-
Notifications
You must be signed in to change notification settings - Fork 18
Expand file tree
/
Copy pathnode-id3-browserify.js
More file actions
21665 lines (18944 loc) · 693 KB
/
node-id3-browserify.js
File metadata and controls
21665 lines (18944 loc) · 693 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
(function(){function r(e,n,t){function o(i,f){if(!n[i]){if(!e[i]){var c="function"==typeof require&&require;if(!f&&c)return c(i,!0);if(u)return u(i,!0);var a=new Error("Cannot find module '"+i+"'");throw a.code="MODULE_NOT_FOUND",a}var p=n[i]={exports:{}};e[i][0].call(p.exports,function(r){var n=e[i][1][r];return o(n||r)},p,p.exports,r,e,n,t)}return n[i].exports}for(var u="function"==typeof require&&require,i=0;i<t.length;i++)o(t[i]);return o}return r})()({1:[function(require,module,exports){
"use strict";
var Buffer = require("safer-buffer").Buffer;
// Multibyte codec. In this scheme, a character is represented by 1 or more bytes.
// Our codec supports UTF-16 surrogates, extensions for GB18030 and unicode sequences.
// To save memory and loading time, we read table files only when requested.
exports._dbcs = DBCSCodec;
var UNASSIGNED = -1,
GB18030_CODE = -2,
SEQ_START = -10,
NODE_START = -1000,
UNASSIGNED_NODE = new Array(0x100),
DEF_CHAR = -1;
for (var i = 0; i < 0x100; i++)
UNASSIGNED_NODE[i] = UNASSIGNED;
// Class DBCSCodec reads and initializes mapping tables.
function DBCSCodec(codecOptions, iconv) {
this.encodingName = codecOptions.encodingName;
if (!codecOptions)
throw new Error("DBCS codec is called without the data.")
if (!codecOptions.table)
throw new Error("Encoding '" + this.encodingName + "' has no data.");
// Load tables.
var mappingTable = codecOptions.table();
// Decode tables: MBCS -> Unicode.
// decodeTables is a trie, encoded as an array of arrays of integers. Internal arrays are trie nodes and all have len = 256.
// Trie root is decodeTables[0].
// Values: >= 0 -> unicode character code. can be > 0xFFFF
// == UNASSIGNED -> unknown/unassigned sequence.
// == GB18030_CODE -> this is the end of a GB18030 4-byte sequence.
// <= NODE_START -> index of the next node in our trie to process next byte.
// <= SEQ_START -> index of the start of a character code sequence, in decodeTableSeq.
this.decodeTables = [];
this.decodeTables[0] = UNASSIGNED_NODE.slice(0); // Create root node.
// Sometimes a MBCS char corresponds to a sequence of unicode chars. We store them as arrays of integers here.
this.decodeTableSeq = [];
// Actual mapping tables consist of chunks. Use them to fill up decode tables.
for (var i = 0; i < mappingTable.length; i++)
this._addDecodeChunk(mappingTable[i]);
// Load & create GB18030 tables when needed.
if (typeof codecOptions.gb18030 === 'function') {
this.gb18030 = codecOptions.gb18030(); // Load GB18030 ranges.
// Add GB18030 common decode nodes.
var commonThirdByteNodeIdx = this.decodeTables.length;
this.decodeTables.push(UNASSIGNED_NODE.slice(0));
var commonFourthByteNodeIdx = this.decodeTables.length;
this.decodeTables.push(UNASSIGNED_NODE.slice(0));
// Fill out the tree
var firstByteNode = this.decodeTables[0];
for (var i = 0x81; i <= 0xFE; i++) {
var secondByteNode = this.decodeTables[NODE_START - firstByteNode[i]];
for (var j = 0x30; j <= 0x39; j++) {
if (secondByteNode[j] === UNASSIGNED) {
secondByteNode[j] = NODE_START - commonThirdByteNodeIdx;
} else if (secondByteNode[j] > NODE_START) {
throw new Error("gb18030 decode tables conflict at byte 2");
}
var thirdByteNode = this.decodeTables[NODE_START - secondByteNode[j]];
for (var k = 0x81; k <= 0xFE; k++) {
if (thirdByteNode[k] === UNASSIGNED) {
thirdByteNode[k] = NODE_START - commonFourthByteNodeIdx;
} else if (thirdByteNode[k] === NODE_START - commonFourthByteNodeIdx) {
continue;
} else if (thirdByteNode[k] > NODE_START) {
throw new Error("gb18030 decode tables conflict at byte 3");
}
var fourthByteNode = this.decodeTables[NODE_START - thirdByteNode[k]];
for (var l = 0x30; l <= 0x39; l++) {
if (fourthByteNode[l] === UNASSIGNED)
fourthByteNode[l] = GB18030_CODE;
}
}
}
}
}
this.defaultCharUnicode = iconv.defaultCharUnicode;
// Encode tables: Unicode -> DBCS.
// `encodeTable` is array mapping from unicode char to encoded char. All its values are integers for performance.
// Because it can be sparse, it is represented as array of buckets by 256 chars each. Bucket can be null.
// Values: >= 0 -> it is a normal char. Write the value (if <=256 then 1 byte, if <=65536 then 2 bytes, etc.).
// == UNASSIGNED -> no conversion found. Output a default char.
// <= SEQ_START -> it's an index in encodeTableSeq, see below. The character starts a sequence.
this.encodeTable = [];
// `encodeTableSeq` is used when a sequence of unicode characters is encoded as a single code. We use a tree of
// objects where keys correspond to characters in sequence and leafs are the encoded dbcs values. A special DEF_CHAR key
// means end of sequence (needed when one sequence is a strict subsequence of another).
// Objects are kept separately from encodeTable to increase performance.
this.encodeTableSeq = [];
// Some chars can be decoded, but need not be encoded.
var skipEncodeChars = {};
if (codecOptions.encodeSkipVals)
for (var i = 0; i < codecOptions.encodeSkipVals.length; i++) {
var val = codecOptions.encodeSkipVals[i];
if (typeof val === 'number')
skipEncodeChars[val] = true;
else
for (var j = val.from; j <= val.to; j++)
skipEncodeChars[j] = true;
}
// Use decode trie to recursively fill out encode tables.
this._fillEncodeTable(0, 0, skipEncodeChars);
// Add more encoding pairs when needed.
if (codecOptions.encodeAdd) {
for (var uChar in codecOptions.encodeAdd)
if (Object.prototype.hasOwnProperty.call(codecOptions.encodeAdd, uChar))
this._setEncodeChar(uChar.charCodeAt(0), codecOptions.encodeAdd[uChar]);
}
this.defCharSB = this.encodeTable[0][iconv.defaultCharSingleByte.charCodeAt(0)];
if (this.defCharSB === UNASSIGNED) this.defCharSB = this.encodeTable[0]['?'];
if (this.defCharSB === UNASSIGNED) this.defCharSB = "?".charCodeAt(0);
}
DBCSCodec.prototype.encoder = DBCSEncoder;
DBCSCodec.prototype.decoder = DBCSDecoder;
// Decoder helpers
DBCSCodec.prototype._getDecodeTrieNode = function(addr) {
var bytes = [];
for (; addr > 0; addr >>>= 8)
bytes.push(addr & 0xFF);
if (bytes.length == 0)
bytes.push(0);
var node = this.decodeTables[0];
for (var i = bytes.length-1; i > 0; i--) { // Traverse nodes deeper into the trie.
var val = node[bytes[i]];
if (val == UNASSIGNED) { // Create new node.
node[bytes[i]] = NODE_START - this.decodeTables.length;
this.decodeTables.push(node = UNASSIGNED_NODE.slice(0));
}
else if (val <= NODE_START) { // Existing node.
node = this.decodeTables[NODE_START - val];
}
else
throw new Error("Overwrite byte in " + this.encodingName + ", addr: " + addr.toString(16));
}
return node;
}
DBCSCodec.prototype._addDecodeChunk = function(chunk) {
// First element of chunk is the hex mbcs code where we start.
var curAddr = parseInt(chunk[0], 16);
// Choose the decoding node where we'll write our chars.
var writeTable = this._getDecodeTrieNode(curAddr);
curAddr = curAddr & 0xFF;
// Write all other elements of the chunk to the table.
for (var k = 1; k < chunk.length; k++) {
var part = chunk[k];
if (typeof part === "string") { // String, write as-is.
for (var l = 0; l < part.length;) {
var code = part.charCodeAt(l++);
if (0xD800 <= code && code < 0xDC00) { // Decode surrogate
var codeTrail = part.charCodeAt(l++);
if (0xDC00 <= codeTrail && codeTrail < 0xE000)
writeTable[curAddr++] = 0x10000 + (code - 0xD800) * 0x400 + (codeTrail - 0xDC00);
else
throw new Error("Incorrect surrogate pair in " + this.encodingName + " at chunk " + chunk[0]);
}
else if (0x0FF0 < code && code <= 0x0FFF) { // Character sequence (our own encoding used)
var len = 0xFFF - code + 2;
var seq = [];
for (var m = 0; m < len; m++)
seq.push(part.charCodeAt(l++)); // Simple variation: don't support surrogates or subsequences in seq.
writeTable[curAddr++] = SEQ_START - this.decodeTableSeq.length;
this.decodeTableSeq.push(seq);
}
else
writeTable[curAddr++] = code; // Basic char
}
}
else if (typeof part === "number") { // Integer, meaning increasing sequence starting with prev character.
var charCode = writeTable[curAddr - 1] + 1;
for (var l = 0; l < part; l++)
writeTable[curAddr++] = charCode++;
}
else
throw new Error("Incorrect type '" + typeof part + "' given in " + this.encodingName + " at chunk " + chunk[0]);
}
if (curAddr > 0xFF)
throw new Error("Incorrect chunk in " + this.encodingName + " at addr " + chunk[0] + ": too long" + curAddr);
}
// Encoder helpers
DBCSCodec.prototype._getEncodeBucket = function(uCode) {
var high = uCode >> 8; // This could be > 0xFF because of astral characters.
if (this.encodeTable[high] === undefined)
this.encodeTable[high] = UNASSIGNED_NODE.slice(0); // Create bucket on demand.
return this.encodeTable[high];
}
DBCSCodec.prototype._setEncodeChar = function(uCode, dbcsCode) {
var bucket = this._getEncodeBucket(uCode);
var low = uCode & 0xFF;
if (bucket[low] <= SEQ_START)
this.encodeTableSeq[SEQ_START-bucket[low]][DEF_CHAR] = dbcsCode; // There's already a sequence, set a single-char subsequence of it.
else if (bucket[low] == UNASSIGNED)
bucket[low] = dbcsCode;
}
DBCSCodec.prototype._setEncodeSequence = function(seq, dbcsCode) {
// Get the root of character tree according to first character of the sequence.
var uCode = seq[0];
var bucket = this._getEncodeBucket(uCode);
var low = uCode & 0xFF;
var node;
if (bucket[low] <= SEQ_START) {
// There's already a sequence with - use it.
node = this.encodeTableSeq[SEQ_START-bucket[low]];
}
else {
// There was no sequence object - allocate a new one.
node = {};
if (bucket[low] !== UNASSIGNED) node[DEF_CHAR] = bucket[low]; // If a char was set before - make it a single-char subsequence.
bucket[low] = SEQ_START - this.encodeTableSeq.length;
this.encodeTableSeq.push(node);
}
// Traverse the character tree, allocating new nodes as needed.
for (var j = 1; j < seq.length-1; j++) {
var oldVal = node[uCode];
if (typeof oldVal === 'object')
node = oldVal;
else {
node = node[uCode] = {}
if (oldVal !== undefined)
node[DEF_CHAR] = oldVal
}
}
// Set the leaf to given dbcsCode.
uCode = seq[seq.length-1];
node[uCode] = dbcsCode;
}
DBCSCodec.prototype._fillEncodeTable = function(nodeIdx, prefix, skipEncodeChars) {
var node = this.decodeTables[nodeIdx];
var hasValues = false;
var subNodeEmpty = {};
for (var i = 0; i < 0x100; i++) {
var uCode = node[i];
var mbCode = prefix + i;
if (skipEncodeChars[mbCode])
continue;
if (uCode >= 0) {
this._setEncodeChar(uCode, mbCode);
hasValues = true;
} else if (uCode <= NODE_START) {
var subNodeIdx = NODE_START - uCode;
if (!subNodeEmpty[subNodeIdx]) { // Skip empty subtrees (they are too large in gb18030).
var newPrefix = (mbCode << 8) >>> 0; // NOTE: '>>> 0' keeps 32-bit num positive.
if (this._fillEncodeTable(subNodeIdx, newPrefix, skipEncodeChars))
hasValues = true;
else
subNodeEmpty[subNodeIdx] = true;
}
} else if (uCode <= SEQ_START) {
this._setEncodeSequence(this.decodeTableSeq[SEQ_START - uCode], mbCode);
hasValues = true;
}
}
return hasValues;
}
// == Encoder ==================================================================
function DBCSEncoder(options, codec) {
// Encoder state
this.leadSurrogate = -1;
this.seqObj = undefined;
// Static data
this.encodeTable = codec.encodeTable;
this.encodeTableSeq = codec.encodeTableSeq;
this.defaultCharSingleByte = codec.defCharSB;
this.gb18030 = codec.gb18030;
}
DBCSEncoder.prototype.write = function(str) {
var newBuf = Buffer.alloc(str.length * (this.gb18030 ? 4 : 3)),
leadSurrogate = this.leadSurrogate,
seqObj = this.seqObj, nextChar = -1,
i = 0, j = 0;
while (true) {
// 0. Get next character.
if (nextChar === -1) {
if (i == str.length) break;
var uCode = str.charCodeAt(i++);
}
else {
var uCode = nextChar;
nextChar = -1;
}
// 1. Handle surrogates.
if (0xD800 <= uCode && uCode < 0xE000) { // Char is one of surrogates.
if (uCode < 0xDC00) { // We've got lead surrogate.
if (leadSurrogate === -1) {
leadSurrogate = uCode;
continue;
} else {
leadSurrogate = uCode;
// Double lead surrogate found.
uCode = UNASSIGNED;
}
} else { // We've got trail surrogate.
if (leadSurrogate !== -1) {
uCode = 0x10000 + (leadSurrogate - 0xD800) * 0x400 + (uCode - 0xDC00);
leadSurrogate = -1;
} else {
// Incomplete surrogate pair - only trail surrogate found.
uCode = UNASSIGNED;
}
}
}
else if (leadSurrogate !== -1) {
// Incomplete surrogate pair - only lead surrogate found.
nextChar = uCode; uCode = UNASSIGNED; // Write an error, then current char.
leadSurrogate = -1;
}
// 2. Convert uCode character.
var dbcsCode = UNASSIGNED;
if (seqObj !== undefined && uCode != UNASSIGNED) { // We are in the middle of the sequence
var resCode = seqObj[uCode];
if (typeof resCode === 'object') { // Sequence continues.
seqObj = resCode;
continue;
} else if (typeof resCode == 'number') { // Sequence finished. Write it.
dbcsCode = resCode;
} else if (resCode == undefined) { // Current character is not part of the sequence.
// Try default character for this sequence
resCode = seqObj[DEF_CHAR];
if (resCode !== undefined) {
dbcsCode = resCode; // Found. Write it.
nextChar = uCode; // Current character will be written too in the next iteration.
} else {
// TODO: What if we have no default? (resCode == undefined)
// Then, we should write first char of the sequence as-is and try the rest recursively.
// Didn't do it for now because no encoding has this situation yet.
// Currently, just skip the sequence and write current char.
}
}
seqObj = undefined;
}
else if (uCode >= 0) { // Regular character
var subtable = this.encodeTable[uCode >> 8];
if (subtable !== undefined)
dbcsCode = subtable[uCode & 0xFF];
if (dbcsCode <= SEQ_START) { // Sequence start
seqObj = this.encodeTableSeq[SEQ_START-dbcsCode];
continue;
}
if (dbcsCode == UNASSIGNED && this.gb18030) {
// Use GB18030 algorithm to find character(s) to write.
var idx = findIdx(this.gb18030.uChars, uCode);
if (idx != -1) {
var dbcsCode = this.gb18030.gbChars[idx] + (uCode - this.gb18030.uChars[idx]);
newBuf[j++] = 0x81 + Math.floor(dbcsCode / 12600); dbcsCode = dbcsCode % 12600;
newBuf[j++] = 0x30 + Math.floor(dbcsCode / 1260); dbcsCode = dbcsCode % 1260;
newBuf[j++] = 0x81 + Math.floor(dbcsCode / 10); dbcsCode = dbcsCode % 10;
newBuf[j++] = 0x30 + dbcsCode;
continue;
}
}
}
// 3. Write dbcsCode character.
if (dbcsCode === UNASSIGNED)
dbcsCode = this.defaultCharSingleByte;
if (dbcsCode < 0x100) {
newBuf[j++] = dbcsCode;
}
else if (dbcsCode < 0x10000) {
newBuf[j++] = dbcsCode >> 8; // high byte
newBuf[j++] = dbcsCode & 0xFF; // low byte
}
else if (dbcsCode < 0x1000000) {
newBuf[j++] = dbcsCode >> 16;
newBuf[j++] = (dbcsCode >> 8) & 0xFF;
newBuf[j++] = dbcsCode & 0xFF;
} else {
newBuf[j++] = dbcsCode >>> 24;
newBuf[j++] = (dbcsCode >>> 16) & 0xFF;
newBuf[j++] = (dbcsCode >>> 8) & 0xFF;
newBuf[j++] = dbcsCode & 0xFF;
}
}
this.seqObj = seqObj;
this.leadSurrogate = leadSurrogate;
return newBuf.slice(0, j);
}
DBCSEncoder.prototype.end = function() {
if (this.leadSurrogate === -1 && this.seqObj === undefined)
return; // All clean. Most often case.
var newBuf = Buffer.alloc(10), j = 0;
if (this.seqObj) { // We're in the sequence.
var dbcsCode = this.seqObj[DEF_CHAR];
if (dbcsCode !== undefined) { // Write beginning of the sequence.
if (dbcsCode < 0x100) {
newBuf[j++] = dbcsCode;
}
else {
newBuf[j++] = dbcsCode >> 8; // high byte
newBuf[j++] = dbcsCode & 0xFF; // low byte
}
} else {
// See todo above.
}
this.seqObj = undefined;
}
if (this.leadSurrogate !== -1) {
// Incomplete surrogate pair - only lead surrogate found.
newBuf[j++] = this.defaultCharSingleByte;
this.leadSurrogate = -1;
}
return newBuf.slice(0, j);
}
// Export for testing
DBCSEncoder.prototype.findIdx = findIdx;
// == Decoder ==================================================================
function DBCSDecoder(options, codec) {
// Decoder state
this.nodeIdx = 0;
this.prevBytes = [];
// Static data
this.decodeTables = codec.decodeTables;
this.decodeTableSeq = codec.decodeTableSeq;
this.defaultCharUnicode = codec.defaultCharUnicode;
this.gb18030 = codec.gb18030;
}
DBCSDecoder.prototype.write = function(buf) {
var newBuf = Buffer.alloc(buf.length*2),
nodeIdx = this.nodeIdx,
prevBytes = this.prevBytes, prevOffset = this.prevBytes.length,
seqStart = -this.prevBytes.length, // idx of the start of current parsed sequence.
uCode;
for (var i = 0, j = 0; i < buf.length; i++) {
var curByte = (i >= 0) ? buf[i] : prevBytes[i + prevOffset];
// Lookup in current trie node.
var uCode = this.decodeTables[nodeIdx][curByte];
if (uCode >= 0) {
// Normal character, just use it.
}
else if (uCode === UNASSIGNED) { // Unknown char.
// TODO: Callback with seq.
uCode = this.defaultCharUnicode.charCodeAt(0);
i = seqStart; // Skip one byte ('i' will be incremented by the for loop) and try to parse again.
}
else if (uCode === GB18030_CODE) {
if (i >= 3) {
var ptr = (buf[i-3]-0x81)*12600 + (buf[i-2]-0x30)*1260 + (buf[i-1]-0x81)*10 + (curByte-0x30);
} else {
var ptr = (prevBytes[i-3+prevOffset]-0x81)*12600 +
(((i-2 >= 0) ? buf[i-2] : prevBytes[i-2+prevOffset])-0x30)*1260 +
(((i-1 >= 0) ? buf[i-1] : prevBytes[i-1+prevOffset])-0x81)*10 +
(curByte-0x30);
}
var idx = findIdx(this.gb18030.gbChars, ptr);
uCode = this.gb18030.uChars[idx] + ptr - this.gb18030.gbChars[idx];
}
else if (uCode <= NODE_START) { // Go to next trie node.
nodeIdx = NODE_START - uCode;
continue;
}
else if (uCode <= SEQ_START) { // Output a sequence of chars.
var seq = this.decodeTableSeq[SEQ_START - uCode];
for (var k = 0; k < seq.length - 1; k++) {
uCode = seq[k];
newBuf[j++] = uCode & 0xFF;
newBuf[j++] = uCode >> 8;
}
uCode = seq[seq.length-1];
}
else
throw new Error("iconv-lite internal error: invalid decoding table value " + uCode + " at " + nodeIdx + "/" + curByte);
// Write the character to buffer, handling higher planes using surrogate pair.
if (uCode >= 0x10000) {
uCode -= 0x10000;
var uCodeLead = 0xD800 | (uCode >> 10);
newBuf[j++] = uCodeLead & 0xFF;
newBuf[j++] = uCodeLead >> 8;
uCode = 0xDC00 | (uCode & 0x3FF);
}
newBuf[j++] = uCode & 0xFF;
newBuf[j++] = uCode >> 8;
// Reset trie node.
nodeIdx = 0; seqStart = i+1;
}
this.nodeIdx = nodeIdx;
this.prevBytes = (seqStart >= 0)
? Array.prototype.slice.call(buf, seqStart)
: prevBytes.slice(seqStart + prevOffset).concat(Array.prototype.slice.call(buf));
return newBuf.slice(0, j).toString('ucs2');
}
DBCSDecoder.prototype.end = function() {
var ret = '';
// Try to parse all remaining chars.
while (this.prevBytes.length > 0) {
// Skip 1 character in the buffer.
ret += this.defaultCharUnicode;
var bytesArr = this.prevBytes.slice(1);
// Parse remaining as usual.
this.prevBytes = [];
this.nodeIdx = 0;
if (bytesArr.length > 0)
ret += this.write(bytesArr);
}
this.prevBytes = [];
this.nodeIdx = 0;
return ret;
}
// Binary search for GB18030. Returns largest i such that table[i] <= val.
function findIdx(table, val) {
if (table[0] > val)
return -1;
var l = 0, r = table.length;
while (l < r-1) { // always table[l] <= val < table[r]
var mid = l + ((r-l+1) >> 1);
if (table[mid] <= val)
l = mid;
else
r = mid;
}
return l;
}
},{"safer-buffer":30}],2:[function(require,module,exports){
"use strict";
// Description of supported double byte encodings and aliases.
// Tables are not require()-d until they are needed to speed up library load.
// require()-s are direct to support Browserify.
module.exports = {
// == Japanese/ShiftJIS ====================================================
// All japanese encodings are based on JIS X set of standards:
// JIS X 0201 - Single-byte encoding of ASCII + ¥ + Kana chars at 0xA1-0xDF.
// JIS X 0208 - Main set of 6879 characters, placed in 94x94 plane, to be encoded by 2 bytes.
// Has several variations in 1978, 1983, 1990 and 1997.
// JIS X 0212 - Supplementary plane of 6067 chars in 94x94 plane. 1990. Effectively dead.
// JIS X 0213 - Extension and modern replacement of 0208 and 0212. Total chars: 11233.
// 2 planes, first is superset of 0208, second - revised 0212.
// Introduced in 2000, revised 2004. Some characters are in Unicode Plane 2 (0x2xxxx)
// Byte encodings are:
// * Shift_JIS: Compatible with 0201, uses not defined chars in top half as lead bytes for double-byte
// encoding of 0208. Lead byte ranges: 0x81-0x9F, 0xE0-0xEF; Trail byte ranges: 0x40-0x7E, 0x80-0x9E, 0x9F-0xFC.
// Windows CP932 is a superset of Shift_JIS. Some companies added more chars, notably KDDI.
// * EUC-JP: Up to 3 bytes per character. Used mostly on *nixes.
// 0x00-0x7F - lower part of 0201
// 0x8E, 0xA1-0xDF - upper part of 0201
// (0xA1-0xFE)x2 - 0208 plane (94x94).
// 0x8F, (0xA1-0xFE)x2 - 0212 plane (94x94).
// * JIS X 208: 7-bit, direct encoding of 0208. Byte ranges: 0x21-0x7E (94 values). Uncommon.
// Used as-is in ISO2022 family.
// * ISO2022-JP: Stateful encoding, with escape sequences to switch between ASCII,
// 0201-1976 Roman, 0208-1978, 0208-1983.
// * ISO2022-JP-1: Adds esc seq for 0212-1990.
// * ISO2022-JP-2: Adds esc seq for GB2313-1980, KSX1001-1992, ISO8859-1, ISO8859-7.
// * ISO2022-JP-3: Adds esc seq for 0201-1976 Kana set, 0213-2000 Planes 1, 2.
// * ISO2022-JP-2004: Adds 0213-2004 Plane 1.
//
// After JIS X 0213 appeared, Shift_JIS-2004, EUC-JISX0213 and ISO2022-JP-2004 followed, with just changing the planes.
//
// Overall, it seems that it's a mess :( http://www8.plala.or.jp/tkubota1/unicode-symbols-map2.html
'shiftjis': {
type: '_dbcs',
table: function() { return require('./tables/shiftjis.json') },
encodeAdd: {'\u00a5': 0x5C, '\u203E': 0x7E},
encodeSkipVals: [{from: 0xED40, to: 0xF940}],
},
'csshiftjis': 'shiftjis',
'mskanji': 'shiftjis',
'sjis': 'shiftjis',
'windows31j': 'shiftjis',
'ms31j': 'shiftjis',
'xsjis': 'shiftjis',
'windows932': 'shiftjis',
'ms932': 'shiftjis',
'932': 'shiftjis',
'cp932': 'shiftjis',
'eucjp': {
type: '_dbcs',
table: function() { return require('./tables/eucjp.json') },
encodeAdd: {'\u00a5': 0x5C, '\u203E': 0x7E},
},
// TODO: KDDI extension to Shift_JIS
// TODO: IBM CCSID 942 = CP932, but F0-F9 custom chars and other char changes.
// TODO: IBM CCSID 943 = Shift_JIS = CP932 with original Shift_JIS lower 128 chars.
// == Chinese/GBK ==========================================================
// http://en.wikipedia.org/wiki/GBK
// We mostly implement W3C recommendation: https://www.w3.org/TR/encoding/#gbk-encoder
// Oldest GB2312 (1981, ~7600 chars) is a subset of CP936
'gb2312': 'cp936',
'gb231280': 'cp936',
'gb23121980': 'cp936',
'csgb2312': 'cp936',
'csiso58gb231280': 'cp936',
'euccn': 'cp936',
// Microsoft's CP936 is a subset and approximation of GBK.
'windows936': 'cp936',
'ms936': 'cp936',
'936': 'cp936',
'cp936': {
type: '_dbcs',
table: function() { return require('./tables/cp936.json') },
},
// GBK (~22000 chars) is an extension of CP936 that added user-mapped chars and some other.
'gbk': {
type: '_dbcs',
table: function() { return require('./tables/cp936.json').concat(require('./tables/gbk-added.json')) },
},
'xgbk': 'gbk',
'isoir58': 'gbk',
// GB18030 is an algorithmic extension of GBK.
// Main source: https://www.w3.org/TR/encoding/#gbk-encoder
// http://icu-project.org/docs/papers/gb18030.html
// http://source.icu-project.org/repos/icu/data/trunk/charset/data/xml/gb-18030-2000.xml
// http://www.khngai.com/chinese/charmap/tblgbk.php?page=0
'gb18030': {
type: '_dbcs',
table: function() { return require('./tables/cp936.json').concat(require('./tables/gbk-added.json')) },
gb18030: function() { return require('./tables/gb18030-ranges.json') },
encodeSkipVals: [0x80],
encodeAdd: {'€': 0xA2E3},
},
'chinese': 'gb18030',
// == Korean ===============================================================
// EUC-KR, KS_C_5601 and KS X 1001 are exactly the same.
'windows949': 'cp949',
'ms949': 'cp949',
'949': 'cp949',
'cp949': {
type: '_dbcs',
table: function() { return require('./tables/cp949.json') },
},
'cseuckr': 'cp949',
'csksc56011987': 'cp949',
'euckr': 'cp949',
'isoir149': 'cp949',
'korean': 'cp949',
'ksc56011987': 'cp949',
'ksc56011989': 'cp949',
'ksc5601': 'cp949',
// == Big5/Taiwan/Hong Kong ================================================
// There are lots of tables for Big5 and cp950. Please see the following links for history:
// http://moztw.org/docs/big5/ http://www.haible.de/bruno/charsets/conversion-tables/Big5.html
// Variations, in roughly number of defined chars:
// * Windows CP 950: Microsoft variant of Big5. Canonical: http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT
// * Windows CP 951: Microsoft variant of Big5-HKSCS-2001. Seems to be never public. http://me.abelcheung.org/articles/research/what-is-cp951/
// * Big5-2003 (Taiwan standard) almost superset of cp950.
// * Unicode-at-on (UAO) / Mozilla 1.8. Falling out of use on the Web. Not supported by other browsers.
// * Big5-HKSCS (-2001, -2004, -2008). Hong Kong standard.
// many unicode code points moved from PUA to Supplementary plane (U+2XXXX) over the years.
// Plus, it has 4 combining sequences.
// Seems that Mozilla refused to support it for 10 yrs. https://bugzilla.mozilla.org/show_bug.cgi?id=162431 https://bugzilla.mozilla.org/show_bug.cgi?id=310299
// because big5-hkscs is the only encoding to include astral characters in non-algorithmic way.
// Implementations are not consistent within browsers; sometimes labeled as just big5.
// MS Internet Explorer switches from big5 to big5-hkscs when a patch applied.
// Great discussion & recap of what's going on https://bugzilla.mozilla.org/show_bug.cgi?id=912470#c31
// In the encoder, it might make sense to support encoding old PUA mappings to Big5 bytes seq-s.
// Official spec: http://www.ogcio.gov.hk/en/business/tech_promotion/ccli/terms/doc/2003cmp_2008.txt
// http://www.ogcio.gov.hk/tc/business/tech_promotion/ccli/terms/doc/hkscs-2008-big5-iso.txt
//
// Current understanding of how to deal with Big5(-HKSCS) is in the Encoding Standard, http://encoding.spec.whatwg.org/#big5-encoder
// Unicode mapping (http://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/OTHER/BIG5.TXT) is said to be wrong.
'windows950': 'cp950',
'ms950': 'cp950',
'950': 'cp950',
'cp950': {
type: '_dbcs',
table: function() { return require('./tables/cp950.json') },
},
// Big5 has many variations and is an extension of cp950. We use Encoding Standard's as a consensus.
'big5': 'big5hkscs',
'big5hkscs': {
type: '_dbcs',
table: function() { return require('./tables/cp950.json').concat(require('./tables/big5-added.json')) },
encodeSkipVals: [0xa2cc],
},
'cnbig5': 'big5hkscs',
'csbig5': 'big5hkscs',
'xxbig5': 'big5hkscs',
};
},{"./tables/big5-added.json":8,"./tables/cp936.json":9,"./tables/cp949.json":10,"./tables/cp950.json":11,"./tables/eucjp.json":12,"./tables/gb18030-ranges.json":13,"./tables/gbk-added.json":14,"./tables/shiftjis.json":15}],3:[function(require,module,exports){
"use strict";
// Update this array if you add/rename/remove files in this directory.
// We support Browserify by skipping automatic module discovery and requiring modules directly.
var modules = [
require("./internal"),
require("./utf32"),
require("./utf16"),
require("./utf7"),
require("./sbcs-codec"),
require("./sbcs-data"),
require("./sbcs-data-generated"),
require("./dbcs-codec"),
require("./dbcs-data"),
];
// Put all encoding/alias/codec definitions to single object and export it.
for (var i = 0; i < modules.length; i++) {
var module = modules[i];
for (var enc in module)
if (Object.prototype.hasOwnProperty.call(module, enc))
exports[enc] = module[enc];
}
},{"./dbcs-codec":1,"./dbcs-data":2,"./internal":4,"./sbcs-codec":5,"./sbcs-data":7,"./sbcs-data-generated":6,"./utf16":16,"./utf32":17,"./utf7":18}],4:[function(require,module,exports){
"use strict";
var Buffer = require("safer-buffer").Buffer;
// Export Node.js internal encodings.
module.exports = {
// Encodings
utf8: { type: "_internal", bomAware: true},
cesu8: { type: "_internal", bomAware: true},
unicode11utf8: "utf8",
ucs2: { type: "_internal", bomAware: true},
utf16le: "ucs2",
binary: { type: "_internal" },
base64: { type: "_internal" },
hex: { type: "_internal" },
// Codec.
_internal: InternalCodec,
};
//------------------------------------------------------------------------------
function InternalCodec(codecOptions, iconv) {
this.enc = codecOptions.encodingName;
this.bomAware = codecOptions.bomAware;
if (this.enc === "base64")
this.encoder = InternalEncoderBase64;
else if (this.enc === "cesu8") {
this.enc = "utf8"; // Use utf8 for decoding.
this.encoder = InternalEncoderCesu8;
// Add decoder for versions of Node not supporting CESU-8
if (Buffer.from('eda0bdedb2a9', 'hex').toString() !== '💩') {
this.decoder = InternalDecoderCesu8;
this.defaultCharUnicode = iconv.defaultCharUnicode;
}
}
}
InternalCodec.prototype.encoder = InternalEncoder;
InternalCodec.prototype.decoder = InternalDecoder;
//------------------------------------------------------------------------------
// We use node.js internal decoder. Its signature is the same as ours.
var StringDecoder = require('string_decoder').StringDecoder;
if (!StringDecoder.prototype.end) // Node v0.8 doesn't have this method.
StringDecoder.prototype.end = function() {};
function InternalDecoder(options, codec) {
this.decoder = new StringDecoder(codec.enc);
}
InternalDecoder.prototype.write = function(buf) {
if (!Buffer.isBuffer(buf)) {
buf = Buffer.from(buf);
}
return this.decoder.write(buf);
}
InternalDecoder.prototype.end = function() {
return this.decoder.end();
}
//------------------------------------------------------------------------------
// Encoder is mostly trivial
function InternalEncoder(options, codec) {
this.enc = codec.enc;
}
InternalEncoder.prototype.write = function(str) {
return Buffer.from(str, this.enc);
}
InternalEncoder.prototype.end = function() {
}
//------------------------------------------------------------------------------
// Except base64 encoder, which must keep its state.
function InternalEncoderBase64(options, codec) {
this.prevStr = '';
}
InternalEncoderBase64.prototype.write = function(str) {
str = this.prevStr + str;
var completeQuads = str.length - (str.length % 4);
this.prevStr = str.slice(completeQuads);
str = str.slice(0, completeQuads);
return Buffer.from(str, "base64");
}
InternalEncoderBase64.prototype.end = function() {
return Buffer.from(this.prevStr, "base64");
}
//------------------------------------------------------------------------------
// CESU-8 encoder is also special.
function InternalEncoderCesu8(options, codec) {
}
InternalEncoderCesu8.prototype.write = function(str) {
var buf = Buffer.alloc(str.length * 3), bufIdx = 0;
for (var i = 0; i < str.length; i++) {
var charCode = str.charCodeAt(i);
// Naive implementation, but it works because CESU-8 is especially easy
// to convert from UTF-16 (which all JS strings are encoded in).
if (charCode < 0x80)
buf[bufIdx++] = charCode;
else if (charCode < 0x800) {
buf[bufIdx++] = 0xC0 + (charCode >>> 6);
buf[bufIdx++] = 0x80 + (charCode & 0x3f);
}
else { // charCode will always be < 0x10000 in javascript.
buf[bufIdx++] = 0xE0 + (charCode >>> 12);
buf[bufIdx++] = 0x80 + ((charCode >>> 6) & 0x3f);
buf[bufIdx++] = 0x80 + (charCode & 0x3f);
}
}
return buf.slice(0, bufIdx);
}
InternalEncoderCesu8.prototype.end = function() {
}
//------------------------------------------------------------------------------
// CESU-8 decoder is not implemented in Node v4.0+
function InternalDecoderCesu8(options, codec) {
this.acc = 0;
this.contBytes = 0;
this.accBytes = 0;
this.defaultCharUnicode = codec.defaultCharUnicode;
}
InternalDecoderCesu8.prototype.write = function(buf) {
var acc = this.acc, contBytes = this.contBytes, accBytes = this.accBytes,
res = '';
for (var i = 0; i < buf.length; i++) {
var curByte = buf[i];
if ((curByte & 0xC0) !== 0x80) { // Leading byte
if (contBytes > 0) { // Previous code is invalid
res += this.defaultCharUnicode;
contBytes = 0;
}
if (curByte < 0x80) { // Single-byte code
res += String.fromCharCode(curByte);
} else if (curByte < 0xE0) { // Two-byte code
acc = curByte & 0x1F;
contBytes = 1; accBytes = 1;
} else if (curByte < 0xF0) { // Three-byte code
acc = curByte & 0x0F;
contBytes = 2; accBytes = 1;
} else { // Four or more are not supported for CESU-8.
res += this.defaultCharUnicode;
}
} else { // Continuation byte
if (contBytes > 0) { // We're waiting for it.
acc = (acc << 6) | (curByte & 0x3f);
contBytes--; accBytes++;
if (contBytes === 0) {
// Check for overlong encoding, but support Modified UTF-8 (encoding NULL as C0 80)
if (accBytes === 2 && acc < 0x80 && acc > 0)
res += this.defaultCharUnicode;
else if (accBytes === 3 && acc < 0x800)
res += this.defaultCharUnicode;
else
// Actually add character.
res += String.fromCharCode(acc);
}
} else { // Unexpected continuation byte
res += this.defaultCharUnicode;
}
}
}
this.acc = acc; this.contBytes = contBytes; this.accBytes = accBytes;
return res;
}
InternalDecoderCesu8.prototype.end = function() {
var res = 0;
if (this.contBytes > 0)
res += this.defaultCharUnicode;
return res;