Source

compiler-libs-hack / ocaml / parsing / lexer.mll

Full commit
  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
(***********************************************************************)
(*                                                                     *)
(*                                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 Q Public License version 1.0.               *)
(*                                                                     *)
(***********************************************************************)

(* 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
  | Keyword_as_label of string
  | Literal_overflow of string
;;

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;
    "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;

    "mod", INFIXOP3("mod");
    "land", INFIXOP3("land");
    "lor", INFIXOP3("lor");
    "lxor", INFIXOP3("lxor");
    "lsl", INFIXOP4("lsl");
    "lsr", INFIXOP4("lsr");
    "asr", INFIXOP4("asr")
]

(* To buffer string literals *)

let initial_string_buffer = String.create 256
let string_buff = ref initial_string_buffer
let string_index = ref 0

let reset_string_buffer () =
  string_buff := initial_string_buffer;
  string_index := 0

let store_string_char c =
  if !string_index >= String.length (!string_buff) then begin
    let new_buff = String.create (String.length (!string_buff) * 2) in
      String.blit (!string_buff) 0 new_buff 0 (String.length (!string_buff));
      string_buff := new_buff
  end;
  String.unsafe_set (!string_buff) (!string_index) c;
  incr string_index

let store_lexeme lexbuf =
  let s = Lexing.lexeme lexbuf in
  for i = 0 to String.length s - 1 do
    store_string_char s.[i];
  done

let get_stored_string () =
  let s = String.sub (!string_buff) 0 (!string_index) in
  string_buff := initial_string_buffer;
  s

(* 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

(* To translate escape sequences *)

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_hexadecimal_code lexbuf i =
  let d1 = Char.code (Lexing.lexeme_char lexbuf i) in
  let val1 = if d1 >= 97 then d1 - 87
             else if d1 >= 65 then d1 - 55
             else d1 - 48
  in
  let d2 = Char.code (Lexing.lexeme_char lexbuf (i+1)) in
  let val2 = if d2 >= 97 then d2 - 87
             else if d2 >= 65 then d2 - 55
             else d2 - 48
  in
  Char.chr (val1 * 16 + val2)

(* To convert integer literals, allowing max_int + 1 (PR#4210) *)

let cvt_int_literal s =
  - int_of_string ("-" ^ s)
let cvt_int32_literal s =
  Int32.neg (Int32.of_string ("-" ^ String.sub s 0 (String.length s - 1)))
let cvt_int64_literal s =
  Int64.neg (Int64.of_string ("-" ^ String.sub s 0 (String.length s - 1)))
let cvt_nativeint_literal s =
  Nativeint.neg (Nativeint.of_string ("-" ^ String.sub s 0
                                                       (String.length s - 1)))

(* Remove underscores from float literals *)

let remove_underscores s =
  let l = String.length s in
  let rec remove src dst =
    if src >= l then
      if dst >= l then s else String.sub s 0 dst
    else
      match s.[src] with
        '_' -> remove (src + 1) dst
      |  c  -> s.[dst] <- c; remove (src + 1) (dst + 1)
  in remove 0 0

(* 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;
  }
;;

(* Warn about Latin-1 characters used in idents *)

let warn_latin1 lexbuf =
  Location.prerr_warning (Location.curr lexbuf)
    (Warnings.Deprecated "ISO-Latin1 characters in identifiers")
;;

(* 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 _ ->
      fprintf ppf "This comment contains an unterminated string literal"
  | Keyword_as_label kwd ->
      fprintf ppf "`%s' is a keyword, it cannot be used as label name" kwd
  | Literal_overflow ty ->
      fprintf ppf "Integer literal exceeds the range of representable \
                   integers of type %s" ty
;;

}

let newline = ('\010' | "\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 decimal_literal =
  ['0'-'9'] ['0'-'9' '_']*
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' '_']*)?

rule token = parse
  | newline
      { update_loc lexbuf None 1 false 0;
        token lexbuf
      }
  | 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
      { try
          INT (cvt_int_literal (Lexing.lexeme lexbuf))
        with Failure _ ->
          raise (Error(Literal_overflow "int", Location.curr lexbuf))
      }
  | float_literal
      { FLOAT (remove_underscores(Lexing.lexeme lexbuf)) }
  | int_literal "l"
      { try
          INT32 (cvt_int32_literal (Lexing.lexeme lexbuf))
        with Failure _ ->
          raise (Error(Literal_overflow "int32", Location.curr lexbuf)) }
  | int_literal "L"
      { try
          INT64 (cvt_int64_literal (Lexing.lexeme lexbuf))
        with Failure _ ->
          raise (Error(Literal_overflow "int64", Location.curr lexbuf)) }
  | int_literal "n"
      { try
          NATIVEINT (cvt_nativeint_literal (Lexing.lexeme lexbuf))
        with Failure _ ->
          raise (Error(Literal_overflow "nativeint", 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()) }
  | "'" 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) }
  | "'\\" '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 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 ();
        COMMENT (s, { start_loc with
                      Location.loc_end = end_loc.Location.loc_end })
      }
  | "(*)"
      { let loc = Location.curr lexbuf  in
        if !print_warnings then
          Location.prerr_warning loc Warnings.Comment_start;
        comment_start_loc := [loc];
        reset_string_buffer ();
        let end_loc = comment lexbuf in
        let s = get_stored_string () in
        reset_string_buffer ();
        COMMENT (s, { loc with Location.loc_end = end_loc.Location.loc_end })
      }
  | "*)"
      { 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
      }
  | "#" [' ' '\t']* (['0'-'9']+ as num) [' ' '\t']*
        ("\"" ([^ '\010' '\013' '"' ] * as name) "\"")?
        [^ '\010' '\013'] * newline
      { update_loc lexbuf name (int_of_string num) true 0;
        token lexbuf
      }
  | "#"  { SHARP }
  | "&"  { AMPERSAND }
  | "&&" { AMPERAMPER }
  | "`"  { BACKQUOTE }
  | "'"  { QUOTE }
  | "("  { LPAREN }
  | ")"  { RPAREN }
  | "*"  { STAR }
  | ","  { COMMA }
  | "->" { MINUSGREATER }
  | "."  { DOT }
  | ".." { DOTDOT }
  | ":"  { COLON }
  | "::" { COLONCOLON }
  | ":=" { COLONEQUAL }
  | ":>" { COLONGREATER }
  | ";"  { SEMI }
  | ";;" { SEMISEMI }
  | "<"  { LESS }
  | "<-" { LESSMINUS }
  | "="  { EQUAL }
  | "["  { LBRACKET }
  | "[|" { LBRACKETBAR }
  | "[<" { LBRACKETLESS }
  | "[>" { LBRACKETGREATER }
  | "]"  { RBRACKET }
  | "{"  { LBRACE }
  | "{<" { LBRACELESS }
  | "|"  { BAR }
  | "||" { BARBAR }
  | "|]" { BARRBRACKET }
  | ">"  { GREATER }
  | ">]" { GREATERRBRACKET }
  | "}"  { RBRACE }
  | ">}" { GREATERRBRACE }
  | "!"  { BANG }

  | "!=" { INFIXOP0 "!=" }
  | "+"  { PLUS }
  | "+." { PLUSDOT }
  | "-"  { 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) }
  | ['*' '/' '%'] symbolchar *
            { INFIXOP3(Lexing.lexeme lexbuf) }
  | eof { EOF }
  | _
      { raise (Error(Illegal_character (Lexing.lexeme_char lexbuf 0),
                     Location.curr 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, _) ->
          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, loc))
        end;
        is_in_string := false;
        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);
        string lexbuf
      }
  | '\\' ['\\' '\'' '"' 'n' 't' 'b' 'r' ' ']
      { store_string_char(char_for_backslash(Lexing.lexeme_char lexbuf 1));
        string lexbuf }
  | '\\' ['0'-'9'] ['0'-'9'] ['0'-'9']
      { store_string_char(char_for_decimal_code lexbuf 1);
         string lexbuf }
  | '\\' 'x' ['0'-'9' 'a'-'f' 'A'-'F'] ['0'-'9' 'a'-'f' 'A'-'F']
      { store_string_char(char_for_hexadecimal_code lexbuf 2);
         string lexbuf }
  | '\\' _
      { if in_comment ()
        then string lexbuf
        else 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;
          store_string_char (Lexing.lexeme_char lexbuf 0);
          store_string_char (Lexing.lexeme_char lexbuf 1);
          string lexbuf
        end
      }
  | 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 skip_sharp_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 = token

  let last_comments = ref []
  let rec token lexbuf =
    match token_with_comments lexbuf with
        COMMENT (s, comment_loc) ->
          last_comments := (s, comment_loc) :: !last_comments;
          token lexbuf
      | tok -> tok
  let comments () = List.rev !last_comments
  let init () =
    is_in_string := false;
    last_comments := [];
    comment_start_loc := []

}