mhonarc-commits
[Top] [All Lists]

CVS: mhonarc/MHonArc/lib mhopt.pl,2.37,2.38

2002-11-28 01:57:37
Update of /cvsroot/mhonarc/mhonarc/MHonArc/lib
In directory subversions:/tmp/cvs-serv368/lib

Modified Files:
	mhopt.pl 
Log Message:
* MHonArc::CharEnt:
  + Added support for Chinese charsets.
  + Added support for converting UTF-8.
  * Optimized the conversion code to use s/// operation for conversion.
    Some simpling testing shows it is faster than the loop/substr()
    method (mainly because character iteration is now done in the
    perl internals).
  - Removed $8bitonly option to str2sgml().  It not very applicable
    now with all the newer charsets added and it complicates the
    conversion code.
* Some additional charset aliases added.


Index: mhopt.pl
===================================================================
RCS file: /cvsroot/mhonarc/mhonarc/MHonArc/lib/mhopt.pl,v
retrieving revision 2.37
retrieving revision 2.38
diff -C2 -r2.37 -r2.38
*** mhopt.pl	24 Nov 2002 06:11:10 -0000	2.37
--- mhopt.pl	28 Nov 2002 08:57:19 -0000	2.38
***************
*** 923,927 ****
--- 923,930 ----
  	    'iso-8859-16',   		'MHonArc::CharEnt::str2sgml',
  	    'iso-2022-jp',   		'iso_2022_jp::str2html',
+ 	    'utf-8',    		'MHonArc::CharEnt::str2sgml',
  	    'cp866',    		'MHonArc::CharEnt::str2sgml',
+ 	    'cp936',    		'MHonArc::CharEnt::str2sgml',
+ 	    'cp950',    		'MHonArc::CharEnt::str2sgml',
  	    'cp1250',   		'MHonArc::CharEnt::str2sgml',
  	    'cp1251',   		'MHonArc::CharEnt::str2sgml',
***************
*** 943,946 ****
--- 946,951 ----
  	    'gost19768-87',            	'MHonArc::CharEnt::str2sgml',
  	    'viscii',            	'MHonArc::CharEnt::str2sgml',
+ 	    'big5-hkscs',		'MHonArc::CharEnt::str2sgml',
+ 	    'gb2312',    		'MHonArc::CharEnt::str2sgml',
  	    'apple-arabic',		'MHonArc::CharEnt::str2sgml',
  	    'apple-centeuro',		'MHonArc::CharEnt::str2sgml',
***************
*** 977,981 ****
--- 982,989 ----
  	    'iso-8859-16',   		'MHonArc/CharEnt.pm',
  	    'iso-2022-jp',   		'iso2022jp.pl',
+ 	    'utf-8',    		'MHonArc/CharEnt.pm',
  	    'cp866',    		'MHonArc/CharEnt.pm',
+ 	    'cp936',    		'MHonArc/CharEnt.pm',
+ 	    'cp950',    		'MHonArc/CharEnt.pm',
  	    'cp1250',   		'MHonArc/CharEnt.pm',
  	    'cp1251',   		'MHonArc/CharEnt.pm',
***************
*** 997,1000 ****
--- 1005,1010 ----
  	    'gost19768-87',            	'MHonArc/CharEnt.pm',
  	    'viscii',            	'MHonArc/CharEnt.pm',
+ 	    'big5-hkscs',		'MHonArc/CharEnt.pm',
+ 	    'gb2312',    		'MHonArc/CharEnt.pm',
  	    'apple-arabic',		'MHonArc/CharEnt.pm',
  	    'apple-centeuro',		'MHonArc/CharEnt.pm',
***************
*** 1017,1022 ****
  	readmail::MAILset_charset_aliases({ 
  	    'us-ascii'     => [ 'ascii',
! 				'iso646', 'iso646-us',
! 				'cp367',
  				'csascii',
  				'iso-ir-6',
--- 1027,1033 ----
  	readmail::MAILset_charset_aliases({ 
  	    'us-ascii'     => [ 'ascii',
! 				'ansi_x3.4-1986',
! 				'iso646', 'iso646-us', 'iso646.irv:1991',
! 				'cp367', 'ibm367',
  				'csascii',
  				'iso-ir-6',
***************
*** 1070,1073 ****
--- 1081,1089 ----
  				'iso8859-15', 'iso8859_15',
  				'8859-15', '8859_15' ],
+ 	    'utf-8'        => [ 'utf8' ],
+ 	    'cp936'        => [ 'gbk',
+ 				'ms936',
+ 				'windows-936' ],
+ 	    'cp950'        => [ 'big5', 'csbig5' ],
  	    'cp1250'       => [ 'windows-1250' ],
  	    'cp1251'       => [ 'windows-1251' ],
***************
*** 1085,1088 ****
--- 1101,1109 ----
  	    'gost-19768-87'  => [ 'ecma-cyrillic',
  				  'ecma-113', 'ecma-113:1988' ],
+ 	    'big5-hkscs'     => [ 'big5hkscs' ],
+ 	    'gb2312'	     => [ 'gb_2312-80', 'csgb2312', 'hz-gb-2312',
+ 				  'iso-ir-58',
+ 				  'chinese',
+ 				  'csiso58gb231280' ],
  	    'apple-arabic'   => [ 'x-mac-arabic' ],
  	    'apple-centeuro' => [ 'x-mac-centeuro' ],

---------------------------------------------------------------------
To sign-off this list, send email to majordomo(_at_)mhonarc(_dot_)org with the
message text UNSUBSCRIBE MHONARC-DEV