rubysl-rexml 1.0.0

data/lib/rexml/encoding.rb

@@ -0,0 +1,71 @@
+# -*- mode: ruby; ruby-indent-level: 2; indent-tabs-mode: t; tab-width: 2 -*- vim: sw=2 ts=2
+module REXML
+  module Encoding
+    @encoding_methods = {}
+    def self.register(enc, &block)
+      @encoding_methods[enc] = block
+    end
+    def self.apply(obj, enc)
+      @encoding_methods[enc][obj]
+    end
+    def self.encoding_method(enc)
+      @encoding_methods[enc]
+    end
+
+    # Native, default format is UTF-8, so it is declared here rather than in
+    # an encodings/ definition.
+    UTF_8 = 'UTF-8'
+    UTF_16 = 'UTF-16'
+    UNILE = 'UNILE'
+
+    # ID ---> Encoding name
+    attr_reader :encoding
+    def encoding=( enc )
+      old_verbosity = $VERBOSE
+      begin
+        $VERBOSE = false
+        enc = enc.nil? ? nil : enc.upcase
+        return false if defined? @encoding and enc == @encoding
+        if enc and enc != UTF_8
+          @encoding = enc
+          raise ArgumentError, "Bad encoding name #@encoding" unless @encoding =~ /^[\w-]+$/
+          @encoding.untaint 
+          begin
+            require 'rexml/encodings/ICONV.rb'
+            Encoding.apply(self, "ICONV")
+          rescue LoadError, Exception
+            begin
+              enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
+              require enc_file
+              Encoding.apply(self, @encoding)
+            rescue LoadError => err
+              puts err.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
+      ensure
+        $VERBOSE = old_verbosity
+      end
+      true
+    end
+
+    def check_encoding str
+      # We have to recognize UTF-16, LSB UTF-16, and UTF-8
+      if str[0] == 0xfe && str[1] == 0xff
+        str[0,2] = ""
+        return UTF_16
+      elsif str[0] == 0xff && str[1] == 0xfe
+        str[0,2] = ""
+        return UNILE
+      end
+      str =~ /^\s*<\?xml\s+version\s*=\s*(['"]).*?\1\s+encoding\s*=\s*(["'])(.*?)\2/um
+      return $3.upcase if $3
+      return UTF_8
+    end
+  end
+end

data/lib/rexml/encodings/CP-1252.rb

@@ -0,0 +1,103 @@
+#
+# This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi
+#
+module REXML
+  module Encoding
+  	register( "CP-1252" ) do |o|
+  		class << o
+  			alias encode encode_cp1252
+			alias decode decode_cp1252
+  		end
+  	end
+
+    # Convert from UTF-8
+    def encode_cp1252(content)
+      array_utf8 = content.unpack('U*')
+      array_enc = []
+      array_utf8.each do |num|
+        case num
+          # shortcut first bunch basic characters
+        when 0..0xFF; array_enc << num
+          # characters added compared to iso-8859-1
+        when 0x20AC; array_enc << 0x80 # 0xe2 0x82 0xac
+        when 0x201A; array_enc << 0x82 # 0xe2 0x82 0x9a
+        when 0x0192; array_enc << 0x83 # 0xc6 0x92
+        when 0x201E; array_enc << 0x84 # 0xe2 0x82 0x9e
+        when 0x2026; array_enc << 0x85 # 0xe2 0x80 0xa6
+        when 0x2020; array_enc << 0x86 # 0xe2 0x80 0xa0
+        when 0x2021; array_enc << 0x87 # 0xe2 0x80 0xa1
+        when 0x02C6; array_enc << 0x88 # 0xcb 0x86
+        when 0x2030; array_enc << 0x89 # 0xe2 0x80 0xb0
+        when 0x0160; array_enc << 0x8A # 0xc5 0xa0
+        when 0x2039; array_enc << 0x8B # 0xe2 0x80 0xb9
+        when 0x0152; array_enc << 0x8C # 0xc5 0x92
+        when 0x017D; array_enc << 0x8E # 0xc5 0xbd
+        when 0x2018; array_enc << 0x91 # 0xe2 0x80 0x98
+        when 0x2019; array_enc << 0x92 # 0xe2 0x80 0x99
+        when 0x201C; array_enc << 0x93 # 0xe2 0x80 0x9c
+        when 0x201D; array_enc << 0x94 # 0xe2 0x80 0x9d
+        when 0x2022; array_enc << 0x95 # 0xe2 0x80 0xa2
+        when 0x2013; array_enc << 0x96 # 0xe2 0x80 0x93
+        when 0x2014; array_enc << 0x97 # 0xe2 0x80 0x94
+        when 0x02DC; array_enc << 0x98 # 0xcb 0x9c
+        when 0x2122; array_enc << 0x99 # 0xe2 0x84 0xa2
+        when 0x0161; array_enc << 0x9A # 0xc5 0xa1
+        when 0x203A; array_enc << 0x9B # 0xe2 0x80 0xba
+        when 0x0152; array_enc << 0x9C # 0xc5 0x93
+        when 0x017E; array_enc << 0x9E # 0xc5 0xbe
+        when 0x0178; array_enc << 0x9F # 0xc5 0xb8
+        else
+          # all remaining basic characters can be used directly
+          if num <= 0xFF
+            array_enc << num
+          else
+            # Numeric entity (&#nnnn;); shard by  Stefan Scholl
+            array_enc.concat "&\##{num};".unpack('C*')
+          end
+        end
+      end
+      array_enc.pack('C*')
+    end
+    
+    # Convert to UTF-8
+    def decode_cp1252(str)
+      array_latin9 = str.unpack('C*')
+      array_enc = []
+      array_latin9.each do |num|
+        case num
+          # characters that added compared to iso-8859-1
+        when 0x80; array_enc << 0x20AC # 0xe2 0x82 0xac
+        when 0x82; array_enc << 0x201A # 0xe2 0x82 0x9a
+        when 0x83; array_enc << 0x0192 # 0xc6 0x92
+        when 0x84; array_enc << 0x201E # 0xe2 0x82 0x9e
+        when 0x85; array_enc << 0x2026 # 0xe2 0x80 0xa6
+        when 0x86; array_enc << 0x2020 # 0xe2 0x80 0xa0
+        when 0x87; array_enc << 0x2021 # 0xe2 0x80 0xa1
+        when 0x88; array_enc << 0x02C6 # 0xcb 0x86
+        when 0x89; array_enc << 0x2030 # 0xe2 0x80 0xb0
+        when 0x8A; array_enc << 0x0160 # 0xc5 0xa0
+        when 0x8B; array_enc << 0x2039 # 0xe2 0x80 0xb9
+        when 0x8C; array_enc << 0x0152 # 0xc5 0x92
+        when 0x8E; array_enc << 0x017D # 0xc5 0xbd
+        when 0x91; array_enc << 0x2018 # 0xe2 0x80 0x98
+        when 0x92; array_enc << 0x2019 # 0xe2 0x80 0x99
+        when 0x93; array_enc << 0x201C # 0xe2 0x80 0x9c
+        when 0x94; array_enc << 0x201D # 0xe2 0x80 0x9d
+        when 0x95; array_enc << 0x2022 # 0xe2 0x80 0xa2
+        when 0x96; array_enc << 0x2013 # 0xe2 0x80 0x93
+        when 0x97; array_enc << 0x2014 # 0xe2 0x80 0x94
+        when 0x98; array_enc << 0x02DC # 0xcb 0x9c
+        when 0x99; array_enc << 0x2122 # 0xe2 0x84 0xa2
+        when 0x9A; array_enc << 0x0161 # 0xc5 0xa1
+        when 0x9B; array_enc << 0x203A # 0xe2 0x80 0xba
+        when 0x9C; array_enc << 0x0152 # 0xc5 0x93
+        when 0x9E; array_enc << 0x017E # 0xc5 0xbe
+        when 0x9F; array_enc << 0x0178 # 0xc5 0xb8
+        else
+          array_enc << num
+        end
+      end
+      array_enc.pack('U*')
+    end
+  end
+end

data/lib/rexml/encodings/EUC-JP.rb

@@ -0,0 +1,35 @@
+module REXML
+  module Encoding
+    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 decode_eucjp(str)
+        NKF.nkf(EUCTOU8, str)
+      end
+
+      def encode_eucjp content
+        NKF.nkf(U8TOEUC, content)
+      end
+    end
+
+    register("EUC-JP") do |obj|
+      class << obj
+        alias decode decode_eucjp
+        alias encode encode_eucjp
+      end
+    end
+  end
+end

data/lib/rexml/encodings/ICONV.rb

@@ -0,0 +1,22 @@
+require "iconv"
+raise LoadError unless defined? Iconv
+
+module REXML
+  module Encoding
+    def decode_iconv(str)
+      Iconv.conv(UTF_8, @encoding, str)
+    end
+
+    def encode_iconv(content)
+      Iconv.conv(@encoding, UTF_8, content)
+    end
+
+    register("ICONV") do |obj|
+      Iconv.conv(UTF_8, obj.encoding, nil)
+      class << obj
+        alias decode decode_iconv
+        alias encode encode_iconv
+      end
+    end
+  end
+end

data/lib/rexml/encodings/ISO-8859-1.rb

@@ -0,0 +1,7 @@
+require 'rexml/encodings/US-ASCII'
+
+module REXML
+  module Encoding
+    register("ISO-8859-1", &encoding_method("US-ASCII"))
+  end
+end

data/lib/rexml/encodings/ISO-8859-15.rb

@@ -0,0 +1,72 @@
+#
+# This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi
+#
+module REXML
+  module Encoding
+  	register("ISO-8859-15") do |o|
+  		alias encode to_iso_8859_15
+      alias decode from_iso_8859_15
+  	end
+
+    # Convert from UTF-8
+    def to_iso_8859_15(content)
+      array_utf8 = content.unpack('U*')
+      array_enc = []
+      array_utf8.each do |num|
+        case num
+          # shortcut first bunch basic characters
+        when 0..0xA3; array_enc << num
+          # characters removed compared to iso-8859-1
+        when 0xA4; array_enc << '&#164;'
+        when 0xA6; array_enc << '&#166;'
+        when 0xA8; array_enc << '&#168;'
+        when 0xB4; array_enc << '&#180;'
+        when 0xB8; array_enc << '&#184;'
+        when 0xBC; array_enc << '&#188;'
+        when 0xBD; array_enc << '&#189;'
+        when 0xBE; array_enc << '&#190;'
+          # characters added compared to iso-8859-1
+        when 0x20AC; array_enc << 0xA4 # 0xe2 0x82 0xac
+        when 0x0160; array_enc << 0xA6 # 0xc5 0xa0
+        when 0x0161; array_enc << 0xA8 # 0xc5 0xa1
+        when 0x017D; array_enc << 0xB4 # 0xc5 0xbd
+        when 0x017E; array_enc << 0xB8 # 0xc5 0xbe
+        when 0x0152; array_enc << 0xBC # 0xc5 0x92
+        when 0x0153; array_enc << 0xBD # 0xc5 0x93
+        when 0x0178; array_enc << 0xBE # 0xc5 0xb8
+        else
+          # all remaining basic characters can be used directly
+          if num <= 0xFF
+            array_enc << num
+          else
+            # Numeric entity (&#nnnn;); shard by  Stefan Scholl
+            array_enc.concat "&\##{num};".unpack('C*')
+          end
+        end
+      end
+      array_enc.pack('C*')
+    end
+    
+    # Convert to UTF-8
+    def from_iso_8859_15(str)
+      array_latin9 = str.unpack('C*')
+      array_enc = []
+      array_latin9.each do |num|
+        case num
+          # characters that differ compared to iso-8859-1
+        when 0xA4; array_enc << 0x20AC
+        when 0xA6; array_enc << 0x0160
+        when 0xA8; array_enc << 0x0161
+        when 0xB4; array_enc << 0x017D
+        when 0xB8; array_enc << 0x017E
+        when 0xBC; array_enc << 0x0152
+        when 0xBD; array_enc << 0x0153
+        when 0xBE; array_enc << 0x0178
+        else
+          array_enc << num
+        end
+      end
+      array_enc.pack('U*')
+    end
+  end
+end

data/lib/rexml/encodings/SHIFT-JIS.rb

@@ -0,0 +1,37 @@
+module REXML
+  module Encoding
+    begin
+      require 'uconv'
+
+      def decode_sjis content
+        Uconv::sjistou8(content)
+      end
+
+      def encode_sjis(str)
+        Uconv::u8tosjis(str)
+      end
+    rescue LoadError
+      require 'nkf'
+
+      SJISTOU8 = '-Swm0x'
+      U8TOSJIS = '-Wsm0x'
+
+      def decode_sjis(str)
+        NKF.nkf(SJISTOU8, str)
+      end
+
+      def encode_sjis content
+        NKF.nkf(U8TOSJIS, content)
+      end
+    end
+
+    b = proc do |obj|
+      class << obj
+        alias decode decode_sjis
+        alias encode encode_sjis
+      end
+    end
+    register("SHIFT-JIS", &b)
+    register("SHIFT_JIS", &b)
+  end
+end

data/lib/rexml/encodings/SHIFT_JIS.rb

@@ -0,0 +1 @@
+require 'rexml/encodings/SHIFT-JIS'

data/lib/rexml/encodings/UNILE.rb

@@ -0,0 +1,34 @@
+module REXML
+  module Encoding
+    def encode_unile content
+      array_utf8 = content.unpack("U*")
+      array_enc = []
+      array_utf8.each do |num|
+        if ((num>>16) > 0)
+          array_enc << ??
+          array_enc << 0
+        else
+          array_enc << (num & 0xFF)
+          array_enc << (num >> 8)
+        end
+      end
+      array_enc.pack('C*')
+    end
+
+    def decode_unile(str)
+      array_enc=str.unpack('C*')
+      array_utf8 = []
+      0.step(array_enc.size-1, 2){|i| 
+        array_utf8 << (array_enc.at(i) + array_enc.at(i+1)*0x100)
+      }
+      array_utf8.pack('U*')
+    end
+
+    register(UNILE) do |obj|
+      class << obj
+        alias decode decode_unile
+        alias encode encode_unile
+      end
+    end
+  end
+end

data/lib/rexml/encodings/US-ASCII.rb

@@ -0,0 +1,30 @@
+module REXML
+  module Encoding
+    # Convert from UTF-8
+    def encode_ascii content
+      array_utf8 = content.unpack('U*')
+      array_enc = []
+      array_utf8.each do |num|
+        if num <= 0x7F
+          array_enc << num
+        else
+          # Numeric entity (&#nnnn;); shard by  Stefan Scholl
+          array_enc.concat "&\##{num};".unpack('C*')
+        end
+      end
+      array_enc.pack('C*')
+    end
+
+    # Convert to UTF-8
+    def decode_ascii(str)
+      str.unpack('C*').pack('U*')
+    end
+
+    register("US-ASCII") do |obj|
+      class << obj
+        alias decode decode_ascii
+        alias encode encode_ascii
+      end
+    end
+  end
+end

data/lib/rexml/encodings/UTF-16.rb

@@ -0,0 +1,35 @@
+module REXML
+  module Encoding
+    def encode_utf16 content
+      array_utf8 = content.unpack("U*")
+      array_enc = []
+      array_utf8.each do |num|
+        if ((num>>16) > 0)
+          array_enc << 0
+          array_enc << ??
+        else
+          array_enc << (num >> 8)
+          array_enc << (num & 0xFF)
+        end
+      end
+      array_enc.pack('C*')
+    end
+
+    def decode_utf16(str)
+      str = str[2..-1] if /^\376\377/n =~ str
+      array_enc=str.unpack('C*')
+      array_utf8 = []
+      0.step(array_enc.size-1, 2){|i| 
+        array_utf8 << (array_enc.at(i+1) + array_enc.at(i)*0x100)
+      }
+      array_utf8.pack('U*')
+    end
+
+    register(UTF_16) do |obj|
+      class << obj
+        alias decode decode_utf16
+        alias encode encode_utf16
+      end
+    end
+  end
+end