Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved get_title_tokens

Browse Source
This commit is contained in:
Kovid Goyal 2011-04-17 11:13:57 -06:00
parent 8ee74bd2fb
commit 45adf46944
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/calibre/ebooks/metadata/sources/base.py
View File

@ -294,8 +294,16 @@ class Source(Plugin):
Excludes connectives and punctuation. Excludes connectives and punctuation.
''' '''
if title: if title:
pat = re.compile(r'''[-,:;+!@#$%^&*(){}.`~"'\s\[\]/]''') title_patterns = [(re.compile(pat, re.IGNORECASE), repl) for pat, repl in
title = pat.sub(' ', title) [
(r'(?i)[({\[](\d{4}|omnibus|anthology|hardcover|paperback|mass\s*market|edition|ed\.)[\])}]', ''),
(r'(\d+),(\d+)', r'\1\2'),
(r'(\s-)', ' '),
(r"'", ''),
(r'''[:,;+!@#$%^&*(){}.`~"\s\[\]/]''', ' ')
]]
for pat, repl in title_patterns:
title = pat.sub(repl, title)
tokens = title.split() tokens = title.split()
for token in tokens: for token in tokens:
token = token.strip() token = token.strip()