Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

KF8 Input: Ignore encoding declarations inside the html markup, as they are sometimes incorrect. Fixes #1022933 (Ebook Viewer shows random Chinese words)

Browse Source
This commit is contained in:
Kovid Goyal 2012-07-10 23:19:45 +05:30
parent 32a52b9e05
commit 95190b45ad
2 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/chardet.py
View File

@ -10,10 +10,15 @@ __docformat__ = 'restructuredtext en'
import re, codecs
ENCODING_PATS = [
# XML declaration
re.compile(r'<\?[^<>]+encoding\s*=\s*[\'"](.*?)[\'"][^<>]*>',
re.IGNORECASE),
# HTML 4 Pragma directive
re.compile(r'''<meta\s+?[^<>]*?content\s*=\s*['"][^'"]*?charset=([-_a-z0-9]+)[^'"]*?['"][^<>]*>''',
re.IGNORECASE),
# HTML 5 charset
re.compile(r'''<meta\s+charset=['"]([-_a-z0-9]+)['"][^<>]*>''',
re.IGNORECASE),
]
ENTITY_PATTERN = re.compile(r'&(\S+?);')

4
src/calibre/ebooks/mobi/reader/markup.py
View File

@ -9,6 +9,8 @@ __docformat__ = 'restructuredtext en'
import re, os
from calibre.ebooks.chardet import strip_encoding_declarations
def update_internal_links(mobi8_reader):
# need to update all links that are internal which
# are based on positions within the xhtml files **BEFORE**
@ -324,6 +326,8 @@ def expand_mobi8_markup(mobi8_reader, resource_map, log):
for i, part in enumerate(parts):
pi = mobi8_reader.partinfo[i]
with open(os.path.join(pi.type, pi.filename), 'wb') as f:
part = strip_encoding_declarations(part)
part = part.replace('<head>', '<head><meta charset="UTF-8"/>')
f.write(part.encode('utf-8'))
spine.append(f.name)