forked from NeilFraser/JS-Interpreter
-
Notifications
You must be signed in to change notification settings - Fork 0
/
acorn.js
2283 lines (2079 loc) · 73.4 KB
/
acorn.js
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
/**
* @license
* Copyright 2012 Marijn Haverbeke
* SPDX-License-Identifier: MIT
*/
// Acorn is a tiny, fast JavaScript parser written in JavaScript.
//
// Acorn was written by Marijn Haverbeke and released under an MIT
// license. The Unicode regexps (for identifiers and whitespace) were
// taken from [Esprima](http://esprima.org) by Ariya Hidayat.
//
// Git repositories for Acorn are available at
//
// http://marijnhaverbeke.nl/git/acorn
// https://github.com/marijnh/acorn.git
//
// Please use the [github bug tracker][ghbt] to report issues.
//
// [ghbt]: https://github.com/marijnh/acorn/issues
//
// This file defines the main parser interface. The library also comes
// with a [error-tolerant parser][dammit] and an
// [abstract syntax tree walker][walk], defined in other files.
//
// [dammit]: acorn_loose.js
// [walk]: util/walk.js
(function(root, mod) {
if (typeof exports === "object" && typeof module === "object") return mod(exports); // CommonJS
if (typeof define === "function" && define.amd) return define(["exports"], mod); // AMD
mod(root.acorn || (root.acorn = {})); // Plain browser env
})((typeof globalThis === 'undefined') ? this || window : globalThis, function(exports) {
"use strict";
exports.version = "0.5.0";
// Plus additional edits marked with 'JS-Interpreter change' comments.
// JS-Interpreter change:
// For global object, use 'globalThis' if it exists,
// fall back to 'this' or 'window'. Same logic as in JS-Interpreter.
// -- Neil Fraser, March 2024.
// JS-Interpreter change:
// Added JSDoc type definitions.
// -- Neil Fraser, July 2023.
// JS-Interpreter change:
// No longer exporting defaultOptions, getLineInfo, tokenize, tokTypes,
// isIdentifierStart, and isIdentifierChar. Not used by JS-Interpreter.
// -- Neil Fraser, February 2023.
// The main exported interface (under `self.acorn` when in the
// browser) is a `parse` function that takes a code string and
// returns an abstract syntax tree as specified by [Mozilla parser
// API][api], with the caveat that the SpiderMonkey-specific syntax
// (`let`, `yield`, inline XML, etc) is not recognized.
//
// [api]: https://developer.mozilla.org/en-US/docs/SpiderMonkey/Parser_API
/** @type {!Object|undefined} */
var options;
/** @type {string} */
var input = '';
/** @type {number|undefined} */
var inputLen;
/** @type {*} */
var sourceFile;
/**
* @param {string} inpt
* @param {Object=} opts
* @returns
*/
exports.parse = function(inpt, opts) {
input = String(inpt);
inputLen = input.length;
setOptions(opts);
initTokenState();
return parseTopLevel(options.program);
};
// A second optional argument can be given to further configure
// the parser process. These options are recognized:
var defaultOptions = {
// JS-Interpreter change:
// `ecmaVersion` option has been removed along with all cases where
// it is checked. In this version of Acorn it was limited to 3 or 5,
// and there's no use case for 3 with JS-Interpreter.
// -- Neil Fraser, December 2022.
// Turn on `strictSemicolons` to prevent the parser from doing
// automatic semicolon insertion.
strictSemicolons: false,
// When `allowTrailingCommas` is false, the parser will not allow
// trailing commas in array and object literals.
allowTrailingCommas: true,
// By default, reserved words are not enforced. Enable
// `forbidReserved` to enforce them. When this option has the
// value "everywhere", reserved words and keywords can also not be
// used as property names.
forbidReserved: false,
// When enabled, a return at the top level is not considered an
// error.
allowReturnOutsideFunction: false,
// When `locations` is on, `loc` properties holding objects with
// `start` and `end` properties in `{line, column}` form (with
// line being 1-based and column 0-based) will be attached to the
// nodes.
locations: false,
// A function can be passed as `onComment` option, which will
// cause Acorn to call that function with `(block, text, start,
// end)` parameters whenever a comment is skipped. `block` is a
// boolean indicating whether this is a block (`/* */`) comment,
// `text` is the content of the comment, and `start` and `end` are
// character offsets that denote the start and end of the comment.
// When the `locations` option is on, two more parameters are
// passed, the full `{line, column}` locations of the start and
// end of the comments. Note that you are not allowed to call the
// parser from the callback—that will corrupt its internal state.
onComment: null,
// Nodes have their start and end characters offsets recorded in
// `start` and `end` properties (directly on the node, rather than
// the `loc` object, which holds line/column data. To also add a
// [semi-standardized][range] `range` property holding a `[start,
// end]` array with the same numbers, set the `ranges` option to
// `true`.
//
// [range]: https://bugzilla.mozilla.org/show_bug.cgi?id=745678
ranges: false,
// It is possible to parse multiple files into a single AST by
// passing the tree produced by parsing the first file as
// `program` option in subsequent parses. This will add the
// toplevel forms of the parsed file to the `Program` (top) node
// of an existing parse tree.
program: null,
// When `locations` is on, you can pass this to record the source
// file in every node's `loc` object.
sourceFile: null,
// This value, if given, is stored in every node, whether
// `locations` is on or off.
directSourceFile: null,
};
/**
* @param {Object|undefined} opts
*/
function setOptions(opts) {
options = opts || {};
for (var opt in defaultOptions) {
if (!Object.prototype.hasOwnProperty.call(options, opt)) {
options[opt] = defaultOptions[opt];
}
}
sourceFile = options.sourceFile;
}
/**
* The `getLineInfo` function is mostly useful when the
* `locations` option is off (for performance reasons) and you
* want to find the line/column position for a given character
* offset. `input` should be the code string that the offset refers
* into.
*
* @param {string} input
* @param {number} offset
* @returns {!Object}
*/
var getLineInfo = function(input, offset) {
for (var line = 1, cur = 0;;) {
lineBreak.lastIndex = cur;
var match = lineBreak.exec(input);
if (match && match.index < offset) {
++line;
cur = match.index + match[0].length;
} else {
break;
}
}
return {line: line, column: offset - cur};
};
// JS-Interpreter change:
// tokenize function never used. Removed.
// -- Neil Fraser, February 2023.
// State is kept in (closure-)global variables. We already saw the
// `options`, `input`, and `inputLen` variables above.
/**
* The current position of the tokenizer in the input.
* @type {number}
*/
var tokPos = 0;
/**
* The start offset of the current token.
* @type {number}
*/
var tokStart = 0;
/**
* The end offset of the current token.
* @type {number}
*/
var tokEnd = 0;
/**
* When `options.locations` is true, holds object
* containing the token's start line/column pairs.
* @type {!line_loc_t|undefined}
*/
var tokStartLoc;
/**
* When `options.locations` is true, holds object
* containing the token's end line/column pairs.
* @type {!line_loc_t|undefined}
*/
var tokEndLoc;
/**
* The type of the current token. Token types are objects,
* named by variables against which they can be compared, and
* holding properties that describe them (indicating, for example,
* the precedence of an infix operator, and the original name of a
* keyword token).
* @type {!Object|undefined}
*/
var tokType;
/**
* The value of the current token. The kind of value that's held in
* `tokVal` depends on the type of the token. For literals, it is the
* literal value, for operators, the operator name, and so on.
* @type {*}
*/
var tokVal;
/**
* Interal state for the tokenizer. To distinguish between division
* operators and regular expressions, it remembers whether the last
* token was one that is allowed to be followed by an expression.
* (If it is, a slash is probably a regexp, if it isn't it's a
* division operator. See the `parseStatement` function for a caveat.)
* @type {boolean|undefined}
*/
var tokRegexpAllowed;
/**
* When `options.locations` is true, `tokCurLine` is used to keep
* track of the current line.
* @type {number|undefined}
*/
var tokCurLine;
/**
* When `options.locations` is true, `tokLineStart` is used to know
* when a new line has been entered.
* @type {number|undefined}
*/
var tokLineStart;
/**
* The start of the position of the previous token, which is useful
* when finishing a node and assigning its `end` position.
* @type {number}
*/
var lastStart = 0;
/**
* The end oy the position of the previous token, which is useful
* when finishing a node and assigning its `end` position.
* @type {number}
*/
var lastEnd = 0;
/**
* Stores the position of the previous token, which is useful
* when finishing a node and assigning its `end` position.
* @type {!line_loc_t|undefined}
*/
var lastEndLoc;
/**
* `inFunction` is used to reject `return` statements outside of functions.
* @type {boolean|undefined}
*/
var inFunction;
/**
* `labels` is used to verify that `break` and `continue` have somewhere
* to jump to.
* @type {!Array<!Object>|undefined}
*/
var labels;
/**
* `strict` indicates whether strict mode is on.
* @type {boolean|undefined}
*/
var strict;
/**
* This function is used to raise exceptions on parse errors. It
* takes an offset integer (into the current `input`) to indicate
* the location of the error, attaches the position to the end
* of the error message, and then raises a `SyntaxError` with that
* message.
*
* @param {number} pos
* @param {string} message
* @throws {SyntaxError}
*/
function raise(pos, message) {
var loc = getLineInfo(input, pos);
message += " (" + loc.line + ":" + loc.column + ")";
var err = new SyntaxError(message);
err.pos = pos;
err.loc = loc;
err.raisedAt = tokPos;
throw err;
}
// Reused empty array added for node fields that are always empty.
var empty = [];
// ## Token types
// The assignment of fine-grained, information-carrying type objects
// allows the tokenizer to store the information it has about a
// token in a way that is very cheap for the parser to look up.
// All token type variables start with an underscore, to make them
// easy to recognize.
// These are the general types. The `type` property is only used to
// make them recognizeable when debugging.
var _num = {type: "num"};
var _regexp = {type: "regexp"};
var _string = {type: "string"};
var _name = {type: "name"};
var _eof = {type: "eof"};
// Keyword tokens. The `keyword` property (also used in keyword-like
// operators) indicates that the token originated from an
// identifier-like word, which is used when parsing property names.
//
// The `beforeExpr` property is used to disambiguate between regular
// expressions and divisions. It is set on all token types that can
// be followed by an expression (thus, a slash after them would be a
// regular expression).
//
// `isLoop` marks a keyword as starting a loop, which is important
// to know when parsing a label, in order to allow or disallow
// continue jumps to that label.
var _break = {keyword: "break"};
var _case = {keyword: "case", beforeExpr: true};
var _catch = {keyword: "catch"};
var _continue = {keyword: "continue"};
var _debugger = {keyword: "debugger"};
var _default = {keyword: "default"};
var _do = {keyword: "do", isLoop: true};
var _else = {keyword: "else", beforeExpr: true};
var _finally = {keyword: "finally"};
var _for = {keyword: "for", isLoop: true};
var _function = {keyword: "function"};
var _if = {keyword: "if"};
var _return = {keyword: "return", beforeExpr: true};
var _switch = {keyword: "switch"};
var _throw = {keyword: "throw", beforeExpr: true};
var _try = {keyword: "try"};
var _var = {keyword: "var"};
var _while = {keyword: "while", isLoop: true};
var _with = {keyword: "with"};
var _new = {keyword: "new", beforeExpr: true};
var _this = {keyword: "this"};
// The keywords that denote values.
var _null = {keyword: "null", atomValue: null};
var _true = {keyword: "true", atomValue: true};
var _false = {keyword: "false", atomValue: false};
// Some keywords are treated as regular operators. `in` sometimes
// (when parsing `for`) needs to be tested against specifically, so
// we assign a variable name to it for quick comparing.
var _in = {keyword: "in", binop: 7, beforeExpr: true};
// Map keyword names to token types.
var keywordTypes = {
"break": _break,
"case": _case,
"catch": _catch,
"continue": _continue,
"debugger": _debugger,
"default": _default,
"do": _do,
"else": _else,
"finally": _finally,
"for": _for,
"function": _function,
"if": _if,
"return": _return,
"switch": _switch,
"throw": _throw,
"try": _try,
"var": _var,
"while": _while,
"with": _with,
"null": _null,
"true": _true,
"false": _false,
"new": _new,
"in": _in,
"instanceof": {keyword: "instanceof", binop: 7, beforeExpr: true},
"this": _this,
"typeof": {keyword: "typeof", prefix: true, beforeExpr: true},
"void": {keyword: "void", prefix: true, beforeExpr: true},
"delete": {keyword: "delete", prefix: true, beforeExpr: true},
};
// Punctuation token types. Again, the `type` property is purely for debugging.
var _bracketL = {type: "[", beforeExpr: true};
var _bracketR = {type: "]"};
var _braceL = {type: "{", beforeExpr: true};
var _braceR = {type: "}"};
var _parenL = {type: "(", beforeExpr: true};
var _parenR = {type: ")"};
var _comma = {type: ",", beforeExpr: true};
var _semi = {type: ";", beforeExpr: true};
var _colon = {type: ":", beforeExpr: true};
var _dot = {type: "."};
var _question = {type: "?", beforeExpr: true};
// Operators. These carry several kinds of properties to help the
// parser use them properly (the presence of these properties is
// what categorizes them as operators).
//
// `binop`, when present, specifies that this operator is a binary
// operator, and will refer to its precedence.
//
// `prefix` and `postfix` mark the operator as a prefix or postfix
// unary operator. `isUpdate` specifies that the node produced by
// the operator should be of type UpdateExpression rather than
// simply UnaryExpression (`++` and `--`).
//
// `isAssign` marks all of `=`, `+=`, `-=` etcetera, which act as
// binary operators with a very low precedence, that should result
// in AssignmentExpression nodes.
var _slash = {binop: 10, beforeExpr: true};
var _eq = {isAssign: true, beforeExpr: true};
var _assign = {isAssign: true, beforeExpr: true};
var _incDec = {postfix: true, prefix: true, isUpdate: true};
var _prefix = {prefix: true, beforeExpr: true};
var _logicalOR = {binop: 1, beforeExpr: true};
var _logicalAND = {binop: 2, beforeExpr: true};
var _bitwiseOR = {binop: 3, beforeExpr: true};
var _bitwiseXOR = {binop: 4, beforeExpr: true};
var _bitwiseAND = {binop: 5, beforeExpr: true};
var _equality = {binop: 6, beforeExpr: true};
var _relational = {binop: 7, beforeExpr: true};
var _bitShift = {binop: 8, beforeExpr: true};
var _plusMin = {binop: 9, prefix: true, beforeExpr: true};
var _multiplyModulo = {binop: 10, beforeExpr: true};
// JS-Interpreter change:
// tokTypes map never used. Removed.
// -- Neil Fraser, February 2023.
// JS-Interpreter change:
// Acorn's original code built up functions using strings for maximum efficiency.
// However, this triggered a CSP unsafe-eval requirement. Here's a slower, but
// simpler approach. -- Neil Fraser, January 2022.
// https://github.com/NeilFraser/JS-Interpreter/issues/228
/**
* @param {string} words
* @returns {function(*): boolean}
*/
function makePredicate(words) {
var wordList = words.split(" ");
var set = Object.create(null);
for (var i = 0; i < wordList.length; i++) {
set[wordList[i]] = true;
}
return function(str) {
return set[str] || false;
};
}
// ECMAScript 5 reserved words.
var isReservedWord5 = makePredicate("class enum extends super const export import");
// The additional reserved words in strict mode.
var isStrictReservedWord = makePredicate("implements interface let package private protected public static yield");
// The forbidden variable names in strict mode.
var isStrictBadIdWord = makePredicate("eval arguments");
// And the keywords.
var isKeyword = makePredicate("break case catch continue debugger default do else finally for function if return switch throw try var while with null true false instanceof typeof void delete new in this");
// ## Character categories
// Big ugly regular expressions that match characters in the
// whitespace, identifier, and identifier-start categories. These
// are only applied when a character is found to actually have a
// code point above 128.
var nonASCIIwhitespace = /[\u1680\u180e\u2000-\u200a\u202f\u205f\u3000\ufeff]/;
var nonASCIIidentifierStartChars = "\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\u02c1\u02c6-\u02d1\u02e0-\u02e4\u02ec\u02ee\u0370-\u0374\u0376\u0377\u037a-\u037d\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03a3-\u03f5\u03f7-\u0481\u048a-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05d0-\u05ea\u05f0-\u05f2\u0620-\u064a\u066e\u066f\u0671-\u06d3\u06d5\u06e5\u06e6\u06ee\u06ef\u06fa-\u06fc\u06ff\u0710\u0712-\u072f\u074d-\u07a5\u07b1\u07ca-\u07ea\u07f4\u07f5\u07fa\u0800-\u0815\u081a\u0824\u0828\u0840-\u0858\u08a0\u08a2-\u08ac\u0904-\u0939\u093d\u0950\u0958-\u0961\u0971-\u0977\u0979-\u097f\u0985-\u098c\u098f\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09bd\u09ce\u09dc\u09dd\u09df-\u09e1\u09f0\u09f1\u0a05-\u0a0a\u0a0f\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32\u0a33\u0a35\u0a36\u0a38\u0a39\u0a59-\u0a5c\u0a5e\u0a72-\u0a74\u0a85-\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2\u0ab3\u0ab5-\u0ab9\u0abd\u0ad0\u0ae0\u0ae1\u0b05-\u0b0c\u0b0f\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32\u0b33\u0b35-\u0b39\u0b3d\u0b5c\u0b5d\u0b5f-\u0b61\u0b71\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99\u0b9a\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8-\u0baa\u0bae-\u0bb9\u0bd0\u0c05-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c33\u0c35-\u0c39\u0c3d\u0c58\u0c59\u0c60\u0c61\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cbd\u0cde\u0ce0\u0ce1\u0cf1\u0cf2\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d3a\u0d3d\u0d4e\u0d60\u0d61\u0d7a-\u0d7f\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0e01-\u0e30\u0e32\u0e33\u0e40-\u0e46\u0e81\u0e82\u0e84\u0e87\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa\u0eab\u0ead-\u0eb0\u0eb2\u0eb3\u0ebd\u0ec0-\u0ec4\u0ec6\u0edc-\u0edf\u0f00\u0f40-\u0f47\u0f49-\u0f6c\u0f88-\u0f8c\u1000-\u102a\u103f\u1050-\u1055\u105a-\u105d\u1061\u1065\u1066\u106e-\u1070\u1075-\u1081\u108e\u10a0-\u10c5\u10c7\u10cd\u10d0-\u10fa\u10fc-\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1288\u128a-\u128d\u1290-\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12d6\u12d8-\u1310\u1312-\u1315\u1318-\u135a\u1380-\u138f\u13a0-\u13f4\u1401-\u166c\u166f-\u167f\u1681-\u169a\u16a0-\u16ea\u16ee-\u16f0\u1700-\u170c\u170e-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176c\u176e-\u1770\u1780-\u17b3\u17d7\u17dc\u1820-\u1877\u1880-\u18a8\u18aa\u18b0-\u18f5\u1900-\u191c\u1950-\u196d\u1970-\u1974\u1980-\u19ab\u19c1-\u19c7\u1a00-\u1a16\u1a20-\u1a54\u1aa7\u1b05-\u1b33\u1b45-\u1b4b\u1b83-\u1ba0\u1bae\u1baf\u1bba-\u1be5\u1c00-\u1c23\u1c4d-\u1c4f\u1c5a-\u1c7d\u1ce9-\u1cec\u1cee-\u1cf1\u1cf5\u1cf6\u1d00-\u1dbf\u1e00-\u1f15\u1f18-\u1f1d\u1f20-\u1f45\u1f48-\u1f4d\u1f50-\u1f57\u1f59\u1f5b\u1f5d\u1f5f-\u1f7d\u1f80-\u1fb4\u1fb6-\u1fbc\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fcc\u1fd0-\u1fd3\u1fd6-\u1fdb\u1fe0-\u1fec\u1ff2-\u1ff4\u1ff6-\u1ffc\u2071\u207f\u2090-\u209c\u2102\u2107\u210a-\u2113\u2115\u2119-\u211d\u2124\u2126\u2128\u212a-\u212d\u212f-\u2139\u213c-\u213f\u2145-\u2149\u214e\u2160-\u2188\u2c00-\u2c2e\u2c30-\u2c5e\u2c60-\u2ce4\u2ceb-\u2cee\u2cf2\u2cf3\u2d00-\u2d25\u2d27\u2d2d\u2d30-\u2d67\u2d6f\u2d80-\u2d96\u2da0-\u2da6\u2da8-\u2dae\u2db0-\u2db6\u2db8-\u2dbe\u2dc0-\u2dc6\u2dc8-\u2dce\u2dd0-\u2dd6\u2dd8-\u2dde\u2e2f\u3005-\u3007\u3021-\u3029\u3031-\u3035\u3038-\u303c\u3041-\u3096\u309d-\u309f\u30a1-\u30fa\u30fc-\u30ff\u3105-\u312d\u3131-\u318e\u31a0-\u31ba\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fcc\ua000-\ua48c\ua4d0-\ua4fd\ua500-\ua60c\ua610-\ua61f\ua62a\ua62b\ua640-\ua66e\ua67f-\ua697\ua6a0-\ua6ef\ua717-\ua71f\ua722-\ua788\ua78b-\ua78e\ua790-\ua793\ua7a0-\ua7aa\ua7f8-\ua801\ua803-\ua805\ua807-\ua80a\ua80c-\ua822\ua840-\ua873\ua882-\ua8b3\ua8f2-\ua8f7\ua8fb\ua90a-\ua925\ua930-\ua946\ua960-\ua97c\ua984-\ua9b2\ua9cf\uaa00-\uaa28\uaa40-\uaa42\uaa44-\uaa4b\uaa60-\uaa76\uaa7a\uaa80-\uaaaf\uaab1\uaab5\uaab6\uaab9-\uaabd\uaac0\uaac2\uaadb-\uaadd\uaae0-\uaaea\uaaf2-\uaaf4\uab01-\uab06\uab09-\uab0e\uab11-\uab16\uab20-\uab26\uab28-\uab2e\uabc0-\uabe2\uac00-\ud7a3\ud7b0-\ud7c6\ud7cb-\ud7fb\uf900-\ufa6d\ufa70-\ufad9\ufb00-\ufb06\ufb13-\ufb17\ufb1d\ufb1f-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40\ufb41\ufb43\ufb44\ufb46-\ufbb1\ufbd3-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdfb\ufe70-\ufe74\ufe76-\ufefc\uff21-\uff3a\uff41-\uff5a\uff66-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc";
var nonASCIIidentifierChars = "\u0300-\u036f\u0483-\u0487\u0591-\u05bd\u05bf\u05c1\u05c2\u05c4\u05c5\u05c7\u0610-\u061a\u0620-\u0649\u0672-\u06d3\u06e7-\u06e8\u06fb-\u06fc\u0730-\u074a\u0800-\u0814\u081b-\u0823\u0825-\u0827\u0829-\u082d\u0840-\u0857\u08e4-\u08fe\u0900-\u0903\u093a-\u093c\u093e-\u094f\u0951-\u0957\u0962-\u0963\u0966-\u096f\u0981-\u0983\u09bc\u09be-\u09c4\u09c7\u09c8\u09d7\u09df-\u09e0\u0a01-\u0a03\u0a3c\u0a3e-\u0a42\u0a47\u0a48\u0a4b-\u0a4d\u0a51\u0a66-\u0a71\u0a75\u0a81-\u0a83\u0abc\u0abe-\u0ac5\u0ac7-\u0ac9\u0acb-\u0acd\u0ae2-\u0ae3\u0ae6-\u0aef\u0b01-\u0b03\u0b3c\u0b3e-\u0b44\u0b47\u0b48\u0b4b-\u0b4d\u0b56\u0b57\u0b5f-\u0b60\u0b66-\u0b6f\u0b82\u0bbe-\u0bc2\u0bc6-\u0bc8\u0bca-\u0bcd\u0bd7\u0be6-\u0bef\u0c01-\u0c03\u0c46-\u0c48\u0c4a-\u0c4d\u0c55\u0c56\u0c62-\u0c63\u0c66-\u0c6f\u0c82\u0c83\u0cbc\u0cbe-\u0cc4\u0cc6-\u0cc8\u0cca-\u0ccd\u0cd5\u0cd6\u0ce2-\u0ce3\u0ce6-\u0cef\u0d02\u0d03\u0d46-\u0d48\u0d57\u0d62-\u0d63\u0d66-\u0d6f\u0d82\u0d83\u0dca\u0dcf-\u0dd4\u0dd6\u0dd8-\u0ddf\u0df2\u0df3\u0e34-\u0e3a\u0e40-\u0e45\u0e50-\u0e59\u0eb4-\u0eb9\u0ec8-\u0ecd\u0ed0-\u0ed9\u0f18\u0f19\u0f20-\u0f29\u0f35\u0f37\u0f39\u0f41-\u0f47\u0f71-\u0f84\u0f86-\u0f87\u0f8d-\u0f97\u0f99-\u0fbc\u0fc6\u1000-\u1029\u1040-\u1049\u1067-\u106d\u1071-\u1074\u1082-\u108d\u108f-\u109d\u135d-\u135f\u170e-\u1710\u1720-\u1730\u1740-\u1750\u1772\u1773\u1780-\u17b2\u17dd\u17e0-\u17e9\u180b-\u180d\u1810-\u1819\u1920-\u192b\u1930-\u193b\u1951-\u196d\u19b0-\u19c0\u19c8-\u19c9\u19d0-\u19d9\u1a00-\u1a15\u1a20-\u1a53\u1a60-\u1a7c\u1a7f-\u1a89\u1a90-\u1a99\u1b46-\u1b4b\u1b50-\u1b59\u1b6b-\u1b73\u1bb0-\u1bb9\u1be6-\u1bf3\u1c00-\u1c22\u1c40-\u1c49\u1c5b-\u1c7d\u1cd0-\u1cd2\u1d00-\u1dbe\u1e01-\u1f15\u200c\u200d\u203f\u2040\u2054\u20d0-\u20dc\u20e1\u20e5-\u20f0\u2d81-\u2d96\u2de0-\u2dff\u3021-\u3028\u3099\u309a\ua640-\ua66d\ua674-\ua67d\ua69f\ua6f0-\ua6f1\ua7f8-\ua800\ua806\ua80b\ua823-\ua827\ua880-\ua881\ua8b4-\ua8c4\ua8d0-\ua8d9\ua8f3-\ua8f7\ua900-\ua909\ua926-\ua92d\ua930-\ua945\ua980-\ua983\ua9b3-\ua9c0\uaa00-\uaa27\uaa40-\uaa41\uaa4c-\uaa4d\uaa50-\uaa59\uaa7b\uaae0-\uaae9\uaaf2-\uaaf3\uabc0-\uabe1\uabec\uabed\uabf0-\uabf9\ufb20-\ufb28\ufe00-\ufe0f\ufe20-\ufe26\ufe33\ufe34\ufe4d-\ufe4f\uff10-\uff19\uff3f";
var nonASCIIidentifierStart = new RegExp("[" + nonASCIIidentifierStartChars + "]");
var nonASCIIidentifier = new RegExp("[" + nonASCIIidentifierStartChars + nonASCIIidentifierChars + "]");
// Whether a single character denotes a newline.
var newline = /[\n\r\u2028\u2029]/;
// Matches a whole line break (where CRLF is considered a single
// line break). Used to count lines.
var lineBreak = /\r\n|[\n\r\u2028\u2029]/g;
/**
* Test whether a given character code starts an identifier.
*
* @param {number} code
* @returns {boolean}
*/
var isIdentifierStart = function(code) {
if (code < 65) return code === 36;
if (code < 91) return true;
if (code < 97) return code === 95;
if (code < 123) return true;
return code >= 0xaa && nonASCIIidentifierStart.test(String.fromCharCode(code));
};
/**
* Test whether a given character is part of an identifier.
*
* @param {number} code
* @returns {boolean}
*/
var isIdentifierChar = function(code) {
if (code < 48) return code === 36;
if (code < 58) return true;
if (code < 65) return false;
if (code < 91) return true;
if (code < 97) return code === 95;
if (code < 123) return true;
return code >= 0xaa && nonASCIIidentifier.test(String.fromCharCode(code));
};
// ## Tokenizer
/**
* These are used when `options.locations` is on, for the
* `tokStartLoc` and `tokEndLoc` properties.
* @constructor
*/
function line_loc_t() {
this.line = tokCurLine;
this.column = tokPos - tokLineStart;
}
/**
* Reset the token state. Used at the start of a parse.
*/
function initTokenState() {
tokCurLine = 1;
tokPos = tokLineStart = 0;
tokRegexpAllowed = true;
skipSpace();
}
/**
* Called at the end of every token. Sets `tokEnd`, `tokVal`, and
* `tokRegexpAllowed`, and skips the space after the token, so that
* the next one's `tokStart` will point at the right position.
*
* @param {!Object} type
* @param {*=} val
*/
function finishToken(type, val) {
tokEnd = tokPos;
if (options.locations) {
tokEndLoc = new line_loc_t();
}
tokType = type;
skipSpace();
tokVal = val;
tokRegexpAllowed = type.beforeExpr;
}
function skipBlockComment() {
var startLoc = options.onComment && options.locations && new line_loc_t();
var start = tokPos;
var end = input.indexOf("*/", tokPos += 2);
if (end === -1) {
raise(tokPos - 2, "Unterminated comment");
}
tokPos = end + 2;
if (options.locations) {
lineBreak.lastIndex = start;
var match;
while ((match = lineBreak.exec(input)) && match.index < tokPos) {
++tokCurLine;
tokLineStart = match.index + match[0].length;
}
}
if (options.onComment) {
options.onComment(true, input.slice(start + 2, end), start, tokPos,
startLoc, options.locations && new line_loc_t());
}
}
function skipLineComment() {
var start = tokPos;
var startLoc = options.onComment && options.locations && new line_loc_t();
var ch = input.charCodeAt(tokPos += 2);
while (tokPos < inputLen && ch !== 10 && ch !== 13 && ch !== 8232 && ch !== 8233) {
++tokPos;
ch = input.charCodeAt(tokPos);
}
if (options.onComment) {
options.onComment(false, input.slice(start + 2, tokPos), start, tokPos,
startLoc, options.locations && new line_loc_t());
}
}
// Called at the start of the parse and after every token. Skips
// whitespace and comments, and.
function skipSpace() {
while (tokPos < inputLen) {
var ch = input.charCodeAt(tokPos);
if (ch === 32) { // ' '
++tokPos;
} else if (ch === 13) {
++tokPos;
var next = input.charCodeAt(tokPos);
if (next === 10) {
++tokPos;
}
if (options.locations) {
++tokCurLine;
tokLineStart = tokPos;
}
} else if (ch === 10 || ch === 8232 || ch === 8233) {
++tokPos;
if (options.locations) {
++tokCurLine;
tokLineStart = tokPos;
}
} else if (ch > 8 && ch < 14) {
++tokPos;
} else if (ch === 47) { // '/'
var next = input.charCodeAt(tokPos + 1);
if (next === 42) { // '*'
skipBlockComment();
} else if (next === 47) { // '/'
skipLineComment();
} else break;
} else if (ch === 160) { // '\xa0'
++tokPos;
} else if (ch >= 5760 && nonASCIIwhitespace.test(String.fromCharCode(ch))) {
++tokPos;
} else {
break;
}
}
}
// ### Token reading
// This is the function that is called to fetch the next token. It
// is somewhat obscure, because it works in character codes rather
// than characters, and because operator parsing has been inlined
// into it.
//
// All in the name of speed.
//
// The `forceRegexp` parameter is used in the one case where the
// `tokRegexpAllowed` trick does not work. See `parseStatement`.
function readToken_dot() {
var next = input.charCodeAt(tokPos + 1);
if (next >= 48 && next <= 57) {
readNumber(true);
} else {
++tokPos;
finishToken(_dot);
}
}
function readToken_slash() { // '/'
var next = input.charCodeAt(tokPos + 1);
if (tokRegexpAllowed) {
++tokPos;
readRegexp();
} else if (next === 61) {
finishOp(_assign, 2);
} else {
finishOp(_slash, 1);
}
}
function readToken_mult_modulo() { // '%*'
var next = input.charCodeAt(tokPos + 1);
if (next === 61) {
finishOp(_assign, 2);
} else {
finishOp(_multiplyModulo, 1);
}
}
/**
* @param {number} code
*/
function readToken_pipe_amp(code) { // '|&'
var next = input.charCodeAt(tokPos + 1);
if (next === code) {
finishOp(code === 124 ? _logicalOR : _logicalAND, 2);
} else if (next === 61) {
finishOp(_assign, 2);
} else {
finishOp(code === 124 ? _bitwiseOR : _bitwiseAND, 1);
}
}
function readToken_caret() { // '^'
var next = input.charCodeAt(tokPos + 1);
if (next === 61) {
finishOp(_assign, 2);
} else {
finishOp(_bitwiseXOR, 1);
}
}
/**
* @param {number} code
*/
function readToken_plus_min(code) { // '+-'
var next = input.charCodeAt(tokPos + 1);
if (next === code) {
if (next === 45 && input.charCodeAt(tokPos + 2) === 62 &&
newline.test(input.slice(lastEnd, tokPos))) {
// A `-->` line comment
tokPos += 3;
skipLineComment();
skipSpace();
readToken();
return;
}
finishOp(_incDec, 2);
} else if (next === 61) {
finishOp(_assign, 2);
} else {
finishOp(_plusMin, 1);
}
}
/**
* @param {number} code
*/
function readToken_lt_gt(code) { // '<>'
var next = input.charCodeAt(tokPos + 1);
var size = 1;
if (next === code) {
size = (code === 62 && input.charCodeAt(tokPos + 2) === 62) ? 3 : 2;
if (input.charCodeAt(tokPos + size) === 61) {
finishOp(_assign, size + 1);
} else {
finishOp(_bitShift, size);
}
return;
}
if (next === 33 && code === 60 && input.charCodeAt(tokPos + 2) === 45 &&
input.charCodeAt(tokPos + 3) === 45) {
// `<!--`, an XML-style comment that should be interpreted as a line comment
tokPos += 4;
skipLineComment();
skipSpace();
readToken();
return;
}
if (next === 61) {
size = input.charCodeAt(tokPos + 2) === 61 ? 3 : 2;
}
finishOp(_relational, size);
}
/**
* @param {number} code
*/
function readToken_eq_excl(code) { // '=!'
var next = input.charCodeAt(tokPos + 1);
if (next === 61) {
finishOp(_equality, input.charCodeAt(tokPos + 2) === 61 ? 3 : 2);
} else {
finishOp(code === 61 ? _eq : _prefix, 1);
}
}
/**
* @param {number} code
* @returns {boolean|undefined}
*/
function getTokenFromCode(code) {
switch(code) {
// The interpretation of a dot depends on whether it is followed
// by a digit.
case 46: // '.'
return readToken_dot();
// Punctuation tokens.
case 40: ++tokPos; return finishToken(_parenL);
case 41: ++tokPos; return finishToken(_parenR);
case 59: ++tokPos; return finishToken(_semi);
case 44: ++tokPos; return finishToken(_comma);
case 91: ++tokPos; return finishToken(_bracketL);
case 93: ++tokPos; return finishToken(_bracketR);
case 123: ++tokPos; return finishToken(_braceL);
case 125: ++tokPos; return finishToken(_braceR);
case 58: ++tokPos; return finishToken(_colon);
case 63: ++tokPos; return finishToken(_question);
// '0x' is a hexadecimal number.
case 48: // '0'
var next = input.charCodeAt(tokPos + 1);
if (next === 120 || next === 88) return readHexNumber();
// Anything else beginning with a digit is an integer, octal
// number, or float.
case 49: case 50: case 51: case 52: case 53: case 54: case 55: case 56: case 57: // 1-9
return readNumber(false);
// Quotes produce strings.
case 34: case 39: // '"', "'"
return readString(code);
// Operators are parsed inline in tiny state machines. '=' (61) is
// often referred to. `finishOp` simply skips the amount of
// characters it is given as second argument, and returns a token
// of the type given by its first argument.
case 47: // '/'
return readToken_slash();
case 37: case 42: // '%*'
return readToken_mult_modulo();
case 124: case 38: // '|&'
return readToken_pipe_amp(code);
case 94: // '^'
return readToken_caret();
case 43: case 45: // '+-'
return readToken_plus_min(code);
case 60: case 62: // '<>'
return readToken_lt_gt(code);
case 61: case 33: // '=!'
return readToken_eq_excl(code);
case 126: // '~'
return finishOp(_prefix, 1);
}
return false;
}
/**
* @param {boolean=} forceRegexp
*/
function readToken(forceRegexp) {
if (!forceRegexp) {
tokStart = tokPos;
} else {
tokPos = tokStart + 1;
}
if (options.locations) {
tokStartLoc = new line_loc_t();
}
if (forceRegexp) return readRegexp();
if (tokPos >= inputLen) return finishToken(_eof);
var code = input.charCodeAt(tokPos);
// Identifier or keyword. '\uXXXX' sequences are allowed in
// identifiers, so '\' also dispatches to that.
if (isIdentifierStart(code) || code === 92) { // '\'
return readWord();
}
var tok = getTokenFromCode(code);
if (tok === false) {
// If we are here, we either found a non-ASCII identifier
// character, or something that's entirely disallowed.
var ch = String.fromCharCode(code);
if (ch === "\\" || nonASCIIidentifierStart.test(ch)) {
return readWord();
}
raise(tokPos, "Unexpected character '" + ch + "'");
}
}
/**
* @param {!Object} type
* @param {number} size
*/
function finishOp(type, size) {
var str = input.slice(tokPos, tokPos + size);
tokPos += size;
finishToken(type, str);
}
/**
* Parse a regular expression. Some context-awareness is necessary,
* since a '/' inside a '[]' set does not end the expression.
*/
function readRegexp() {
// JS-Interpreter change:
// Removed redundant declaration of 'content' here. Caused lint errors.
// -- Neil Fraser, June 2022.
var escaped;
var inClass;
var start = tokPos;
for (;;) {
if (tokPos >= inputLen) raise(start, "Unterminated regexp");
var ch = input.charAt(tokPos);
if (newline.test(ch)) raise(start, "Unterminated regexp");
if (!escaped) {
if (ch === "[") {
inClass = true;
} else if (ch === "]" && inClass) {
inClass = false;
} else if (ch === "/" && !inClass) {
break;
}
escaped = ch === "\\";
} else escaped = false;
++tokPos;
}
var content = input.slice(start, tokPos);
++tokPos;
// Need to use `readWord1` because '\uXXXX' sequences are allowed
// here (don't ask).
var mods = readWord1();
// JS-Interpreter change:
// Acorn used to use 'gmsiy' to check for flags. But 's' and 'y' are ES6.
// -- Neil Fraser, December 2022.
// https://github.com/acornjs/acorn/issues/1163
if (mods && !/^[gmi]*$/.test(mods)) {
raise(start, "Invalid regexp flag");
}
try {
var value = new RegExp(content, mods);
} catch (e) {
if (e instanceof SyntaxError) raise(start, e.message);
// JS-Interpreter change:
// Acorn used to use raise(e) here which is incorrect.
// -- Neil Fraser, July 2023.
throw(e);
}
finishToken(_regexp, value);
}
/**
* Read an integer in the given radix. Return null if zero digits
* were read, the integer value otherwise. When `len` is given, this
* will return `null` unless the integer has exactly `len` digits.
* @param {number} radix
* @param {number=} len
* @returns {?number}
*/
function readInt(radix, len) {
var start = tokPos;
var total = 0;
var e = (len === undefined) ? Infinity : len;
for (var i = 0; i < e; ++i) {
var code = input.charCodeAt(tokPos), val;
if (code >= 97) {
val = code - 97 + 10; // a