aboutsummaryrefslogblamecommitdiffstats
path: root/internal/revision/parser.go
blob: b45a6d8d0291bbe38a4a8ef564bf4612258a0878 (plain) (tree)
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













































































































































































































































































































































































































































































































































































































































                                                                                                                                                                           
// Package revision extracts git revision from string
// More informations about revision : https://www.kernel.org/pub/software/scm/git/docs/gitrevisions.html
package revision

import (
	"bytes"
	"fmt"
	"io"
	"regexp"
	"strconv"
	"time"
)

// ErrInvalidRevision is emitted if string doesn't match valid revision
type ErrInvalidRevision struct {
	s string
}

func (e *ErrInvalidRevision) Error() string {
	return "Revision invalid : " + e.s
}

// Revisioner represents a revision component.
// A revision is made of multiple revision components
// obtained after parsing a revision string,
// for instance revision "master~" will be converted in
// two revision components Ref and TildePath
type Revisioner interface {
}

// Ref represents a reference name : HEAD, master
type Ref string

// TildePath represents ~, ~{n}
type TildePath struct {
	Depth int
}

// CaretPath represents ^, ^{n}
type CaretPath struct {
	Depth int
}

// CaretReg represents ^{/foo bar}
type CaretReg struct {
	Regexp *regexp.Regexp
	Negate bool
}

// CaretType represents ^{commit}
type CaretType struct {
	ObjectType string
}

// AtReflog represents @{n}
type AtReflog struct {
	Depth int
}

// AtCheckout represents @{-n}
type AtCheckout struct {
	Depth int
}

// AtUpstream represents @{upstream}, @{u}
type AtUpstream struct {
	BranchName string
}

// AtPush represents @{push}
type AtPush struct {
	BranchName string
}

// AtDate represents @{"2006-01-02T15:04:05Z"}
type AtDate struct {
	Date time.Time
}

// ColonReg represents :/foo bar
type ColonReg struct {
	Regexp *regexp.Regexp
	Negate bool
}

// ColonPath represents :./<path> :<path>
type ColonPath struct {
	Path string
}

// ColonStagePath represents :<n>:/<path>
type ColonStagePath struct {
	Path  string
	Stage int
}

// Parser represents a parser
// use to tokenize and transform to revisioner chunks
// a given string
type Parser struct {
	s                 *scanner
	currentParsedChar struct {
		tok token
		lit string
	}
	unreadLastChar bool
}

// NewParserFromString returns a new instance of parser from a string.
func NewParserFromString(s string) *Parser {
	return NewParser(bytes.NewBufferString(s))
}

// NewParser returns a new instance of parser.
func NewParser(r io.Reader) *Parser {
	return &Parser{s: newScanner(r)}
}

// scan returns the next token from the underlying scanner
// or the last scanned token if an unscan was requested
func (p *Parser) scan() (token, string, error) {
	if p.unreadLastChar {
		p.unreadLastChar = false
		return p.currentParsedChar.tok, p.currentParsedChar.lit, nil
	}

	tok, lit, err := p.s.scan()

	p.currentParsedChar.tok, p.currentParsedChar.lit = tok, lit

	return tok, lit, err
}

// unscan pushes the previously read token back onto the buffer.
func (p *Parser) unscan() { p.unreadLastChar = true }

// Parse explode a revision string into revisioner chunks
func (p *Parser) Parse() ([]Revisioner, error) {
	var rev Revisioner
	var revs []Revisioner
	var tok token
	var err error

	for {
		tok, _, err = p.scan()

		if err != nil {
			return nil, err
		}

		switch tok {
		case at:
			rev, err = p.parseAt()
		case tilde:
			rev, err = p.parseTilde()
		case caret:
			rev, err = p.parseCaret()
		case colon:
			rev, err = p.parseColon()
		case eof:
			err = p.validateFullRevision(&revs)

			if err != nil {
				return []Revisioner{}, err
			}

			return revs, nil
		default:
			p.unscan()
			rev, err = p.parseRef()
		}

		if err != nil {
			return []Revisioner{}, err
		}

		revs = append(revs, rev)
	}
}

// validateFullRevision ensures all revisioner chunks make a valid revision
func (p *Parser) validateFullRevision(chunks *[]Revisioner) error {
	var hasReference bool

	for i, chunk := range *chunks {
		switch chunk.(type) {
		case Ref:
			if i == 0 {
				hasReference = true
			} else {
				return &ErrInvalidRevision{`reference must be defined once at the beginning`}
			}
		case AtDate:
			if len(*chunks) == 1 || hasReference && len(*chunks) == 2 {
				return nil
			}

			return &ErrInvalidRevision{`"@" statement is not valid, could be : <refname>@{<ISO-8601 date>}, @{<ISO-8601 date>}`}
		case AtReflog:
			if len(*chunks) == 1 || hasReference && len(*chunks) == 2 {
				return nil
			}

			return &ErrInvalidRevision{`"@" statement is not valid, could be : <refname>@{<n>}, @{<n>}`}
		case AtCheckout:
			if len(*chunks) == 1 {
				return nil
			}

			return &ErrInvalidRevision{`"@" statement is not valid, could be : @{-<n>}`}
		case AtUpstream:
			if len(*chunks) == 1 || hasReference && len(*chunks) == 2 {
				return nil
			}

			return &ErrInvalidRevision{`"@" statement is not valid, could be : <refname>@{upstream}, @{upstream}, <refname>@{u}, @{u}`}
		case AtPush:
			if len(*chunks) == 1 || hasReference && len(*chunks) == 2 {
				return nil
			}

			return &ErrInvalidRevision{`"@" statement is not valid, could be : <refname>@{push}, @{push}`}
		case TildePath, CaretPath, CaretReg:
			if !hasReference {
				return &ErrInvalidRevision{`"~" or "^" statement must have a reference defined at the beginning`}
			}
		case ColonReg:
			if len(*chunks) == 1 {
				return nil
			}

			return &ErrInvalidRevision{`":" statement is not valid, could be : :/<regexp>`}
		case ColonPath:
			if i == len(*chunks)-1 && hasReference || len(*chunks) == 1 {
				return nil
			}

			return &ErrInvalidRevision{`":" statement is not valid, could be : <revision>:<path>`}
		case ColonStagePath:
			if len(*chunks) == 1 {
				return nil
			}

			return &ErrInvalidRevision{`":" statement is not valid, could be : :<n>:<path>`}
		}
	}

	return nil
}

// parseAt extract @ statements
func (p *Parser) parseAt() (Revisioner, error) {
	var tok, nextTok token
	var lit, nextLit string
	var err error

	tok, lit, err = p.scan()

	if err != nil {
		return nil, err
	}

	if tok != obrace {
		p.unscan()

		return Ref("HEAD"), nil
	}

	tok, lit, err = p.scan()

	if err != nil {
		return nil, err
	}

	nextTok, nextLit, err = p.scan()

	if err != nil {
		return nil, err
	}

	switch {
	case tok == word && (lit == "u" || lit == "upstream") && nextTok == cbrace:
		return AtUpstream{}, nil
	case tok == word && lit == "push" && nextTok == cbrace:
		return AtPush{}, nil
	case tok == number && nextTok == cbrace:
		n, _ := strconv.Atoi(lit)

		return AtReflog{n}, nil
	case tok == minus && nextTok == number:
		n, _ := strconv.Atoi(nextLit)

		t, _, err := p.scan()

		if err != nil {
			return nil, err
		}

		if t != cbrace {
			return nil, &ErrInvalidRevision{fmt.Sprintf(`missing "}" in @{-n} structure`)}
		}

		return AtCheckout{n}, nil
	default:
		p.unscan()

		date := lit

		for {
			tok, lit, err = p.scan()

			if err != nil {
				return nil, err
			}

			switch {
			case tok == cbrace:
				t, err := time.Parse("2006-01-02T15:04:05Z", date)

				if err != nil {
					return nil, &ErrInvalidRevision{fmt.Sprintf(`wrong date "%s" must fit ISO-8601 format : 2006-01-02T15:04:05Z`, date)}
				}

				return AtDate{t}, nil
			default:
				date += lit
			}
		}
	}
}

// parseTilde extract ~ statements
func (p *Parser) parseTilde() (Revisioner, error) {
	var tok token
	var lit string
	var err error

	tok, lit, err = p.scan()

	if err != nil {
		return nil, err
	}

	switch {
	case tok == number:
		n, _ := strconv.Atoi(lit)

		return TildePath{n}, nil
	default:
		p.unscan()
		return TildePath{1}, nil
	}
}

// parseCaret extract ^ statements
func (p *Parser) parseCaret() (Revisioner, error) {
	var tok token
	var lit string
	var err error

	tok, lit, err = p.scan()

	if err != nil {
		return nil, err
	}

	switch {
	case tok == obrace:
		r, err := p.parseCaretBraces()

		if err != nil {
			return nil, err
		}

		return r, nil
	case tok == number:
		n, _ := strconv.Atoi(lit)

		if n > 2 {
			return nil, &ErrInvalidRevision{fmt.Sprintf(`"%s" found must be 0, 1 or 2 after "^"`, lit)}
		}

		return CaretPath{n}, nil
	default:
		p.unscan()
		return CaretPath{1}, nil
	}
}

// parseCaretBraces extract ^{<data>} statements
func (p *Parser) parseCaretBraces() (Revisioner, error) {
	var tok, nextTok token
	var lit, _ string
	start := true
	var re string
	var negate bool
	var err error

	for {
		tok, lit, err = p.scan()

		if err != nil {
			return nil, err
		}

		nextTok, _, err = p.scan()

		if err != nil {
			return nil, err
		}

		switch {
		case tok == word && nextTok == cbrace && (lit == "commit" || lit == "tree" || lit == "blob" || lit == "tag" || lit == "object"):
			return CaretType{lit}, nil
		case re == "" && tok == cbrace:
			return CaretType{"tag"}, nil
		case re == "" && tok == emark && nextTok == emark:
			re += lit
		case re == "" && tok == emark && nextTok == minus:
			negate = true
		case re == "" && tok == emark:
			return nil, &ErrInvalidRevision{fmt.Sprintf(`revision suffix brace component sequences starting with "/!" others than those defined are reserved`)}
		case re == "" && tok == slash:
			p.unscan()
		case tok != slash && start:
			return nil, &ErrInvalidRevision{fmt.Sprintf(`"%s" is not a valid revision suffix brace component`, lit)}
		case tok != cbrace:
			p.unscan()
			re += lit
		case tok == cbrace:
			p.unscan()

			reg, err := regexp.Compile(re)

			if err != nil {
				return CaretReg{}, &ErrInvalidRevision{fmt.Sprintf(`revision suffix brace component, %s`, err.Error())}
			}

			return CaretReg{reg, negate}, nil
		}

		start = false
	}
}

// parseColon extract : statements
func (p *Parser) parseColon() (Revisioner, error) {
	var tok token
	var err error

	tok, _, err = p.scan()

	if err != nil {
		return nil, err
	}

	switch tok {
	case slash:
		return p.parseColonSlash()
	default:
		p.unscan()
		return p.parseColonDefault()
	}
}

// parseColonSlash extract :/<data> statements
func (p *Parser) parseColonSlash() (Revisioner, error) {
	var tok, nextTok token
	var lit string
	var re string
	var negate bool
	var err error

	for {
		tok, lit, err = p.scan()

		if err != nil {
			return nil, err
		}

		nextTok, _, err = p.scan()

		if err != nil {
			return nil, err
		}

		switch {
		case tok == emark && nextTok == emark:
			re += lit
		case re == "" && tok == emark && nextTok == minus:
			negate = true
		case re == "" && tok == emark:
			return nil, &ErrInvalidRevision{fmt.Sprintf(`revision suffix brace component sequences starting with "/!" others than those defined are reserved`)}
		case tok == eof:
			p.unscan()
			reg, err := regexp.Compile(re)

			if err != nil {
				return ColonReg{}, &ErrInvalidRevision{fmt.Sprintf(`revision suffix brace component, %s`, err.Error())}
			}

			return ColonReg{reg, negate}, nil
		default:
			p.unscan()
			re += lit
		}
	}
}

// parseColonDefault extract :<data> statements
func (p *Parser) parseColonDefault() (Revisioner, error) {
	var tok token
	var lit string
	var path string
	var stage int
	var err error
	var n = -1

	tok, lit, err = p.scan()

	if err != nil {
		return nil, err
	}

	nextTok, _, err := p.scan()

	if err != nil {
		return nil, err
	}

	if tok == number && nextTok == colon {
		n, _ = strconv.Atoi(lit)
	}

	switch n {
	case 0, 1, 2, 3:
		stage = n
	default:
		path += lit
		p.unscan()
	}

	for {
		tok, lit, err = p.scan()

		if err != nil {
			return nil, err
		}

		switch {
		case tok == eof && n == -1:
			return ColonPath{path}, nil
		case tok == eof:
			return ColonStagePath{path, stage}, nil
		default:
			path += lit
		}
	}
}

// parseRef extract reference name
func (p *Parser) parseRef() (Revisioner, error) {
	var tok, prevTok token
	var lit, buf string
	var endOfRef bool
	var err error

	for {
		tok, lit, err = p.scan()

		if err != nil {
			return nil, err
		}

		switch tok {
		case eof, at, colon, tilde, caret:
			endOfRef = true
		}

		err := p.checkRefFormat(tok, lit, prevTok, buf, endOfRef)

		if err != nil {
			return "", err
		}

		if endOfRef {
			p.unscan()
			return Ref(buf), nil
		}

		buf += lit
		prevTok = tok
	}
}

// checkRefFormat ensure reference name follow rules defined here :
// https://git-scm.com/docs/git-check-ref-format
func (p *Parser) checkRefFormat(token token, literal string, previousToken token, buffer string, endOfRef bool) error {
	switch token {
	case aslash, space, control, qmark, asterisk, obracket:
		return &ErrInvalidRevision{fmt.Sprintf(`must not contains "%s"`, literal)}
	}

	switch {
	case (token == dot || token == slash) && buffer == "":
		return &ErrInvalidRevision{fmt.Sprintf(`must not start with "%s"`, literal)}
	case previousToken == slash && endOfRef:
		return &ErrInvalidRevision{`must not end with "/"`}
	case previousToken == dot && endOfRef:
		return &ErrInvalidRevision{`must not end with "."`}
	case token == dot && previousToken == slash:
		return &ErrInvalidRevision{`must not contains "/."`}
	case previousToken == dot && token == dot:
		return &ErrInvalidRevision{`must not contains ".."`}
	case previousToken == slash && token == slash:
		return &ErrInvalidRevision{`must not contains consecutively "/"`}
	case (token == slash || endOfRef) && len(buffer) > 4 && buffer[len(buffer)-5:] == ".lock":
		return &ErrInvalidRevision{"cannot end with .lock"}
	}

	return nil
}