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

When detecting the encoding of HTML documents, if the document contains multiple charset declarations, prefer the HTML 5 syntax to the HTML 4 syntax. Fixes #1364961 [Unicode Conversion on Amazon after Release 2.x](https://bugs.launchpad.net/calibre/+bug/1364961)

Browse Source
This commit is contained in:
Kovid Goyal 2014-09-04 15:45:24 +05:30
parent e905c093b8
commit 78e28cbe9e
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/chardet.py
View File

@ -12,10 +12,10 @@ 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]+)[^'"]*?['"][^<>]*>(?:\s*</meta>){0,1}''', re.IGNORECASE),
# HTML 5 charset
re.compile(r'''<meta\s+charset=['"]([-_a-z0-9]+)['"][^<>]*>(?:\s*</meta>){0,1}''', re.IGNORECASE),
# HTML 4 Pragma directive
re.compile(r'''<meta\s+?[^<>]*?content\s*=\s*['"][^'"]*?charset=([-_a-z0-9]+)[^'"]*?['"][^<>]*>(?:\s*</meta>){0,1}''', re.IGNORECASE),
]
ENTITY_PATTERN = re.compile(r'&(\S+?);')