aboutsummaryrefslogtreecommitdiff
path: root/locale/programs/linereader.c
blob: 01f5c9d6923e16184f5fb60473c86443ed4fab33 (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
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
810
811
812
813
814
815
816
/* Copyright (C) 1996, 1997, 1998, 1999, 2000 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Ulrich Drepper <drepper@gnu.org>, 1996.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public License as
   published by the Free Software Foundation; either version 2 of the
   License, or (at your option) any later version.

   The GNU C Library 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
   Library General Public License for more details.

   You should have received a copy of the GNU Library General Public
   License along with the GNU C Library; see the file COPYING.LIB.  If not,
   write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
   Boston, MA 02111-1307, USA.  */

#ifdef HAVE_CONFIG_H
# include <config.h>
#endif

#include <ctype.h>
#include <errno.h>
#include <libintl.h>
#include <stdarg.h>
#include <stdlib.h>
#include <string.h>

#include "charmap.h"
#include "error.h"
#include "linereader.h"
#include "localedef.h"


/* Prototypes for local functions.  */
static struct token *get_toplvl_escape (struct linereader *lr);
static struct token *get_symname (struct linereader *lr);
static struct token *get_ident (struct linereader *lr);
static struct token *get_string (struct linereader *lr,
				 const struct charmap_t *charmap,
				 const struct repertoire_t *repertoire);


struct linereader *
lr_open (const char *fname, kw_hash_fct_t hf)
{
  FILE *fp;

  if (fname == NULL || strcmp (fname, "-") == 0
      || strcmp (fname, "/dev/stdin") == 0)
    return lr_create (stdin, "<stdin>", hf);
  else
    {
      fp = fopen (fname, "r");
      if (fp == NULL)
	return NULL;
      return lr_create (fp, fname, hf);
    }
}

struct linereader *
lr_create (FILE *fp, const char *fname, kw_hash_fct_t hf)
{
  struct linereader *result;
  int n;

  result = (struct linereader *) xmalloc (sizeof (*result));

  result->fp = fp;
  result->fname = xstrdup (fname);
  result->buf = NULL;
  result->bufsize = 0;
  result->lineno = 1;
  result->idx = 0;
  result->comment_char = '#';
  result->escape_char = '\\';
  result->translate_strings = 1;

  n = getdelim (&result->buf, &result->bufsize, '\n', result->fp);
  if (n < 0)
    {
      int save = errno;
      fclose (result->fp);
      free ((char *) result->fname);
      free (result);
      errno = save;
      return NULL;
    }

  if (n > 1 && result->buf[n - 2] == '\\' && result->buf[n - 1] == '\n')
    n -= 2;

  result->buf[n] = '\0';
  result->bufact = n;
  result->hash_fct = hf;

  return result;
}


int
lr_eof (struct linereader *lr)
{
  return lr->bufact = 0;
}


void
lr_close (struct linereader *lr)
{
  fclose (lr->fp);
  free (lr->buf);
  free (lr);
}


int
lr_next (struct linereader *lr)
{
  int n;

  n = getdelim (&lr->buf, &lr->bufsize, '\n', lr->fp);
  if (n < 0)
    return -1;

  ++lr->lineno;

  if (n > 1 && lr->buf[n - 2] == lr->escape_char && lr->buf[n - 1] == '\n')
    {
#if 0
      /* XXX Is this correct?  */
      /* An escaped newline character is substituted with a single <SP>.  */
      --n;
      lr->buf[n - 1] = ' ';
#else
      n -= 2;
#endif
    }

  lr->buf[n] = '\0';
  lr->bufact = n;
  lr->idx = 0;

  return 0;
}


/* Defined in error.c.  */
/* This variable is incremented each time `error' is called.  */
extern unsigned int error_message_count;

/* The calling program should define program_name and set it to the
   name of the executing program.  */
extern char *program_name;


struct token *
lr_token (struct linereader *lr, const struct charmap_t *charmap,
	  const struct repertoire_t *repertoire)
{
  int ch;

  while (1)
    {
      do
	{
	  ch = lr_getc (lr);

	  if (ch == EOF)
	    {
	      lr->token.tok = tok_eof;
	      return &lr->token;
	    };

	  if (ch == '\n')
	    {
	      lr->token.tok = tok_eol;
	      return &lr->token;
	    }
	}
      while (isspace (ch));

      if (ch == EOF)
	{
	  lr->token.tok = tok_eof;
	  return &lr->token;
	};

      if (ch != lr->comment_char)
	break;

      /* Is there an newline at the end of the buffer?  */
      if (lr->buf[lr->bufact - 1] != '\n')
	{
	  /* No.  Some people want this to mean that only the line in
	     the file not the logical, concatenated line is ignored.
	     Let's try this.  */
	  lr->idx = lr->bufact;
	  continue;
	}

      /* Ignore rest of line.  */
      lr_ignore_rest (lr, 0);
      lr->token.tok = tok_eol;
      return &lr->token;
    }

  /* Match escape sequences.  */
  if (ch == lr->escape_char)
    return get_toplvl_escape (lr);

  /* Match ellipsis.  */
  if (ch == '.')
    {
      if (strncmp (&lr->buf[lr->idx], "...(2)....", 10) == 0)
	{
	  int cnt;
	  for (cnt = 0; cnt < 10; ++cnt)
	    lr_getc (lr);
	  lr->token.tok = tok_ellipsis4_2;
	  return &lr->token;
	}
      if (strncmp (&lr->buf[lr->idx], "...", 3) == 0)
	{
	  lr_getc (lr);
	  lr_getc (lr);
	  lr_getc (lr);
	  lr->token.tok = tok_ellipsis4;
	  return &lr->token;
	}
      if (strncmp (&lr->buf[lr->idx], "..", 2) == 0)
	{
	  lr_getc (lr);
	  lr_getc (lr);
	  lr->token.tok = tok_ellipsis3;
	  return &lr->token;
	}
      if (strncmp (&lr->buf[lr->idx], ".(2)..", 6) == 0)
	{
	  int cnt;
	  for (cnt = 0; cnt < 6; ++cnt)
	    lr_getc (lr);
	  lr->token.tok = tok_ellipsis2_2;
	  return &lr->token;
	}
      if (lr->buf[lr->idx] == '.')
	{
	  lr_getc (lr);
	  lr->token.tok = tok_ellipsis2;
	  return &lr->token;
	}
    }

  switch (ch)
    {
    case '<':
      return get_symname (lr);

    case '0' ... '9':
      lr->token.tok = tok_number;
      lr->token.val.num = ch - '0';

      while (isdigit (ch = lr_getc (lr)))
	{
	  lr->token.val.num *= 10;
	  lr->token.val.num += ch - '0';
	}
      if (isalpha (ch))
	lr_error (lr, _("garbage at end of number"));
      lr_ungetn (lr, 1);

      return &lr->token;

    case ';':
      lr->token.tok = tok_semicolon;
      return &lr->token;

    case ',':
      lr->token.tok = tok_comma;
      return &lr->token;

    case '(':
      lr->token.tok = tok_open_brace;
      return &lr->token;

    case ')':
      lr->token.tok = tok_close_brace;
      return &lr->token;

    case '"':
      return get_string (lr, charmap, repertoire);

    case '-':
      ch = lr_getc (lr);
      if (ch == '1')
	{
	  lr->token.tok = tok_minus1;
	  return &lr->token;
	}
      lr_ungetn (lr, 2);
      break;
    }

  return get_ident (lr);
}


static struct token *
get_toplvl_escape (struct linereader *lr)
{
  /* This is supposed to be a numeric value.  We return the
     numerical value and the number of bytes.  */
  size_t start_idx = lr->idx - 1;
  char *bytes = lr->token.val.charcode.bytes;
  int nbytes = 0;
  int ch;

  do
    {
      unsigned int byte = 0;
      unsigned int base = 8;

      ch = lr_getc (lr);

      if (ch == 'd')
	{
	  base = 10;
	  ch = lr_getc (lr);
	}
      else if (ch == 'x')
	{
	  base = 16;
	  ch = lr_getc (lr);
	}

      if ((base == 16 && !isxdigit (ch))
	  || (base != 16 && (ch < '0' || ch >= (int) ('0' + base))))
	{
	esc_error:
	  lr->token.val.str.startmb = &lr->buf[start_idx];

	  while (ch != EOF && !isspace (ch))
	    ch = lr_getc (lr);
	  lr->token.val.str.lenmb = lr->idx - start_idx;

	  lr->token.tok = tok_error;
	  return &lr->token;
	}

      if (isdigit (ch))
	byte = ch - '0';
      else
	byte = tolower (ch) - 'a' + 10;

      ch = lr_getc (lr);
      if ((base == 16 && !isxdigit (ch))
	  || (base != 16 && (ch < '0' || ch >= (int) ('0' + base))))
	goto esc_error;

      byte *= base;
      if (isdigit (ch))
	byte += ch - '0';
      else
	byte += tolower (ch) - 'a' + 10;

      ch = lr_getc (lr);
      if (base != 16 && isdigit (ch))
	{
	  byte *= base;
	  byte += ch - '0';

	  ch = lr_getc (lr);
	}

      bytes[nbytes++] = byte;
    }
  while (ch == lr->escape_char
	 && nbytes < sizeof (lr->token.val.charcode.bytes));

  if (!isspace (ch))
    lr_error (lr, _("garbage at end of character code specification"));

  lr_ungetn (lr, 1);

  lr->token.tok = tok_charcode;
  lr->token.val.charcode.nbytes = nbytes;

  return &lr->token;
}


#define ADDC(ch) \
  do									      \
    {									      \
      if (bufact == bufmax)						      \
	{								      \
	  bufmax *= 2;							      \
	  buf = xrealloc (buf, bufmax);					      \
	}								      \
      buf[bufact++] = (ch);						      \
    }									      \
  while (0)


#define ADDS(s, l) \
  do									      \
    {									      \
      size_t _l = (l);							      \
      if (bufact + _l > bufmax)						      \
	{								      \
	  if (bufact < _l)						      \
	    bufact = _l;						      \
	  bufmax *= 2;							      \
	  buf = xrealloc (buf, bufmax);					      \
	}								      \
      memcpy (&buf[bufact], s, _l);					      \
      bufact += _l;							      \
    }									      \
  while (0)


#define ADDWC(ch) \
  do									      \
    {									      \
      if (buf2act == buf2max)						      \
	{								      \
	  buf2max *= 2;							      \
	  buf2 = xrealloc (buf2, buf2max * 4);				      \
	}								      \
      buf2[buf2act++] = (ch);						      \
    }									      \
  while (0)


static struct token *
get_symname (struct linereader *lr)
{
  /* Symbol in brackets.  We must distinguish three kinds:
     1. reserved words
     2. ISO 10646 position values
     3. all other.  */
  char *buf;
  size_t bufact = 0;
  size_t bufmax = 56;
  const struct keyword_t *kw;
  int ch;

  buf = (char *) xmalloc (bufmax);

  do
    {
      ch = lr_getc (lr);
      if (ch == lr->escape_char)
	{
	  int c2 = lr_getc (lr);
	  ADDC (c2);

	  if (c2 == '\n')
	    ch = '\n';
	}
      else
	ADDC (ch);
    }
  while (ch != '>' && ch != '\n');

  if (ch == '\n')
    lr_error (lr, _("unterminated symbolic name"));

  /* Test for ISO 10646 position value.  */
  if (buf[0] == 'U' && (bufact == 6 || bufact == 10))
    {
      char *cp = buf + 1;
      while (cp < &buf[bufact - 1] && isxdigit (*cp))
	++cp;

      if (cp == &buf[bufact - 1])
	{
	  /* Yes, it is.  */
	  lr->token.tok = tok_ucs4;
	  lr->token.val.ucs4 = strtoul (buf + 1, NULL, 16);

	  return &lr->token;
	}
    }

  /* It is a symbolic name.  Test for reserved words.  */
  kw = lr->hash_fct (buf, bufact - 1);

  if (kw != NULL && kw->symname_or_ident == 1)
    {
      lr->token.tok = kw->token;
      free (buf);
    }
  else
    {
      lr->token.tok = tok_bsymbol;

      buf[bufact] = '\0';
      buf = xrealloc (buf, bufact + 1);

      lr->token.val.str.startmb = buf;
      lr->token.val.str.lenmb = bufact - 1;
    }

  return &lr->token;
}


static struct token *
get_ident (struct linereader *lr)
{
  char *buf;
  size_t bufact;
  size_t bufmax = 56;
  const struct keyword_t *kw;
  int ch;

  buf = xmalloc (bufmax);
  bufact = 0;

  ADDC (lr->buf[lr->idx - 1]);

  while (!isspace ((ch = lr_getc (lr))) && ch != '"' && ch != ';'
	 && ch != '<' && ch != ',')
    {
      if (ch == lr->escape_char)
	{
	  ch = lr_getc (lr);
	  if (ch == '\n' || ch == EOF)
	    {
	      lr_error (lr, _("invalid escape sequence"));
	      break;
	    }
	}
      ADDC (ch);
    }

  lr_ungetn (lr, 1);

  kw = lr->hash_fct (buf, bufact);

  if (kw != NULL && kw->symname_or_ident == 0)
    {
      lr->token.tok = kw->token;
      free (buf);
    }
  else
    {
      lr->token.tok = tok_ident;

      buf[bufact] = '\0';
      buf = xrealloc (buf, bufact + 1);

      lr->token.val.str.startmb = buf;
      lr->token.val.str.lenmb = bufact;
    }

  return &lr->token;
}


static struct token *
get_string (struct linereader *lr, const struct charmap_t *charmap,
	    const struct repertoire_t *repertoire)
{
  int return_widestr = lr->return_widestr;
  char *buf;
  wchar_t *buf2 = NULL;
  size_t bufact;
  size_t bufmax = 56;

  /* We must return two different strings.  */
  buf = xmalloc (bufmax);
  bufact = 0;

  /* We know it'll be a string.  */
  lr->token.tok = tok_string;

  /* If we need not translate the strings (i.e., expand <...> parts)
     we can run a simple loop.  */
  if (!lr->translate_strings)
    {
      int ch;

      buf2 = NULL;
      while ((ch = lr_getc (lr)) != '"' && ch != '\n' && ch != EOF)
	ADDC (ch);

      /* Catch errors with trailing escape character.  */
      if (bufact > 0 && buf[bufact - 1] == lr->escape_char
	  && (bufact == 1 || buf[bufact - 2] != lr->escape_char))
	{
	  lr_error (lr, _("illegal escape sequence at end of string"));
	  --bufact;
	}
      else if (ch == '\n' || ch == EOF)
	lr_error (lr, _("unterminated string"));

      ADDC ('\0');
    }
  else
    {
      int illegal_string = 0;
      size_t buf2act = 0;
      size_t buf2max = 56 * sizeof (uint32_t);
      int ch;
      int warned = 0;

      /* We have to provide the wide character result as well.  */
      if (return_widestr)
	buf2 = xmalloc (buf2max);

      /* Read until the end of the string (or end of the line or file).  */
      while ((ch = lr_getc (lr)) != '"' && ch != '\n' && ch != EOF)
	{
	  size_t startidx;
	  uint32_t wch;
	  struct charseq *seq;

	  if (ch != '<')
	    {
	      /* The standards leave it up to the implementation to decide
		 what to do with character which stand for themself.  We
		 could jump through hoops to find out the value relative to
		 the charmap and the repertoire map, but instead we leave
		 it up to the locale definition author to write a better
		 definition.  We assume here that every character which
		 stands for itself is encoded using ISO 8859-1.  Using the
		 escape character is allowed.  */
	      if (ch == lr->escape_char)
		{
		  ch = lr_getc (lr);
		  if (ch == '\n' || ch == EOF)
		    break;
		}

	      if (verbose && !warned)
		{
		  lr_error (lr, _("\
non-symbolic character value should not be used"));
		  warned = 1;
		}

	      ADDC (ch);
	      if (return_widestr)
		ADDWC ((uint32_t) ch);

	      continue;
	    }

	  /* Now we have to search for the end of the symbolic name, i.e.,
	     the closing '>'.  */
	  startidx = bufact;
	  while ((ch = lr_getc (lr)) != '>' && ch != '\n' && ch != EOF)
	    {
	      if (ch == lr->escape_char)
		{
		  ch = lr_getc (lr);
		  if (ch == '\n' || ch == EOF)
		    break;
		}
	      ADDC (ch);
	    }
	  if (ch == '\n' || ch == EOF)
	    /* Not a correct string.  */
	    break;
	  if (bufact == startidx)
	    {
	      /* <> is no correct name.  Ignore it and also signal an
		 error.  */
	      illegal_string = 1;
	      continue;
	    }

	  /* It might be a Uxxxx symbol.  */
	  if (buf[startidx] == 'U'
	      && (bufact - startidx == 5 || bufact - startidx == 9))
	    {
	      char *cp = buf + startidx + 1;
	      while (cp < &buf[bufact] && isxdigit (*cp))
		++cp;

	      if (cp == &buf[bufact])
		{
		  char utmp[10];
		  const char *symbol = NULL;

		  /* Yes, it is.  */
		  ADDC ('\0');
		  wch = strtoul (buf + startidx + 1, NULL, 16);

		  /* Now forget about the name we just added.  */
		  bufact = startidx;

		  if (return_widestr)
		    ADDWC (wch);

		  /* See whether the charmap contains the Uxxxxxxxx names.  */
		  snprintf (utmp, sizeof (utmp), "U%08X", wch);
		  seq = charmap_find_value (charmap, utmp, 9);

		  if (seq == NULL)
		    {
		     /* No, this isn't the case.  Now determine from
			the repertoire the name of the character and
			find it in the charmap.  */
		      if (repertoire != NULL)
			symbol = repertoire_find_symbol (repertoire, wch);

		      if (symbol == NULL)
			/* We cannot generate a string since we
			   cannot map from the Unicode number to the
			   character symbol.  */
			illegal_string = 1;
		      else
			{
			  seq = charmap_find_value (charmap, symbol,
						    strlen (symbol));

			  if (seq == NULL)
			    /* Not a known name.  */
			    illegal_string = 1;
			}
		    }

		  if (seq != NULL)
		    ADDS (seq->bytes, seq->nbytes);

		  continue;
		}
	    }

	  /* We now have the symbolic name in buf[startidx] to
	     buf[bufact-1].  Now find out the value for this character
	     in the charmap as well as in the repertoire map (in this
	     order).  */
	  seq = charmap_find_value (charmap, &buf[startidx],
				    bufact - startidx);

	  if (seq == NULL)
	    {
	      /* This name is not in the charmap.  */
	      lr_error (lr, _("symbol `%.*s' not in charmap"),
			(int) (bufact - startidx), &buf[startidx]);
	      illegal_string = 1;
	    }

	  if (return_widestr)
	    {
	      /* Now the same for the multibyte representation.  */
	      if (seq != NULL && seq->ucs4 != UNINITIALIZED_CHAR_VALUE)
		wch = seq->ucs4;
	      else
		{
		  wch = repertoire_find_value (repertoire, &buf[startidx],
					       bufact - startidx);
		  if (seq != NULL)
		    seq->ucs4 = wch;
		}

	      if (wch == ILLEGAL_CHAR_VALUE)
		{
		  /* This name is not in the repertoire map.  */
		  lr_error (lr, _("symbol `%.*s' not in repertoire map"),
			    (int) (bufact - startidx), &buf[startidx]);
		  illegal_string = 1;
		}
	      else
		ADDWC (wch);
	    }

	  /* Now forget about the name we just added.  */
	  bufact = startidx;

	  /* And copy the bytes.  */
	  if (seq != NULL)
	    ADDS (seq->bytes, seq->nbytes);
	}

      if (ch == '\n' || ch == EOF)
	{
	  lr_error (lr, _("unterminated string"));
	  illegal_string = 1;
	}

      if (illegal_string)
	{
	  free (buf);
	  if (buf2 != NULL)
	    free (buf2);
	  lr->token.val.str.startmb = NULL;
	  lr->token.val.str.lenmb = 0;
	  lr->token.val.str.startwc = NULL;
	  lr->token.val.str.lenwc = 0;

	  return &lr->token;
	}

      ADDC ('\0');

      if (return_widestr)
	{
	  ADDWC (0);
	  lr->token.val.str.startwc = xrealloc (buf2,
						buf2act * sizeof (uint32_t));
	  lr->token.val.str.lenwc = buf2act;
	}
    }

  lr->token.val.str.startmb = xrealloc (buf, bufact);
  lr->token.val.str.lenmb = bufact;

  return &lr->token;
}