[REXML] encoding precedence

Hi,

Currently, REXML prefers iconv module to convert encodings.
Iconv can be useful for general purpose, but, to be frank, is
halfdone, I guess.  In many cases, particular conversion
engines would be much preferable if available.

Also, nkf module, a bundled library, can deal with Japanese
characters in utf-8 as well as in others already, so I'd like
to give priority nkf to over uconv, which is not bundled.


Index: ruby-ruby_1_8/lib/rexml/encoding.rb
===================================================================
RCS file: /cvs/ruby/src/ruby/lib/rexml/encoding.rb,v
retrieving revision 1.5.2.1
diff -U2 -p -r1.5.2.1 encoding.rb
--- ruby-ruby_1_8/lib/rexml/encoding.rb	19 May 2005 03:51:52 -0000	1.5.2.1
+++ ruby-ruby_1_8/lib/rexml/encoding.rb	18 Oct 2005 02:10:51 -0000
@@ -26,26 +26,20 @@ module REXML
 				$VERBOSE = false
 				return if defined? @encoding and enc == @encoding
-				if enc and enc != UTF_8
-					@encoding = enc.upcase
+				if enc
+					raise ArgumentError, "Bad encoding name #{enc}" unless /\A[\w-]+\z/n =~ enc
+					@encoding = enc.upcase.untaint
+				else
+					@encoding = UTF_8
+				end
+				err = nil
+				[@encoding, "ICONV"].each do |enc|
 					begin
-                                               require 'rexml/encodings/ICONV.rb'
-                                               Encoding.apply(self, "ICONV")
+						require File.join("rexml", "encodings", "#{enc}.rb")
+						return Encoding.apply(self, enc)
 					rescue LoadError, Exception => err
-                                               raise ArgumentError, "Bad encoding name #@encoding" unless @encoding =~ /^[\w-]+$/
-						@encoding.untaint 
-						enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
-						begin
-                                                       require enc_file
-                                                       Encoding.apply(self, @encoding)
-						rescue LoadError
-                                                       puts $!.message
-                                                       raise ArgumentError, "No decoder found for encoding #@encoding.  Please install iconv."
 						end
 					end
-				else
-                                       @encoding = UTF_8
-                                       require 'rexml/encodings/UTF-8.rb'
-                                       Encoding.apply(self, @encoding)
-				end
+				puts err.message
+				raise ArgumentError, "No decoder found for encoding #@encoding.  Please install iconv."
 			ensure
 				$VERBOSE = old_verbosity
Index: ruby-ruby_1_8/lib/rexml/encodings/EUC-JP.rb
===================================================================
RCS file: /cvs/ruby/src/ruby/lib/rexml/encodings/EUC-JP.rb,v
retrieving revision 1.6.2.1
diff -U2 -p -r1.6.2.1 EUC-JP.rb
--- ruby-ruby_1_8/lib/rexml/encodings/EUC-JP.rb	19 May 2005 03:51:53 -0000	1.6.2.1
+++ ruby-ruby_1_8/lib/rexml/encodings/EUC-JP.rb	31 Oct 2005 04:31:52 -0000
@@ -1,12 +1,27 @@
-require 'uconv'
-
 module REXML
   module Encoding
-    def decode_eucjp(str)
-      Uconv::euctou8(str)
-    end
+    begin
+      require 'uconv'
+
+      def decode_eucjp(str)
+        Uconv::euctou8(str)
+      end
+
+      def encode_eucjp content
+        Uconv::u8toeuc(content)
+      end
+    rescue LoadError
+      require 'nkf'
+
+      EUCTOU8 = '-Ewm0'
+      U8TOEUC = '-Wem0'
 
-    def encode_eucjp content
-      Uconv::u8toeuc(content)
+      def decode_eucjp(str)
+        NKF.nkf(EUCTOU8, str)
+      end
+
+      def encode_eucjp content
+        NKF.nkf(U8TOEUC, content)
+      end
     end
 
Index: ruby-ruby_1_8/lib/rexml/encodings/SHIFT-JIS.rb
===================================================================
RCS file: /cvs/ruby/src/ruby/lib/rexml/encodings/SHIFT-JIS.rb,v
retrieving revision 1.2.2.3
diff -U2 -p -r1.2.2.3 SHIFT-JIS.rb
--- ruby-ruby_1_8/lib/rexml/encodings/SHIFT-JIS.rb	19 May 2005 10:08:11 -0000	1.2.2.3
+++ ruby-ruby_1_8/lib/rexml/encodings/SHIFT-JIS.rb	31 Oct 2005 04:31:52 -0000
@@ -1,12 +1,27 @@
-require 'uconv'
-
 module REXML
   module Encoding
-    def decode_sjis content
-      Uconv::sjistou8(content)
-    end
+    begin
+      require 'uconv'
+
+      def decode_sjis content
+        Uconv::sjistou8(content)
+      end
+
+      def encode_sjis(str)
+        Uconv::u8tosjis(str)
+      end
+    rescue LoadError
+      require 'nkf'
+
+      SJISTOU8 = '-Swm0'
+      U8TOSJIS = '-Wsm0'
 
-    def encode_sjis(str)
-      Uconv::u8tosjis(str)
+      def decode_sjis(str)
+        NKF.nkf(SJISTOU8, str)
+      end
+
+      def encode_sjis content
+        NKF.nkf(U8TOSJIS, content)
+      end
     end
 


-- 
Nobu Nakada