From 7d21c237ccd46ec1d56639ce53b5882bf97d9de3 Mon Sep 17 00:00:00 2001
From: ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Fri, 10 Oct 2003 12:54:46 +0000
Subject: * Changes to the encoding mechanism.  If iconv is found, it is used
 first   for encoding changes.  This should be the case on all 1.8
 installations.   When it isn't found (<1.6), the native REXML encoding
 mechanism is used.   This cleaned out some files, and tightened up the code a
 bit; and iconv   should be faster than the pure Ruby code. * Changed
 deprecated assert_not_nil to assert throughout the tests. * Parse exceptions
 are a little more verbose, and extend RuntimeError. * Bug fixes to
 XPathParser * The Light API is still shifting, like the sands of the desert.
 * Fixed a new Ruby 1.8.0 warning, added some speed optimizations, and  
 tightened error reporting in the base parser

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@4737 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 lib/rexml/encoding.rb | 74 +++++++++++++++++++++------------------------------
 1 file changed, 31 insertions(+), 43 deletions(-)

(limited to 'lib/rexml/encoding.rb')

diff --git a/lib/rexml/encoding.rb b/lib/rexml/encoding.rb
index 06385d8d52..ad8ba7e342 100644
--- a/lib/rexml/encoding.rb
+++ b/lib/rexml/encoding.rb
@@ -2,61 +2,49 @@ module REXML
 	module Encoding
 		@@uconv_available = false
 
-		ENCODING_CLAIMS = { }
-
-		def Encoding.claim( encoding_str, match=nil )
-			if match
-				ENCODING_CLAIMS[ match ] = encoding_str
-			else
-				ENCODING_CLAIMS[ /^\s*<?xml\s*version=(['"]).*?\1\s*encoding=(["'])#{encoding_str}\2/i ] = encoding_str
-			end
-		end
-
 		# Native, default format is UTF-8, so it is declared here rather than in
 		# an encodings/ definition.
 		UTF_8 = 'UTF-8'
-		claim( UTF_8 )
+		UTF_16 = 'UTF-16'
+		UNILE = 'UNILE'
 
 		# ID ---> Encoding name
 		attr_reader :encoding
 		def encoding=( enc )
-                	enc = UTF_8 unless enc
-                	@encoding = enc.upcase
-                	require "rexml/encodings/#@encoding" unless @encoding == UTF_8
-		end
-
-		def check_encoding str
-			rv = ENCODING_CLAIMS.find{|k,v| str =~ k }
-			# Raise an exception if there is a declared encoding and we don't
-			# recognize it
-			unless rv
-				if str =~ /^\s*<?xml\s*version=(['"]).*?\1\s*encoding=(["'])(.*?)\2/
-					raise "A matching encoding handler was not found for encoding '#{$3}', or the encoding handler failed to load due to a missing support library (such as uconv)."
+			old_verbosity = $VERBOSE
+			begin
+				$VERBOSE = false
+				return if defined? @encoding and enc == @encoding
+				if enc and enc != UTF_8
+					@encoding = enc.upcase
+					begin
+						load 'rexml/encodings/ICONV.rb'
+						Iconv::iconv( UTF_8, @encoding, "" )
+					rescue LoadError, Exception => err
+						enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
+						begin
+							load enc_file
+						rescue LoadError
+							raise Exception.new( "No decoder found for encoding #@encoding.  Please install iconv." )
+						end
+					end
 				else
-					return UTF_8
+					enc = UTF_8
+					@encoding = enc.upcase
+					load 'rexml/encodings/UTF-8.rb'
 				end
+			ensure
+				$VERBOSE = old_verbosity
 			end
-			return rv[1]
 		end
 
-		def to_utf_8(str)
-			return str
-		end
-
-		def from_utf_8 content
-			return content
-		end
-	end
-
-	module Encodingses
-		encodings = []
-		$:.each do |incl_dir|
-			if Dir[ File.join(incl_dir, 'rexml', 'encodings') ].size > 0
-				encodings |= Dir[ File.join(incl_dir, 'rexml', 'encodings', '*_decl.rb') ]
-			end
-			encodings.collect!{ |f| File.basename(f) }
-			encodings.uniq!
+		def check_encoding str
+			# We have to recognize UTF-16, LSB UTF-16, and UTF-8
+			return UTF_16 if str[0] == 254 && str[1] == 255
+			return UNILE if str[0] == 255 && str[1] == 254
+			str =~ /^\s*<?xml\s*version=(['"]).*?\2\s*encoding=(["'])(.*?)\2/um
+			return $1.upcase if $1
+			return UTF_8
 		end
-		encodings.each { |enc| require "rexml/encodings/#{enc}" }
 	end
 end
-- 
cgit v1.2.3