aboutsummaryrefslogtreecommitdiff
path: root/gdb/ada-lex.l
blob: 93df2fba0f53792e7d62622dd5a2abaa0be3b79c (plain)
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
/* FLEX lexer for Ada expressions, for GDB.
   Copyright (C) 1994-2013 Free Software Foundation, Inc.

   This file is part of GDB.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */

/*----------------------------------------------------------------------*/

/* The converted version of this file is to be included in ada-exp.y, */
/* the Ada parser for gdb.  The function yylex obtains characters from */
/* the global pointer lexptr.  It returns a syntactic category for */
/* each successive token and places a semantic value into yylval */
/* (ada-lval), defined by the parser.   */

DIG	[0-9]
NUM10	({DIG}({DIG}|_)*)
HEXDIG	[0-9a-f]
NUM16	({HEXDIG}({HEXDIG}|_)*)
OCTDIG	[0-7]
LETTER	[a-z_]
ID	({LETTER}({LETTER}|{DIG})*|"<"{LETTER}({LETTER}|{DIG})*">")
WHITE	[ \t\n]
TICK	("'"{WHITE}*)
GRAPHIC [a-z0-9 #&'()*+,-./:;<>=_|!$%?@\[\]\\^`{}~]
OPER    ([-+*/=<>&]|"<="|">="|"**"|"/="|"and"|"or"|"xor"|"not"|"mod"|"rem"|"abs")

EXP	(e[+-]{NUM10})
POSEXP  (e"+"?{NUM10})

%{

#define NUMERAL_WIDTH 256
#define LONGEST_SIGN ((ULONGEST) 1 << (sizeof(LONGEST) * HOST_CHAR_BIT - 1))

/* Temporary staging for numeric literals.  */
static char numbuf[NUMERAL_WIDTH];
 static void canonicalizeNumeral (char *s1, const char *);
static struct stoken processString (const char*, int);
static int processInt (const char *, const char *, const char *);
static int processReal (const char *);
static struct stoken processId (const char *, int);
static int processAttribute (const char *);
static int find_dot_all (const char *);
static void rewind_to_char (int);

#undef YY_DECL
#define YY_DECL static int yylex ( void )

/* Flex generates a static function "input" which is not used.
   Defining YY_NO_INPUT comments it out.  */
#define YY_NO_INPUT

#undef YY_INPUT
#define YY_INPUT(BUF, RESULT, MAX_SIZE) \
    if ( *lexptr == '\000' ) \
      (RESULT) = YY_NULL; \
    else \
      { \
        *(BUF) = *lexptr; \
        (RESULT) = 1; \
	lexptr += 1; \
      }

static int find_dot_all (const char *);

%}

%option case-insensitive interactive nodefault

%s BEFORE_QUAL_QUOTE

%%

{WHITE}		 { }

"--".*		 { yyterminate(); }

{NUM10}{POSEXP}  {
		   canonicalizeNumeral (numbuf, yytext);
		   return processInt (NULL, numbuf, strrchr(numbuf, 'e')+1);
		 }

{NUM10}          {
		   canonicalizeNumeral (numbuf, yytext);
		   return processInt (NULL, numbuf, NULL);
		 }

{NUM10}"#"{HEXDIG}({HEXDIG}|_)*"#"{POSEXP} {
		   canonicalizeNumeral (numbuf, yytext);
    		   return processInt (numbuf,
				      strchr (numbuf, '#') + 1,
				      strrchr(numbuf, '#') + 1);
		 }

{NUM10}"#"{HEXDIG}({HEXDIG}|_)*"#" {
		   canonicalizeNumeral (numbuf, yytext);
    		   return processInt (numbuf, strchr (numbuf, '#') + 1, NULL);
		 }

"0x"{HEXDIG}+	{
		  canonicalizeNumeral (numbuf, yytext+2);
		  return processInt ("16#", numbuf, NULL);
		}


{NUM10}"."{NUM10}{EXP} {
		   canonicalizeNumeral (numbuf, yytext);
		   return processReal (numbuf);
		}

{NUM10}"."{NUM10} {
		   canonicalizeNumeral (numbuf, yytext);
		   return processReal (numbuf);
		}

{NUM10}"#"{NUM16}"."{NUM16}"#"{EXP} {
                   error (_("Based real literals not implemented yet."));
		}

{NUM10}"#"{NUM16}"."{NUM16}"#" {
                   error (_("Based real literals not implemented yet."));
		}

<INITIAL>"'"({GRAPHIC}|\")"'" {
		   yylval.typed_val.type = type_char ();
		   yylval.typed_val.val = yytext[1];
		   return CHARLIT;
		}

<INITIAL>"'[\""{HEXDIG}{2}"\"]'"   {
                   int v;
                   yylval.typed_val.type = type_char ();
		   sscanf (yytext+3, "%2x", &v);
		   yylval.typed_val.val = v;
		   return CHARLIT;
		}

\"({GRAPHIC}|"[\""({HEXDIG}{2}|\")"\"]")*\"   {
	           yylval.sval = processString (yytext+1, yyleng-2);
		   return STRING;
		}

\"              {
                   error (_("ill-formed or non-terminated string literal"));
		}


if		{
                  rewind_to_char ('i');
		  return 0;
		}

task            {
                  rewind_to_char ('t');
		  return 0;
		}

thread{WHITE}+{DIG} {
                  /* This keyword signals the end of the expression and
                     will be processed separately.  */
                  rewind_to_char ('t');
		  return 0;
		}

	/* ADA KEYWORDS */

abs		{ return ABS; }
and		{ return _AND_; }
else		{ return ELSE; }
in		{ return IN; }
mod		{ return MOD; }
new		{ return NEW; }
not		{ return NOT; }
null		{ return NULL_PTR; }
or		{ return OR; }
others          { return OTHERS; }
rem		{ return REM; }
then		{ return THEN; }
xor		{ return XOR; }

	/* BOOLEAN "KEYWORDS" */

 /* True and False are not keywords in Ada, but rather enumeration constants.
    However, the boolean type is no longer represented as an enum, so True
    and False are no longer defined in symbol tables.  We compromise by
    making them keywords (when bare). */

true		{ return TRUEKEYWORD; }
false		{ return FALSEKEYWORD; }

        /* ATTRIBUTES */

{TICK}[a-zA-Z][a-zA-Z]+ { return processAttribute (yytext+1); }

	/* PUNCTUATION */

"=>"		{ return ARROW; }
".."		{ return DOTDOT; }
"**"		{ return STARSTAR; }
":="		{ return ASSIGN; }
"/="		{ return NOTEQUAL; }
"<="		{ return LEQ; }
">="		{ return GEQ; }

<BEFORE_QUAL_QUOTE>"'" { BEGIN INITIAL; return '\''; }

[-&*+./:<>=|;\[\]] { return yytext[0]; }

","		{ if (paren_depth == 0 && comma_terminates)
		    {
		      rewind_to_char (',');
		      return 0;
		    }
		  else
		    return ',';
		}

"("		{ paren_depth += 1; return '('; }
")"		{ if (paren_depth == 0)
		    {
		      rewind_to_char (')');
		      return 0;
		    }
		  else
 		    {
		      paren_depth -= 1;
		      return ')';
		    }
		}

"."{WHITE}*all  { return DOT_ALL; }

"."{WHITE}*{ID} {
	 	  yylval.sval = processId (yytext+1, yyleng-1);
	          return DOT_ID;
		}

{ID}({WHITE}*"."{WHITE}*({ID}|\"{OPER}\"))*(" "*"'")?  {
                  int all_posn = find_dot_all (yytext);

                  if (all_posn == -1 && yytext[yyleng-1] == '\'')
		    {
		      BEGIN BEFORE_QUAL_QUOTE;
		      yyless (yyleng-1);
		    }
                  else if (all_posn >= 0)
		    yyless (all_posn);
                  yylval.sval = processId (yytext, yyleng);
                  return NAME;
               }


	/* GDB EXPRESSION CONSTRUCTS  */

"'"[^']+"'"{WHITE}*:: {
                  yyless (yyleng - 2);
		  yylval.sval = processId (yytext, yyleng);
		  return NAME;
		}

"::"            { return COLONCOLON; }

[{}@]		{ return yytext[0]; }

	/* REGISTERS AND GDB CONVENIENCE VARIABLES */

"$"({LETTER}|{DIG}|"$")*  {
		  yylval.sval.ptr = yytext;
		  yylval.sval.length = yyleng;
		  return SPECIAL_VARIABLE;
		}

	/* CATCH-ALL ERROR CASE */

.		{ error (_("Invalid character '%s' in expression."), yytext); }
%%

#include <ctype.h>
#include "gdb_string.h"

/* Initialize the lexer for processing new expression. */

static void
lexer_init (FILE *inp)
{
  BEGIN INITIAL;
  yyrestart (inp);
}


/* Copy S2 to S1, removing all underscores, and downcasing all letters.  */

static void
canonicalizeNumeral (char *s1, const char *s2)
{
  for (; *s2 != '\000'; s2 += 1)
    {
      if (*s2 != '_')
	{
	  *s1 = tolower(*s2);
	  s1 += 1;
	}
    }
  s1[0] = '\000';
}

/* Interprets the prefix of NUM that consists of digits of the given BASE
   as an integer of that BASE, with the string EXP as an exponent.
   Puts value in yylval, and returns INT, if the string is valid.  Causes
   an error if the number is improperly formated.   BASE, if NULL, defaults
   to "10", and EXP to "1".  The EXP does not contain a leading 'e' or 'E'.
 */

static int
processInt (const char *base0, const char *num0, const char *exp0)
{
  ULONGEST result;
  long exp;
  int base;
  const char *trailer;

  if (base0 == NULL)
    base = 10;
  else
    {
      base = strtol (base0, (char **) NULL, 10);
      if (base < 2 || base > 16)
	error (_("Invalid base: %d."), base);
    }

  if (exp0 == NULL)
    exp = 0;
  else
    exp = strtol(exp0, (char **) NULL, 10);

  errno = 0;
  result = strtoulst (num0, &trailer, base);
  if (errno == ERANGE)
    error (_("Integer literal out of range"));
  if (isxdigit(*trailer))
    error (_("Invalid digit `%c' in based literal"), *trailer);

  while (exp > 0)
    {
      if (result > (ULONG_MAX / base))
	error (_("Integer literal out of range"));
      result *= base;
      exp -= 1;
    }

  if ((result >> (gdbarch_int_bit (parse_gdbarch)-1)) == 0)
    yylval.typed_val.type = type_int ();
  else if ((result >> (gdbarch_long_bit (parse_gdbarch)-1)) == 0)
    yylval.typed_val.type = type_long ();
  else if (((result >> (gdbarch_long_bit (parse_gdbarch)-1)) >> 1) == 0)
    {
      /* We have a number representable as an unsigned integer quantity.
         For consistency with the C treatment, we will treat it as an
	 anonymous modular (unsigned) quantity.  Alas, the types are such
	 that we need to store .val as a signed quantity.  Sorry
         for the mess, but C doesn't officially guarantee that a simple
         assignment does the trick (no, it doesn't; read the reference manual).
       */
      yylval.typed_val.type
	= builtin_type (parse_gdbarch)->builtin_unsigned_long;
      if (result & LONGEST_SIGN)
	yylval.typed_val.val =
	  (LONGEST) (result & ~LONGEST_SIGN)
	  - (LONGEST_SIGN>>1) - (LONGEST_SIGN>>1);
      else
	yylval.typed_val.val = (LONGEST) result;
      return INT;
    }
  else
    yylval.typed_val.type = type_long_long ();

  yylval.typed_val.val = (LONGEST) result;
  return INT;
}

static int
processReal (const char *num0)
{
  sscanf (num0, "%" DOUBLEST_SCAN_FORMAT, &yylval.typed_val_float.dval);

  yylval.typed_val_float.type = type_float ();
  if (sizeof(DOUBLEST) >= gdbarch_double_bit (parse_gdbarch)
			    / TARGET_CHAR_BIT)
    yylval.typed_val_float.type = type_double ();
  if (sizeof(DOUBLEST) >= gdbarch_long_double_bit (parse_gdbarch)
			    / TARGET_CHAR_BIT)
    yylval.typed_val_float.type = type_long_double ();

  return FLOAT;
}


/* Store a canonicalized version of NAME0[0..LEN-1] in yylval.ssym.  The
   resulting string is valid until the next call to ada_parse.  If
   NAME0 contains the substring "___", it is assumed to be already
   encoded and the resulting name is equal to it.  Otherwise, it differs
   from NAME0 in that:
    + Characters between '...' or <...> are transfered verbatim to 
      yylval.ssym.
    + <, >, and trailing "'" characters in quoted sequences are removed
      (a leading quote is preserved to indicate that the name is not to be
      GNAT-encoded).
    + Unquoted whitespace is removed.
    + Unquoted alphabetic characters are mapped to lower case.
   Result is returned as a struct stoken, but for convenience, the string
   is also null-terminated.  Result string valid until the next call of
   ada_parse.
 */
static struct stoken
processId (const char *name0, int len)
{
  char *name = obstack_alloc (&temp_parse_space, len + 11);
  int i0, i;
  struct stoken result;

  result.ptr = name;
  while (len > 0 && isspace (name0[len-1]))
    len -= 1;

  if (strstr (name0, "___") != NULL)
    {
      strncpy (name, name0, len);
      name[len] = '\000';
      result.length = len;
      return result;
    }

  i = i0 = 0;
  while (i0 < len)
    {
      if (isalnum (name0[i0]))
	{
	  name[i] = tolower (name0[i0]);
	  i += 1; i0 += 1;
	}
      else switch (name0[i0])
	{
	default:
	  name[i] = name0[i0];
	  i += 1; i0 += 1;
	  break;
	case ' ': case '\t':
	  i0 += 1;
	  break;
	case '\'':
	  do
	    {
	      name[i] = name0[i0];
	      i += 1; i0 += 1;
	    }
	  while (i0 < len && name0[i0] != '\'');
	  i0 += 1;
	  break;
	case '<':
	  i0 += 1;
	  while (i0 < len && name0[i0] != '>')
	    {
	      name[i] = name0[i0];
	      i += 1; i0 += 1;
	    }
	  i0 += 1;
	  break;
	}
    }
  name[i] = '\000';

  result.length = i;
  return result;
}

/* Return TEXT[0..LEN-1], a string literal without surrounding quotes,
   with special hex character notations replaced with characters. 
   Result valid until the next call to ada_parse.  */

static struct stoken
processString (const char *text, int len)
{
  const char *p;
  char *q;
  const char *lim = text + len;
  struct stoken result;

  q = result.ptr = obstack_alloc (&temp_parse_space, len);
  p = text;
  while (p < lim)
    {
      if (p[0] == '[' && p[1] == '"' && p+2 < lim)
         {
           if (p[2] == '"')  /* "...["""]... */
             {
               *q = '"';
	       p += 4;
	     }
           else
	     {
               int chr;
	       sscanf (p+2, "%2x", &chr);
	       *q = (char) chr;
	       p += 5;
	     }
         }
       else
         *q = *p;
       q += 1;
       p += 1;
     }
  result.length = q - result.ptr;
  return result;
}

/* Returns the position within STR of the '.' in a
   '.{WHITE}*all' component of a dotted name, or -1 if there is none.
   Note: we actually don't need this routine, since 'all' can never be an
   Ada identifier.  Thus, looking up foo.all or foo.all.x as a name
   must fail, and will eventually be interpreted as (foo).all or
   (foo).all.x.  However, this does avoid an extraneous lookup. */

static int
find_dot_all (const char *str)
{
  int i;
  for (i = 0; str[i] != '\000'; i += 1)
    {
      if (str[i] == '.')
	{
	  int i0 = i;
	  do
	    i += 1;
	  while (isspace (str[i]));
	  if (strncmp (str+i, "all", 3) == 0
	      && ! isalnum (str[i+3]) && str[i+3] != '_')
	    return i0;
	}
    }
  return -1;
}

/* Returns non-zero iff string SUBSEQ matches a subsequence of STR, ignoring
   case.  */

static int
subseqMatch (const char *subseq, const char *str)
{
  if (subseq[0] == '\0')
    return 1;
  else if (str[0] == '\0')
    return 0;
  else if (tolower (subseq[0]) == tolower (str[0]))
    return subseqMatch (subseq+1, str+1) || subseqMatch (subseq, str+1);
  else
    return subseqMatch (subseq, str+1);
}


static struct { const char *name; int code; }
attributes[] = {
  { "address", TICK_ADDRESS },
  { "unchecked_access", TICK_ACCESS },
  { "unrestricted_access", TICK_ACCESS },
  { "access", TICK_ACCESS },
  { "first", TICK_FIRST },
  { "last", TICK_LAST },
  { "length", TICK_LENGTH },
  { "max", TICK_MAX },
  { "min", TICK_MIN },
  { "modulus", TICK_MODULUS },
  { "pos", TICK_POS },
  { "range", TICK_RANGE },
  { "size", TICK_SIZE },
  { "tag", TICK_TAG },
  { "val", TICK_VAL },
  { NULL, -1 }
};

/* Return the syntactic code corresponding to the attribute name or
   abbreviation STR.  */

static int
processAttribute (const char *str)
{
  int i, k;

  for (i = 0; attributes[i].code != -1; i += 1)
    if (strcasecmp (str, attributes[i].name) == 0)
      return attributes[i].code;

  for (i = 0, k = -1; attributes[i].code != -1; i += 1)
    if (subseqMatch (str, attributes[i].name))
      {
	if (k == -1)
	  k = i;
	else
	  error (_("ambiguous attribute name: `%s'"), str);
      }
  if (k == -1)
    error (_("unrecognized attribute: `%s'"), str);

  return attributes[k].code;
}

/* Back up lexptr by yyleng and then to the rightmost occurrence of
   character CH, case-folded (there must be one).  WARNING: since
   lexptr points to the next input character that Flex has not yet
   transferred to its internal buffer, the use of this function
   depends on the assumption that Flex calls YY_INPUT only when it is
   logically necessary to do so (thus, there is no reading ahead
   farther than needed to identify the next token.)  */

static void
rewind_to_char (int ch)
{
  lexptr -= yyleng;
  while (toupper (*lexptr) != toupper (ch))
    lexptr -= 1;
  yyrestart (NULL);
}

int
yywrap(void)
{
  return 1;
}

/* Dummy definition to suppress warnings about unused static definitions. */
typedef void (*dummy_function) ();
dummy_function ada_flex_use[] = 
{ 
  (dummy_function) yyunput
};