-
Notifications
You must be signed in to change notification settings - Fork 11
/
lexer.grace
1027 lines (1007 loc) · 48.9 KB
/
lexer.grace
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
#pragma DefaultVisibility=public
import "io" as io
import "sys" as sys
import "util" as util
import "unicode" as unicode
import "mgcollections" as collections
import "errormessages" as errormessages
// Return the numeric value of the single hexadecimal character c.
method hexdecchar(c) {
var chars := ["0", "1", "2", "3", "4", "5", "6", "7", "8",
"9", "a", "b", "c", "d", "e", "f"]
var ret := 0
var i := 0
for (chars) do {cr->
if (cr == c) then {
ret := i
}
i := i + 1
}
ret
}
method padl(s, l, w) {
if (s.size >= l) then {
return s
}
var s' := s
while {s'.size < l} do {
s' := w ++ s'
}
return s'
}
def LexerClass = object {
method new {
var lineNumber := 1
var linePosition := 0
var startPosition := 1
var indentLevel := 0
class Token.new() {
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
var next := false
var prev := false
method ==(other) {
if(other == false) then {
false
} else {
(other.line == line) && (other.linePos == linePos)
}
}
}
class IdentifierToken.new(s) {
inherits Token.new
def kind = "identifier"
def value = s
def size = s.size
}
class StringToken.new(s) {
inherits Token.new
def kind = "string"
def value = s
def size = s.size + 2
}
class CommentToken.new(s) {
inherits Token.new
def kind = "comment"
def value = s
def size = s.size + 2
}
class OctetsToken.new(s) {
inherits Token.new
def kind = "octets"
def value = s
def size = s.size + 3
}
class LBraceToken.new {
inherits Token.new
def kind = "lbrace"
def value = "\{"
def size = 1
}
class RBraceToken.new {
inherits Token.new
def kind = "rbrace"
def value = "}"
def size = 1
}
class LParenToken.new {
inherits Token.new
def kind = "lparen"
def value = "("
def size = 1
}
class RParenToken.new {
inherits Token.new
def kind = "rparen"
def value = ")"
def size = 1
}
class LSquareToken.new {
inherits Token.new
def kind = "lsquare"
def value = "["
def size = 1
}
class RSquareToken.new {
inherits Token.new
def kind = "rsquare"
def value = "]"
def size = 1
}
class CommaToken.new {
inherits Token.new
def kind = "comma"
def value = ","
def size = 1
}
class ColonToken.new {
inherits Token.new
def kind = "colon"
def value = ":"
def size = 1
}
class DotToken.new {
inherits Token.new
def kind = "dot"
def value = "."
def size = 1
}
class NumToken.new(v, b) {
inherits Token.new
def kind = "num"
def value = v
def base = b
def size = linePosition - startPosition
}
class KeywordToken.new(v) {
inherits Token.new
def kind = "keyword"
def value = v
def size = v.size
}
class OpToken.new(v) {
inherits Token.new
def kind = "op"
def value = v
def size = v.size
}
class ArrowToken.new {
inherits Token.new
def kind = "arrow"
def value = "->"
def size = 2
}
class BindToken.new {
inherits Token.new
def kind = "bind"
def value = ":="
def size = 2
}
class SemicolonToken.new {
inherits Token.new
def kind = "semicolon"
def value = ";"
def size = 1
}
class LGenericToken.new {
inherits Token.new
def kind = "lgeneric"
def value = "<"
def size = 1
}
class RGenericToken.new {
inherits Token.new
def kind = "rgeneric"
def value = ">"
def size = 1
}
object {
// When a new lexical class has begun, add to the tokens list
// the token corresponding to the previous accumulated data.
// mode is the previous lexical mode (a string), and accum the
// accumulated characters since that mode began. Modes are:
// n Whitespace i Identifier
// " Quoted string x Octets literal
// m Number o Any operator
// p Pragma d Indentation
// c Comment
// ,.{}()[]<>; The corresponding literal character
//
// There are three special cases for mode o. If accum is "->",
// ":=", or "=", the corresponding special token is created.
// For mode i, a keyword token is created for an identifier
// whose name is a reserved keyword.
method modechange(tokens, mode, accum) {
var done := false
var tok := 0
if ((mode != "n") || (accum.size > 0)) then {
if (mode == "i") then {
tok := IdentifierToken.new(accum)
if ((accum == "object") || (accum == "method")
|| (accum == "var") || (accum == "type")
|| (accum == "import") || (accum == "class")
|| (accum == "return") || (accum == "def")
|| (accum == "inherits") || (accum == "is")
|| (accum == "dialect")
|| (accum == "constructor")) then {
tok := KeywordToken.new(accum)
}
tokens.push(tok)
done := true
}
if (mode == "I") then {
tok := IdentifierToken.new(accum)
tokens.push(tok)
done := true
} elseif {mode == "\""} then {
tok := StringToken.new(accum)
tokens.push(tok)
done := true
} elseif {mode == "x"} then {
tok := OctetsToken.new(accum)
tokens.push(tok)
done := true
} elseif {mode == ","} then {
tok := CommaToken.new
tokens.push(tok)
done := true
} elseif {mode == "."} then {
tok := DotToken.new
tokens.push(tok)
done := true
} elseif {mode == "\{"} then {
tok := LBraceToken.new
tokens.push(tok)
done := true
} elseif {mode == "}"} then {
tok := RBraceToken.new
tokens.push(tok)
done := true
} elseif {mode == "("} then {
tok := LParenToken.new
tokens.push(tok)
done := true
} elseif {mode == ")"} then {
tok := RParenToken.new
tokens.push(tok)
done := true
} elseif {mode == "["} then {
tok := LSquareToken.new
tokens.push(tok)
done := true
}
if (mode == "]") then {
tok := RSquareToken.new
tokens.push(tok)
done := true
} elseif {mode == "<"} then {
tok := LGenericToken.new
tokens.push(tok)
done := true
} elseif {mode == ">"} then {
tok := RGenericToken.new
tokens.push(tok)
done := true
} elseif {mode == ";"} then {
tok := SemicolonToken.new
tokens.push(tok)
done := true
} elseif {mode == "m"} then {
if ((tokens.size > 1).andAlso {tokens.last.kind == "dot"}) then {
def dot = tokens.pop
if (tokens.last.kind == "num") then {
if (tokens.last.base == 10) then {
tok := tokens.pop
var decimal := makeNumToken(accum)
if(decimal.base == 10) then {
tok := NumToken.new(tok.value ++ "." ++ accum, 10)
} else {
def suggestions = []
var suggestion := errormessages.suggestion.new
suggestion.replaceRange(dot.linePos + 1, linePosition - 1)with(decimal.value)onLine(lineNumber)
suggestions.push(suggestion)
suggestion := errormessages.suggestion.new
suggestion.deleteRange(dot.linePos, linePosition - 1)onLine(lineNumber)
suggestions.push(suggestion)
errormessages.syntaxError("The fractional part of a number must be in base 10.")atRange(
lineNumber, dot.linePos + 1, linePosition - 1)withSuggestions(suggestions)
}
} else {
def suggestions = []
var suggestion := errormessages.suggestion.new
suggestion.replaceRange(tokens.last.linePos, dot.linePos - 1)with(tokens.last.value)onLine(lineNumber)
suggestions.push(suggestion)
suggestion := errormessages.suggestion.new
suggestion.deleteChar(dot.linePos)onLine(lineNumber)
suggestions.push(suggestion)
errormessages.syntaxError("A number in base {tokens.last.base} cannot have a fractional part.")atRange(
lineNumber, dot.linePos, linePosition - 1)withSuggestions(suggestions)
}
} else {
if(tokens.last.kind == "string") then {
def suggestion = errormessages.suggestion.new
suggestion.replaceChar(dot.linePos)with("++")onLine(dot.line)
errormessages.syntaxError("A number may only follow a '.' if there is a number before the '.'. "
++ "To join a number to a string, use '++'.")atRange(
dot.line, dot.linePos, dot.linePos)withSuggestion(suggestion)
} elseif{(tokens.last.kind == "op") || (tokens.last.kind == "bind")} then {
def suggestion = errormessages.suggestion.new
suggestion.insert("0")atPosition(dot.linePos)onLine(dot.line)
errormessages.syntaxError("A number must have a digit before the decimal point.")atPosition(
dot.line, dot.linePos)withSuggestion(suggestion)
} elseif{tokens.last.kind == "identifier"} then {
def suggestions = []
if(tokens.last.value == "o") then {
def suggestion = errormessages.suggestion.new
suggestion.replaceChar(tokens.last.linePos)with("0")onLine(tokens.last.line)
suggestions.push(suggestion)
}
def suggestion = errormessages.suggestion.new
suggestion.replaceRange(dot.linePos, linePosition - 1)with("({accum})")onLine(tokens.last.line)
suggestions.push(suggestion)
errormessages.syntaxError("A number may only follow a '.' if there is a number before the '.'.")atRange(
dot.line, dot.linePos, dot.linePos)withSuggestions(suggestions)
} else {
errormessages.syntaxError("A number may only follow a '.' if there is a number before the '.'.")atRange(
dot.line, dot.linePos, dot.linePos)
}
}
} else {
tok := makeNumToken(accum)
}
tokens.push(tok)
done := true
} elseif {mode == "o"} then {
tok := OpToken.new(accum)
if (accum == "->") then {
tok := ArrowToken.new
} elseif {accum == ":="} then {
tok := BindToken.new
} elseif {accum == ":"} then {
tok := ColonToken.new
}
tokens.push(tok)
done := true
} elseif {mode == "d"} then {
indentLevel := linePosition - 1//accum.size
done := true
} elseif {mode == "n"} then {
done := true
} elseif {mode == "c"} then {
def cmt = accum.substringFrom(3)to(accum.size)
tokens.push(CommentToken.new(cmt))
done := true
} elseif {mode == "p"} then {
if (accum.substringFrom(1)to(8) == "#pragma ") then {
util.processExtension(
accum.substringFrom(9)to(accum.size))
}
} elseif {done} then {
//print(mode, accum, tokens)
} else {
errormessages.syntaxError("Lexing error: no handler for mode {mode} with accum {accum}.")atPosition(lineNumber, linePosition)
}
}
startPosition := linePosition
}
method fromBase(str, base) {
var val := 0
var i := 0
for (str) do {c->
def n = c.ord
val := val * base
var inc := 0
if ((n >= 48) && (n <= 57)) then {
inc := n - 48 // 0
} elseif{(n >= 65) && (n <= 90)} then {
inc := n - 55 // 'A' - 10
} else {
inc := n - 87 // 'a' - 10
}
if (inc >= base) then {
if((str[1] == "0") && (inc < 16)) then {
def suggestion = errormessages.suggestion.new
suggestion.insert("x")atPosition(linePosition - str.size + 1)onLine(lineNumber)
errormessages.syntaxError("A number in base 16 must start with '0x'.")atPosition(
lineNumber, linePosition - str.size + 1)withSuggestion(suggestion)
} else {
def suggestion = errormessages.suggestion.new
if(str.size == 1) then {
suggestion.deleteRange(linePosition - str.size - 1, linePosition - 1)onLine(lineNumber)
} else {
suggestion.deleteChar(linePosition - str.size + i)onLine(lineNumber)
}
def validDigits = if(base <= 10) then {
"'0' to '{base - 1}'"
} else {
"'0' to '9', 'a' to '{unicode.create(87 + base)}'"
}
errormessages.syntaxError("'{c}' is not a valid digit in base {base}. Valid digits are {validDigits}.")atRange(
lineNumber, linePosition - str.size + i, linePosition - str.size + i)withSuggestion(suggestion)
}
}
val := val + inc
i := i + 1
}
val
}
method makeNumToken(accum) {
var base := 10
var baseSet := false
var sofar := ""
var i := 0
for (accum) do {c->
if ((c == "x") && (!baseSet)) then {
base := sofar.asNumber
baseSet := true
if (base == 0) then {
base := 16
}
if((base < 2) || (base > 36)) then {
def suggestions = []
var suggestion := errormessages.suggestion.new
suggestion.replaceChar(linePosition - accum.size + i)with("*")onLine(lineNumber)
suggestions.push(suggestion)
suggestion := errormessages.suggestion.new
suggestion.deleteRange(linePosition - accum.size, linePosition - accum.size + i)onLine(lineNumber)
suggestions.push(suggestion)
errormessages.syntaxError("Base {base} is not a valid numerical base.")atRange(
lineNumber, linePosition - accum.size, linePosition - accum.size + i - 1)withSuggestions(suggestions)
}
sofar := ""
} else {
sofar := sofar ++ c
}
i := i + 1
}
if(sofar == "") then {
def suggestions = []
var suggestion := errormessages.suggestion.new
suggestion.deleteRange(linePosition - accum.size + i - 1, linePosition - 1)onLine(lineNumber)
suggestions.push(suggestion)
suggestion := errormessages.suggestion.new
suggestion.insert("0")atPosition(linePosition)onLine(lineNumber)
suggestions.push(suggestion)
errormessages.syntaxError("At least one digit must follow the 'x' in a number.")atPosition(
lineNumber, linePosition - accum.size + i)withSuggestions(suggestions)
}
NumToken.new(fromBase(sofar, base).asString, base)
}
// Read the program text from util.infile and return a list of
// tokens.
method lexfile(file) {
util.log_verbose("reading source.")
def lines = []
def cLines = []
var line := ""
var cLine := ""
var source := ""
for(file.read) do { c ->
if((c == "\n") || (c == "\l")) then {
lines.push(line)
cLines.push(cLine)
line := ""
cLine := ""
} elseif{c == "\r"} then {
} elseif{c == "\\"} then {
line := line ++ "\\"
cLine := cLine ++ "\\\\"
} elseif{c == "\""} then {
line := line ++ "\""
cLine := cLine ++ "\\\""
} else {
line := line ++ c
cLine := cLine ++ c
}
source := source ++ c
}
if(line != "") then {
lines.push(line)
cLines.push(cLine)
}
util.lines := lines
util.cLines := cLines
lexinput(source)
}
method lexinput(input) {
// tokens is a doubly-linked list of tokens.
var tokens := object {
var first := false
var last := false
var size' := 0
method push(t) {
if(first == false) then {
first := t
last := t
} else {
last.next := t
t.prev := last
last := t
}
size' := size' + 1
}
method pop {
if(last != false) then {
def popped = last
last := last.prev
if(last == false) then {
first := false
}
size' := size' - 1
popped
}
}
method poll {
if(first != false) then {
def polled = first
first := first.next
if(first == false) then {
last := false
}
size' := size' - 1
polled
}
}
method size {
size' + 0
}
method iter {
object {
var n := first
method havemore {
n != false
}
method next {
def ret = n
n := n.next
ret
}
}
}
method iterator {
iter
}
}
var mode := "d"
var newmode := mode
var instr := false
var inBackticks := false
var backtickIdent := false
var accum := ""
var escaped := false
var prev := ""
var unichars := 0
var codepoint := 0
var interpdepth := 0
var interpString := false
var atStart := true
linePosition := 0
util.log_verbose("lexing.")
def badSeparator = unicode.pattern("Z", 9)not(32, 8232)
def badControl = unicode.pattern("C")not(10, 13)
def selfModes = unicode.pattern("(".ord, ")".ord, ",".ord,
".".ord, "\{".ord, "}".ord, "[".ord, "]".ord, ";".ord)
def brackets = unicode.pattern("(".ord, ")".ord,
"\{".ord, "}".ord, "[".ord, "]".ord)
def identifierChar = unicode.pattern("L", "N", 95, 39)
def digit = unicode.pattern("0".ord, "1".ord, "2".ord, "3".ord,
"4".ord, "5".ord, "6".ord, "7".ord, "8".ord, "9".ord)
def digitB = unicode.pattern("0".ord, "1".ord, "2".ord, "3".ord,
"4".ord, "5".ord, "6".ord, "7".ord, "8".ord, "9".ord)
def operatorChar = unicode.pattern("Sm", "So",
"-".ord, "&".ord, "|".ord, ":".ord,
"%".ord, "^".ord, "@".ord, "?".ord,
"*".ord, "/".ord, "+".ord, "!".ord, "$".ord
)
def iGTLT = unicode.pattern("i".ord, "<".ord, ">".ord)
def notcp = unicode.pattern()not("c".ord, "p".ord)
def mainBlock = { c->
var ct := ""
var ordval := c.ord // String.ord gives the codepoint
if (badSeparator.match(ordval)) then {
// Character is whitespace, but not an ASCII space or
// Unicode LINE SEPARATOR, or is a tab
def suggestion = errormessages.suggestion.new
suggestion.replaceChar(linePosition)with(" ")onLine(lineNumber)
if(ordval == 9) then {
if (instr) then {
suggestion.replaceRange(linePosition, linePosition)
with("\\u{padl(ordval.inBase 16, 4, "0")}")
onLine(lineNumber)
errormessages.syntaxError("tabs cannot be "
++ "written in the source code; "
++ "use the Unicode escape \\u"
++ padl(ordval.inBase 16, 4, "0")
++ " instead")
atRange(lineNumber, linePosition, linePosition)
withSuggestion(suggestion)
}
errormessages.syntaxError("Tabs are not allowed; use spaces instead.")atRange(lineNumber,
linePosition, linePosition)withSuggestion(suggestion)
} else {
if (instr) then {
suggestion.replaceRange(linePosition, linePosition)
with("\\u{padl(ordval.inBase 16, 4, "0")}")
onLine(lineNumber)
errormessages.syntaxError("{unicode.name(c)} (U+{padl(ordval.inBase 16, 4, "0")}) "
++ "is not a valid whitespace character"
++ " and cannot be "
++ "written in the source code; "
++ "use the Unicode escape \\u"
++ padl(ordval.inBase 16, 4, "0")
++ " instead")
atRange(lineNumber, linePosition, linePosition)
withSuggestion(suggestion)
}
errormessages.syntaxError("{unicode.name(c)} (U+{padl(ordval.inBase 16, 4, "0")}) "
++ "is not a valid whitespace character; use spaces instead.")atRange(lineNumber,
linePosition, linePosition)withSuggestion(suggestion)
}
}
if (badControl.match(ordval)) then {
// Character is a control character other than
// carriage return or line feed.
def suggestion = errormessages.suggestion.new
if (instr) then {
suggestion.replaceRange(linePosition, linePosition)
with("\\u{padl(ordval.inBase 16, 4, "0")}")
onLine(lineNumber)
errormessages.syntaxError("{unicode.name(c)} (U+{padl(ordval.inBase 16, 4, "0")}) "
++ "is a control character and cannot be "
++ "written in the source code; "
++ "use the Unicode escape \\u"
++ padl(ordval.inBase 16, 4, "0")
++ " instead")
atRange(lineNumber, linePosition, linePosition)
withSuggestion(suggestion)
}
suggestion.deleteChar(linePosition)onLine(lineNumber)
errormessages.syntaxError("{unicode.name(c)} (U+{padl(ordval.inBase 16, 4, "0")}) "
++ "is a control character and cannot be written in the source code; consider using spaces instead.")atRange(lineNumber,
linePosition, linePosition)withSuggestion(suggestion)
}
if (atStart) then {
if (linePosition == 1) then {
if (c == "#") then {
mode := "p"
newmode := mode
} else {
atStart := false
}
}
}
if (instr) then {
} elseif {(mode != "c") && (mode != "p")} then {
// Not in a comment, so look for a mode.
if ((c == " ") && (mode != "d")) then {
newmode := "n"
}
if (c == "\"") then {
// Beginning of a string
newmode := "\""
instr := true
}
if (identifierChar.match(ordval)) then {
newmode := "i"
}
ct := ((ordval >= 48) && (ordval <=57))
if (digit.match(ordval)) then {
if (mode != "i") then {
newmode := "m"
}
}
if (mode == "m") then {
if ((ordval >= 97) && (ordval <=122)) then {
newmode := "m"
} else {
if ((ordval >= 65) && (ordval <= 90)) then {
newmode := "m"
}
}
}
if ((mode == "i") && (c == "<")) then {
newmode := "<"
} elseif {iGTLT.match(mode)
&& (c == ">")} then {
if (mode == ">") then {
modechange(tokens, mode, accum)
}
newmode := ">"
} elseif {operatorChar.match(ordval)} then {
newmode := "o"
}
if (selfModes.match(ordval)) then {
newmode := c
}
if (c == "#") then {
if (mode != "p") then {
if(util.lines.at(lineNumber).substringFrom(1)to(7) == "#pragma") then {
if(tokens.size == 0) then {
def suggestion = errormessages.suggestion.new
suggestion.addLine(1, util.lines.at(lineNumber))
suggestion.addLine(lineNumber, "")
errormessages.syntaxError("Pragma directives must be at the start of the file.")atLine(
lineNumber)withSuggestion(suggestion)
} else {
errormessages.syntaxError("Pragma directives must be at the start of the file.")atLine(
lineNumber)
}
} else {
def suggestion = errormessages.suggestion.new
suggestion.replaceChar(linePosition)with("//")onLine(lineNumber)
errormessages.syntaxError("'#' is not allowed here. For a comment use '//'.")atRange(
lineNumber, linePosition, linePosition)withSuggestion(suggestion)
}
}
}
if (c == ".") then {
if (accum == ".") then {
// Special handler for .. operator
mode := "o"
newmode := mode
}
if (accum == "..") then {
// Special handler for ... identifier
mode := "n"
newmode := mode
modechange(tokens, "i", "...")
accum := ""
}
}
if (c == "/") then {
if (accum == "/") then {
// Start of comment
mode := "c"
newmode := mode
}
}
if (mode == "n") then {
if (mode == newmode) then {
if (unicode.isSeparator(ordval).not) then {
if (unicode.isControl(ordval).not) then {
if (ordval != 10) then {
if (ordval != 13) then {
if (ordval != 32) then {
if (c != ".") then{
errormessages.syntaxError("{unicode.name(c)} (U+{padl(ordval.inBase 16, 4, "0")}) "
++ "is not a valid character; use spaces instead.")atRange(
lineNumber, linePosition, linePosition)
}
}
}
}
}
}
}
}
}
if (mode == "\"") then {
if (c == "\"") then {
if (escaped.not) then {
// End of string literal
newmode := "n"
instr := false
if (interpString) then {
modechange(tokens, mode, accum)
modechange(tokens, ")", ")")
mode := newmode
interpString := false
}
}
}
}
if (newmode != mode) then {
// This character is the beginning of a different
// lexical mode - process the old one now.
modechange(tokens, mode, accum)
if (interpdepth > 0) then {
if (newmode == "}") then {
// Find the position of the opening brace to check in the interpolation is empty.
if (util.lines.at(tokens.last.line)[tokens.last.linePos] == "\{") then {
def suggestion = errormessages.suggestion.new
suggestion.deleteRange(linePosition - 1, linePosition)onLine(lineNumber)
errormessages.syntaxError("A string interpolation cannot be empty.")atRange(
lineNumber, tokens.last.linePos, linePosition)withSuggestion(suggestion)
}
modechange(tokens, ")", ")")
modechange(tokens, "o", "++")
newmode := "\""
instr := true
interpdepth := interpdepth - 1
}
}
mode := newmode
if (instr) then {
// String accum should skip the opening quote, but
// other modes' should include their first
// character.
accum := ""
} else {
accum := c
}
if (brackets.match(mode)) then {
modechange(tokens, mode, accum)
mode := "n"
newmode := "n"
accum := ""
}
} elseif {instr} then {
if (c == "\n") then {
if (interpdepth > 0) then {
// Find closest {.
var line := lineNumber
var i := util.lines.at(line).size
while { util.lines.at(line)[i] != "\{" } do {
i := i - 1
if(i == 0) then {
lineNumber := line - 1
i := util.lines.at(line).size
}
}
def suggestions = []
var suggestion := errormessages.suggestion.new
suggestion.insert("\\")atPosition(i)onLine(line)
suggestions.push(suggestion)
if((line == lineNumber) && (i == (linePosition - 2))) then {
errormessages.syntaxError("For a '\{' character in a string use '\\\{'.")atPosition(
line, i)withSuggestions(suggestions)
} else {
suggestion := errormessages.suggestion.new
suggestion.insert("}")atPosition(linePosition - accum.size - 1)onLine(lineNumber)
suggestions.push(suggestion)
errormessages.syntaxError("A string interpolation must end with a '}'. For a '\{' character in a string use '\\\{'.")atPosition(
lineNumber, linePosition - accum.size - 1)withSuggestions(suggestions)
}
} else {
def errorLine = util.lines.at(lineNumber)
def nextLine = if(util.lines.size >= (lineNumber + 1)) then {
util.lines.at(lineNumber + 1)
} else {
""
}
// Count the number of literal quotes in the next line.
var i := 1
var count := 0
while { i <= nextLine.size } do {
if(nextLine[i] == "\"") then { count := count + 1 }
elseif{nextLine[i] == "\\"} then { i := i + 1 }
i := i + 1
}
if ((count % 2) == 1) then {
def suggestions = []
var suggestion := errormessages.suggestion.new
suggestion.addLine(lineNumber, errorLine ++ nextLine)
suggestion.addLine(lineNumber + 1, "")
suggestions.push(suggestion)
suggestion := errormessages.suggestion.new
suggestion.addLine(lineNumber, errorLine ++ "\"")
suggestion.addLine(lineNumber + 1, " ++ \"" ++ nextLine)
suggestions.push(suggestion)
suggestion := errormessages.suggestion.new
suggestion.addLine(lineNumber, errorLine ++ "\\n" ++ nextLine)
suggestion.addLine(lineNumber + 1, "")
suggestions.push(suggestion)
errormessages.syntaxError("A string must end with a '\"'. To insert a newline in a string use '\\n'. "
++ "To split a string over multiple lines use '++' to join strings together.")atRange(
lineNumber, linePosition, linePosition)withSuggestions(suggestions)
} else {
def suggestion = errormessages.suggestion.new
suggestion.addLine(lineNumber, errorLine ++ "\"")
errormessages.syntaxError("A string must end with a '\"'.")atPosition(
lineNumber, linePosition)withSuggestion(suggestion)
}
}
}
if (escaped) then {
if (c == "n") then {
// Newline escape
accum := accum ++ "\u000a"
} elseif {c == "u"} then {
// Beginning of a four-digit Unicode escape
// (for a BMP codepoint).
unichars := 4
codepoint := 0
} elseif {c == "U"} then {
// Beginning of a six-digit Unicode escape
// (for a general codepoint).
unichars := 6
codepoint := 0
} elseif {c == "t"} then {
// Tab escape
accum := accum ++ "\u0009"
} elseif {c == "r"} then {
// Carriage return escape
accum := accum ++ "\u000d"
} elseif {c == "b"} then {
// Backspace escape
accum := accum ++ "\u0008"
} elseif {c == "l"} then {
// LINE SEPARATOR escape
accum := accum ++ "\u2028"
} elseif {c == "f"} then {
// Form feed/"page down" escape
accum := accum ++ "\u000c"
} elseif {c == "e"} then {
// Escape escape
accum := accum ++ "\u001b"
} else {
// For any other character preceded by \,
// insert it literally.
accum := accum ++ c
}
escaped := false
} elseif {c == "\\"} then {
// Begin an escape sequence
escaped := true
} elseif {unichars > 0} then {
// There are still hex digits to read for a
// Unicode escape. Use the current character
// as a hex digit and update the codepoint
// being calculated with its value.
unichars := unichars - 1
codepoint := codepoint * 16
codepoint := codepoint + hexdecchar(c)
if (unichars == 0) then {
// At the end of the sequence construct
// the character in the unicode library.
accum := accum ++ unicode.create(codepoint)
}
} elseif {c == "\{"} then {
if (interpString.not) then {
modechange(tokens, "(", "(")
interpString := true
}
modechange(tokens, mode, accum)
modechange(tokens, "o", "++")
modechange(tokens, "(", "(")
mode := "n"
newmode := "n"
accum := ""
instr := false
interpdepth := interpdepth + 1
} else {
accum := accum ++ c
}
} elseif {(c == "\n") || (c == "\r")} then {
// Linebreaks terminate any open tokens
modechange(tokens, mode, accum)
mode := "d"
newmode := "d"
accum := ""
} else {
accum := accum ++ c
}
if (accum == "...") then {
if (mode == "o") then {
modechange(tokens, "i", "...")
newmode := "n"
mode := newmode
accum := ""
}
}
if (c == "\n") then {
// Linebreaks increment the line counter and insert a
// special "line" token, which the parser can use to
// track the origin of AST nodes for later error
// reporting.
lineNumber := lineNumber + 1
linePosition := 0
startPosition := 1
}
}
for (input) do { c ->
linePosition := linePosition + 1
if (c == " ") then {
if (mode == "d") then {
} else {
if (mode != "n") then {
mainBlock.apply(c)
}
}