validator/htdocs/config charset.cfg,1.16,1.17

Update of /sources/public/validator/htdocs/config
In directory hutz:/tmp/cvs-serv25579/htdocs/config

Modified Files:
	charset.cfg 
Log Message:
Move Encode alias definitions to charset.cfg, register also our non-recommended but recognized aliases.

Index: charset.cfg
===================================================================
RCS file: /sources/public/validator/htdocs/config/charset.cfg,v
retrieving revision 1.16
retrieving revision 1.17
diff -u -d -r1.16 -r1.17
--- charset.cfg	20 Jul 2007 02:58:10 -0000	1.16
+++ charset.cfg	29 Jun 2009 19:57:51 -0000	1.17
@@ -11,11 +11,13 @@
 #
 # ? indicates the action to take:
 # 1: OK, character supported
+# A: OK, character supported, Encode::Alias it to result
 # 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
 
 #e.g:
 # utf-8         = 1
+# some-alias    = A perl-Encode-name
 # odd-alias     = X good-alias
 # bad_charset   = ERR explain reason
 
@@ -30,11 +32,11 @@
 iso-8859-5                      = 1
 iso-8859-6                      = 1
 # implicit bidi, but character encoding is the same
-iso-8859-6-i                    = 1
+iso-8859-6-i                    = A iso-8859-6
 iso-8859-7                      = 1
 iso-8859-8                      = 1
 # implicit bidi, but character encoding is the same
-iso-8859-8-i                    = 1
+iso-8859-8-i                    = A iso-8859-8
 iso-8859-9                      = 1
 iso-8859-10                     = 1
 iso-8859-11                     = 1
@@ -53,7 +55,9 @@
 iso-2022-kr                     = 1
 euc-kr                          = 1
 gb18030                         = 1
-tis-620                         = 1
+# 0xA0 is U+00A0 in ISO-8859-11 but undefined in tis-620
+# other than that the character encodings are equivalent
+tis-620                         = A iso-8859-11
 koi8-r                          = 1
 koi8-u                          = 1
 iso-ir-111                      = 1
@@ -66,9 +70,11 @@
 windows-1256                    = 1
 windows-1257                    = 1
 # windows-1258                  = 1
-macintosh                       = 1
+# Encode::Byte does not know 'macintosh' but MacRoman
+macintosh                       = A MacRoman
 ks_c_5601-1987                  = 1
-ksc_5601                        = 1
+# Encode only knows the long hand version of 'ksc_5601'
+ksc_5601                        = A KS_C_5601-1987
 
 x-mac-roman                     = X macintosh
 x-sjis                          = X shift_jis

Received on Monday, 29 June 2009 19:58:03 UTC