1 | /*! https://mths.be/utf8js v2.1.2 by @mathias */
|
---|
2 |
|
---|
3 | var stringFromCharCode = String.fromCharCode;
|
---|
4 |
|
---|
5 | // Taken from https://mths.be/punycode
|
---|
6 | function ucs2decode(string) {
|
---|
7 | var output = [];
|
---|
8 | var counter = 0;
|
---|
9 | var length = string.length;
|
---|
10 | var value;
|
---|
11 | var extra;
|
---|
12 | while (counter < length) {
|
---|
13 | value = string.charCodeAt(counter++);
|
---|
14 | if (value >= 0xD800 && value <= 0xDBFF && counter < length) {
|
---|
15 | // high surrogate, and there is a next character
|
---|
16 | extra = string.charCodeAt(counter++);
|
---|
17 | if ((extra & 0xFC00) == 0xDC00) { // low surrogate
|
---|
18 | output.push(((value & 0x3FF) << 10) + (extra & 0x3FF) + 0x10000);
|
---|
19 | } else {
|
---|
20 | // unmatched surrogate; only append this code unit, in case the next
|
---|
21 | // code unit is the high surrogate of a surrogate pair
|
---|
22 | output.push(value);
|
---|
23 | counter--;
|
---|
24 | }
|
---|
25 | } else {
|
---|
26 | output.push(value);
|
---|
27 | }
|
---|
28 | }
|
---|
29 | return output;
|
---|
30 | }
|
---|
31 |
|
---|
32 | // Taken from https://mths.be/punycode
|
---|
33 | function ucs2encode(array) {
|
---|
34 | var length = array.length;
|
---|
35 | var index = -1;
|
---|
36 | var value;
|
---|
37 | var output = '';
|
---|
38 | while (++index < length) {
|
---|
39 | value = array[index];
|
---|
40 | if (value > 0xFFFF) {
|
---|
41 | value -= 0x10000;
|
---|
42 | output += stringFromCharCode(value >>> 10 & 0x3FF | 0xD800);
|
---|
43 | value = 0xDC00 | value & 0x3FF;
|
---|
44 | }
|
---|
45 | output += stringFromCharCode(value);
|
---|
46 | }
|
---|
47 | return output;
|
---|
48 | }
|
---|
49 |
|
---|
50 | function checkScalarValue(codePoint, strict) {
|
---|
51 | if (codePoint >= 0xD800 && codePoint <= 0xDFFF) {
|
---|
52 | if (strict) {
|
---|
53 | throw Error(
|
---|
54 | 'Lone surrogate U+' + codePoint.toString(16).toUpperCase() +
|
---|
55 | ' is not a scalar value'
|
---|
56 | );
|
---|
57 | }
|
---|
58 | return false;
|
---|
59 | }
|
---|
60 | return true;
|
---|
61 | }
|
---|
62 | /*--------------------------------------------------------------------------*/
|
---|
63 |
|
---|
64 | function createByte(codePoint, shift) {
|
---|
65 | return stringFromCharCode(((codePoint >> shift) & 0x3F) | 0x80);
|
---|
66 | }
|
---|
67 |
|
---|
68 | function encodeCodePoint(codePoint, strict) {
|
---|
69 | if ((codePoint & 0xFFFFFF80) == 0) { // 1-byte sequence
|
---|
70 | return stringFromCharCode(codePoint);
|
---|
71 | }
|
---|
72 | var symbol = '';
|
---|
73 | if ((codePoint & 0xFFFFF800) == 0) { // 2-byte sequence
|
---|
74 | symbol = stringFromCharCode(((codePoint >> 6) & 0x1F) | 0xC0);
|
---|
75 | }
|
---|
76 | else if ((codePoint & 0xFFFF0000) == 0) { // 3-byte sequence
|
---|
77 | if (!checkScalarValue(codePoint, strict)) {
|
---|
78 | codePoint = 0xFFFD;
|
---|
79 | }
|
---|
80 | symbol = stringFromCharCode(((codePoint >> 12) & 0x0F) | 0xE0);
|
---|
81 | symbol += createByte(codePoint, 6);
|
---|
82 | }
|
---|
83 | else if ((codePoint & 0xFFE00000) == 0) { // 4-byte sequence
|
---|
84 | symbol = stringFromCharCode(((codePoint >> 18) & 0x07) | 0xF0);
|
---|
85 | symbol += createByte(codePoint, 12);
|
---|
86 | symbol += createByte(codePoint, 6);
|
---|
87 | }
|
---|
88 | symbol += stringFromCharCode((codePoint & 0x3F) | 0x80);
|
---|
89 | return symbol;
|
---|
90 | }
|
---|
91 |
|
---|
92 | function utf8encode(string, opts) {
|
---|
93 | opts = opts || {};
|
---|
94 | var strict = false !== opts.strict;
|
---|
95 |
|
---|
96 | var codePoints = ucs2decode(string);
|
---|
97 | var length = codePoints.length;
|
---|
98 | var index = -1;
|
---|
99 | var codePoint;
|
---|
100 | var byteString = '';
|
---|
101 | while (++index < length) {
|
---|
102 | codePoint = codePoints[index];
|
---|
103 | byteString += encodeCodePoint(codePoint, strict);
|
---|
104 | }
|
---|
105 | return byteString;
|
---|
106 | }
|
---|
107 |
|
---|
108 | /*--------------------------------------------------------------------------*/
|
---|
109 |
|
---|
110 | function readContinuationByte() {
|
---|
111 | if (byteIndex >= byteCount) {
|
---|
112 | throw Error('Invalid byte index');
|
---|
113 | }
|
---|
114 |
|
---|
115 | var continuationByte = byteArray[byteIndex] & 0xFF;
|
---|
116 | byteIndex++;
|
---|
117 |
|
---|
118 | if ((continuationByte & 0xC0) == 0x80) {
|
---|
119 | return continuationByte & 0x3F;
|
---|
120 | }
|
---|
121 |
|
---|
122 | // If we end up here, it’s not a continuation byte
|
---|
123 | throw Error('Invalid continuation byte');
|
---|
124 | }
|
---|
125 |
|
---|
126 | function decodeSymbol(strict) {
|
---|
127 | var byte1;
|
---|
128 | var byte2;
|
---|
129 | var byte3;
|
---|
130 | var byte4;
|
---|
131 | var codePoint;
|
---|
132 |
|
---|
133 | if (byteIndex > byteCount) {
|
---|
134 | throw Error('Invalid byte index');
|
---|
135 | }
|
---|
136 |
|
---|
137 | if (byteIndex == byteCount) {
|
---|
138 | return false;
|
---|
139 | }
|
---|
140 |
|
---|
141 | // Read first byte
|
---|
142 | byte1 = byteArray[byteIndex] & 0xFF;
|
---|
143 | byteIndex++;
|
---|
144 |
|
---|
145 | // 1-byte sequence (no continuation bytes)
|
---|
146 | if ((byte1 & 0x80) == 0) {
|
---|
147 | return byte1;
|
---|
148 | }
|
---|
149 |
|
---|
150 | // 2-byte sequence
|
---|
151 | if ((byte1 & 0xE0) == 0xC0) {
|
---|
152 | byte2 = readContinuationByte();
|
---|
153 | codePoint = ((byte1 & 0x1F) << 6) | byte2;
|
---|
154 | if (codePoint >= 0x80) {
|
---|
155 | return codePoint;
|
---|
156 | } else {
|
---|
157 | throw Error('Invalid continuation byte');
|
---|
158 | }
|
---|
159 | }
|
---|
160 |
|
---|
161 | // 3-byte sequence (may include unpaired surrogates)
|
---|
162 | if ((byte1 & 0xF0) == 0xE0) {
|
---|
163 | byte2 = readContinuationByte();
|
---|
164 | byte3 = readContinuationByte();
|
---|
165 | codePoint = ((byte1 & 0x0F) << 12) | (byte2 << 6) | byte3;
|
---|
166 | if (codePoint >= 0x0800) {
|
---|
167 | return checkScalarValue(codePoint, strict) ? codePoint : 0xFFFD;
|
---|
168 | } else {
|
---|
169 | throw Error('Invalid continuation byte');
|
---|
170 | }
|
---|
171 | }
|
---|
172 |
|
---|
173 | // 4-byte sequence
|
---|
174 | if ((byte1 & 0xF8) == 0xF0) {
|
---|
175 | byte2 = readContinuationByte();
|
---|
176 | byte3 = readContinuationByte();
|
---|
177 | byte4 = readContinuationByte();
|
---|
178 | codePoint = ((byte1 & 0x07) << 0x12) | (byte2 << 0x0C) |
|
---|
179 | (byte3 << 0x06) | byte4;
|
---|
180 | if (codePoint >= 0x010000 && codePoint <= 0x10FFFF) {
|
---|
181 | return codePoint;
|
---|
182 | }
|
---|
183 | }
|
---|
184 |
|
---|
185 | throw Error('Invalid UTF-8 detected');
|
---|
186 | }
|
---|
187 |
|
---|
188 | var byteArray;
|
---|
189 | var byteCount;
|
---|
190 | var byteIndex;
|
---|
191 | function utf8decode(byteString, opts) {
|
---|
192 | opts = opts || {};
|
---|
193 | var strict = false !== opts.strict;
|
---|
194 |
|
---|
195 | byteArray = ucs2decode(byteString);
|
---|
196 | byteCount = byteArray.length;
|
---|
197 | byteIndex = 0;
|
---|
198 | var codePoints = [];
|
---|
199 | var tmp;
|
---|
200 | while ((tmp = decodeSymbol(strict)) !== false) {
|
---|
201 | codePoints.push(tmp);
|
---|
202 | }
|
---|
203 | return ucs2encode(codePoints);
|
---|
204 | }
|
---|
205 |
|
---|
206 | module.exports = {
|
---|
207 | version: '2.1.2',
|
---|
208 | encode: utf8encode,
|
---|
209 | decode: utf8decode
|
---|
210 | };
|
---|