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

Unicode normalize string received from metadata download plugins

Browse Source
This commit is contained in:
Kovid Goyal 2022-01-21 15:24:22 +05:30
parent 38aca62463
commit 73a2648bfa
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/calibre/ebooks/metadata/sources/identify.py
View File

@ -6,6 +6,7 @@ __copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re import re
import unicodedata
import time import time
from datetime import datetime from datetime import datetime
from io import StringIO from io import StringIO
@ -22,7 +23,7 @@ from calibre.utils.date import UNDEFINED_DATE, as_utc, utc_tz
from calibre.utils.formatter import EvalFormatter from calibre.utils.formatter import EvalFormatter
from calibre.utils.html2text import html2text from calibre.utils.html2text import html2text
from calibre.utils.icu import lower, primary_sort_key from calibre.utils.icu import lower, primary_sort_key
from polyglot.builtins import iteritems, itervalues from polyglot.builtins import iteritems, itervalues, as_unicode
from polyglot.queue import Empty, Queue from polyglot.queue import Empty, Queue
from polyglot.urllib import quote, urlparse from polyglot.urllib import quote, urlparse
@ -507,6 +508,21 @@ def identify(log, abort, # {{{
from calibre.ebooks.metadata.author_mapper import compile_rules, map_authors from calibre.ebooks.metadata.author_mapper import compile_rules, map_authors
am_rules = compile_rules(am_rules) am_rules = compile_rules(am_rules)
# normalize unicode strings
n = lambda x: unicodedata.normalize('NFC', as_unicode(x or '', errors='replace'))
for r in results:
if r.tags:
r.tags = list(map(n, r.tags))
if r.authors:
r.authors = list(map(n, r.authors))
if r.author_sort:
r.author_sort = n(r.author_sort)
if r.title:
r.title = n(r.title)
if r.publisher:
r.publisher = n(r.publisher)
if r.comments:
r.comments = n(r.comments)
max_tags = msprefs['max_tags'] max_tags = msprefs['max_tags']
for r in results: for r in results:
if tm_rules: if tm_rules: