1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
|
// == UTF16-BE codec. ==========================================================
exports.utf16be = function(options) {
return {
encoder: utf16beEncoder,
decoder: utf16beDecoder,
bom: new Buffer([0xFE, 0xFF]),
};
};
// -- Encoding
function utf16beEncoder(options) {
return {
write: utf16beEncoderWrite,
end: function() {},
}
}
function utf16beEncoderWrite(str) {
var buf = new Buffer(str, 'ucs2');
for (var i = 0; i < buf.length; i += 2) {
var tmp = buf[i]; buf[i] = buf[i+1]; buf[i+1] = tmp;
}
return buf;
}
// -- Decoding
function utf16beDecoder(options) {
return {
write: utf16beDecoderWrite,
end: function() {},
overflowByte: -1,
};
}
function utf16beDecoderWrite(buf) {
if (buf.length == 0)
return '';
var buf2 = new Buffer(buf.length + 1),
i = 0, j = 0;
if (this.overflowByte !== -1) {
buf2[0] = buf[0];
buf2[1] = this.overflowByte;
i = 1; j = 2;
}
for (; i < buf.length-1; i += 2, j+= 2) {
buf2[j] = buf[i+1];
buf2[j+1] = buf[i];
}
this.overflowByte = (i == buf.length-1) ? buf[buf.length-1] : -1;
return buf2.slice(0, j).toString('ucs2');
}
// == UTF-16 codec =============================================================
// Decoder chooses automatically from UTF-16LE and UTF-16BE using BOM and space-based heuristic.
// Defaults to UTF-16BE, according to RFC 2781, although it is against some industry practices, see
// http://en.wikipedia.org/wiki/UTF-16 and http://encoding.spec.whatwg.org/#utf-16le
// Decoder default can be changed: iconv.decode(buf, 'utf16', {default: 'utf-16le'});
// Encoder prepends BOM and uses UTF-16BE.
// Endianness can also be changed: iconv.encode(str, 'utf16', {use: 'utf-16le'});
exports.utf16 = function(options) {
return {
encoder: utf16Encoder,
decoder: utf16Decoder,
getCodec: options.iconv.getCodec,
};
};
// -- Encoding
function utf16Encoder(options) {
options = options || {};
var codec = this.getCodec(options.use || 'utf-16be');
if (!codec.bom)
throw new Error("iconv-lite: in UTF-16 encoder, 'use' parameter should be either UTF-16BE or UTF16-LE.");
return {
write: utf16EncoderWrite,
end: utf16EncoderEnd,
bom: codec.bom,
internalEncoder: codec.encoder(options),
};
}
function utf16EncoderWrite(str) {
var buf = this.internalEncoder.write(str);
if (this.bom) {
buf = Buffer.concat([this.bom, buf]);
this.bom = null;
}
return buf;
}
function utf16EncoderEnd() {
return this.internalEncoder.end();
}
// -- Decoding
function utf16Decoder(options) {
return {
write: utf16DecoderWrite,
end: utf16DecoderEnd,
internalDecoder: null,
initialBytes: [],
initialBytesLen: 0,
options: options || {},
getCodec: this.getCodec,
};
}
function utf16DecoderWrite(buf) {
if (this.internalDecoder)
return this.internalDecoder.write(buf);
// Codec is not chosen yet. Accumulate initial bytes.
this.initialBytes.push(buf);
this.initialBytesLen += buf.length;
if (this.initialBytesLen < 16) // We need > 2 bytes to use space heuristic (see below)
return '';
// We have enough bytes -> decide endianness.
return utf16DecoderDecideEndianness.call(this);
}
function utf16DecoderEnd() {
if (this.internalDecoder)
return this.internalDecoder.end();
var res = utf16DecoderDecideEndianness.call(this);
var trail;
if (this.internalDecoder)
trail = this.internalDecoder.end();
return (trail && trail.length > 0) ? (res + trail) : res;
}
function utf16DecoderDecideEndianness() {
var buf = Buffer.concat(this.initialBytes);
this.initialBytes.length = this.initialBytesLen = 0;
if (buf.length < 2)
return ''; // Not a valid UTF-16 sequence anyway.
// Default encoding.
var enc = this.options.default || 'utf-16be';
// Check BOM.
if (buf[0] == 0xFE && buf[1] == 0xFF) { // UTF-16BE BOM
enc = 'utf-16be'; buf = buf.slice(2);
}
else if (buf[0] == 0xFF && buf[1] == 0xFE) { // UTF-16LE BOM
enc = 'utf-16le'; buf = buf.slice(2);
}
else {
// No BOM found. Try to deduce encoding from initial content.
// Most of the time, the content has spaces (U+0020), but the opposite (U+2000) is very uncommon.
// So, we count spaces as if it was LE or BE, and decide from that.
var spaces = [0, 0], // Counts of space chars in both positions
_len = Math.min(buf.length - (buf.length % 2), 64); // Len is always even.
for (var i = 0; i < _len; i += 2) {
if (buf[i] == 0x00 && buf[i+1] == 0x20) spaces[0]++;
if (buf[i] == 0x20 && buf[i+1] == 0x00) spaces[1]++;
}
if (spaces[0] > 0 && spaces[1] == 0)
enc = 'utf-16be';
else if (spaces[0] == 0 && spaces[1] > 0)
enc = 'utf-16le';
}
this.internalDecoder = this.getCodec(enc).decoder(this.options);
return this.internalDecoder.write(buf);
}
|
