-
Notifications
You must be signed in to change notification settings - Fork 283
/
scanner.go
952 lines (881 loc) · 22.2 KB
/
scanner.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
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
// Copyright 2018 The CUE Authors
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
// Package scanner implements a scanner for CUE source text. It takes a []byte
// as source which can then be tokenized through repeated calls to the Scan
// method.
package scanner // import "cuelang.org/go/cue/scanner"
import (
"bytes"
"fmt"
"path/filepath"
"strconv"
"unicode"
"unicode/utf8"
"cuelang.org/go/cue/token"
)
// An ErrorHandler is a generic error handler used throughout CUE packages.
//
// The position points to the beginning of the offending value.
type ErrorHandler func(pos token.Pos, msg string, args []interface{})
// A Scanner holds the Scanner's internal state while processing
// a given text. It can be allocated as part of another data
// structure but must be initialized via Init before use.
type Scanner struct {
// immutable state
file *token.File // source file handle
dir string // directory portion of file.Name()
src []byte // source
errh ErrorHandler // error reporting; or nil
mode Mode // scanning mode
// scanning state
ch rune // current character
offset int // character offset
rdOffset int // reading offset (position after current character)
lineOffset int // current line offset
linesSinceLast int
spacesSinceLast int
insertEOL bool // insert a comma before next newline
quoteStack []quoteInfo
// public state - ok to modify
ErrorCount int // number of errors encountered
}
type quoteInfo struct {
char rune
numChar int
numHash int
}
const bom = 0xFEFF // byte order mark, only permitted as very first character
// Read the next Unicode char into s.ch.
// s.ch < 0 means end-of-file.
func (s *Scanner) next() {
if s.rdOffset < len(s.src) {
s.offset = s.rdOffset
if s.ch == '\n' {
s.lineOffset = s.offset
s.file.AddLine(s.offset)
}
r, w := rune(s.src[s.rdOffset]), 1
switch {
case r == 0:
s.errf(s.offset, "illegal character NUL")
case r >= utf8.RuneSelf:
// not ASCII
r, w = utf8.DecodeRune(s.src[s.rdOffset:])
if r == utf8.RuneError && w == 1 {
s.errf(s.offset, "illegal UTF-8 encoding")
} else if r == bom && s.offset > 0 {
s.errf(s.offset, "illegal byte order mark")
}
}
s.rdOffset += w
s.ch = r
} else {
s.offset = len(s.src)
if s.ch == '\n' {
s.lineOffset = s.offset
s.file.AddLine(s.offset)
}
s.ch = -1 // eof
}
}
// A Mode value is a set of flags (or 0).
// They control scanner behavior.
type Mode uint
// These constants are options to the Init function.
const (
ScanComments Mode = 1 << iota // return comments as COMMENT tokens
DontInsertCommas // do not automatically insert commas
)
// Init prepares the scanner s to tokenize the text src by setting the
// scanner at the beginning of src. 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 src size.
//
// Calls to Scan will invoke the error handler err if they encounter a
// syntax error and err 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 err if there is an error in the first character
// of the file.
func (s *Scanner) Init(file *token.File, src []byte, eh ErrorHandler, mode Mode) {
// Explicitly initialize all fields since a scanner may be reused.
if file.Size() != len(src) {
panic(fmt.Sprintf("file size (%d) does not match src len (%d)", file.Size(), len(src)))
}
s.file = file
s.dir, _ = filepath.Split(file.Name())
s.src = src
s.errh = eh
s.mode = mode
s.ch = ' '
s.offset = 0
s.rdOffset = 0
s.lineOffset = 0
s.insertEOL = false
s.ErrorCount = 0
s.next()
if s.ch == bom {
s.next() // ignore BOM at file beginning
}
}
func (s *Scanner) errf(offs int, msg string, args ...interface{}) {
if s.errh != nil {
s.errh(s.file.Pos(offs, 0), msg, args)
}
s.ErrorCount++
}
var prefix = []byte("//line ")
func (s *Scanner) interpretLineComment(text []byte) {
if bytes.HasPrefix(text, prefix) {
// get filename and line number, if any
if i := bytes.LastIndex(text, []byte{':'}); i > 0 {
if line, err := strconv.Atoi(string(text[i+1:])); err == nil && line > 0 {
// valid //line filename:line comment
filename := string(bytes.TrimSpace(text[len(prefix):i]))
if filename != "" {
filename = filepath.Clean(filename)
if !filepath.IsAbs(filename) {
// make filename relative to current directory
filename = filepath.Join(s.dir, filename)
}
}
// update scanner position
s.file.AddLineInfo(s.lineOffset+len(text)+1, filename, line) // +len(text)+1 since comment applies to next line
}
}
}
}
func (s *Scanner) scanComment() string {
// initial '/' already consumed; s.ch == '/'
offs := s.offset - 1 // position of initial '/'
hasCR := false
if s.ch == '/' {
//-style comment
s.next()
for s.ch != '\n' && s.ch >= 0 {
if s.ch == '\r' {
hasCR = true
}
s.next()
}
if offs == s.lineOffset {
// comment starts at the beginning of the current line
s.interpretLineComment(s.src[offs:s.offset])
}
goto exit
}
s.errf(offs, "comment not terminated")
exit:
lit := s.src[offs:s.offset]
if hasCR {
// TODO: preserve /r/n
lit = stripCR(lit)
}
return string(lit)
}
func isLetter(ch rune) bool {
return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch >= utf8.RuneSelf && unicode.IsLetter(ch)
}
func isDigit(ch rune) bool {
// TODO(mpvl): Is this correct?
return '0' <= ch && ch <= '9' || ch >= utf8.RuneSelf && unicode.IsDigit(ch)
}
func (s *Scanner) scanFieldIdentifier() string {
offs := s.offset
if s.ch == '_' {
s.next()
}
if s.ch == '#' {
s.next()
// TODO: remove this block to allow #<num>
if isDigit(s.ch) {
return string(s.src[offs:s.offset])
}
}
for isLetter(s.ch) || isDigit(s.ch) || s.ch == '_' || s.ch == '$' {
s.next()
}
return string(s.src[offs:s.offset])
}
func (s *Scanner) scanIdentifier() string {
offs := s.offset
for isLetter(s.ch) || isDigit(s.ch) || s.ch == '_' || s.ch == '$' {
s.next()
}
return string(s.src[offs:s.offset])
}
func digitVal(ch rune) int {
switch {
case '0' <= ch && ch <= '9':
return int(ch - '0')
case ch == '_':
return 0
case 'a' <= ch && ch <= 'f':
return int(ch - 'a' + 10)
case 'A' <= ch && ch <= 'F':
return int(ch - 'A' + 10)
}
return 16 // larger than any legal digit val
}
func (s *Scanner) scanMantissa(base int) {
var last rune
for digitVal(s.ch) < base {
if last == '_' && s.ch == '_' {
s.errf(s.offset, "illegal '_' in number")
}
last = s.ch
s.next()
}
if last == '_' {
s.errf(s.offset-1, "illegal '_' in number")
}
}
func (s *Scanner) scanNumber(seenDecimalPoint bool) (token.Token, string) {
// digitVal(s.ch) < 10
offs := s.offset
tok := token.INT
if seenDecimalPoint {
offs--
tok = token.FLOAT
s.scanMantissa(10)
goto exponent
}
if s.ch == '0' {
// int or float
offs := s.offset
s.next()
if s.ch == 'x' || s.ch == 'X' {
// hexadecimal int
s.next()
s.scanMantissa(16)
if s.offset-offs <= 2 {
// only scanned "0x" or "0X"
s.errf(offs, "illegal hexadecimal number")
}
} else if s.ch == 'b' {
// binary int
s.next()
s.scanMantissa(2)
if s.offset-offs <= 2 {
// only scanned "0b"
s.errf(offs, "illegal binary number")
}
} else if s.ch == 'o' {
// octal int
s.next()
s.scanMantissa(8)
if s.offset-offs <= 2 {
// only scanned "0o"
s.errf(offs, "illegal octal number")
}
} else {
// 0 or float
seenDigits := false
if s.ch >= '0' && s.ch <= '9' {
seenDigits = true
s.scanMantissa(10)
}
if s.ch == '.' || s.ch == 'e' || s.ch == 'E' {
goto fraction
}
if seenDigits {
// integer other than 0 may not start with 0
s.errf(offs, "illegal integer number")
}
}
goto exit
}
// decimal int or float
s.scanMantissa(10)
// TODO: allow 3h4s, etc.
// switch s.ch {
// case 'h', 'm', 's', "µ"[0], 'u', 'n':
// }
fraction:
if s.ch == '.' {
if p := s.offset + 1; p < len(s.src) && s.src[p] == '.' {
// interpret dot as part of a range.
goto exit
}
tok = token.FLOAT
s.next()
s.scanMantissa(10)
}
exponent:
switch s.ch {
case 'K', 'M', 'G', 'T', 'P':
tok = token.INT // TODO: Or should we allow this to be a float?
s.next()
if s.ch == 'i' {
s.next()
}
goto exit
}
if s.ch == 'e' || s.ch == 'E' {
tok = token.FLOAT
s.next()
if s.ch == '-' || s.ch == '+' {
s.next()
}
s.scanMantissa(10)
}
exit:
return tok, string(s.src[offs:s.offset])
}
// scanEscape parses an escape sequence where rune is the accepted
// escaped quote. In case of a syntax error, it stops at the offending
// character (without consuming it) and returns false. Otherwise
// it returns true.
//
// Must be compliant with https://tools.ietf.org/html/rfc4627.
func (s *Scanner) scanEscape(quote quoteInfo) (ok, interpolation bool) {
for i := 0; i < quote.numHash; i++ {
if s.ch != '#' {
return true, false
}
s.next()
}
offs := s.offset
var n int
var base, max uint32
switch s.ch {
case '(':
return true, true
case 'a', 'b', 'f', 'n', 'r', 't', 'v', '\\', '/', quote.char:
s.next()
return true, false
case '0', '1', '2', '3', '4', '5', '6', '7':
n, base, max = 3, 8, 255
case 'x':
s.next()
n, base, max = 2, 16, 255
case 'u':
s.next()
n, base, max = 4, 16, unicode.MaxRune
case 'U':
s.next()
n, base, max = 8, 16, unicode.MaxRune
default:
msg := "unknown escape sequence"
if s.ch < 0 {
msg = "escape sequence not terminated"
}
s.errf(offs, msg)
return false, false
}
var x uint32
for n > 0 {
d := uint32(digitVal(s.ch))
if d >= base {
if s.ch < 0 {
s.errf(s.offset, "escape sequence not terminated")
} else {
s.errf(s.offset, "illegal character %#U in escape sequence", s.ch)
}
return false, false
}
x = x*base + d
s.next()
n--
}
// TODO: this is valid JSON, so remove, but normalize and report an error
// if for unmatched surrogate pairs .
if x > max {
s.errf(offs, "escape sequence is invalid Unicode code point")
return false, false
}
return true, false
}
func (s *Scanner) scanString(offs int, quote quoteInfo) (token.Token, string) {
// ", """, ', or ''' opening already consumed
tok := token.STRING
hasCR := false
extra := 0
for {
ch := s.ch
if (quote.numChar != 3 && ch == '\n') || ch < 0 {
s.errf(offs, "string literal not terminated")
lit := s.src[offs:s.offset]
if hasCR {
lit = stripCR(lit)
}
return tok, string(lit)
}
s.next()
ch, ok := s.consumeStringClose(ch, quote)
if ok {
break
}
if ch == '\r' && quote.numChar == 3 {
hasCR = true
}
if ch == '\\' {
if _, interpolation := s.scanEscape(quote); interpolation {
tok = token.INTERPOLATION
extra = 1
s.quoteStack = append(s.quoteStack, quote)
break
}
}
}
lit := s.src[offs : s.offset+extra]
if hasCR {
lit = stripCR(lit)
}
return tok, string(lit)
}
func (s *Scanner) consumeQuotes(quote rune, max int) (next rune, n int) {
for ; n < max; n++ {
if s.ch != quote {
return s.ch, n
}
s.next()
}
return s.ch, n
}
func (s *Scanner) consumeStringClose(ch rune, quote quoteInfo) (next rune, atEnd bool) {
if quote.char != ch {
return ch, false
}
numChar := quote.numChar
n := numChar + quote.numHash
want := quote.char
for i := 1; i < n; i++ {
if i == numChar {
want = '#'
}
if want != s.ch {
return ch, false
}
ch = s.ch
s.next()
}
return s.ch, true
}
func (s *Scanner) scanHashes(maxHash int) int {
for i := 0; i < maxHash; i++ {
if s.ch != '#' {
return i
}
s.next()
}
return maxHash
}
func stripCR(b []byte) []byte {
c := make([]byte, len(b))
i := 0
for _, ch := range b {
if ch != '\r' {
c[i] = ch
i++
}
}
return c[:i]
}
// scanAttribute scans aa full attribute of the form @foo(str). An attribute
// is a lexical entry and as such whitespace is treated as normal characters
// within the attribute.
func (s *Scanner) scanAttribute() (tok token.Token, lit string) {
offs := s.offset - 1 // @ already consumed
s.scanIdentifier()
if _, tok, _ := s.Scan(); tok == token.LPAREN {
s.scanAttributeTokens(token.RPAREN)
} else {
s.errf(s.offset, "invalid attribute: expected '('")
}
return token.ATTRIBUTE, string(s.src[offs:s.offset])
}
func (s *Scanner) scanAttributeTokens(close token.Token) {
for {
switch _, tok, _ := s.Scan(); tok {
case close:
return
case token.EOF:
s.errf(s.offset, "attribute missing '%s'", close)
return
case token.INTERPOLATION:
s.errf(s.offset, "interpolation not allowed in attribute")
s.popInterpolation()
s.recoverParen(1)
case token.LPAREN:
s.scanAttributeTokens(token.RPAREN)
case token.LBRACE:
s.scanAttributeTokens(token.RBRACE)
case token.LBRACK:
s.scanAttributeTokens(token.RBRACK)
case token.RPAREN, token.RBRACK, token.RBRACE:
s.errf(s.offset, "unexpected '%s'", tok)
}
}
}
// recoverParen is an approximate recovery mechanism to recover from invalid
// attributes.
func (s *Scanner) recoverParen(open int) {
for {
switch s.ch {
case '\n', -1:
return
case '(':
open++
case ')':
if open--; open == 0 {
return
}
}
s.next()
}
}
func (s *Scanner) skipWhitespace(inc int) {
for {
switch s.ch {
case ' ', '\t':
s.spacesSinceLast += inc
case '\n':
s.linesSinceLast += inc
if s.insertEOL {
return
}
case '\r':
default:
return
}
s.next()
}
}
// Helper functions for scanning multi-byte tokens such as >> += >>= .
// Different routines recognize different length tok_i based on matches
// of ch_i. If a token ends in '=', the result is tok1 or tok3
// respectively. Otherwise, the result is tok0 if there was no other
// matching character, or tok2 if the matching character was ch2.
func (s *Scanner) switch2(tok0, tok1 token.Token) token.Token {
if s.ch == '=' {
s.next()
return tok1
}
return tok0
}
func (s *Scanner) popInterpolation() quoteInfo {
quote := s.quoteStack[len(s.quoteStack)-1]
s.quoteStack = s.quoteStack[:len(s.quoteStack)-1]
return quote
}
// ResumeInterpolation resumes scanning of a string interpolation.
func (s *Scanner) ResumeInterpolation() string {
quote := s.popInterpolation()
_, str := s.scanString(s.offset-1, quote)
return str
}
// Offset returns the current position offset.
func (s *Scanner) Offset() int {
return s.offset
}
// Scan scans the next token and returns the token position, the token,
// and its literal string if applicable. The source end is indicated by
// EOF.
//
// If the returned token is a literal (IDENT, INT, FLOAT,
// IMAG, CHAR, STRING) or COMMENT, the literal string
// has the corresponding value.
//
// If the returned token is a keyword, the literal string is the keyword.
//
// If the returned token is Comma, the corresponding
// literal string is "," if the comma was present in the source,
// and "\n" if the semicolon was inserted because of a newline or
// at EOF.
//
// If the returned token is ILLEGAL, the literal string is the
// offending character.
//
// In all other cases, Scan returns an empty literal string.
//
// For more tolerant parsing, Scan will return a valid token if
// possible even if a syntax error was encountered. Thus, even
// if the resulting token sequence contains no illegal tokens,
// a client may not assume that no error occurred. Instead it
// must check the scanner's ErrorCount or the number of calls
// of the error handler, if there was one installed.
//
// Scan adds line information to the file added to the file
// set with Init. Token positions are relative to that file
// and thus relative to the file set.
func (s *Scanner) Scan() (pos token.Pos, tok token.Token, lit string) {
scanAgain:
s.skipWhitespace(1)
var rel token.RelPos
switch {
case s.linesSinceLast > 1:
rel = token.NewSection
case s.linesSinceLast == 1:
rel = token.Newline
case s.spacesSinceLast > 0:
rel = token.Blank
default:
rel = token.NoSpace
}
// current token start
offset := s.offset
pos = s.file.Pos(offset, rel)
// determine token value
insertEOL := false
var quote quoteInfo
switch ch := s.ch; {
case '0' <= ch && ch <= '9':
insertEOL = true
tok, lit = s.scanNumber(false)
case isLetter(ch), ch == '$', ch == '#':
lit = s.scanFieldIdentifier()
if len(lit) > 1 {
// keywords are longer than one letter - avoid lookup otherwise
tok = token.Lookup(lit)
insertEOL = true
break
}
if ch != '#' || (s.ch != '\'' && s.ch != '"' && s.ch != '#') {
tok = token.IDENT
insertEOL = true
break
}
quote.numHash = 1
ch = s.ch
fallthrough
default:
s.next() // always make progress
switch ch {
case -1:
if s.insertEOL {
s.insertEOL = false // EOF consumed
return s.file.Pos(offset, token.Elided), token.COMMA, "\n"
}
tok = token.EOF
case '_':
if s.ch == '|' {
// Unconditionally require this to be followed by another
// underscore to avoid needing an extra lookahead.
// Note that `_|x` is always equal to _.
s.next()
if s.ch != '_' {
s.errf(s.file.Offset(pos), "illegal token '_|'; expected '_'")
insertEOL = s.insertEOL // preserve insertComma info
tok = token.ILLEGAL
lit = "_|"
break
}
s.next()
tok = token.BOTTOM
lit = "_|_"
} else {
tok = token.IDENT
lit = "_" + s.scanFieldIdentifier()
}
insertEOL = true
case '\n':
// we only reach here if s.insertComma was
// set in the first place and exited early
// from s.skipWhitespace()
s.insertEOL = false // newline consumed
p := s.file.Pos(offset, token.Elided)
s.skipWhitespace(1)
// Don't elide comma before a ',' or ':' to ensure JSON
// conformance. Note that cue fmt should immediately undo those.
if s.ch == ',' || s.ch == ':' {
return s.Scan()
}
return p, token.COMMA, "\n"
case '#':
for quote.numHash++; s.ch == '#'; quote.numHash++ {
s.next()
}
ch = s.ch
if ch != '\'' && ch != '"' {
break
}
s.next()
fallthrough
case '"', '\'':
insertEOL = true
quote.char = ch
quote.numChar = 1
offs := s.offset - 1 - quote.numHash
switch _, n := s.consumeQuotes(ch, 2); n {
case 0:
quote.numChar = 1
tok, lit = s.scanString(offs, quote)
case 1:
// When the string is surrounded by hashes,
// a single leading quote is OK (and part of the string)
// e.g. #""hello""#
// unless it's succeeded by the correct number of terminating
// hash characters
// e.g. ##""##
if n := s.scanHashes(quote.numHash); n == quote.numHash {
// It's the empty string.
tok, lit = token.STRING, string(s.src[offs:s.offset])
} else {
tok, lit = s.scanString(offs, quote)
}
case 2:
quote.numChar = 3
switch s.ch {
case '\n':
s.next()
tok, lit = s.scanString(offs, quote)
case '\r':
s.next()
if s.ch == '\n' {
s.next()
tok, lit = s.scanString(offs, quote)
break
}
fallthrough
default:
s.errf(offs, "expected newline after multiline quote %s",
s.src[offs:s.offset])
tok, lit = token.STRING, string(s.src[offs:s.offset])
}
}
case '@':
insertEOL = true
tok, lit = s.scanAttribute()
case ':':
tok = token.COLON
case ';':
tok = token.SEMICOLON
insertEOL = true
case '?':
tok = token.OPTION
insertEOL = true
case '.':
if '0' <= s.ch && s.ch <= '9' {
insertEOL = true
tok, lit = s.scanNumber(true)
} else if s.ch == '.' {
s.next()
if s.ch == '.' {
s.next()
tok = token.ELLIPSIS
insertEOL = true
} else {
s.errf(s.file.Offset(pos), "illegal token '..'; expected '.'")
}
} else {
tok = token.PERIOD
}
case ',':
tok = token.COMMA
lit = ","
case '(':
tok = token.LPAREN
case ')':
insertEOL = true
tok = token.RPAREN
case '[':
tok = token.LBRACK
case ']':
insertEOL = true
tok = token.RBRACK
case '{':
tok = token.LBRACE
case '}':
insertEOL = true
tok = token.RBRACE
case '+':
tok = token.ADD // Consider ++ for list concatenate.
case '-':
tok = token.SUB
case '*':
tok = token.MUL
case '/':
if s.ch == '/' {
// comment
if s.insertEOL {
// reset position to the beginning of the comment
s.ch = '/'
s.offset = s.file.Offset(pos)
s.rdOffset = s.offset + 1
s.insertEOL = false // newline consumed
return s.file.Pos(offset, token.Elided), token.COMMA, "\n"
}
comment := s.scanComment()
if s.mode&ScanComments == 0 {
// skip comment
s.insertEOL = false // newline consumed
goto scanAgain
}
tok = token.COMMENT
lit = comment
} else {
tok = token.QUO
}
// We no longer use %, but seems like a useful token to use for
// something else at some point.
// case '%':
case '<':
if s.ch == '-' {
s.next()
tok = token.ARROW
} else {
tok = s.switch2(token.LSS, token.LEQ)
}
case '>':
tok = s.switch2(token.GTR, token.GEQ)
case '=':
if s.ch == '~' {
s.next()
tok = token.MAT
} else {
tok = s.switch2(token.BIND, token.EQL)
}
case '!':
if s.ch == '~' {
s.next()
tok = token.NMAT
} else {
tok = s.switch2(token.NOT, token.NEQ)
}
case '&':
switch s.ch {
case '&':
s.next()
tok = token.LAND
default:
tok = token.AND
}
case '|':
if s.ch == '|' {
s.next()
tok = token.LOR
} else {
tok = token.OR
}
default:
// next reports unexpected BOMs - don't repeat
if ch != bom {
s.errf(s.file.Offset(pos), "illegal character %#U", ch)
}
insertEOL = s.insertEOL // preserve insertSemi info
tok = token.ILLEGAL
lit = string(ch)
}
}
if s.mode&DontInsertCommas == 0 {
s.insertEOL = insertEOL
}
s.linesSinceLast = 0
s.spacesSinceLast = 0
return
}