aboutsummaryrefslogtreecommitdiff
path: root/ld/ldlex.l
blob: 82f6659ca280e601d934cbaeb238acfdd3c9f479 (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
%{
/* Copyright (C) 1991 Free Software Foundation, Inc.

This file is part of GLD, the Gnu Linker.

GLD 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 1, or (at your option)
any later version.

GLD 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 GLD; see the file COPYING.  If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.  */

/*
 *  $Id$ 

 *
*/



/*SUPPRESS 529*/
/*SUPPRESS 26*/
/*SUPPRESS 29*/
#define LEXDEBUG 0
#include "sysdep.h"
#include "bfd.h"

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

#include "ld.h"
#include "ldexp.h"
#include "ldgram.tab.h"
#include "ldmisc.h"

#undef input
#undef unput
#define input lex_input
#define unput lex_unput
int debug;

extern boolean ldgram_in_expression;
extern boolean ldgram_in_defsym;
extern boolean ldgram_in_script;
static char *command_line;

extern int fgetc();
extern int yyparse();

typedef struct {
	char *name;	
int value;
} keyword_type;
#define RTOKEN(x)  {  yylval.token = x; return x; }
keyword_type keywords[] = 
{
"MEMORY",MEMORY,
"ORIGIN",ORIGIN,
"BLOCK",BLOCK,
"LENGTH",LENGTH,
"ALIGN",ALIGN_K,
"SUBSECTION_ALIGN",SUBSECTION_ALIGN,
"ADDR",ADDR,
"ENTRY",ENTRY,
"SCRIPT", SCRIPT,
"ENDSCRIPT", ENDSCRIPT,
"NEXT",NEXT,
"MAP",MAP,
"SIZEOF",SIZEOF,
"TARGET",TARGET_K,
"SEARCH_DIR",SEARCH_DIR,
"OUTPUT",OUTPUT,
"INPUT",INPUT,
"DEFINED",DEFINED,
"CREATE_OBJECT_SYMBOLS",CREATE_OBJECT_SYMBOLS,
"FORCE_COMMON_ALLOCATION",FORCE_COMMON_ALLOCATION,
"SECTIONS",SECTIONS,
"FILL",FILL,
"STARTUP",STARTUP,
"OUTPUT_FORMAT",OUTPUT_FORMAT,
"HLL",HLL,
"SYSLIB",SYSLIB,
"FLOAT",FLOAT,
"LONG", LONG,
"SHORT", SHORT,
"BYTE", BYTE,
"NOFLOAT",NOFLOAT,
"o",ORIGIN,
"org",ORIGIN,
"l", LENGTH,
"len", LENGTH,
0,0};
unsigned int lineno;
extern boolean hex_mode;
FILE *ldlex_input_stack;
static unsigned int have_pushback;
#define NPUSHBACK 10
int pushback[NPUSHBACK];
int thischar;
extern char *ldfile_input_filename;
int donehash = 0;
int
lex_input()
{
  if (have_pushback > 0) 
      {
	have_pushback --;
	return thischar = pushback[have_pushback];
      }
  if (ldlex_input_stack) {
    thischar = fgetc(ldlex_input_stack);

    if (thischar == EOF)  {
      fclose(ldlex_input_stack);
      ldlex_input_stack = (FILE *)NULL;
      ldfile_input_filename = (char *)NULL;
      /* First char after script eof is a @ so that we can tell the grammer
	 that we've eft */
      thischar = '@';

    }
  }
  else if (command_line && *command_line)  {
    thischar = *(command_line++);
  }
  else {
 thischar = 0;
  }
  if(thischar == '\t') thischar = ' ';
  if (thischar == '\n') { thischar = ' '; lineno++; }
  return thischar ;
}

void
lex_unput(c)
int c;
{
  if (have_pushback > NPUSHBACK) {
    info("%F%P Too many pushbacks\n");
  }

  pushback[have_pushback] = c;
  have_pushback ++;
}


	int
yywrap()
	 { return 1; }
/*VARARGS*/

void
allprint(x) 
int x;
{
fprintf(yyout,"%d",x);
}

void
sprint(x) 
char *x;
{
fprintf(yyout,"%s",x);
}

int  thischar;

void parse_line(arg)
char *arg;
{
  command_line = arg;
  have_pushback = 0;
  yyparse();
}



void
parse_args(ac, av)
int ac;
char **av;
{
  char *p;
  int i;
  size_t size = 0;
  char *dst;
  debug = 1;
  for (i= 1; i < ac; i++) {
    size += strlen(av[i]) + 2; 
  }
  dst = p = (char *)ldmalloc(size + 2);
/* Put a space arount each option */


  for (i =1; i < ac; i++) {

    unsigned int s = strlen(av[i]);
  *dst++ = ' ';
    memcpy(dst, av[i], s);
    dst[s] = ' ';
    dst += s + 1;
  }
  *dst	= 0;
  parse_line(p);

  free(p);


}

long number(text, base)
char *text;
int base;
{
  unsigned  long l = 0;
  char *p;
  for (p = text; *p != 0; p++) {
    if (*p == 'K') {
      l =l * 1024;
    }
    else if(*p== 'M') {
      l =l * 1024 * 1024;
    }
    else {
      l =l * base;
      if (isdigit(*p))  {
	l += *p - '0';
      }
      else if (islower(*p)) {
	l += *p - 'a' + 10;
      }
      else {
	l += *p - 'A' + 10;
      }
    }
  }
  return l;
}
%}

%a 4000
%o 5000
FILENAMECHAR	[a-zA-Z0-9\/\.\-\_\+\=]
FILENAME	{FILENAMECHAR}+


WHITE		[ \t]+

%%

"@" { return ENDSCRIPT; }
"\ -defsym\ " { return OPTION_defsym; }
"\ -noinhibit_exec\ " { return OPTION_noinhibit_exec; }
"\ -format\ " { return OPTION_format; }
"\ -n\ "		{ return OPTION_n; }
"\ -r\ "		{ return OPTION_r; }
"\ -Ur\ "		{ return OPTION_Ur; }
"\ -o\ "		{ return OPTION_o; }
"\ -g\ "		{ return OPTION_g; }
"\ -e\ "		{ return OPTION_e; }
"\ -b\ "		{ return OPTION_b; }
"\ -dc\ "		{ return OPTION_dc; }
"\ -dp\ "		{ return OPTION_dp; }
"\ -d\ "		{ return OPTION_d; }
"\ -v\ "		{ return OPTION_v; }
"\ -M\ "		{ return OPTION_M; }
"\ -t\ "		{ return OPTION_t; }
"\ -X\ "		{ return OPTION_X; }
"\ -x\ "		{ return OPTION_x; }
"\ -c\ "		{ return OPTION_c; }
"\ -R\ "		{ return OPTION_R; }
"\ -u\ "		{ return OPTION_u; }
"\ -s\ "            { return OPTION_s; }
"\ -S\ "            { return OPTION_S; }
"\ -l"{FILENAME} {
	 	yylval.name = buystring(yytext+3);
		return OPTION_l; 
	}

"\ -L"{FILENAME} 	{ 
		yylval.name = buystring(yytext+3);
	 	return OPTION_L; 
	 }
"\ -Ttext\ "  {
		 yylval.name = ".text";
		 return OPTION_Texp;
	       }
"\ -Tdata\ "  {
		 yylval.name = ".data";
		 return OPTION_Texp;
	       }
"\ -Tbss\ "  {
		 yylval.name = ".bss";
		 return OPTION_Texp;
	       }

"\ -T"{FILENAME}  {
		 yylval.name = buystring(yytext+3);
		 return OPTION_Tfile;
	       }
"\ -T\ "          {
		 return OPTION_T;
	       }

"\ -F"{FILENAME}  {
		 return OPTION_F;
	       }
"\ -F\ "          {
		 return OPTION_F;
	       }

"\ -A"{FILENAME} {
                 yylval.name = buystring(yytext+3);
		 return OPTION_Aarch;
	       }
" " { }
"<<="		{ RTOKEN(LSHIFTEQ);}
">>="		{ RTOKEN(RSHIFTEQ);}
"||"		{ RTOKEN(OROR);}
"=="		{ RTOKEN(EQ);}
"!="		{ RTOKEN(NE);}
">="		{ RTOKEN(GE);}
"<="		{ RTOKEN(LE);}
"<<"		{ RTOKEN(LSHIFT);}
">>"		{ RTOKEN(RSHIFT);}
"+="		{ RTOKEN(PLUSEQ);}
"-="		{ RTOKEN(MINUSEQ);}
"*="		{ RTOKEN(MULTEQ);}
"/="		{ RTOKEN(DIVEQ);}
"&="		{ RTOKEN(ANDEQ);}
"|="		{ RTOKEN(OREQ);}
"&&"		{ RTOKEN(ANDAND);}
">"		{ RTOKEN('>');}
","		{ RTOKEN(',');}
"&"		{ RTOKEN('&');}
"|"		{ RTOKEN('|');}
"~"		{ RTOKEN('~');}
"!"		{ RTOKEN('!');}
"?"		{ RTOKEN('?');}
"*"		{ RTOKEN('*');}
"%"		{ RTOKEN('%');}
"<"		{ RTOKEN('<');}
">"		{ RTOKEN('>');}
"}"		{ RTOKEN('}') ; }
"{"		{ RTOKEN('{'); }
")"		{ RTOKEN(')');}
"("		{ RTOKEN('(');}
"]"		{ RTOKEN(']');}
"["		{ RTOKEN('[');}
":"		{ RTOKEN(':'); }
";"		{ RTOKEN('\;');}
"-"		{ RTOKEN('-');}



"/*"		{ 
  while (1) {
    int ch;
    ch = input();
    while (ch != '*') {
      ch = input();
    }



    if (input() == '/') {
      break;
    }
    unput(yytext[yyleng-1]);
  }
}

"\""[^\"]*"\"" {

  yylval.name = buystring(yytext+1);
  yylval.name[yyleng-2] = 0; /* Fry final quote */
  return NAME;
}
[0][0-7KM]* {

  yylval.integer = number(yytext+1, 8);
 return INT;
}

[0-9]+[KM]? {
  if (hex_mode == true || ldgram_in_defsym == true) {
    yylval.integer = number(yytext, 16);
  }
  else {
    yylval.integer = number(yytext, 10);
  }
  return INT;
}

0[Xx][0-9a-fA-FKM]+ {
 
  yylval.integer = number(yytext+2,16);	
  return INT;
}

"\#"{WHITE}*{FILENAMECHAR}+ {
  char *p = yytext+1;
  while(*p ==' ' || *p == '\t') p++;
  yylval.name = buystring(p);
  return NAME;
}
{FILENAMECHAR} {

  boolean loop = false;
  /*
    Tokenize a name, this is really pain, since a name can be a
    filename or a symbol name. filenames have slashes and stuff whist
    in an expression those things are seperate tokens. We hack this by
    setting ldlang_in_script when we are expecting a symbol, so that
    [/+-] get taken to be seperate tokens. An extra gotcha is
    expressions after defsyms, we only allow +s and -s in a defsym
    expression, so -defsym foo=bar+9 /file.o is parsed ok.
    
    The more I think about this the more I hate it. I've got a problem
    now with the = sign, what should I do ? imagine:
    __start=.;
    You'd think that was pretty unambiguous wouldn't you. Well it's
    not since __start=. is (at the moment) a perfectly valid
    filename. And in some cases we don't know what's going on. I'm
    going to have to hack this. If we see a '/' before the = sign then
    we say we've got an = in a filename, otherwise it's an operator.
    (later)
    That's it, I've had enough. From now on, an =s on a command line
    will be taken to be part of a file name unless its in a defsym,
    and an = in a file will be taken to be an operator.
    */
  int ch;
  keyword_type *k;

  if (hex_mode) {
    ch = yytext[0];
    /* Then always read a number */
    while (isxdigit(ch)) {
      yytext[yyleng++] = ch;
      ch = input();
    }
    yytext[yyleng] = 0;
    unput(ch);

    yylval.integer = number(yytext,16);
    return INT;
  }

  if (ldfile_input_filename) {
    /* We're inside a file */
    if (yytext[0]== '=') {
      RTOKEN('=');
    }
  }

    

    /* Otherwise we only notice special things if were in an
       expression */

  if (ldgram_in_expression) {
    if (yytext[0] != '/' ||  ldgram_in_defsym == false)  {
      switch (yytext[0]) {
      case '/': RTOKEN('/');
      case '=': RTOKEN('=');
      case '+': RTOKEN('+');
      case '-': RTOKEN('-');
      }
    }
  }

  ch = input();
  while (true)
      {
	if (isalpha(ch) || isdigit(ch) || ch == '.'  || ch == '_' ) {
	  yytext[yyleng++] = ch;
	}
else if (ch == '=' && ldgram_in_script) {
/* An = within a script is always taken to be an operator */
break;
}
	else if (ch == '+' || ch == '-' || ch == '/' || ch == '=') {
	  if (ldgram_in_expression) break;
	  yytext[yyleng++] = ch;
	}
	else 
	  break;
	ch = input();
      }

  yytext[yyleng] = 0;
  unput(ch);
  /* Filenames  of just =signs are tokens */
  if (yyleng == 1 && yytext[0] == '=') {
    RTOKEN('=');
  }
  for(k = keywords; k ->name != (char *)NULL; k++) {

    if (strcmp(k->name, yytext)==0) {
      yylval.token = k->value;
      return k->value;
    }
  }
  yylval.name = buystring(yytext);
  return NAME;
}





%%