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

Fix bug in regex to extract charset from <meta> tags

Browse Source
This commit is contained in:
Kovid Goyal 2010-11-05 18:59:20 -06:00
parent 43103496ab
commit 5f6ff5609d
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/ebooks/chardet/__init__.py
View File

@ -32,7 +32,7 @@ def detect(aBuf):
ENCODING_PATS = [ ENCODING_PATS = [
re.compile(r'<\?[^<>]+encoding\s*=\s*[\'"](.*?)[\'"][^<>]*>', re.compile(r'<\?[^<>]+encoding\s*=\s*[\'"](.*?)[\'"][^<>]*>',
re.IGNORECASE), re.IGNORECASE),
re.compile(r'''<meta\s+?[^<>]+?content\s*=\s*['"][^'"]*?charset=([-a-z0-9]+)[^'"]*?['"][^<>]*>''', re.compile(r'''<meta\s+?[^<>]*?content\s*=\s*['"][^'"]*?charset=([-a-z0-9]+)[^'"]*?['"][^<>]*>''',
re.IGNORECASE) re.IGNORECASE)
] ]
ENTITY_PATTERN = re.compile(r'&(\S+?);') ENTITY_PATTERN = re.compile(r'&(\S+?);')