utf8-support.js
4.11 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
/*
* Copyright © 2016-2020 The Thingsboard Authors
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
export function utf8Encode(str) {
var result;
if (angular.isUndefined(Uint8Array)) { // eslint-disable-line no-undef
result = utf8ToBytes(str);
} else {
result = new Uint8Array(utf8ToBytes(str)); // eslint-disable-line no-undef
}
return result;
}
export function utf8Decode(bytes) {
return utf8Slice(bytes, 0, bytes.length);
}
function utf8Slice (buf, start, end) {
var res = ''
var tmp = ''
end = Math.min(buf.length, end || Infinity)
start = start || 0;
for (var i = start; i < end; i++) {
if (buf[i] <= 0x7F) {
res += decodeUtf8Char(tmp) + String.fromCharCode(buf[i])
tmp = ''
} else {
tmp += '%' + buf[i].toString(16)
}
}
return res + decodeUtf8Char(tmp)
}
function decodeUtf8Char (str) {
try {
return decodeURIComponent(str)
} catch (err) {
return String.fromCharCode(0xFFFD) // UTF 8 invalid char
}
}
function utf8ToBytes (string, units) {
units = units || Infinity
var codePoint
var length = string.length
var leadSurrogate = null
var bytes = []
var i = 0
for (; i < length; i++) {
codePoint = string.charCodeAt(i)
// is surrogate component
if (codePoint > 0xD7FF && codePoint < 0xE000) {
// last char was a lead
if (leadSurrogate) {
// 2 leads in a row
if (codePoint < 0xDC00) {
if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD)
leadSurrogate = codePoint
continue
} else {
// valid surrogate pair
codePoint = leadSurrogate - 0xD800 << 10 | codePoint - 0xDC00 | 0x10000
leadSurrogate = null
}
} else {
// no lead yet
if (codePoint > 0xDBFF) {
// unexpected trail
if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD)
continue
} else if (i + 1 === length) {
// unpaired lead
if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD)
continue
} else {
// valid lead
leadSurrogate = codePoint
continue
}
}
} else if (leadSurrogate) {
// valid bmp char, but last char was a lead
if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD)
leadSurrogate = null
}
// encode utf8
if (codePoint < 0x80) {
if ((units -= 1) < 0) break
bytes.push(codePoint)
} else if (codePoint < 0x800) {
if ((units -= 2) < 0) break
bytes.push(
codePoint >> 0x6 | 0xC0,
codePoint & 0x3F | 0x80
)
} else if (codePoint < 0x10000) {
if ((units -= 3) < 0) break
bytes.push(
codePoint >> 0xC | 0xE0,
codePoint >> 0x6 & 0x3F | 0x80,
codePoint & 0x3F | 0x80
)
} else if (codePoint < 0x200000) {
if ((units -= 4) < 0) break
bytes.push(
codePoint >> 0x12 | 0xF0,
codePoint >> 0xC & 0x3F | 0x80,
codePoint >> 0x6 & 0x3F | 0x80,
codePoint & 0x3F | 0x80
)
} else {
throw new Error('Invalid code point')
}
}
return bytes
}