Module REXML::Encoding
In: lib/rexml/encoding.rb
lib/rexml/encodings/US-ASCII.rb
lib/rexml/encodings/ICONV.rb
lib/rexml/encodings/ISO-8859-1.rb
lib/rexml/encodings/SHIFT-JIS.rb
lib/rexml/encodings/UNILE.rb
lib/rexml/encodings/ISO-8859-15.rb
lib/rexml/encodings/UTF-16.rb
lib/rexml/encodings/CP-1252.rb
lib/rexml/encodings/EUC-JP.rb
lib/rexml/encodings/UTF-8.rb

Methods

Constants

UTF_8 = 'UTF-8'   Native, default format is UTF-8, so it is declared here rather than in an encodings/ definition.
UTF_16 = 'UTF-16'
UNILE = 'UNILE'
SJISTOU8 = '-Swm0x'
U8TOSJIS = '-Wsm0x'
EUCTOU8 = '-Ewm0'
U8TOEUC = '-Wem0'

External Aliases

to_iso_8859_15 -> encode
from_iso_8859_15 -> decode

Attributes

encoding  [R]  ID —> Encoding name

Public Class methods

[Source]

    # File lib/rexml/encoding.rb, line 8
 8:     def self.apply(obj, enc)
 9:       @encoding_methods[enc][obj]
10:     end

[Source]

    # File lib/rexml/encoding.rb, line 11
11:     def self.encoding_method(enc)
12:       @encoding_methods[enc]
13:     end

[Source]

   # File lib/rexml/encoding.rb, line 5
5:     def self.register(enc, &block)
6:       @encoding_methods[enc] = block
7:     end

Public Instance methods

[Source]

    # File lib/rexml/encoding.rb, line 57
57:     def check_encoding str
58:       # We have to recognize UTF-16, LSB UTF-16, and UTF-8
59:       if str[0] == 0xfe && str[1] == 0xff
60:         str[0,2] = ""
61:         return UTF_16
62:       elsif str[0] == 0xff && str[1] == 0xfe
63:         str[0,2] = ""
64:         return UNILE
65:       end
66:       str =~ /^\s*<\?xml\s+version\s*=\s*(['"]).*?\1\s+encoding\s*=\s*(["'])(.*?)\2/um
67:       return $3.upcase if $3
68:       return UTF_8
69:     end

Convert to UTF-8

[Source]

    # File lib/rexml/encodings/US-ASCII.rb, line 19
19:     def decode_ascii(str)
20:       str.unpack('C*').pack('U*')
21:     end

Convert to UTF-8

[Source]

     # File lib/rexml/encodings/CP-1252.rb, line 63
 63:     def decode_cp1252(str)
 64:       array_latin9 = str.unpack('C*')
 65:       array_enc = []
 66:       array_latin9.each do |num|
 67:         case num
 68:           # characters that added compared to iso-8859-1
 69:         when 0x80; array_enc << 0x20AC # 0xe2 0x82 0xac
 70:         when 0x82; array_enc << 0x201A # 0xe2 0x82 0x9a
 71:         when 0x83; array_enc << 0x0192 # 0xc6 0x92
 72:         when 0x84; array_enc << 0x201E # 0xe2 0x82 0x9e
 73:         when 0x85; array_enc << 0x2026 # 0xe2 0x80 0xa6
 74:         when 0x86; array_enc << 0x2020 # 0xe2 0x80 0xa0
 75:         when 0x87; array_enc << 0x2021 # 0xe2 0x80 0xa1
 76:         when 0x88; array_enc << 0x02C6 # 0xcb 0x86
 77:         when 0x89; array_enc << 0x2030 # 0xe2 0x80 0xb0
 78:         when 0x8A; array_enc << 0x0160 # 0xc5 0xa0
 79:         when 0x8B; array_enc << 0x2039 # 0xe2 0x80 0xb9
 80:         when 0x8C; array_enc << 0x0152 # 0xc5 0x92
 81:         when 0x8E; array_enc << 0x017D # 0xc5 0xbd
 82:         when 0x91; array_enc << 0x2018 # 0xe2 0x80 0x98
 83:         when 0x92; array_enc << 0x2019 # 0xe2 0x80 0x99
 84:         when 0x93; array_enc << 0x201C # 0xe2 0x80 0x9c
 85:         when 0x94; array_enc << 0x201D # 0xe2 0x80 0x9d
 86:         when 0x95; array_enc << 0x2022 # 0xe2 0x80 0xa2
 87:         when 0x96; array_enc << 0x2013 # 0xe2 0x80 0x93
 88:         when 0x97; array_enc << 0x2014 # 0xe2 0x80 0x94
 89:         when 0x98; array_enc << 0x02DC # 0xcb 0x9c
 90:         when 0x99; array_enc << 0x2122 # 0xe2 0x84 0xa2
 91:         when 0x9A; array_enc << 0x0161 # 0xc5 0xa1
 92:         when 0x9B; array_enc << 0x203A # 0xe2 0x80 0xba
 93:         when 0x9C; array_enc << 0x0152 # 0xc5 0x93
 94:         when 0x9E; array_enc << 0x017E # 0xc5 0xbe
 95:         when 0x9F; array_enc << 0x0178 # 0xc5 0xb8
 96:         else
 97:           array_enc << num
 98:         end
 99:       end
100:       array_enc.pack('U*')
101:     end

[Source]

    # File lib/rexml/encodings/EUC-JP.rb, line 19
19:       def decode_eucjp(str)
20:         NKF.nkf(EUCTOU8, str)
21:       end

[Source]

   # File lib/rexml/encodings/EUC-JP.rb, line 6
6:       def decode_eucjp(str)
7:         Uconv::euctou8(str)
8:       end

[Source]

   # File lib/rexml/encodings/ICONV.rb, line 6
6:     def decode_iconv(str)
7:       Iconv.conv(UTF_8, @encoding, str)
8:     end

[Source]

   # File lib/rexml/encodings/SHIFT-JIS.rb, line 6
6:       def decode_sjis content
7:         Uconv::sjistou8(content)
8:       end

[Source]

    # File lib/rexml/encodings/SHIFT-JIS.rb, line 19
19:       def decode_sjis(str)
20:         NKF.nkf(SJISTOU8, str)
21:       end

[Source]

    # File lib/rexml/encodings/UNILE.rb, line 18
18:     def decode_unile(str)
19:       array_enc=str.unpack('C*')
20:       array_utf8 = []
21:       0.step(array_enc.size-1, 2){|i| 
22:         array_utf8 << (array_enc.at(i) + array_enc.at(i+1)*0x100)
23:       }
24:       array_utf8.pack('U*')
25:     end

[Source]

    # File lib/rexml/encodings/UTF-16.rb, line 18
18:     def decode_utf16(str)
19:       str = str[2..-1] if /^\376\377/n =~ str
20:       array_enc=str.unpack('C*')
21:       array_utf8 = []
22:       0.step(array_enc.size-1, 2){|i| 
23:         array_utf8 << (array_enc.at(i+1) + array_enc.at(i)*0x100)
24:       }
25:       array_utf8.pack('U*')
26:     end

[Source]

   # File lib/rexml/encodings/UTF-8.rb, line 7
7:     def decode_utf8(str)
8:       str
9:     end

Convert from UTF-8

[Source]

    # File lib/rexml/encodings/US-ASCII.rb, line 4
 4:     def encode_ascii content
 5:       array_utf8 = content.unpack('U*')
 6:       array_enc = []
 7:       array_utf8.each do |num|
 8:         if num <= 0x7F
 9:           array_enc << num
10:         else
11:           # Numeric entity (&#nnnn;); shard by  Stefan Scholl
12:           array_enc.concat "&\##{num};".unpack('C*')
13:         end
14:       end
15:       array_enc.pack('C*')
16:     end

Convert from UTF-8

[Source]

    # File lib/rexml/encodings/CP-1252.rb, line 14
14:     def encode_cp1252(content)
15:       array_utf8 = content.unpack('U*')
16:       array_enc = []
17:       array_utf8.each do |num|
18:         case num
19:           # shortcut first bunch basic characters
20:         when 0..0xFF; array_enc << num
21:           # characters added compared to iso-8859-1
22:         when 0x20AC; array_enc << 0x80 # 0xe2 0x82 0xac
23:         when 0x201A; array_enc << 0x82 # 0xe2 0x82 0x9a
24:         when 0x0192; array_enc << 0x83 # 0xc6 0x92
25:         when 0x201E; array_enc << 0x84 # 0xe2 0x82 0x9e
26:         when 0x2026; array_enc << 0x85 # 0xe2 0x80 0xa6
27:         when 0x2020; array_enc << 0x86 # 0xe2 0x80 0xa0
28:         when 0x2021; array_enc << 0x87 # 0xe2 0x80 0xa1
29:         when 0x02C6; array_enc << 0x88 # 0xcb 0x86
30:         when 0x2030; array_enc << 0x89 # 0xe2 0x80 0xb0
31:         when 0x0160; array_enc << 0x8A # 0xc5 0xa0
32:         when 0x2039; array_enc << 0x8B # 0xe2 0x80 0xb9
33:         when 0x0152; array_enc << 0x8C # 0xc5 0x92
34:         when 0x017D; array_enc << 0x8E # 0xc5 0xbd
35:         when 0x2018; array_enc << 0x91 # 0xe2 0x80 0x98
36:         when 0x2019; array_enc << 0x92 # 0xe2 0x80 0x99
37:         when 0x201C; array_enc << 0x93 # 0xe2 0x80 0x9c
38:         when 0x201D; array_enc << 0x94 # 0xe2 0x80 0x9d
39:         when 0x2022; array_enc << 0x95 # 0xe2 0x80 0xa2
40:         when 0x2013; array_enc << 0x96 # 0xe2 0x80 0x93
41:         when 0x2014; array_enc << 0x97 # 0xe2 0x80 0x94
42:         when 0x02DC; array_enc << 0x98 # 0xcb 0x9c
43:         when 0x2122; array_enc << 0x99 # 0xe2 0x84 0xa2
44:         when 0x0161; array_enc << 0x9A # 0xc5 0xa1
45:         when 0x203A; array_enc << 0x9B # 0xe2 0x80 0xba
46:         when 0x0152; array_enc << 0x9C # 0xc5 0x93
47:         when 0x017E; array_enc << 0x9E # 0xc5 0xbe
48:         when 0x0178; array_enc << 0x9F # 0xc5 0xb8
49:         else
50:           # all remaining basic characters can be used directly
51:           if num <= 0xFF
52:             array_enc << num
53:           else
54:             # Numeric entity (&#nnnn;); shard by  Stefan Scholl
55:             array_enc.concat "&\##{num};".unpack('C*')
56:           end
57:         end
58:       end
59:       array_enc.pack('C*')
60:     end

[Source]

    # File lib/rexml/encodings/EUC-JP.rb, line 23
23:       def encode_eucjp content
24:         NKF.nkf(U8TOEUC, content)
25:       end

[Source]

    # File lib/rexml/encodings/EUC-JP.rb, line 10
10:       def encode_eucjp content
11:         Uconv::u8toeuc(content)
12:       end

[Source]

    # File lib/rexml/encodings/ICONV.rb, line 10
10:     def encode_iconv(content)
11:       Iconv.conv(@encoding, UTF_8, content)
12:     end

[Source]

    # File lib/rexml/encodings/SHIFT-JIS.rb, line 23
23:       def encode_sjis content
24:         NKF.nkf(U8TOSJIS, content)
25:       end

[Source]

    # File lib/rexml/encodings/SHIFT-JIS.rb, line 10
10:       def encode_sjis(str)
11:         Uconv::u8tosjis(str)
12:       end

[Source]

    # File lib/rexml/encodings/UNILE.rb, line 3
 3:     def encode_unile content
 4:       array_utf8 = content.unpack("U*")
 5:       array_enc = []
 6:       array_utf8.each do |num|
 7:         if ((num>>16) > 0)
 8:           array_enc << ??
 9:           array_enc << 0
10:         else
11:           array_enc << (num & 0xFF)
12:           array_enc << (num >> 8)
13:         end
14:       end
15:       array_enc.pack('C*')
16:     end

[Source]

    # File lib/rexml/encodings/UTF-16.rb, line 3
 3:     def encode_utf16 content
 4:       array_utf8 = content.unpack("U*")
 5:       array_enc = []
 6:       array_utf8.each do |num|
 7:         if ((num>>16) > 0)
 8:           array_enc << 0
 9:           array_enc << ??
10:         else
11:           array_enc << (num >> 8)
12:           array_enc << (num & 0xFF)
13:         end
14:       end
15:       array_enc.pack('C*')
16:     end

[Source]

   # File lib/rexml/encodings/UTF-8.rb, line 3
3:     def encode_utf8 content
4:       content
5:     end

[Source]

    # File lib/rexml/encoding.rb, line 23
23:     def encoding=( enc )
24:       old_verbosity = $VERBOSE
25:       begin
26:         $VERBOSE = false
27:         enc = enc.nil? ? nil : enc.upcase
28:         return false if defined? @encoding and enc == @encoding
29:         if enc and enc != UTF_8
30:           @encoding = enc
31:           raise ArgumentError, "Bad encoding name #@encoding" unless @encoding =~ /^[\w-]+$/
32:           @encoding.untaint 
33:           begin
34:             require 'rexml/encodings/ICONV.rb'
35:             Encoding.apply(self, "ICONV")
36:           rescue LoadError, Exception
37:             begin
38:               enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
39:               require enc_file
40:               Encoding.apply(self, @encoding)
41:             rescue LoadError => err
42:               puts err.message
43:               raise ArgumentError, "No decoder found for encoding #@encoding.  Please install iconv."
44:             end
45:           end
46:         else
47:           @encoding = UTF_8
48:           require 'rexml/encodings/UTF-8.rb'
49:           Encoding.apply(self, @encoding)
50:         end
51:       ensure
52:         $VERBOSE = old_verbosity
53:       end
54:       true
55:     end

Convert to UTF-8

[Source]

    # File lib/rexml/encodings/ISO-8859-15.rb, line 51
51:     def from_iso_8859_15(str)
52:       array_latin9 = str.unpack('C*')
53:       array_enc = []
54:       array_latin9.each do |num|
55:         case num
56:           # characters that differ compared to iso-8859-1
57:         when 0xA4; array_enc << 0x20AC
58:         when 0xA6; array_enc << 0x0160
59:         when 0xA8; array_enc << 0x0161
60:         when 0xB4; array_enc << 0x017D
61:         when 0xB8; array_enc << 0x017E
62:         when 0xBC; array_enc << 0x0152
63:         when 0xBD; array_enc << 0x0153
64:         when 0xBE; array_enc << 0x0178
65:         else
66:           array_enc << num
67:         end
68:       end
69:       array_enc.pack('U*')
70:     end

Convert from UTF-8

[Source]

    # File lib/rexml/encodings/ISO-8859-15.rb, line 12
12:     def to_iso_8859_15(content)
13:       array_utf8 = content.unpack('U*')
14:       array_enc = []
15:       array_utf8.each do |num|
16:         case num
17:           # shortcut first bunch basic characters
18:         when 0..0xA3; array_enc << num
19:           # characters removed compared to iso-8859-1
20:         when 0xA4; array_enc << '&#164;'
21:         when 0xA6; array_enc << '&#166;'
22:         when 0xA8; array_enc << '&#168;'
23:         when 0xB4; array_enc << '&#180;'
24:         when 0xB8; array_enc << '&#184;'
25:         when 0xBC; array_enc << '&#188;'
26:         when 0xBD; array_enc << '&#189;'
27:         when 0xBE; array_enc << '&#190;'
28:           # characters added compared to iso-8859-1
29:         when 0x20AC; array_enc << 0xA4 # 0xe2 0x82 0xac
30:         when 0x0160; array_enc << 0xA6 # 0xc5 0xa0
31:         when 0x0161; array_enc << 0xA8 # 0xc5 0xa1
32:         when 0x017D; array_enc << 0xB4 # 0xc5 0xbd
33:         when 0x017E; array_enc << 0xB8 # 0xc5 0xbe
34:         when 0x0152; array_enc << 0xBC # 0xc5 0x92
35:         when 0x0153; array_enc << 0xBD # 0xc5 0x93
36:         when 0x0178; array_enc << 0xBE # 0xc5 0xb8
37:         else
38:           # all remaining basic characters can be used directly
39:           if num <= 0xFF
40:             array_enc << num
41:           else
42:             # Numeric entity (&#nnnn;); shard by  Stefan Scholl
43:             array_enc.concat "&\##{num};".unpack('C*')
44:           end
45:         end
46:       end
47:       array_enc.pack('C*')
48:     end

[Validate]