string_decoder.js
8.1 KB
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
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
'use strict';
var Buffer = require('safe-buffer').Buffer;
var isEncoding = Buffer.isEncoding || function (encoding) {
encoding = '' + encoding;
switch (encoding && encoding.toLowerCase()) {
case 'hex':case 'utf8':case 'utf-8':case 'ascii':case 'binary':case 'base64':case 'ucs2':case 'ucs-2':case 'utf16le':case 'utf-16le':case 'raw':
return true;
default:
return false;
}
};
function _normalizeEncoding(enc) {
if (!enc) return 'utf8';
var retried;
while (true) {
switch (enc) {
case 'utf8':
case 'utf-8':
return 'utf8';
case 'ucs2':
case 'ucs-2':
case 'utf16le':
case 'utf-16le':
return 'utf16le';
case 'latin1':
case 'binary':
return 'latin1';
case 'base64':
case 'ascii':
case 'hex':
return enc;
default:
if (retried) return; // undefined
enc = ('' + enc).toLowerCase();
retried = true;
}
}
};
// Do not cache `Buffer.isEncoding` when checking encoding names as some
// modules monkey-patch it to support additional encodings
function normalizeEncoding(enc) {
var nenc = _normalizeEncoding(enc);
if (typeof nenc !== 'string' && (Buffer.isEncoding === isEncoding || !isEncoding(enc))) throw new Error('Unknown encoding: ' + enc);
return nenc || enc;
}
// StringDecoder provides an interface for efficiently splitting a series of
// buffers into a series of JS strings without breaking apart multi-byte
// characters.
exports.StringDecoder = StringDecoder;
function StringDecoder(encoding) {
this.encoding = normalizeEncoding(encoding);
var nb;
switch (this.encoding) {
case 'utf16le':
this.text = utf16Text;
this.end = utf16End;
nb = 4;
break;
case 'utf8':
this.fillLast = utf8FillLast;
nb = 4;
break;
case 'base64':
this.text = base64Text;
this.end = base64End;
nb = 3;
break;
default:
this.write = simpleWrite;
this.end = simpleEnd;
return;
}
this.lastNeed = 0;
this.lastTotal = 0;
this.lastChar = Buffer.allocUnsafe(nb);
}
StringDecoder.prototype.write = function (buf) {
if (buf.length === 0) return '';
var r;
var i;
if (this.lastNeed) {
r = this.fillLast(buf);
if (r === undefined) return '';
i = this.lastNeed;
this.lastNeed = 0;
} else {
i = 0;
}
if (i < buf.length) return r ? r + this.text(buf, i) : this.text(buf, i);
return r || '';
};
StringDecoder.prototype.end = utf8End;
// Returns only complete characters in a Buffer
StringDecoder.prototype.text = utf8Text;
// Attempts to complete a partial non-UTF-8 character using bytes from a Buffer
StringDecoder.prototype.fillLast = function (buf) {
if (this.lastNeed <= buf.length) {
buf.copy(this.lastChar, this.lastTotal - this.lastNeed, 0, this.lastNeed);
return this.lastChar.toString(this.encoding, 0, this.lastTotal);
}
buf.copy(this.lastChar, this.lastTotal - this.lastNeed, 0, buf.length);
this.lastNeed -= buf.length;
};
// Checks the type of a UTF-8 byte, whether it's ASCII, a leading byte, or a
// continuation byte.
function utf8CheckByte(byte) {
if (byte <= 0x7F) return 0;else if (byte >> 5 === 0x06) return 2;else if (byte >> 4 === 0x0E) return 3;else if (byte >> 3 === 0x1E) return 4;
return -1;
}
// Checks at most 3 bytes at the end of a Buffer in order to detect an
// incomplete multi-byte UTF-8 character. The total number of bytes (2, 3, or 4)
// needed to complete the UTF-8 character (if applicable) are returned.
function utf8CheckIncomplete(self, buf, i) {
var j = buf.length - 1;
if (j < i) return 0;
var nb = utf8CheckByte(buf[j]);
if (nb >= 0) {
if (nb > 0) self.lastNeed = nb - 1;
return nb;
}
if (--j < i) return 0;
nb = utf8CheckByte(buf[j]);
if (nb >= 0) {
if (nb > 0) self.lastNeed = nb - 2;
return nb;
}
if (--j < i) return 0;
nb = utf8CheckByte(buf[j]);
if (nb >= 0) {
if (nb > 0) {
if (nb === 2) nb = 0;else self.lastNeed = nb - 3;
}
return nb;
}
return 0;
}
// Validates as many continuation bytes for a multi-byte UTF-8 character as
// needed or are available. If we see a non-continuation byte where we expect
// one, we "replace" the validated continuation bytes we've seen so far with
// UTF-8 replacement characters ('\ufffd'), to match v8's UTF-8 decoding
// behavior. The continuation byte check is included three times in the case
// where all of the continuation bytes for a character exist in the same buffer.
// It is also done this way as a slight performance increase instead of using a
// loop.
function utf8CheckExtraBytes(self, buf, p) {
if ((buf[0] & 0xC0) !== 0x80) {
self.lastNeed = 0;
return '\ufffd'.repeat(p);
}
if (self.lastNeed > 1 && buf.length > 1) {
if ((buf[1] & 0xC0) !== 0x80) {
self.lastNeed = 1;
return '\ufffd'.repeat(p + 1);
}
if (self.lastNeed > 2 && buf.length > 2) {
if ((buf[2] & 0xC0) !== 0x80) {
self.lastNeed = 2;
return '\ufffd'.repeat(p + 2);
}
}
}
}
// Attempts to complete a multi-byte UTF-8 character using bytes from a Buffer.
function utf8FillLast(buf) {
var p = this.lastTotal - this.lastNeed;
var r = utf8CheckExtraBytes(this, buf, p);
if (r !== undefined) return r;
if (this.lastNeed <= buf.length) {
buf.copy(this.lastChar, p, 0, this.lastNeed);
return this.lastChar.toString(this.encoding, 0, this.lastTotal);
}
buf.copy(this.lastChar, p, 0, buf.length);
this.lastNeed -= buf.length;
}
// Returns all complete UTF-8 characters in a Buffer. If the Buffer ended on a
// partial character, the character's bytes are buffered until the required
// number of bytes are available.
function utf8Text(buf, i) {
var total = utf8CheckIncomplete(this, buf, i);
if (!this.lastNeed) return buf.toString('utf8', i);
this.lastTotal = total;
var end = buf.length - (total - this.lastNeed);
buf.copy(this.lastChar, 0, end);
return buf.toString('utf8', i, end);
}
// For UTF-8, a replacement character for each buffered byte of a (partial)
// character needs to be added to the output.
function utf8End(buf) {
var r = buf && buf.length ? this.write(buf) : '';
if (this.lastNeed) return r + '\ufffd'.repeat(this.lastTotal - this.lastNeed);
return r;
}
// UTF-16LE typically needs two bytes per character, but even if we have an even
// number of bytes available, we need to check if we end on a leading/high
// surrogate. In that case, we need to wait for the next two bytes in order to
// decode the last character properly.
function utf16Text(buf, i) {
if ((buf.length - i) % 2 === 0) {
var r = buf.toString('utf16le', i);
if (r) {
var c = r.charCodeAt(r.length - 1);
if (c >= 0xD800 && c <= 0xDBFF) {
this.lastNeed = 2;
this.lastTotal = 4;
this.lastChar[0] = buf[buf.length - 2];
this.lastChar[1] = buf[buf.length - 1];
return r.slice(0, -1);
}
}
return r;
}
this.lastNeed = 1;
this.lastTotal = 2;
this.lastChar[0] = buf[buf.length - 1];
return buf.toString('utf16le', i, buf.length - 1);
}
// For UTF-16LE we do not explicitly append special replacement characters if we
// end on a partial character, we simply let v8 handle that.
function utf16End(buf) {
var r = buf && buf.length ? this.write(buf) : '';
if (this.lastNeed) {
var end = this.lastTotal - this.lastNeed;
return r + this.lastChar.toString('utf16le', 0, end);
}
return r;
}
function base64Text(buf, i) {
var n = (buf.length - i) % 3;
if (n === 0) return buf.toString('base64', i);
this.lastNeed = 3 - n;
this.lastTotal = 3;
if (n === 1) {
this.lastChar[0] = buf[buf.length - 1];
} else {
this.lastChar[0] = buf[buf.length - 2];
this.lastChar[1] = buf[buf.length - 1];
}
return buf.toString('base64', i, buf.length - n);
}
function base64End(buf) {
var r = buf && buf.length ? this.write(buf) : '';
if (this.lastNeed) return r + this.lastChar.toString('base64', 0, 3 - this.lastNeed);
return r;
}
// Pass bytes on through for single-byte encodings (e.g. ascii, latin1, hex)
function simpleWrite(buf) {
return buf.toString(this.encoding);
}
function simpleEnd(buf) {
return buf && buf.length ? this.write(buf) : '';
}