utf8.js
5.23 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
/*! https://mths.be/utf8js v2.1.2 by @mathias */
var stringFromCharCode = String.fromCharCode;
// Taken from https://mths.be/punycode
function ucs2decode(string) {
var output = [];
var counter = 0;
var length = string.length;
var value;
var extra;
while (counter < length) {
value = string.charCodeAt(counter++);
if (value >= 0xD800 && value <= 0xDBFF && counter < length) {
// high surrogate, and there is a next character
extra = string.charCodeAt(counter++);
if ((extra & 0xFC00) == 0xDC00) { // low surrogate
output.push(((value & 0x3FF) << 10) + (extra & 0x3FF) + 0x10000);
} else {
// unmatched surrogate; only append this code unit, in case the next
// code unit is the high surrogate of a surrogate pair
output.push(value);
counter--;
}
} else {
output.push(value);
}
}
return output;
}
// Taken from https://mths.be/punycode
function ucs2encode(array) {
var length = array.length;
var index = -1;
var value;
var output = '';
while (++index < length) {
value = array[index];
if (value > 0xFFFF) {
value -= 0x10000;
output += stringFromCharCode(value >>> 10 & 0x3FF | 0xD800);
value = 0xDC00 | value & 0x3FF;
}
output += stringFromCharCode(value);
}
return output;
}
function checkScalarValue(codePoint, strict) {
if (codePoint >= 0xD800 && codePoint <= 0xDFFF) {
if (strict) {
throw Error(
'Lone surrogate U+' + codePoint.toString(16).toUpperCase() +
' is not a scalar value'
);
}
return false;
}
return true;
}
/*--------------------------------------------------------------------------*/
function createByte(codePoint, shift) {
return stringFromCharCode(((codePoint >> shift) & 0x3F) | 0x80);
}
function encodeCodePoint(codePoint, strict) {
if ((codePoint & 0xFFFFFF80) == 0) { // 1-byte sequence
return stringFromCharCode(codePoint);
}
var symbol = '';
if ((codePoint & 0xFFFFF800) == 0) { // 2-byte sequence
symbol = stringFromCharCode(((codePoint >> 6) & 0x1F) | 0xC0);
}
else if ((codePoint & 0xFFFF0000) == 0) { // 3-byte sequence
if (!checkScalarValue(codePoint, strict)) {
codePoint = 0xFFFD;
}
symbol = stringFromCharCode(((codePoint >> 12) & 0x0F) | 0xE0);
symbol += createByte(codePoint, 6);
}
else if ((codePoint & 0xFFE00000) == 0) { // 4-byte sequence
symbol = stringFromCharCode(((codePoint >> 18) & 0x07) | 0xF0);
symbol += createByte(codePoint, 12);
symbol += createByte(codePoint, 6);
}
symbol += stringFromCharCode((codePoint & 0x3F) | 0x80);
return symbol;
}
function utf8encode(string, opts) {
opts = opts || {};
var strict = false !== opts.strict;
var codePoints = ucs2decode(string);
var length = codePoints.length;
var index = -1;
var codePoint;
var byteString = '';
while (++index < length) {
codePoint = codePoints[index];
byteString += encodeCodePoint(codePoint, strict);
}
return byteString;
}
/*--------------------------------------------------------------------------*/
function readContinuationByte() {
if (byteIndex >= byteCount) {
throw Error('Invalid byte index');
}
var continuationByte = byteArray[byteIndex] & 0xFF;
byteIndex++;
if ((continuationByte & 0xC0) == 0x80) {
return continuationByte & 0x3F;
}
// If we end up here, it’s not a continuation byte
throw Error('Invalid continuation byte');
}
function decodeSymbol(strict) {
var byte1;
var byte2;
var byte3;
var byte4;
var codePoint;
if (byteIndex > byteCount) {
throw Error('Invalid byte index');
}
if (byteIndex == byteCount) {
return false;
}
// Read first byte
byte1 = byteArray[byteIndex] & 0xFF;
byteIndex++;
// 1-byte sequence (no continuation bytes)
if ((byte1 & 0x80) == 0) {
return byte1;
}
// 2-byte sequence
if ((byte1 & 0xE0) == 0xC0) {
byte2 = readContinuationByte();
codePoint = ((byte1 & 0x1F) << 6) | byte2;
if (codePoint >= 0x80) {
return codePoint;
} else {
throw Error('Invalid continuation byte');
}
}
// 3-byte sequence (may include unpaired surrogates)
if ((byte1 & 0xF0) == 0xE0) {
byte2 = readContinuationByte();
byte3 = readContinuationByte();
codePoint = ((byte1 & 0x0F) << 12) | (byte2 << 6) | byte3;
if (codePoint >= 0x0800) {
return checkScalarValue(codePoint, strict) ? codePoint : 0xFFFD;
} else {
throw Error('Invalid continuation byte');
}
}
// 4-byte sequence
if ((byte1 & 0xF8) == 0xF0) {
byte2 = readContinuationByte();
byte3 = readContinuationByte();
byte4 = readContinuationByte();
codePoint = ((byte1 & 0x07) << 0x12) | (byte2 << 0x0C) |
(byte3 << 0x06) | byte4;
if (codePoint >= 0x010000 && codePoint <= 0x10FFFF) {
return codePoint;
}
}
throw Error('Invalid UTF-8 detected');
}
var byteArray;
var byteCount;
var byteIndex;
function utf8decode(byteString, opts) {
opts = opts || {};
var strict = false !== opts.strict;
byteArray = ucs2decode(byteString);
byteCount = byteArray.length;
byteIndex = 0;
var codePoints = [];
var tmp;
while ((tmp = decodeSymbol(strict)) !== false) {
codePoints.push(tmp);
}
return ucs2encode(codePoints);
}
module.exports = {
version: '2.1.2',
encode: utf8encode,
decode: utf8decode
};