From afb2610676556c004358ee60d391fbd868273a52 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 1 Nov 2024 09:35:15 +0530 Subject: [PATCH] Fix #2086237 [LookupError: unknown encoding mac-centraleurope](https://bugs.launchpad.net/calibre/+bug/2086237) --- src/calibre/ebooks/chardet.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/calibre/ebooks/chardet.py b/src/calibre/ebooks/chardet.py index 0caaa05f5e..402d28bd3c 100644 --- a/src/calibre/ebooks/chardet.py +++ b/src/calibre/ebooks/chardet.py @@ -100,7 +100,7 @@ def find_declared_encoding(raw, limit=50*1024): return ans -_CHARSET_ALIASES = {"macintosh" : "mac-roman", "x-sjis" : "shift-jis"} +_CHARSET_ALIASES = {"macintosh" : "mac-roman", "x-sjis" : "shift-jis", 'mac-centraleurope': 'cp1250'} def detect(bytestring): @@ -108,6 +108,7 @@ def detect(bytestring): bytestring = bytestring.encode('utf-8', 'replace') from calibre_extensions.uchardet import detect as implementation enc = implementation(bytestring).lower() + enc = _CHARSET_ALIASES.get(enc, enc) return {'encoding': enc, 'confidence': 1 if enc else 0}