| SJISTOU8 | = | '-Swm0x' | ||
| U8TOSJIS | = | '-Wsm0x' | ||
| EUCTOU8 | = | '-Ewm0' | ||
| U8TOEUC | = | '-Wem0' | ||
| 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' |
| to_iso_8859_15 | -> | encode |
| from_iso_8859_15 | -> | decode |
| encoding | [R] | ID —> Encoding name |
# File lib/rexml/encoding.rb, line 8
8: def self.apply(obj, enc)
9: @encoding_methods[enc][obj]
10: end
# File lib/rexml/encoding.rb, line 11
11: def self.encoding_method(enc)
12: @encoding_methods[enc]
13: end
# File lib/rexml/encoding.rb, line 5 5: def self.register(enc, &block) 6: @encoding_methods[enc] = block 7: end
# 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
# 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
# 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
# File lib/rexml/encodings/EUC-JP.rb, line 19
19: def decode_eucjp(str)
20: NKF.nkf(EUCTOU8, str)
21: end
# File lib/rexml/encodings/ICONV.rb, line 6 6: def decode_iconv(str) 7: Iconv.conv(UTF_8, @encoding, str) 8: end
# File lib/rexml/encodings/SHIFT-JIS.rb, line 19
19: def decode_sjis(str)
20: NKF.nkf(SJISTOU8, str)
21: end
# File lib/rexml/encodings/SHIFT-JIS.rb, line 6 6: def decode_sjis content 7: Uconv::sjistou8(content) 8: end
# 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
# 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
Convert from UTF-8
# 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
# 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
# File lib/rexml/encodings/EUC-JP.rb, line 10
10: def encode_eucjp content
11: Uconv::u8toeuc(content)
12: end
# File lib/rexml/encodings/EUC-JP.rb, line 23
23: def encode_eucjp content
24: NKF.nkf(U8TOEUC, content)
25: end
# File lib/rexml/encodings/ICONV.rb, line 10
10: def encode_iconv(content)
11: Iconv.conv(@encoding, UTF_8, content)
12: end
# File lib/rexml/encodings/SHIFT-JIS.rb, line 10
10: def encode_sjis(str)
11: Uconv::u8tosjis(str)
12: end
# File lib/rexml/encodings/SHIFT-JIS.rb, line 23
23: def encode_sjis content
24: NKF.nkf(U8TOSJIS, content)
25: end
# 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
# 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
# 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
# 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
# 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 << '¤'
21: when 0xA6; array_enc << '¦'
22: when 0xA8; array_enc << '¨'
23: when 0xB4; array_enc << '´'
24: when 0xB8; array_enc << '¸'
25: when 0xBC; array_enc << '¼'
26: when 0xBD; array_enc << '½'
27: when 0xBE; array_enc << '¾'
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