forked from ocaml/ocaml
-
Notifications
You must be signed in to change notification settings - Fork 0
/
lexer.mll
809 lines (753 loc) · 26.1 KB
/
lexer.mll
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
(**************************************************************************)
(* *)
(* OCaml *)
(* *)
(* Xavier Leroy, projet Cristal, INRIA Rocquencourt *)
(* *)
(* Copyright 1996 Institut National de Recherche en Informatique et *)
(* en Automatique. *)
(* *)
(* All rights reserved. This file is distributed under the terms of *)
(* the GNU Lesser General Public License version 2.1, with the *)
(* special exception on linking described in the file LICENSE. *)
(* *)
(**************************************************************************)
(* The lexer definition *)
{
open Lexing
open Misc
open Parser
type error =
| Illegal_character of char
| Illegal_escape of string
| Unterminated_comment of Location.t
| Unterminated_string
| Unterminated_string_in_comment of Location.t * Location.t
| Keyword_as_label of string
| Invalid_literal of string
| Invalid_directive of string * string option
;;
exception Error of error * Location.t;;
(* The table of keywords *)
let keyword_table =
create_hashtable 149 [
"and", AND;
"as", AS;
"assert", ASSERT;
"begin", BEGIN;
"class", CLASS;
"constraint", CONSTRAINT;
"do", DO;
"done", DONE;
"downto", DOWNTO;
"else", ELSE;
"end", END;
"exception", EXCEPTION;
"external", EXTERNAL;
"false", FALSE;
"for", FOR;
"fun", FUN;
"function", FUNCTION;
"functor", FUNCTOR;
"if", IF;
"in", IN;
"include", INCLUDE;
"inherit", INHERIT;
"initializer", INITIALIZER;
"lazy", LAZY;
"let", LET;
"match", MATCH;
"method", METHOD;
"module", MODULE;
"mutable", MUTABLE;
"new", NEW;
"nonrec", NONREC;
"object", OBJECT;
"of", OF;
"open", OPEN;
"or", OR;
(* "parser", PARSER; *)
"private", PRIVATE;
"rec", REC;
"sig", SIG;
"struct", STRUCT;
"then", THEN;
"to", TO;
"true", TRUE;
"try", TRY;
"type", TYPE;
"val", VAL;
"virtual", VIRTUAL;
"when", WHEN;
"while", WHILE;
"with", WITH;
"lor", INFIXOP3("lor"); (* Should be INFIXOP2 *)
"lxor", INFIXOP3("lxor"); (* Should be INFIXOP2 *)
"mod", INFIXOP3("mod");
"land", INFIXOP3("land");
"lsl", INFIXOP4("lsl");
"lsr", INFIXOP4("lsr");
"asr", INFIXOP4("asr")
]
(* To buffer string literals *)
let string_buffer = Buffer.create 256
let reset_string_buffer () = Buffer.reset string_buffer
let get_stored_string () = Buffer.contents string_buffer
let store_string_char c = Buffer.add_char string_buffer c
let store_string_utf_8_uchar u = Buffer.add_utf_8_uchar string_buffer u
let store_string s = Buffer.add_string string_buffer s
let store_lexeme lexbuf = store_string (Lexing.lexeme lexbuf)
(* To store the position of the beginning of a string and comment *)
let string_start_loc = ref Location.none;;
let comment_start_loc = ref [];;
let in_comment () = !comment_start_loc <> [];;
let is_in_string = ref false
let in_string () = !is_in_string
let print_warnings = ref true
(* Escaped chars are interpreted in strings unless they are in comments. *)
let store_escaped_char lexbuf c =
if in_comment () then store_lexeme lexbuf else store_string_char c
let store_escaped_uchar lexbuf u =
if in_comment () then store_lexeme lexbuf else store_string_utf_8_uchar u
let with_comment_buffer comment lexbuf =
let start_loc = Location.curr lexbuf in
comment_start_loc := [start_loc];
reset_string_buffer ();
let end_loc = comment lexbuf in
let s = get_stored_string () in
reset_string_buffer ();
let loc = { start_loc with Location.loc_end = end_loc.Location.loc_end } in
s, loc
(* To translate escape sequences *)
let hex_digit_value d = (* assert (d in '0'..'9' 'a'..'f' 'A'..'F') *)
let d = Char.code d in
if d >= 97 then d - 87 else
if d >= 65 then d - 55 else
d - 48
let hex_num_value lexbuf ~first ~last =
let rec loop acc i = match i > last with
| true -> acc
| false ->
let value = hex_digit_value (Lexing.lexeme_char lexbuf i) in
loop (16 * acc + value) (i + 1)
in
loop 0 first
let char_for_backslash = function
| 'n' -> '\010'
| 'r' -> '\013'
| 'b' -> '\008'
| 't' -> '\009'
| c -> c
let char_for_decimal_code lexbuf i =
let c = 100 * (Char.code(Lexing.lexeme_char lexbuf i) - 48) +
10 * (Char.code(Lexing.lexeme_char lexbuf (i+1)) - 48) +
(Char.code(Lexing.lexeme_char lexbuf (i+2)) - 48) in
if (c < 0 || c > 255) then
if in_comment ()
then 'x'
else raise (Error(Illegal_escape (Lexing.lexeme lexbuf),
Location.curr lexbuf))
else Char.chr c
let char_for_octal_code lexbuf i =
let c = 64 * (Char.code(Lexing.lexeme_char lexbuf i) - 48) +
8 * (Char.code(Lexing.lexeme_char lexbuf (i+1)) - 48) +
(Char.code(Lexing.lexeme_char lexbuf (i+2)) - 48) in
Char.chr c
let char_for_hexadecimal_code lexbuf i =
let byte = hex_num_value lexbuf ~first:i ~last:(i+1) in
Char.chr byte
let uchar_for_uchar_escape lexbuf =
let err e =
raise
(Error (Illegal_escape (Lexing.lexeme lexbuf ^ e), Location.curr lexbuf))
in
let len = Lexing.lexeme_end lexbuf - Lexing.lexeme_start lexbuf in
let first = 3 (* skip opening \u{ *) in
let last = len - 2 (* skip closing } *) in
let digit_count = last - first + 1 in
match digit_count > 6 with
| true -> err ", too many digits, expected 1 to 6 hexadecimal digits"
| false ->
let cp = hex_num_value lexbuf ~first ~last in
if Uchar.is_valid cp then Uchar.unsafe_of_int cp else
err (", " ^ Printf.sprintf "%X" cp ^ " is not a Unicode scalar value")
(* recover the name from a LABEL or OPTLABEL token *)
let get_label_name lexbuf =
let s = Lexing.lexeme lexbuf in
let name = String.sub s 1 (String.length s - 2) in
if Hashtbl.mem keyword_table name then
raise (Error(Keyword_as_label name, Location.curr lexbuf));
name
;;
(* Update the current location with file name and line number. *)
let update_loc lexbuf file line absolute chars =
let pos = lexbuf.lex_curr_p in
let new_file = match file with
| None -> pos.pos_fname
| Some s -> s
in
lexbuf.lex_curr_p <- { pos with
pos_fname = new_file;
pos_lnum = if absolute then line else pos.pos_lnum + line;
pos_bol = pos.pos_cnum - chars;
}
;;
let preprocessor = ref None
let escaped_newlines = ref false
(* Warn about Latin-1 characters used in idents *)
let warn_latin1 lexbuf =
Location.deprecated (Location.curr lexbuf)"ISO-Latin1 characters in identifiers"
let handle_docstrings = ref true
let comment_list = ref []
let add_comment com =
comment_list := com :: !comment_list
let add_docstring_comment ds =
let com =
("*" ^ Docstrings.docstring_body ds, Docstrings.docstring_loc ds)
in
add_comment com
let comments () = List.rev !comment_list
(* Error report *)
open Format
let report_error ppf = function
| Illegal_character c ->
fprintf ppf "Illegal character (%s)" (Char.escaped c)
| Illegal_escape s ->
fprintf ppf "Illegal backslash escape in string or character (%s)" s
| Unterminated_comment _ ->
fprintf ppf "Comment not terminated"
| Unterminated_string ->
fprintf ppf "String literal not terminated"
| Unterminated_string_in_comment (_, loc) ->
fprintf ppf "This comment contains an unterminated string literal@.\
%aString literal begins here"
Location.print_error loc
| Keyword_as_label kwd ->
fprintf ppf "`%s' is a keyword, it cannot be used as label name" kwd
| Invalid_literal s ->
fprintf ppf "Invalid literal %s" s
| Invalid_directive (dir, explanation) ->
fprintf ppf "Invalid lexer directive %S" dir;
begin match explanation with
| None -> ()
| Some expl -> fprintf ppf ": %s" expl
end
let () =
Location.register_error_of_exn
(function
| Error (err, loc) ->
Some (Location.error_of_printer loc report_error err)
| _ ->
None
)
}
let newline = ('\013'* '\010')
let blank = [' ' '\009' '\012']
let lowercase = ['a'-'z' '_']
let uppercase = ['A'-'Z']
let identchar = ['A'-'Z' 'a'-'z' '_' '\'' '0'-'9']
let lowercase_latin1 = ['a'-'z' '\223'-'\246' '\248'-'\255' '_']
let uppercase_latin1 = ['A'-'Z' '\192'-'\214' '\216'-'\222']
let identchar_latin1 =
['A'-'Z' 'a'-'z' '_' '\192'-'\214' '\216'-'\246' '\248'-'\255' '\'' '0'-'9']
let symbolchar =
['!' '$' '%' '&' '*' '+' '-' '.' '/' ':' '<' '=' '>' '?' '@' '^' '|' '~']
let dotsymbolchar =
['!' '$' '%' '&' '*' '+' '-' '/' ':' '=' '>' '?' '@' '^' '|' '~']
let decimal_literal =
['0'-'9'] ['0'-'9' '_']*
let hex_digit =
['0'-'9' 'A'-'F' 'a'-'f']
let hex_literal =
'0' ['x' 'X'] ['0'-'9' 'A'-'F' 'a'-'f']['0'-'9' 'A'-'F' 'a'-'f' '_']*
let oct_literal =
'0' ['o' 'O'] ['0'-'7'] ['0'-'7' '_']*
let bin_literal =
'0' ['b' 'B'] ['0'-'1'] ['0'-'1' '_']*
let int_literal =
decimal_literal | hex_literal | oct_literal | bin_literal
let float_literal =
['0'-'9'] ['0'-'9' '_']*
('.' ['0'-'9' '_']* )?
(['e' 'E'] ['+' '-']? ['0'-'9'] ['0'-'9' '_']* )?
let hex_float_literal =
'0' ['x' 'X']
['0'-'9' 'A'-'F' 'a'-'f'] ['0'-'9' 'A'-'F' 'a'-'f' '_']*
('.' ['0'-'9' 'A'-'F' 'a'-'f' '_']* )?
(['p' 'P'] ['+' '-']? ['0'-'9'] ['0'-'9' '_']* )?
let literal_modifier = ['G'-'Z' 'g'-'z']
rule token = parse
| "\\" newline {
if not !escaped_newlines then
raise (Error(Illegal_character (Lexing.lexeme_char lexbuf 0),
Location.curr lexbuf));
update_loc lexbuf None 1 false 0;
token lexbuf }
| newline
{ update_loc lexbuf None 1 false 0;
EOL }
| blank +
{ token lexbuf }
| "_"
{ UNDERSCORE }
| "~"
{ TILDE }
| "~" lowercase identchar * ':'
{ LABEL (get_label_name lexbuf) }
| "~" lowercase_latin1 identchar_latin1 * ':'
{ warn_latin1 lexbuf; LABEL (get_label_name lexbuf) }
| "?"
{ QUESTION }
| "?" lowercase identchar * ':'
{ OPTLABEL (get_label_name lexbuf) }
| "?" lowercase_latin1 identchar_latin1 * ':'
{ warn_latin1 lexbuf; OPTLABEL (get_label_name lexbuf) }
| lowercase identchar *
{ let s = Lexing.lexeme lexbuf in
try Hashtbl.find keyword_table s
with Not_found -> LIDENT s }
| lowercase_latin1 identchar_latin1 *
{ warn_latin1 lexbuf; LIDENT (Lexing.lexeme lexbuf) }
| uppercase identchar *
{ UIDENT(Lexing.lexeme lexbuf) } (* No capitalized keywords *)
| uppercase_latin1 identchar_latin1 *
{ warn_latin1 lexbuf; UIDENT(Lexing.lexeme lexbuf) }
| int_literal { INT (Lexing.lexeme lexbuf, None) }
| (int_literal as lit) (literal_modifier as modif)
{ INT (lit, Some modif) }
| float_literal | hex_float_literal
{ FLOAT (Lexing.lexeme lexbuf, None) }
| ((float_literal | hex_float_literal) as lit) (literal_modifier as modif)
{ FLOAT (lit, Some modif) }
| (float_literal | hex_float_literal | int_literal) identchar+
{ raise (Error(Invalid_literal (Lexing.lexeme lexbuf),
Location.curr lexbuf)) }
| "\""
{ reset_string_buffer();
is_in_string := true;
let string_start = lexbuf.lex_start_p in
string_start_loc := Location.curr lexbuf;
string lexbuf;
is_in_string := false;
lexbuf.lex_start_p <- string_start;
STRING (get_stored_string(), None) }
| "{" lowercase* "|"
{ reset_string_buffer();
let delim = Lexing.lexeme lexbuf in
let delim = String.sub delim 1 (String.length delim - 2) in
is_in_string := true;
let string_start = lexbuf.lex_start_p in
string_start_loc := Location.curr lexbuf;
quoted_string delim lexbuf;
is_in_string := false;
lexbuf.lex_start_p <- string_start;
STRING (get_stored_string(), Some delim) }
| "\'" newline "\'"
{ update_loc lexbuf None 1 false 1;
CHAR (Lexing.lexeme_char lexbuf 1) }
| "\'" [^ '\\' '\'' '\010' '\013'] "\'"
{ CHAR(Lexing.lexeme_char lexbuf 1) }
| "\'\\" ['\\' '\'' '\"' 'n' 't' 'b' 'r' ' '] "\'"
{ CHAR(char_for_backslash (Lexing.lexeme_char lexbuf 2)) }
| "\'\\" ['0'-'9'] ['0'-'9'] ['0'-'9'] "\'"
{ CHAR(char_for_decimal_code lexbuf 2) }
| "\'\\" 'o' ['0'-'3'] ['0'-'7'] ['0'-'7'] "\'"
{ CHAR(char_for_octal_code lexbuf 3) }
| "\'\\" 'x' ['0'-'9' 'a'-'f' 'A'-'F'] ['0'-'9' 'a'-'f' 'A'-'F'] "\'"
{ CHAR(char_for_hexadecimal_code lexbuf 3) }
| "\'\\" _
{ let l = Lexing.lexeme lexbuf in
let esc = String.sub l 1 (String.length l - 1) in
raise (Error(Illegal_escape esc, Location.curr lexbuf))
}
| "(*"
{ let s, loc = with_comment_buffer comment lexbuf in
COMMENT (s, loc) }
| "(**"
{ let s, loc = with_comment_buffer comment lexbuf in
if !handle_docstrings then
DOCSTRING (Docstrings.docstring s loc)
else
COMMENT ("*" ^ s, loc)
}
| "(**" (('*'+) as stars)
{ let s, loc =
with_comment_buffer
(fun lexbuf ->
store_string ("*" ^ stars);
comment lexbuf)
lexbuf
in
COMMENT (s, loc) }
| "(*)"
{ if !print_warnings then
Location.prerr_warning (Location.curr lexbuf) Warnings.Comment_start;
let s, loc = with_comment_buffer comment lexbuf in
COMMENT (s, loc) }
| "(*" (('*'*) as stars) "*)"
{ if !handle_docstrings && stars="" then
(* (**) is an empty docstring *)
DOCSTRING(Docstrings.docstring "" (Location.curr lexbuf))
else
COMMENT (stars, Location.curr lexbuf) }
| "*)"
{ let loc = Location.curr lexbuf in
Location.prerr_warning loc Warnings.Comment_not_end;
lexbuf.Lexing.lex_curr_pos <- lexbuf.Lexing.lex_curr_pos - 1;
let curpos = lexbuf.lex_curr_p in
lexbuf.lex_curr_p <- { curpos with pos_cnum = curpos.pos_cnum - 1 };
STAR
}
| "#"
{ let at_beginning_of_line pos = (pos.pos_cnum = pos.pos_bol) in
if not (at_beginning_of_line lexbuf.lex_start_p)
then HASH
else try directive lexbuf with Failure _ -> HASH
}
| "&" { AMPERSAND }
| "&&" { AMPERAMPER }
| "`" { BACKQUOTE }
| "\'" { QUOTE }
| "(" { LPAREN }
| ")" { RPAREN }
| "*" { STAR }
| "," { COMMA }
| "->" { MINUSGREATER }
| "." { DOT }
| ".." { DOTDOT }
| "." (dotsymbolchar symbolchar* as s) { DOTOP s }
| ":" { COLON }
| "::" { COLONCOLON }
| ":=" { COLONEQUAL }
| ":>" { COLONGREATER }
| ";" { SEMI }
| ";;" { SEMISEMI }
| "<" { LESS }
| "<-" { LESSMINUS }
| "=" { EQUAL }
| "[" { LBRACKET }
| "[|" { LBRACKETBAR }
| "[<" { LBRACKETLESS }
| "[>" { LBRACKETGREATER }
| "]" { RBRACKET }
| "{" { LBRACE }
| "{<" { LBRACELESS }
| "|" { BAR }
| "||" { BARBAR }
| "|]" { BARRBRACKET }
| ">" { GREATER }
| ">]" { GREATERRBRACKET }
| "}" { RBRACE }
| ">}" { GREATERRBRACE }
| "[@" { LBRACKETAT }
| "[@@" { LBRACKETATAT }
| "[@@@" { LBRACKETATATAT }
| "[%" { LBRACKETPERCENT }
| "[%%" { LBRACKETPERCENTPERCENT }
| "!" { BANG }
| "!=" { INFIXOP0 "!=" }
| "+" { PLUS }
| "+." { PLUSDOT }
| "+=" { PLUSEQ }
| "-" { MINUS }
| "-." { MINUSDOT }
| "!" symbolchar +
{ PREFIXOP(Lexing.lexeme lexbuf) }
| ['~' '?'] symbolchar +
{ PREFIXOP(Lexing.lexeme lexbuf) }
| ['=' '<' '>' '|' '&' '$'] symbolchar *
{ INFIXOP0(Lexing.lexeme lexbuf) }
| ['@' '^'] symbolchar *
{ INFIXOP1(Lexing.lexeme lexbuf) }
| ['+' '-'] symbolchar *
{ INFIXOP2(Lexing.lexeme lexbuf) }
| "**" symbolchar *
{ INFIXOP4(Lexing.lexeme lexbuf) }
| '%' { PERCENT }
| ['*' '/' '%'] symbolchar *
{ INFIXOP3(Lexing.lexeme lexbuf) }
| '#' (symbolchar | '#') +
{ HASHOP(Lexing.lexeme lexbuf) }
| eof { EOF }
| _
{ raise (Error(Illegal_character (Lexing.lexeme_char lexbuf 0),
Location.curr lexbuf))
}
and directive = parse
| ([' ' '\t']* (['0'-'9']+ as num) [' ' '\t']*
("\"" ([^ '\010' '\013' '\"' ] * as name) "\"") as directive)
[^ '\010' '\013'] *
{
match int_of_string num with
| exception _ ->
(* PR#7165 *)
let loc = Location.curr lexbuf in
let explanation = "line number out of range" in
let error = Invalid_directive ("#" ^ directive, Some explanation) in
raise (Error (error, loc))
| line_num ->
(* Documentation says that the line number should be
positive, but we have never guarded against this and it
might have useful hackish uses. *)
update_loc lexbuf (Some name) (line_num - 1) true 0;
token lexbuf
}
and comment = parse
"(*"
{ comment_start_loc := (Location.curr lexbuf) :: !comment_start_loc;
store_lexeme lexbuf;
comment lexbuf
}
| "*)"
{ match !comment_start_loc with
| [] -> assert false
| [_] -> comment_start_loc := []; Location.curr lexbuf
| _ :: l -> comment_start_loc := l;
store_lexeme lexbuf;
comment lexbuf
}
| "\""
{
string_start_loc := Location.curr lexbuf;
store_string_char '\"';
is_in_string := true;
begin try string lexbuf
with Error (Unterminated_string, str_start) ->
match !comment_start_loc with
| [] -> assert false
| loc :: _ ->
let start = List.hd (List.rev !comment_start_loc) in
comment_start_loc := [];
raise (Error (Unterminated_string_in_comment (start, str_start),
loc))
end;
is_in_string := false;
store_string_char '\"';
comment lexbuf }
| "{" lowercase* "|"
{
let delim = Lexing.lexeme lexbuf in
let delim = String.sub delim 1 (String.length delim - 2) in
string_start_loc := Location.curr lexbuf;
store_lexeme lexbuf;
is_in_string := true;
begin try quoted_string delim lexbuf
with Error (Unterminated_string, str_start) ->
match !comment_start_loc with
| [] -> assert false
| loc :: _ ->
let start = List.hd (List.rev !comment_start_loc) in
comment_start_loc := [];
raise (Error (Unterminated_string_in_comment (start, str_start),
loc))
end;
is_in_string := false;
store_string_char '|';
store_string delim;
store_string_char '}';
comment lexbuf }
| "\'\'"
{ store_lexeme lexbuf; comment lexbuf }
| "\'" newline "\'"
{ update_loc lexbuf None 1 false 1;
store_lexeme lexbuf;
comment lexbuf
}
| "\'" [^ '\\' '\'' '\010' '\013' ] "\'"
{ store_lexeme lexbuf; comment lexbuf }
| "\'\\" ['\\' '\"' '\'' 'n' 't' 'b' 'r' ' '] "\'"
{ store_lexeme lexbuf; comment lexbuf }
| "\'\\" ['0'-'9'] ['0'-'9'] ['0'-'9'] "\'"
{ store_lexeme lexbuf; comment lexbuf }
| "\'\\" 'x' ['0'-'9' 'a'-'f' 'A'-'F'] ['0'-'9' 'a'-'f' 'A'-'F'] "\'"
{ store_lexeme lexbuf; comment lexbuf }
| eof
{ match !comment_start_loc with
| [] -> assert false
| loc :: _ ->
let start = List.hd (List.rev !comment_start_loc) in
comment_start_loc := [];
raise (Error (Unterminated_comment start, loc))
}
| newline
{ update_loc lexbuf None 1 false 0;
store_lexeme lexbuf;
comment lexbuf
}
| _
{ store_lexeme lexbuf; comment lexbuf }
and string = parse
'\"'
{ () }
| '\\' newline ([' ' '\t'] * as space)
{ update_loc lexbuf None 1 false (String.length space);
if in_comment () then store_lexeme lexbuf;
string lexbuf
}
| '\\' ['\\' '\'' '\"' 'n' 't' 'b' 'r' ' ']
{ store_escaped_char lexbuf
(char_for_backslash(Lexing.lexeme_char lexbuf 1));
string lexbuf }
| '\\' ['0'-'9'] ['0'-'9'] ['0'-'9']
{ store_escaped_char lexbuf (char_for_decimal_code lexbuf 1);
string lexbuf }
| '\\' 'o' ['0'-'3'] ['0'-'7'] ['0'-'7']
{ store_escaped_char lexbuf (char_for_octal_code lexbuf 2);
string lexbuf }
| '\\' 'x' ['0'-'9' 'a'-'f' 'A'-'F'] ['0'-'9' 'a'-'f' 'A'-'F']
{ store_escaped_char lexbuf (char_for_hexadecimal_code lexbuf 2);
string lexbuf }
| '\\' 'u' '{' hex_digit+ '}'
{ store_escaped_uchar lexbuf (uchar_for_uchar_escape lexbuf);
string lexbuf }
| '\\' _
{ if not (in_comment ()) then begin
(* Should be an error, but we are very lax.
raise (Error (Illegal_escape (Lexing.lexeme lexbuf),
Location.curr lexbuf))
*)
let loc = Location.curr lexbuf in
Location.prerr_warning loc Warnings.Illegal_backslash;
end;
store_lexeme lexbuf;
string lexbuf
}
| newline
{ if not (in_comment ()) then
Location.prerr_warning (Location.curr lexbuf) Warnings.Eol_in_string;
update_loc lexbuf None 1 false 0;
store_lexeme lexbuf;
string lexbuf
}
| eof
{ is_in_string := false;
raise (Error (Unterminated_string, !string_start_loc)) }
| _
{ store_string_char(Lexing.lexeme_char lexbuf 0);
string lexbuf }
and quoted_string delim = parse
| newline
{ update_loc lexbuf None 1 false 0;
store_lexeme lexbuf;
quoted_string delim lexbuf
}
| eof
{ is_in_string := false;
raise (Error (Unterminated_string, !string_start_loc)) }
| "|" lowercase* "}"
{
let edelim = Lexing.lexeme lexbuf in
let edelim = String.sub edelim 1 (String.length edelim - 2) in
if delim = edelim then ()
else (store_lexeme lexbuf; quoted_string delim lexbuf)
}
| _
{ store_string_char(Lexing.lexeme_char lexbuf 0);
quoted_string delim lexbuf }
and skip_hash_bang = parse
| "#!" [^ '\n']* '\n' [^ '\n']* "\n!#\n"
{ update_loc lexbuf None 3 false 0 }
| "#!" [^ '\n']* '\n'
{ update_loc lexbuf None 1 false 0 }
| "" { () }
{
let token_with_comments lexbuf =
match !preprocessor with
| None -> token lexbuf
| Some (_init, preprocess) -> preprocess token lexbuf
type newline_state =
| NoLine (* There have been no blank lines yet. *)
| NewLine
(* There have been no blank lines, and the previous
token was a newline. *)
| BlankLine (* There have been blank lines. *)
type doc_state =
| Initial (* There have been no docstrings yet *)
| After of docstring list
(* There have been docstrings, none of which were
preceded by a blank line *)
| Before of docstring list * docstring list * docstring list
(* There have been docstrings, some of which were
preceded by a blank line *)
and docstring = Docstrings.docstring
let token lexbuf =
let post_pos = lexeme_end_p lexbuf in
let attach lines docs pre_pos =
let open Docstrings in
match docs, lines with
| Initial, _ -> ()
| After a, (NoLine | NewLine) ->
set_post_docstrings post_pos (List.rev a);
set_pre_docstrings pre_pos a;
| After a, BlankLine ->
set_post_docstrings post_pos (List.rev a);
set_pre_extra_docstrings pre_pos (List.rev a)
| Before(a, f, b), (NoLine | NewLine) ->
set_post_docstrings post_pos (List.rev a);
set_post_extra_docstrings post_pos
(List.rev_append f (List.rev b));
set_floating_docstrings pre_pos (List.rev f);
set_pre_extra_docstrings pre_pos (List.rev a);
set_pre_docstrings pre_pos b
| Before(a, f, b), BlankLine ->
set_post_docstrings post_pos (List.rev a);
set_post_extra_docstrings post_pos
(List.rev_append f (List.rev b));
set_floating_docstrings pre_pos
(List.rev_append f (List.rev b));
set_pre_extra_docstrings pre_pos (List.rev a)
in
let rec loop lines docs lexbuf =
match token_with_comments lexbuf with
| COMMENT (s, loc) ->
add_comment (s, loc);
let lines' =
match lines with
| NoLine -> NoLine
| NewLine -> NoLine
| BlankLine -> BlankLine
in
loop lines' docs lexbuf
| EOL ->
let lines' =
match lines with
| NoLine -> NewLine
| NewLine -> BlankLine
| BlankLine -> BlankLine
in
loop lines' docs lexbuf
| DOCSTRING doc ->
Docstrings.register doc;
add_docstring_comment doc;
let docs' =
if Docstrings.docstring_body doc = "/*" then
match docs with
| Initial -> Before([], [doc], [])
| After a -> Before (a, [doc], [])
| Before(a, f, b) -> Before(a, doc :: b @ f, [])
else
match docs, lines with
| Initial, (NoLine | NewLine) -> After [doc]
| Initial, BlankLine -> Before([], [], [doc])
| After a, (NoLine | NewLine) -> After (doc :: a)
| After a, BlankLine -> Before (a, [], [doc])
| Before(a, f, b), (NoLine | NewLine) -> Before(a, f, doc :: b)
| Before(a, f, b), BlankLine -> Before(a, b @ f, [doc])
in
loop NoLine docs' lexbuf
| tok ->
attach lines docs (lexeme_start_p lexbuf);
tok
in
loop NoLine Initial lexbuf
let init () =
is_in_string := false;
comment_start_loc := [];
comment_list := [];
match !preprocessor with
| None -> ()
| Some (init, _preprocess) -> init ()
let set_preprocessor init preprocess =
escaped_newlines := true;
preprocessor := Some (init, preprocess)
}