summaryrefslogtreecommitdiff
path: root/deps/npm/node_modules/minimatch/dist/cjs/parse.js
blob: 2fff625bcbb6e9213cac305910bd995003ec549d (plain)
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
"use strict";
// parse a single path portion
Object.defineProperty(exports, "__esModule", { value: true });
exports.AST = void 0;
const brace_expressions_1 = require("./brace-expressions");
const types = new Set(['!', '?', '+', '*', '@']);
const isExtglobType = (c) => types.has(c);
// characters that indicate a start of pattern needs the "no dots" bit
const addPatternStart = new Set(['[', '.']);
const justDots = new Set(['..', '.']);
const reSpecials = new Set('().*{}+?[]^$\\!');
const regExpEscape = (s) => s.replace(/[-[\]{}()*+?.,\\^$|#\s]/g, '\\$&');
// any single thing other than /
// don't need to escape / when using new RegExp()
const qmark = '[^/]';
// * => any number of characters
const star = qmark + '*?';
class AST {
    type;
    #root;
    #parts = [];
    #parent;
    #parentIndex;
    #negs;
    #filledNegs = false;
    #options;
    constructor(type, parent, options = {}) {
        this.type = type;
        this.#parent = parent;
        this.#root = this.#parent ? this.#parent.#root : this;
        this.#options = this.#root === this ? options : this.#root.#options;
        this.#negs = this.#root === this ? [] : this.#root.#negs;
        if (type === '!' && !this.#root.#filledNegs)
            this.#negs.push(this);
        this.#parentIndex = this.#parent ? this.#parent.#parts.length : 0;
    }
    fillNegs() {
        if (this !== this.#root) {
            this.#root.fillNegs();
            return this;
        }
        if (this.#filledNegs)
            return this;
        this.#filledNegs = true;
        let n;
        while ((n = this.#negs.pop())) {
            if (n.type !== '!')
                continue;
            // walk up the tree, appending everthing that comes AFTER parentIndex
            let p = n;
            let pp = p.#parent;
            while (pp) {
                for (let i = p.#parentIndex + 1; !pp.type && i < pp.#parts.length; i++) {
                    for (const part of n.#parts) {
                        /* c8 ignore start */
                        if (typeof part === 'string') {
                            throw new Error('string part in extglob AST??');
                        }
                        /* c8 ignore stop */
                        part.copyIn(pp.#parts[i]);
                    }
                }
                p = pp;
                pp = p.#parent;
            }
        }
        return this;
    }
    push(...parts) {
        for (const p of parts) {
            if (p === '')
                continue;
            /* c8 ignore start */
            if (typeof p !== 'string' && !(p instanceof AST && p.#parent === this)) {
                throw new Error('invalid part: ' + p);
            }
            /* c8 ignore stop */
            this.#parts.push(p);
        }
    }
    toJSON() {
        const ret = this.type === null ? this.#parts.slice() : [this.type, ...this.#parts];
        if (this.isStart() && !this.type)
            ret.unshift([]);
        if (this.isEnd() &&
            (this === this.#root ||
                (this.#root.#filledNegs && this.#parent?.type === '!'))) {
            ret.push({});
        }
        return ret;
    }
    isStart() {
        if (this.#root === this)
            return true;
        // if (this.type) return !!this.#parent?.isStart()
        if (!this.#parent?.isStart())
            return false;
        return this.#parentIndex === 0;
    }
    isEnd() {
        if (this.#root === this)
            return true;
        if (this.#parent?.type === '!')
            return true;
        if (!this.#parent?.isEnd())
            return false;
        if (!this.type)
            return this.#parent?.isEnd();
        return (this.#parentIndex === (this.#parent ? this.#parent.#parts.length : 0) - 1);
    }
    copyIn(part) {
        if (typeof part === 'string')
            this.push(part);
        else
            this.push(part.clone(this));
    }
    clone(parent) {
        const c = new AST(this.type, parent);
        for (const p of this.#parts) {
            c.copyIn(p);
        }
        return c;
    }
    static #parseAST(str, ast, pos, opt) {
        let escaping = false;
        if (ast.type === null) {
            // outside of a extglob, append until we find a start
            let i = pos;
            let acc = '';
            while (i < str.length) {
                const c = str.charAt(i++);
                // still accumulate escapes at this point, but we do ignore
                // starts that are escaped
                if (escaping || c === '\\') {
                    escaping = !escaping;
                    acc += c;
                    continue;
                }
                if (!opt.noext && isExtglobType(c) && str.charAt(i) === '(') {
                    ast.push(acc);
                    acc = '';
                    const ext = new AST(c, ast);
                    i = AST.#parseAST(str, ext, i, opt);
                    ast.push(ext);
                    continue;
                }
                acc += c;
            }
            ast.push(acc);
            return i;
        }
        // some kind of extglob, pos is at the (
        // find the next | or )
        let i = pos + 1;
        let part = new AST(null, ast);
        const parts = [];
        let acc = '';
        while (i < str.length) {
            const c = str.charAt(i++);
            // still accumulate escapes at this point, but we do ignore
            // starts that are escaped
            if (escaping || c === '\\') {
                escaping = !escaping;
                acc += c;
                continue;
            }
            if (isExtglobType(c) && str.charAt(i) === '(') {
                part.push(acc);
                acc = '';
                const ext = new AST(c, part);
                part.push(ext);
                i = AST.#parseAST(str, ext, i, opt);
                continue;
            }
            if (c === '|') {
                part.push(acc);
                acc = '';
                parts.push(part);
                part = new AST(null, ast);
                continue;
            }
            if (c === ')') {
                part.push(acc);
                acc = '';
                ast.push(...parts, part);
                return i;
            }
            acc += c;
        }
        // if we got here, it was a malformed extglob! not an extglob, but
        // maybe something else in there.
        ast.type = null;
        ast.#parts = [str.substring(pos)];
        return i;
    }
    static fromGlob(pattern, options = {}) {
        const ast = new AST(null, undefined, options);
        AST.#parseAST(pattern, ast, 0, options);
        console.log('parsed', pattern, JSON.stringify(ast));
        return ast;
    }
    toRegExpSource() {
        if (this.#root === this)
            this.fillNegs();
        if (!this.type) {
            const src = this.#parts
                .map(p => {
                if (typeof p === 'string')
                    return AST.#parseGlob(p, this.#options);
                else
                    return p.toRegExpSource();
            })
                .join('');
            let start = '';
            if (this.isStart() && typeof this.#parts[0] === 'string') {
                // '.' and '..' cannot match unless the pattern is that exactly
                const dotTravAllowed = this.#parts.length === 1 && justDots.has(this.#parts[0]);
                if (dotTravAllowed) {
                    start = '(?:^|\\/)';
                }
                else {
                    const dotsAllowed = this.#options.dot ||
                        // no need to prevent dots if it can't match a dot, or if a sub-pattern
                        // will be preventing it anyway.
                        !addPatternStart.has(src.charAt(0));
                    start = dotsAllowed ? '(?!(?:^|\\/)\\.{1,2}(?:$|\\/))' : '(?!\\.)';
                }
            }
            let end = '';
            if (this.isEnd() &&
                (this === this.#root ||
                    (this.#root.#filledNegs && this.#parent?.type === '!'))) {
                end = '(?:$|\\/)';
            }
            return start + src + end;
        }
        // some kind of extglob
        const start = this.type === '!' ? '(?:(?!(?:' : '(?:';
        const body = this.#parts
            .map(p => {
            /* c8 ignore start */
            if (typeof p === 'string') {
                throw new Error('string type in extglob ast??');
            }
            /* c8 ignore stop */
            return p.toRegExpSource();
        })
            .join('|');
        const close = this.type === '!'
            ? '))[^/]*?)'
            : this.type === '@'
                ? ')'
                : `)${this.type}`;
        return start + body + close;
    }
    static #parseGlob(glob, options) {
        let escaping = false;
        let re = '';
        let uflag = false;
        let hasMagic = false;
        for (let i = 0; i < glob.length; i++) {
            const c = glob.charAt(i);
            if (escaping) {
                escaping = false;
                re += (reSpecials.has(c) ? '\\' : '') + c;
                continue;
            }
            if (c === '\\') {
                if (i === glob.length - 1) {
                    re += '\\\\';
                }
                else {
                    escaping = true;
                }
                continue;
            }
            if (c === '[') {
                const [src, needUflag, consumed, magic] = (0, brace_expressions_1.parseClass)(glob, i);
                if (consumed) {
                    re += src;
                    uflag = uflag || needUflag;
                    i += consumed - 1;
                    hasMagic = hasMagic || magic;
                    continue;
                }
            }
            if (c === '*') {
                re += star;
                hasMagic = true;
                continue;
            }
            if (c === '?') {
                re += qmark;
                hasMagic = true;
                continue;
            }
            re += regExpEscape(c);
        }
        return re;
    }
}
exports.AST = AST;
const pattern = 'a@(i|w!(x|y)z+(l|m)|j)';
const ast = AST.fromGlob(pattern).fillNegs();
console.log('negged', pattern, JSON.stringify(ast));
console.log('to re src', pattern, ast.toRegExpSource());
// // the type (exttype or null for strings), and array of children tokens
//
// // append everything after a negative extglob to each of the parts
// // of the negative extglob node.  So, eg, [a, [!, x, y], z]
//
// //
// //
// //
// //
//
// const globUnescape = (s: string) => s.replace(/\\(.)/g, '$1')
// const regExpEscape = (s: string) =>
//   s.replace(/[-[\]{}()*+?.,\\^$|#\s]/g, '\\$&')
//
// // "abc" -> { a:true, b:true, c:true }
// const charSet = (s: string) =>
//   s.split('').reduce((set: { [k: string]: boolean }, c) => {
//     set[c] = true
//     return set
//   }, {})
//
// // characters that need to be escaped in RegExp.
// const reSpecials = charSet('().*{}+?[]^$\\!')
//
// // characters that indicate we have to add the pattern start
// const addPatternStartSet = charSet('[.(')
//
// // any single thing other than /
// // don't need to escape / when using new RegExp()
// const qmark = '[^/]'
//
// // * => any number of characters
// const star = qmark + '*?'
//
// // TODO: take an offset and length, so we can sub-parse the extglobs
// const parse = (
//   options: MinimatchOptions,
//   pattern: string,
//   debug: (...a: any[]) => void
// ): false | string => {
//   assertValidPattern(pattern)
//
//   if (pattern === '') return ''
//
//   let re = ''
//   let hasMagic = false
//   let escaping = false
//   // ? => one single character
//   let uflag = false
//
//   // . and .. never match anything that doesn't start with .,
//   // even when options.dot is set.  However, if the pattern
//   // starts with ., then traversal patterns can match.
//   let dotTravAllowed = pattern.charAt(0) === '.'
//   let dotFileAllowed = options.dot || dotTravAllowed
//   const patternStart = () =>
//     dotTravAllowed
//       ? ''
//       : dotFileAllowed
//       ? '(?!(?:^|\\/)\\.{1,2}(?:$|\\/))'
//       : '(?!\\.)'
//   const subPatternStart = (p: string) =>
//     p.charAt(0) === '.'
//       ? ''
//       : options.dot
//       ? '(?!(?:^|\\/)\\.{1,2}(?:$|\\/))'
//       : '(?!\\.)'
//
//   const clearStateChar = () => {
//     if (stateChar) {
//       // we had some state-tracking character
//       // that wasn't consumed by this pass.
//       switch (stateChar) {
//         case '*':
//           re += star
//           hasMagic = true
//           break
//         case '?':
//           re += qmark
//           hasMagic = true
//           break
//         default:
//           re += '\\' + stateChar
//           break
//       }
//       debug('clearStateChar %j %j', stateChar, re)
//       stateChar = false
//     }
//   }
//
//   for (
//     let i = 0, c: string;
//     i < pattern.length && (c = pattern.charAt(i));
//     i++
//   ) {
//     debug('%s\t%s %s %j', pattern, i, re, c)
//
//     // skip over any that are escaped.
//     if (escaping) {
//       // completely not allowed, even escaped.
//       // should be impossible.
//       /* c8 ignore start */
//       if (c === '/') {
//         return false
//       }
//       /* c8 ignore stop */
//
//       if (reSpecials[c]) {
//         re += '\\'
//       }
//       re += c
//       escaping = false
//       continue
//     }
//
//     switch (c) {
//       // Should already be path-split by now.
//       /* c8 ignore start */
//       case '/': {
//         return false
//       }
//       /* c8 ignore stop */
//
//       case '\\':
//         clearStateChar()
//         escaping = true
//         continue
//
//       // the various stateChar values
//       // for the "extglob" stuff.
//       case '?':
//       case '*':
//       case '+':
//       case '@':
//       case '!':
//         debug('%s\t%s %s %j <-- stateChar', pattern, i, re, c)
//
//         // if we already have a stateChar, then it means
//         // that there was something like ** or +? in there.
//         // Handle the stateChar, then proceed with this one.
//         debug('call clearStateChar %j', stateChar)
//         clearStateChar()
//         stateChar = c
//         // if extglob is disabled, then +(asdf|foo) isn't a thing.
//         // just clear the statechar *now*, rather than even diving into
//         // the patternList stuff.
//         if (options.noext) clearStateChar()
//         continue
//
//       case '(': {
//         if (!stateChar) {
//           re += '\\('
//           continue
//         }
//
//         const plEntry: PatternListEntry = {
//           type: stateChar,
//           start: i - 1,
//           reStart: re.length,
//           open: plTypes[stateChar].open,
//           close: plTypes[stateChar].close,
//         }
//         debug(pattern, '\t', plEntry)
//         patternListStack.push(plEntry)
//         // negation is (?:(?!(?:js)(?:<rest>))[^/]*)
//         re += plEntry.open
//         // next entry starts with a dot maybe?
//         if (plEntry.start === 0 && plEntry.type !== '!') {
//           dotTravAllowed = true
//           re += subPatternStart(pattern.slice(i + 1))
//         }
//         debug('plType %j %j', stateChar, re)
//         stateChar = false
//         continue
//       }
//
//       case ')': {
//         const plEntry = patternListStack[patternListStack.length - 1]
//         if (!plEntry) {
//           re += '\\)'
//           continue
//         }
//         patternListStack.pop()
//
//         // closing an extglob
//         clearStateChar()
//         hasMagic = true
//         pl = plEntry
//         // negation is (?:(?!js)[^/]*)
//         // The others are (?:<pattern>)<type>
//         re += pl.close
//         if (pl.type === '!') {
//           negativeLists.push(Object.assign(pl, { reEnd: re.length }))
//         }
//         continue
//       }
//
//       case '|': {
//         const plEntry = patternListStack[patternListStack.length - 1]
//         if (!plEntry) {
//           re += '\\|'
//           continue
//         }
//
//         clearStateChar()
//         re += '|'
//         // next subpattern can start with a dot?
//         if (plEntry.start === 0 && plEntry.type !== '!') {
//           dotTravAllowed = true
//           re += subPatternStart(pattern.slice(i + 1))
//         }
//         continue
//       }
//
//       // these are mostly the same in regexp and glob
//       case '[':
//         // swallow any state-tracking char before the [
//         clearStateChar()
//         const [src, needUflag, consumed, magic] = parseClass(pattern, i)
//         if (consumed) {
//           re += src
//           uflag = uflag || needUflag
//           i += consumed - 1
//           hasMagic = hasMagic || magic
//         } else {
//           re += '\\['
//         }
//         continue
//
//       case ']':
//         re += '\\' + c
//         continue
//
//       default:
//         // swallow any state char that wasn't consumed
//         clearStateChar()
//
//         re += regExpEscape(c)
//         break
//     } // switch
//   } // for
//
//   // handle the case where we had a +( thing at the *end*
//   // of the pattern.
//   // each pattern list stack adds 3 chars, and we need to go through
//   // and escape any | chars that were passed through as-is for the regexp.
//   // Go through and escape them, taking care not to double-escape any
//   // | chars that were already escaped.
//   for (pl = patternListStack.pop(); pl; pl = patternListStack.pop()) {
//     let tail: string
//     tail = re.slice(pl.reStart + pl.open.length)
//     debug(pattern, 'setting tail', re, pl)
//     // maybe some even number of \, then maybe 1 \, followed by a |
//     tail = tail.replace(/((?:\\{2}){0,64})(\\?)\|/g, (_, $1, $2) => {
//       if (!$2) {
//         // the | isn't already escaped, so escape it.
//         $2 = '\\'
//         // should already be done
//         /* c8 ignore start */
//       }
//       /* c8 ignore stop */
//
//       // need to escape all those slashes *again*, without escaping the
//       // one that we need for escaping the | character.  As it works out,
//       // escaping an even number of slashes can be done by simply repeating
//       // it exactly after itself.  That's why this trick works.
//       //
//       // I am sorry that you have to see this.
//       return $1 + $1 + $2 + '|'
//     })
//
//     debug('tail=%j\n   %s', tail, tail, pl, re)
//     const t = pl.type === '*' ? star : pl.type === '?' ? qmark : '\\' + pl.type
//
//     hasMagic = true
//     re = re.slice(0, pl.reStart) + t + '\\(' + tail
//   }
//
//   // handle trailing things that only matter at the very end.
//   clearStateChar()
//   if (escaping) {
//     // trailing \\
//     re += '\\\\'
//   }
//
//   // only need to apply the nodot start if the re starts with
//   // something that could conceivably capture a dot
//   const addPatternStart = addPatternStartSet[re.charAt(0)]
//
//   // Hack to work around lack of negative lookbehind in JS
//   // A pattern like: *.!(x).!(y|z) needs to ensure that a name
//   // like 'a.xyz.yz' doesn't match.  So, the first negative
//   // lookahead, has to look ALL the way ahead, to the end of
//   // the pattern.
//   for (let n = negativeLists.length - 1; n > -1; n--) {
//     const nl = negativeLists[n]
//
//     const nlBefore = re.slice(0, nl.reStart)
//     const nlFirst = re.slice(nl.reStart, nl.reEnd - 8)
//     let nlAfter = re.slice(nl.reEnd)
//     const nlLast = re.slice(nl.reEnd - 8, nl.reEnd) + nlAfter
//
//     // Handle nested stuff like *(*.js|!(*.json)), where open parens
//     // mean that we should *not* include the ) in the bit that is considered
//     // "after" the negated section.
//     const closeParensBefore = nlBefore.split(')').length
//     const openParensBefore = nlBefore.split('(').length - closeParensBefore
//     let cleanAfter = nlAfter
//     for (let i = 0; i < openParensBefore; i++) {
//       cleanAfter = cleanAfter.replace(/\)[+*?]?/, '')
//     }
//     nlAfter = cleanAfter
//
//     const dollar = nlAfter === '' ? '(?:$|\\/)' : ''
//
//     re = nlBefore + nlFirst + nlAfter + dollar + nlLast
//   }
//
//   // if the re is not "" at this point, then we need to make sure
//   // it doesn't match against an empty path part.
//   // Otherwise a/* will match a/, which it should not.
//   if (re !== '' && hasMagic) {
//     re = '(?=.)' + re
//   }
//
//   if (addPatternStart) {
//     re = patternStart() + re
//   }
//
//   // if it's nocase, and the lcase/uppercase don't match, it's magic
//   if (options.nocase && !hasMagic && !options.nocaseMagicOnly) {
//     hasMagic = pattern.toUpperCase() !== pattern.toLowerCase()
//   }
//
//   // skip the regexp for non-magical patterns
//   // unescape anything in it, though, so that it'll be
//   // an exact match against a file etc.
//   if (!hasMagic) {
//     return globUnescape(re)
//   }
//
//   return re
// }
//# sourceMappingURL=parse.js.map