summary refs log tree commit diff
path: root/locale/programs/locfile.c
blob: 284c7ce5b663208802415b01816ceba2393560b0 (plain) (blame)
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
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
/* Copyright (C) 1996 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Ulrich Drepper, <drepper@gnu.ai.mit.edu>.

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 <errno.h>
#include <fcntl.h>
#include <locale.h>
#include <malloc.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/uio.h>

#include "locfile.h"
#include "linereader.h"
#include "localeinfo.h"
#include "locales.h"


/* Uncomment the following line in the production version. */
/* #define NDEBUG 1 */
#include <assert.h>

/* Define the lookup function.  */
#include "locfile-kw.h"


/* Some useful macros.  */
#define MIN(a, b) (__extension__ ({ typeof (a) _a = (a);		      \
				    typeof (b) _b = (b);		      \
				    _a < _b ? _a : _b; }))


void *xmalloc (size_t __n);
char *xstrdup (const char *__str);

struct localedef_t *
locfile_read (const char *filename, struct charset_t *charset)
{
  struct linereader *ldfile;
  struct localedef_t *result;
  int state;
  enum token_t expected_tok = tok_none;
  const char *expected_str = NULL;
  enum token_t ctype_tok_sym = tok_none;
  const char *ctype_tok_str = NULL;
  int copy_category = 0;
  int cnt;

  /* Allocate space for result.  */
  result = (struct localedef_t *) xmalloc (sizeof (struct localedef_t));
  memset (result, '\0', sizeof (struct localedef_t));

  ldfile = lr_open (filename, locfile_hash);
  if (ldfile == NULL)
    {
      if (filename[0] != '/')
	{
	  char path[strlen (filename) + 1 + sizeof (LOCSRCDIR)];

	  stpcpy (stpcpy (stpcpy (path, LOCSRCDIR), "/"), filename);
	  ldfile = lr_open (path, locfile_hash);
	}

      if (ldfile == NULL)
	{
	  result->failed = 1;
	  return result;
	}
    }

#define HANDLE_COPY(category, token, string)				      \
  if (nowtok == tok_copy)						      \
    {									      \
      copy_category = category;						      \
      expected_tok = token;						      \
      expected_str = string;						      \
      state = 8;							      \
      continue;								      \
    }									      \
  ++state

#define LOCALE_PROLOG(token, string)					      \
  if (nowtok == tok_eol)						      \
    /* Ignore empty lines.  */						      \
    continue;								      \
  if (nowtok == tok_end)						      \
    {									      \
      expected_tok = token;						      \
      expected_str = string;						      \
      state = 4;							      \
      continue;								      \
    }									      \
  if (nowtok == tok_copy)						      \
    goto only_copy;


#define READ_STRING(fn, errlabel)					      \
  do									      \
    {									      \
      arg = lr_token (ldfile, charset);					      \
      if (arg->tok != tok_string)					      \
	goto errlabel;							      \
      fn (ldfile, result, nowtok, arg, charset);			      \
      lr_ignore_rest (ldfile, 1);					      \
    }									      \
  while (0)

#define READ_STRING_LIST(fn, errlabel)					      \
  do									      \
    {									      \
      arg = lr_token (ldfile, charset);					      \
      while (arg->tok == tok_string)					      \
	{								      \
	  fn (ldfile, result, nowtok, arg, charset);			      \
	  arg = lr_token (ldfile, charset);				      \
	  if (arg->tok != tok_semicolon)				      \
	    break;							      \
	  arg = lr_token (ldfile, charset);				      \
	}								      \
      if (arg->tok != tok_eol)						      \
	goto errlabel;							      \
    }									      \
  while (0)

#define READ_NUMBER(fn, errlabel)					      \
  do									      \
    {									      \
      arg = lr_token (ldfile, charset);					      \
      if (arg->tok != tok_minus1 && arg->tok != tok_number)		      \
	goto errlabel;							      \
      fn (ldfile, result, nowtok, arg, charset);			      \
      lr_ignore_rest (ldfile, 1);					      \
    }									      \
  while (0)

#define READ_NUMBER_LIST(fn, errlabel)					      \
  do									      \
    {									      \
      arg = lr_token (ldfile, charset);					      \
      while (arg->tok == tok_minus1 || arg->tok == tok_number)		      \
	{								      \
	  fn (ldfile, result, nowtok, arg, charset);			      \
	  arg = lr_token (ldfile, charset);				      \
	  if (arg->tok != tok_semicolon)				      \
	    break;							      \
	  arg = lr_token (ldfile, charset);				      \
	}								      \
      if (arg->tok != tok_eol)						      \
	goto errlabel;							      \
    }									      \
  while (0)

#define SYNTAX_ERROR(string)						      \
  lr_error (ldfile, string);						      \
  lr_ignore_rest (ldfile, 0);


  /* Parse locale definition file and store result in RESULT.  */
  state = 1;
  while (1)
    {
      /* What's on?  */
      struct token *now = lr_token (ldfile, charset);
      enum token_t nowtok = now->tok;
      struct token *arg;

      if (nowtok == tok_eof)
	break;

      switch (state)
	{
	case 1:
	  /* The beginning.  We expect the special declarations, EOL or
	     the start of any locale.  */
	  if (nowtok == tok_eol)
	    /* Ignore empty lines.  */
	    continue;

	  switch (nowtok)
	    {
	    case tok_escape_char:
	    case tok_comment_char:
	      /* We need an argument.  */
	      arg = lr_token (ldfile, charset);

	      if (arg->tok != tok_ident)
		{
		  SYNTAX_ERROR (_("bad argument"));
		  continue;
		}

	      if (arg->val.str.len != 1)
		{
		  lr_error (ldfile, _("\
argument to `%s' must be a single character"),
			    nowtok == tok_escape_char ? "escape_char"
						      : "comment_char");

		  lr_ignore_rest (ldfile, 0);
		  continue;
		}

	      if (nowtok == tok_escape_char)
		ldfile->escape_char = *arg->val.str.start;
	      else
		ldfile->comment_char = *arg->val.str.start;
	      break;

	    case tok_lc_ctype:
	      state = 2;
	      break;

	    case tok_lc_collate:
	      state = 10;
	      break;

	    case tok_lc_monetary:
	      state = 20;
	      break;

	    case tok_lc_numeric:
	      state = 30;
	      break;

	    case tok_lc_time:
	      state = 40;
	      break;

	    case tok_lc_messages:
	      state = 50;
	      break;

	    default:
	      SYNTAX_ERROR (_("\
syntax error: not inside a locale definition section"));
	      continue;
	    }
	  lr_ignore_rest (ldfile, 1);
	  continue;

	case 2:
	  HANDLE_COPY (LC_CTYPE, tok_lc_ctype, "LC_CYTPE");

	  ctype_startup (ldfile, result, charset);
	  /* FALLTHROUGH */

	case 3:
	  /* Here we accept all the character classes, tolower/toupper,
	     and following ANSI C:1995 self-defined classes.  */
	  LOCALE_PROLOG (tok_lc_ctype, "LC_CTYPE");

	  if (nowtok == tok_charclass)
	    {
	      READ_STRING_LIST (ctype_class_new, bad_new_charclass);
	      continue;
	    bad_new_charclass:
	      SYNTAX_ERROR (_("\
syntax error in definition of new character class"));
	      continue;
	    }

	  if (nowtok == tok_charmap)
	    {
	      READ_STRING_LIST (ctype_map_new, bad_new_charmap);
	      continue;
	    bad_new_charmap:
	      SYNTAX_ERROR (_("\
syntax error in definition of new character map"));
	      continue;
	    }

	  if (nowtok == tok_upper || nowtok == tok_lower
	      || nowtok == tok_alpha || nowtok == tok_digit
	      || nowtok == tok_alnum || nowtok == tok_space
	      || nowtok == tok_cntrl || nowtok == tok_punct
	      || nowtok == tok_graph || nowtok == tok_print
	      || nowtok == tok_xdigit || nowtok == tok_blank)
	    {
	      ctype_tok_sym = nowtok;
	      ctype_tok_str = NULL;
	      state = 5;
	      continue;
	    }

	  if (nowtok == tok_toupper|| nowtok == tok_tolower)
	    {
	      ctype_tok_sym = nowtok;
	      ctype_tok_str = NULL;
	      state = 6;
	      continue;
	    }

	  if (nowtok != tok_ident)
	    goto bad_charclass;

	  /* We possibly have a self-defined character class.  */
	  if (ctype_is_charclass (ldfile, result, now->val.str.start))
	    {
	      ctype_tok_sym = nowtok;
	      ctype_tok_str = now->val.str.start;
	      state = 5;
	      continue;
	    }

	  /* ...or a self-defined character map.  */
	  if (ctype_is_charmap (ldfile, result, now->val.str.start))
	    {
	      ctype_tok_sym = nowtok;
	      ctype_tok_str = now->val.str.start;
	      state = 6;
	      continue;
	    }

	  SYNTAX_ERROR (_("syntax error in definition of LC_CTYPE category"));
	  continue;

	case 4:
	  /* Handle `END xxx'.  */
	  if (nowtok != expected_tok)
	    lr_error (ldfile, _("\
`%1$s' definition does not end with `END %1$s'"), expected_str);

	  lr_ignore_rest (ldfile, nowtok == expected_tok);
	  state = 1;
	  continue;

	case 5:
	  /* Here we expect a semicolon separated list of bsymbols.  The
	     bit to be set in the word is given in CHARCLASS_BIT.  */
	  arg = now;

	  ctype_class_start (ldfile, result, ctype_tok_sym, ctype_tok_str,
			     charset);

	  while (arg->tok != tok_eol)
	    {
	      /* Any token other than a bsymbol is an error.  */
	      if (arg->tok != tok_bsymbol)
		{
		bad_charclass:
		  SYNTAX_ERROR (_("\
syntax error in character class definition"));
		  break;
		}

	      /* Lookup value for token and write into array.  */
	      ctype_class_from (ldfile, result, arg, charset);

	      arg = lr_token (ldfile, charset);
	      if (arg->tok == tok_semicolon)
		arg = lr_token (ldfile, charset);
	      else if (arg->tok != tok_eol)
		goto bad_charclass;

	      /* Look for ellipsis.  */
	      if (arg->tok == tok_ellipsis)
		{
		  arg = lr_token (ldfile, charset);
		  if (arg->tok != tok_semicolon)
		    goto bad_charclass;

		  arg = lr_token (ldfile, charset);
		  if (arg->tok != tok_bsymbol)
		    goto bad_charclass;

		  /* Write range starting at LAST to ARG->VAL.  */
		  ctype_class_to (ldfile, result, arg, charset);

		  arg = lr_token (ldfile, charset);
		  if (arg->tok == tok_semicolon)
		    arg = lr_token (ldfile, charset);
		  else if (arg->tok != tok_eol)
		    goto bad_charclass;
		}
	  }

	  /* Mark class as already seen.  */
	  ctype_class_end (ldfile, result);
	  state = 3;

	  continue;

	case 6:
	  /* Here we expect a list of character mappings.  Note: the
	     first opening brace is already matched.  */
	  ctype_map_start (ldfile, result, ctype_tok_sym, ctype_tok_str,
			   charset);

	  while (1)
	    {
	      /* Match ( bsymbol , bsymbol )  */
	      if (now->tok != tok_open_brace)
		goto bad_charmap;

	      now = lr_token (ldfile, charset);
	      if (now->tok != tok_bsymbol)
		{
		bad_charmap:
		  SYNTAX_ERROR (_("\
syntax error in character mapping definition"));
		  state = 3;
		  break;
		}

	      /* Lookup arg and assign to FROM.  */
	      ctype_map_from (ldfile, result, now, charset);

	      now = lr_token (ldfile, charset);
	      if (now->tok != tok_comma)
		goto bad_charmap;

	      now = lr_token (ldfile, charset);
	      if (now->tok != tok_bsymbol)
		goto bad_charmap;

	      /* Lookup arg and assign to TO.  */
	      ctype_map_to (ldfile, result, now, charset);

	      now = lr_token (ldfile, charset);
	      if (now->tok != tok_close_brace)
		goto bad_charmap;

	      now = lr_token (ldfile, charset);
	      if (now->tok == tok_eol)
		{
		  state = 3;
		  break;
		}
	      if (now->tok != tok_semicolon)
		goto bad_charmap;

	      now = lr_token (ldfile, charset);
	    }

	  ctype_map_end (ldfile, result);
	  continue;

	case 8:
	  {
	    /* We have seen `copy'.  First match the argument.  */
	    int warned = 0;

	    if (nowtok != tok_string)
	      lr_error (ldfile, _("expect string argument for `copy'"));
	    else
	      def_to_process (now->val.str.start, 1 << copy_category);

	    lr_ignore_rest (ldfile, nowtok == tok_string);

	    /* The rest of the line must be empty
	       and the next keyword must be `END xxx'.  */

	    while (lr_token (ldfile, charset)->tok != tok_end)
	      {
		if (warned == 0)
		  {
		  only_copy:
		    lr_error (ldfile, _("\
no other keyword shall be specified when `copy' is used"));
		    warned = 1;
		  }

		lr_ignore_rest (ldfile, 0);
	      }

	    state = 4;
	  }
	  continue;

	case 10:
	  HANDLE_COPY (LC_COLLATE, tok_lc_collate, "LC_COLLATE");

	  collate_startup (ldfile, result, charset);
	  /* FALLTHROUGH */

	case 11:
	  /* Process the LC_COLLATE section.  We expect `END LC_COLLATE'
	     any of the collation specifications, or any bsymbol.  */
	  LOCALE_PROLOG (tok_lc_collate, "LC_COLLATE");

	  if (nowtok == tok_order_start)
	    {
	      state = 12;
	      continue;
	    }

	  if (nowtok != tok_collating_element
	      && nowtok != tok_collating_symbol)
	    {
	    bad_collation:
	      lr_error (ldfile, _("\
syntax error in collation definition"));
	      lr_ignore_rest (ldfile, 0);
	      continue;
	    }

	  /* Get argument.  */
	  arg = lr_token (ldfile, charset);
	  if (arg->tok != tok_bsymbol)
	    {
	      lr_error (ldfile, _("\
collation symbol expected after `%s'"),
			nowtok == tok_collating_element
			? "collating-element" : "collating-symbol");
	      lr_ignore_rest (ldfile, 0);
	      continue;
	    }

	  if (nowtok == tok_collating_element)
	    {
	      /* Save to-value as new name.  */
	      collate_element_to (ldfile, result, arg, charset);

	      arg = lr_token (ldfile, charset);
	      if (arg->tok != tok_from)
		{
		  lr_error (ldfile, _("\
`from' expected after first argument to `collating-element'"));
		  lr_ignore_rest (ldfile, 0);
		  continue;
		}

	      arg = lr_token (ldfile, charset);
	      if (arg->tok != tok_string)
		{
		  lr_error (ldfile, _("\
from-value of `collating-element' must be a string"));
		  lr_ignore_rest (ldfile, 0);
		  continue;
		}

	      /* Enter new collating element.  */
	      collate_element_from (ldfile, result, arg, charset);
	    }
	  else
	    /* Enter new collating symbol into table.  */
	    collate_symbol (ldfile, result, arg, charset);

	  lr_ignore_rest (ldfile, 1);
	  continue;

	case 12:
	  /* We parse the rest of the line containing `order_start'.
	     In any case we continue with parsing the symbols.  */
	  state = 13;

	  cnt = 0;
	  while (now->tok != tok_eol)
	    {
	      int collation_method = 0;

	      ++cnt;

	      do
		{
		  if (now->tok == tok_forward)
		    collation_method |= sort_forward;
		  else if (now->tok == tok_backward)
		    collation_method |= sort_backward;
		  else if (now->tok == tok_position)
		    collation_method |= sort_position;
		  else
		    {
		      lr_error (ldfile, _("unknown collation directive"));
		      lr_ignore_rest (ldfile, 0);
		      continue;
		    }

		  now = lr_token (ldfile, charset);
		}
	      while (now->tok == tok_comma
		     && (now == lr_token (ldfile, charset) != tok_none));

	      /* Check for consistency: forward and backwards are
		 mutually exclusive.  */
	      if ((collation_method & sort_forward) != 0
		  && (collation_method & sort_backward) != 0)
		{
		  lr_error (ldfile, _("\
sorting order `forward' and `backward' are mutually exclusive"));
		  /* The recover clear the backward flag.  */
		  collation_method &= ~sort_backward;
		}

	      /* ??? I don't know whether this is correct but while
		 thinking about the `strcoll' functions I found that I
		 need a direction when performing position depended
		 collation.  So I assume here that implicitly the
		 direction `forward' is given when `position' alone is
		 written.  --drepper  */
	      if (collation_method == sort_position)
		collation_method |= sort_forward;

	      /* Enter info about next collation order.  */
	      collate_new_order (ldfile, result, collation_method);

	      if (now->tok != tok_eol && now->tok != tok_semicolon)
		{
		  lr_error (ldfile, _("\
syntax error in `order_start' directive"));
		  lr_ignore_rest (ldfile, 0);
		  break;
		}

	      if (now->tok == tok_semicolon)
		now = lr_token (ldfile, charset);
	    }

	  /* If no argument to `order_start' is given, one `forward'
	     argument is implicitely assumed.  */
	  if (cnt == 0)
	    collate_new_order (ldfile, result, sort_forward);


	  /* We now know about all sorting rules.  */
	  collate_build_arrays (ldfile, result);

	  continue;

	case 13:
	  /* We read one symbol a line until `order_end' is found.  */
	  {
	    static int last_correct = 1;

	    if (nowtok == tok_order_end)
	      {
		state = 14;
		lr_ignore_rest (ldfile, 1);
		continue;
	      }

	    /* Ignore empty lines.  */
	    if (nowtok == tok_eol)
	      continue;

	    if (nowtok != tok_bsymbol && nowtok != tok_undefined
		&& nowtok != tok_ellipsis)
	      {
		if (last_correct == 1)
		  {
		    lr_error (ldfile, _("\
syntax error in collating order definition"));
		    last_correct = 0;
		  }
		lr_ignore_rest (ldfile, 0);
		continue;
	      }
	    else
	      {
		last_correct = 1;

		/* Remember current token.  */
		if (collate_order_elem (ldfile, result, now, charset) < 0)
		  continue;
	      }

	    /* Read optional arguments.  */
	    arg = lr_token (ldfile, charset);
	    while (arg->tok != tok_eol)
	      {
		if (arg->tok != tok_ignore && arg->tok != tok_ellipsis
		    && arg->tok != tok_bsymbol && arg->tok != tok_string)
		  break;

		if (arg->tok == tok_ignore || arg->tok == tok_ellipsis
		    || arg->tok == tok_string)
		  {
		    /* Call handler for simple weights.  */
		    if (collate_simple_weight (ldfile, result, arg, charset)
			< 0)
		      goto illegal_weight;

		    arg = lr_token (ldfile, charset);
		  }
		else
		  do
		    {
		      /* Collect char.  */
		      int ok = collate_weight_bsymbol (ldfile, result, arg,
						       charset);
		      if (ok < 0)
			goto illegal_weight;

		      arg = lr_token (ldfile, charset);
		    }
		  while (arg->tok == tok_bsymbol);

		/* Are there more weights?  */
		if (arg->tok != tok_semicolon)
		  break;

		/* Yes, prepare next weight.  */
		if (collate_next_weight (ldfile, result) < 0)
		  goto illegal_weight;

		arg = lr_token (ldfile, charset);
	      }

	    if (arg->tok != tok_eol)
	      {
		SYNTAX_ERROR (_("syntax error in order specification"));
	      }

	    collate_end_weight (ldfile, result);
	  illegal_weight:
	  }
	  continue;

	case 14:
	  /* Following to the `order_end' keyword we don't expect
	     anything but the `END'.  */
	  if (nowtok == tok_eol)
	    continue;

	  if (nowtok != tok_end)
	    goto bad_collation;

	  expected_tok = tok_lc_collate;
	  expected_str = "LC_COLLATE";
	  state = 4;

	  ldfile->translate_strings = 1;
	  continue;

	case 20:
	  HANDLE_COPY (LC_MONETARY, tok_lc_monetary, "LC_MONETARY");

	  monetary_startup (ldfile, result, charset);
	  /* FALLTHROUGH */

	case 21:
	  LOCALE_PROLOG (tok_lc_monetary, "LC_MONETARY");

	  switch (nowtok)
	    {
	    case tok_int_curr_symbol:
	    case tok_currency_symbol:
	    case tok_mon_decimal_point:
	    case tok_mon_thousands_sep:
	    case tok_positive_sign:
	    case tok_negative_sign:
	      READ_STRING (monetary_add, bad_monetary);
	      break;

	    case tok_int_frac_digits:
	    case tok_frac_digits:
	    case tok_p_cs_precedes:
	    case tok_p_sep_by_space:
	    case tok_n_cs_precedes:
	    case tok_n_sep_by_space:
	    case tok_p_sign_posn:
	    case tok_n_sign_posn:
	      READ_NUMBER (monetary_add, bad_monetary);
	      break;

	    case tok_mon_grouping:
	      /* We have a semicolon separated list of integers.  */
	      READ_NUMBER_LIST (monetary_add, bad_monetary);
	      break;

	    default:
	    bad_monetary:
	      SYNTAX_ERROR (_("syntax error in monetary locale definition"));
	    }
	  continue;

	case 30:
	  HANDLE_COPY (LC_NUMERIC, tok_lc_numeric, "LC_NUMERIC");

	  numeric_startup (ldfile, result, charset);
	  /* FALLTHROUGH */

	case 31:
	  LOCALE_PROLOG (tok_lc_numeric, "LC_NUMERIC");

	  switch (nowtok)
	    {
	    case tok_decimal_point:
	    case tok_thousands_sep:
	      READ_STRING (numeric_add, bad_numeric);
	      break;

	    case tok_grouping:
	      /* We have a semicolon separated list of integers.  */
	      READ_NUMBER_LIST (numeric_add, bad_numeric);
	      break;

	    default:
	    bad_numeric:
	      SYNTAX_ERROR (_("syntax error in numeric locale definition"));
	    }
	  continue;

	case 40:
	  HANDLE_COPY (LC_TIME, tok_lc_time, "LC_TIME");

	  time_startup (ldfile, result, charset);
	  /* FALLTHROUGH */

	case 41:
	  LOCALE_PROLOG (tok_lc_time, "LC_TIME");

	  switch (nowtok)
	    {
	    case tok_abday:
	    case tok_day:
	    case tok_abmon:
	    case tok_mon:
	    case tok_am_pm:
	    case tok_alt_digits:
	      READ_STRING_LIST (time_add, bad_time);
	      continue;

	    case tok_d_t_fmt:
	    case tok_d_fmt:
	    case tok_t_fmt:
	    case tok_t_fmt_ampm:
	    case tok_era:
	    case tok_era_year:
	    case tok_era_d_t_fmt:
	    case tok_era_d_fmt:
	    case tok_era_t_fmt:
	      READ_STRING (time_add, bad_time);
	      break;

	    default:
	    bad_time:
	      SYNTAX_ERROR (_("syntax error in time locale definition"));
	    }
	  continue;

	case 50:
	  HANDLE_COPY (LC_MESSAGES, tok_lc_messages, "LC_MESSAGES");

	  messages_startup (ldfile, result, charset);
	  /* FALLTHROUGH */

	case 51:
	  LOCALE_PROLOG (tok_lc_messages, "LC_MESSAGES");

	  switch (nowtok)
	    {
	    case tok_yesexpr:
	    case tok_noexpr:
	    case tok_yesstr:
	    case tok_nostr:
	      READ_STRING (messages_add, bad_message);
	      break;

	    default:
	    bad_message:
	      SYNTAX_ERROR (_("syntax error in message locale definition"));
	    }
	  continue;

	default:
	  error (5, 0, _("%s: error in state machine"), __FILE__);
	  /* NOTREACHED */
	}

      break;
    }

  /* We read all of the file.  */
  lr_close (ldfile);

  /* Let's see what information is available.  */
  for (cnt = LC_CTYPE; cnt <= LC_MESSAGES; ++cnt)
    if (result->categories[cnt].generic != NULL)
      result->avail |= 1 << cnt;

  return result;
}


void
check_all_categories (struct localedef_t *locale, struct charset_t *charset)
{
 /* Call the finishing functions for all locales.  */
  if ((locale->binary & (1 << LC_CTYPE)) == 0)
    ctype_finish (locale, charset);
  if ((locale->binary & (1 << LC_COLLATE)) == 0)
    collate_finish (locale, charset);
  if ((locale->binary & (1 << LC_MONETARY)) == 0)
    monetary_finish (locale);
  if ((locale->binary & (1 << LC_NUMERIC)) == 0)
    numeric_finish (locale);
  if ((locale->binary & (1 << LC_TIME)) == 0)
    time_finish (locale);
  if ((locale->binary & (1 << LC_MESSAGES)) == 0)
    messages_finish (locale);
}


void
write_all_categories (struct localedef_t *locale, struct charset_t *charset,
		      const char *output_path)
{
  /* Call all functions to write locale data.  */
  ctype_output (locale, charset, output_path);
  collate_output (locale, output_path);
  monetary_output (locale, output_path);
  numeric_output (locale, output_path);
  time_output (locale, output_path);
  messages_output (locale, output_path);
}


void
write_locale_data (const char *output_path, const char *category,
		   size_t n_elem, struct iovec *vec)
{
  size_t cnt, step;
  int fd;
  char *fname;

  asprintf (&fname, "%s%s", output_path, category);
  fd = creat (fname, 0666);
  if (fd == -1)
    {
      int save_err = errno;

      if (errno == EISDIR)
	{
	  free (fname);
	  asprintf (&fname, "%1$s%2$s/SYS_%2$s", output_path, category);
	  fd = creat (fname, 0666);
	  if (fd == -1)
	    save_err = errno;
	}

      if (fd == -1)
	{
	  error (0, save_err, _("cannot open output file for category `%s'"),
		 category);
	  return;
	}
    }
  free (fname);

  /* Write the data using writev.  But we must take care for the
     limitation of the implementation.  */
  for (cnt = 0; cnt < n_elem; cnt += step)
    {
      step = MIN (UIO_MAXIOV, n_elem - cnt);

      if (writev (fd, &vec[cnt], step) < 0)
	{
	  error (0, errno, _("failure while writing data for category `%s'"),
		 category);
	  break;
	}
    }

  close (fd);
}