diff options
Diffstat (limited to 'lib/xsd/charset.rb')
-rw-r--r-- | lib/xsd/charset.rb | 76 |
1 files changed, 46 insertions, 30 deletions
diff --git a/lib/xsd/charset.rb b/lib/xsd/charset.rb index ccd22a7744..15d5500fce 100644 --- a/lib/xsd/charset.rb +++ b/lib/xsd/charset.rb @@ -1,5 +1,5 @@ # XSD4R - Charset handling library. -# Copyright (C) 2001, 2003 NAKAMURA, Hiroshi <nahi@ruby-lang.org>. +# Copyright (C) 2001, 2003, 2005 NAKAMURA, Hiroshi <nahi@ruby-lang.org>. # This program is copyrighted free software by NAKAMURA, Hiroshi. You can # redistribute it and/or modify it under the same terms of Ruby's license; @@ -10,7 +10,7 @@ module XSD module Charset - @encoding = $KCODE + @internal_encoding = $KCODE class XSDError < StandardError; end class CharsetError < XSDError; end @@ -24,27 +24,40 @@ public # EncodingConvertMap = {} 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' - @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) } + @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) } + 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' - @encoding = 'UTF8' + @internal_encoding = 'UTF8' EncodingConvertMap[['UTF8', 'EUC' ]] = Uconv.method(:u8toeuc) EncodingConvertMap[['UTF8', 'SJIS']] = Uconv.method(:u8tosjis) EncodingConvertMap[['EUC' , 'UTF8']] = Uconv.method(:euctou8) @@ -60,6 +73,8 @@ public 'EUC' => 'euc-jp', 'SJIS' => 'shift_jis', 'UTF8' => 'utf-8', + 'X_ISO_8859_1' => 'iso-8859-1', + 'X_UNKNOWN' => nil, } @@ -67,24 +82,24 @@ public ## handlers # def Charset.encoding - @encoding + @internal_encoding end def Charset.encoding=(encoding) warn("xsd charset is set to #{encoding}") if $DEBUG - @encoding = encoding + @internal_encoding = encoding end - def Charset.encoding_label - charset_label(@encoding) + def Charset.xml_encoding_label + charset_label(@internal_encoding) end def Charset.encoding_to_xml(str, charset) - encoding_conv(str, @encoding, charset_str(charset)) + encoding_conv(str, @internal_encoding, charset_str(charset)) end def Charset.encoding_from_xml(str, charset) - encoding_conv(str, charset_str(charset), @encoding) + encoding_conv(str, charset_str(charset), @internal_encoding) end def Charset.encoding_conv(str, enc_from, enc_to) @@ -94,7 +109,7 @@ public converter.call(str) else raise CharsetConversionError.new( - "Converter not found: #{ enc_from } -> #{ enc_to }") + "Converter not found: #{enc_from} -> #{enc_to}") end end @@ -104,26 +119,26 @@ public def Charset.charset_str(label) if CharsetMap.respond_to?(:key) - CharsetMap.key(label.downcase) + CharsetMap.key(label.downcase) || 'X_UNKNOWN' else - CharsetMap.index(label.downcase) + CharsetMap.index(label.downcase) || 'X_UNKNOWN' end end # us_ascii = '[\x00-\x7F]' us_ascii = '[\x9\xa\xd\x20-\x7F]' # XML 1.0 restricted. - USASCIIRegexp = Regexp.new("\\A#{ us_ascii }*\\z", nil, "NONE") + USASCIIRegexp = Regexp.new("\\A#{us_ascii}*\\z", nil, "NONE") twobytes_euc = '(?:[\x8E\xA1-\xFE][\xA1-\xFE])' threebytes_euc = '(?:\x8F[\xA1-\xFE][\xA1-\xFE])' - character_euc = "(?:#{ us_ascii }|#{ twobytes_euc }|#{ threebytes_euc })" - EUCRegexp = Regexp.new("\\A#{ character_euc }*\\z", nil, "NONE") + character_euc = "(?:#{us_ascii}|#{twobytes_euc}|#{threebytes_euc})" + EUCRegexp = Regexp.new("\\A#{character_euc}*\\z", nil, "NONE") # onebyte_sjis = '[\x00-\x7F\xA1-\xDF]' onebyte_sjis = '[\x9\xa\xd\x20-\x7F\xA1-\xDF]' # XML 1.0 restricted. twobytes_sjis = '(?:[\x81-\x9F\xE0-\xFC][\x40-\x7E\x80-\xFC])' - character_sjis = "(?:#{ onebyte_sjis }|#{ twobytes_sjis })" - SJISRegexp = Regexp.new("\\A#{ character_sjis }*\\z", nil, "NONE") + character_sjis = "(?:#{onebyte_sjis}|#{twobytes_sjis})" + SJISRegexp = Regexp.new("\\A#{character_sjis}*\\z", nil, "NONE") # 0xxxxxxx # 110yyyyy 10xxxxxx @@ -132,8 +147,9 @@ public threebytes_utf8 = '(?:[\xE0-\xEF][\x80-\xBF][\x80-\xBF])' # 11110uuu 10uuuzzz 10yyyyyy 10xxxxxx fourbytes_utf8 = '(?:[\xF0-\xF7][\x80-\xBF][\x80-\xBF][\x80-\xBF])' - character_utf8 = "(?:#{ us_ascii }|#{ twobytes_utf8 }|#{ threebytes_utf8 }|#{ fourbytes_utf8 })" - UTF8Regexp = Regexp.new("\\A#{ character_utf8 }*\\z", nil, "NONE") + character_utf8 = + "(?:#{us_ascii}|#{twobytes_utf8}|#{threebytes_utf8}|#{fourbytes_utf8})" + UTF8Regexp = Regexp.new("\\A#{character_utf8}*\\z", nil, "NONE") def Charset.is_us_ascii(str) USASCIIRegexp =~ str @@ -162,7 +178,7 @@ public when 'SJIS' is_sjis(str) else - raise UnknownCharsetError.new("Unknown charset: #{ code }") + raise UnknownCharsetError.new("Unknown charset: #{code}") end end end |