# File xsd/charset.rb, line 116 def Charset.charset_label(encoding) CharsetMap[encoding.upcase] end
# File xsd/charset.rb, line 120 def Charset.charset_str(label) if CharsetMap.respond_to?(:key) CharsetMap.key(label.downcase) || 'X_UNKNOWN' else CharsetMap.index(label.downcase) || 'X_UNKNOWN' end end
handlers
# File xsd/charset.rb, line 84 def Charset.encoding @internal_encoding end
# File xsd/charset.rb, line 88 def Charset.encoding=(encoding) warn("xsd charset is set to #{encoding}") if $DEBUG @internal_encoding = encoding end
# File xsd/charset.rb, line 105 def Charset.encoding_conv(str, enc_from, enc_to) if enc_from == enc_to or enc_from == 'NONE' or enc_to == 'NONE' str elsif converter = EncodingConvertMap[[enc_from, enc_to]] converter.call(str) else raise CharsetConversionError.new( "Converter not found: #{enc_from} -> #{enc_to}") end end
# File xsd/charset.rb, line 101 def Charset.encoding_from_xml(str, charset) encoding_conv(str, charset_str(charset), @internal_encoding) end
# File xsd/charset.rb, line 97 def Charset.encoding_to_xml(str, charset) encoding_conv(str, @internal_encoding, charset_str(charset)) end
# File xsd/charset.rb, line 26 def Charset.init EncodingConvertMap[['UTF8', 'X_ISO8859_1']] = Proc.new { |str| str.unpack('U*').pack('C*') } EncodingConvertMap[['X_ISO8859_1', 'UTF8']] = Proc.new { |str| str.unpack('C*').pack('U*') } begin require 'xsd/iconvcharset' @internal_encoding = 'UTF8' sjtag = (/(mswin|bccwin|mingw|cygwin|emx)/ =~ RUBY_PLATFORM) ? 'cp932' : 'shift_jis' EncodingConvertMap[['UTF8', 'EUC' ]] = Proc.new { |str| IconvCharset.safe_iconv("euc-jp", "utf-8", str) } EncodingConvertMap[['EUC' , 'UTF8']] = Proc.new { |str| IconvCharset.safe_iconv("utf-8", "euc-jp", str) } EncodingConvertMap[['EUC' , 'SJIS']] = Proc.new { |str| IconvCharset.safe_iconv(sjtag, "euc-jp", str) } EncodingConvertMap[['UTF8', 'SJIS']] = Proc.new { |str| IconvCharset.safe_iconv(sjtag, "utf-8", str) } EncodingConvertMap[['SJIS', 'UTF8']] = Proc.new { |str| IconvCharset.safe_iconv("utf-8", sjtag, str) } EncodingConvertMap[['SJIS', 'EUC' ]] = Proc.new { |str| IconvCharset.safe_iconv("euc-jp", sjtag, str) } rescue LoadError begin require 'nkf' EncodingConvertMap[['EUC' , 'SJIS']] = Proc.new { |str| NKF.nkf('-sXm0', str) } EncodingConvertMap[['SJIS', 'EUC' ]] = Proc.new { |str| NKF.nkf('-eXm0', str) } rescue LoadError end begin require 'uconv' @internal_encoding = 'UTF8' EncodingConvertMap[['UTF8', 'EUC' ]] = Uconv.method(:u8toeuc) EncodingConvertMap[['UTF8', 'SJIS']] = Uconv.method(:u8tosjis) EncodingConvertMap[['EUC' , 'UTF8']] = Uconv.method(:euctou8) EncodingConvertMap[['SJIS', 'UTF8']] = Uconv.method(:sjistou8) rescue LoadError end end end
# File xsd/charset.rb, line 170 def Charset.is_ces(str, code = $KCODE) case code when 'NONE' is_us_ascii(str) when 'UTF8' is_utf8(str) when 'EUC' is_euc(str) when 'SJIS' is_sjis(str) else raise UnknownCharsetError.new("Unknown charset: #{code}") end end
# File xsd/charset.rb, line 162 def Charset.is_euc(str) EUCRegexp =~ str end
# File xsd/charset.rb, line 166 def Charset.is_sjis(str) SJISRegexp =~ str end
# File xsd/charset.rb, line 154 def Charset.is_us_ascii(str) USASCIIRegexp =~ str end