-
Notifications
You must be signed in to change notification settings - Fork 8
/
scanner.ts
1623 lines (1451 loc) · 43.2 KB
/
scanner.ts
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import { Pos, Position, SrcFile } from './pos'
import * as utf8 from './utf8'
import * as unicode from './unicode'
import { ErrorCode, ErrorReporter, ErrorHandler } from './error'
import { token, lookupKeyword, prec } from './token'
import * as path from './path'
import { Int64 } from './int64'
import { IntParser } from './intparse'
import {
AppendBuffer,
bufcmp,
asciibuf,
asciistr,
asciistrn,
// debuglog as dlog,
} from './util'
export enum Mode {
None = 0,
ScanComments = 1, // do not skip comments; produce token.COMMENT
CopySource = 2,
// copy slices of source data for tokens with literal values instead of
// referencing the source buffer. This means slightly lower speed but
// less memory usage since when scanning is done, the source code memory
// can be reclaimed. If you plan to keep the source code around after
// scanning (common case) you should leave this disabled.
}
const linePrefix = asciibuf('//!line ')
enum istrOne { OFF, WAIT, CONT }
const decodeRes :utf8.DecodeResult = {c:0,w:0}
// Snapshot represents a point between tokens and is
// just enough data to "time travel" a scanner within the same
// source file and scan session.
//
export interface Snapshot {
tok :token
ch :int
offset :int
rdOffset :int
lineOffset :int
insertSemi :bool
parenL :int
interpStrL :int
byteval :Uint8Array|null
errorCount :int
}
// A Scanner holds the scanner's internal state while processing a given text.
// It must be initialized via init before use or resue.
//
export class Scanner extends ErrorReporter {
// immutable state (only changed by init())
// Note: `undefined as any as X` is a workaround for a TypeScript issue
// where members are otherwise not initialized at construction which causes
// duplicate struct definitions in v8.
public sfile :SrcFile = undefined as any as SrcFile // source file handle
public sdata :Uint8Array = undefined as any as Uint8Array // source data
public dir :string = '' // directory portion of file.name
public mode :Mode = 0 // scanning mode
// scanning state
public ch :int = -1 // current character (unicode; -1=EOF)
public offset :int = 0 // character offset
public rdOffset :int = 0 // reading offset (position after current char)
private lineOffset :int = 0 // current line offset
private insertSemi :bool = false // insert a semicolon before next newline
private parenL :int = 0 // parenthesis level, for string interpolation
private interpStrL :int = 0 // string interpolation level
private istrOne :istrOne = istrOne.OFF // string interpolation
private byteval :Uint8Array|null = null // value for some string tokens
private intParser = new IntParser()
// public scanning state (read-only)
public pos :Pos = 0 // token start position
public startoffs :int = 0 // token start offset
public endoffs :int = 0 // token end offset
public tok :token = token.EOF
public prec :prec = prec.LOWEST
public hash :int = 0 // hash value for current token (if NAME*)
public int32val :int = 0 // value for some tokens (char and int lits)
public int64val :Int64|null = null // value for large int tokens
public floatval :number = +0.0 // IEEE 754-2008 float
// sparse buffer state (not reset by s.init)
private appendbuf :AppendBuffer|null = null // for string literals
private snapshotFreeList :Snapshot[] = []
// public state - ok to modify
public errorCount :int = 0 // number of errors encountered
constructor(traceInDebugMode? :bool) {
super('E_SYNTAX', null, traceInDebugMode)
}
// Init prepares the scanner s to tokenize the text sdata by setting the
// scanner at the beginning of sdata. The scanner uses the file set file
// for position information and it adds line information for each line.
// It is ok to re-use the same file when re-scanning the same file as
// line information which is already present is ignored. Init causes a
// panic if the file size does not match the sdata size.
//
// Calls to Scan will invoke the error handler errh if they encounter a
// syntax error and errh is not nil. Also, for each error encountered,
// the Scanner field ErrorCount is incremented by one. The mode parameter
// determines how comments are handled.
//
// Note that Init may call errh if there is an error in the first character
// of the file.
//
init(
sfile :SrcFile,
sdata :Uint8Array,
errh? :ErrorHandler|null,
mode :Mode = Mode.None,
) {
const s = this
// Explicitly initialize all fields since a scanner may be reused
if (sfile.size != sdata.length) {
panic(
`file size (${sfile.size}) `+
`does not match source size (${sdata.length})`
)
}
s.sfile = sfile
s.dir = path.dir(sfile.name)
s.sdata = sdata
s.errh = errh || null
s.mode = mode
// reset scanner state
s.tok = token.EOF
s.ch = 0x20 /*' '*/
s.offset = 0
s.rdOffset = 0
s.lineOffset = 0
s.insertSemi = false
s.parenL = 0
s.interpStrL = 0
s.byteval = null
s.errorCount = 0
s.readchar()
}
recordSnapshot(s :Snapshot) {
s.tok = this.tok
s.ch = this.ch
s.offset = this.offset
s.rdOffset = this.rdOffset
s.lineOffset = this.lineOffset
s.insertSemi = this.insertSemi
s.parenL = this.parenL
s.interpStrL = this.interpStrL
s.byteval = this.byteval
s.errorCount = this.errorCount
}
restoreSnapshot(s :Snapshot) {
this.tok = s.tok
this.ch = s.ch
this.offset = s.offset
this.rdOffset = s.rdOffset
this.lineOffset = s.lineOffset
this.insertSemi = s.insertSemi
this.parenL = s.parenL
this.interpStrL = s.interpStrL
this.byteval = s.byteval
this.errorCount = s.errorCount
}
allocSnapshot() :Snapshot {
let s = this.snapshotFreeList.pop()
if (!s) { s = {} as Snapshot }
return s
}
freeSnapshot(s :Snapshot) {
this.snapshotFreeList.push(s)
}
// setOffset sets the read offset.
// it's only safe to call this outside of next() and readchar()
//
setOffset(offs :int) {
const s = this
s.offset = s.rdOffset = offs
}
// setEOF sets the state to EOF, as if we had scanned until the end
setEOF() {
const s = this
s.setOffset(s.sdata.length)
s.ch = -1 // eof
s.tok = token.EOF
}
// Read the next Unicode char into s.ch.
// s.ch < 0 means end-of-file.
readchar() {
const s = this
if (s.rdOffset < s.sdata.length) {
s.offset = s.rdOffset
if (s.ch == 0xA /*\n*/ ) {
s.lineOffset = s.offset
s.sfile.addLine(s.offset)
}
decodeRes.w = 1
decodeRes.c = s.sdata[s.rdOffset]
if (decodeRes.c >= 0x80) {
// uncommon case: non-ASCII character
if (!utf8.decode(s.sdata, s.rdOffset, decodeRes)) {
s.errorAtOffs('invalid UTF-8 encoding', s.offset)
} else if (decodeRes.c == 0) {
s.errorAtOffs('illegal NUL byte in input', s.offset)
}
}
s.rdOffset += decodeRes.w
s.ch = decodeRes.c
} else {
s.offset = s.sdata.length
if (s.ch == 0xA /*\n*/) {
s.lineOffset = s.offset
s.sfile.addLine(s.offset)
}
s.ch = -1 // eof
}
}
// undobyte "puts back" the last-read byte.
// note that this does NOT fully update scanner state -- after calling this
// function, you should either call readchar() to update s.ch and s.offset
// or call next().
//
undobyte() {
const s = this
assert(s.ch < 0x80)
s.rdOffset -= 1
s.offset -= 1
s.endoffs = s.offset
}
// gotchar reads the next character and returns true if s.ch == ch
private gotchar(ch :int) :bool {
const s = this
if (s.ch == ch) {
s.readchar()
return true
}
return false
}
currentPosition() :Position {
const s = this
return s.sfile.position(s.pos)
}
// byteValue returns a byte buffer representing the literal value of the
// current token.
// Note that this method returns a byte buffer that is potentially referenced
// internally and which value might change next time s.scan is called. If you
// plan to keep referencing the byte buffer, use s.takeByteValue instead.
//
byteValue() :Uint8Array {
const s = this
const end = s.endoffs == -1 ? s.offset : s.endoffs
return s.byteval || s.sdata.subarray(s.startoffs, end)
}
// takeByteValue returns a new byte buffer that is not referenced by
// the scanner.
// If Mode.CopySource is set, a mutable copy is returned, otherwise an immutable
// view on the underlying source code is returned.
//
takeByteValue() :Uint8Array {
const s = this
const b = s.byteValue()
s.byteval = null
return (this.mode & Mode.CopySource) ? b.slice() : b
}
// stringValue returns a string of the literal value of the
// current token. This is mainly a convenience method; it
// decodes the underlying buffer as UTF-8.
stringValue() :string {
return utf8.decodeToString(this.byteValue())
}
// Increment errorCount and call any error handler
//
error(msg :string, pos :Pos = this.pos, code? :ErrorCode) {
const s = this
s.errorAt(msg, s.sfile.position(pos), code)
}
errorAtOffs(msg :string, offs :int, code? :ErrorCode) {
const s = this
s.errorAt(msg, s.sfile.position(s.sfile.pos(offs)), code)
}
// Scan the next token
//
next() {
while (true) {
const s = this
if (s.istrOne == istrOne.OFF) {
// skip whitespace
while (
s.ch == 0x20 ||
s.ch == 0x9 ||
(s.ch == 0xA && !s.insertSemi) ||
s.ch == 0xD
) {
s.readchar()
}
}
// current token start
s.pos = s.sfile.pos(s.offset)
s.startoffs = s.offset
s.endoffs = -1
s.byteval = null
if (s.istrOne == istrOne.CONT) {
// continue interpolated string
s.istrOne = istrOne.OFF
s.startoffs-- // b/c scanString increments it, assuming it's skipping `"`
s.tok = s.scanString()
s.insertSemi = s.tok != token.STRING_PIECE
return
} else if (s.istrOne == istrOne.WAIT) {
// we are about to scan a single token following $ in a string template
s.istrOne = istrOne.CONT
}
// make progress
let ch = s.ch
s.readchar()
let insertSemi = false
switch (ch) {
case -1: {
s.tok = s.insertSemi ? token.SEMICOLON : token.EOF
break
}
case 0x30: case 0x31: case 0x32: case 0x33: case 0x34:
case 0x35: case 0x36: case 0x37: case 0x38: case 0x39:
// 0..9
s.scanNumber(ch, /*modch=*/0)
insertSemi = true
break
case 0xA: { // \n
// we only reach here if s.insertSemi was set in the first place
// and exited early from skipping whitespace.
// newline consumed
s.tok = token.SEMICOLON
break
}
case 0x22: // "
s.tok = s.scanString()
insertSemi = s.tok != token.STRING_PIECE
break
case 0x27: // '
s.scanChar()
insertSemi = true
break
case 0x3a: // :
if (s.gotchar(0x3D)) {
s.tok = token.SET_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.COLON
}
break
case 0x2e: { // .
if (
isDigit(s.ch) &&
s.tok != token.NAME &&
s.tok != token.RPAREN &&
s.tok != token.RBRACKET
) {
// Note: We check for NAME so that:
// x.1 => (selector (name x) (int 1))
// ).1 => (selector (name x) (int 1))
// ].1 => (selector (name x) (int 1))
// .1 => (float 0.1)
s.scanFloatNumber(/*seenDecimal*/true, /*modc*/0)
insertSemi = true
} else {
if (s.gotchar(0x2e)) { // ..
if (s.gotchar(0x2e)) { // ...
s.tok = token.ELLIPSIS
} else {
s.tok = token.PERIODS
}
} else {
s.tok = token.DOT
}
}
break
}
case 0x40: { // @
s.startoffs++ // skip @
let c = s.ch
if (c < utf8.UniSelf && (asciiFeats[c] & langIdentStart)) {
s.readchar()
s.scanIdentifier(c)
} else if (c >= utf8.UniSelf && isUniIdentStart(c)) {
s.readchar()
s.scanIdentifierU(c, this.startoffs)
}
s.tok = token.NAMEAT
insertSemi = true
break
}
case 0x2C: // ,
s.tok = token.COMMA
break
case 0x3B: // ;
s.tok = token.SEMICOLON
break
case 0x28: // (
if (s.interpStrL) {
s.parenL++
}
s.tok = token.LPAREN
break
case 0x29: // )
s.tok = token.RPAREN
insertSemi = true
if (s.interpStrL) {
if (s.parenL == 0) {
// continue interpolated string
s.interpStrL--
s.tok = s.scanString()
insertSemi = s.tok != token.STRING_PIECE
} else {
s.parenL--
}
}
break
case 0x5b: // [
s.tok = token.LBRACKET
break
case 0x5d: // ]
s.tok = token.RBRACKET
insertSemi = true
break
case 0x7b: // {
s.tok = token.LBRACE
break
case 0x7d: // }
s.tok = token.RBRACE
insertSemi = true
break
case 0x3f: // ?
s.tok = token.QUESTION
insertSemi = true
break
case 0x2B: { // +
s.prec = prec.LOWEST
if (s.gotchar(0x3D)) { // +=
s.tok = token.ADD_ASSIGN
} else if (s.gotchar(ch)) { // ++
s.tok = token.INC
insertSemi = true
} else if (s.ch >= 0x30 && s.ch <= 0x39) { // 0..9
ch = s.ch
s.readchar()
s.scanNumber(ch, /*modch=*/0x2B)
insertSemi = true
} else if (s.gotchar(0x2e)) { // .
s.scanFloatNumber(/*seenDecimal*/true, /*modc=*/0x2B)
insertSemi = true
} else {
s.tok = token.ADD
s.prec = prec.ADD
}
break
}
case 0x2D: { // -
s.prec = prec.LOWEST
if (s.gotchar(0x3e)) { // ->
s.tok = token.ARROWR
} else if (s.gotchar(0x3D)) { // -=
s.tok = token.SUB_ASSIGN
} else if (s.gotchar(ch)) { // --
s.tok = token.DEC
insertSemi = true
} else if (s.ch >= 0x30 && s.ch <= 0x39) { // 0..9
ch = s.ch
s.readchar()
s.scanNumber(ch, /*modc=*/0x2D)
insertSemi = true
} else if (s.gotchar(0x2e)) { // .
s.scanFloatNumber(/*seenDecimal*/true, /*modc=*/0x2D)
insertSemi = true
} else {
s.tok = token.SUB
s.prec = prec.ADD
}
break
}
case 0x2a: // *
if (s.gotchar(0x3D)) { // *=
s.tok = token.MUL_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.MUL
s.prec = prec.MUL
}
break
case 0x2f: { // /
if (s.ch == 0x2f) { // //
s.scanLineComment()
if (!(s.mode & Mode.ScanComments)) {
continue
}
insertSemi = s.insertSemi // persist s.insertSemi
} else if (s.ch == 0x2a) { // /*
const CRcount = s.scanGeneralComment()
if (!(s.mode & Mode.ScanComments)) {
continue
}
s.tok = token.COMMENT
if (CRcount) {
// strip CR characters from comment
const v = s.sdata.subarray(
s.startoffs,
s.endoffs == -1 ? s.offset : s.endoffs
)
s.byteval = stripByte(v, 0xD, CRcount) // copy; no mutation
}
insertSemi = s.insertSemi // persist s.insertSemi
} else {
if (s.gotchar(0x3D)) { // /=
s.tok = token.QUO_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.QUO
s.prec = prec.MUL
}
}
break
}
case 0x25: // %
if (s.gotchar(0x3D)) { // %=
s.tok = token.REM_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.REM
s.prec = prec.MUL
}
break
case 0x5e: // ^
if (s.gotchar(0x3D)) { // ^=
s.tok = token.XOR_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.XOR
s.prec = prec.ADD
}
break
case 0x3c: { // <
if (s.gotchar(0x2D)) { // <-
s.tok = token.ARROWL
s.prec = prec.LOWEST
} else if (s.gotchar(0x3D)) { // <=
s.tok = token.LEQ
s.prec = prec.CMP
} else if (s.gotchar(ch)) { // <<
if (s.gotchar(0x3D)) { // <<=
s.tok = token.SHL_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.SHL
s.prec = prec.MUL
}
} else {
s.tok = token.LSS
s.prec = prec.CMP
}
break
}
case 0x3E: // >
if (s.gotchar(0x3D)) { // >=
s.tok = token.GEQ
s.prec = prec.CMP
} else if (s.gotchar(ch)) { // >>
if (s.gotchar(0x3D)) { // >>=
s.tok = token.SHR_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.SHR
s.prec = prec.MUL
insertSemi = true
}
} else {
s.tok = token.GTR
s.prec = prec.CMP
insertSemi = true
}
break
case 0x3D: // =
if (s.gotchar(0x3D)) { // ==
s.tok = token.EQL
s.prec = prec.CMP
} else {
s.tok = token.ASSIGN
s.prec = prec.LOWEST
}
break
case 0x21: // !
if (s.gotchar(0x3D)) { // !=
s.tok = token.NEQ
s.prec = prec.CMP
} else {
s.tok = token.NOT
s.prec = prec.LOWEST
}
break
case 0x26: { // &
if (s.gotchar(0x5E)) { // &^
if (s.gotchar(0x3D)) { // &^=
s.tok = token.AND_NOT_ASSIGN
s.prec = prec.LOWEST
} else {
s.tok = token.AND_NOT
s.prec = prec.MUL
}
} else if (s.gotchar(0x3D)) { // &=
s.tok = token.AND_ASSIGN
s.prec = prec.LOWEST
} else if (s.gotchar(ch)) { // &&
s.tok = token.ANDAND
s.prec = prec.ANDAND
} else {
s.tok = token.AND
s.prec = prec.MUL
}
break
}
case 0x7c: // |
if (s.gotchar(0x3D)) { // |=
s.tok = token.OR_ASSIGN
s.prec = prec.LOWEST
} else if (s.gotchar(ch)) { // ||
s.tok = token.OROR
s.prec = prec.OROR
} else {
s.tok = token.OR
s.prec = prec.ADD
}
break
case 0x23: { // #
s.startoffs++ // skip #
let c = s.ch
if (c < utf8.UniSelf && (asciiFeats[c] & langIdent)) {
s.readchar()
s.scanIdentifier(c)
}
s.tok = token.DIRECTIVE
insertSemi = true
break
}
default: {
if (
(ch < utf8.UniSelf && (asciiFeats[ch] & langIdentStart)) ||
(ch >= utf8.UniSelf && isUniIdentStart(ch))
) {
if (ch < utf8.UniSelf) {
s.scanIdentifier(ch)
} else {
s.scanIdentifierU(ch, this.startoffs)
}
if (s.offset - s.startoffs > 1) {
// shortest keyword is 2
switch (s.tok = lookupKeyword(s.byteValue())) {
case token.NAME:
case token.BREAK:
case token.CONTINUE:
case token.FALLTHROUGH:
case token.RETURN:
insertSemi = true
break
}
} else {
s.tok = token.NAME
insertSemi = true
}
} else {
s.error(`unexpected character ${unicode.repr(ch)} in input`)
s.tok = token.ILLEGAL
}
break
}
} // switch (ch)
if (s.endoffs == -1) {
s.endoffs = s.offset
}
s.insertSemi = insertSemi
// dlog(
// `-> ${tokstr(s.tok)} "${utf8.decodeToString(s.byteValue())}"`)
return
} // while(true)
}
scanIdentifierU(c :int, hashOffs :int, hash :int = 0x811c9dc5) {
// Scan identifier with non-ASCII characters.
// c is already verified to be a valid indentifier character.
// Hash is calculated as a second pass at the end.
const s = this
const ZeroWidthJoiner = 0x200D
let lastCp = c
c = s.ch
while (
isUniIdentCont(c) ||
unicode.isEmojiModifier(c) ||
unicode.isEmojiModifierBase(c) ||
c == ZeroWidthJoiner
) {
if (lastCp == 0x2D && c == 0x2D) { // --
s.undobyte() // "put back" the "-" byte
break
}
lastCp = c
s.readchar()
c = s.ch
}
if (lastCp == ZeroWidthJoiner) {
s.error(`illegal zero width-joiner character at end of identifer`)
s.tok = token.ILLEGAL
return
}
// computing rest of hash
for (let i = hashOffs; i < s.offset; ++i) {
hash = (hash ^ s.sdata[i]) * 0x1000193 // fnv1a
}
s.hash = hash >>> 0
}
scanIdentifier(c :int) {
// enters past first char; c = 1st char, s.ch = 2nd char
// c is already verified to be a valid indentifier character.
// The hash function used here must exactly match what's in bytestr.
const s = this
let hash = (0x811c9dc5 ^ c) * 0x1000193 // fnv1a
c = s.ch
while (
isLetter(c) ||
isDigit(c) ||
c == 0x2D || // -
c == 0x5F || // _
c == 0x24 // $
) {
s.readchar()
if (c == 0x2D && s.ch == 0x2D) { // --
s.undobyte() // "put back" the "-" byte
break
}
hash = (hash ^ c) * 0x1000193 // fnv1a
c = s.ch
}
if (c >= utf8.UniSelf && isUniIdentCont(c)) {
return s.scanIdentifierU(c, s.offset, hash)
}
s.hash = hash >>> 0
}
scanChar() {
const s = this
let cp = -1
s.tok = token.CHAR
s.int32val = NaN
switch (s.ch) {
case -1: // EOF
s.error("unterminated character literal")
s.tok = token.ILLEGAL
return
case 0x27: // '
s.error("empty character literal or unescaped ' in character literal")
s.readchar()
s.tok = token.ILLEGAL
return
case 0x5c: // \
s.readchar()
cp = s.scanEscape(0x27) // '
// note: cp is -1 for illegal escape sequences
break
default:
cp = s.ch
if (cp < 0x20) {
s.error("invalid character literal")
s.tok = token.ILLEGAL
cp = -1
}
s.readchar()
break
}
if (s.ch == 0x27) { // '
s.readchar()
if (cp == -1) {
s.tok = token.ILLEGAL
} else {
s.int32val = cp
}
} else {
// failed -- read until EOF or '
s.tok = token.ILLEGAL
while (true) {
if (s.ch == -1) {
break
}
if (s.ch == 0x27) { // '
s.readchar() // consume '
break
}
s.readchar()
}
s.error("invalid character literal")
}
}
resetAppendBuf() :AppendBuffer {
const s = this
if (s.appendbuf) {
s.appendbuf.reset()
} else {
// we need to buffer the value since it's not a 1:1 literal
s.appendbuf = new AppendBuffer(64)
}
return s.appendbuf
}
scanString() :token {
// opening char already consumed
const s = this
let buf :AppendBuffer|null = null
s.startoffs++ // skip initial "
let chunkStart = s.startoffs
let tok = token.STRING
loop1:
while (true) {
switch (s.ch) {
case -1:
s.error("string literal not terminated")
if (buf) {
buf = null
}
break loop1
case 0x22: // "
if (buf) {
buf.write(s.sdata, chunkStart, s.offset)
}
s.readchar()
break loop1
case 0x5c: { // \
// we need to buffer the value since it's not a 1:1 literal
if (!buf) {
buf = s.resetAppendBuf()
}
if (chunkStart != s.offset) {
buf.write(s.sdata, chunkStart, s.offset)
}
s.readchar()
const ch = s.ch as int // e.g. "u", "x", etc
const n = s.scanEscape(0x22) // "
// we continue even if there was an error
if (n >= 0) {
if (n >= utf8.UniSelf && (ch == 0x75 || ch == 0x55)) { // u | U
// Write unicode code point as UTF8 to value buffer
if (0xD800 <= n && n <= 0xE000) {
s.error("illegal: surrogate half in string literal")
} else if (n > unicode.MaxRune) {
s.error("escape sequence is invalid Unicode code point")
}
buf.reserve(utf8.UTFMax)
buf.length += utf8.encode(buf.buffer, buf.length, n)
} else {
buf.writeByte(n)
}
}
chunkStart = s.offset
break
}
case 0x24: { // $
s.readchar()
// start interpolated string
if (buf) {
s.byteval = buf.bytes()
}
if (s.gotchar(0x28)) { // (
// don't close until we see a balanced closing ')'
s.interpStrL++
s.endoffs = s.offset - 2 // exclude `$(`
} else if (s.ch as int == 0x22) { // "
// "foo $"bar"" is invalid -- hard to read, hard to parse.
// ("foo $("bar")" _is_ valid however.)
s.error(
"invalid \" in string template — string literals inside string " +
"templates need to be enclosed in parenthesis"
)
break // consume
} else {
// expect a single token to follow
s.endoffs = s.offset - 1 // exclude `$`
s.istrOne = istrOne.WAIT
}
return token.STRING_PIECE
}
case 0xA: // \n
tok = token.STRING_MULTI
s.readchar()
break
default:
s.readchar()
}
}
if (buf) {
s.byteval = buf.bytes()
} else {
s.endoffs = s.offset - 1
}
return tok
}
// scanEscape parses an escape sequence where `quote` is the accepted