forked from mwh/minigrace
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlexer.grace
735 lines (726 loc) · 30.4 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
#pragma DefaultVisibility=public
import "io" as io
import "sys" as sys
import "util" as util
import "unicode" as unicode
import "mgcollections" as collections
// 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 IdentifierToken.new(s) {
def kind = "identifier"
def value = s
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class StringToken.new(s) {
def kind = "string"
def value = s
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class OctetsToken.new(s) {
def kind = "octets"
def value = s
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class LBraceToken.new {
def kind = "lbrace"
def value = "\{"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class RBraceToken.new {
def kind = "rbrace"
def value = "}"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class LParenToken.new {
def kind = "lparen"
def value = "("
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class RParenToken.new {
def kind = "rparen"
def value = ")"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class LSquareToken.new {
def kind = "lsquare"
def value = "["
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class RSquareToken.new {
def kind = "rsquare"
def value = "]"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class CommaToken.new {
def kind = "comma"
def value = ","
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class ColonToken.new {
def kind = "colon"
def value = ":"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class DotToken.new {
def kind = "dot"
def value = "."
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class NumToken.new(v) {
def kind = "num"
def value = v
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class KeywordToken.new(v) {
def kind = "keyword"
def value = v
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class OpToken.new(v) {
def kind = "op"
def value = v
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class ArrowToken.new {
def kind = "arrow"
def value = "->"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class BindToken.new {
def kind = "bind"
def value = ":="
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class SemicolonToken.new {
def kind = "semicolon"
def value = ";"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class LGenericToken.new {
def kind = "lgeneric"
def value = "<"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
class RGenericToken.new {
def kind = "rgeneric"
def value = ">"
def line = lineNumber
def indent = indentLevel
def linePos = startPosition
}
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
// 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")) 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 {
tok := NumToken.new(accum)
tok := makeNumToken(accum)
if (tokens.size > 1) then {
if (tokens.last.kind == "dot") then {
tokens.pop
if (tokens.last.kind == "num") then {
tok := tokens.pop
tok := NumToken.new(tok.value ++ "." ++ accum)
} else {
util.syntax_error("Found '.{accum}'" ++
", expected term.")
}
}
}
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 := accum.size
done := true
} elseif (mode == "n") then {
done := true
} elseif (mode == "c") then {
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 {
util.syntax_error("Lexing error: no handler for mode {mode}" ++
" with accum {accum}.")
}
}
startPosition := linePosition
}
def cLines = collections.list.new
def lines = collections.list.new
method fromBase(str, base) {
def digits = "0123456789abcdefghijklmnopqrstuvqxyz"
var val := 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
} else {
inc := n - 87 // 'a' - 10
}
if (inc >= base) then {
util.syntax_error("No such digit '{c}' in base {base}.")
}
val := val + inc
}
val
}
method makeNumToken(accum) {
var base := 10
var sofar := ""
for (accum) do {c->
if (c == "x") then {
base := sofar.asNumber
if (base == 0) then {
base := 16
}
sofar := ""
} else {
sofar := sofar ++ c
}
}
NumToken.new(fromBase(sofar, base).asString)
}
// True if ov is a valid identifier character. Identifier
// characters are Unicode letters, Unicode numbers, apostrophe,
// and (currently) underscore.
method isidentifierchar(ov) {
if (unicode.isLetter(ov) || unicode.isNumber(ov)
|| (ov == 95) || (ov == 39)) then {
// 95 is _, 39 is '
true
} else {
false
}
}
// True if c (with codepoint ordval) is a valid operator character.
method isoperatorchar(c, ordval) {
if ((c == "-") || (c == "&") || (c == "|") || (c == ":")
|| (c == "%") || (c == "^") || (c == "@") || (c == "?")
|| (c == "*") || (c == "/") || (c == "+") || (c == "!")
) then {
return true
}
if (unicode.isSymbolMathematical(ordval)) then {
return true
} elseif (unicode.iscategory(c, "So")) then {
return true
}
return false
}
// Read the program text from util.infile and return a list of
// tokens.
method lexfile(file) {
util.log_verbose("reading source.")
lexinput(file.read)
}
method lexinput(input) {
var tokens := []
var mode := "n"
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
var cline := ""
var lineStr := ""
linePosition := 0
util.log_verbose("lexing.")
util.lines := lines
util.cLines := cLines
for (input) do { c ->
linePosition := linePosition + 1
util.setPosition(lineNumber, linePosition)
var ct := ""
var ordval := c.ord // String.ord gives the codepoint
if ((unicode.isSeparator(ordval) && (ordval != 32) &&
(ordval != 8232)) || (ordval == 9)) then {
// Character is whitespace, but not an ASCII space or
// Unicode LINE SEPARATOR, or is a tab
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Illegal whitespace in input: "
++ "U+{padl(ordval.inBase 16, 4, "0")} "
++ "({ordval}), {unicode.name(c)}.")
}
if (unicode.isControl(ordval) && (ordval != 10)
&& (ordval != 13)) then {
// Character is a control character other than
// carriage return or line feed.
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Illegal control character in "
++ "input: U+{padl(ordval.inBase 16, 4, "0")} "
++ "({ordval}), {unicode.name(c)}.")
}
if (atStart && (linePosition == 1)) then {
if (c == "#") then {
mode := "p"
newmode := mode
} else {
atStart := false
}
}
if (instr || inBackticks) 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 (prev == "x") then {
// Or, actually of an Octet literal
newmode := "x"
mode := "n"
}
}
if (c == "`") then {
newmode := "I"
inBackticks := true
}
ct := isidentifierchar(ordval)
if (ct) then {
newmode := "i"
}
ct := ((ordval >= 48) && (ordval <=57))
if (ct && (mode != "i")) then {
newmode := "m"
}
if ((ordval >= 97) && (ordval <=122) && (mode == "m")) then {
newmode := "m"
}
if ((mode == "i") && (c == "<")) then {
newmode := "<"
} elseif (((mode == "i") || (mode == ">")
|| (mode == "<"))
&& (c == ">")) then {
if (mode == ">") then {
modechange(tokens, mode, accum)
}
newmode := ">"
} elseif (isoperatorchar(c, ordval)) then {
newmode := "o"
}
if ((c == "(") || (c == ")") || (c == ",") || (c == ".")
|| (c == "\{") || (c == "}") || (c == "[")
|| (c == "]") || (c == ";")) then {
newmode := c
}
if ((c == "#") && (mode != "p")) then {
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Illegal operator character in "
++ "input: U+{padl(ordval.inBase 16, 4, "0")} "
++ "({ordval}), {unicode.name(c)}.")
}
if ((c == ".") && (accum == ".")) then {
// Special handler for .. operator
mode := "o"
newmode := mode
}
if ((c == "/") && (accum == "/")) then {
// Start of comment
mode := "c"
newmode := mode
}
if ((newmode == mode) && (mode == "n")
&& (unicode.isSeparator(ordval).not)
&& (unicode.isControl(ordval).not)) then {
if ((unicode.isSeparator(ordval).not)
&& (ordval != 10) && (ordval != 13)
&& (ordval != 32)) then {
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Unknown character in "
++ "input: #{ordval}"
++ " '{c}', {unicode.name(c)}")
}
}
if ((c == ".") && (accum == "..")) then {
// Special handler for ... identifier
mode := "n"
newmode := mode
modechange(tokens, "i", "...")
accum := ""
}
}
if ((mode == "x") && (c == "\"") && (escaped.not)) then {
// End of octet literal
newmode := "n"
instr := false
}
if ((mode == "\"") && (c == "\"") && (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 ((mode == "I") && (inBackticks) && (c == "`")) then {
// End of backticked identifier
newmode := "n"
inBackticks := false
backtickIdent := true
}
if (newmode != mode) then {
// This character is the beginning of a different
// lexical mode - process the old one now.
modechange(tokens, mode, accum)
if ((newmode == "}") && (interpdepth > 0)) then {
modechange(tokens, ")", ")")
modechange(tokens, "o", "++")
newmode := "\""
instr := true
interpdepth := interpdepth - 1
}
mode := newmode
if (instr || inBackticks) then {
// String accum should skip the opening quote, but
// other modes' should include their first
// character.
accum := ""
} else {
accum := c
}
if ((mode == "(") || (mode == ")") || (mode == "[")
|| (mode == "]") || (mode == "\{")
|| (mode == "}")) then {
modechange(tokens, mode, accum)
mode := "n"
newmode := "n"
accum := ""
}
backtickIdent := false
} elseif (instr) then {
if (c == "\n") then {
if (interpdepth > 0) then {
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Runaway string "
++ "interpolation.")
} else {
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Newlines not permitted "
++ "in string literals.")
}
}
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 (inBackticks) then {
if (c == "\n") then {
lineStr := lineStr ++ c
lines.push(lineStr)
util.syntax_error("Newlines not permitted in"
++ " backtick identifiers.")
}
accum := accum ++ c
} elseif ((c == "\n") || (c == "\r")) then {
// Linebreaks terminate any open tokens
modechange(tokens, mode, accum)
mode := "d"
newmode := "d"
accum := ""
if (c != "\r") then {
cLines.push(cline)
cline := ""
lines.push(lineStr)
lineStr := ""
}
} else {
accum := accum ++ c
}
if ((accum == "...") && {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
util.setPosition(lineNumber, 0)
} elseif (c == "\r") then {
} else {
if (c == "\"") then {
cline := cline ++ "\\\""
} else {
if (c == "\\") then {
cline := cline ++ "\\\\"
} else {
cline := cline ++ c
}
}
lineStr := lineStr ++ c
}
prev := c
}
// If file doesn't end in newline, add last line to the collection of lines.
if ((prev != "\n") && (prev != "\r")) then {
cLines.push(cline)
lines.push(lineStr)
}
modechange(tokens, mode, accum)
tokens
}
}
}
}
method Lexer {
LexerClass
}