diff options
Diffstat (limited to 'htdocs')
| -rw-r--r-- | htdocs/config/charset.cfg | 89 |
1 files changed, 72 insertions, 17 deletions
diff --git a/htdocs/config/charset.cfg b/htdocs/config/charset.cfg index aed81a6..f007cc4 100644 --- a/htdocs/config/charset.cfg +++ b/htdocs/config/charset.cfg @@ -1,23 +1,78 @@ # -# List of encodings aliases and forbidden encodings +# list of accepted/preferred character encodings # -# $Id: charset.cfg,v 1.14 2007-07-19 03:59:23 ot Exp $ - -# This list indicates character encoding aliases that are -# not recommended, along with a recommended equivalent, e.g: -# encoding-obscure = encoding-well-known - -# It also lists encoding names that the validator will refuse to treat: -# bogus_encoding = Encoding Forbidden (Reason why) +# $Id: charset.cfg,v 1.15 2007-07-19 08:18:30 ot Exp $ +# +# Syntax: +# +# charset/encoding = ? result +# +# Note: charsets and results are lowercase, actions are uppercase +# +# ? indicates the action to take: +# 1: OK, character supported +# X: frequent error, e.g. starting with x-; ask user to replace with result +# ERR: a charset we refuse, per some policy. Reason stated after ERR -# The list is independent of what -# is supported on a specific system but subject to the Validator -# policy for acceptable encodings. +#e.g: +# utf-8 = 1 +# odd-alias = X good-alias +# bad_charset = ERR explain reason +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 +# implicit bidi, but character encoding is the same +iso-8859-6-i = 1 +iso-8859-7 = 1 +iso-8859-8 = 1 +# implicit bidi, but character encoding is the same +iso-8859-8-i = 1 +iso-8859-9 = 1 +iso-8859-10 = 1 +iso-8859-11 = 1 +# iso-8859-12 doesn't exist (yet?) +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 +iso-ir-111 = 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 +# windows-1258 = 1 +macintosh = 1 +ks_c_5601-1987 = 1 +ksc_5601 = 1 -x-mac-roman = macintosh -x-sjis = shift_jis -iso8859-1 = iso-8859-1 -ascii = us-ascii +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 = windows-1252 +iso-8859-1-Windows-3.1-Latin-1 = X windows-1252 |