generated from altid/template
-
-
Notifications
You must be signed in to change notification settings - Fork 1
/
lexer.go
741 lines (623 loc) · 11.3 KB
/
lexer.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
package markup
import (
"bytes"
"fmt"
"strings"
"unicode/utf8"
)
// The various types of text tokens
const (
NormalText byte = iota
ColorCode
ColorText
ColorTextBold
ColorTextStrong
ColorTextStrike
ColorTextEmphasis
URLLink
URLText
ImagePath
ImageText
ImageLink
BoldText
StrikeText
EmphasisText
StrongText
ErrorText
EOF
)
var escapable = "\\!#([])*_~`"
type stateFn func(*Lexer) stateFn
// Lexer allows tokenizing of altid-flavored markdown for client-side parsers
type Lexer struct {
src []byte
start int
width int
pos int
items chan Item
state stateFn
}
// NewLexer takes in a byte array and returns a ready to run Lexer
func NewLexer(src []byte) *Lexer {
return &Lexer{
src: src,
items: make(chan Item, 24),
state: lexText,
}
}
// NewStringLexer takes in a string and returns a ready to run Lexer
func NewStringLexer(src string) *Lexer {
return &Lexer{
src: []byte(src),
items: make(chan Item, 24),
state: lexText,
}
}
// Bytes wil return a parsed byte array from the input with markdown elements cleaned
// Any URL will be turned from `[some text](someurl)` to `some text (some url)`
// IMG will be turned from `![some text](someimage)` to `some text (some image)`
// color tags will be removed and the raw text will be output
func (l *Lexer) Bytes() ([]byte, error) {
var dst bytes.Buffer
for {
i := l.Next()
switch i.ItemType {
case ErrorText:
return nil, fmt.Errorf("%s", i.Data)
case EOF:
return dst.Bytes(), nil
case ColorCode, ImagePath:
continue
case URLLink, ImageLink:
dst.WriteString(" (")
dst.Write(i.Data)
dst.WriteString(") ")
default:
dst.Write(i.Data)
}
}
}
// String is the same as Bytes, but returns a string
func (l *Lexer) String() (string, error) {
b, err := l.Bytes()
if err != nil {
return "", err
}
return string(b), nil
}
// Item is returned from a call to Next()
// ItemType will be an ItemType
type Item struct {
ItemType byte
Data []byte
}
// Next returns the next Item from the tokenizer
// If ItemType is EOF, any subsequent calls to Next() will panic
func (l *Lexer) Next() Item {
for {
select {
case item := <-l.items:
return item
default:
l.state = l.state(l)
}
}
}
func (l *Lexer) nextChar() byte {
if l.pos >= len(l.src) {
l.width = 0
return EOF
}
rune, width := utf8.DecodeRune(l.src[l.pos:])
l.width = width
l.pos += l.width
return byte(rune)
}
func lexText(l *Lexer) stateFn {
for {
// pre-emptively emit our normal type here on any potential match
switch l.peek() {
case '\\', '%', '[', '!', '*', '~', '_':
l.emit(NormalText)
}
switch l.nextChar() {
case EOF:
l.emit(NormalText)
l.emit(EOF)
return nil
case '\\':
l.escape()
case '~':
l.accept("~")
l.ignore()
return lexStrike
case '_':
l.accept("_")
l.ignore()
return lexEmphasis
case '%':
return lexMaybeColor
case '[':
return lexMaybeURL
case '!':
return lexMaybeImage
case '*':
return lexMaybeBold
}
}
}
func lexStrike(l *Lexer) stateFn {
for {
// Fire off Strike on match
switch l.peek() {
case '~', '\\':
l.emit(StrikeText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: no closing stikeout tag")
return nil
case '\\':
l.escape()
case '~':
l.accept("~")
l.ignore()
return lexText
}
}
}
func lexEmphasis(l *Lexer) stateFn {
for {
switch l.peek() {
case '_', '\\', '*':
l.emit(EmphasisText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: no closing emphasis tag")
return nil
case '\\':
l.escape()
case '_', '*':
l.accept("_*")
l.ignore()
return lexText
}
}
}
// See if we're at ** or not
func lexMaybeBold(l *Lexer) stateFn {
l.ignore()
switch l.nextChar() {
case EOF:
l.error("found no closing tag for '*'")
return nil
case '*':
l.accept("*")
l.ignore()
return lexBold
default:
return lexEmphasis
}
}
func lexBold(l *Lexer) stateFn {
for {
switch l.peek() {
case '_', '\\', '*':
l.emit(BoldText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: no closing bold tag")
return nil
case '_':
l.accept("_")
l.ignore()
return lexStrong
case '\\':
l.escape()
case '*':
l.ignore()
// There could be malformed input here with no closing, `**hello world* how are you`
if l.peek() != '*' {
l.error("unexpected single '*' inside bold token")
return nil
}
l.accept("*")
l.ignore()
return lexText
}
}
}
func lexStrong(l *Lexer) stateFn {
for {
switch l.peek() {
case '_', '\\':
l.emit(StrongText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: no closing strong tag")
return nil
case '\\':
l.escape()
case '_':
l.accept("_")
l.ignore()
// Exit bold tag as well if we are at the end
if bytes.HasPrefix(l.src[l.start:], []byte("**")) {
l.accept("*")
l.accept("*")
l.ignore()
return lexText
}
return lexBold
}
}
}
func lexMaybeColor(l *Lexer) stateFn {
switch l.nextChar() {
case EOF:
// Benign, just send what we have and EOF
l.emit(NormalText)
l.emit(EOF)
return nil
case '[':
l.accept("[")
l.ignore()
return lexColorText
default:
return lexText
}
}
func lexColorText(l *Lexer) stateFn {
for {
switch l.peek() {
case ']', '*', '_', '~', '\\':
l.emit(ColorText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: no closing color tag")
return nil
case ']':
l.accept("]")
l.ignore()
return lexColorCode
case '*':
l.accept("*")
l.ignore()
return lexColorMaybeBold
case '_':
l.accept("_")
l.ignore()
return lexColorEmphasis
case '~':
l.accept("~")
l.ignore()
return lexColorStrikeout
case '\\': // eat a single slash
l.escape()
}
}
}
func lexColorStrikeout(l *Lexer) stateFn {
for {
switch l.peek() {
case '~', '\\':
l.emit(ColorTextStrike)
}
switch l.nextChar() {
case EOF, ']':
l.error("incorrect input: no closing strikeout tag")
return nil
case '\\':
l.escape()
case '~':
l.accept("~")
l.ignore()
return lexColorText
}
}
}
func lexColorEmphasis(l *Lexer) stateFn {
for {
switch l.peek() {
case '_', '*', '\\':
l.emit(ColorTextEmphasis)
}
switch l.nextChar() {
case EOF, ']':
l.error("incorrect input: no closing emphasis tag")
return nil
case '\\':
l.escape()
case '_':
l.accept("_")
l.ignore()
return lexColorText
case '*':
l.accept("*")
l.ignore()
return lexColorText
}
}
}
func lexColorStrong(l *Lexer) stateFn {
for {
switch l.peek() {
case '_', '\\':
l.emit(ColorTextStrong)
}
switch l.nextChar() {
case EOF, ']':
l.error("could not parse: no closing strong tag")
return nil
case '\\':
l.escape()
case '_':
l.accept("_")
l.ignore()
// Exit bold tag as well if we are at the end
if bytes.HasPrefix(l.src[l.start:], []byte("**")) {
l.accept("*")
l.accept("*")
l.ignore()
return lexColorText
}
return lexColorBold
}
}
}
func lexColorMaybeBold(l *Lexer) stateFn {
l.ignore()
switch l.nextChar() {
case EOF, ']':
l.error("found no closing tag for '*'")
return nil
case '*':
l.accept("*")
l.ignore()
return lexColorBold
default:
return lexColorEmphasis
}
}
func lexColorBold(l *Lexer) stateFn {
for {
switch l.peek() {
case '*', '\\', '_':
l.emit(ColorTextBold)
}
switch l.nextChar() {
case EOF, ']':
l.error("incorrect input: no closing bold tag")
return nil
case '_':
l.accept("_")
l.ignore()
return lexColorStrong
case '\\':
l.escape()
case '*':
l.ignore()
// There could be malformed input here with no closing tag
if l.peek() != '*' {
l.error("unexpected single '*' inside bold token")
return nil
}
l.accept("*")
l.ignore()
return lexColorText
}
}
}
func lexColorCode(l *Lexer) stateFn {
l.accept("]")
l.accept("(")
l.ignore()
// Hex code
if l.peek() == '#' {
l.accept("#")
l.acceptRun("1234567890,")
}
l.acceptRun("abcdefghijklmnopqrstuvwxyz,")
if l.peek() != ')' {
// Give a reasonably good error
err := fmt.Sprintf("unsupported color tag %s", l.src[l.start:l.pos])
l.error(err)
return nil
}
l.emit(ColorCode)
l.accept(")")
l.ignore()
return lexText
}
func lexMaybeURL(l *Lexer) stateFn {
l.ignore()
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed URL")
return nil
case '!':
return lexImageLinkText
default:
return lexURLText
}
}
func lexURLText(l *Lexer) stateFn {
for {
if l.peek() == ']' {
l.emit(URLText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed URL")
return nil
case ']':
return lexURLLink
}
}
}
func lexURLLink(l *Lexer) stateFn {
l.acceptRun("](")
l.ignore()
for {
if l.peek() == ')' {
l.emit(URLLink)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malfored URL")
return nil
case ')':
l.accept(")")
l.ignore()
return lexText
}
}
}
// [![alt text](/path/to/image)](link)
func lexImageLinkText(l *Lexer) stateFn {
l.acceptRun("[!")
l.ignore()
for {
if l.peek() == ']' {
l.emit(ImageText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed image tag")
return nil
case ']':
return lexImageLinkPath
}
}
}
func lexImageLinkPath(l *Lexer) stateFn {
l.acceptRun("](")
l.ignore()
for {
if l.peek() == ')' {
l.emit(ImagePath)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed image tag")
return nil
case ')':
return lexImageLink
}
}
}
func lexImageLink(l *Lexer) stateFn {
l.acceptRun(")](")
l.ignore()
for {
if l.peek() == ')' {
l.emit(ImageLink)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed image tag")
return nil
case ')':
l.accept(")")
l.ignore()
return lexText
}
}
}
func lexMaybeImage(l *Lexer) stateFn {
switch l.nextChar() {
case EOF:
l.emit(EOF)
return nil
case '[':
return lexImageText
default:
return lexText
}
}
func lexImageText(l *Lexer) stateFn {
l.accept("[")
l.ignore()
for {
if l.peek() == ']' {
l.emit(ImageText)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed image tag")
return nil
case ']':
return lexImagePath
}
}
}
func lexImagePath(l *Lexer) stateFn {
l.acceptRun("](")
l.ignore()
for {
if l.peek() == ')' {
l.emit(ImagePath)
}
switch l.nextChar() {
case EOF:
l.error("incorrect input: malformed image tag")
return nil
case ')':
l.accept(")")
l.ignore()
return lexText
}
}
}
func (l *Lexer) emit(t byte) {
// Short circuit null writes
if l.pos <= l.start && t != EOF {
return
}
l.items <- Item{
t,
l.src[l.start:l.pos],
}
l.start = l.pos
}
func (l *Lexer) ignore() {
l.start = l.pos
}
func (l *Lexer) backup() {
l.pos -= l.width
}
func (l *Lexer) peek() byte {
rune := l.nextChar()
l.backup()
return rune
}
func (l *Lexer) accept(valid string) bool {
if strings.IndexByte(valid, l.nextChar()) >= 0 {
return true
}
l.backup()
return false
}
func (l *Lexer) acceptRun(valid string) {
for {
if strings.IndexByte(valid, l.nextChar()) < 0 {
l.backup()
return
}
}
}
func (l *Lexer) escape() {
l.accept("\\")
l.ignore()
l.accept(escapable)
}
func (l *Lexer) error(err string) {
l.src = []byte(err)
l.start = 0
l.pos = len(l.src)
l.emit(ErrorText)
}