@loaders.gl/polyfills 4.2.0-alpha.4 → 4.2.0-alpha.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (81) hide show
  1. package/dist/buffer/btoa.node.js +5 -3
  2. package/dist/buffer/to-array-buffer.node.js +6 -6
  3. package/dist/crypto/node-hash.js +41 -45
  4. package/dist/fetch/decode-data-uri.js +56 -41
  5. package/dist/fetch/fetch-polyfill.d.ts +1 -1
  6. package/dist/fetch/fetch-polyfill.d.ts.map +1 -1
  7. package/dist/fetch/fetch-polyfill.js +118 -103
  8. package/dist/fetch/headers-polyfill.js +90 -89
  9. package/dist/fetch/response-polyfill.d.ts +1 -1
  10. package/dist/fetch/response-polyfill.d.ts.map +1 -1
  11. package/dist/fetch/response-polyfill.js +65 -57
  12. package/dist/fetch/utils/decode-data-uri.node.js +56 -41
  13. package/dist/file/blob-stream-controller.js +54 -38
  14. package/dist/file/blob-stream.d.ts +1 -1
  15. package/dist/file/blob-stream.d.ts.map +1 -1
  16. package/dist/file/blob-stream.js +29 -15
  17. package/dist/file/blob.d.ts +1 -1
  18. package/dist/file/blob.d.ts.map +1 -1
  19. package/dist/file/blob.js +146 -109
  20. package/dist/file/file-reader.js +22 -50
  21. package/dist/file/file.js +30 -15
  22. package/dist/file/install-blob-polyfills.js +6 -5
  23. package/dist/file/install-file-polyfills.js +11 -8
  24. package/dist/file/readable-stream.js +5 -2
  25. package/dist/filesystems/fetch-node.js +78 -68
  26. package/dist/filesystems/node-file.js +119 -87
  27. package/dist/filesystems/node-filesystem.d.ts +1 -1
  28. package/dist/filesystems/node-filesystem.d.ts.map +1 -1
  29. package/dist/filesystems/node-filesystem.js +39 -35
  30. package/dist/filesystems/stream-utils.node.js +88 -55
  31. package/dist/images/encode-image-node.js +25 -12
  32. package/dist/images/encode-image.node.js +25 -12
  33. package/dist/images/parse-image-node.js +30 -23
  34. package/dist/images/parse-image.node.js +30 -23
  35. package/dist/index.browser.js +8 -3
  36. package/dist/index.cjs +13 -65091
  37. package/dist/index.cjs.map +7 -0
  38. package/dist/index.d.ts +4 -4
  39. package/dist/index.d.ts.map +1 -1
  40. package/dist/index.js +45 -15
  41. package/dist/libs/encoding-indexes-asian.js +6 -7
  42. package/dist/load-library/require-utils.node.js +70 -44
  43. package/dist/streams/make-node-stream.js +48 -46
  44. package/dist/text-encoder/encoding-indexes.js +31 -28
  45. package/dist/text-encoder/text-encoder.js +2604 -1033
  46. package/dist/utils/assert.js +3 -4
  47. package/dist/utils/is-browser.js +7 -2
  48. package/package.json +10 -8
  49. package/dist/buffer/btoa.node.js.map +0 -1
  50. package/dist/buffer/to-array-buffer.node.js.map +0 -1
  51. package/dist/crypto/node-hash.js.map +0 -1
  52. package/dist/dist.dev.js +0 -45
  53. package/dist/fetch/decode-data-uri.js.map +0 -1
  54. package/dist/fetch/fetch-polyfill.js.map +0 -1
  55. package/dist/fetch/headers-polyfill.js.map +0 -1
  56. package/dist/fetch/response-polyfill.js.map +0 -1
  57. package/dist/fetch/utils/decode-data-uri.node.js.map +0 -1
  58. package/dist/file/blob-stream-controller.js.map +0 -1
  59. package/dist/file/blob-stream.js.map +0 -1
  60. package/dist/file/blob.js.map +0 -1
  61. package/dist/file/file-reader.js.map +0 -1
  62. package/dist/file/file.js.map +0 -1
  63. package/dist/file/install-blob-polyfills.js.map +0 -1
  64. package/dist/file/install-file-polyfills.js.map +0 -1
  65. package/dist/file/readable-stream.js.map +0 -1
  66. package/dist/filesystems/fetch-node.js.map +0 -1
  67. package/dist/filesystems/node-file.js.map +0 -1
  68. package/dist/filesystems/node-filesystem.js.map +0 -1
  69. package/dist/filesystems/stream-utils.node.js.map +0 -1
  70. package/dist/images/encode-image-node.js.map +0 -1
  71. package/dist/images/encode-image.node.js.map +0 -1
  72. package/dist/images/parse-image-node.js.map +0 -1
  73. package/dist/images/parse-image.node.js.map +0 -1
  74. package/dist/index.browser.js.map +0 -1
  75. package/dist/index.js.map +0 -1
  76. package/dist/load-library/require-utils.node.js.map +0 -1
  77. package/dist/streams/make-node-stream.js.map +0 -1
  78. package/dist/text-encoder/encoding-indexes.js.map +0 -1
  79. package/dist/text-encoder/text-encoder.js.map +0 -1
  80. package/dist/utils/assert.js.map +0 -1
  81. package/dist/utils/is-browser.js.map +0 -1
@@ -1,1206 +1,2777 @@
1
+ // @ts-nocheck
2
+ /* eslint-disable */
3
+ // Copied from https://github.com/inexorabletash/text-encoding/blob/b4e5bc26e26e51f56e3daa9f13138c79f49d3c34/lib/encoding.js
4
+ // This is free and unencumbered software released into the public domain.
5
+ // See LICENSE.md for more information.
1
6
  import indexes from "./encoding-indexes.js";
7
+ // Note: Aaian character indices add half a megabyte to bundle. Ignore, since we really only want the built-in UTF8...
8
+ // import indexes from './encoding-indexes-asian.js';
2
9
  globalThis['encoding-indexes'] = indexes || {};
10
+ //
11
+ // Utilities
12
+ //
13
+ /**
14
+ * @param {number} a The number to test.
15
+ * @param {number} min The minimum value in the range, inclusive.
16
+ * @param {number} max The maximum value in the range, inclusive.
17
+ * @return {boolean} True if a >= min and a <= max.
18
+ */
3
19
  function inRange(a, min, max) {
4
- return min <= a && a <= max;
20
+ return min <= a && a <= max;
5
21
  }
22
+ /**
23
+ * @param {!Array.<*>} array The array to check.
24
+ * @param {*} item The item to look for in the array.
25
+ * @return {boolean} True if the item appears in the array.
26
+ */
6
27
  function includes(array, item) {
7
- return array.indexOf(item) !== -1;
28
+ return array.indexOf(item) !== -1;
8
29
  }
9
30
  var floor = Math.floor;
31
+ /**
32
+ * @param {*} o
33
+ * @return {Object}
34
+ */
10
35
  function ToDictionary(o) {
11
- if (o === undefined) return {};
12
- if (o === Object(o)) return o;
13
- throw TypeError('Could not convert argument to dictionary');
36
+ if (o === undefined)
37
+ return {};
38
+ if (o === Object(o))
39
+ return o;
40
+ throw TypeError('Could not convert argument to dictionary');
14
41
  }
42
+ /**
43
+ * @param {string} string Input string of UTF-16 code units.
44
+ * @return {!Array.<number>} Code points.
45
+ */
15
46
  function stringToCodePoints(string) {
16
- var s = String(string);
17
- var n = s.length;
18
- var i = 0;
19
- var u = [];
20
- while (i < n) {
21
- var c = s.charCodeAt(i);
22
- if (c < 0xd800 || c > 0xdfff) {
23
- u.push(c);
24
- } else if (0xdc00 <= c && c <= 0xdfff) {
25
- u.push(0xfffd);
26
- } else if (0xd800 <= c && c <= 0xdbff) {
27
- if (i === n - 1) {
28
- u.push(0xfffd);
29
- } else {
30
- var d = s.charCodeAt(i + 1);
31
- if (0xdc00 <= d && d <= 0xdfff) {
32
- var a = c & 0x3ff;
33
- var b = d & 0x3ff;
34
- u.push(0x10000 + (a << 10) + b);
35
- i += 1;
36
- } else {
37
- u.push(0xfffd);
38
- }
39
- }
47
+ // https://heycam.github.io/webidl/#dfn-obtain-unicode
48
+ // 1. Let S be the DOMString value.
49
+ var s = String(string);
50
+ // 2. Let n be the length of S.
51
+ var n = s.length;
52
+ // 3. Initialize i to 0.
53
+ var i = 0;
54
+ // 4. Initialize U to be an empty sequence of Unicode characters.
55
+ var u = [];
56
+ // 5. While i < n:
57
+ while (i < n) {
58
+ // 1. Let c be the code unit in S at index i.
59
+ var c = s.charCodeAt(i);
60
+ // 2. Depending on the value of c:
61
+ // c < 0xD800 or c > 0xDFFF
62
+ if (c < 0xd800 || c > 0xdfff) {
63
+ // Append to U the Unicode character with code point c.
64
+ u.push(c);
65
+ }
66
+ // 0xDC00 ≤ c ≤ 0xDFFF
67
+ else if (0xdc00 <= c && c <= 0xdfff) {
68
+ // Append to U a U+FFFD REPLACEMENT CHARACTER.
69
+ u.push(0xfffd);
70
+ }
71
+ // 0xD800 ≤ c ≤ 0xDBFF
72
+ else if (0xd800 <= c && c <= 0xdbff) {
73
+ // 1. If i = n−1, then append to U a U+FFFD REPLACEMENT
74
+ // CHARACTER.
75
+ if (i === n - 1) {
76
+ u.push(0xfffd);
77
+ }
78
+ // 2. Otherwise, i < n−1:
79
+ else {
80
+ // 1. Let d be the code unit in S at index i+1.
81
+ var d = s.charCodeAt(i + 1);
82
+ // 2. If 0xDC00 ≤ d ≤ 0xDFFF, then:
83
+ if (0xdc00 <= d && d <= 0xdfff) {
84
+ // 1. Let a be c & 0x3FF.
85
+ var a = c & 0x3ff;
86
+ // 2. Let b be d & 0x3FF.
87
+ var b = d & 0x3ff;
88
+ // 3. Append to U the Unicode character with code point
89
+ // 2^16+2^10*a+b.
90
+ u.push(0x10000 + (a << 10) + b);
91
+ // 4. Set i to i+1.
92
+ i += 1;
93
+ }
94
+ // 3. Otherwise, d < 0xDC00 or d > 0xDFFF. Append to U a
95
+ // U+FFFD REPLACEMENT CHARACTER.
96
+ else {
97
+ u.push(0xfffd);
98
+ }
99
+ }
100
+ }
101
+ // 3. Set i to i+1.
102
+ i += 1;
40
103
  }
41
- i += 1;
42
- }
43
- return u;
104
+ // 6. Return U.
105
+ return u;
44
106
  }
107
+ /**
108
+ * @param {!Array.<number>} code_points Array of code points.
109
+ * @return {string} string String of UTF-16 code units.
110
+ */
45
111
  function codePointsToString(code_points) {
46
- var s = '';
47
- for (var i = 0; i < code_points.length; ++i) {
48
- var cp = code_points[i];
49
- if (cp <= 0xffff) {
50
- s += String.fromCharCode(cp);
51
- } else {
52
- cp -= 0x10000;
53
- s += String.fromCharCode((cp >> 10) + 0xd800, (cp & 0x3ff) + 0xdc00);
112
+ var s = '';
113
+ for (var i = 0; i < code_points.length; ++i) {
114
+ var cp = code_points[i];
115
+ if (cp <= 0xffff) {
116
+ s += String.fromCharCode(cp);
117
+ }
118
+ else {
119
+ cp -= 0x10000;
120
+ s += String.fromCharCode((cp >> 10) + 0xd800, (cp & 0x3ff) + 0xdc00);
121
+ }
54
122
  }
55
- }
56
- return s;
123
+ return s;
57
124
  }
125
+ //
126
+ // Implementation of Encoding specification
127
+ // https://encoding.spec.whatwg.org/
128
+ //
129
+ //
130
+ // 4. Terminology
131
+ //
132
+ /**
133
+ * An ASCII byte is a byte in the range 0x00 to 0x7F, inclusive.
134
+ * @param {number} a The number to test.
135
+ * @return {boolean} True if a is in the range 0x00 to 0x7F, inclusive.
136
+ */
58
137
  function isASCIIByte(a) {
59
- return 0x00 <= a && a <= 0x7f;
138
+ return 0x00 <= a && a <= 0x7f;
60
139
  }
140
+ /**
141
+ * An ASCII code point is a code point in the range U+0000 to
142
+ * U+007F, inclusive.
143
+ */
61
144
  var isASCIICodePoint = isASCIIByte;
62
- var end_of_stream = -1;
145
+ /**
146
+ * End-of-stream is a special token that signifies no more tokens
147
+ * are in the stream.
148
+ * @const
149
+ */ var end_of_stream = -1;
150
+ /**
151
+ * A stream represents an ordered sequence of tokens.
152
+ *
153
+ * @constructor
154
+ * @param {!(Array.<number>|Uint8Array)} tokens Array of tokens that provide
155
+ * the stream.
156
+ */
63
157
  function Stream(tokens) {
64
- this.tokens = [].slice.call(tokens);
65
- this.tokens.reverse();
158
+ /** @type {!Array.<number>} */
159
+ this.tokens = [].slice.call(tokens);
160
+ // Reversed as push/pop is more efficient than shift/unshift.
161
+ this.tokens.reverse();
66
162
  }
67
163
  Stream.prototype = {
68
- endOfStream: function () {
69
- return !this.tokens.length;
70
- },
71
- read: function () {
72
- if (!this.tokens.length) return end_of_stream;
73
- return this.tokens.pop();
74
- },
75
- prepend: function (token) {
76
- if (Array.isArray(token)) {
77
- var tokens = token;
78
- while (tokens.length) this.tokens.push(tokens.pop());
79
- } else {
80
- this.tokens.push(token);
81
- }
82
- },
83
- push: function (token) {
84
- if (Array.isArray(token)) {
85
- var tokens = token;
86
- while (tokens.length) this.tokens.unshift(tokens.shift());
87
- } else {
88
- this.tokens.unshift(token);
164
+ /**
165
+ * @return {boolean} True if end-of-stream has been hit.
166
+ */
167
+ endOfStream: function () {
168
+ return !this.tokens.length;
169
+ },
170
+ /**
171
+ * When a token is read from a stream, the first token in the
172
+ * stream must be returned and subsequently removed, and
173
+ * end-of-stream must be returned otherwise.
174
+ *
175
+ * @return {number} Get the next token from the stream, or
176
+ * end_of_stream.
177
+ */
178
+ read: function () {
179
+ if (!this.tokens.length)
180
+ return end_of_stream;
181
+ return this.tokens.pop();
182
+ },
183
+ /**
184
+ * When one or more tokens are prepended to a stream, those tokens
185
+ * must be inserted, in given order, before the first token in the
186
+ * stream.
187
+ *
188
+ * @param {(number|!Array.<number>)} token The token(s) to prepend to the
189
+ * stream.
190
+ */
191
+ prepend: function (token) {
192
+ if (Array.isArray(token)) {
193
+ var tokens = /**@type {!Array.<number>}*/ token;
194
+ while (tokens.length)
195
+ this.tokens.push(tokens.pop());
196
+ }
197
+ else {
198
+ this.tokens.push(token);
199
+ }
200
+ },
201
+ /**
202
+ * When one or more tokens are pushed to a stream, those tokens
203
+ * must be inserted, in given order, after the last token in the
204
+ * stream.
205
+ *
206
+ * @param {(number|!Array.<number>)} token The tokens(s) to push to the
207
+ * stream.
208
+ */
209
+ push: function (token) {
210
+ if (Array.isArray(token)) {
211
+ var tokens = /**@type {!Array.<number>}*/ token;
212
+ while (tokens.length)
213
+ this.tokens.unshift(tokens.shift());
214
+ }
215
+ else {
216
+ this.tokens.unshift(token);
217
+ }
89
218
  }
90
- }
91
219
  };
220
+ //
221
+ // 5. Encodings
222
+ //
223
+ // 5.1 Encoders and decoders
224
+ /** @const */
92
225
  var finished = -1;
226
+ /**
227
+ * @param {boolean} fatal If true, decoding errors raise an exception.
228
+ * @param {number=} opt_code_point Override the standard fallback code point.
229
+ * @return {number} The code point to insert on a decoding error.
230
+ */
93
231
  function decoderError(fatal, opt_code_point) {
94
- if (fatal) throw TypeError('Decoder error');
95
- return opt_code_point || 0xfffd;
232
+ if (fatal)
233
+ throw TypeError('Decoder error');
234
+ return opt_code_point || 0xfffd;
96
235
  }
236
+ /**
237
+ * @param {number} code_point The code point that could not be encoded.
238
+ * @return {number} Always throws, no value is actually returned.
239
+ */
97
240
  function encoderError(code_point) {
98
- throw TypeError('The code point ' + code_point + ' could not be encoded.');
241
+ throw TypeError('The code point ' + code_point + ' could not be encoded.');
99
242
  }
100
- function Decoder() {}
243
+ /** @interface */
244
+ function Decoder() { }
101
245
  Decoder.prototype = {
102
- handler: function (stream, bite) {}
246
+ /**
247
+ * @param {Stream} stream The stream of bytes being decoded.
248
+ * @param {number} bite The next byte read from the stream.
249
+ * @return {?(number|!Array.<number>)} The next code point(s)
250
+ * decoded, or null if not enough data exists in the input
251
+ * stream to decode a complete code point, or |finished|.
252
+ */
253
+ handler: function (stream, bite) { }
103
254
  };
104
- function Encoder() {}
255
+ /** @interface */
256
+ function Encoder() { }
105
257
  Encoder.prototype = {
106
- handler: function (stream, code_point) {}
258
+ /**
259
+ * @param {Stream} stream The stream of code points being encoded.
260
+ * @param {number} code_point Next code point read from the stream.
261
+ * @return {(number|!Array.<number>)} Byte(s) to emit, or |finished|.
262
+ */
263
+ handler: function (stream, code_point) { }
107
264
  };
265
+ // 5.2 Names and labels
266
+ // TODO: Define @typedef for Encoding: {name:string,labels:Array.<string>}
267
+ // https://github.com/google/closure-compiler/issues/247
268
+ /**
269
+ * @param {string} label The encoding label.
270
+ * @return {?{name:string,labels:Array.<string>}}
271
+ */
108
272
  function getEncoding(label) {
109
- label = String(label).trim().toLowerCase();
110
- if (Object.prototype.hasOwnProperty.call(label_to_encoding, label)) {
111
- return label_to_encoding[label];
112
- }
113
- return null;
273
+ // 1. Remove any leading and trailing ASCII whitespace from label.
274
+ label = String(label).trim().toLowerCase();
275
+ // 2. If label is an ASCII case-insensitive match for any of the
276
+ // labels listed in the table below, return the corresponding
277
+ // encoding, and failure otherwise.
278
+ if (Object.prototype.hasOwnProperty.call(label_to_encoding, label)) {
279
+ return label_to_encoding[label];
280
+ }
281
+ return null;
114
282
  }
115
- var encodings = [{
116
- encodings: [{
117
- labels: ['unicode-1-1-utf-8', 'utf-8', 'utf8'],
118
- name: 'UTF-8'
119
- }],
120
- heading: 'The Encoding'
121
- }, {
122
- encodings: [{
123
- labels: ['866', 'cp866', 'csibm866', 'ibm866'],
124
- name: 'IBM866'
125
- }, {
126
- labels: ['csisolatin2', 'iso-8859-2', 'iso-ir-101', 'iso8859-2', 'iso88592', 'iso_8859-2', 'iso_8859-2:1987', 'l2', 'latin2'],
127
- name: 'ISO-8859-2'
128
- }, {
129
- labels: ['csisolatin3', 'iso-8859-3', 'iso-ir-109', 'iso8859-3', 'iso88593', 'iso_8859-3', 'iso_8859-3:1988', 'l3', 'latin3'],
130
- name: 'ISO-8859-3'
131
- }, {
132
- labels: ['csisolatin4', 'iso-8859-4', 'iso-ir-110', 'iso8859-4', 'iso88594', 'iso_8859-4', 'iso_8859-4:1988', 'l4', 'latin4'],
133
- name: 'ISO-8859-4'
134
- }, {
135
- labels: ['csisolatincyrillic', 'cyrillic', 'iso-8859-5', 'iso-ir-144', 'iso8859-5', 'iso88595', 'iso_8859-5', 'iso_8859-5:1988'],
136
- name: 'ISO-8859-5'
137
- }, {
138
- labels: ['arabic', 'asmo-708', 'csiso88596e', 'csiso88596i', 'csisolatinarabic', 'ecma-114', 'iso-8859-6', 'iso-8859-6-e', 'iso-8859-6-i', 'iso-ir-127', 'iso8859-6', 'iso88596', 'iso_8859-6', 'iso_8859-6:1987'],
139
- name: 'ISO-8859-6'
140
- }, {
141
- labels: ['csisolatingreek', 'ecma-118', 'elot_928', 'greek', 'greek8', 'iso-8859-7', 'iso-ir-126', 'iso8859-7', 'iso88597', 'iso_8859-7', 'iso_8859-7:1987', 'sun_eu_greek'],
142
- name: 'ISO-8859-7'
143
- }, {
144
- labels: ['csiso88598e', 'csisolatinhebrew', 'hebrew', 'iso-8859-8', 'iso-8859-8-e', 'iso-ir-138', 'iso8859-8', 'iso88598', 'iso_8859-8', 'iso_8859-8:1988', 'visual'],
145
- name: 'ISO-8859-8'
146
- }, {
147
- labels: ['csiso88598i', 'iso-8859-8-i', 'logical'],
148
- name: 'ISO-8859-8-I'
149
- }, {
150
- labels: ['csisolatin6', 'iso-8859-10', 'iso-ir-157', 'iso8859-10', 'iso885910', 'l6', 'latin6'],
151
- name: 'ISO-8859-10'
152
- }, {
153
- labels: ['iso-8859-13', 'iso8859-13', 'iso885913'],
154
- name: 'ISO-8859-13'
155
- }, {
156
- labels: ['iso-8859-14', 'iso8859-14', 'iso885914'],
157
- name: 'ISO-8859-14'
158
- }, {
159
- labels: ['csisolatin9', 'iso-8859-15', 'iso8859-15', 'iso885915', 'iso_8859-15', 'l9'],
160
- name: 'ISO-8859-15'
161
- }, {
162
- labels: ['iso-8859-16'],
163
- name: 'ISO-8859-16'
164
- }, {
165
- labels: ['cskoi8r', 'koi', 'koi8', 'koi8-r', 'koi8_r'],
166
- name: 'KOI8-R'
167
- }, {
168
- labels: ['koi8-ru', 'koi8-u'],
169
- name: 'KOI8-U'
170
- }, {
171
- labels: ['csmacintosh', 'mac', 'macintosh', 'x-mac-roman'],
172
- name: 'macintosh'
173
- }, {
174
- labels: ['dos-874', 'iso-8859-11', 'iso8859-11', 'iso885911', 'tis-620', 'windows-874'],
175
- name: 'windows-874'
176
- }, {
177
- labels: ['cp1250', 'windows-1250', 'x-cp1250'],
178
- name: 'windows-1250'
179
- }, {
180
- labels: ['cp1251', 'windows-1251', 'x-cp1251'],
181
- name: 'windows-1251'
182
- }, {
183
- labels: ['ansi_x3.4-1968', 'ascii', 'cp1252', 'cp819', 'csisolatin1', 'ibm819', 'iso-8859-1', 'iso-ir-100', 'iso8859-1', 'iso88591', 'iso_8859-1', 'iso_8859-1:1987', 'l1', 'latin1', 'us-ascii', 'windows-1252', 'x-cp1252'],
184
- name: 'windows-1252'
185
- }, {
186
- labels: ['cp1253', 'windows-1253', 'x-cp1253'],
187
- name: 'windows-1253'
188
- }, {
189
- labels: ['cp1254', 'csisolatin5', 'iso-8859-9', 'iso-ir-148', 'iso8859-9', 'iso88599', 'iso_8859-9', 'iso_8859-9:1989', 'l5', 'latin5', 'windows-1254', 'x-cp1254'],
190
- name: 'windows-1254'
191
- }, {
192
- labels: ['cp1255', 'windows-1255', 'x-cp1255'],
193
- name: 'windows-1255'
194
- }, {
195
- labels: ['cp1256', 'windows-1256', 'x-cp1256'],
196
- name: 'windows-1256'
197
- }, {
198
- labels: ['cp1257', 'windows-1257', 'x-cp1257'],
199
- name: 'windows-1257'
200
- }, {
201
- labels: ['cp1258', 'windows-1258', 'x-cp1258'],
202
- name: 'windows-1258'
203
- }, {
204
- labels: ['x-mac-cyrillic', 'x-mac-ukrainian'],
205
- name: 'x-mac-cyrillic'
206
- }],
207
- heading: 'Legacy single-byte encodings'
208
- }, {
209
- encodings: [{
210
- labels: ['chinese', 'csgb2312', 'csiso58gb231280', 'gb2312', 'gb_2312', 'gb_2312-80', 'gbk', 'iso-ir-58', 'x-gbk'],
211
- name: 'GBK'
212
- }, {
213
- labels: ['gb18030'],
214
- name: 'gb18030'
215
- }],
216
- heading: 'Legacy multi-byte Chinese (simplified) encodings'
217
- }, {
218
- encodings: [{
219
- labels: ['big5', 'big5-hkscs', 'cn-big5', 'csbig5', 'x-x-big5'],
220
- name: 'Big5'
221
- }],
222
- heading: 'Legacy multi-byte Chinese (traditional) encodings'
223
- }, {
224
- encodings: [{
225
- labels: ['cseucpkdfmtjapanese', 'euc-jp', 'x-euc-jp'],
226
- name: 'EUC-JP'
227
- }, {
228
- labels: ['csiso2022jp', 'iso-2022-jp'],
229
- name: 'ISO-2022-JP'
230
- }, {
231
- labels: ['csshiftjis', 'ms932', 'ms_kanji', 'shift-jis', 'shift_jis', 'sjis', 'windows-31j', 'x-sjis'],
232
- name: 'Shift_JIS'
233
- }],
234
- heading: 'Legacy multi-byte Japanese encodings'
235
- }, {
236
- encodings: [{
237
- labels: ['cseuckr', 'csksc56011987', 'euc-kr', 'iso-ir-149', 'korean', 'ks_c_5601-1987', 'ks_c_5601-1989', 'ksc5601', 'ksc_5601', 'windows-949'],
238
- name: 'EUC-KR'
239
- }],
240
- heading: 'Legacy multi-byte Korean encodings'
241
- }, {
242
- encodings: [{
243
- labels: ['csiso2022kr', 'hz-gb-2312', 'iso-2022-cn', 'iso-2022-cn-ext', 'iso-2022-kr'],
244
- name: 'replacement'
245
- }, {
246
- labels: ['utf-16be'],
247
- name: 'UTF-16BE'
248
- }, {
249
- labels: ['utf-16', 'utf-16le'],
250
- name: 'UTF-16LE'
251
- }, {
252
- labels: ['x-user-defined'],
253
- name: 'x-user-defined'
254
- }],
255
- heading: 'Legacy miscellaneous encodings'
256
- }];
283
+ /**
284
+ * Encodings table: https://encoding.spec.whatwg.org/encodings.json
285
+ * @const
286
+ * @type {!Array.<{
287
+ * heading: string,
288
+ * encodings: Array.<{name:string,labels:Array.<string>}>
289
+ * }>}
290
+ */
291
+ var encodings = [
292
+ {
293
+ encodings: [
294
+ {
295
+ labels: ['unicode-1-1-utf-8', 'utf-8', 'utf8'],
296
+ name: 'UTF-8'
297
+ }
298
+ ],
299
+ heading: 'The Encoding'
300
+ },
301
+ {
302
+ encodings: [
303
+ {
304
+ labels: ['866', 'cp866', 'csibm866', 'ibm866'],
305
+ name: 'IBM866'
306
+ },
307
+ {
308
+ labels: [
309
+ 'csisolatin2',
310
+ 'iso-8859-2',
311
+ 'iso-ir-101',
312
+ 'iso8859-2',
313
+ 'iso88592',
314
+ 'iso_8859-2',
315
+ 'iso_8859-2:1987',
316
+ 'l2',
317
+ 'latin2'
318
+ ],
319
+ name: 'ISO-8859-2'
320
+ },
321
+ {
322
+ labels: [
323
+ 'csisolatin3',
324
+ 'iso-8859-3',
325
+ 'iso-ir-109',
326
+ 'iso8859-3',
327
+ 'iso88593',
328
+ 'iso_8859-3',
329
+ 'iso_8859-3:1988',
330
+ 'l3',
331
+ 'latin3'
332
+ ],
333
+ name: 'ISO-8859-3'
334
+ },
335
+ {
336
+ labels: [
337
+ 'csisolatin4',
338
+ 'iso-8859-4',
339
+ 'iso-ir-110',
340
+ 'iso8859-4',
341
+ 'iso88594',
342
+ 'iso_8859-4',
343
+ 'iso_8859-4:1988',
344
+ 'l4',
345
+ 'latin4'
346
+ ],
347
+ name: 'ISO-8859-4'
348
+ },
349
+ {
350
+ labels: [
351
+ 'csisolatincyrillic',
352
+ 'cyrillic',
353
+ 'iso-8859-5',
354
+ 'iso-ir-144',
355
+ 'iso8859-5',
356
+ 'iso88595',
357
+ 'iso_8859-5',
358
+ 'iso_8859-5:1988'
359
+ ],
360
+ name: 'ISO-8859-5'
361
+ },
362
+ {
363
+ labels: [
364
+ 'arabic',
365
+ 'asmo-708',
366
+ 'csiso88596e',
367
+ 'csiso88596i',
368
+ 'csisolatinarabic',
369
+ 'ecma-114',
370
+ 'iso-8859-6',
371
+ 'iso-8859-6-e',
372
+ 'iso-8859-6-i',
373
+ 'iso-ir-127',
374
+ 'iso8859-6',
375
+ 'iso88596',
376
+ 'iso_8859-6',
377
+ 'iso_8859-6:1987'
378
+ ],
379
+ name: 'ISO-8859-6'
380
+ },
381
+ {
382
+ labels: [
383
+ 'csisolatingreek',
384
+ 'ecma-118',
385
+ 'elot_928',
386
+ 'greek',
387
+ 'greek8',
388
+ 'iso-8859-7',
389
+ 'iso-ir-126',
390
+ 'iso8859-7',
391
+ 'iso88597',
392
+ 'iso_8859-7',
393
+ 'iso_8859-7:1987',
394
+ 'sun_eu_greek'
395
+ ],
396
+ name: 'ISO-8859-7'
397
+ },
398
+ {
399
+ labels: [
400
+ 'csiso88598e',
401
+ 'csisolatinhebrew',
402
+ 'hebrew',
403
+ 'iso-8859-8',
404
+ 'iso-8859-8-e',
405
+ 'iso-ir-138',
406
+ 'iso8859-8',
407
+ 'iso88598',
408
+ 'iso_8859-8',
409
+ 'iso_8859-8:1988',
410
+ 'visual'
411
+ ],
412
+ name: 'ISO-8859-8'
413
+ },
414
+ {
415
+ labels: ['csiso88598i', 'iso-8859-8-i', 'logical'],
416
+ name: 'ISO-8859-8-I'
417
+ },
418
+ {
419
+ labels: [
420
+ 'csisolatin6',
421
+ 'iso-8859-10',
422
+ 'iso-ir-157',
423
+ 'iso8859-10',
424
+ 'iso885910',
425
+ 'l6',
426
+ 'latin6'
427
+ ],
428
+ name: 'ISO-8859-10'
429
+ },
430
+ {
431
+ labels: ['iso-8859-13', 'iso8859-13', 'iso885913'],
432
+ name: 'ISO-8859-13'
433
+ },
434
+ {
435
+ labels: ['iso-8859-14', 'iso8859-14', 'iso885914'],
436
+ name: 'ISO-8859-14'
437
+ },
438
+ {
439
+ labels: ['csisolatin9', 'iso-8859-15', 'iso8859-15', 'iso885915', 'iso_8859-15', 'l9'],
440
+ name: 'ISO-8859-15'
441
+ },
442
+ {
443
+ labels: ['iso-8859-16'],
444
+ name: 'ISO-8859-16'
445
+ },
446
+ {
447
+ labels: ['cskoi8r', 'koi', 'koi8', 'koi8-r', 'koi8_r'],
448
+ name: 'KOI8-R'
449
+ },
450
+ {
451
+ labels: ['koi8-ru', 'koi8-u'],
452
+ name: 'KOI8-U'
453
+ },
454
+ {
455
+ labels: ['csmacintosh', 'mac', 'macintosh', 'x-mac-roman'],
456
+ name: 'macintosh'
457
+ },
458
+ {
459
+ labels: ['dos-874', 'iso-8859-11', 'iso8859-11', 'iso885911', 'tis-620', 'windows-874'],
460
+ name: 'windows-874'
461
+ },
462
+ {
463
+ labels: ['cp1250', 'windows-1250', 'x-cp1250'],
464
+ name: 'windows-1250'
465
+ },
466
+ {
467
+ labels: ['cp1251', 'windows-1251', 'x-cp1251'],
468
+ name: 'windows-1251'
469
+ },
470
+ {
471
+ labels: [
472
+ 'ansi_x3.4-1968',
473
+ 'ascii',
474
+ 'cp1252',
475
+ 'cp819',
476
+ 'csisolatin1',
477
+ 'ibm819',
478
+ 'iso-8859-1',
479
+ 'iso-ir-100',
480
+ 'iso8859-1',
481
+ 'iso88591',
482
+ 'iso_8859-1',
483
+ 'iso_8859-1:1987',
484
+ 'l1',
485
+ 'latin1',
486
+ 'us-ascii',
487
+ 'windows-1252',
488
+ 'x-cp1252'
489
+ ],
490
+ name: 'windows-1252'
491
+ },
492
+ {
493
+ labels: ['cp1253', 'windows-1253', 'x-cp1253'],
494
+ name: 'windows-1253'
495
+ },
496
+ {
497
+ labels: [
498
+ 'cp1254',
499
+ 'csisolatin5',
500
+ 'iso-8859-9',
501
+ 'iso-ir-148',
502
+ 'iso8859-9',
503
+ 'iso88599',
504
+ 'iso_8859-9',
505
+ 'iso_8859-9:1989',
506
+ 'l5',
507
+ 'latin5',
508
+ 'windows-1254',
509
+ 'x-cp1254'
510
+ ],
511
+ name: 'windows-1254'
512
+ },
513
+ {
514
+ labels: ['cp1255', 'windows-1255', 'x-cp1255'],
515
+ name: 'windows-1255'
516
+ },
517
+ {
518
+ labels: ['cp1256', 'windows-1256', 'x-cp1256'],
519
+ name: 'windows-1256'
520
+ },
521
+ {
522
+ labels: ['cp1257', 'windows-1257', 'x-cp1257'],
523
+ name: 'windows-1257'
524
+ },
525
+ {
526
+ labels: ['cp1258', 'windows-1258', 'x-cp1258'],
527
+ name: 'windows-1258'
528
+ },
529
+ {
530
+ labels: ['x-mac-cyrillic', 'x-mac-ukrainian'],
531
+ name: 'x-mac-cyrillic'
532
+ }
533
+ ],
534
+ heading: 'Legacy single-byte encodings'
535
+ },
536
+ {
537
+ encodings: [
538
+ {
539
+ labels: [
540
+ 'chinese',
541
+ 'csgb2312',
542
+ 'csiso58gb231280',
543
+ 'gb2312',
544
+ 'gb_2312',
545
+ 'gb_2312-80',
546
+ 'gbk',
547
+ 'iso-ir-58',
548
+ 'x-gbk'
549
+ ],
550
+ name: 'GBK'
551
+ },
552
+ {
553
+ labels: ['gb18030'],
554
+ name: 'gb18030'
555
+ }
556
+ ],
557
+ heading: 'Legacy multi-byte Chinese (simplified) encodings'
558
+ },
559
+ {
560
+ encodings: [
561
+ {
562
+ labels: ['big5', 'big5-hkscs', 'cn-big5', 'csbig5', 'x-x-big5'],
563
+ name: 'Big5'
564
+ }
565
+ ],
566
+ heading: 'Legacy multi-byte Chinese (traditional) encodings'
567
+ },
568
+ {
569
+ encodings: [
570
+ {
571
+ labels: ['cseucpkdfmtjapanese', 'euc-jp', 'x-euc-jp'],
572
+ name: 'EUC-JP'
573
+ },
574
+ {
575
+ labels: ['csiso2022jp', 'iso-2022-jp'],
576
+ name: 'ISO-2022-JP'
577
+ },
578
+ {
579
+ labels: [
580
+ 'csshiftjis',
581
+ 'ms932',
582
+ 'ms_kanji',
583
+ 'shift-jis',
584
+ 'shift_jis',
585
+ 'sjis',
586
+ 'windows-31j',
587
+ 'x-sjis'
588
+ ],
589
+ name: 'Shift_JIS'
590
+ }
591
+ ],
592
+ heading: 'Legacy multi-byte Japanese encodings'
593
+ },
594
+ {
595
+ encodings: [
596
+ {
597
+ labels: [
598
+ 'cseuckr',
599
+ 'csksc56011987',
600
+ 'euc-kr',
601
+ 'iso-ir-149',
602
+ 'korean',
603
+ 'ks_c_5601-1987',
604
+ 'ks_c_5601-1989',
605
+ 'ksc5601',
606
+ 'ksc_5601',
607
+ 'windows-949'
608
+ ],
609
+ name: 'EUC-KR'
610
+ }
611
+ ],
612
+ heading: 'Legacy multi-byte Korean encodings'
613
+ },
614
+ {
615
+ encodings: [
616
+ {
617
+ labels: ['csiso2022kr', 'hz-gb-2312', 'iso-2022-cn', 'iso-2022-cn-ext', 'iso-2022-kr'],
618
+ name: 'replacement'
619
+ },
620
+ {
621
+ labels: ['utf-16be'],
622
+ name: 'UTF-16BE'
623
+ },
624
+ {
625
+ labels: ['utf-16', 'utf-16le'],
626
+ name: 'UTF-16LE'
627
+ },
628
+ {
629
+ labels: ['x-user-defined'],
630
+ name: 'x-user-defined'
631
+ }
632
+ ],
633
+ heading: 'Legacy miscellaneous encodings'
634
+ }
635
+ ];
636
+ // Label to encoding registry.
637
+ /** @type {Object.<string,{name:string,labels:Array.<string>}>} */
257
638
  var label_to_encoding = {};
258
639
  encodings.forEach(function (category) {
259
- category.encodings.forEach(function (encoding) {
260
- encoding.labels.forEach(function (label) {
261
- label_to_encoding[label] = encoding;
640
+ category.encodings.forEach(function (encoding) {
641
+ encoding.labels.forEach(function (label) {
642
+ label_to_encoding[label] = encoding;
643
+ });
262
644
  });
263
- });
264
645
  });
646
+ // Registry of of encoder/decoder factories, by encoding name.
647
+ /** @type {Object.<string, function({fatal:boolean}): Encoder>} */
265
648
  var encoders = {};
649
+ /** @type {Object.<string, function({fatal:boolean}): Decoder>} */
266
650
  var decoders = {};
651
+ //
652
+ // 6. Indexes
653
+ //
654
+ /**
655
+ * @param {number} pointer The |pointer| to search for.
656
+ * @param {(!Array.<?number>|undefined)} index The |index| to search within.
657
+ * @return {?number} The code point corresponding to |pointer| in |index|,
658
+ * or null if |code point| is not in |index|.
659
+ */
267
660
  function indexCodePointFor(pointer, index) {
268
- if (!index) return null;
269
- return index[pointer] || null;
661
+ if (!index)
662
+ return null;
663
+ return index[pointer] || null;
270
664
  }
665
+ /**
666
+ * @param {number} code_point The |code point| to search for.
667
+ * @param {!Array.<?number>} index The |index| to search within.
668
+ * @return {?number} The first pointer corresponding to |code point| in
669
+ * |index|, or null if |code point| is not in |index|.
670
+ */
271
671
  function indexPointerFor(code_point, index) {
272
- var pointer = index.indexOf(code_point);
273
- return pointer === -1 ? null : pointer;
672
+ var pointer = index.indexOf(code_point);
673
+ return pointer === -1 ? null : pointer;
274
674
  }
675
+ /**
676
+ * @param {string} name Name of the index.
677
+ * @return {(!Array.<number>|!Array.<Array.<number>>)}
678
+ * */
275
679
  function index(name) {
276
- if (!('encoding-indexes' in globalThis)) {
277
- throw Error('Indexes missing.' + ' Did you forget to include encoding-indexes.js first?');
278
- }
279
- return globalThis['encoding-indexes'][name];
680
+ if (!('encoding-indexes' in globalThis)) {
681
+ throw Error('Indexes missing.' + ' Did you forget to include encoding-indexes.js first?');
682
+ }
683
+ return globalThis['encoding-indexes'][name];
280
684
  }
685
+ /**
686
+ * @param {number} pointer The |pointer| to search for in the gb18030 index.
687
+ * @return {?number} The code point corresponding to |pointer| in |index|,
688
+ * or null if |code point| is not in the gb18030 index.
689
+ */
281
690
  function indexGB18030RangesCodePointFor(pointer) {
282
- if (pointer > 39419 && pointer < 189000 || pointer > 1237575) return null;
283
- if (pointer === 7457) return 0xe7c7;
284
- var offset = 0;
285
- var code_point_offset = 0;
286
- var idx = index('gb18030-ranges');
287
- var i;
288
- for (i = 0; i < idx.length; ++i) {
289
- var entry = idx[i];
290
- if (entry[0] <= pointer) {
291
- offset = entry[0];
292
- code_point_offset = entry[1];
293
- } else {
294
- break;
691
+ // 1. If pointer is greater than 39419 and less than 189000, or
692
+ // pointer is greater than 1237575, return null.
693
+ if ((pointer > 39419 && pointer < 189000) || pointer > 1237575)
694
+ return null;
695
+ // 2. If pointer is 7457, return code point U+E7C7.
696
+ if (pointer === 7457)
697
+ return 0xe7c7;
698
+ // 3. Let offset be the last pointer in index gb18030 ranges that
699
+ // is equal to or less than pointer and let code point offset be
700
+ // its corresponding code point.
701
+ var offset = 0;
702
+ var code_point_offset = 0;
703
+ var idx = index('gb18030-ranges');
704
+ var i;
705
+ for (i = 0; i < idx.length; ++i) {
706
+ /** @type {!Array.<number>} */
707
+ var entry = idx[i];
708
+ if (entry[0] <= pointer) {
709
+ offset = entry[0];
710
+ code_point_offset = entry[1];
711
+ }
712
+ else {
713
+ break;
714
+ }
295
715
  }
296
- }
297
- return code_point_offset + pointer - offset;
716
+ // 4. Return a code point whose value is code point offset +
717
+ // pointer offset.
718
+ return code_point_offset + pointer - offset;
298
719
  }
720
+ /**
721
+ * @param {number} code_point The |code point| to locate in the gb18030 index.
722
+ * @return {number} The first pointer corresponding to |code point| in the
723
+ * gb18030 index.
724
+ */
299
725
  function indexGB18030RangesPointerFor(code_point) {
300
- if (code_point === 0xe7c7) return 7457;
301
- var offset = 0;
302
- var pointer_offset = 0;
303
- var idx = index('gb18030-ranges');
304
- var i;
305
- for (i = 0; i < idx.length; ++i) {
306
- var entry = idx[i];
307
- if (entry[1] <= code_point) {
308
- offset = entry[1];
309
- pointer_offset = entry[0];
310
- } else {
311
- break;
726
+ // 1. If code point is U+E7C7, return pointer 7457.
727
+ if (code_point === 0xe7c7)
728
+ return 7457;
729
+ // 2. Let offset be the last code point in index gb18030 ranges
730
+ // that is equal to or less than code point and let pointer offset
731
+ // be its corresponding pointer.
732
+ var offset = 0;
733
+ var pointer_offset = 0;
734
+ var idx = index('gb18030-ranges');
735
+ var i;
736
+ for (i = 0; i < idx.length; ++i) {
737
+ /** @type {!Array.<number>} */
738
+ var entry = idx[i];
739
+ if (entry[1] <= code_point) {
740
+ offset = entry[1];
741
+ pointer_offset = entry[0];
742
+ }
743
+ else {
744
+ break;
745
+ }
312
746
  }
313
- }
314
- return pointer_offset + code_point - offset;
747
+ // 3. Return a pointer whose value is pointer offset + code point
748
+ // offset.
749
+ return pointer_offset + code_point - offset;
315
750
  }
751
+ /**
752
+ * @param {number} code_point The |code_point| to search for in the Shift_JIS
753
+ * index.
754
+ * @return {?number} The code point corresponding to |pointer| in |index|,
755
+ * or null if |code point| is not in the Shift_JIS index.
756
+ */
316
757
  function indexShiftJISPointerFor(code_point) {
317
- shift_jis_index = shift_jis_index || index('jis0208').map(function (code_point, pointer) {
318
- return inRange(pointer, 8272, 8835) ? null : code_point;
319
- });
320
- var index_ = shift_jis_index;
321
- return index_.indexOf(code_point);
758
+ // 1. Let index be index jis0208 excluding all entries whose
759
+ // pointer is in the range 8272 to 8835, inclusive.
760
+ shift_jis_index =
761
+ shift_jis_index ||
762
+ index('jis0208').map(function (code_point, pointer) {
763
+ return inRange(pointer, 8272, 8835) ? null : code_point;
764
+ });
765
+ var index_ = shift_jis_index;
766
+ // 2. Return the index pointer for code point in index.
767
+ return index_.indexOf(code_point);
322
768
  }
323
769
  var shift_jis_index;
770
+ /**
771
+ * @param {number} code_point The |code_point| to search for in the big5
772
+ * index.
773
+ * @return {?number} The code point corresponding to |pointer| in |index|,
774
+ * or null if |code point| is not in the big5 index.
775
+ */
324
776
  function indexBig5PointerFor(code_point) {
325
- big5_index_no_hkscs = big5_index_no_hkscs || index('big5').map(function (code_point, pointer) {
326
- return pointer < (0xa1 - 0x81) * 157 ? null : code_point;
327
- });
328
- var index_ = big5_index_no_hkscs;
329
- if (code_point === 0x2550 || code_point === 0x255e || code_point === 0x2561 || code_point === 0x256a || code_point === 0x5341 || code_point === 0x5345) {
330
- return index_.lastIndexOf(code_point);
331
- }
332
- return indexPointerFor(code_point, index_);
777
+ // 1. Let index be index Big5 excluding all entries whose pointer
778
+ big5_index_no_hkscs =
779
+ big5_index_no_hkscs ||
780
+ index('big5').map(function (code_point, pointer) {
781
+ return pointer < (0xa1 - 0x81) * 157 ? null : code_point;
782
+ });
783
+ var index_ = big5_index_no_hkscs;
784
+ // 2. If code point is U+2550, U+255E, U+2561, U+256A, U+5341, or
785
+ // U+5345, return the last pointer corresponding to code point in
786
+ // index.
787
+ if (code_point === 0x2550 ||
788
+ code_point === 0x255e ||
789
+ code_point === 0x2561 ||
790
+ code_point === 0x256a ||
791
+ code_point === 0x5341 ||
792
+ code_point === 0x5345) {
793
+ return index_.lastIndexOf(code_point);
794
+ }
795
+ // 3. Return the index pointer for code point in index.
796
+ return indexPointerFor(code_point, index_);
333
797
  }
334
798
  var big5_index_no_hkscs;
335
- var DEFAULT_ENCODING = 'utf-8';
799
+ //
800
+ // 8. API
801
+ //
802
+ /** @const */ var DEFAULT_ENCODING = 'utf-8';
803
+ // 8.1 Interface TextDecoder
804
+ /**
805
+ * @constructor
806
+ * @param {string=} label The label of the encoding;
807
+ * defaults to 'utf-8'.
808
+ * @param {Object=} options
809
+ */
336
810
  function TextDecoder(label, options) {
337
- if (!(this instanceof TextDecoder)) throw TypeError("Called as a function. Did you forget 'new'?");
338
- label = label !== undefined ? String(label) : DEFAULT_ENCODING;
339
- options = ToDictionary(options);
340
- this._encoding = null;
341
- this._decoder = null;
342
- this._ignoreBOM = false;
343
- this._BOMseen = false;
344
- this._error_mode = 'replacement';
345
- this._do_not_flush = false;
346
- var encoding = getEncoding(label);
347
- if (encoding === null || encoding.name === 'replacement') throw RangeError('Unknown encoding: ' + label);
348
- if (!decoders[encoding.name]) {
349
- throw Error('Decoder not present.' + ' Did you forget to include encoding-indexes.js first?');
350
- }
351
- var dec = this;
352
- dec._encoding = encoding;
353
- if (Boolean(options['fatal'])) dec._error_mode = 'fatal';
354
- if (Boolean(options['ignoreBOM'])) dec._ignoreBOM = true;
355
- if (!Object.defineProperty) {
356
- this.encoding = dec._encoding.name.toLowerCase();
357
- this.fatal = dec._error_mode === 'fatal';
358
- this.ignoreBOM = dec._ignoreBOM;
359
- }
360
- return dec;
811
+ // Web IDL conventions
812
+ if (!(this instanceof TextDecoder))
813
+ throw TypeError("Called as a function. Did you forget 'new'?");
814
+ label = label !== undefined ? String(label) : DEFAULT_ENCODING;
815
+ options = ToDictionary(options);
816
+ // A TextDecoder object has an associated encoding, decoder,
817
+ // stream, ignore BOM flag (initially unset), BOM seen flag
818
+ // (initially unset), error mode (initially replacement), and do
819
+ // not flush flag (initially unset).
820
+ /** @private */
821
+ this._encoding = null;
822
+ /** @private @type {?Decoder} */
823
+ this._decoder = null;
824
+ /** @private @type {boolean} */
825
+ this._ignoreBOM = false;
826
+ /** @private @type {boolean} */
827
+ this._BOMseen = false;
828
+ /** @private @type {string} */
829
+ this._error_mode = 'replacement';
830
+ /** @private @type {boolean} */
831
+ this._do_not_flush = false;
832
+ // 1. Let encoding be the result of getting an encoding from
833
+ // label.
834
+ var encoding = getEncoding(label);
835
+ // 2. If encoding is failure or replacement, throw a RangeError.
836
+ if (encoding === null || encoding.name === 'replacement')
837
+ throw RangeError('Unknown encoding: ' + label);
838
+ if (!decoders[encoding.name]) {
839
+ throw Error('Decoder not present.' + ' Did you forget to include encoding-indexes.js first?');
840
+ }
841
+ // 3. Let dec be a new TextDecoder object.
842
+ var dec = this;
843
+ // 4. Set dec's encoding to encoding.
844
+ dec._encoding = encoding;
845
+ // 5. If options's fatal member is true, set dec's error mode to
846
+ // fatal.
847
+ if (Boolean(options['fatal']))
848
+ dec._error_mode = 'fatal';
849
+ // 6. If options's ignoreBOM member is true, set dec's ignore BOM
850
+ // flag.
851
+ if (Boolean(options['ignoreBOM']))
852
+ dec._ignoreBOM = true;
853
+ // For pre-ES5 runtimes:
854
+ if (!Object.defineProperty) {
855
+ this.encoding = dec._encoding.name.toLowerCase();
856
+ this.fatal = dec._error_mode === 'fatal';
857
+ this.ignoreBOM = dec._ignoreBOM;
858
+ }
859
+ // 7. Return dec.
860
+ return dec;
361
861
  }
362
862
  if (Object.defineProperty) {
363
- Object.defineProperty(TextDecoder.prototype, 'encoding', {
364
- get: function () {
365
- return this._encoding.name.toLowerCase();
863
+ // The encoding attribute's getter must return encoding's name.
864
+ Object.defineProperty(TextDecoder.prototype, 'encoding', {
865
+ /** @this {TextDecoder} */
866
+ get: function () {
867
+ return this._encoding.name.toLowerCase();
868
+ }
869
+ });
870
+ // The fatal attribute's getter must return true if error mode
871
+ // is fatal, and false otherwise.
872
+ Object.defineProperty(TextDecoder.prototype, 'fatal', {
873
+ /** @this {TextDecoder} */
874
+ get: function () {
875
+ return this._error_mode === 'fatal';
876
+ }
877
+ });
878
+ // The ignoreBOM attribute's getter must return true if ignore
879
+ // BOM flag is set, and false otherwise.
880
+ Object.defineProperty(TextDecoder.prototype, 'ignoreBOM', {
881
+ /** @this {TextDecoder} */
882
+ get: function () {
883
+ return this._ignoreBOM;
884
+ }
885
+ });
886
+ }
887
+ /**
888
+ * @param {BufferSource=} input The buffer of bytes to decode.
889
+ * @param {Object=} options
890
+ * @return {string} The decoded string.
891
+ */
892
+ TextDecoder.prototype.decode = function decode(input, options) {
893
+ var bytes;
894
+ if (typeof input === 'object' && input instanceof ArrayBuffer) {
895
+ bytes = new Uint8Array(input);
366
896
  }
367
- });
368
- Object.defineProperty(TextDecoder.prototype, 'fatal', {
369
- get: function () {
370
- return this._error_mode === 'fatal';
897
+ else if (typeof input === 'object' &&
898
+ 'buffer' in input &&
899
+ input.buffer instanceof ArrayBuffer) {
900
+ bytes = new Uint8Array(input.buffer, input.byteOffset, input.byteLength);
371
901
  }
372
- });
373
- Object.defineProperty(TextDecoder.prototype, 'ignoreBOM', {
374
- get: function () {
375
- return this._ignoreBOM;
902
+ else {
903
+ bytes = new Uint8Array(0);
376
904
  }
377
- });
378
- }
379
- TextDecoder.prototype.decode = function decode(input, options) {
380
- var bytes;
381
- if (typeof input === 'object' && input instanceof ArrayBuffer) {
382
- bytes = new Uint8Array(input);
383
- } else if (typeof input === 'object' && 'buffer' in input && input.buffer instanceof ArrayBuffer) {
384
- bytes = new Uint8Array(input.buffer, input.byteOffset, input.byteLength);
385
- } else {
386
- bytes = new Uint8Array(0);
387
- }
388
- options = ToDictionary(options);
389
- if (!this._do_not_flush) {
390
- this._decoder = decoders[this._encoding.name]({
391
- fatal: this._error_mode === 'fatal'
392
- });
393
- this._BOMseen = false;
394
- }
395
- this._do_not_flush = Boolean(options['stream']);
396
- var input_stream = new Stream(bytes);
397
- var output = [];
398
- var result;
399
- while (true) {
400
- var token = input_stream.read();
401
- if (token === end_of_stream) break;
402
- result = this._decoder.handler(input_stream, token);
403
- if (result === finished) break;
404
- if (result !== null) {
405
- if (Array.isArray(result)) output.push.apply(output, result);else output.push(result);
905
+ options = ToDictionary(options);
906
+ // 1. If the do not flush flag is unset, set decoder to a new
907
+ // encoding's decoder, set stream to a new stream, and unset the
908
+ // BOM seen flag.
909
+ if (!this._do_not_flush) {
910
+ this._decoder = decoders[this._encoding.name]({
911
+ fatal: this._error_mode === 'fatal'
912
+ });
913
+ this._BOMseen = false;
406
914
  }
407
- }
408
- if (!this._do_not_flush) {
409
- do {
410
- result = this._decoder.handler(input_stream, input_stream.read());
411
- if (result === finished) break;
412
- if (result === null) continue;
413
- if (Array.isArray(result)) output.push.apply(output, result);else output.push(result);
414
- } while (!input_stream.endOfStream());
415
- this._decoder = null;
416
- }
417
- function serializeStream(stream) {
418
- if (includes(['UTF-8', 'UTF-16LE', 'UTF-16BE'], this._encoding.name) && !this._ignoreBOM && !this._BOMseen) {
419
- if (stream.length > 0 && stream[0] === 0xfeff) {
420
- this._BOMseen = true;
421
- stream.shift();
422
- } else if (stream.length > 0) {
423
- this._BOMseen = true;
424
- } else {}
915
+ // 2. If options's stream is true, set the do not flush flag, and
916
+ // unset the do not flush flag otherwise.
917
+ this._do_not_flush = Boolean(options['stream']);
918
+ // 3. If input is given, push a copy of input to stream.
919
+ // TODO: Align with spec algorithm - maintain stream on instance.
920
+ var input_stream = new Stream(bytes);
921
+ // 4. Let output be a new stream.
922
+ var output = [];
923
+ /** @type {?(number|!Array.<number>)} */
924
+ var result;
925
+ // 5. While true:
926
+ while (true) {
927
+ // 1. Let token be the result of reading from stream.
928
+ var token = input_stream.read();
929
+ // 2. If token is end-of-stream and the do not flush flag is
930
+ // set, return output, serialized.
931
+ // TODO: Align with spec algorithm.
932
+ if (token === end_of_stream)
933
+ break;
934
+ // 3. Otherwise, run these subsubsteps:
935
+ // 1. Let result be the result of processing token for decoder,
936
+ // stream, output, and error mode.
937
+ result = this._decoder.handler(input_stream, token);
938
+ // 2. If result is finished, return output, serialized.
939
+ if (result === finished)
940
+ break;
941
+ if (result !== null) {
942
+ if (Array.isArray(result))
943
+ output.push.apply(output, /**@type {!Array.<number>}*/ result);
944
+ else
945
+ output.push(result);
946
+ }
947
+ // 3. Otherwise, if result is error, throw a TypeError.
948
+ // (Thrown in handler)
949
+ // 4. Otherwise, do nothing.
950
+ }
951
+ // TODO: Align with spec algorithm.
952
+ if (!this._do_not_flush) {
953
+ do {
954
+ result = this._decoder.handler(input_stream, input_stream.read());
955
+ if (result === finished)
956
+ break;
957
+ if (result === null)
958
+ continue;
959
+ if (Array.isArray(result))
960
+ output.push.apply(output, /**@type {!Array.<number>}*/ result);
961
+ else
962
+ output.push(result);
963
+ } while (!input_stream.endOfStream());
964
+ this._decoder = null;
965
+ }
966
+ // A TextDecoder object also has an associated serialize stream
967
+ // algorithm...
968
+ /**
969
+ * @param {!Array.<number>} stream
970
+ * @return {string}
971
+ * @this {TextDecoder}
972
+ */
973
+ function serializeStream(stream) {
974
+ // 1. Let token be the result of reading from stream.
975
+ // (Done in-place on array, rather than as a stream)
976
+ // 2. If encoding is UTF-8, UTF-16BE, or UTF-16LE, and ignore
977
+ // BOM flag and BOM seen flag are unset, run these subsubsteps:
978
+ if (includes(['UTF-8', 'UTF-16LE', 'UTF-16BE'], this._encoding.name) &&
979
+ !this._ignoreBOM &&
980
+ !this._BOMseen) {
981
+ if (stream.length > 0 && stream[0] === 0xfeff) {
982
+ // 1. If token is U+FEFF, set BOM seen flag.
983
+ this._BOMseen = true;
984
+ stream.shift();
985
+ }
986
+ else if (stream.length > 0) {
987
+ // 2. Otherwise, if token is not end-of-stream, set BOM seen
988
+ // flag and append token to stream.
989
+ this._BOMseen = true;
990
+ }
991
+ else {
992
+ // 3. Otherwise, if token is not end-of-stream, append token
993
+ // to output.
994
+ // (no-op)
995
+ }
996
+ }
997
+ // 4. Otherwise, return output.
998
+ return codePointsToString(stream);
425
999
  }
426
- return codePointsToString(stream);
427
- }
428
- return serializeStream.call(this, output);
1000
+ return serializeStream.call(this, output);
429
1001
  };
1002
+ // 8.2 Interface TextEncoder
1003
+ /**
1004
+ * @constructor
1005
+ * @param {string=} label The label of the encoding. NONSTANDARD.
1006
+ * @param {Object=} options NONSTANDARD.
1007
+ */
430
1008
  function TextEncoder(label, options) {
431
- if (!(this instanceof TextEncoder)) throw TypeError("Called as a function. Did you forget 'new'?");
432
- options = ToDictionary(options);
433
- this._encoding = null;
434
- this._encoder = null;
435
- this._do_not_flush = false;
436
- this._fatal = Boolean(options['fatal']) ? 'fatal' : 'replacement';
437
- var enc = this;
438
- if (Boolean(options['NONSTANDARD_allowLegacyEncoding'])) {
439
- label = label !== undefined ? String(label) : DEFAULT_ENCODING;
440
- var encoding = getEncoding(label);
441
- if (encoding === null || encoding.name === 'replacement') throw RangeError('Unknown encoding: ' + label);
442
- if (!encoders[encoding.name]) {
443
- throw Error('Encoder not present.' + ' Did you forget to include encoding-indexes.js first?');
1009
+ // Web IDL conventions
1010
+ if (!(this instanceof TextEncoder))
1011
+ throw TypeError("Called as a function. Did you forget 'new'?");
1012
+ options = ToDictionary(options);
1013
+ // A TextEncoder object has an associated encoding and encoder.
1014
+ /** @private */
1015
+ this._encoding = null;
1016
+ /** @private @type {?Encoder} */
1017
+ this._encoder = null;
1018
+ // Non-standard
1019
+ /** @private @type {boolean} */
1020
+ this._do_not_flush = false;
1021
+ /** @private @type {string} */
1022
+ this._fatal = Boolean(options['fatal']) ? 'fatal' : 'replacement';
1023
+ // 1. Let enc be a new TextEncoder object.
1024
+ var enc = this;
1025
+ // 2. Set enc's encoding to UTF-8's encoder.
1026
+ if (Boolean(options['NONSTANDARD_allowLegacyEncoding'])) {
1027
+ // NONSTANDARD behavior.
1028
+ label = label !== undefined ? String(label) : DEFAULT_ENCODING;
1029
+ var encoding = getEncoding(label);
1030
+ if (encoding === null || encoding.name === 'replacement')
1031
+ throw RangeError('Unknown encoding: ' + label);
1032
+ if (!encoders[encoding.name]) {
1033
+ throw Error('Encoder not present.' + ' Did you forget to include encoding-indexes.js first?');
1034
+ }
1035
+ enc._encoding = encoding;
444
1036
  }
445
- enc._encoding = encoding;
446
- } else {
447
- enc._encoding = getEncoding('utf-8');
448
- if (label !== undefined && 'console' in globalThis) {
449
- console.warn('TextEncoder constructor called with encoding label, ' + 'which is ignored.');
1037
+ else {
1038
+ // Standard behavior.
1039
+ enc._encoding = getEncoding('utf-8');
1040
+ if (label !== undefined && 'console' in globalThis) {
1041
+ console.warn('TextEncoder constructor called with encoding label, ' + 'which is ignored.');
1042
+ }
450
1043
  }
451
- }
452
- if (!Object.defineProperty) this.encoding = enc._encoding.name.toLowerCase();
453
- return enc;
1044
+ // For pre-ES5 runtimes:
1045
+ if (!Object.defineProperty)
1046
+ this.encoding = enc._encoding.name.toLowerCase();
1047
+ // 3. Return enc.
1048
+ return enc;
454
1049
  }
455
1050
  if (Object.defineProperty) {
456
- Object.defineProperty(TextEncoder.prototype, 'encoding', {
457
- get: function () {
458
- return this._encoding.name.toLowerCase();
459
- }
460
- });
1051
+ // The encoding attribute's getter must return encoding's name.
1052
+ Object.defineProperty(TextEncoder.prototype, 'encoding', {
1053
+ /** @this {TextEncoder} */
1054
+ get: function () {
1055
+ return this._encoding.name.toLowerCase();
1056
+ }
1057
+ });
461
1058
  }
1059
+ /**
1060
+ * @param {string=} opt_string The string to encode.
1061
+ * @param {Object=} options
1062
+ * @return {!Uint8Array} Encoded bytes, as a Uint8Array.
1063
+ */
462
1064
  TextEncoder.prototype.encode = function encode(opt_string, options) {
463
- opt_string = opt_string === undefined ? '' : String(opt_string);
464
- options = ToDictionary(options);
465
- if (!this._do_not_flush) this._encoder = encoders[this._encoding.name]({
466
- fatal: this._fatal === 'fatal'
467
- });
468
- this._do_not_flush = Boolean(options['stream']);
469
- var input = new Stream(stringToCodePoints(opt_string));
470
- var output = [];
471
- var result;
472
- while (true) {
473
- var token = input.read();
474
- if (token === end_of_stream) break;
475
- result = this._encoder.handler(input, token);
476
- if (result === finished) break;
477
- if (Array.isArray(result)) output.push.apply(output, result);else output.push(result);
478
- }
479
- if (!this._do_not_flush) {
1065
+ opt_string = opt_string === undefined ? '' : String(opt_string);
1066
+ options = ToDictionary(options);
1067
+ // NOTE: This option is nonstandard. None of the encodings
1068
+ // permitted for encoding (i.e. UTF-8, UTF-16) are stateful when
1069
+ // the input is a USVString so streaming is not necessary.
1070
+ if (!this._do_not_flush)
1071
+ this._encoder = encoders[this._encoding.name]({
1072
+ fatal: this._fatal === 'fatal'
1073
+ });
1074
+ this._do_not_flush = Boolean(options['stream']);
1075
+ // 1. Convert input to a stream.
1076
+ var input = new Stream(stringToCodePoints(opt_string));
1077
+ // 2. Let output be a new stream
1078
+ var output = [];
1079
+ /** @type {?(number|!Array.<number>)} */
1080
+ var result;
1081
+ // 3. While true, run these substeps:
480
1082
  while (true) {
481
- result = this._encoder.handler(input, input.read());
482
- if (result === finished) break;
483
- if (Array.isArray(result)) output.push.apply(output, result);else output.push(result);
1083
+ // 1. Let token be the result of reading from input.
1084
+ var token = input.read();
1085
+ if (token === end_of_stream)
1086
+ break;
1087
+ // 2. Let result be the result of processing token for encoder,
1088
+ // input, output.
1089
+ result = this._encoder.handler(input, token);
1090
+ if (result === finished)
1091
+ break;
1092
+ if (Array.isArray(result))
1093
+ output.push.apply(output, /**@type {!Array.<number>}*/ result);
1094
+ else
1095
+ output.push(result);
484
1096
  }
485
- this._encoder = null;
486
- }
487
- return new Uint8Array(output);
1097
+ // TODO: Align with spec algorithm.
1098
+ if (!this._do_not_flush) {
1099
+ while (true) {
1100
+ result = this._encoder.handler(input, input.read());
1101
+ if (result === finished)
1102
+ break;
1103
+ if (Array.isArray(result))
1104
+ output.push.apply(output, /**@type {!Array.<number>}*/ result);
1105
+ else
1106
+ output.push(result);
1107
+ }
1108
+ this._encoder = null;
1109
+ }
1110
+ // 3. If result is finished, convert output into a byte sequence,
1111
+ // and then return a Uint8Array object wrapping an ArrayBuffer
1112
+ // containing output.
1113
+ return new Uint8Array(output);
488
1114
  };
1115
+ //
1116
+ // 9. The encoding
1117
+ //
1118
+ // 9.1 utf-8
1119
+ // 9.1.1 utf-8 decoder
1120
+ /**
1121
+ * @constructor
1122
+ * @implements {Decoder}
1123
+ * @param {{fatal: boolean}} options
1124
+ */
489
1125
  function UTF8Decoder(options) {
490
- var fatal = options.fatal;
491
- var utf8_code_point = 0,
492
- utf8_bytes_seen = 0,
493
- utf8_bytes_needed = 0,
494
- utf8_lower_boundary = 0x80,
495
- utf8_upper_boundary = 0xbf;
496
- this.handler = function (stream, bite) {
497
- if (bite === end_of_stream && utf8_bytes_needed !== 0) {
498
- utf8_bytes_needed = 0;
499
- return decoderError(fatal);
500
- }
501
- if (bite === end_of_stream) return finished;
502
- if (utf8_bytes_needed === 0) {
503
- if (inRange(bite, 0x00, 0x7f)) {
504
- return bite;
505
- } else if (inRange(bite, 0xc2, 0xdf)) {
506
- utf8_bytes_needed = 1;
507
- utf8_code_point = bite & 0x1f;
508
- } else if (inRange(bite, 0xe0, 0xef)) {
509
- if (bite === 0xe0) utf8_lower_boundary = 0xa0;
510
- if (bite === 0xed) utf8_upper_boundary = 0x9f;
511
- utf8_bytes_needed = 2;
512
- utf8_code_point = bite & 0xf;
513
- } else if (inRange(bite, 0xf0, 0xf4)) {
514
- if (bite === 0xf0) utf8_lower_boundary = 0x90;
515
- if (bite === 0xf4) utf8_upper_boundary = 0x8f;
516
- utf8_bytes_needed = 3;
517
- utf8_code_point = bite & 0x7;
518
- } else {
519
- return decoderError(fatal);
520
- }
521
- return null;
522
- }
523
- if (!inRange(bite, utf8_lower_boundary, utf8_upper_boundary)) {
524
- utf8_code_point = utf8_bytes_needed = utf8_bytes_seen = 0;
525
- utf8_lower_boundary = 0x80;
526
- utf8_upper_boundary = 0xbf;
527
- stream.prepend(bite);
528
- return decoderError(fatal);
529
- }
530
- utf8_lower_boundary = 0x80;
531
- utf8_upper_boundary = 0xbf;
532
- utf8_code_point = utf8_code_point << 6 | bite & 0x3f;
533
- utf8_bytes_seen += 1;
534
- if (utf8_bytes_seen !== utf8_bytes_needed) return null;
535
- var code_point = utf8_code_point;
536
- utf8_code_point = utf8_bytes_needed = utf8_bytes_seen = 0;
537
- return code_point;
538
- };
1126
+ var fatal = options.fatal;
1127
+ // utf-8's decoder's has an associated utf-8 code point, utf-8
1128
+ // bytes seen, and utf-8 bytes needed (all initially 0), a utf-8
1129
+ // lower boundary (initially 0x80), and a utf-8 upper boundary
1130
+ // (initially 0xBF).
1131
+ var /** @type {number} */ utf8_code_point = 0,
1132
+ /** @type {number} */ utf8_bytes_seen = 0,
1133
+ /** @type {number} */ utf8_bytes_needed = 0,
1134
+ /** @type {number} */ utf8_lower_boundary = 0x80,
1135
+ /** @type {number} */ utf8_upper_boundary = 0xbf;
1136
+ /**
1137
+ * @param {Stream} stream The stream of bytes being decoded.
1138
+ * @param {number} bite The next byte read from the stream.
1139
+ * @return {?(number|!Array.<number>)} The next code point(s)
1140
+ * decoded, or null if not enough data exists in the input
1141
+ * stream to decode a complete code point.
1142
+ */
1143
+ this.handler = function (stream, bite) {
1144
+ // 1. If byte is end-of-stream and utf-8 bytes needed is not 0,
1145
+ // set utf-8 bytes needed to 0 and return error.
1146
+ if (bite === end_of_stream && utf8_bytes_needed !== 0) {
1147
+ utf8_bytes_needed = 0;
1148
+ return decoderError(fatal);
1149
+ }
1150
+ // 2. If byte is end-of-stream, return finished.
1151
+ if (bite === end_of_stream)
1152
+ return finished;
1153
+ // 3. If utf-8 bytes needed is 0, based on byte:
1154
+ if (utf8_bytes_needed === 0) {
1155
+ // 0x00 to 0x7F
1156
+ if (inRange(bite, 0x00, 0x7f)) {
1157
+ // Return a code point whose value is byte.
1158
+ return bite;
1159
+ }
1160
+ // 0xC2 to 0xDF
1161
+ else if (inRange(bite, 0xc2, 0xdf)) {
1162
+ // 1. Set utf-8 bytes needed to 1.
1163
+ utf8_bytes_needed = 1;
1164
+ // 2. Set UTF-8 code point to byte & 0x1F.
1165
+ utf8_code_point = bite & 0x1f;
1166
+ }
1167
+ // 0xE0 to 0xEF
1168
+ else if (inRange(bite, 0xe0, 0xef)) {
1169
+ // 1. If byte is 0xE0, set utf-8 lower boundary to 0xA0.
1170
+ if (bite === 0xe0)
1171
+ utf8_lower_boundary = 0xa0;
1172
+ // 2. If byte is 0xED, set utf-8 upper boundary to 0x9F.
1173
+ if (bite === 0xed)
1174
+ utf8_upper_boundary = 0x9f;
1175
+ // 3. Set utf-8 bytes needed to 2.
1176
+ utf8_bytes_needed = 2;
1177
+ // 4. Set UTF-8 code point to byte & 0xF.
1178
+ utf8_code_point = bite & 0xf;
1179
+ }
1180
+ // 0xF0 to 0xF4
1181
+ else if (inRange(bite, 0xf0, 0xf4)) {
1182
+ // 1. If byte is 0xF0, set utf-8 lower boundary to 0x90.
1183
+ if (bite === 0xf0)
1184
+ utf8_lower_boundary = 0x90;
1185
+ // 2. If byte is 0xF4, set utf-8 upper boundary to 0x8F.
1186
+ if (bite === 0xf4)
1187
+ utf8_upper_boundary = 0x8f;
1188
+ // 3. Set utf-8 bytes needed to 3.
1189
+ utf8_bytes_needed = 3;
1190
+ // 4. Set UTF-8 code point to byte & 0x7.
1191
+ utf8_code_point = bite & 0x7;
1192
+ }
1193
+ // Otherwise
1194
+ else {
1195
+ // Return error.
1196
+ return decoderError(fatal);
1197
+ }
1198
+ // Return continue.
1199
+ return null;
1200
+ }
1201
+ // 4. If byte is not in the range utf-8 lower boundary to utf-8
1202
+ // upper boundary, inclusive, run these substeps:
1203
+ if (!inRange(bite, utf8_lower_boundary, utf8_upper_boundary)) {
1204
+ // 1. Set utf-8 code point, utf-8 bytes needed, and utf-8
1205
+ // bytes seen to 0, set utf-8 lower boundary to 0x80, and set
1206
+ // utf-8 upper boundary to 0xBF.
1207
+ utf8_code_point = utf8_bytes_needed = utf8_bytes_seen = 0;
1208
+ utf8_lower_boundary = 0x80;
1209
+ utf8_upper_boundary = 0xbf;
1210
+ // 2. Prepend byte to stream.
1211
+ stream.prepend(bite);
1212
+ // 3. Return error.
1213
+ return decoderError(fatal);
1214
+ }
1215
+ // 5. Set utf-8 lower boundary to 0x80 and utf-8 upper boundary
1216
+ // to 0xBF.
1217
+ utf8_lower_boundary = 0x80;
1218
+ utf8_upper_boundary = 0xbf;
1219
+ // 6. Set UTF-8 code point to (UTF-8 code point << 6) | (byte &
1220
+ // 0x3F)
1221
+ utf8_code_point = (utf8_code_point << 6) | (bite & 0x3f);
1222
+ // 7. Increase utf-8 bytes seen by one.
1223
+ utf8_bytes_seen += 1;
1224
+ // 8. If utf-8 bytes seen is not equal to utf-8 bytes needed,
1225
+ // continue.
1226
+ if (utf8_bytes_seen !== utf8_bytes_needed)
1227
+ return null;
1228
+ // 9. Let code point be utf-8 code point.
1229
+ var code_point = utf8_code_point;
1230
+ // 10. Set utf-8 code point, utf-8 bytes needed, and utf-8 bytes
1231
+ // seen to 0.
1232
+ utf8_code_point = utf8_bytes_needed = utf8_bytes_seen = 0;
1233
+ // 11. Return a code point whose value is code point.
1234
+ return code_point;
1235
+ };
539
1236
  }
1237
+ // 9.1.2 utf-8 encoder
1238
+ /**
1239
+ * @constructor
1240
+ * @implements {Encoder}
1241
+ * @param {{fatal: boolean}} options
1242
+ */
540
1243
  function UTF8Encoder(options) {
541
- var fatal = options.fatal;
542
- this.handler = function (stream, code_point) {
543
- if (code_point === end_of_stream) return finished;
544
- if (isASCIICodePoint(code_point)) return code_point;
545
- var count, offset;
546
- if (inRange(code_point, 0x0080, 0x07ff)) {
547
- count = 1;
548
- offset = 0xc0;
549
- } else if (inRange(code_point, 0x0800, 0xffff)) {
550
- count = 2;
551
- offset = 0xe0;
552
- } else if (inRange(code_point, 0x10000, 0x10ffff)) {
553
- count = 3;
554
- offset = 0xf0;
555
- }
556
- var bytes = [(code_point >> 6 * count) + offset];
557
- while (count > 0) {
558
- var temp = code_point >> 6 * (count - 1);
559
- bytes.push(0x80 | temp & 0x3f);
560
- count -= 1;
561
- }
562
- return bytes;
563
- };
1244
+ var fatal = options.fatal;
1245
+ /**
1246
+ * @param {Stream} stream Input stream.
1247
+ * @param {number} code_point Next code point read from the stream.
1248
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
1249
+ */
1250
+ this.handler = function (stream, code_point) {
1251
+ // 1. If code point is end-of-stream, return finished.
1252
+ if (code_point === end_of_stream)
1253
+ return finished;
1254
+ // 2. If code point is an ASCII code point, return a byte whose
1255
+ // value is code point.
1256
+ if (isASCIICodePoint(code_point))
1257
+ return code_point;
1258
+ // 3. Set count and offset based on the range code point is in:
1259
+ var count, offset;
1260
+ // U+0080 to U+07FF, inclusive:
1261
+ if (inRange(code_point, 0x0080, 0x07ff)) {
1262
+ // 1 and 0xC0
1263
+ count = 1;
1264
+ offset = 0xc0;
1265
+ }
1266
+ // U+0800 to U+FFFF, inclusive:
1267
+ else if (inRange(code_point, 0x0800, 0xffff)) {
1268
+ // 2 and 0xE0
1269
+ count = 2;
1270
+ offset = 0xe0;
1271
+ }
1272
+ // U+10000 to U+10FFFF, inclusive:
1273
+ else if (inRange(code_point, 0x10000, 0x10ffff)) {
1274
+ // 3 and 0xF0
1275
+ count = 3;
1276
+ offset = 0xf0;
1277
+ }
1278
+ // 4. Let bytes be a byte sequence whose first byte is (code
1279
+ // point >> (6 × count)) + offset.
1280
+ var bytes = [(code_point >> (6 * count)) + offset];
1281
+ // 5. Run these substeps while count is greater than 0:
1282
+ while (count > 0) {
1283
+ // 1. Set temp to code point >> (6 × (count − 1)).
1284
+ var temp = code_point >> (6 * (count - 1));
1285
+ // 2. Append to bytes 0x80 | (temp & 0x3F).
1286
+ bytes.push(0x80 | (temp & 0x3f));
1287
+ // 3. Decrease count by one.
1288
+ count -= 1;
1289
+ }
1290
+ // 6. Return bytes bytes, in order.
1291
+ return bytes;
1292
+ };
564
1293
  }
1294
+ /** @param {{fatal: boolean}} options */
565
1295
  encoders['UTF-8'] = function (options) {
566
- return new UTF8Encoder(options);
1296
+ return new UTF8Encoder(options);
567
1297
  };
1298
+ /** @param {{fatal: boolean}} options */
568
1299
  decoders['UTF-8'] = function (options) {
569
- return new UTF8Decoder(options);
1300
+ return new UTF8Decoder(options);
570
1301
  };
1302
+ //
1303
+ // 10. Legacy single-byte encodings
1304
+ //
1305
+ // 10.1 single-byte decoder
1306
+ /**
1307
+ * @constructor
1308
+ * @implements {Decoder}
1309
+ * @param {!Array.<number>} index The encoding index.
1310
+ * @param {{fatal: boolean}} options
1311
+ */
571
1312
  function SingleByteDecoder(index, options) {
572
- var fatal = options.fatal;
573
- this.handler = function (stream, bite) {
574
- if (bite === end_of_stream) return finished;
575
- if (isASCIIByte(bite)) return bite;
576
- var code_point = index[bite - 0x80];
577
- if (code_point === null) return decoderError(fatal);
578
- return code_point;
579
- };
1313
+ var fatal = options.fatal;
1314
+ /**
1315
+ * @param {Stream} stream The stream of bytes being decoded.
1316
+ * @param {number} bite The next byte read from the stream.
1317
+ * @return {?(number|!Array.<number>)} The next code point(s)
1318
+ * decoded, or null if not enough data exists in the input
1319
+ * stream to decode a complete code point.
1320
+ */
1321
+ this.handler = function (stream, bite) {
1322
+ // 1. If byte is end-of-stream, return finished.
1323
+ if (bite === end_of_stream)
1324
+ return finished;
1325
+ // 2. If byte is an ASCII byte, return a code point whose value
1326
+ // is byte.
1327
+ if (isASCIIByte(bite))
1328
+ return bite;
1329
+ // 3. Let code point be the index code point for byte − 0x80 in
1330
+ // index single-byte.
1331
+ var code_point = index[bite - 0x80];
1332
+ // 4. If code point is null, return error.
1333
+ if (code_point === null)
1334
+ return decoderError(fatal);
1335
+ // 5. Return a code point whose value is code point.
1336
+ return code_point;
1337
+ };
580
1338
  }
1339
+ // 10.2 single-byte encoder
1340
+ /**
1341
+ * @constructor
1342
+ * @implements {Encoder}
1343
+ * @param {!Array.<?number>} index The encoding index.
1344
+ * @param {{fatal: boolean}} options
1345
+ */
581
1346
  function SingleByteEncoder(index, options) {
582
- var fatal = options.fatal;
583
- this.handler = function (stream, code_point) {
584
- if (code_point === end_of_stream) return finished;
585
- if (isASCIICodePoint(code_point)) return code_point;
586
- var pointer = indexPointerFor(code_point, index);
587
- if (pointer === null) encoderError(code_point);
588
- return pointer + 0x80;
589
- };
1347
+ var fatal = options.fatal;
1348
+ /**
1349
+ * @param {Stream} stream Input stream.
1350
+ * @param {number} code_point Next code point read from the stream.
1351
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
1352
+ */
1353
+ this.handler = function (stream, code_point) {
1354
+ // 1. If code point is end-of-stream, return finished.
1355
+ if (code_point === end_of_stream)
1356
+ return finished;
1357
+ // 2. If code point is an ASCII code point, return a byte whose
1358
+ // value is code point.
1359
+ if (isASCIICodePoint(code_point))
1360
+ return code_point;
1361
+ // 3. Let pointer be the index pointer for code point in index
1362
+ // single-byte.
1363
+ var pointer = indexPointerFor(code_point, index);
1364
+ // 4. If pointer is null, return error with code point.
1365
+ if (pointer === null)
1366
+ encoderError(code_point);
1367
+ // 5. Return a byte whose value is pointer + 0x80.
1368
+ return pointer + 0x80;
1369
+ };
590
1370
  }
591
1371
  (function () {
592
- if (!('encoding-indexes' in globalThis)) return;
593
- encodings.forEach(function (category) {
594
- if (category.heading !== 'Legacy single-byte encodings') return;
595
- category.encodings.forEach(function (encoding) {
596
- var name = encoding.name;
597
- var idx = index(name.toLowerCase());
598
- decoders[name] = function (options) {
599
- return new SingleByteDecoder(idx, options);
600
- };
601
- encoders[name] = function (options) {
602
- return new SingleByteEncoder(idx, options);
603
- };
1372
+ if (!('encoding-indexes' in globalThis))
1373
+ return;
1374
+ encodings.forEach(function (category) {
1375
+ if (category.heading !== 'Legacy single-byte encodings')
1376
+ return;
1377
+ category.encodings.forEach(function (encoding) {
1378
+ var name = encoding.name;
1379
+ var idx = index(name.toLowerCase());
1380
+ /** @param {{fatal: boolean}} options */
1381
+ decoders[name] = function (options) {
1382
+ return new SingleByteDecoder(idx, options);
1383
+ };
1384
+ /** @param {{fatal: boolean}} options */
1385
+ encoders[name] = function (options) {
1386
+ return new SingleByteEncoder(idx, options);
1387
+ };
1388
+ });
604
1389
  });
605
- });
606
1390
  })();
1391
+ //
1392
+ // 11. Legacy multi-byte Chinese (simplified) encodings
1393
+ //
1394
+ // 11.1 gbk
1395
+ // 11.1.1 gbk decoder
1396
+ // gbk's decoder is gb18030's decoder.
1397
+ /** @param {{fatal: boolean}} options */
607
1398
  decoders['GBK'] = function (options) {
608
- return new GB18030Decoder(options);
1399
+ return new GB18030Decoder(options);
609
1400
  };
1401
+ // 11.1.2 gbk encoder
1402
+ // gbk's encoder is gb18030's encoder with its gbk flag set.
1403
+ /** @param {{fatal: boolean}} options */
610
1404
  encoders['GBK'] = function (options) {
611
- return new GB18030Encoder(options, true);
1405
+ return new GB18030Encoder(options, true);
612
1406
  };
1407
+ // 11.2 gb18030
1408
+ // 11.2.1 gb18030 decoder
1409
+ /**
1410
+ * @constructor
1411
+ * @implements {Decoder}
1412
+ * @param {{fatal: boolean}} options
1413
+ */
613
1414
  function GB18030Decoder(options) {
614
- var fatal = options.fatal;
615
- var gb18030_first = 0x00,
616
- gb18030_second = 0x00,
617
- gb18030_third = 0x00;
618
- this.handler = function (stream, bite) {
619
- if (bite === end_of_stream && gb18030_first === 0x00 && gb18030_second === 0x00 && gb18030_third === 0x00) {
620
- return finished;
621
- }
622
- if (bite === end_of_stream && (gb18030_first !== 0x00 || gb18030_second !== 0x00 || gb18030_third !== 0x00)) {
623
- gb18030_first = 0x00;
624
- gb18030_second = 0x00;
625
- gb18030_third = 0x00;
626
- decoderError(fatal);
627
- }
628
- var code_point;
629
- if (gb18030_third !== 0x00) {
630
- code_point = null;
631
- if (inRange(bite, 0x30, 0x39)) {
632
- code_point = indexGB18030RangesCodePointFor((((gb18030_first - 0x81) * 10 + gb18030_second - 0x30) * 126 + gb18030_third - 0x81) * 10 + bite - 0x30);
633
- }
634
- var buffer = [gb18030_second, gb18030_third, bite];
635
- gb18030_first = 0x00;
636
- gb18030_second = 0x00;
637
- gb18030_third = 0x00;
638
- if (code_point === null) {
639
- stream.prepend(buffer);
1415
+ var fatal = options.fatal;
1416
+ // gb18030's decoder has an associated gb18030 first, gb18030
1417
+ // second, and gb18030 third (all initially 0x00).
1418
+ var /** @type {number} */ gb18030_first = 0x00,
1419
+ /** @type {number} */ gb18030_second = 0x00,
1420
+ /** @type {number} */ gb18030_third = 0x00;
1421
+ /**
1422
+ * @param {Stream} stream The stream of bytes being decoded.
1423
+ * @param {number} bite The next byte read from the stream.
1424
+ * @return {?(number|!Array.<number>)} The next code point(s)
1425
+ * decoded, or null if not enough data exists in the input
1426
+ * stream to decode a complete code point.
1427
+ */
1428
+ this.handler = function (stream, bite) {
1429
+ // 1. If byte is end-of-stream and gb18030 first, gb18030
1430
+ // second, and gb18030 third are 0x00, return finished.
1431
+ if (bite === end_of_stream &&
1432
+ gb18030_first === 0x00 &&
1433
+ gb18030_second === 0x00 &&
1434
+ gb18030_third === 0x00) {
1435
+ return finished;
1436
+ }
1437
+ // 2. If byte is end-of-stream, and gb18030 first, gb18030
1438
+ // second, or gb18030 third is not 0x00, set gb18030 first,
1439
+ // gb18030 second, and gb18030 third to 0x00, and return error.
1440
+ if (bite === end_of_stream &&
1441
+ (gb18030_first !== 0x00 || gb18030_second !== 0x00 || gb18030_third !== 0x00)) {
1442
+ gb18030_first = 0x00;
1443
+ gb18030_second = 0x00;
1444
+ gb18030_third = 0x00;
1445
+ decoderError(fatal);
1446
+ }
1447
+ var code_point;
1448
+ // 3. If gb18030 third is not 0x00, run these substeps:
1449
+ if (gb18030_third !== 0x00) {
1450
+ // 1. Let code point be null.
1451
+ code_point = null;
1452
+ // 2. If byte is in the range 0x30 to 0x39, inclusive, set
1453
+ // code point to the index gb18030 ranges code point for
1454
+ // (((gb18030 first − 0x81) × 10 + gb18030 second − 0x30) ×
1455
+ // 126 + gb18030 third − 0x81) × 10 + byte − 0x30.
1456
+ if (inRange(bite, 0x30, 0x39)) {
1457
+ code_point = indexGB18030RangesCodePointFor((((gb18030_first - 0x81) * 10 + gb18030_second - 0x30) * 126 + gb18030_third - 0x81) *
1458
+ 10 +
1459
+ bite -
1460
+ 0x30);
1461
+ }
1462
+ // 3. Let buffer be a byte sequence consisting of gb18030
1463
+ // second, gb18030 third, and byte, in order.
1464
+ var buffer = [gb18030_second, gb18030_third, bite];
1465
+ // 4. Set gb18030 first, gb18030 second, and gb18030 third to
1466
+ // 0x00.
1467
+ gb18030_first = 0x00;
1468
+ gb18030_second = 0x00;
1469
+ gb18030_third = 0x00;
1470
+ // 5. If code point is null, prepend buffer to stream and
1471
+ // return error.
1472
+ if (code_point === null) {
1473
+ stream.prepend(buffer);
1474
+ return decoderError(fatal);
1475
+ }
1476
+ // 6. Return a code point whose value is code point.
1477
+ return code_point;
1478
+ }
1479
+ // 4. If gb18030 second is not 0x00, run these substeps:
1480
+ if (gb18030_second !== 0x00) {
1481
+ // 1. If byte is in the range 0x81 to 0xFE, inclusive, set
1482
+ // gb18030 third to byte and return continue.
1483
+ if (inRange(bite, 0x81, 0xfe)) {
1484
+ gb18030_third = bite;
1485
+ return null;
1486
+ }
1487
+ // 2. Prepend gb18030 second followed by byte to stream, set
1488
+ // gb18030 first and gb18030 second to 0x00, and return error.
1489
+ stream.prepend([gb18030_second, bite]);
1490
+ gb18030_first = 0x00;
1491
+ gb18030_second = 0x00;
1492
+ return decoderError(fatal);
1493
+ }
1494
+ // 5. If gb18030 first is not 0x00, run these substeps:
1495
+ if (gb18030_first !== 0x00) {
1496
+ // 1. If byte is in the range 0x30 to 0x39, inclusive, set
1497
+ // gb18030 second to byte and return continue.
1498
+ if (inRange(bite, 0x30, 0x39)) {
1499
+ gb18030_second = bite;
1500
+ return null;
1501
+ }
1502
+ // 2. Let lead be gb18030 first, let pointer be null, and set
1503
+ // gb18030 first to 0x00.
1504
+ var lead = gb18030_first;
1505
+ var pointer = null;
1506
+ gb18030_first = 0x00;
1507
+ // 3. Let offset be 0x40 if byte is less than 0x7F and 0x41
1508
+ // otherwise.
1509
+ var offset = bite < 0x7f ? 0x40 : 0x41;
1510
+ // 4. If byte is in the range 0x40 to 0x7E, inclusive, or 0x80
1511
+ // to 0xFE, inclusive, set pointer to (lead − 0x81) × 190 +
1512
+ // (byte − offset).
1513
+ if (inRange(bite, 0x40, 0x7e) || inRange(bite, 0x80, 0xfe))
1514
+ pointer = (lead - 0x81) * 190 + (bite - offset);
1515
+ // 5. Let code point be null if pointer is null and the index
1516
+ // code point for pointer in index gb18030 otherwise.
1517
+ code_point = pointer === null ? null : indexCodePointFor(pointer, index('gb18030'));
1518
+ // 6. If code point is null and byte is an ASCII byte, prepend
1519
+ // byte to stream.
1520
+ if (code_point === null && isASCIIByte(bite))
1521
+ stream.prepend(bite);
1522
+ // 7. If code point is null, return error.
1523
+ if (code_point === null)
1524
+ return decoderError(fatal);
1525
+ // 8. Return a code point whose value is code point.
1526
+ return code_point;
1527
+ }
1528
+ // 6. If byte is an ASCII byte, return a code point whose value
1529
+ // is byte.
1530
+ if (isASCIIByte(bite))
1531
+ return bite;
1532
+ // 7. If byte is 0x80, return code point U+20AC.
1533
+ if (bite === 0x80)
1534
+ return 0x20ac;
1535
+ // 8. If byte is in the range 0x81 to 0xFE, inclusive, set
1536
+ // gb18030 first to byte and return continue.
1537
+ if (inRange(bite, 0x81, 0xfe)) {
1538
+ gb18030_first = bite;
1539
+ return null;
1540
+ }
1541
+ // 9. Return error.
640
1542
  return decoderError(fatal);
641
- }
642
- return code_point;
643
- }
644
- if (gb18030_second !== 0x00) {
645
- if (inRange(bite, 0x81, 0xfe)) {
646
- gb18030_third = bite;
647
- return null;
648
- }
649
- stream.prepend([gb18030_second, bite]);
650
- gb18030_first = 0x00;
651
- gb18030_second = 0x00;
652
- return decoderError(fatal);
653
- }
654
- if (gb18030_first !== 0x00) {
655
- if (inRange(bite, 0x30, 0x39)) {
656
- gb18030_second = bite;
657
- return null;
658
- }
659
- var lead = gb18030_first;
660
- var pointer = null;
661
- gb18030_first = 0x00;
662
- var offset = bite < 0x7f ? 0x40 : 0x41;
663
- if (inRange(bite, 0x40, 0x7e) || inRange(bite, 0x80, 0xfe)) pointer = (lead - 0x81) * 190 + (bite - offset);
664
- code_point = pointer === null ? null : indexCodePointFor(pointer, index('gb18030'));
665
- if (code_point === null && isASCIIByte(bite)) stream.prepend(bite);
666
- if (code_point === null) return decoderError(fatal);
667
- return code_point;
668
- }
669
- if (isASCIIByte(bite)) return bite;
670
- if (bite === 0x80) return 0x20ac;
671
- if (inRange(bite, 0x81, 0xfe)) {
672
- gb18030_first = bite;
673
- return null;
674
- }
675
- return decoderError(fatal);
676
- };
1543
+ };
677
1544
  }
1545
+ // 11.2.2 gb18030 encoder
1546
+ /**
1547
+ * @constructor
1548
+ * @implements {Encoder}
1549
+ * @param {{fatal: boolean}} options
1550
+ * @param {boolean=} gbk_flag
1551
+ */
678
1552
  function GB18030Encoder(options, gbk_flag) {
679
- var fatal = options.fatal;
680
- this.handler = function (stream, code_point) {
681
- if (code_point === end_of_stream) return finished;
682
- if (isASCIICodePoint(code_point)) return code_point;
683
- if (code_point === 0xe5e5) return encoderError(code_point);
684
- if (gbk_flag && code_point === 0x20ac) return 0x80;
685
- var pointer = indexPointerFor(code_point, index('gb18030'));
686
- if (pointer !== null) {
687
- var lead = floor(pointer / 190) + 0x81;
688
- var trail = pointer % 190;
689
- var offset = trail < 0x3f ? 0x40 : 0x41;
690
- return [lead, trail + offset];
691
- }
692
- if (gbk_flag) return encoderError(code_point);
693
- pointer = indexGB18030RangesPointerFor(code_point);
694
- var byte1 = floor(pointer / 10 / 126 / 10);
695
- pointer = pointer - byte1 * 10 * 126 * 10;
696
- var byte2 = floor(pointer / 10 / 126);
697
- pointer = pointer - byte2 * 10 * 126;
698
- var byte3 = floor(pointer / 10);
699
- var byte4 = pointer - byte3 * 10;
700
- return [byte1 + 0x81, byte2 + 0x30, byte3 + 0x81, byte4 + 0x30];
701
- };
1553
+ var fatal = options.fatal;
1554
+ // gb18030's decoder has an associated gbk flag (initially unset).
1555
+ /**
1556
+ * @param {Stream} stream Input stream.
1557
+ * @param {number} code_point Next code point read from the stream.
1558
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
1559
+ */
1560
+ this.handler = function (stream, code_point) {
1561
+ // 1. If code point is end-of-stream, return finished.
1562
+ if (code_point === end_of_stream)
1563
+ return finished;
1564
+ // 2. If code point is an ASCII code point, return a byte whose
1565
+ // value is code point.
1566
+ if (isASCIICodePoint(code_point))
1567
+ return code_point;
1568
+ // 3. If code point is U+E5E5, return error with code point.
1569
+ if (code_point === 0xe5e5)
1570
+ return encoderError(code_point);
1571
+ // 4. If the gbk flag is set and code point is U+20AC, return
1572
+ // byte 0x80.
1573
+ if (gbk_flag && code_point === 0x20ac)
1574
+ return 0x80;
1575
+ // 5. Let pointer be the index pointer for code point in index
1576
+ // gb18030.
1577
+ var pointer = indexPointerFor(code_point, index('gb18030'));
1578
+ // 6. If pointer is not null, run these substeps:
1579
+ if (pointer !== null) {
1580
+ // 1. Let lead be floor(pointer / 190) + 0x81.
1581
+ var lead = floor(pointer / 190) + 0x81;
1582
+ // 2. Let trail be pointer % 190.
1583
+ var trail = pointer % 190;
1584
+ // 3. Let offset be 0x40 if trail is less than 0x3F and 0x41 otherwise.
1585
+ var offset = trail < 0x3f ? 0x40 : 0x41;
1586
+ // 4. Return two bytes whose values are lead and trail + offset.
1587
+ return [lead, trail + offset];
1588
+ }
1589
+ // 7. If gbk flag is set, return error with code point.
1590
+ if (gbk_flag)
1591
+ return encoderError(code_point);
1592
+ // 8. Set pointer to the index gb18030 ranges pointer for code
1593
+ // point.
1594
+ pointer = indexGB18030RangesPointerFor(code_point);
1595
+ // 9. Let byte1 be floor(pointer / 10 / 126 / 10).
1596
+ var byte1 = floor(pointer / 10 / 126 / 10);
1597
+ // 10. Set pointer to pointer − byte1 × 10 × 126 × 10.
1598
+ pointer = pointer - byte1 * 10 * 126 * 10;
1599
+ // 11. Let byte2 be floor(pointer / 10 / 126).
1600
+ var byte2 = floor(pointer / 10 / 126);
1601
+ // 12. Set pointer to pointer − byte2 × 10 × 126.
1602
+ pointer = pointer - byte2 * 10 * 126;
1603
+ // 13. Let byte3 be floor(pointer / 10).
1604
+ var byte3 = floor(pointer / 10);
1605
+ // 14. Let byte4 be pointer − byte3 × 10.
1606
+ var byte4 = pointer - byte3 * 10;
1607
+ // 15. Return four bytes whose values are byte1 + 0x81, byte2 +
1608
+ // 0x30, byte3 + 0x81, byte4 + 0x30.
1609
+ return [byte1 + 0x81, byte2 + 0x30, byte3 + 0x81, byte4 + 0x30];
1610
+ };
702
1611
  }
1612
+ /** @param {{fatal: boolean}} options */
703
1613
  encoders['gb18030'] = function (options) {
704
- return new GB18030Encoder(options);
1614
+ return new GB18030Encoder(options);
705
1615
  };
1616
+ /** @param {{fatal: boolean}} options */
706
1617
  decoders['gb18030'] = function (options) {
707
- return new GB18030Decoder(options);
1618
+ return new GB18030Decoder(options);
708
1619
  };
1620
+ //
1621
+ // 12. Legacy multi-byte Chinese (traditional) encodings
1622
+ //
1623
+ // 12.1 Big5
1624
+ // 12.1.1 Big5 decoder
1625
+ /**
1626
+ * @constructor
1627
+ * @implements {Decoder}
1628
+ * @param {{fatal: boolean}} options
1629
+ */
709
1630
  function Big5Decoder(options) {
710
- var fatal = options.fatal;
711
- var Big5_lead = 0x00;
712
- this.handler = function (stream, bite) {
713
- if (bite === end_of_stream && Big5_lead !== 0x00) {
714
- Big5_lead = 0x00;
715
- return decoderError(fatal);
716
- }
717
- if (bite === end_of_stream && Big5_lead === 0x00) return finished;
718
- if (Big5_lead !== 0x00) {
719
- var lead = Big5_lead;
720
- var pointer = null;
721
- Big5_lead = 0x00;
722
- var offset = bite < 0x7f ? 0x40 : 0x62;
723
- if (inRange(bite, 0x40, 0x7e) || inRange(bite, 0xa1, 0xfe)) pointer = (lead - 0x81) * 157 + (bite - offset);
724
- switch (pointer) {
725
- case 1133:
726
- return [0x00ca, 0x0304];
727
- case 1135:
728
- return [0x00ca, 0x030c];
729
- case 1164:
730
- return [0x00ea, 0x0304];
731
- case 1166:
732
- return [0x00ea, 0x030c];
733
- }
734
- var code_point = pointer === null ? null : indexCodePointFor(pointer, index('big5'));
735
- if (code_point === null && isASCIIByte(bite)) stream.prepend(bite);
736
- if (code_point === null) return decoderError(fatal);
737
- return code_point;
738
- }
739
- if (isASCIIByte(bite)) return bite;
740
- if (inRange(bite, 0x81, 0xfe)) {
741
- Big5_lead = bite;
742
- return null;
743
- }
744
- return decoderError(fatal);
745
- };
1631
+ var fatal = options.fatal;
1632
+ // Big5's decoder has an associated Big5 lead (initially 0x00).
1633
+ var /** @type {number} */ Big5_lead = 0x00;
1634
+ /**
1635
+ * @param {Stream} stream The stream of bytes being decoded.
1636
+ * @param {number} bite The next byte read from the stream.
1637
+ * @return {?(number|!Array.<number>)} The next code point(s)
1638
+ * decoded, or null if not enough data exists in the input
1639
+ * stream to decode a complete code point.
1640
+ */
1641
+ this.handler = function (stream, bite) {
1642
+ // 1. If byte is end-of-stream and Big5 lead is not 0x00, set
1643
+ // Big5 lead to 0x00 and return error.
1644
+ if (bite === end_of_stream && Big5_lead !== 0x00) {
1645
+ Big5_lead = 0x00;
1646
+ return decoderError(fatal);
1647
+ }
1648
+ // 2. If byte is end-of-stream and Big5 lead is 0x00, return
1649
+ // finished.
1650
+ if (bite === end_of_stream && Big5_lead === 0x00)
1651
+ return finished;
1652
+ // 3. If Big5 lead is not 0x00, let lead be Big5 lead, let
1653
+ // pointer be null, set Big5 lead to 0x00, and then run these
1654
+ // substeps:
1655
+ if (Big5_lead !== 0x00) {
1656
+ var lead = Big5_lead;
1657
+ var pointer = null;
1658
+ Big5_lead = 0x00;
1659
+ // 1. Let offset be 0x40 if byte is less than 0x7F and 0x62
1660
+ // otherwise.
1661
+ var offset = bite < 0x7f ? 0x40 : 0x62;
1662
+ // 2. If byte is in the range 0x40 to 0x7E, inclusive, or 0xA1
1663
+ // to 0xFE, inclusive, set pointer to (lead − 0x81) × 157 +
1664
+ // (byte − offset).
1665
+ if (inRange(bite, 0x40, 0x7e) || inRange(bite, 0xa1, 0xfe))
1666
+ pointer = (lead - 0x81) * 157 + (bite - offset);
1667
+ // 3. If there is a row in the table below whose first column
1668
+ // is pointer, return the two code points listed in its second
1669
+ // column
1670
+ // Pointer | Code points
1671
+ // --------+--------------
1672
+ // 1133 | U+00CA U+0304
1673
+ // 1135 | U+00CA U+030C
1674
+ // 1164 | U+00EA U+0304
1675
+ // 1166 | U+00EA U+030C
1676
+ switch (pointer) {
1677
+ case 1133:
1678
+ return [0x00ca, 0x0304];
1679
+ case 1135:
1680
+ return [0x00ca, 0x030c];
1681
+ case 1164:
1682
+ return [0x00ea, 0x0304];
1683
+ case 1166:
1684
+ return [0x00ea, 0x030c];
1685
+ }
1686
+ // 4. Let code point be null if pointer is null and the index
1687
+ // code point for pointer in index Big5 otherwise.
1688
+ var code_point = pointer === null ? null : indexCodePointFor(pointer, index('big5'));
1689
+ // 5. If code point is null and byte is an ASCII byte, prepend
1690
+ // byte to stream.
1691
+ if (code_point === null && isASCIIByte(bite))
1692
+ stream.prepend(bite);
1693
+ // 6. If code point is null, return error.
1694
+ if (code_point === null)
1695
+ return decoderError(fatal);
1696
+ // 7. Return a code point whose value is code point.
1697
+ return code_point;
1698
+ }
1699
+ // 4. If byte is an ASCII byte, return a code point whose value
1700
+ // is byte.
1701
+ if (isASCIIByte(bite))
1702
+ return bite;
1703
+ // 5. If byte is in the range 0x81 to 0xFE, inclusive, set Big5
1704
+ // lead to byte and return continue.
1705
+ if (inRange(bite, 0x81, 0xfe)) {
1706
+ Big5_lead = bite;
1707
+ return null;
1708
+ }
1709
+ // 6. Return error.
1710
+ return decoderError(fatal);
1711
+ };
746
1712
  }
1713
+ // 12.1.2 Big5 encoder
1714
+ /**
1715
+ * @constructor
1716
+ * @implements {Encoder}
1717
+ * @param {{fatal: boolean}} options
1718
+ */
747
1719
  function Big5Encoder(options) {
748
- var fatal = options.fatal;
749
- this.handler = function (stream, code_point) {
750
- if (code_point === end_of_stream) return finished;
751
- if (isASCIICodePoint(code_point)) return code_point;
752
- var pointer = indexBig5PointerFor(code_point);
753
- if (pointer === null) return encoderError(code_point);
754
- var lead = floor(pointer / 157) + 0x81;
755
- if (lead < 0xa1) return encoderError(code_point);
756
- var trail = pointer % 157;
757
- var offset = trail < 0x3f ? 0x40 : 0x62;
758
- return [lead, trail + offset];
759
- };
1720
+ var fatal = options.fatal;
1721
+ /**
1722
+ * @param {Stream} stream Input stream.
1723
+ * @param {number} code_point Next code point read from the stream.
1724
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
1725
+ */
1726
+ this.handler = function (stream, code_point) {
1727
+ // 1. If code point is end-of-stream, return finished.
1728
+ if (code_point === end_of_stream)
1729
+ return finished;
1730
+ // 2. If code point is an ASCII code point, return a byte whose
1731
+ // value is code point.
1732
+ if (isASCIICodePoint(code_point))
1733
+ return code_point;
1734
+ // 3. Let pointer be the index Big5 pointer for code point.
1735
+ var pointer = indexBig5PointerFor(code_point);
1736
+ // 4. If pointer is null, return error with code point.
1737
+ if (pointer === null)
1738
+ return encoderError(code_point);
1739
+ // 5. Let lead be floor(pointer / 157) + 0x81.
1740
+ var lead = floor(pointer / 157) + 0x81;
1741
+ // 6. If lead is less than 0xA1, return error with code point.
1742
+ if (lead < 0xa1)
1743
+ return encoderError(code_point);
1744
+ // 7. Let trail be pointer % 157.
1745
+ var trail = pointer % 157;
1746
+ // 8. Let offset be 0x40 if trail is less than 0x3F and 0x62
1747
+ // otherwise.
1748
+ var offset = trail < 0x3f ? 0x40 : 0x62;
1749
+ // Return two bytes whose values are lead and trail + offset.
1750
+ return [lead, trail + offset];
1751
+ };
760
1752
  }
1753
+ /** @param {{fatal: boolean}} options */
761
1754
  encoders['Big5'] = function (options) {
762
- return new Big5Encoder(options);
1755
+ return new Big5Encoder(options);
763
1756
  };
1757
+ /** @param {{fatal: boolean}} options */
764
1758
  decoders['Big5'] = function (options) {
765
- return new Big5Decoder(options);
1759
+ return new Big5Decoder(options);
766
1760
  };
1761
+ //
1762
+ // 13. Legacy multi-byte Japanese encodings
1763
+ //
1764
+ // 13.1 euc-jp
1765
+ // 13.1.1 euc-jp decoder
1766
+ /**
1767
+ * @constructor
1768
+ * @implements {Decoder}
1769
+ * @param {{fatal: boolean}} options
1770
+ */
767
1771
  function EUCJPDecoder(options) {
768
- var fatal = options.fatal;
769
- var eucjp_jis0212_flag = false,
770
- eucjp_lead = 0x00;
771
- this.handler = function (stream, bite) {
772
- if (bite === end_of_stream && eucjp_lead !== 0x00) {
773
- eucjp_lead = 0x00;
774
- return decoderError(fatal);
775
- }
776
- if (bite === end_of_stream && eucjp_lead === 0x00) return finished;
777
- if (eucjp_lead === 0x8e && inRange(bite, 0xa1, 0xdf)) {
778
- eucjp_lead = 0x00;
779
- return 0xff61 - 0xa1 + bite;
780
- }
781
- if (eucjp_lead === 0x8f && inRange(bite, 0xa1, 0xfe)) {
782
- eucjp_jis0212_flag = true;
783
- eucjp_lead = bite;
784
- return null;
785
- }
786
- if (eucjp_lead !== 0x00) {
787
- var lead = eucjp_lead;
788
- eucjp_lead = 0x00;
789
- var code_point = null;
790
- if (inRange(lead, 0xa1, 0xfe) && inRange(bite, 0xa1, 0xfe)) {
791
- code_point = indexCodePointFor((lead - 0xa1) * 94 + (bite - 0xa1), index(!eucjp_jis0212_flag ? 'jis0208' : 'jis0212'));
792
- }
793
- eucjp_jis0212_flag = false;
794
- if (!inRange(bite, 0xa1, 0xfe)) stream.prepend(bite);
795
- if (code_point === null) return decoderError(fatal);
796
- return code_point;
797
- }
798
- if (isASCIIByte(bite)) return bite;
799
- if (bite === 0x8e || bite === 0x8f || inRange(bite, 0xa1, 0xfe)) {
800
- eucjp_lead = bite;
801
- return null;
802
- }
803
- return decoderError(fatal);
804
- };
1772
+ var fatal = options.fatal;
1773
+ // euc-jp's decoder has an associated euc-jp jis0212 flag
1774
+ // (initially unset) and euc-jp lead (initially 0x00).
1775
+ var /** @type {boolean} */ eucjp_jis0212_flag = false,
1776
+ /** @type {number} */ eucjp_lead = 0x00;
1777
+ /**
1778
+ * @param {Stream} stream The stream of bytes being decoded.
1779
+ * @param {number} bite The next byte read from the stream.
1780
+ * @return {?(number|!Array.<number>)} The next code point(s)
1781
+ * decoded, or null if not enough data exists in the input
1782
+ * stream to decode a complete code point.
1783
+ */
1784
+ this.handler = function (stream, bite) {
1785
+ // 1. If byte is end-of-stream and euc-jp lead is not 0x00, set
1786
+ // euc-jp lead to 0x00, and return error.
1787
+ if (bite === end_of_stream && eucjp_lead !== 0x00) {
1788
+ eucjp_lead = 0x00;
1789
+ return decoderError(fatal);
1790
+ }
1791
+ // 2. If byte is end-of-stream and euc-jp lead is 0x00, return
1792
+ // finished.
1793
+ if (bite === end_of_stream && eucjp_lead === 0x00)
1794
+ return finished;
1795
+ // 3. If euc-jp lead is 0x8E and byte is in the range 0xA1 to
1796
+ // 0xDF, inclusive, set euc-jp lead to 0x00 and return a code
1797
+ // point whose value is 0xFF61 − 0xA1 + byte.
1798
+ if (eucjp_lead === 0x8e && inRange(bite, 0xa1, 0xdf)) {
1799
+ eucjp_lead = 0x00;
1800
+ return 0xff61 - 0xa1 + bite;
1801
+ }
1802
+ // 4. If euc-jp lead is 0x8F and byte is in the range 0xA1 to
1803
+ // 0xFE, inclusive, set the euc-jp jis0212 flag, set euc-jp lead
1804
+ // to byte, and return continue.
1805
+ if (eucjp_lead === 0x8f && inRange(bite, 0xa1, 0xfe)) {
1806
+ eucjp_jis0212_flag = true;
1807
+ eucjp_lead = bite;
1808
+ return null;
1809
+ }
1810
+ // 5. If euc-jp lead is not 0x00, let lead be euc-jp lead, set
1811
+ // euc-jp lead to 0x00, and run these substeps:
1812
+ if (eucjp_lead !== 0x00) {
1813
+ var lead = eucjp_lead;
1814
+ eucjp_lead = 0x00;
1815
+ // 1. Let code point be null.
1816
+ var code_point = null;
1817
+ // 2. If lead and byte are both in the range 0xA1 to 0xFE,
1818
+ // inclusive, set code point to the index code point for (lead
1819
+ // − 0xA1) × 94 + byte − 0xA1 in index jis0208 if the euc-jp
1820
+ // jis0212 flag is unset and in index jis0212 otherwise.
1821
+ if (inRange(lead, 0xa1, 0xfe) && inRange(bite, 0xa1, 0xfe)) {
1822
+ code_point = indexCodePointFor((lead - 0xa1) * 94 + (bite - 0xa1), index(!eucjp_jis0212_flag ? 'jis0208' : 'jis0212'));
1823
+ }
1824
+ // 3. Unset the euc-jp jis0212 flag.
1825
+ eucjp_jis0212_flag = false;
1826
+ // 4. If byte is not in the range 0xA1 to 0xFE, inclusive,
1827
+ // prepend byte to stream.
1828
+ if (!inRange(bite, 0xa1, 0xfe))
1829
+ stream.prepend(bite);
1830
+ // 5. If code point is null, return error.
1831
+ if (code_point === null)
1832
+ return decoderError(fatal);
1833
+ // 6. Return a code point whose value is code point.
1834
+ return code_point;
1835
+ }
1836
+ // 6. If byte is an ASCII byte, return a code point whose value
1837
+ // is byte.
1838
+ if (isASCIIByte(bite))
1839
+ return bite;
1840
+ // 7. If byte is 0x8E, 0x8F, or in the range 0xA1 to 0xFE,
1841
+ // inclusive, set euc-jp lead to byte and return continue.
1842
+ if (bite === 0x8e || bite === 0x8f || inRange(bite, 0xa1, 0xfe)) {
1843
+ eucjp_lead = bite;
1844
+ return null;
1845
+ }
1846
+ // 8. Return error.
1847
+ return decoderError(fatal);
1848
+ };
805
1849
  }
1850
+ // 13.1.2 euc-jp encoder
1851
+ /**
1852
+ * @constructor
1853
+ * @implements {Encoder}
1854
+ * @param {{fatal: boolean}} options
1855
+ */
806
1856
  function EUCJPEncoder(options) {
807
- var fatal = options.fatal;
808
- this.handler = function (stream, code_point) {
809
- if (code_point === end_of_stream) return finished;
810
- if (isASCIICodePoint(code_point)) return code_point;
811
- if (code_point === 0x00a5) return 0x5c;
812
- if (code_point === 0x203e) return 0x7e;
813
- if (inRange(code_point, 0xff61, 0xff9f)) return [0x8e, code_point - 0xff61 + 0xa1];
814
- if (code_point === 0x2212) code_point = 0xff0d;
815
- var pointer = indexPointerFor(code_point, index('jis0208'));
816
- if (pointer === null) return encoderError(code_point);
817
- var lead = floor(pointer / 94) + 0xa1;
818
- var trail = pointer % 94 + 0xa1;
819
- return [lead, trail];
820
- };
1857
+ var fatal = options.fatal;
1858
+ /**
1859
+ * @param {Stream} stream Input stream.
1860
+ * @param {number} code_point Next code point read from the stream.
1861
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
1862
+ */
1863
+ this.handler = function (stream, code_point) {
1864
+ // 1. If code point is end-of-stream, return finished.
1865
+ if (code_point === end_of_stream)
1866
+ return finished;
1867
+ // 2. If code point is an ASCII code point, return a byte whose
1868
+ // value is code point.
1869
+ if (isASCIICodePoint(code_point))
1870
+ return code_point;
1871
+ // 3. If code point is U+00A5, return byte 0x5C.
1872
+ if (code_point === 0x00a5)
1873
+ return 0x5c;
1874
+ // 4. If code point is U+203E, return byte 0x7E.
1875
+ if (code_point === 0x203e)
1876
+ return 0x7e;
1877
+ // 5. If code point is in the range U+FF61 to U+FF9F, inclusive,
1878
+ // return two bytes whose values are 0x8E and code point −
1879
+ // 0xFF61 + 0xA1.
1880
+ if (inRange(code_point, 0xff61, 0xff9f))
1881
+ return [0x8e, code_point - 0xff61 + 0xa1];
1882
+ // 6. If code point is U+2212, set it to U+FF0D.
1883
+ if (code_point === 0x2212)
1884
+ code_point = 0xff0d;
1885
+ // 7. Let pointer be the index pointer for code point in index
1886
+ // jis0208.
1887
+ var pointer = indexPointerFor(code_point, index('jis0208'));
1888
+ // 8. If pointer is null, return error with code point.
1889
+ if (pointer === null)
1890
+ return encoderError(code_point);
1891
+ // 9. Let lead be floor(pointer / 94) + 0xA1.
1892
+ var lead = floor(pointer / 94) + 0xa1;
1893
+ // 10. Let trail be pointer % 94 + 0xA1.
1894
+ var trail = (pointer % 94) + 0xa1;
1895
+ // 11. Return two bytes whose values are lead and trail.
1896
+ return [lead, trail];
1897
+ };
821
1898
  }
1899
+ /** @param {{fatal: boolean}} options */
822
1900
  encoders['EUC-JP'] = function (options) {
823
- return new EUCJPEncoder(options);
1901
+ return new EUCJPEncoder(options);
824
1902
  };
1903
+ /** @param {{fatal: boolean}} options */
825
1904
  decoders['EUC-JP'] = function (options) {
826
- return new EUCJPDecoder(options);
1905
+ return new EUCJPDecoder(options);
827
1906
  };
1907
+ // 13.2 iso-2022-jp
1908
+ // 13.2.1 iso-2022-jp decoder
1909
+ /**
1910
+ * @constructor
1911
+ * @implements {Decoder}
1912
+ * @param {{fatal: boolean}} options
1913
+ */
828
1914
  function ISO2022JPDecoder(options) {
829
- var fatal = options.fatal;
830
- var states = {
831
- ASCII: 0,
832
- Roman: 1,
833
- Katakana: 2,
834
- LeadByte: 3,
835
- TrailByte: 4,
836
- EscapeStart: 5,
837
- Escape: 6
838
- };
839
- var iso2022jp_decoder_state = states.ASCII,
840
- iso2022jp_decoder_output_state = states.ASCII,
841
- iso2022jp_lead = 0x00,
842
- iso2022jp_output_flag = false;
843
- this.handler = function (stream, bite) {
844
- switch (iso2022jp_decoder_state) {
845
- default:
846
- case states.ASCII:
847
- if (bite === 0x1b) {
848
- iso2022jp_decoder_state = states.EscapeStart;
849
- return null;
850
- }
851
- if (inRange(bite, 0x00, 0x7f) && bite !== 0x0e && bite !== 0x0f && bite !== 0x1b) {
852
- iso2022jp_output_flag = false;
853
- return bite;
854
- }
855
- if (bite === end_of_stream) {
856
- return finished;
857
- }
858
- iso2022jp_output_flag = false;
859
- return decoderError(fatal);
860
- case states.Roman:
861
- if (bite === 0x1b) {
862
- iso2022jp_decoder_state = states.EscapeStart;
863
- return null;
864
- }
865
- if (bite === 0x5c) {
866
- iso2022jp_output_flag = false;
867
- return 0x00a5;
1915
+ var fatal = options.fatal;
1916
+ /** @enum */
1917
+ var states = {
1918
+ ASCII: 0,
1919
+ Roman: 1,
1920
+ Katakana: 2,
1921
+ LeadByte: 3,
1922
+ TrailByte: 4,
1923
+ EscapeStart: 5,
1924
+ Escape: 6
1925
+ };
1926
+ // iso-2022-jp's decoder has an associated iso-2022-jp decoder
1927
+ // state (initially ASCII), iso-2022-jp decoder output state
1928
+ // (initially ASCII), iso-2022-jp lead (initially 0x00), and
1929
+ // iso-2022-jp output flag (initially unset).
1930
+ var /** @type {number} */ iso2022jp_decoder_state = states.ASCII,
1931
+ /** @type {number} */ iso2022jp_decoder_output_state = states.ASCII,
1932
+ /** @type {number} */ iso2022jp_lead = 0x00,
1933
+ /** @type {boolean} */ iso2022jp_output_flag = false;
1934
+ /**
1935
+ * @param {Stream} stream The stream of bytes being decoded.
1936
+ * @param {number} bite The next byte read from the stream.
1937
+ * @return {?(number|!Array.<number>)} The next code point(s)
1938
+ * decoded, or null if not enough data exists in the input
1939
+ * stream to decode a complete code point.
1940
+ */
1941
+ this.handler = function (stream, bite) {
1942
+ // switching on iso-2022-jp decoder state:
1943
+ switch (iso2022jp_decoder_state) {
1944
+ default:
1945
+ case states.ASCII:
1946
+ // ASCII
1947
+ // Based on byte:
1948
+ // 0x1B
1949
+ if (bite === 0x1b) {
1950
+ // Set iso-2022-jp decoder state to escape start and return
1951
+ // continue.
1952
+ iso2022jp_decoder_state = states.EscapeStart;
1953
+ return null;
1954
+ }
1955
+ // 0x00 to 0x7F, excluding 0x0E, 0x0F, and 0x1B
1956
+ if (inRange(bite, 0x00, 0x7f) && bite !== 0x0e && bite !== 0x0f && bite !== 0x1b) {
1957
+ // Unset the iso-2022-jp output flag and return a code point
1958
+ // whose value is byte.
1959
+ iso2022jp_output_flag = false;
1960
+ return bite;
1961
+ }
1962
+ // end-of-stream
1963
+ if (bite === end_of_stream) {
1964
+ // Return finished.
1965
+ return finished;
1966
+ }
1967
+ // Otherwise
1968
+ // Unset the iso-2022-jp output flag and return error.
1969
+ iso2022jp_output_flag = false;
1970
+ return decoderError(fatal);
1971
+ case states.Roman:
1972
+ // Roman
1973
+ // Based on byte:
1974
+ // 0x1B
1975
+ if (bite === 0x1b) {
1976
+ // Set iso-2022-jp decoder state to escape start and return
1977
+ // continue.
1978
+ iso2022jp_decoder_state = states.EscapeStart;
1979
+ return null;
1980
+ }
1981
+ // 0x5C
1982
+ if (bite === 0x5c) {
1983
+ // Unset the iso-2022-jp output flag and return code point
1984
+ // U+00A5.
1985
+ iso2022jp_output_flag = false;
1986
+ return 0x00a5;
1987
+ }
1988
+ // 0x7E
1989
+ if (bite === 0x7e) {
1990
+ // Unset the iso-2022-jp output flag and return code point
1991
+ // U+203E.
1992
+ iso2022jp_output_flag = false;
1993
+ return 0x203e;
1994
+ }
1995
+ // 0x00 to 0x7F, excluding 0x0E, 0x0F, 0x1B, 0x5C, and 0x7E
1996
+ if (inRange(bite, 0x00, 0x7f) &&
1997
+ bite !== 0x0e &&
1998
+ bite !== 0x0f &&
1999
+ bite !== 0x1b &&
2000
+ bite !== 0x5c &&
2001
+ bite !== 0x7e) {
2002
+ // Unset the iso-2022-jp output flag and return a code point
2003
+ // whose value is byte.
2004
+ iso2022jp_output_flag = false;
2005
+ return bite;
2006
+ }
2007
+ // end-of-stream
2008
+ if (bite === end_of_stream) {
2009
+ // Return finished.
2010
+ return finished;
2011
+ }
2012
+ // Otherwise
2013
+ // Unset the iso-2022-jp output flag and return error.
2014
+ iso2022jp_output_flag = false;
2015
+ return decoderError(fatal);
2016
+ case states.Katakana:
2017
+ // Katakana
2018
+ // Based on byte:
2019
+ // 0x1B
2020
+ if (bite === 0x1b) {
2021
+ // Set iso-2022-jp decoder state to escape start and return
2022
+ // continue.
2023
+ iso2022jp_decoder_state = states.EscapeStart;
2024
+ return null;
2025
+ }
2026
+ // 0x21 to 0x5F
2027
+ if (inRange(bite, 0x21, 0x5f)) {
2028
+ // Unset the iso-2022-jp output flag and return a code point
2029
+ // whose value is 0xFF61 − 0x21 + byte.
2030
+ iso2022jp_output_flag = false;
2031
+ return 0xff61 - 0x21 + bite;
2032
+ }
2033
+ // end-of-stream
2034
+ if (bite === end_of_stream) {
2035
+ // Return finished.
2036
+ return finished;
2037
+ }
2038
+ // Otherwise
2039
+ // Unset the iso-2022-jp output flag and return error.
2040
+ iso2022jp_output_flag = false;
2041
+ return decoderError(fatal);
2042
+ case states.LeadByte:
2043
+ // Lead byte
2044
+ // Based on byte:
2045
+ // 0x1B
2046
+ if (bite === 0x1b) {
2047
+ // Set iso-2022-jp decoder state to escape start and return
2048
+ // continue.
2049
+ iso2022jp_decoder_state = states.EscapeStart;
2050
+ return null;
2051
+ }
2052
+ // 0x21 to 0x7E
2053
+ if (inRange(bite, 0x21, 0x7e)) {
2054
+ // Unset the iso-2022-jp output flag, set iso-2022-jp lead
2055
+ // to byte, iso-2022-jp decoder state to trail byte, and
2056
+ // return continue.
2057
+ iso2022jp_output_flag = false;
2058
+ iso2022jp_lead = bite;
2059
+ iso2022jp_decoder_state = states.TrailByte;
2060
+ return null;
2061
+ }
2062
+ // end-of-stream
2063
+ if (bite === end_of_stream) {
2064
+ // Return finished.
2065
+ return finished;
2066
+ }
2067
+ // Otherwise
2068
+ // Unset the iso-2022-jp output flag and return error.
2069
+ iso2022jp_output_flag = false;
2070
+ return decoderError(fatal);
2071
+ case states.TrailByte:
2072
+ // Trail byte
2073
+ // Based on byte:
2074
+ // 0x1B
2075
+ if (bite === 0x1b) {
2076
+ // Set iso-2022-jp decoder state to escape start and return
2077
+ // continue.
2078
+ iso2022jp_decoder_state = states.EscapeStart;
2079
+ return decoderError(fatal);
2080
+ }
2081
+ // 0x21 to 0x7E
2082
+ if (inRange(bite, 0x21, 0x7e)) {
2083
+ // 1. Set the iso-2022-jp decoder state to lead byte.
2084
+ iso2022jp_decoder_state = states.LeadByte;
2085
+ // 2. Let pointer be (iso-2022-jp lead − 0x21) × 94 + byte − 0x21.
2086
+ var pointer = (iso2022jp_lead - 0x21) * 94 + bite - 0x21;
2087
+ // 3. Let code point be the index code point for pointer in
2088
+ // index jis0208.
2089
+ var code_point = indexCodePointFor(pointer, index('jis0208'));
2090
+ // 4. If code point is null, return error.
2091
+ if (code_point === null)
2092
+ return decoderError(fatal);
2093
+ // 5. Return a code point whose value is code point.
2094
+ return code_point;
2095
+ }
2096
+ // end-of-stream
2097
+ if (bite === end_of_stream) {
2098
+ // Set the iso-2022-jp decoder state to lead byte, prepend
2099
+ // byte to stream, and return error.
2100
+ iso2022jp_decoder_state = states.LeadByte;
2101
+ stream.prepend(bite);
2102
+ return decoderError(fatal);
2103
+ }
2104
+ // Otherwise
2105
+ // Set iso-2022-jp decoder state to lead byte and return
2106
+ // error.
2107
+ iso2022jp_decoder_state = states.LeadByte;
2108
+ return decoderError(fatal);
2109
+ case states.EscapeStart:
2110
+ // Escape start
2111
+ // 1. If byte is either 0x24 or 0x28, set iso-2022-jp lead to
2112
+ // byte, iso-2022-jp decoder state to escape, and return
2113
+ // continue.
2114
+ if (bite === 0x24 || bite === 0x28) {
2115
+ iso2022jp_lead = bite;
2116
+ iso2022jp_decoder_state = states.Escape;
2117
+ return null;
2118
+ }
2119
+ // 2. Prepend byte to stream.
2120
+ stream.prepend(bite);
2121
+ // 3. Unset the iso-2022-jp output flag, set iso-2022-jp
2122
+ // decoder state to iso-2022-jp decoder output state, and
2123
+ // return error.
2124
+ iso2022jp_output_flag = false;
2125
+ iso2022jp_decoder_state = iso2022jp_decoder_output_state;
2126
+ return decoderError(fatal);
2127
+ case states.Escape:
2128
+ // Escape
2129
+ // 1. Let lead be iso-2022-jp lead and set iso-2022-jp lead to
2130
+ // 0x00.
2131
+ var lead = iso2022jp_lead;
2132
+ iso2022jp_lead = 0x00;
2133
+ // 2. Let state be null.
2134
+ var state = null;
2135
+ // 3. If lead is 0x28 and byte is 0x42, set state to ASCII.
2136
+ if (lead === 0x28 && bite === 0x42)
2137
+ state = states.ASCII;
2138
+ // 4. If lead is 0x28 and byte is 0x4A, set state to Roman.
2139
+ if (lead === 0x28 && bite === 0x4a)
2140
+ state = states.Roman;
2141
+ // 5. If lead is 0x28 and byte is 0x49, set state to Katakana.
2142
+ if (lead === 0x28 && bite === 0x49)
2143
+ state = states.Katakana;
2144
+ // 6. If lead is 0x24 and byte is either 0x40 or 0x42, set
2145
+ // state to lead byte.
2146
+ if (lead === 0x24 && (bite === 0x40 || bite === 0x42))
2147
+ state = states.LeadByte;
2148
+ // 7. If state is non-null, run these substeps:
2149
+ if (state !== null) {
2150
+ // 1. Set iso-2022-jp decoder state and iso-2022-jp decoder
2151
+ // output state to states.
2152
+ iso2022jp_decoder_state = iso2022jp_decoder_state = state;
2153
+ // 2. Let output flag be the iso-2022-jp output flag.
2154
+ var output_flag = iso2022jp_output_flag;
2155
+ // 3. Set the iso-2022-jp output flag.
2156
+ iso2022jp_output_flag = true;
2157
+ // 4. Return continue, if output flag is unset, and error
2158
+ // otherwise.
2159
+ return !output_flag ? null : decoderError(fatal);
2160
+ }
2161
+ // 8. Prepend lead and byte to stream.
2162
+ stream.prepend([lead, bite]);
2163
+ // 9. Unset the iso-2022-jp output flag, set iso-2022-jp
2164
+ // decoder state to iso-2022-jp decoder output state and
2165
+ // return error.
2166
+ iso2022jp_output_flag = false;
2167
+ iso2022jp_decoder_state = iso2022jp_decoder_output_state;
2168
+ return decoderError(fatal);
868
2169
  }
869
- if (bite === 0x7e) {
870
- iso2022jp_output_flag = false;
871
- return 0x203e;
872
- }
873
- if (inRange(bite, 0x00, 0x7f) && bite !== 0x0e && bite !== 0x0f && bite !== 0x1b && bite !== 0x5c && bite !== 0x7e) {
874
- iso2022jp_output_flag = false;
875
- return bite;
876
- }
877
- if (bite === end_of_stream) {
878
- return finished;
879
- }
880
- iso2022jp_output_flag = false;
881
- return decoderError(fatal);
882
- case states.Katakana:
883
- if (bite === 0x1b) {
884
- iso2022jp_decoder_state = states.EscapeStart;
885
- return null;
2170
+ };
2171
+ }
2172
+ // 13.2.2 iso-2022-jp encoder
2173
+ /**
2174
+ * @constructor
2175
+ * @implements {Encoder}
2176
+ * @param {{fatal: boolean}} options
2177
+ */
2178
+ function ISO2022JPEncoder(options) {
2179
+ var fatal = options.fatal;
2180
+ // iso-2022-jp's encoder has an associated iso-2022-jp encoder
2181
+ // state which is one of ASCII, Roman, and jis0208 (initially
2182
+ // ASCII).
2183
+ /** @enum */
2184
+ var states = {
2185
+ ASCII: 0,
2186
+ Roman: 1,
2187
+ jis0208: 2
2188
+ };
2189
+ var /** @type {number} */ iso2022jp_state = states.ASCII;
2190
+ /**
2191
+ * @param {Stream} stream Input stream.
2192
+ * @param {number} code_point Next code point read from the stream.
2193
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
2194
+ */
2195
+ this.handler = function (stream, code_point) {
2196
+ // 1. If code point is end-of-stream and iso-2022-jp encoder
2197
+ // state is not ASCII, prepend code point to stream, set
2198
+ // iso-2022-jp encoder state to ASCII, and return three bytes
2199
+ // 0x1B 0x28 0x42.
2200
+ if (code_point === end_of_stream && iso2022jp_state !== states.ASCII) {
2201
+ stream.prepend(code_point);
2202
+ iso2022jp_state = states.ASCII;
2203
+ return [0x1b, 0x28, 0x42];
886
2204
  }
887
- if (inRange(bite, 0x21, 0x5f)) {
888
- iso2022jp_output_flag = false;
889
- return 0xff61 - 0x21 + bite;
2205
+ // 2. If code point is end-of-stream and iso-2022-jp encoder
2206
+ // state is ASCII, return finished.
2207
+ if (code_point === end_of_stream && iso2022jp_state === states.ASCII)
2208
+ return finished;
2209
+ // 3. If ISO-2022-JP encoder state is ASCII or Roman, and code
2210
+ // point is U+000E, U+000F, or U+001B, return error with U+FFFD.
2211
+ if ((iso2022jp_state === states.ASCII || iso2022jp_state === states.Roman) &&
2212
+ (code_point === 0x000e || code_point === 0x000f || code_point === 0x001b)) {
2213
+ return encoderError(0xfffd);
890
2214
  }
891
- if (bite === end_of_stream) {
892
- return finished;
2215
+ // 4. If iso-2022-jp encoder state is ASCII and code point is an
2216
+ // ASCII code point, return a byte whose value is code point.
2217
+ if (iso2022jp_state === states.ASCII && isASCIICodePoint(code_point))
2218
+ return code_point;
2219
+ // 5. If iso-2022-jp encoder state is Roman and code point is an
2220
+ // ASCII code point, excluding U+005C and U+007E, or is U+00A5
2221
+ // or U+203E, run these substeps:
2222
+ if (iso2022jp_state === states.Roman &&
2223
+ ((isASCIICodePoint(code_point) && code_point !== 0x005c && code_point !== 0x007e) ||
2224
+ code_point == 0x00a5 ||
2225
+ code_point == 0x203e)) {
2226
+ // 1. If code point is an ASCII code point, return a byte
2227
+ // whose value is code point.
2228
+ if (isASCIICodePoint(code_point))
2229
+ return code_point;
2230
+ // 2. If code point is U+00A5, return byte 0x5C.
2231
+ if (code_point === 0x00a5)
2232
+ return 0x5c;
2233
+ // 3. If code point is U+203E, return byte 0x7E.
2234
+ if (code_point === 0x203e)
2235
+ return 0x7e;
893
2236
  }
894
- iso2022jp_output_flag = false;
895
- return decoderError(fatal);
896
- case states.LeadByte:
897
- if (bite === 0x1b) {
898
- iso2022jp_decoder_state = states.EscapeStart;
899
- return null;
2237
+ // 6. If code point is an ASCII code point, and iso-2022-jp
2238
+ // encoder state is not ASCII, prepend code point to stream, set
2239
+ // iso-2022-jp encoder state to ASCII, and return three bytes
2240
+ // 0x1B 0x28 0x42.
2241
+ if (isASCIICodePoint(code_point) && iso2022jp_state !== states.ASCII) {
2242
+ stream.prepend(code_point);
2243
+ iso2022jp_state = states.ASCII;
2244
+ return [0x1b, 0x28, 0x42];
900
2245
  }
901
- if (inRange(bite, 0x21, 0x7e)) {
902
- iso2022jp_output_flag = false;
903
- iso2022jp_lead = bite;
904
- iso2022jp_decoder_state = states.TrailByte;
905
- return null;
2246
+ // 7. If code point is either U+00A5 or U+203E, and iso-2022-jp
2247
+ // encoder state is not Roman, prepend code point to stream, set
2248
+ // iso-2022-jp encoder state to Roman, and return three bytes
2249
+ // 0x1B 0x28 0x4A.
2250
+ if ((code_point === 0x00a5 || code_point === 0x203e) && iso2022jp_state !== states.Roman) {
2251
+ stream.prepend(code_point);
2252
+ iso2022jp_state = states.Roman;
2253
+ return [0x1b, 0x28, 0x4a];
906
2254
  }
907
- if (bite === end_of_stream) {
908
- return finished;
2255
+ // 8. If code point is U+2212, set it to U+FF0D.
2256
+ if (code_point === 0x2212)
2257
+ code_point = 0xff0d;
2258
+ // 9. Let pointer be the index pointer for code point in index
2259
+ // jis0208.
2260
+ var pointer = indexPointerFor(code_point, index('jis0208'));
2261
+ // 10. If pointer is null, return error with code point.
2262
+ if (pointer === null)
2263
+ return encoderError(code_point);
2264
+ // 11. If iso-2022-jp encoder state is not jis0208, prepend code
2265
+ // point to stream, set iso-2022-jp encoder state to jis0208,
2266
+ // and return three bytes 0x1B 0x24 0x42.
2267
+ if (iso2022jp_state !== states.jis0208) {
2268
+ stream.prepend(code_point);
2269
+ iso2022jp_state = states.jis0208;
2270
+ return [0x1b, 0x24, 0x42];
909
2271
  }
910
- iso2022jp_output_flag = false;
911
- return decoderError(fatal);
912
- case states.TrailByte:
913
- if (bite === 0x1b) {
914
- iso2022jp_decoder_state = states.EscapeStart;
915
- return decoderError(fatal);
916
- }
917
- if (inRange(bite, 0x21, 0x7e)) {
918
- iso2022jp_decoder_state = states.LeadByte;
919
- var pointer = (iso2022jp_lead - 0x21) * 94 + bite - 0x21;
920
- var code_point = indexCodePointFor(pointer, index('jis0208'));
921
- if (code_point === null) return decoderError(fatal);
922
- return code_point;
923
- }
924
- if (bite === end_of_stream) {
925
- iso2022jp_decoder_state = states.LeadByte;
926
- stream.prepend(bite);
927
- return decoderError(fatal);
928
- }
929
- iso2022jp_decoder_state = states.LeadByte;
930
- return decoderError(fatal);
931
- case states.EscapeStart:
932
- if (bite === 0x24 || bite === 0x28) {
933
- iso2022jp_lead = bite;
934
- iso2022jp_decoder_state = states.Escape;
935
- return null;
936
- }
937
- stream.prepend(bite);
938
- iso2022jp_output_flag = false;
939
- iso2022jp_decoder_state = iso2022jp_decoder_output_state;
940
- return decoderError(fatal);
941
- case states.Escape:
942
- var lead = iso2022jp_lead;
943
- iso2022jp_lead = 0x00;
944
- var state = null;
945
- if (lead === 0x28 && bite === 0x42) state = states.ASCII;
946
- if (lead === 0x28 && bite === 0x4a) state = states.Roman;
947
- if (lead === 0x28 && bite === 0x49) state = states.Katakana;
948
- if (lead === 0x24 && (bite === 0x40 || bite === 0x42)) state = states.LeadByte;
949
- if (state !== null) {
950
- iso2022jp_decoder_state = iso2022jp_decoder_state = state;
951
- var output_flag = iso2022jp_output_flag;
952
- iso2022jp_output_flag = true;
953
- return !output_flag ? null : decoderError(fatal);
954
- }
955
- stream.prepend([lead, bite]);
956
- iso2022jp_output_flag = false;
957
- iso2022jp_decoder_state = iso2022jp_decoder_output_state;
958
- return decoderError(fatal);
959
- }
960
- };
961
- }
962
- function ISO2022JPEncoder(options) {
963
- var fatal = options.fatal;
964
- var states = {
965
- ASCII: 0,
966
- Roman: 1,
967
- jis0208: 2
968
- };
969
- var iso2022jp_state = states.ASCII;
970
- this.handler = function (stream, code_point) {
971
- if (code_point === end_of_stream && iso2022jp_state !== states.ASCII) {
972
- stream.prepend(code_point);
973
- iso2022jp_state = states.ASCII;
974
- return [0x1b, 0x28, 0x42];
975
- }
976
- if (code_point === end_of_stream && iso2022jp_state === states.ASCII) return finished;
977
- if ((iso2022jp_state === states.ASCII || iso2022jp_state === states.Roman) && (code_point === 0x000e || code_point === 0x000f || code_point === 0x001b)) {
978
- return encoderError(0xfffd);
979
- }
980
- if (iso2022jp_state === states.ASCII && isASCIICodePoint(code_point)) return code_point;
981
- if (iso2022jp_state === states.Roman && (isASCIICodePoint(code_point) && code_point !== 0x005c && code_point !== 0x007e || code_point == 0x00a5 || code_point == 0x203e)) {
982
- if (isASCIICodePoint(code_point)) return code_point;
983
- if (code_point === 0x00a5) return 0x5c;
984
- if (code_point === 0x203e) return 0x7e;
985
- }
986
- if (isASCIICodePoint(code_point) && iso2022jp_state !== states.ASCII) {
987
- stream.prepend(code_point);
988
- iso2022jp_state = states.ASCII;
989
- return [0x1b, 0x28, 0x42];
990
- }
991
- if ((code_point === 0x00a5 || code_point === 0x203e) && iso2022jp_state !== states.Roman) {
992
- stream.prepend(code_point);
993
- iso2022jp_state = states.Roman;
994
- return [0x1b, 0x28, 0x4a];
995
- }
996
- if (code_point === 0x2212) code_point = 0xff0d;
997
- var pointer = indexPointerFor(code_point, index('jis0208'));
998
- if (pointer === null) return encoderError(code_point);
999
- if (iso2022jp_state !== states.jis0208) {
1000
- stream.prepend(code_point);
1001
- iso2022jp_state = states.jis0208;
1002
- return [0x1b, 0x24, 0x42];
1003
- }
1004
- var lead = floor(pointer / 94) + 0x21;
1005
- var trail = pointer % 94 + 0x21;
1006
- return [lead, trail];
1007
- };
2272
+ // 12. Let lead be floor(pointer / 94) + 0x21.
2273
+ var lead = floor(pointer / 94) + 0x21;
2274
+ // 13. Let trail be pointer % 94 + 0x21.
2275
+ var trail = (pointer % 94) + 0x21;
2276
+ // 14. Return two bytes whose values are lead and trail.
2277
+ return [lead, trail];
2278
+ };
1008
2279
  }
2280
+ /** @param {{fatal: boolean}} options */
1009
2281
  encoders['ISO-2022-JP'] = function (options) {
1010
- return new ISO2022JPEncoder(options);
2282
+ return new ISO2022JPEncoder(options);
1011
2283
  };
2284
+ /** @param {{fatal: boolean}} options */
1012
2285
  decoders['ISO-2022-JP'] = function (options) {
1013
- return new ISO2022JPDecoder(options);
2286
+ return new ISO2022JPDecoder(options);
1014
2287
  };
2288
+ // 13.3 Shift_JIS
2289
+ // 13.3.1 Shift_JIS decoder
2290
+ /**
2291
+ * @constructor
2292
+ * @implements {Decoder}
2293
+ * @param {{fatal: boolean}} options
2294
+ */
1015
2295
  function ShiftJISDecoder(options) {
1016
- var fatal = options.fatal;
1017
- var Shift_JIS_lead = 0x00;
1018
- this.handler = function (stream, bite) {
1019
- if (bite === end_of_stream && Shift_JIS_lead !== 0x00) {
1020
- Shift_JIS_lead = 0x00;
1021
- return decoderError(fatal);
1022
- }
1023
- if (bite === end_of_stream && Shift_JIS_lead === 0x00) return finished;
1024
- if (Shift_JIS_lead !== 0x00) {
1025
- var lead = Shift_JIS_lead;
1026
- var pointer = null;
1027
- Shift_JIS_lead = 0x00;
1028
- var offset = bite < 0x7f ? 0x40 : 0x41;
1029
- var lead_offset = lead < 0xa0 ? 0x81 : 0xc1;
1030
- if (inRange(bite, 0x40, 0x7e) || inRange(bite, 0x80, 0xfc)) pointer = (lead - lead_offset) * 188 + bite - offset;
1031
- if (inRange(pointer, 8836, 10715)) return 0xe000 - 8836 + pointer;
1032
- var code_point = pointer === null ? null : indexCodePointFor(pointer, index('jis0208'));
1033
- if (code_point === null && isASCIIByte(bite)) stream.prepend(bite);
1034
- if (code_point === null) return decoderError(fatal);
1035
- return code_point;
1036
- }
1037
- if (isASCIIByte(bite) || bite === 0x80) return bite;
1038
- if (inRange(bite, 0xa1, 0xdf)) return 0xff61 - 0xa1 + bite;
1039
- if (inRange(bite, 0x81, 0x9f) || inRange(bite, 0xe0, 0xfc)) {
1040
- Shift_JIS_lead = bite;
1041
- return null;
1042
- }
1043
- return decoderError(fatal);
1044
- };
2296
+ var fatal = options.fatal;
2297
+ // Shift_JIS's decoder has an associated Shift_JIS lead (initially
2298
+ // 0x00).
2299
+ var /** @type {number} */ Shift_JIS_lead = 0x00;
2300
+ /**
2301
+ * @param {Stream} stream The stream of bytes being decoded.
2302
+ * @param {number} bite The next byte read from the stream.
2303
+ * @return {?(number|!Array.<number>)} The next code point(s)
2304
+ * decoded, or null if not enough data exists in the input
2305
+ * stream to decode a complete code point.
2306
+ */
2307
+ this.handler = function (stream, bite) {
2308
+ // 1. If byte is end-of-stream and Shift_JIS lead is not 0x00,
2309
+ // set Shift_JIS lead to 0x00 and return error.
2310
+ if (bite === end_of_stream && Shift_JIS_lead !== 0x00) {
2311
+ Shift_JIS_lead = 0x00;
2312
+ return decoderError(fatal);
2313
+ }
2314
+ // 2. If byte is end-of-stream and Shift_JIS lead is 0x00,
2315
+ // return finished.
2316
+ if (bite === end_of_stream && Shift_JIS_lead === 0x00)
2317
+ return finished;
2318
+ // 3. If Shift_JIS lead is not 0x00, let lead be Shift_JIS lead,
2319
+ // let pointer be null, set Shift_JIS lead to 0x00, and then run
2320
+ // these substeps:
2321
+ if (Shift_JIS_lead !== 0x00) {
2322
+ var lead = Shift_JIS_lead;
2323
+ var pointer = null;
2324
+ Shift_JIS_lead = 0x00;
2325
+ // 1. Let offset be 0x40, if byte is less than 0x7F, and 0x41
2326
+ // otherwise.
2327
+ var offset = bite < 0x7f ? 0x40 : 0x41;
2328
+ // 2. Let lead offset be 0x81, if lead is less than 0xA0, and
2329
+ // 0xC1 otherwise.
2330
+ var lead_offset = lead < 0xa0 ? 0x81 : 0xc1;
2331
+ // 3. If byte is in the range 0x40 to 0x7E, inclusive, or 0x80
2332
+ // to 0xFC, inclusive, set pointer to (lead − lead offset) ×
2333
+ // 188 + byte − offset.
2334
+ if (inRange(bite, 0x40, 0x7e) || inRange(bite, 0x80, 0xfc))
2335
+ pointer = (lead - lead_offset) * 188 + bite - offset;
2336
+ // 4. If pointer is in the range 8836 to 10715, inclusive,
2337
+ // return a code point whose value is 0xE000 − 8836 + pointer.
2338
+ if (inRange(pointer, 8836, 10715))
2339
+ return 0xe000 - 8836 + pointer;
2340
+ // 5. Let code point be null, if pointer is null, and the
2341
+ // index code point for pointer in index jis0208 otherwise.
2342
+ var code_point = pointer === null ? null : indexCodePointFor(pointer, index('jis0208'));
2343
+ // 6. If code point is null and byte is an ASCII byte, prepend
2344
+ // byte to stream.
2345
+ if (code_point === null && isASCIIByte(bite))
2346
+ stream.prepend(bite);
2347
+ // 7. If code point is null, return error.
2348
+ if (code_point === null)
2349
+ return decoderError(fatal);
2350
+ // 8. Return a code point whose value is code point.
2351
+ return code_point;
2352
+ }
2353
+ // 4. If byte is an ASCII byte or 0x80, return a code point
2354
+ // whose value is byte.
2355
+ if (isASCIIByte(bite) || bite === 0x80)
2356
+ return bite;
2357
+ // 5. If byte is in the range 0xA1 to 0xDF, inclusive, return a
2358
+ // code point whose value is 0xFF61 − 0xA1 + byte.
2359
+ if (inRange(bite, 0xa1, 0xdf))
2360
+ return 0xff61 - 0xa1 + bite;
2361
+ // 6. If byte is in the range 0x81 to 0x9F, inclusive, or 0xE0
2362
+ // to 0xFC, inclusive, set Shift_JIS lead to byte and return
2363
+ // continue.
2364
+ if (inRange(bite, 0x81, 0x9f) || inRange(bite, 0xe0, 0xfc)) {
2365
+ Shift_JIS_lead = bite;
2366
+ return null;
2367
+ }
2368
+ // 7. Return error.
2369
+ return decoderError(fatal);
2370
+ };
1045
2371
  }
2372
+ // 13.3.2 Shift_JIS encoder
2373
+ /**
2374
+ * @constructor
2375
+ * @implements {Encoder}
2376
+ * @param {{fatal: boolean}} options
2377
+ */
1046
2378
  function ShiftJISEncoder(options) {
1047
- var fatal = options.fatal;
1048
- this.handler = function (stream, code_point) {
1049
- if (code_point === end_of_stream) return finished;
1050
- if (isASCIICodePoint(code_point) || code_point === 0x0080) return code_point;
1051
- if (code_point === 0x00a5) return 0x5c;
1052
- if (code_point === 0x203e) return 0x7e;
1053
- if (inRange(code_point, 0xff61, 0xff9f)) return code_point - 0xff61 + 0xa1;
1054
- if (code_point === 0x2212) code_point = 0xff0d;
1055
- var pointer = indexShiftJISPointerFor(code_point);
1056
- if (pointer === null) return encoderError(code_point);
1057
- var lead = floor(pointer / 188);
1058
- var lead_offset = lead < 0x1f ? 0x81 : 0xc1;
1059
- var trail = pointer % 188;
1060
- var offset = trail < 0x3f ? 0x40 : 0x41;
1061
- return [lead + lead_offset, trail + offset];
1062
- };
2379
+ var fatal = options.fatal;
2380
+ /**
2381
+ * @param {Stream} stream Input stream.
2382
+ * @param {number} code_point Next code point read from the stream.
2383
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
2384
+ */
2385
+ this.handler = function (stream, code_point) {
2386
+ // 1. If code point is end-of-stream, return finished.
2387
+ if (code_point === end_of_stream)
2388
+ return finished;
2389
+ // 2. If code point is an ASCII code point or U+0080, return a
2390
+ // byte whose value is code point.
2391
+ if (isASCIICodePoint(code_point) || code_point === 0x0080)
2392
+ return code_point;
2393
+ // 3. If code point is U+00A5, return byte 0x5C.
2394
+ if (code_point === 0x00a5)
2395
+ return 0x5c;
2396
+ // 4. If code point is U+203E, return byte 0x7E.
2397
+ if (code_point === 0x203e)
2398
+ return 0x7e;
2399
+ // 5. If code point is in the range U+FF61 to U+FF9F, inclusive,
2400
+ // return a byte whose value is code point − 0xFF61 + 0xA1.
2401
+ if (inRange(code_point, 0xff61, 0xff9f))
2402
+ return code_point - 0xff61 + 0xa1;
2403
+ // 6. If code point is U+2212, set it to U+FF0D.
2404
+ if (code_point === 0x2212)
2405
+ code_point = 0xff0d;
2406
+ // 7. Let pointer be the index Shift_JIS pointer for code point.
2407
+ var pointer = indexShiftJISPointerFor(code_point);
2408
+ // 8. If pointer is null, return error with code point.
2409
+ if (pointer === null)
2410
+ return encoderError(code_point);
2411
+ // 9. Let lead be floor(pointer / 188).
2412
+ var lead = floor(pointer / 188);
2413
+ // 10. Let lead offset be 0x81, if lead is less than 0x1F, and
2414
+ // 0xC1 otherwise.
2415
+ var lead_offset = lead < 0x1f ? 0x81 : 0xc1;
2416
+ // 11. Let trail be pointer % 188.
2417
+ var trail = pointer % 188;
2418
+ // 12. Let offset be 0x40, if trail is less than 0x3F, and 0x41
2419
+ // otherwise.
2420
+ var offset = trail < 0x3f ? 0x40 : 0x41;
2421
+ // 13. Return two bytes whose values are lead + lead offset and
2422
+ // trail + offset.
2423
+ return [lead + lead_offset, trail + offset];
2424
+ };
1063
2425
  }
2426
+ /** @param {{fatal: boolean}} options */
1064
2427
  encoders['Shift_JIS'] = function (options) {
1065
- return new ShiftJISEncoder(options);
2428
+ return new ShiftJISEncoder(options);
1066
2429
  };
2430
+ /** @param {{fatal: boolean}} options */
1067
2431
  decoders['Shift_JIS'] = function (options) {
1068
- return new ShiftJISDecoder(options);
2432
+ return new ShiftJISDecoder(options);
1069
2433
  };
2434
+ //
2435
+ // 14. Legacy multi-byte Korean encodings
2436
+ //
2437
+ // 14.1 euc-kr
2438
+ // 14.1.1 euc-kr decoder
2439
+ /**
2440
+ * @constructor
2441
+ * @implements {Decoder}
2442
+ * @param {{fatal: boolean}} options
2443
+ */
1070
2444
  function EUCKRDecoder(options) {
1071
- var fatal = options.fatal;
1072
- var euckr_lead = 0x00;
1073
- this.handler = function (stream, bite) {
1074
- if (bite === end_of_stream && euckr_lead !== 0) {
1075
- euckr_lead = 0x00;
1076
- return decoderError(fatal);
1077
- }
1078
- if (bite === end_of_stream && euckr_lead === 0) return finished;
1079
- if (euckr_lead !== 0x00) {
1080
- var lead = euckr_lead;
1081
- var pointer = null;
1082
- euckr_lead = 0x00;
1083
- if (inRange(bite, 0x41, 0xfe)) pointer = (lead - 0x81) * 190 + (bite - 0x41);
1084
- var code_point = pointer === null ? null : indexCodePointFor(pointer, index('euc-kr'));
1085
- if (pointer === null && isASCIIByte(bite)) stream.prepend(bite);
1086
- if (code_point === null) return decoderError(fatal);
1087
- return code_point;
1088
- }
1089
- if (isASCIIByte(bite)) return bite;
1090
- if (inRange(bite, 0x81, 0xfe)) {
1091
- euckr_lead = bite;
1092
- return null;
1093
- }
1094
- return decoderError(fatal);
1095
- };
2445
+ var fatal = options.fatal;
2446
+ // euc-kr's decoder has an associated euc-kr lead (initially 0x00).
2447
+ var /** @type {number} */ euckr_lead = 0x00;
2448
+ /**
2449
+ * @param {Stream} stream The stream of bytes being decoded.
2450
+ * @param {number} bite The next byte read from the stream.
2451
+ * @return {?(number|!Array.<number>)} The next code point(s)
2452
+ * decoded, or null if not enough data exists in the input
2453
+ * stream to decode a complete code point.
2454
+ */
2455
+ this.handler = function (stream, bite) {
2456
+ // 1. If byte is end-of-stream and euc-kr lead is not 0x00, set
2457
+ // euc-kr lead to 0x00 and return error.
2458
+ if (bite === end_of_stream && euckr_lead !== 0) {
2459
+ euckr_lead = 0x00;
2460
+ return decoderError(fatal);
2461
+ }
2462
+ // 2. If byte is end-of-stream and euc-kr lead is 0x00, return
2463
+ // finished.
2464
+ if (bite === end_of_stream && euckr_lead === 0)
2465
+ return finished;
2466
+ // 3. If euc-kr lead is not 0x00, let lead be euc-kr lead, let
2467
+ // pointer be null, set euc-kr lead to 0x00, and then run these
2468
+ // substeps:
2469
+ if (euckr_lead !== 0x00) {
2470
+ var lead = euckr_lead;
2471
+ var pointer = null;
2472
+ euckr_lead = 0x00;
2473
+ // 1. If byte is in the range 0x41 to 0xFE, inclusive, set
2474
+ // pointer to (lead − 0x81) × 190 + (byte − 0x41).
2475
+ if (inRange(bite, 0x41, 0xfe))
2476
+ pointer = (lead - 0x81) * 190 + (bite - 0x41);
2477
+ // 2. Let code point be null, if pointer is null, and the
2478
+ // index code point for pointer in index euc-kr otherwise.
2479
+ var code_point = pointer === null ? null : indexCodePointFor(pointer, index('euc-kr'));
2480
+ // 3. If code point is null and byte is an ASCII byte, prepend
2481
+ // byte to stream.
2482
+ if (pointer === null && isASCIIByte(bite))
2483
+ stream.prepend(bite);
2484
+ // 4. If code point is null, return error.
2485
+ if (code_point === null)
2486
+ return decoderError(fatal);
2487
+ // 5. Return a code point whose value is code point.
2488
+ return code_point;
2489
+ }
2490
+ // 4. If byte is an ASCII byte, return a code point whose value
2491
+ // is byte.
2492
+ if (isASCIIByte(bite))
2493
+ return bite;
2494
+ // 5. If byte is in the range 0x81 to 0xFE, inclusive, set
2495
+ // euc-kr lead to byte and return continue.
2496
+ if (inRange(bite, 0x81, 0xfe)) {
2497
+ euckr_lead = bite;
2498
+ return null;
2499
+ }
2500
+ // 6. Return error.
2501
+ return decoderError(fatal);
2502
+ };
1096
2503
  }
2504
+ // 14.1.2 euc-kr encoder
2505
+ /**
2506
+ * @constructor
2507
+ * @implements {Encoder}
2508
+ * @param {{fatal: boolean}} options
2509
+ */
1097
2510
  function EUCKREncoder(options) {
1098
- var fatal = options.fatal;
1099
- this.handler = function (stream, code_point) {
1100
- if (code_point === end_of_stream) return finished;
1101
- if (isASCIICodePoint(code_point)) return code_point;
1102
- var pointer = indexPointerFor(code_point, index('euc-kr'));
1103
- if (pointer === null) return encoderError(code_point);
1104
- var lead = floor(pointer / 190) + 0x81;
1105
- var trail = pointer % 190 + 0x41;
1106
- return [lead, trail];
1107
- };
2511
+ var fatal = options.fatal;
2512
+ /**
2513
+ * @param {Stream} stream Input stream.
2514
+ * @param {number} code_point Next code point read from the stream.
2515
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
2516
+ */
2517
+ this.handler = function (stream, code_point) {
2518
+ // 1. If code point is end-of-stream, return finished.
2519
+ if (code_point === end_of_stream)
2520
+ return finished;
2521
+ // 2. If code point is an ASCII code point, return a byte whose
2522
+ // value is code point.
2523
+ if (isASCIICodePoint(code_point))
2524
+ return code_point;
2525
+ // 3. Let pointer be the index pointer for code point in index
2526
+ // euc-kr.
2527
+ var pointer = indexPointerFor(code_point, index('euc-kr'));
2528
+ // 4. If pointer is null, return error with code point.
2529
+ if (pointer === null)
2530
+ return encoderError(code_point);
2531
+ // 5. Let lead be floor(pointer / 190) + 0x81.
2532
+ var lead = floor(pointer / 190) + 0x81;
2533
+ // 6. Let trail be pointer % 190 + 0x41.
2534
+ var trail = (pointer % 190) + 0x41;
2535
+ // 7. Return two bytes whose values are lead and trail.
2536
+ return [lead, trail];
2537
+ };
1108
2538
  }
2539
+ /** @param {{fatal: boolean}} options */
1109
2540
  encoders['EUC-KR'] = function (options) {
1110
- return new EUCKREncoder(options);
2541
+ return new EUCKREncoder(options);
1111
2542
  };
2543
+ /** @param {{fatal: boolean}} options */
1112
2544
  decoders['EUC-KR'] = function (options) {
1113
- return new EUCKRDecoder(options);
2545
+ return new EUCKRDecoder(options);
1114
2546
  };
2547
+ //
2548
+ // 15. Legacy miscellaneous encodings
2549
+ //
2550
+ // 15.1 replacement
2551
+ // Not needed - API throws RangeError
2552
+ // 15.2 Common infrastructure for utf-16be and utf-16le
2553
+ /**
2554
+ * @param {number} code_unit
2555
+ * @param {boolean} utf16be
2556
+ * @return {!Array.<number>} bytes
2557
+ */
1115
2558
  function convertCodeUnitToBytes(code_unit, utf16be) {
1116
- var byte1 = code_unit >> 8;
1117
- var byte2 = code_unit & 0x00ff;
1118
- if (utf16be) return [byte1, byte2];
1119
- return [byte2, byte1];
2559
+ // 1. Let byte1 be code unit >> 8.
2560
+ var byte1 = code_unit >> 8;
2561
+ // 2. Let byte2 be code unit & 0x00FF.
2562
+ var byte2 = code_unit & 0x00ff;
2563
+ // 3. Then return the bytes in order:
2564
+ // utf-16be flag is set: byte1, then byte2.
2565
+ if (utf16be)
2566
+ return [byte1, byte2];
2567
+ // utf-16be flag is unset: byte2, then byte1.
2568
+ return [byte2, byte1];
1120
2569
  }
2570
+ // 15.2.1 shared utf-16 decoder
2571
+ /**
2572
+ * @constructor
2573
+ * @implements {Decoder}
2574
+ * @param {boolean} utf16_be True if big-endian, false if little-endian.
2575
+ * @param {{fatal: boolean}} options
2576
+ */
1121
2577
  function UTF16Decoder(utf16_be, options) {
1122
- var fatal = options.fatal;
1123
- var utf16_lead_byte = null,
1124
- utf16_lead_surrogate = null;
1125
- this.handler = function (stream, bite) {
1126
- if (bite === end_of_stream && (utf16_lead_byte !== null || utf16_lead_surrogate !== null)) {
1127
- return decoderError(fatal);
1128
- }
1129
- if (bite === end_of_stream && utf16_lead_byte === null && utf16_lead_surrogate === null) {
1130
- return finished;
1131
- }
1132
- if (utf16_lead_byte === null) {
1133
- utf16_lead_byte = bite;
1134
- return null;
1135
- }
1136
- var code_unit;
1137
- if (utf16_be) {
1138
- code_unit = (utf16_lead_byte << 8) + bite;
1139
- } else {
1140
- code_unit = (bite << 8) + utf16_lead_byte;
1141
- }
1142
- utf16_lead_byte = null;
1143
- if (utf16_lead_surrogate !== null) {
1144
- var lead_surrogate = utf16_lead_surrogate;
1145
- utf16_lead_surrogate = null;
1146
- if (inRange(code_unit, 0xdc00, 0xdfff)) {
1147
- return 0x10000 + (lead_surrogate - 0xd800) * 0x400 + (code_unit - 0xdc00);
1148
- }
1149
- stream.prepend(convertCodeUnitToBytes(code_unit, utf16_be));
1150
- return decoderError(fatal);
1151
- }
1152
- if (inRange(code_unit, 0xd800, 0xdbff)) {
1153
- utf16_lead_surrogate = code_unit;
1154
- return null;
1155
- }
1156
- if (inRange(code_unit, 0xdc00, 0xdfff)) return decoderError(fatal);
1157
- return code_unit;
1158
- };
2578
+ var fatal = options.fatal;
2579
+ var /** @type {?number} */ utf16_lead_byte = null,
2580
+ /** @type {?number} */ utf16_lead_surrogate = null;
2581
+ /**
2582
+ * @param {Stream} stream The stream of bytes being decoded.
2583
+ * @param {number} bite The next byte read from the stream.
2584
+ * @return {?(number|!Array.<number>)} The next code point(s)
2585
+ * decoded, or null if not enough data exists in the input
2586
+ * stream to decode a complete code point.
2587
+ */
2588
+ this.handler = function (stream, bite) {
2589
+ // 1. If byte is end-of-stream and either utf-16 lead byte or
2590
+ // utf-16 lead surrogate is not null, set utf-16 lead byte and
2591
+ // utf-16 lead surrogate to null, and return error.
2592
+ if (bite === end_of_stream && (utf16_lead_byte !== null || utf16_lead_surrogate !== null)) {
2593
+ return decoderError(fatal);
2594
+ }
2595
+ // 2. If byte is end-of-stream and utf-16 lead byte and utf-16
2596
+ // lead surrogate are null, return finished.
2597
+ if (bite === end_of_stream && utf16_lead_byte === null && utf16_lead_surrogate === null) {
2598
+ return finished;
2599
+ }
2600
+ // 3. If utf-16 lead byte is null, set utf-16 lead byte to byte
2601
+ // and return continue.
2602
+ if (utf16_lead_byte === null) {
2603
+ utf16_lead_byte = bite;
2604
+ return null;
2605
+ }
2606
+ // 4. Let code unit be the result of:
2607
+ var code_unit;
2608
+ if (utf16_be) {
2609
+ // utf-16be decoder flag is set
2610
+ // (utf-16 lead byte << 8) + byte.
2611
+ code_unit = (utf16_lead_byte << 8) + bite;
2612
+ }
2613
+ else {
2614
+ // utf-16be decoder flag is unset
2615
+ // (byte << 8) + utf-16 lead byte.
2616
+ code_unit = (bite << 8) + utf16_lead_byte;
2617
+ }
2618
+ // Then set utf-16 lead byte to null.
2619
+ utf16_lead_byte = null;
2620
+ // 5. If utf-16 lead surrogate is not null, let lead surrogate
2621
+ // be utf-16 lead surrogate, set utf-16 lead surrogate to null,
2622
+ // and then run these substeps:
2623
+ if (utf16_lead_surrogate !== null) {
2624
+ var lead_surrogate = utf16_lead_surrogate;
2625
+ utf16_lead_surrogate = null;
2626
+ // 1. If code unit is in the range U+DC00 to U+DFFF,
2627
+ // inclusive, return a code point whose value is 0x10000 +
2628
+ // ((lead surrogate − 0xD800) << 10) + (code unit − 0xDC00).
2629
+ if (inRange(code_unit, 0xdc00, 0xdfff)) {
2630
+ return 0x10000 + (lead_surrogate - 0xd800) * 0x400 + (code_unit - 0xdc00);
2631
+ }
2632
+ // 2. Prepend the sequence resulting of converting code unit
2633
+ // to bytes using utf-16be decoder flag to stream and return
2634
+ // error.
2635
+ stream.prepend(convertCodeUnitToBytes(code_unit, utf16_be));
2636
+ return decoderError(fatal);
2637
+ }
2638
+ // 6. If code unit is in the range U+D800 to U+DBFF, inclusive,
2639
+ // set utf-16 lead surrogate to code unit and return continue.
2640
+ if (inRange(code_unit, 0xd800, 0xdbff)) {
2641
+ utf16_lead_surrogate = code_unit;
2642
+ return null;
2643
+ }
2644
+ // 7. If code unit is in the range U+DC00 to U+DFFF, inclusive,
2645
+ // return error.
2646
+ if (inRange(code_unit, 0xdc00, 0xdfff))
2647
+ return decoderError(fatal);
2648
+ // 8. Return code point code unit.
2649
+ return code_unit;
2650
+ };
1159
2651
  }
2652
+ // 15.2.2 shared utf-16 encoder
2653
+ /**
2654
+ * @constructor
2655
+ * @implements {Encoder}
2656
+ * @param {boolean} utf16_be True if big-endian, false if little-endian.
2657
+ * @param {{fatal: boolean}} options
2658
+ */
1160
2659
  function UTF16Encoder(utf16_be, options) {
1161
- var fatal = options.fatal;
1162
- this.handler = function (stream, code_point) {
1163
- if (code_point === end_of_stream) return finished;
1164
- if (inRange(code_point, 0x0000, 0xffff)) return convertCodeUnitToBytes(code_point, utf16_be);
1165
- var lead = convertCodeUnitToBytes((code_point - 0x10000 >> 10) + 0xd800, utf16_be);
1166
- var trail = convertCodeUnitToBytes((code_point - 0x10000 & 0x3ff) + 0xdc00, utf16_be);
1167
- return lead.concat(trail);
1168
- };
2660
+ var fatal = options.fatal;
2661
+ /**
2662
+ * @param {Stream} stream Input stream.
2663
+ * @param {number} code_point Next code point read from the stream.
2664
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
2665
+ */
2666
+ this.handler = function (stream, code_point) {
2667
+ // 1. If code point is end-of-stream, return finished.
2668
+ if (code_point === end_of_stream)
2669
+ return finished;
2670
+ // 2. If code point is in the range U+0000 to U+FFFF, inclusive,
2671
+ // return the sequence resulting of converting code point to
2672
+ // bytes using utf-16be encoder flag.
2673
+ if (inRange(code_point, 0x0000, 0xffff))
2674
+ return convertCodeUnitToBytes(code_point, utf16_be);
2675
+ // 3. Let lead be ((code point − 0x10000) >> 10) + 0xD800,
2676
+ // converted to bytes using utf-16be encoder flag.
2677
+ var lead = convertCodeUnitToBytes(((code_point - 0x10000) >> 10) + 0xd800, utf16_be);
2678
+ // 4. Let trail be ((code point − 0x10000) & 0x3FF) + 0xDC00,
2679
+ // converted to bytes using utf-16be encoder flag.
2680
+ var trail = convertCodeUnitToBytes(((code_point - 0x10000) & 0x3ff) + 0xdc00, utf16_be);
2681
+ // 5. Return a byte sequence of lead followed by trail.
2682
+ return lead.concat(trail);
2683
+ };
1169
2684
  }
2685
+ // 15.3 utf-16be
2686
+ // 15.3.1 utf-16be decoder
2687
+ /** @param {{fatal: boolean}} options */
1170
2688
  encoders['UTF-16BE'] = function (options) {
1171
- return new UTF16Encoder(true, options);
2689
+ return new UTF16Encoder(true, options);
1172
2690
  };
2691
+ // 15.3.2 utf-16be encoder
2692
+ /** @param {{fatal: boolean}} options */
1173
2693
  decoders['UTF-16BE'] = function (options) {
1174
- return new UTF16Decoder(true, options);
2694
+ return new UTF16Decoder(true, options);
1175
2695
  };
2696
+ // 15.4 utf-16le
2697
+ // 15.4.1 utf-16le decoder
2698
+ /** @param {{fatal: boolean}} options */
1176
2699
  encoders['UTF-16LE'] = function (options) {
1177
- return new UTF16Encoder(false, options);
2700
+ return new UTF16Encoder(false, options);
1178
2701
  };
2702
+ // 15.4.2 utf-16le encoder
2703
+ /** @param {{fatal: boolean}} options */
1179
2704
  decoders['UTF-16LE'] = function (options) {
1180
- return new UTF16Decoder(false, options);
2705
+ return new UTF16Decoder(false, options);
1181
2706
  };
2707
+ // 15.5 x-user-defined
2708
+ // 15.5.1 x-user-defined decoder
2709
+ /**
2710
+ * @constructor
2711
+ * @implements {Decoder}
2712
+ * @param {{fatal: boolean}} options
2713
+ */
1182
2714
  function XUserDefinedDecoder(options) {
1183
- var fatal = options.fatal;
1184
- this.handler = function (stream, bite) {
1185
- if (bite === end_of_stream) return finished;
1186
- if (isASCIIByte(bite)) return bite;
1187
- return 0xf780 + bite - 0x80;
1188
- };
2715
+ var fatal = options.fatal;
2716
+ /**
2717
+ * @param {Stream} stream The stream of bytes being decoded.
2718
+ * @param {number} bite The next byte read from the stream.
2719
+ * @return {?(number|!Array.<number>)} The next code point(s)
2720
+ * decoded, or null if not enough data exists in the input
2721
+ * stream to decode a complete code point.
2722
+ */
2723
+ this.handler = function (stream, bite) {
2724
+ // 1. If byte is end-of-stream, return finished.
2725
+ if (bite === end_of_stream)
2726
+ return finished;
2727
+ // 2. If byte is an ASCII byte, return a code point whose value
2728
+ // is byte.
2729
+ if (isASCIIByte(bite))
2730
+ return bite;
2731
+ // 3. Return a code point whose value is 0xF780 + byte − 0x80.
2732
+ return 0xf780 + bite - 0x80;
2733
+ };
1189
2734
  }
2735
+ // 15.5.2 x-user-defined encoder
2736
+ /**
2737
+ * @constructor
2738
+ * @implements {Encoder}
2739
+ * @param {{fatal: boolean}} options
2740
+ */
1190
2741
  function XUserDefinedEncoder(options) {
1191
- var fatal = options.fatal;
1192
- this.handler = function (stream, code_point) {
1193
- if (code_point === end_of_stream) return finished;
1194
- if (isASCIICodePoint(code_point)) return code_point;
1195
- if (inRange(code_point, 0xf780, 0xf7ff)) return code_point - 0xf780 + 0x80;
1196
- return encoderError(code_point);
1197
- };
2742
+ var fatal = options.fatal;
2743
+ /**
2744
+ * @param {Stream} stream Input stream.
2745
+ * @param {number} code_point Next code point read from the stream.
2746
+ * @return {(number|!Array.<number>)} Byte(s) to emit.
2747
+ */
2748
+ this.handler = function (stream, code_point) {
2749
+ // 1.If code point is end-of-stream, return finished.
2750
+ if (code_point === end_of_stream)
2751
+ return finished;
2752
+ // 2. If code point is an ASCII code point, return a byte whose
2753
+ // value is code point.
2754
+ if (isASCIICodePoint(code_point))
2755
+ return code_point;
2756
+ // 3. If code point is in the range U+F780 to U+F7FF, inclusive,
2757
+ // return a byte whose value is code point − 0xF780 + 0x80.
2758
+ if (inRange(code_point, 0xf780, 0xf7ff))
2759
+ return code_point - 0xf780 + 0x80;
2760
+ // 4. Return error with code point.
2761
+ return encoderError(code_point);
2762
+ };
1198
2763
  }
2764
+ /** @param {{fatal: boolean}} options */
1199
2765
  encoders['x-user-defined'] = function (options) {
1200
- return new XUserDefinedEncoder(options);
2766
+ return new XUserDefinedEncoder(options);
1201
2767
  };
2768
+ /** @param {{fatal: boolean}} options */
1202
2769
  decoders['x-user-defined'] = function (options) {
1203
- return new XUserDefinedDecoder(options);
2770
+ return new XUserDefinedDecoder(options);
1204
2771
  };
2772
+ // FORK
2773
+ // if (!globalThis['TextEncoder']) globalThis['TextEncoder'] = TextEncoder;
2774
+ // if (!globalThis['TextDecoder']) globalThis['TextDecoder'] = TextDecoder;
2775
+ // babel.config.js skip transpiling files in `libs/`
2776
+ // module.exports = {TextEncoder, TextDecoder};
1205
2777
  export { TextEncoder, TextDecoder };
1206
- //# sourceMappingURL=text-encoder.js.map