forked from msgpack/msgpack-javascript
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathutf8.ts
More file actions
170 lines (149 loc) · 4.92 KB
/
utf8.ts
File metadata and controls
170 lines (149 loc) · 4.92 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
const TEXT_ENCODING_AVAILABLE =
typeof process !== "undefined" &&
process.env.TEXT_ENCODING !== "never" &&
typeof TextEncoder !== "undefined" &&
typeof TextDecoder !== "undefined";
const STR_SIZE_MAX = 0xffff_ffff; // uint32_max
export function utf8Count(str: string): number {
const strLength = str.length;
let byteLength = 0;
let pos = 0;
while (pos < strLength) {
let value = str.charCodeAt(pos++);
if ((value & 0xffffff80) === 0) {
// 1-byte
byteLength++;
continue;
} else if ((value & 0xfffff800) === 0) {
// 2-bytes
byteLength += 2;
} else {
// handle surrogate pair
if (value >= 0xd800 && value <= 0xdbff) {
// high surrogate
if (pos < strLength) {
const extra = str.charCodeAt(pos);
if ((extra & 0xfc00) === 0xdc00) {
++pos;
value = ((value & 0x3ff) << 10) + (extra & 0x3ff) + 0x10000;
}
}
}
if ((value & 0xffff0000) === 0) {
// 3-byte
byteLength += 3;
} else {
// 4-byte
byteLength += 4;
}
}
}
return byteLength;
}
export function utf8EncodeJs(str: string, output: Uint8Array, outputOffset: number): void {
const strLength = str.length;
let offset = outputOffset;
let pos = 0;
while (pos < strLength) {
let value = str.charCodeAt(pos++);
if ((value & 0xffffff80) === 0) {
// 1-byte
output[offset++] = value;
continue;
} else if ((value & 0xfffff800) === 0) {
// 2-bytes
output[offset++] = ((value >> 6) & 0x1f) | 0xc0;
} else {
// handle surrogate pair
if (value >= 0xd800 && value <= 0xdbff) {
// high surrogate
if (pos < strLength) {
const extra = str.charCodeAt(pos);
if ((extra & 0xfc00) === 0xdc00) {
++pos;
value = ((value & 0x3ff) << 10) + (extra & 0x3ff) + 0x10000;
}
}
}
if ((value & 0xffff0000) === 0) {
// 3-byte
output[offset++] = ((value >> 12) & 0x0f) | 0xe0;
output[offset++] = ((value >> 6) & 0x3f) | 0x80;
} else {
// 4-byte
output[offset++] = ((value >> 18) & 0x07) | 0xf0;
output[offset++] = ((value >> 12) & 0x3f) | 0x80;
output[offset++] = ((value >> 6) & 0x3f) | 0x80;
}
}
output[offset++] = (value & 0x3f) | 0x80;
}
}
const sharedTextEncoder = TEXT_ENCODING_AVAILABLE ? new TextEncoder() : undefined;
export const TEXT_ENCODER_THRESHOLD = !TEXT_ENCODING_AVAILABLE
? STR_SIZE_MAX
: typeof process !== "undefined" && process.env.TEXT_ENCODING !== "force"
? 200
: 0;
function utf8EncodeTEencode(str: string, output: Uint8Array, outputOffset: number): void {
output.set(sharedTextEncoder!.encode(str), outputOffset);
}
function utf8EncodeTEencodeInto(str: string, output: Uint8Array, outputOffset: number): void {
sharedTextEncoder!.encodeInto(str, output.subarray(outputOffset));
}
export const utf8EncodeTE = sharedTextEncoder?.encodeInto ? utf8EncodeTEencodeInto : utf8EncodeTEencode;
const CHUNK_SIZE = 0x1_000;
export function utf8DecodeJs(bytes: Uint8Array, inputOffset: number, byteLength: number): string {
let offset = inputOffset;
const end = offset + byteLength;
const units: Array<number> = [];
let result = "";
while (offset < end) {
const byte1 = bytes[offset++]!;
if ((byte1 & 0x80) === 0) {
// 1 byte
units.push(byte1);
} else if ((byte1 & 0xe0) === 0xc0) {
// 2 bytes
const byte2 = bytes[offset++]! & 0x3f;
units.push(((byte1 & 0x1f) << 6) | byte2);
} else if ((byte1 & 0xf0) === 0xe0) {
// 3 bytes
const byte2 = bytes[offset++]! & 0x3f;
const byte3 = bytes[offset++]! & 0x3f;
units.push(((byte1 & 0x1f) << 12) | (byte2 << 6) | byte3);
} else if ((byte1 & 0xf8) === 0xf0) {
// 4 bytes
const byte2 = bytes[offset++]! & 0x3f;
const byte3 = bytes[offset++]! & 0x3f;
const byte4 = bytes[offset++]! & 0x3f;
let unit = ((byte1 & 0x07) << 0x12) | (byte2 << 0x0c) | (byte3 << 0x06) | byte4;
if (unit > 0xffff) {
unit -= 0x10000;
units.push(((unit >>> 10) & 0x3ff) | 0xd800);
unit = 0xdc00 | (unit & 0x3ff);
}
units.push(unit);
} else {
units.push(byte1);
}
if (units.length >= CHUNK_SIZE) {
result += String.fromCharCode(...units);
units.length = 0;
}
}
if (units.length > 0) {
result += String.fromCharCode(...units);
}
return result;
}
const sharedTextDecoder = TEXT_ENCODING_AVAILABLE ? new TextDecoder() : null;
export const TEXT_DECODER_THRESHOLD = !TEXT_ENCODING_AVAILABLE
? STR_SIZE_MAX
: typeof process !== "undefined" && process.env.TEXT_DECODER !== "force"
? 200
: 0;
export function utf8DecodeTD(bytes: Uint8Array, inputOffset: number, byteLength: number): string {
const stringBytes = bytes.subarray(inputOffset, inputOffset + byteLength);
return sharedTextDecoder!.decode(stringBytes);
}