- From: Bjoern Hoehrmann via cvs-syncmail <cvsmail@w3.org>
- Date: Thu, 18 Aug 2005 02:52:52 +0000
- To: www-validator-cvs@w3.org
Update of /sources/public/validator/htdocs/config In directory hutz:/tmp/cvs-serv24998 Modified Files: charset.cfg Log Message: Use HTML::Encoding instead of proprietary code and some cleanup Index: charset.cfg =================================================================== RCS file: /sources/public/validator/htdocs/config/charset.cfg,v retrieving revision 1.10 retrieving revision 1.11 diff -u -d -r1.10 -r1.11 --- charset.cfg 18 May 2005 09:31:51 -0000 1.10 +++ charset.cfg 18 Aug 2005 02:52:50 -0000 1.11 @@ -1,71 +1,59 @@ # -# Mapping of 'charset' or 'encoding' parameter to conversion parameter +# List of accepted encodings. # # $Id$ # -# this version for glibc iconv 2.1; change for other versions -# -# Syntax: -# -# charset/encoding = ? result -# -# Note: charsets and results are lowercase, actions are uppercase +# The Validator will refuse to decode documents in an encoding +# other than those listed here. The list is independent of what +# is supported on a specific system but subject to the Validator +# policy for acceptable encodings. # -# ? indicates the action to take: -# I iconv: use result as input to iconv -# Note: use this also if iconv takes charset parameter directly -# X: frequent error, e.g. starting with x-; ask user to replace with result -utf-16 = I utf-16 -utf-16be = I utf-16be -utf-16le = I utf-16le -iso-8859-1 = I iso-8859-1 -iso-8859-2 = I iso-8859-2 -iso-8859-3 = iso-8859-3 -iso-8859-4 = iso-8859-4 -iso-8859-5 = I iso-8859-5 -iso-8859-6 = I iso-8859-6 -# implicit bidi, but character encoding is the same -iso-8859-6-i = I iso-8859-6 -iso-8859-7 = I iso-8859-7 -iso-8859-8 = I iso-8859-8 -# implicit bidi, but character encoding is the same -iso-8859-8-i = I iso-8859-8 -iso-8859-9 = I iso-8859-9 -iso-8859-10 = I iso-8859-10 -# iso-8859-11/12 don't exist yet -iso-8859-13 = I iso-8859-13 -iso-8859-14 = I iso-8859-14 -iso-8859-15 = I iso-8859-15 -iso-8859-16 = I iso-8859-16 -us-ascii = I us-ascii -iso-2022-jp = I iso-2022-jp -shift_jis = I shift_jis -euc-jp = I euc-jp -gb2312 = I gb2312 -big5 = I big5 -iso-2022-kr = I iso-2022-kr -euc-kr = I euc-kr -gb18030 = I gb18030 -tis-620 = I tis-620 -koi8-r = I koi8-r -koi8-u = I koi8-u -windows-1250 = I cp1250 -windows-1251 = I cp1251 -windows-1252 = I cp1252 -windows-1253 = I cp1253 -windows-1254 = I cp1254 -windows-1255 = I cp1255 -windows-1256 = I cp1256 -windows-1257 = I cp1257 -# windows-1258 = I cp1258 # wait until normalization checked -macintosh = I macintosh -x-mac-roman = X macintosh -x-sjis = X shift_jis -iso8859-1 = X iso-8859-1 -ascii = X us-ascii -8859_1 = X iso-8859-1 -# this one is in IANA, but better use only windows-1252 -iso-8859-1-Windows-3.1-Latin-1 = X windows-1252 -ks_c_5601-1987 = I ks_c_5601-1987 -ksc_5601 = I ksc_5601 +utf-8 = 1 +utf-16 = 1 +utf-16be = 1 +utf-16le = 1 +iso-8859-1 = 1 +iso-8859-2 = 1 +iso-8859-3 = 1 +iso-8859-4 = 1 +iso-8859-5 = 1 +iso-8859-6 = 1 +iso-8859-6-i = 1 +iso-8859-7 = 1 +iso-8859-8 = 1 +iso-8859-8-i = 1 +iso-8859-9 = 1 +iso-8859-10 = 1 +iso-8859-13 = 1 +iso-8859-14 = 1 +iso-8859-15 = 1 +iso-8859-16 = 1 +us-ascii = 1 +iso-2022-jp = 1 +shift_jis = 1 +euc-jp = 1 +gb2312 = 1 +big5 = 1 +iso-2022-kr = 1 +euc-kr = 1 +gb18030 = 1 +tis-620 = 1 +koi8-r = 1 +koi8-u = 1 +windows-1250 = 1 +windows-1251 = 1 +windows-1252 = 1 +windows-1253 = 1 +windows-1254 = 1 +windows-1255 = 1 +windows-1256 = 1 +windows-1257 = 1 +macintosh = 1 +x-mac-roman = 1 +x-sjis = 1 +iso8859-1 = 1 +ascii = 1 +iso-8859-1-Windows-3.1-Latin-1 = 1 +ks_c_5601-1987 = 1 +ksc_5601 = 1
Received on Thursday, 18 August 2005 02:53:02 UTC