1 | // regjsparser
|
---|
2 | //
|
---|
3 | // ==================================================================
|
---|
4 | //
|
---|
5 | // See ECMA-262 Standard: 15.10.1
|
---|
6 | //
|
---|
7 | // NOTE: The ECMA-262 standard uses the term "Assertion" for /^/. Here the
|
---|
8 | // term "Anchor" is used.
|
---|
9 | //
|
---|
10 | // Pattern ::
|
---|
11 | // Disjunction
|
---|
12 | //
|
---|
13 | // Disjunction ::
|
---|
14 | // Alternative
|
---|
15 | // Alternative | Disjunction
|
---|
16 | //
|
---|
17 | // Alternative ::
|
---|
18 | // [empty]
|
---|
19 | // Alternative Term
|
---|
20 | //
|
---|
21 | // Term ::
|
---|
22 | // Anchor
|
---|
23 | // Atom
|
---|
24 | // Atom Quantifier
|
---|
25 | //
|
---|
26 | // Anchor ::
|
---|
27 | // ^
|
---|
28 | // $
|
---|
29 | // \ b
|
---|
30 | // \ B
|
---|
31 | // ( ? = Disjunction )
|
---|
32 | // ( ? ! Disjunction )
|
---|
33 | // ( ? < = Disjunction )
|
---|
34 | // ( ? < ! Disjunction )
|
---|
35 | //
|
---|
36 | // Quantifier ::
|
---|
37 | // QuantifierPrefix
|
---|
38 | // QuantifierPrefix ?
|
---|
39 | //
|
---|
40 | // QuantifierPrefix ::
|
---|
41 | // *
|
---|
42 | // +
|
---|
43 | // ?
|
---|
44 | // { DecimalDigits }
|
---|
45 | // { DecimalDigits , }
|
---|
46 | // { DecimalDigits , DecimalDigits }
|
---|
47 | //
|
---|
48 | // Atom ::
|
---|
49 | // PatternCharacter
|
---|
50 | // .
|
---|
51 | // \ AtomEscape
|
---|
52 | // CharacterClass
|
---|
53 | // ( GroupSpecifier Disjunction )
|
---|
54 | // ( ? : Disjunction )
|
---|
55 | //
|
---|
56 | // PatternCharacter ::
|
---|
57 | // SourceCharacter but not any of: ^ $ \ . * + ? ( ) [ ] { } |
|
---|
58 | //
|
---|
59 | // AtomEscape ::
|
---|
60 | // DecimalEscape
|
---|
61 | // CharacterClassEscape
|
---|
62 | // CharacterEscape
|
---|
63 | // k GroupName
|
---|
64 | //
|
---|
65 | // CharacterEscape[U] ::
|
---|
66 | // ControlEscape
|
---|
67 | // c ControlLetter
|
---|
68 | // HexEscapeSequence
|
---|
69 | // RegExpUnicodeEscapeSequence[?U] (ES6)
|
---|
70 | // IdentityEscape[?U]
|
---|
71 | //
|
---|
72 | // ControlEscape ::
|
---|
73 | // one of f n r t v
|
---|
74 | // ControlLetter ::
|
---|
75 | // one of
|
---|
76 | // a b c d e f g h i j k l m n o p q r s t u v w x y z
|
---|
77 | // A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
|
---|
78 | //
|
---|
79 | // IdentityEscape ::
|
---|
80 | // SourceCharacter but not c
|
---|
81 | //
|
---|
82 | // DecimalEscape ::
|
---|
83 | // DecimalIntegerLiteral [lookahead ∉ DecimalDigit]
|
---|
84 | //
|
---|
85 | // CharacterClassEscape ::
|
---|
86 | // one of d D s S w W
|
---|
87 | //
|
---|
88 | // CharacterClass ::
|
---|
89 | // [ [lookahead ∉ {^}] ClassRanges ]
|
---|
90 | // [ ^ ClassRanges ]
|
---|
91 | //
|
---|
92 | // ClassRanges ::
|
---|
93 | // [empty]
|
---|
94 | // [~V] NonemptyClassRanges
|
---|
95 | // [+V] ClassContents
|
---|
96 | //
|
---|
97 | // NonemptyClassRanges ::
|
---|
98 | // ClassAtom
|
---|
99 | // ClassAtom NonemptyClassRangesNoDash
|
---|
100 | // ClassAtom - ClassAtom ClassRanges
|
---|
101 | //
|
---|
102 | // NonemptyClassRangesNoDash ::
|
---|
103 | // ClassAtom
|
---|
104 | // ClassAtomNoDash NonemptyClassRangesNoDash
|
---|
105 | // ClassAtomNoDash - ClassAtom ClassRanges
|
---|
106 | //
|
---|
107 | // ClassAtom ::
|
---|
108 | // -
|
---|
109 | // ClassAtomNoDash
|
---|
110 | //
|
---|
111 | // ClassAtomNoDash ::
|
---|
112 | // SourceCharacter but not one of \ or ] or -
|
---|
113 | // \ ClassEscape
|
---|
114 | //
|
---|
115 | // ClassEscape ::
|
---|
116 | // DecimalEscape
|
---|
117 | // b
|
---|
118 | // CharacterEscape
|
---|
119 | // CharacterClassEscape
|
---|
120 | //
|
---|
121 | // GroupSpecifier ::
|
---|
122 | // [empty]
|
---|
123 | // ? GroupName
|
---|
124 | //
|
---|
125 | // GroupName ::
|
---|
126 | // < RegExpIdentifierName >
|
---|
127 | //
|
---|
128 | // RegExpIdentifierName ::
|
---|
129 | // RegExpIdentifierStart
|
---|
130 | // RegExpIdentifierName RegExpIdentifierContinue
|
---|
131 | //
|
---|
132 | // RegExpIdentifierStart ::
|
---|
133 | // UnicodeIDStart
|
---|
134 | // $
|
---|
135 | // _
|
---|
136 | // \ RegExpUnicodeEscapeSequence
|
---|
137 | //
|
---|
138 | // RegExpIdentifierContinue ::
|
---|
139 | // UnicodeIDContinue
|
---|
140 | // $
|
---|
141 | // _
|
---|
142 | // \ RegExpUnicodeEscapeSequence
|
---|
143 | // <ZWNJ>
|
---|
144 | // <ZWJ>
|
---|
145 | //
|
---|
146 | // --------------------------------------------------------------
|
---|
147 | // NOTE: The following productions refer to the "set notation and
|
---|
148 | // properties of strings" proposal.
|
---|
149 | // https://github.com/tc39/proposal-regexp-set-notation
|
---|
150 | // --------------------------------------------------------------
|
---|
151 | //
|
---|
152 | // ClassContents ::
|
---|
153 | // ClassUnion
|
---|
154 | // ClassIntersection
|
---|
155 | // ClassSubtraction
|
---|
156 | //
|
---|
157 | // ClassUnion ::
|
---|
158 | // ClassRange ClassUnion?
|
---|
159 | // ClassOperand ClassUnion?
|
---|
160 | //
|
---|
161 | // ClassIntersection ::
|
---|
162 | // ClassOperand && [lookahead ≠ &] ClassOperand
|
---|
163 | // ClassIntersection && [lookahead ≠ &] ClassOperand
|
---|
164 | //
|
---|
165 | // ClassSubtraction ::
|
---|
166 | // ClassOperand -- ClassOperand
|
---|
167 | // ClassSubtraction -- ClassOperand
|
---|
168 | //
|
---|
169 | // ClassOperand ::
|
---|
170 | // ClassCharacter
|
---|
171 | // ClassStrings
|
---|
172 | // NestedClass
|
---|
173 | //
|
---|
174 | // NestedClass ::
|
---|
175 | // [ [lookahead ≠ ^] ClassRanges[+U,+V] ]
|
---|
176 | // [ ^ ClassRanges[+U,+V] ]
|
---|
177 | // \ CharacterClassEscape[+U, +V]
|
---|
178 | //
|
---|
179 | // ClassRange ::
|
---|
180 | // ClassCharacter - ClassCharacter
|
---|
181 | //
|
---|
182 | // ClassCharacter ::
|
---|
183 | // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter
|
---|
184 | // \ CharacterEscape[+U]
|
---|
185 | // \ ClassHalfOfDouble
|
---|
186 | // \ b
|
---|
187 | //
|
---|
188 | // ClassSyntaxCharacter ::
|
---|
189 | // one of ( ) [ ] { } / - \ |
|
---|
190 | //
|
---|
191 | // ClassStrings ::
|
---|
192 | // ( ClassString MoreClassStrings? )
|
---|
193 | //
|
---|
194 | // MoreClassStrings ::
|
---|
195 | // | ClassString MoreClassStrings?
|
---|
196 | //
|
---|
197 | // ClassString ::
|
---|
198 | // [empty]
|
---|
199 | // NonEmptyClassString
|
---|
200 | //
|
---|
201 | // NonEmptyClassString ::
|
---|
202 | // ClassCharacter NonEmptyClassString?
|
---|
203 | //
|
---|
204 | // ClassReservedDouble ::
|
---|
205 | // one of && !! ## $$ %% ** ++ ,, .. :: ;; << == >> ?? @@ ^^ __ `` ~~
|
---|
206 | //
|
---|
207 | // ClassHalfOfDouble ::
|
---|
208 | // one of & - ! # % , : ; < = > @ _ ` ~
|
---|
209 | //
|
---|
210 |
|
---|
211 | (function() {
|
---|
212 |
|
---|
213 | var fromCodePoint = String.fromCodePoint || (function() {
|
---|
214 | // Implementation taken from
|
---|
215 | // https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/fromCodePoint
|
---|
216 |
|
---|
217 | var stringFromCharCode = String.fromCharCode;
|
---|
218 | var floor = Math.floor;
|
---|
219 |
|
---|
220 | return function fromCodePoint() {
|
---|
221 | var MAX_SIZE = 0x4000;
|
---|
222 | var codeUnits = [];
|
---|
223 | var highSurrogate;
|
---|
224 | var lowSurrogate;
|
---|
225 | var index = -1;
|
---|
226 | var length = arguments.length;
|
---|
227 | if (!length) {
|
---|
228 | return '';
|
---|
229 | }
|
---|
230 | var result = '';
|
---|
231 | while (++index < length) {
|
---|
232 | var codePoint = Number(arguments[index]);
|
---|
233 | if (
|
---|
234 | !isFinite(codePoint) || // `NaN`, `+Infinity`, or `-Infinity`
|
---|
235 | codePoint < 0 || // not a valid Unicode code point
|
---|
236 | codePoint > 0x10FFFF || // not a valid Unicode code point
|
---|
237 | floor(codePoint) != codePoint // not an integer
|
---|
238 | ) {
|
---|
239 | throw RangeError('Invalid code point: ' + codePoint);
|
---|
240 | }
|
---|
241 | if (codePoint <= 0xFFFF) { // BMP code point
|
---|
242 | codeUnits.push(codePoint);
|
---|
243 | } else { // Astral code point; split in surrogate halves
|
---|
244 | // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
|
---|
245 | codePoint -= 0x10000;
|
---|
246 | highSurrogate = (codePoint >> 10) + 0xD800;
|
---|
247 | lowSurrogate = (codePoint % 0x400) + 0xDC00;
|
---|
248 | codeUnits.push(highSurrogate, lowSurrogate);
|
---|
249 | }
|
---|
250 | if (index + 1 == length || codeUnits.length > MAX_SIZE) {
|
---|
251 | result += stringFromCharCode.apply(null, codeUnits);
|
---|
252 | codeUnits.length = 0;
|
---|
253 | }
|
---|
254 | }
|
---|
255 | return result;
|
---|
256 | };
|
---|
257 | }());
|
---|
258 |
|
---|
259 | function parse(str, flags, features) {
|
---|
260 | if (!features) {
|
---|
261 | features = {};
|
---|
262 | }
|
---|
263 | function addRaw(node) {
|
---|
264 | node.raw = str.substring(node.range[0], node.range[1]);
|
---|
265 | return node;
|
---|
266 | }
|
---|
267 |
|
---|
268 | function updateRawStart(node, start) {
|
---|
269 | node.range[0] = start;
|
---|
270 | return addRaw(node);
|
---|
271 | }
|
---|
272 |
|
---|
273 | function createAnchor(kind, rawLength) {
|
---|
274 | return addRaw({
|
---|
275 | type: 'anchor',
|
---|
276 | kind: kind,
|
---|
277 | range: [
|
---|
278 | pos - rawLength,
|
---|
279 | pos
|
---|
280 | ]
|
---|
281 | });
|
---|
282 | }
|
---|
283 |
|
---|
284 | function createValue(kind, codePoint, from, to) {
|
---|
285 | return addRaw({
|
---|
286 | type: 'value',
|
---|
287 | kind: kind,
|
---|
288 | codePoint: codePoint,
|
---|
289 | range: [from, to]
|
---|
290 | });
|
---|
291 | }
|
---|
292 |
|
---|
293 | function createEscaped(kind, codePoint, value, fromOffset) {
|
---|
294 | fromOffset = fromOffset || 0;
|
---|
295 | return createValue(kind, codePoint, pos - (value.length + fromOffset), pos);
|
---|
296 | }
|
---|
297 |
|
---|
298 | function createCharacter(matches) {
|
---|
299 | var _char = matches[0];
|
---|
300 | var first = _char.charCodeAt(0);
|
---|
301 | if (hasUnicodeFlag) {
|
---|
302 | var second;
|
---|
303 | if (_char.length === 1 && first >= 0xD800 && first <= 0xDBFF) {
|
---|
304 | second = lookahead().charCodeAt(0);
|
---|
305 | if (second >= 0xDC00 && second <= 0xDFFF) {
|
---|
306 | // Unicode surrogate pair
|
---|
307 | pos++;
|
---|
308 | return createValue(
|
---|
309 | 'symbol',
|
---|
310 | (first - 0xD800) * 0x400 + second - 0xDC00 + 0x10000,
|
---|
311 | pos - 2, pos);
|
---|
312 | }
|
---|
313 | }
|
---|
314 | }
|
---|
315 | return createValue('symbol', first, pos - 1, pos);
|
---|
316 | }
|
---|
317 |
|
---|
318 | function createDisjunction(alternatives, from, to) {
|
---|
319 | return addRaw({
|
---|
320 | type: 'disjunction',
|
---|
321 | body: alternatives,
|
---|
322 | range: [
|
---|
323 | from,
|
---|
324 | to
|
---|
325 | ]
|
---|
326 | });
|
---|
327 | }
|
---|
328 |
|
---|
329 | function createDot() {
|
---|
330 | return addRaw({
|
---|
331 | type: 'dot',
|
---|
332 | range: [
|
---|
333 | pos - 1,
|
---|
334 | pos
|
---|
335 | ]
|
---|
336 | });
|
---|
337 | }
|
---|
338 |
|
---|
339 | function createCharacterClassEscape(value) {
|
---|
340 | return addRaw({
|
---|
341 | type: 'characterClassEscape',
|
---|
342 | value: value,
|
---|
343 | range: [
|
---|
344 | pos - 2,
|
---|
345 | pos
|
---|
346 | ]
|
---|
347 | });
|
---|
348 | }
|
---|
349 |
|
---|
350 | function createReference(matchIndex) {
|
---|
351 | return addRaw({
|
---|
352 | type: 'reference',
|
---|
353 | matchIndex: parseInt(matchIndex, 10),
|
---|
354 | range: [
|
---|
355 | pos - 1 - matchIndex.length,
|
---|
356 | pos
|
---|
357 | ]
|
---|
358 | });
|
---|
359 | }
|
---|
360 |
|
---|
361 | function createNamedReference(name) {
|
---|
362 | return addRaw({
|
---|
363 | type: 'reference',
|
---|
364 | name: name,
|
---|
365 | range: [
|
---|
366 | name.range[0] - 3,
|
---|
367 | pos
|
---|
368 | ]
|
---|
369 | });
|
---|
370 | }
|
---|
371 |
|
---|
372 | function createGroup(behavior, disjunction, from, to) {
|
---|
373 | return addRaw({
|
---|
374 | type: 'group',
|
---|
375 | behavior: behavior,
|
---|
376 | body: disjunction,
|
---|
377 | range: [
|
---|
378 | from,
|
---|
379 | to
|
---|
380 | ]
|
---|
381 | });
|
---|
382 | }
|
---|
383 |
|
---|
384 | function createQuantifier(min, max, from, to) {
|
---|
385 | if (to == null) {
|
---|
386 | from = pos - 1;
|
---|
387 | to = pos;
|
---|
388 | }
|
---|
389 |
|
---|
390 | return addRaw({
|
---|
391 | type: 'quantifier',
|
---|
392 | min: min,
|
---|
393 | max: max,
|
---|
394 | greedy: true,
|
---|
395 | body: null, // set later on
|
---|
396 | range: [
|
---|
397 | from,
|
---|
398 | to
|
---|
399 | ]
|
---|
400 | });
|
---|
401 | }
|
---|
402 |
|
---|
403 | function createAlternative(terms, from, to) {
|
---|
404 | return addRaw({
|
---|
405 | type: 'alternative',
|
---|
406 | body: terms,
|
---|
407 | range: [
|
---|
408 | from,
|
---|
409 | to
|
---|
410 | ]
|
---|
411 | });
|
---|
412 | }
|
---|
413 |
|
---|
414 | function createCharacterClass(contents, negative, from, to) {
|
---|
415 | return addRaw({
|
---|
416 | type: 'characterClass',
|
---|
417 | kind: contents.kind,
|
---|
418 | body: contents.body,
|
---|
419 | negative: negative,
|
---|
420 | range: [
|
---|
421 | from,
|
---|
422 | to
|
---|
423 | ]
|
---|
424 | });
|
---|
425 | }
|
---|
426 |
|
---|
427 | function createClassRange(min, max, from, to) {
|
---|
428 | // See 15.10.2.15:
|
---|
429 | if (min.codePoint > max.codePoint) {
|
---|
430 | bail('invalid range in character class', min.raw + '-' + max.raw, from, to);
|
---|
431 | }
|
---|
432 |
|
---|
433 | return addRaw({
|
---|
434 | type: 'characterClassRange',
|
---|
435 | min: min,
|
---|
436 | max: max,
|
---|
437 | range: [
|
---|
438 | from,
|
---|
439 | to
|
---|
440 | ]
|
---|
441 | });
|
---|
442 | }
|
---|
443 |
|
---|
444 | function createClassStrings(strings, from, to) {
|
---|
445 | return addRaw({
|
---|
446 | type: 'classStrings',
|
---|
447 | strings: strings,
|
---|
448 | range: [from, to]
|
---|
449 | });
|
---|
450 | }
|
---|
451 |
|
---|
452 | function createClassString(characters, from, to) {
|
---|
453 | return addRaw({
|
---|
454 | type: 'classString',
|
---|
455 | characters: characters,
|
---|
456 | range: [from, to]
|
---|
457 | });
|
---|
458 | }
|
---|
459 |
|
---|
460 | function flattenBody(body) {
|
---|
461 | if (body.type === 'alternative') {
|
---|
462 | return body.body;
|
---|
463 | } else {
|
---|
464 | return [body];
|
---|
465 | }
|
---|
466 | }
|
---|
467 |
|
---|
468 | function incr(amount) {
|
---|
469 | amount = (amount || 1);
|
---|
470 | var res = str.substring(pos, pos + amount);
|
---|
471 | pos += (amount || 1);
|
---|
472 | return res;
|
---|
473 | }
|
---|
474 |
|
---|
475 | function skip(value) {
|
---|
476 | if (!match(value)) {
|
---|
477 | bail('character', value);
|
---|
478 | }
|
---|
479 | }
|
---|
480 |
|
---|
481 | function match(value) {
|
---|
482 | if (str.indexOf(value, pos) === pos) {
|
---|
483 | return incr(value.length);
|
---|
484 | }
|
---|
485 | }
|
---|
486 |
|
---|
487 | function lookahead() {
|
---|
488 | return str[pos];
|
---|
489 | }
|
---|
490 |
|
---|
491 | function current(value) {
|
---|
492 | return str.indexOf(value, pos) === pos;
|
---|
493 | }
|
---|
494 |
|
---|
495 | function next(value) {
|
---|
496 | return str[pos + 1] === value;
|
---|
497 | }
|
---|
498 |
|
---|
499 | function matchReg(regExp) {
|
---|
500 | var subStr = str.substring(pos);
|
---|
501 | var res = subStr.match(regExp);
|
---|
502 | if (res) {
|
---|
503 | res.range = [];
|
---|
504 | res.range[0] = pos;
|
---|
505 | incr(res[0].length);
|
---|
506 | res.range[1] = pos;
|
---|
507 | }
|
---|
508 | return res;
|
---|
509 | }
|
---|
510 |
|
---|
511 | function parseDisjunction() {
|
---|
512 | // Disjunction ::
|
---|
513 | // Alternative
|
---|
514 | // Alternative | Disjunction
|
---|
515 | var res = [], from = pos;
|
---|
516 | res.push(parseAlternative());
|
---|
517 |
|
---|
518 | while (match('|')) {
|
---|
519 | res.push(parseAlternative());
|
---|
520 | }
|
---|
521 |
|
---|
522 | if (res.length === 1) {
|
---|
523 | return res[0];
|
---|
524 | }
|
---|
525 |
|
---|
526 | return createDisjunction(res, from, pos);
|
---|
527 | }
|
---|
528 |
|
---|
529 | function parseAlternative() {
|
---|
530 | var res = [], from = pos;
|
---|
531 | var term;
|
---|
532 |
|
---|
533 | // Alternative ::
|
---|
534 | // [empty]
|
---|
535 | // Alternative Term
|
---|
536 | while (term = parseTerm()) {
|
---|
537 | res.push(term);
|
---|
538 | }
|
---|
539 |
|
---|
540 | if (res.length === 1) {
|
---|
541 | return res[0];
|
---|
542 | }
|
---|
543 |
|
---|
544 | return createAlternative(res, from, pos);
|
---|
545 | }
|
---|
546 |
|
---|
547 | function parseTerm() {
|
---|
548 | // Term ::
|
---|
549 | // Anchor
|
---|
550 | // Atom
|
---|
551 | // Atom Quantifier
|
---|
552 |
|
---|
553 | if (pos >= str.length || current('|') || current(')')) {
|
---|
554 | return null; /* Means: The term is empty */
|
---|
555 | }
|
---|
556 |
|
---|
557 | var anchor = parseAnchor();
|
---|
558 |
|
---|
559 | if (anchor) {
|
---|
560 | return anchor;
|
---|
561 | }
|
---|
562 |
|
---|
563 | var atom = parseAtomAndExtendedAtom();
|
---|
564 | if (!atom) {
|
---|
565 | // Check if a quantifier is following. A quantifier without an atom
|
---|
566 | // is an error.
|
---|
567 | pos_backup = pos
|
---|
568 | var quantifier = parseQuantifier() || false;
|
---|
569 | if (quantifier) {
|
---|
570 | pos = pos_backup
|
---|
571 | bail('Expected atom');
|
---|
572 | }
|
---|
573 |
|
---|
574 | // If no unicode flag, then try to parse ExtendedAtom -> ExtendedPatternCharacter.
|
---|
575 | // ExtendedPatternCharacter
|
---|
576 | if (!hasUnicodeFlag && (res = matchReg(/^{/))) {
|
---|
577 | atom = createCharacter(res);
|
---|
578 | } else {
|
---|
579 | bail('Expected atom');
|
---|
580 | }
|
---|
581 | }
|
---|
582 | var quantifier = parseQuantifier() || false;
|
---|
583 | if (quantifier) {
|
---|
584 | quantifier.body = flattenBody(atom);
|
---|
585 | // The quantifier contains the atom. Therefore, the beginning of the
|
---|
586 | // quantifier range is given by the beginning of the atom.
|
---|
587 | updateRawStart(quantifier, atom.range[0]);
|
---|
588 | return quantifier;
|
---|
589 | }
|
---|
590 | return atom;
|
---|
591 | }
|
---|
592 |
|
---|
593 | function parseGroup(matchA, typeA, matchB, typeB) {
|
---|
594 | var type = null, from = pos;
|
---|
595 |
|
---|
596 | if (match(matchA)) {
|
---|
597 | type = typeA;
|
---|
598 | } else if (match(matchB)) {
|
---|
599 | type = typeB;
|
---|
600 | } else {
|
---|
601 | return false;
|
---|
602 | }
|
---|
603 |
|
---|
604 | return finishGroup(type, from);
|
---|
605 | }
|
---|
606 |
|
---|
607 | function finishGroup(type, from) {
|
---|
608 | var body = parseDisjunction();
|
---|
609 | if (!body) {
|
---|
610 | bail('Expected disjunction');
|
---|
611 | }
|
---|
612 | skip(')');
|
---|
613 | var group = createGroup(type, flattenBody(body), from, pos);
|
---|
614 |
|
---|
615 | if (type == 'normal') {
|
---|
616 | // Keep track of the number of closed groups. This is required for
|
---|
617 | // parseDecimalEscape(). In case the string is parsed a second time the
|
---|
618 | // value already holds the total count and no incrementation is required.
|
---|
619 | if (firstIteration) {
|
---|
620 | closedCaptureCounter++;
|
---|
621 | }
|
---|
622 | }
|
---|
623 | return group;
|
---|
624 | }
|
---|
625 |
|
---|
626 | function parseAnchor() {
|
---|
627 | // Anchor ::
|
---|
628 | // ^
|
---|
629 | // $
|
---|
630 | // \ b
|
---|
631 | // \ B
|
---|
632 | // ( ? = Disjunction )
|
---|
633 | // ( ? ! Disjunction )
|
---|
634 | var res, from = pos;
|
---|
635 |
|
---|
636 | if (match('^')) {
|
---|
637 | return createAnchor('start', 1 /* rawLength */);
|
---|
638 | } else if (match('$')) {
|
---|
639 | return createAnchor('end', 1 /* rawLength */);
|
---|
640 | } else if (match('\\b')) {
|
---|
641 | return createAnchor('boundary', 2 /* rawLength */);
|
---|
642 | } else if (match('\\B')) {
|
---|
643 | return createAnchor('not-boundary', 2 /* rawLength */);
|
---|
644 | } else {
|
---|
645 | return parseGroup('(?=', 'lookahead', '(?!', 'negativeLookahead');
|
---|
646 | }
|
---|
647 | }
|
---|
648 |
|
---|
649 | function parseQuantifier() {
|
---|
650 | // Quantifier ::
|
---|
651 | // QuantifierPrefix
|
---|
652 | // QuantifierPrefix ?
|
---|
653 | //
|
---|
654 | // QuantifierPrefix ::
|
---|
655 | // *
|
---|
656 | // +
|
---|
657 | // ?
|
---|
658 | // { DecimalDigits }
|
---|
659 | // { DecimalDigits , }
|
---|
660 | // { DecimalDigits , DecimalDigits }
|
---|
661 |
|
---|
662 | var res, from = pos;
|
---|
663 | var quantifier;
|
---|
664 | var min, max;
|
---|
665 |
|
---|
666 | if (match('*')) {
|
---|
667 | quantifier = createQuantifier(0);
|
---|
668 | }
|
---|
669 | else if (match('+')) {
|
---|
670 | quantifier = createQuantifier(1);
|
---|
671 | }
|
---|
672 | else if (match('?')) {
|
---|
673 | quantifier = createQuantifier(0, 1);
|
---|
674 | }
|
---|
675 | else if (res = matchReg(/^\{([0-9]+)\}/)) {
|
---|
676 | min = parseInt(res[1], 10);
|
---|
677 | quantifier = createQuantifier(min, min, res.range[0], res.range[1]);
|
---|
678 | }
|
---|
679 | else if (res = matchReg(/^\{([0-9]+),\}/)) {
|
---|
680 | min = parseInt(res[1], 10);
|
---|
681 | quantifier = createQuantifier(min, undefined, res.range[0], res.range[1]);
|
---|
682 | }
|
---|
683 | else if (res = matchReg(/^\{([0-9]+),([0-9]+)\}/)) {
|
---|
684 | min = parseInt(res[1], 10);
|
---|
685 | max = parseInt(res[2], 10);
|
---|
686 | if (min > max) {
|
---|
687 | bail('numbers out of order in {} quantifier', '', from, pos);
|
---|
688 | }
|
---|
689 | quantifier = createQuantifier(min, max, res.range[0], res.range[1]);
|
---|
690 | }
|
---|
691 |
|
---|
692 | if (quantifier) {
|
---|
693 | if (match('?')) {
|
---|
694 | quantifier.greedy = false;
|
---|
695 | quantifier.range[1] += 1;
|
---|
696 | }
|
---|
697 | }
|
---|
698 |
|
---|
699 | return quantifier;
|
---|
700 | }
|
---|
701 |
|
---|
702 | function parseAtomAndExtendedAtom() {
|
---|
703 | // Parsing Atom and ExtendedAtom together due to redundancy.
|
---|
704 | // ExtendedAtom is defined in Apendix B of the ECMA-262 standard.
|
---|
705 | //
|
---|
706 | // SEE: https://www.ecma-international.org/ecma-262/10.0/index.html#prod-annexB-ExtendedPatternCharacter
|
---|
707 | //
|
---|
708 | // Atom ::
|
---|
709 | // PatternCharacter
|
---|
710 | // .
|
---|
711 | // \ AtomEscape
|
---|
712 | // CharacterClass
|
---|
713 | // ( GroupSpecifier Disjunction )
|
---|
714 | // ( ? : Disjunction )
|
---|
715 | // ExtendedAtom ::
|
---|
716 | // ExtendedPatternCharacter
|
---|
717 | // ExtendedPatternCharacter ::
|
---|
718 | // SourceCharacter but not one of ^$\.*+?()[|
|
---|
719 |
|
---|
720 | var res;
|
---|
721 |
|
---|
722 | // jviereck: allow ']', '}' here as well to be compatible with browser's
|
---|
723 | // implementations: ']'.match(/]/);
|
---|
724 | if (res = matchReg(/^[^^$\\.*+?()[\]{}|]/)) {
|
---|
725 | // PatternCharacter
|
---|
726 | return createCharacter(res);
|
---|
727 | }
|
---|
728 | else if (!hasUnicodeFlag && (res = matchReg(/^(?:]|})/))) {
|
---|
729 | // ExtendedPatternCharacter, first part. See parseTerm.
|
---|
730 | return createCharacter(res);
|
---|
731 | }
|
---|
732 | else if (match('.')) {
|
---|
733 | // .
|
---|
734 | return createDot();
|
---|
735 | }
|
---|
736 | else if (match('\\')) {
|
---|
737 | // \ AtomEscape
|
---|
738 | res = parseAtomEscape();
|
---|
739 | if (!res) {
|
---|
740 | if (!hasUnicodeFlag && lookahead() == 'c') {
|
---|
741 | // B.1.4 ExtendedAtom
|
---|
742 | // \[lookahead = c]
|
---|
743 | return createValue('symbol', 92, pos - 1, pos);
|
---|
744 | }
|
---|
745 | bail('atomEscape');
|
---|
746 | }
|
---|
747 | return res;
|
---|
748 | }
|
---|
749 | else if (res = parseCharacterClass()) {
|
---|
750 | return res;
|
---|
751 | }
|
---|
752 | else if (features.lookbehind && (res = parseGroup('(?<=', 'lookbehind', '(?<!', 'negativeLookbehind'))) {
|
---|
753 | return res;
|
---|
754 | }
|
---|
755 | else if (features.namedGroups && match("(?<")) {
|
---|
756 | var name = parseIdentifier();
|
---|
757 | skip(">");
|
---|
758 | var group = finishGroup("normal", name.range[0] - 3);
|
---|
759 | group.name = name;
|
---|
760 | return group;
|
---|
761 | }
|
---|
762 | else {
|
---|
763 | // ( Disjunction )
|
---|
764 | // ( ? : Disjunction )
|
---|
765 | return parseGroup('(?:', 'ignore', '(', 'normal');
|
---|
766 | }
|
---|
767 | }
|
---|
768 |
|
---|
769 | function parseUnicodeSurrogatePairEscape(firstEscape) {
|
---|
770 | if (hasUnicodeFlag) {
|
---|
771 | var first, second;
|
---|
772 | if (firstEscape.kind == 'unicodeEscape' &&
|
---|
773 | (first = firstEscape.codePoint) >= 0xD800 && first <= 0xDBFF &&
|
---|
774 | current('\\') && next('u') ) {
|
---|
775 | var prevPos = pos;
|
---|
776 | pos++;
|
---|
777 | var secondEscape = parseClassEscape();
|
---|
778 | if (secondEscape.kind == 'unicodeEscape' &&
|
---|
779 | (second = secondEscape.codePoint) >= 0xDC00 && second <= 0xDFFF) {
|
---|
780 | // Unicode surrogate pair
|
---|
781 | firstEscape.range[1] = secondEscape.range[1];
|
---|
782 | firstEscape.codePoint = (first - 0xD800) * 0x400 + second - 0xDC00 + 0x10000;
|
---|
783 | firstEscape.type = 'value';
|
---|
784 | firstEscape.kind = 'unicodeCodePointEscape';
|
---|
785 | addRaw(firstEscape);
|
---|
786 | }
|
---|
787 | else {
|
---|
788 | pos = prevPos;
|
---|
789 | }
|
---|
790 | }
|
---|
791 | }
|
---|
792 | return firstEscape;
|
---|
793 | }
|
---|
794 |
|
---|
795 | function parseClassEscape() {
|
---|
796 | return parseAtomEscape(true);
|
---|
797 | }
|
---|
798 |
|
---|
799 | function parseAtomEscape(insideCharacterClass) {
|
---|
800 | // AtomEscape ::
|
---|
801 | // DecimalEscape
|
---|
802 | // CharacterEscape
|
---|
803 | // CharacterClassEscape
|
---|
804 | // k GroupName
|
---|
805 |
|
---|
806 | var res, from = pos;
|
---|
807 |
|
---|
808 | res = parseDecimalEscape() || parseNamedReference();
|
---|
809 | if (res) {
|
---|
810 | return res;
|
---|
811 | }
|
---|
812 |
|
---|
813 | // For ClassEscape
|
---|
814 | if (insideCharacterClass) {
|
---|
815 | // b
|
---|
816 | if (match('b')) {
|
---|
817 | // 15.10.2.19
|
---|
818 | // The production ClassEscape :: b evaluates by returning the
|
---|
819 | // CharSet containing the one character <BS> (Unicode value 0008).
|
---|
820 | return createEscaped('singleEscape', 0x0008, '\\b');
|
---|
821 | } else if (match('B')) {
|
---|
822 | bail('\\B not possible inside of CharacterClass', '', from);
|
---|
823 | } else if (!hasUnicodeFlag && (res = matchReg(/^c([0-9])/))) {
|
---|
824 | // B.1.4
|
---|
825 | // c ClassControlLetter, ClassControlLetter = DecimalDigit
|
---|
826 | return createEscaped('controlLetter', res[1] + 16, res[1], 2);
|
---|
827 | } else if (!hasUnicodeFlag && (res = matchReg(/^c_/))) {
|
---|
828 | // B.1.4
|
---|
829 | // c ClassControlLetter, ClassControlLetter = _
|
---|
830 | return createEscaped('controlLetter', 31, '_', 2);
|
---|
831 | }
|
---|
832 | // [+U] -
|
---|
833 | if (hasUnicodeFlag && match('-')) {
|
---|
834 | return createEscaped('singleEscape', 0x002d, '\\-');
|
---|
835 | }
|
---|
836 | }
|
---|
837 |
|
---|
838 | res = parseCharacterClassEscape() || parseCharacterEscape();
|
---|
839 |
|
---|
840 | return res;
|
---|
841 | }
|
---|
842 |
|
---|
843 |
|
---|
844 | function parseDecimalEscape() {
|
---|
845 | // DecimalEscape ::
|
---|
846 | // DecimalIntegerLiteral [lookahead ∉ DecimalDigit]
|
---|
847 |
|
---|
848 | var res, match;
|
---|
849 |
|
---|
850 | if (res = matchReg(/^(?!0)\d+/)) {
|
---|
851 | match = res[0];
|
---|
852 | var refIdx = parseInt(res[0], 10);
|
---|
853 | if (refIdx <= closedCaptureCounter) {
|
---|
854 | // If the number is smaller than the normal-groups found so
|
---|
855 | // far, then it is a reference...
|
---|
856 | return createReference(res[0]);
|
---|
857 | } else {
|
---|
858 | // ... otherwise it needs to be interpreted as a octal (if the
|
---|
859 | // number is in an octal format). If it is NOT octal format,
|
---|
860 | // then the slash is ignored and the number is matched later
|
---|
861 | // as normal characters.
|
---|
862 |
|
---|
863 | // Recall the negative decision to decide if the input must be parsed
|
---|
864 | // a second time with the total normal-groups.
|
---|
865 | backrefDenied.push(refIdx);
|
---|
866 |
|
---|
867 | // Reset the position again, as maybe only parts of the previous
|
---|
868 | // matched numbers are actual octal numbers. E.g. in '019' only
|
---|
869 | // the '01' should be matched.
|
---|
870 | incr(-res[0].length);
|
---|
871 | if (res = matchReg(/^[0-7]{1,3}/)) {
|
---|
872 | return createEscaped('octal', parseInt(res[0], 8), res[0], 1);
|
---|
873 | } else {
|
---|
874 | // If we end up here, we have a case like /\91/. Then the
|
---|
875 | // first slash is to be ignored and the 9 & 1 to be treated
|
---|
876 | // like ordinary characters. Create a character for the
|
---|
877 | // first number only here - other number-characters
|
---|
878 | // (if available) will be matched later.
|
---|
879 | res = createCharacter(matchReg(/^[89]/));
|
---|
880 | return updateRawStart(res, res.range[0] - 1);
|
---|
881 | }
|
---|
882 | }
|
---|
883 | }
|
---|
884 | // Only allow octal numbers in the following. All matched numbers start
|
---|
885 | // with a zero (if the do not, the previous if-branch is executed).
|
---|
886 | // If the number is not octal format and starts with zero (e.g. `091`)
|
---|
887 | // then only the zeros `0` is treated here and the `91` are ordinary
|
---|
888 | // characters.
|
---|
889 | // Example:
|
---|
890 | // /\091/.exec('\091')[0].length === 3
|
---|
891 | else if (res = matchReg(/^[0-7]{1,3}/)) {
|
---|
892 | match = res[0];
|
---|
893 | if (/^0{1,3}$/.test(match)) {
|
---|
894 | // If they are all zeros, then only take the first one.
|
---|
895 | return createEscaped('null', 0x0000, '0', match.length);
|
---|
896 | } else {
|
---|
897 | return createEscaped('octal', parseInt(match, 8), match, 1);
|
---|
898 | }
|
---|
899 | }
|
---|
900 | return false;
|
---|
901 | }
|
---|
902 |
|
---|
903 | function parseCharacterClassEscape() {
|
---|
904 | // CharacterClassEscape :: one of d D s S w W
|
---|
905 | var res;
|
---|
906 | if (res = matchReg(/^[dDsSwW]/)) {
|
---|
907 | return createCharacterClassEscape(res[0]);
|
---|
908 | } else if (features.unicodePropertyEscape && (hasUnicodeFlag || hasUnicodeSetFlag) && (res = matchReg(/^([pP])\{([^\}]+)\}/))) {
|
---|
909 | // https://github.com/jviereck/regjsparser/issues/77
|
---|
910 | return addRaw({
|
---|
911 | type: 'unicodePropertyEscape',
|
---|
912 | negative: res[1] === 'P',
|
---|
913 | value: res[2],
|
---|
914 | range: [res.range[0] - 1, res.range[1]],
|
---|
915 | raw: res[0]
|
---|
916 | });
|
---|
917 | }
|
---|
918 | return false;
|
---|
919 | }
|
---|
920 |
|
---|
921 | function parseNamedReference() {
|
---|
922 | if (features.namedGroups && matchReg(/^k<(?=.*?>)/)) {
|
---|
923 | var name = parseIdentifier();
|
---|
924 | skip('>');
|
---|
925 | return createNamedReference(name);
|
---|
926 | }
|
---|
927 | }
|
---|
928 |
|
---|
929 | function parseRegExpUnicodeEscapeSequence() {
|
---|
930 | var res;
|
---|
931 | if (res = matchReg(/^u([0-9a-fA-F]{4})/)) {
|
---|
932 | // UnicodeEscapeSequence
|
---|
933 | return parseUnicodeSurrogatePairEscape(
|
---|
934 | createEscaped('unicodeEscape', parseInt(res[1], 16), res[1], 2)
|
---|
935 | );
|
---|
936 | } else if (hasUnicodeFlag && (res = matchReg(/^u\{([0-9a-fA-F]+)\}/))) {
|
---|
937 | // RegExpUnicodeEscapeSequence (ES6 Unicode code point escape)
|
---|
938 | return createEscaped('unicodeCodePointEscape', parseInt(res[1], 16), res[1], 4);
|
---|
939 | }
|
---|
940 | }
|
---|
941 |
|
---|
942 | function parseCharacterEscape() {
|
---|
943 | // CharacterEscape ::
|
---|
944 | // ControlEscape
|
---|
945 | // c ControlLetter
|
---|
946 | // HexEscapeSequence
|
---|
947 | // UnicodeEscapeSequence
|
---|
948 | // IdentityEscape
|
---|
949 |
|
---|
950 | var res;
|
---|
951 | var from = pos;
|
---|
952 | if (res = matchReg(/^[fnrtv]/)) {
|
---|
953 | // ControlEscape
|
---|
954 | var codePoint = 0;
|
---|
955 | switch (res[0]) {
|
---|
956 | case 't': codePoint = 0x009; break;
|
---|
957 | case 'n': codePoint = 0x00A; break;
|
---|
958 | case 'v': codePoint = 0x00B; break;
|
---|
959 | case 'f': codePoint = 0x00C; break;
|
---|
960 | case 'r': codePoint = 0x00D; break;
|
---|
961 | }
|
---|
962 | return createEscaped('singleEscape', codePoint, '\\' + res[0]);
|
---|
963 | } else if (res = matchReg(/^c([a-zA-Z])/)) {
|
---|
964 | // c ControlLetter
|
---|
965 | return createEscaped('controlLetter', res[1].charCodeAt(0) % 32, res[1], 2);
|
---|
966 | } else if (res = matchReg(/^x([0-9a-fA-F]{2})/)) {
|
---|
967 | // HexEscapeSequence
|
---|
968 | return createEscaped('hexadecimalEscape', parseInt(res[1], 16), res[1], 2);
|
---|
969 | } else if (res = parseRegExpUnicodeEscapeSequence()) {
|
---|
970 | if (!res || res.codePoint > 0x10FFFF) {
|
---|
971 | bail('Invalid escape sequence', null, from, pos);
|
---|
972 | }
|
---|
973 | return res;
|
---|
974 | } else {
|
---|
975 | // IdentityEscape
|
---|
976 | return parseIdentityEscape();
|
---|
977 | }
|
---|
978 | }
|
---|
979 |
|
---|
980 | function parseIdentifierAtom(check) {
|
---|
981 | var ch = lookahead();
|
---|
982 | var from = pos;
|
---|
983 | if (ch === '\\') {
|
---|
984 | incr();
|
---|
985 | var esc = parseRegExpUnicodeEscapeSequence();
|
---|
986 | if (!esc || !check(esc.codePoint)) {
|
---|
987 | bail('Invalid escape sequence', null, from, pos);
|
---|
988 | }
|
---|
989 | return fromCodePoint(esc.codePoint);
|
---|
990 | }
|
---|
991 | var code = ch.charCodeAt(0);
|
---|
992 | if (code >= 0xD800 && code <= 0xDBFF) {
|
---|
993 | ch += str[pos + 1];
|
---|
994 | var second = ch.charCodeAt(1);
|
---|
995 | if (second >= 0xDC00 && second <= 0xDFFF) {
|
---|
996 | // Unicode surrogate pair
|
---|
997 | code = (code - 0xD800) * 0x400 + second - 0xDC00 + 0x10000;
|
---|
998 | }
|
---|
999 | }
|
---|
1000 | if (!check(code)) return;
|
---|
1001 | incr();
|
---|
1002 | if (code > 0xFFFF) incr();
|
---|
1003 | return ch;
|
---|
1004 | }
|
---|
1005 |
|
---|
1006 | function parseIdentifier() {
|
---|
1007 | // RegExpIdentifierName ::
|
---|
1008 | // RegExpIdentifierStart
|
---|
1009 | // RegExpIdentifierName RegExpIdentifierContinue
|
---|
1010 | //
|
---|
1011 | // RegExpIdentifierStart ::
|
---|
1012 | // UnicodeIDStart
|
---|
1013 | // $
|
---|
1014 | // _
|
---|
1015 | // \ RegExpUnicodeEscapeSequence
|
---|
1016 | //
|
---|
1017 | // RegExpIdentifierContinue ::
|
---|
1018 | // UnicodeIDContinue
|
---|
1019 | // $
|
---|
1020 | // _
|
---|
1021 | // \ RegExpUnicodeEscapeSequence
|
---|
1022 | // <ZWNJ>
|
---|
1023 | // <ZWJ>
|
---|
1024 |
|
---|
1025 | var start = pos;
|
---|
1026 | var res = parseIdentifierAtom(isIdentifierStart);
|
---|
1027 | if (!res) {
|
---|
1028 | bail('Invalid identifier');
|
---|
1029 | }
|
---|
1030 |
|
---|
1031 | var ch;
|
---|
1032 | while (ch = parseIdentifierAtom(isIdentifierPart)) {
|
---|
1033 | res += ch;
|
---|
1034 | }
|
---|
1035 |
|
---|
1036 | return addRaw({
|
---|
1037 | type: 'identifier',
|
---|
1038 | value: res,
|
---|
1039 | range: [start, pos]
|
---|
1040 | });
|
---|
1041 | }
|
---|
1042 |
|
---|
1043 | function isIdentifierStart(ch) {
|
---|
1044 | // Generated by `tools/generate-identifier-regex.js`.
|
---|
1045 | var NonAsciiIdentifierStart = /[\$A-Z_a-z\xAA\xB5\xBA\xC0-\xD6\xD8-\xF6\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u052F\u0531-\u0556\u0559\u0560-\u0588\u05D0-\u05EA\u05EF-\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\u0860-\u086A\u08A0-\u08B4\u08B6-\u08BD\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u09FC\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\u0AF9\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-\u0C39\u0C3D\u0C58-\u0C5A\u0C60\u0C61\u0C80\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D54-\u0D56\u0D5F-\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-\u13F5\u13F8-\u13FD\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16EE-\u16F8\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1878\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1C80-\u1C88\u1C90-\u1CBA\u1CBD-\u1CBF\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\u2118-\u211D\u2124\u2126\u2128\u212A-\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\u3005-\u3007\u3021-\u3029\u3031-\u3035\u3038-\u303C\u3041-\u3096\u309B-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312F\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FEF\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6EF\uA717-\uA71F\uA722-\uA788\uA78B-\uA7B9\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA8FD\uA8FE\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uA9E0-\uA9E4\uA9E6-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA7E-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB65\uAB70-\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]|\uD800[\uDC00-\uDC0B\uDC0D-\uDC26\uDC28-\uDC3A\uDC3C\uDC3D\uDC3F-\uDC4D\uDC50-\uDC5D\uDC80-\uDCFA\uDD40-\uDD74\uDE80-\uDE9C\uDEA0-\uDED0\uDF00-\uDF1F\uDF2D-\uDF4A\uDF50-\uDF75\uDF80-\uDF9D\uDFA0-\uDFC3\uDFC8-\uDFCF\uDFD1-\uDFD5]|\uD801[\uDC00-\uDC9D\uDCB0-\uDCD3\uDCD8-\uDCFB\uDD00-\uDD27\uDD30-\uDD63\uDE00-\uDF36\uDF40-\uDF55\uDF60-\uDF67]|\uD802[\uDC00-\uDC05\uDC08\uDC0A-\uDC35\uDC37\uDC38\uDC3C\uDC3F-\uDC55\uDC60-\uDC76\uDC80-\uDC9E\uDCE0-\uDCF2\uDCF4\uDCF5\uDD00-\uDD15\uDD20-\uDD39\uDD80-\uDDB7\uDDBE\uDDBF\uDE00\uDE10-\uDE13\uDE15-\uDE17\uDE19-\uDE35\uDE60-\uDE7C\uDE80-\uDE9C\uDEC0-\uDEC7\uDEC9-\uDEE4\uDF00-\uDF35\uDF40-\uDF55\uDF60-\uDF72\uDF80-\uDF91]|\uD803[\uDC00-\uDC48\uDC80-\uDCB2\uDCC0-\uDCF2\uDD00-\uDD23\uDF00-\uDF1C\uDF27\uDF30-\uDF45]|\uD804[\uDC03-\uDC37\uDC83-\uDCAF\uDCD0-\uDCE8\uDD03-\uDD26\uDD44\uDD50-\uDD72\uDD76\uDD83-\uDDB2\uDDC1-\uDDC4\uDDDA\uDDDC\uDE00-\uDE11\uDE13-\uDE2B\uDE80-\uDE86\uDE88\uDE8A-\uDE8D\uDE8F-\uDE9D\uDE9F-\uDEA8\uDEB0-\uDEDE\uDF05-\uDF0C\uDF0F\uDF10\uDF13-\uDF28\uDF2A-\uDF30\uDF32\uDF33\uDF35-\uDF39\uDF3D\uDF50\uDF5D-\uDF61]|\uD805[\uDC00-\uDC34\uDC47-\uDC4A\uDC80-\uDCAF\uDCC4\uDCC5\uDCC7\uDD80-\uDDAE\uDDD8-\uDDDB\uDE00-\uDE2F\uDE44\uDE80-\uDEAA\uDF00-\uDF1A]|\uD806[\uDC00-\uDC2B\uDCA0-\uDCDF\uDCFF\uDE00\uDE0B-\uDE32\uDE3A\uDE50\uDE5C-\uDE83\uDE86-\uDE89\uDE9D\uDEC0-\uDEF8]|\uD807[\uDC00-\uDC08\uDC0A-\uDC2E\uDC40\uDC72-\uDC8F\uDD00-\uDD06\uDD08\uDD09\uDD0B-\uDD30\uDD46\uDD60-\uDD65\uDD67\uDD68\uDD6A-\uDD89\uDD98\uDEE0-\uDEF2]|\uD808[\uDC00-\uDF99]|\uD809[\uDC00-\uDC6E\uDC80-\uDD43]|[\uD80C\uD81C-\uD820\uD840-\uD868\uD86A-\uD86C\uD86F-\uD872\uD874-\uD879][\uDC00-\uDFFF]|\uD80D[\uDC00-\uDC2E]|\uD811[\uDC00-\uDE46]|\uD81A[\uDC00-\uDE38\uDE40-\uDE5E\uDED0-\uDEED\uDF00-\uDF2F\uDF40-\uDF43\uDF63-\uDF77\uDF7D-\uDF8F]|\uD81B[\uDE40-\uDE7F\uDF00-\uDF44\uDF50\uDF93-\uDF9F\uDFE0\uDFE1]|\uD821[\uDC00-\uDFF1]|\uD822[\uDC00-\uDEF2]|\uD82C[\uDC00-\uDD1E\uDD70-\uDEFB]|\uD82F[\uDC00-\uDC6A\uDC70-\uDC7C\uDC80-\uDC88\uDC90-\uDC99]|\uD835[\uDC00-\uDC54\uDC56-\uDC9C\uDC9E\uDC9F\uDCA2\uDCA5\uDCA6\uDCA9-\uDCAC\uDCAE-\uDCB9\uDCBB\uDCBD-\uDCC3\uDCC5-\uDD05\uDD07-\uDD0A\uDD0D-\uDD14\uDD16-\uDD1C\uDD1E-\uDD39\uDD3B-\uDD3E\uDD40-\uDD44\uDD46\uDD4A-\uDD50\uDD52-\uDEA5\uDEA8-\uDEC0\uDEC2-\uDEDA\uDEDC-\uDEFA\uDEFC-\uDF14\uDF16-\uDF34\uDF36-\uDF4E\uDF50-\uDF6E\uDF70-\uDF88\uDF8A-\uDFA8\uDFAA-\uDFC2\uDFC4-\uDFCB]|\uD83A[\uDC00-\uDCC4\uDD00-\uDD43]|\uD83B[\uDE00-\uDE03\uDE05-\uDE1F\uDE21\uDE22\uDE24\uDE27\uDE29-\uDE32\uDE34-\uDE37\uDE39\uDE3B\uDE42\uDE47\uDE49\uDE4B\uDE4D-\uDE4F\uDE51\uDE52\uDE54\uDE57\uDE59\uDE5B\uDE5D\uDE5F\uDE61\uDE62\uDE64\uDE67-\uDE6A\uDE6C-\uDE72\uDE74-\uDE77\uDE79-\uDE7C\uDE7E\uDE80-\uDE89\uDE8B-\uDE9B\uDEA1-\uDEA3\uDEA5-\uDEA9\uDEAB-\uDEBB]|\uD869[\uDC00-\uDED6\uDF00-\uDFFF]|\uD86D[\uDC00-\uDF34\uDF40-\uDFFF]|\uD86E[\uDC00-\uDC1D\uDC20-\uDFFF]|\uD873[\uDC00-\uDEA1\uDEB0-\uDFFF]|\uD87A[\uDC00-\uDFE0]|\uD87E[\uDC00-\uDE1D]/;
|
---|
1046 |
|
---|
1047 | return (ch === 36) || (ch === 95) || // $ (dollar) and _ (underscore)
|
---|
1048 | (ch >= 65 && ch <= 90) || // A..Z
|
---|
1049 | (ch >= 97 && ch <= 122) || // a..z
|
---|
1050 | ((ch >= 0x80) && NonAsciiIdentifierStart.test(fromCodePoint(ch)));
|
---|
1051 | }
|
---|
1052 |
|
---|
1053 | // Taken from the Esprima parser.
|
---|
1054 | function isIdentifierPart(ch) {
|
---|
1055 | // Generated by `tools/generate-identifier-regex.js`.
|
---|
1056 | var NonAsciiIdentifierPartOnly = /[0-9_\xB7\u0300-\u036F\u0387\u0483-\u0487\u0591-\u05BD\u05BF\u05C1\u05C2\u05C4\u05C5\u05C7\u0610-\u061A\u064B-\u0669\u0670\u06D6-\u06DC\u06DF-\u06E4\u06E7\u06E8\u06EA-\u06ED\u06F0-\u06F9\u0711\u0730-\u074A\u07A6-\u07B0\u07C0-\u07C9\u07EB-\u07F3\u07FD\u0816-\u0819\u081B-\u0823\u0825-\u0827\u0829-\u082D\u0859-\u085B\u08D3-\u08E1\u08E3-\u0903\u093A-\u093C\u093E-\u094F\u0951-\u0957\u0962\u0963\u0966-\u096F\u0981-\u0983\u09BC\u09BE-\u09C4\u09C7\u09C8\u09CB-\u09CD\u09D7\u09E2\u09E3\u09E6-\u09EF\u09FE\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\u0AFA-\u0AFF\u0B01-\u0B03\u0B3C\u0B3E-\u0B44\u0B47\u0B48\u0B4B-\u0B4D\u0B56\u0B57\u0B62\u0B63\u0B66-\u0B6F\u0B82\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE6-\u0BEF\u0C00-\u0C04\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55\u0C56\u0C62\u0C63\u0C66-\u0C6F\u0C81-\u0C83\u0CBC\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5\u0CD6\u0CE2\u0CE3\u0CE6-\u0CEF\u0D00-\u0D03\u0D3B\u0D3C\u0D3E-\u0D44\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D62\u0D63\u0D66-\u0D6F\u0D82\u0D83\u0DCA\u0DCF-\u0DD4\u0DD6\u0DD8-\u0DDF\u0DE6-\u0DEF\u0DF2\u0DF3\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0E50-\u0E59\u0EB1\u0EB4-\u0EB9\u0EBB\u0EBC\u0EC8-\u0ECD\u0ED0-\u0ED9\u0F18\u0F19\u0F20-\u0F29\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86\u0F87\u0F8D-\u0F97\u0F99-\u0FBC\u0FC6\u102B-\u103E\u1040-\u1049\u1056-\u1059\u105E-\u1060\u1062-\u1064\u1067-\u106D\u1071-\u1074\u1082-\u108D\u108F-\u109D\u135D-\u135F\u1369-\u1371\u1712-\u1714\u1732-\u1734\u1752\u1753\u1772\u1773\u17B4-\u17D3\u17DD\u17E0-\u17E9\u180B-\u180D\u1810-\u1819\u18A9\u1920-\u192B\u1930-\u193B\u1946-\u194F\u19D0-\u19DA\u1A17-\u1A1B\u1A55-\u1A5E\u1A60-\u1A7C\u1A7F-\u1A89\u1A90-\u1A99\u1AB0-\u1ABD\u1B00-\u1B04\u1B34-\u1B44\u1B50-\u1B59\u1B6B-\u1B73\u1B80-\u1B82\u1BA1-\u1BAD\u1BB0-\u1BB9\u1BE6-\u1BF3\u1C24-\u1C37\u1C40-\u1C49\u1C50-\u1C59\u1CD0-\u1CD2\u1CD4-\u1CE8\u1CED\u1CF2-\u1CF4\u1CF7-\u1CF9\u1DC0-\u1DF9\u1DFB-\u1DFF\u200C\u200D\u203F\u2040\u2054\u20D0-\u20DC\u20E1\u20E5-\u20F0\u2CEF-\u2CF1\u2D7F\u2DE0-\u2DFF\u302A-\u302F\u3099\u309A\uA620-\uA629\uA66F\uA674-\uA67D\uA69E\uA69F\uA6F0\uA6F1\uA802\uA806\uA80B\uA823-\uA827\uA880\uA881\uA8B4-\uA8C5\uA8D0-\uA8D9\uA8E0-\uA8F1\uA8FF-\uA909\uA926-\uA92D\uA947-\uA953\uA980-\uA983\uA9B3-\uA9C0\uA9D0-\uA9D9\uA9E5\uA9F0-\uA9F9\uAA29-\uAA36\uAA43\uAA4C\uAA4D\uAA50-\uAA59\uAA7B-\uAA7D\uAAB0\uAAB2-\uAAB4\uAAB7\uAAB8\uAABE\uAABF\uAAC1\uAAEB-\uAAEF\uAAF5\uAAF6\uABE3-\uABEA\uABEC\uABED\uABF0-\uABF9\uFB1E\uFE00-\uFE0F\uFE20-\uFE2F\uFE33\uFE34\uFE4D-\uFE4F\uFF10-\uFF19\uFF3F]|\uD800[\uDDFD\uDEE0\uDF76-\uDF7A]|\uD801[\uDCA0-\uDCA9]|\uD802[\uDE01-\uDE03\uDE05\uDE06\uDE0C-\uDE0F\uDE38-\uDE3A\uDE3F\uDEE5\uDEE6]|\uD803[\uDD24-\uDD27\uDD30-\uDD39\uDF46-\uDF50]|\uD804[\uDC00-\uDC02\uDC38-\uDC46\uDC66-\uDC6F\uDC7F-\uDC82\uDCB0-\uDCBA\uDCF0-\uDCF9\uDD00-\uDD02\uDD27-\uDD34\uDD36-\uDD3F\uDD45\uDD46\uDD73\uDD80-\uDD82\uDDB3-\uDDC0\uDDC9-\uDDCC\uDDD0-\uDDD9\uDE2C-\uDE37\uDE3E\uDEDF-\uDEEA\uDEF0-\uDEF9\uDF00-\uDF03\uDF3B\uDF3C\uDF3E-\uDF44\uDF47\uDF48\uDF4B-\uDF4D\uDF57\uDF62\uDF63\uDF66-\uDF6C\uDF70-\uDF74]|\uD805[\uDC35-\uDC46\uDC50-\uDC59\uDC5E\uDCB0-\uDCC3\uDCD0-\uDCD9\uDDAF-\uDDB5\uDDB8-\uDDC0\uDDDC\uDDDD\uDE30-\uDE40\uDE50-\uDE59\uDEAB-\uDEB7\uDEC0-\uDEC9\uDF1D-\uDF2B\uDF30-\uDF39]|\uD806[\uDC2C-\uDC3A\uDCE0-\uDCE9\uDE01-\uDE0A\uDE33-\uDE39\uDE3B-\uDE3E\uDE47\uDE51-\uDE5B\uDE8A-\uDE99]|\uD807[\uDC2F-\uDC36\uDC38-\uDC3F\uDC50-\uDC59\uDC92-\uDCA7\uDCA9-\uDCB6\uDD31-\uDD36\uDD3A\uDD3C\uDD3D\uDD3F-\uDD45\uDD47\uDD50-\uDD59\uDD8A-\uDD8E\uDD90\uDD91\uDD93-\uDD97\uDDA0-\uDDA9\uDEF3-\uDEF6]|\uD81A[\uDE60-\uDE69\uDEF0-\uDEF4\uDF30-\uDF36\uDF50-\uDF59]|\uD81B[\uDF51-\uDF7E\uDF8F-\uDF92]|\uD82F[\uDC9D\uDC9E]|\uD834[\uDD65-\uDD69\uDD6D-\uDD72\uDD7B-\uDD82\uDD85-\uDD8B\uDDAA-\uDDAD\uDE42-\uDE44]|\uD835[\uDFCE-\uDFFF]|\uD836[\uDE00-\uDE36\uDE3B-\uDE6C\uDE75\uDE84\uDE9B-\uDE9F\uDEA1-\uDEAF]|\uD838[\uDC00-\uDC06\uDC08-\uDC18\uDC1B-\uDC21\uDC23\uDC24\uDC26-\uDC2A]|\uD83A[\uDCD0-\uDCD6\uDD44-\uDD4A\uDD50-\uDD59]|\uDB40[\uDD00-\uDDEF]/;
|
---|
1057 |
|
---|
1058 | return isIdentifierStart(ch) ||
|
---|
1059 | (ch >= 48 && ch <= 57) || // 0..9
|
---|
1060 | ((ch >= 0x80) && NonAsciiIdentifierPartOnly.test(fromCodePoint(ch)));
|
---|
1061 | }
|
---|
1062 |
|
---|
1063 | function parseIdentityEscape() {
|
---|
1064 | // IdentityEscape ::
|
---|
1065 | // [+U] SyntaxCharacter
|
---|
1066 | // [+U] /
|
---|
1067 | // [~U] SourceCharacterIdentityEscape[?N]
|
---|
1068 | // SourceCharacterIdentityEscape[?N] ::
|
---|
1069 | // [~N] SourceCharacter but not c
|
---|
1070 | // [+N] SourceCharacter but not one of c or k
|
---|
1071 |
|
---|
1072 |
|
---|
1073 | var tmp;
|
---|
1074 | var l = lookahead();
|
---|
1075 | if (
|
---|
1076 | (hasUnicodeFlag && /[\^\$\.\*\+\?\(\)\\\[\]\{\}\|\/]/.test(l)) ||
|
---|
1077 | (!hasUnicodeFlag && l !== "c")
|
---|
1078 | ) {
|
---|
1079 | if (l === "k" && features.lookbehind) {
|
---|
1080 | return null;
|
---|
1081 | }
|
---|
1082 | tmp = incr();
|
---|
1083 | return createEscaped('identifier', tmp.charCodeAt(0), tmp, 1);
|
---|
1084 | }
|
---|
1085 |
|
---|
1086 | return null;
|
---|
1087 | }
|
---|
1088 |
|
---|
1089 | function parseCharacterClass() {
|
---|
1090 | // CharacterClass ::
|
---|
1091 | // [ [lookahead ∉ {^}] ClassRanges ]
|
---|
1092 | // [ ^ ClassRanges ]
|
---|
1093 |
|
---|
1094 | var res, from = pos;
|
---|
1095 | if (res = matchReg(/^\[\^/)) {
|
---|
1096 | res = parseClassRanges();
|
---|
1097 | skip(']');
|
---|
1098 | return createCharacterClass(res, true, from, pos);
|
---|
1099 | } else if (match('[')) {
|
---|
1100 | res = parseClassRanges();
|
---|
1101 | skip(']');
|
---|
1102 | return createCharacterClass(res, false, from, pos);
|
---|
1103 | }
|
---|
1104 |
|
---|
1105 | return null;
|
---|
1106 | }
|
---|
1107 |
|
---|
1108 | function parseClassRanges() {
|
---|
1109 | // ClassRanges ::
|
---|
1110 | // [empty]
|
---|
1111 | // [~V] NonemptyClassRanges
|
---|
1112 | // [+V] ClassContents
|
---|
1113 |
|
---|
1114 | var res;
|
---|
1115 | if (current(']')) {
|
---|
1116 | // Empty array means nothing inside of the ClassRange.
|
---|
1117 | return { kind: 'union', body: [] };
|
---|
1118 | } else if (hasUnicodeSetFlag) {
|
---|
1119 | return parseClassContents();
|
---|
1120 | } else {
|
---|
1121 | res = parseNonemptyClassRanges();
|
---|
1122 | if (!res) {
|
---|
1123 | bail('nonEmptyClassRanges');
|
---|
1124 | }
|
---|
1125 | return { kind: 'union', body: res };
|
---|
1126 | }
|
---|
1127 | }
|
---|
1128 |
|
---|
1129 | function parseHelperClassRanges(atom) {
|
---|
1130 | var from, to, res, atomTo, dash;
|
---|
1131 | if (current('-') && !next(']')) {
|
---|
1132 | // ClassAtom - ClassAtom ClassRanges
|
---|
1133 | from = atom.range[0];
|
---|
1134 | dash = createCharacter(match('-'));
|
---|
1135 |
|
---|
1136 | atomTo = parseClassAtom();
|
---|
1137 | if (!atomTo) {
|
---|
1138 | bail('classAtom');
|
---|
1139 | }
|
---|
1140 | to = pos;
|
---|
1141 |
|
---|
1142 | // Parse the next class range if exists.
|
---|
1143 | var classRanges = parseClassRanges();
|
---|
1144 | if (!classRanges) {
|
---|
1145 | bail('classRanges');
|
---|
1146 | }
|
---|
1147 |
|
---|
1148 | // Check if both the from and atomTo have codePoints.
|
---|
1149 | if (!('codePoint' in atom) || !('codePoint' in atomTo)) {
|
---|
1150 | if (!hasUnicodeFlag) {
|
---|
1151 | // If not, don't create a range but treat them as
|
---|
1152 | // `atom` `-` `atom` instead.
|
---|
1153 | //
|
---|
1154 | // SEE: https://tc39.es/ecma262/#sec-regular-expression-patterns-semantics
|
---|
1155 | // NonemptyClassRanges::ClassAtom-ClassAtomClassRanges
|
---|
1156 | // CharacterRangeOrUnion
|
---|
1157 | res = [atom, dash, atomTo];
|
---|
1158 | } else {
|
---|
1159 | // With unicode flag, both sides must have codePoints if
|
---|
1160 | // one side has a codePoint.
|
---|
1161 | //
|
---|
1162 | // SEE: https://tc39.es/ecma262/#sec-patterns-static-semantics-early-errors
|
---|
1163 | // NonemptyClassRanges :: ClassAtom - ClassAtom ClassRanges
|
---|
1164 | bail('invalid character class');
|
---|
1165 | }
|
---|
1166 | } else {
|
---|
1167 | res = [createClassRange(atom, atomTo, from, to)];
|
---|
1168 | }
|
---|
1169 |
|
---|
1170 | if (classRanges.type === 'empty') {
|
---|
1171 | return res;
|
---|
1172 | }
|
---|
1173 | return res.concat(classRanges.body);
|
---|
1174 | }
|
---|
1175 |
|
---|
1176 | res = parseNonemptyClassRangesNoDash();
|
---|
1177 | if (!res) {
|
---|
1178 | bail('nonEmptyClassRangesNoDash');
|
---|
1179 | }
|
---|
1180 |
|
---|
1181 | return [atom].concat(res);
|
---|
1182 | }
|
---|
1183 |
|
---|
1184 | function parseNonemptyClassRanges() {
|
---|
1185 | // NonemptyClassRanges ::
|
---|
1186 | // ClassAtom
|
---|
1187 | // ClassAtom NonemptyClassRangesNoDash
|
---|
1188 | // ClassAtom - ClassAtom ClassRanges
|
---|
1189 |
|
---|
1190 | var atom = parseClassAtom();
|
---|
1191 | if (!atom) {
|
---|
1192 | bail('classAtom');
|
---|
1193 | }
|
---|
1194 |
|
---|
1195 | if (current(']')) {
|
---|
1196 | // ClassAtom
|
---|
1197 | return [atom];
|
---|
1198 | }
|
---|
1199 |
|
---|
1200 | // ClassAtom NonemptyClassRangesNoDash
|
---|
1201 | // ClassAtom - ClassAtom ClassRanges
|
---|
1202 | return parseHelperClassRanges(atom);
|
---|
1203 | }
|
---|
1204 |
|
---|
1205 | function parseNonemptyClassRangesNoDash() {
|
---|
1206 | // NonemptyClassRangesNoDash ::
|
---|
1207 | // ClassAtom
|
---|
1208 | // ClassAtomNoDash NonemptyClassRangesNoDash
|
---|
1209 | // ClassAtomNoDash - ClassAtom ClassRanges
|
---|
1210 |
|
---|
1211 | var res = parseClassAtom();
|
---|
1212 | if (!res) {
|
---|
1213 | bail('classAtom');
|
---|
1214 | }
|
---|
1215 | if (current(']')) {
|
---|
1216 | // ClassAtom
|
---|
1217 | return res;
|
---|
1218 | }
|
---|
1219 |
|
---|
1220 | // ClassAtomNoDash NonemptyClassRangesNoDash
|
---|
1221 | // ClassAtomNoDash - ClassAtom ClassRanges
|
---|
1222 | return parseHelperClassRanges(res);
|
---|
1223 | }
|
---|
1224 |
|
---|
1225 | function parseClassAtom() {
|
---|
1226 | // ClassAtom ::
|
---|
1227 | // -
|
---|
1228 | // ClassAtomNoDash
|
---|
1229 | if (match('-')) {
|
---|
1230 | return createCharacter('-');
|
---|
1231 | } else {
|
---|
1232 | return parseClassAtomNoDash();
|
---|
1233 | }
|
---|
1234 | }
|
---|
1235 |
|
---|
1236 | function parseClassAtomNoDash() {
|
---|
1237 | // ClassAtomNoDash ::
|
---|
1238 | // SourceCharacter but not one of \ or ] or -
|
---|
1239 | // \ ClassEscape
|
---|
1240 |
|
---|
1241 | var res;
|
---|
1242 | if (res = matchReg(/^[^\\\]-]/)) {
|
---|
1243 | return createCharacter(res[0]);
|
---|
1244 | } else if (match('\\')) {
|
---|
1245 | res = parseClassEscape();
|
---|
1246 | if (!res) {
|
---|
1247 | bail('classEscape');
|
---|
1248 | }
|
---|
1249 |
|
---|
1250 | return parseUnicodeSurrogatePairEscape(res);
|
---|
1251 | }
|
---|
1252 | }
|
---|
1253 |
|
---|
1254 | function parseClassContents() {
|
---|
1255 | // ClassContents ::
|
---|
1256 | // ClassUnion
|
---|
1257 | // ClassIntersection
|
---|
1258 | // ClassSubtraction
|
---|
1259 | //
|
---|
1260 | // ClassUnion ::
|
---|
1261 | // ClassRange ClassUnion?
|
---|
1262 | // ClassOperand ClassUnion?
|
---|
1263 | //
|
---|
1264 | // ClassIntersection ::
|
---|
1265 | // ClassOperand && [lookahead ≠ &] ClassOperand
|
---|
1266 | // ClassIntersection && [lookahead ≠ &] ClassOperand
|
---|
1267 | //
|
---|
1268 | // ClassSubtraction ::
|
---|
1269 | // ClassOperand -- ClassOperand
|
---|
1270 | // ClassSubtraction -- ClassOperand
|
---|
1271 |
|
---|
1272 | var body = [];
|
---|
1273 | var kind;
|
---|
1274 | var from = pos;
|
---|
1275 |
|
---|
1276 | var operand = parseClassOperand(/* allowRanges*/ true);
|
---|
1277 | body.push(operand);
|
---|
1278 |
|
---|
1279 | if (operand.type === 'classRange') {
|
---|
1280 | kind = 'union';
|
---|
1281 | } else if (current('&')) {
|
---|
1282 | kind = 'intersection';
|
---|
1283 | } else if (current('-')) {
|
---|
1284 | kind = 'subtraction';
|
---|
1285 | } else {
|
---|
1286 | kind = 'union';
|
---|
1287 | }
|
---|
1288 |
|
---|
1289 | while (!current(']')) {
|
---|
1290 | if (kind === 'intersection') {
|
---|
1291 | skip('&');
|
---|
1292 | skip('&');
|
---|
1293 | if (current('&')) {
|
---|
1294 | bail('&& cannot be followed by &. Wrap it in parentheses: &&(&).');
|
---|
1295 | }
|
---|
1296 | } else if (kind === 'subtraction') {
|
---|
1297 | skip('-');
|
---|
1298 | skip('-');
|
---|
1299 | }
|
---|
1300 |
|
---|
1301 | operand = parseClassOperand(/* allowRanges*/ kind === 'union');
|
---|
1302 | body.push(operand);
|
---|
1303 | }
|
---|
1304 |
|
---|
1305 | return { kind: kind, body: body };
|
---|
1306 | }
|
---|
1307 |
|
---|
1308 | function parseClassOperand(allowRanges) {
|
---|
1309 | // ClassOperand ::
|
---|
1310 | // ClassCharacter
|
---|
1311 | // ClassStrings
|
---|
1312 | // NestedClass
|
---|
1313 | //
|
---|
1314 | // NestedClass ::
|
---|
1315 | // [ [lookahead ≠ ^] ClassRanges[+U,+V] ]
|
---|
1316 | // [ ^ ClassRanges[+U,+V] ]
|
---|
1317 | // \ CharacterClassEscape[+U, +V]
|
---|
1318 | //
|
---|
1319 | // ClassRange ::
|
---|
1320 | // ClassCharacter - ClassCharacter
|
---|
1321 | //
|
---|
1322 | // ClassCharacter ::
|
---|
1323 | // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter
|
---|
1324 | // \ CharacterEscape[+U]
|
---|
1325 | // \ ClassHalfOfDouble
|
---|
1326 | // \ b
|
---|
1327 | //
|
---|
1328 | // ClassSyntaxCharacter ::
|
---|
1329 | // one of ( ) [ ] { } / - \ |
|
---|
1330 |
|
---|
1331 | var from = pos;
|
---|
1332 | var start, res;
|
---|
1333 |
|
---|
1334 | if (match('\\')) {
|
---|
1335 | if (res = parseCharacterClassEscape()) {
|
---|
1336 | start = res;
|
---|
1337 | } else if (res = parseClassCharacterEscapedHelper()) {
|
---|
1338 | // ClassOperand ::
|
---|
1339 | // ...
|
---|
1340 | // NestedClass
|
---|
1341 | //
|
---|
1342 | // NestedClass ::
|
---|
1343 | // ...
|
---|
1344 | // \ CharacterClassEscape[+U, +V]
|
---|
1345 | return res;
|
---|
1346 | } else {
|
---|
1347 | bail('Invalid escape', '\\' + lookahead(), from);
|
---|
1348 | }
|
---|
1349 | } else if (res = parseClassCharacterUnescapedHelper()) {
|
---|
1350 | start = res;
|
---|
1351 | } else if (res = parseClassStrings() || parseCharacterClass()) {
|
---|
1352 | // ClassOperand ::
|
---|
1353 | // ...
|
---|
1354 | // ClassStrings
|
---|
1355 | // NestedClass
|
---|
1356 | //
|
---|
1357 | // NestedClass ::
|
---|
1358 | // [ [lookahead ≠ ^] ClassRanges[+U,+V] ]
|
---|
1359 | // [ ^ ClassRanges[+U,+V] ]
|
---|
1360 | // ...
|
---|
1361 | return res;
|
---|
1362 | } else {
|
---|
1363 | bail('Invalid character', lookahead());
|
---|
1364 | }
|
---|
1365 |
|
---|
1366 | if (allowRanges && current('-') && !next('-')) {
|
---|
1367 | skip('-');
|
---|
1368 |
|
---|
1369 | if (res = parseClassCharacter()) {
|
---|
1370 | // ClassRange ::
|
---|
1371 | // ClassCharacter - ClassCharacter
|
---|
1372 | return createClassRange(start, res, from, pos);
|
---|
1373 | }
|
---|
1374 |
|
---|
1375 | bail('Invalid range end', lookahead());
|
---|
1376 | }
|
---|
1377 |
|
---|
1378 | // ClassOperand ::
|
---|
1379 | // ClassCharacter
|
---|
1380 | // ...
|
---|
1381 | return start;
|
---|
1382 | }
|
---|
1383 |
|
---|
1384 | function parseClassCharacter() {
|
---|
1385 | // ClassCharacter ::
|
---|
1386 | // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter
|
---|
1387 | // \ CharacterEscape[+U]
|
---|
1388 | // \ ClassHalfOfDouble
|
---|
1389 | // \ b
|
---|
1390 |
|
---|
1391 | if (match('\\')) {
|
---|
1392 | if (res = parseClassCharacterEscapedHelper()) {
|
---|
1393 | return res;
|
---|
1394 | } else {
|
---|
1395 | bail('Invalid escape', '\\' + lookahead(), from);
|
---|
1396 | }
|
---|
1397 | }
|
---|
1398 |
|
---|
1399 | return parseClassCharacterUnescapedHelper();
|
---|
1400 | }
|
---|
1401 |
|
---|
1402 | function parseClassCharacterUnescapedHelper() {
|
---|
1403 | // ClassCharacter ::
|
---|
1404 | // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter
|
---|
1405 | // ...
|
---|
1406 |
|
---|
1407 | var res;
|
---|
1408 | if (res = matchReg(/^[^()[\]{}/\-\\|]/)) {
|
---|
1409 | return createCharacter(res);
|
---|
1410 | };
|
---|
1411 | }
|
---|
1412 |
|
---|
1413 | function parseClassCharacterEscapedHelper() {
|
---|
1414 | // ClassCharacter ::
|
---|
1415 | // ...
|
---|
1416 | // \ CharacterEscape[+U]
|
---|
1417 | // \ ClassHalfOfDouble
|
---|
1418 | // \ b
|
---|
1419 |
|
---|
1420 | if (match('b')) {
|
---|
1421 | return createEscaped('singleEscape', 0x0008, '\\b');
|
---|
1422 | } else if (match('B')) {
|
---|
1423 | bail('\\B not possible inside of ClassContents', '', pos - 2);
|
---|
1424 | } else if (res = matchReg(/^[&\-!#%,:;<=>@_`~]/)) {
|
---|
1425 | return createEscaped('identifier', res[0].codePointAt(0), res[0]);
|
---|
1426 | } else if (res = parseCharacterEscape()) {
|
---|
1427 | return res;
|
---|
1428 | } else {
|
---|
1429 | return null;
|
---|
1430 | }
|
---|
1431 | }
|
---|
1432 |
|
---|
1433 | function parseClassStrings() {
|
---|
1434 | // ClassStrings ::
|
---|
1435 | // ( ClassString MoreClassStrings? )
|
---|
1436 |
|
---|
1437 | var res = [];
|
---|
1438 | var from = pos;
|
---|
1439 |
|
---|
1440 | if (!match('(')) {
|
---|
1441 | return null;
|
---|
1442 | }
|
---|
1443 |
|
---|
1444 | do {
|
---|
1445 | res.push(parseClassString());
|
---|
1446 | } while (match('|'));
|
---|
1447 |
|
---|
1448 | skip(')');
|
---|
1449 |
|
---|
1450 | return createClassStrings(res, from, pos);
|
---|
1451 | }
|
---|
1452 |
|
---|
1453 | function parseClassString() {
|
---|
1454 | // ClassString ::
|
---|
1455 | // [empty]
|
---|
1456 | // NonEmptyClassString
|
---|
1457 | //
|
---|
1458 | // NonEmptyClassString ::
|
---|
1459 | // ClassCharacter NonEmptyClassString?
|
---|
1460 |
|
---|
1461 | var res = [], from = pos;
|
---|
1462 | var char;
|
---|
1463 |
|
---|
1464 | while (char = parseClassCharacter()) {
|
---|
1465 | res.push(char);
|
---|
1466 | }
|
---|
1467 |
|
---|
1468 | return createClassString(res, from, pos);
|
---|
1469 | }
|
---|
1470 |
|
---|
1471 | function bail(message, details, from, to) {
|
---|
1472 | from = from == null ? pos : from;
|
---|
1473 | to = to == null ? from : to;
|
---|
1474 |
|
---|
1475 | var contextStart = Math.max(0, from - 10);
|
---|
1476 | var contextEnd = Math.min(to + 10, str.length);
|
---|
1477 |
|
---|
1478 | // Output a bit of context and a line pointing to where our error is.
|
---|
1479 | //
|
---|
1480 | // We are assuming that there are no actual newlines in the content as this is a regular expression.
|
---|
1481 | var context = ' ' + str.substring(contextStart, contextEnd);
|
---|
1482 | var pointer = ' ' + new Array(from - contextStart + 1).join(' ') + '^';
|
---|
1483 |
|
---|
1484 | throw SyntaxError(message + ' at position ' + from + (details ? ': ' + details : '') + '\n' + context + '\n' + pointer);
|
---|
1485 | }
|
---|
1486 |
|
---|
1487 | var backrefDenied = [];
|
---|
1488 | var closedCaptureCounter = 0;
|
---|
1489 | var firstIteration = true;
|
---|
1490 | var hasUnicodeFlag = (flags || "").indexOf("u") !== -1;
|
---|
1491 | var hasUnicodeSetFlag = (flags || "").indexOf("v") !== -1;
|
---|
1492 | var pos = 0;
|
---|
1493 |
|
---|
1494 | if (hasUnicodeSetFlag && !features.unicodeSet) {
|
---|
1495 | throw new Error('The "v" flag is only supported when the .unicodeSet option is enabled.');
|
---|
1496 | }
|
---|
1497 |
|
---|
1498 | if (hasUnicodeFlag && hasUnicodeSetFlag) {
|
---|
1499 | throw new Error('The "u" and "v" flags are mutually exclusive.');
|
---|
1500 | }
|
---|
1501 |
|
---|
1502 | // Convert the input to a string and treat the empty string special.
|
---|
1503 | str = String(str);
|
---|
1504 | if (str === '') {
|
---|
1505 | str = '(?:)';
|
---|
1506 | }
|
---|
1507 |
|
---|
1508 | var result = parseDisjunction();
|
---|
1509 |
|
---|
1510 | if (result.range[1] !== str.length) {
|
---|
1511 | bail('Could not parse entire input - got stuck', '', result.range[1]);
|
---|
1512 | }
|
---|
1513 |
|
---|
1514 | // The spec requires to interpret the `\2` in `/\2()()/` as backreference.
|
---|
1515 | // As the parser collects the number of capture groups as the string is
|
---|
1516 | // parsed it is impossible to make these decisions at the point when the
|
---|
1517 | // `\2` is handled. In case the local decision turns out to be wrong after
|
---|
1518 | // the parsing has finished, the input string is parsed a second time with
|
---|
1519 | // the total number of capture groups set.
|
---|
1520 | //
|
---|
1521 | // SEE: https://github.com/jviereck/regjsparser/issues/70
|
---|
1522 | for (var i = 0; i < backrefDenied.length; i++) {
|
---|
1523 | if (backrefDenied[i] <= closedCaptureCounter) {
|
---|
1524 | // Parse the input a second time.
|
---|
1525 | pos = 0;
|
---|
1526 | firstIteration = false;
|
---|
1527 | return parseDisjunction();
|
---|
1528 | }
|
---|
1529 | }
|
---|
1530 |
|
---|
1531 | return result;
|
---|
1532 | }
|
---|
1533 |
|
---|
1534 | var regjsparser = {
|
---|
1535 | parse: parse
|
---|
1536 | };
|
---|
1537 |
|
---|
1538 | if (typeof module !== 'undefined' && module.exports) {
|
---|
1539 | module.exports = regjsparser;
|
---|
1540 | } else {
|
---|
1541 | window.regjsparser = regjsparser;
|
---|
1542 | }
|
---|
1543 |
|
---|
1544 | }());
|
---|