#{pattern}\s*:?\s*\[\[(.+?)(?:\|.*?)?\]\]' .format(pattern=pattern), re.IGNORECASE | re.DOTALL)