From: Marek Stępniowski Date: Mon, 15 Sep 2008 14:26:10 +0000 (+0200) Subject: Improved some regexes. X-Git-Url: https://git.mdrn.pl/wolnelektury.git/commitdiff_plain/f8228cc6712f9a71f877b0ea60719c256519f16e Improved some regexes. --- diff --git a/lib/librarian/bin/book2txt.py b/lib/librarian/bin/book2txt.py index 86f6f1274..413ff674b 100755 --- a/lib/librarian/bin/book2txt.py +++ b/lib/librarian/bin/book2txt.py @@ -11,10 +11,10 @@ REGEXES = [ (r']*>(.|\n)*?', ''), ('<(begin|end)\\sid=[\'|"][b|e]\\d+[\'|"]\\s/>', ''), (r'(()|())', ''), - (r'[^<]*', ''), - (r'(.|\n)*?

', ''), + (r'(.|\n)*?', ''), + (r'(.|\n)*?', ''), (r'<[^>]+>', ''), - (r'/$', ''), + (r'/\n', ''), (r'---', u'—'), (r'--', u'-'), (r',,', u'„'),