Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   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
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
/* xgettext Scheme backend.
   Copyright (C) 2004-2006 Free Software Foundation, Inc.

   This file was written by Bruno Haible <bruno@clisp.org>, 2004-2005.

   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 2, 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, write to the Free Software Foundation,
   Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */

#ifdef HAVE_CONFIG_H
# include "config.h"
#endif

#include <errno.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "message.h"
#include "xgettext.h"
#include "x-scheme.h"
#include "error.h"
#include "xalloc.h"
#include "exit.h"
#include "hash.h"
#include "gettext.h"

#define _(s) gettext(s)


/* The Scheme syntax is described in R5RS.  It is implemented in
   guile-1.6.4/libguile/read.c.
   Since we are interested only in strings and in forms similar to
        (gettext msgid ...)
   or   (ngettext msgid msgid_plural ...)
   we make the following simplifications:

   - Assume the keywords and strings are in an ASCII compatible encoding.
     This means we can read the input file one byte at a time, instead of
     one character at a time.  No need to worry about multibyte characters:
     If they occur as part of identifiers, they most probably act as
     constituent characters, and the byte based approach will do the same.

   - Assume the read-hash-procedures is in the default state.
     Non-standard reader extensions are mostly used to read data, not programs.

   The remaining syntax rules are:

   - The syntax code assigned to each character, and how tokens are built
     up from characters (single escape, multiple escape etc.).

   - Comment syntax: ';' and '#! ... \n!#\n'.

   - String syntax: "..." with single escapes.

   - Read macros and dispatch macro character '#'.  Needed to be able to
     tell which is the n-th argument of a function call.

 */


/* ====================== Keyword set customization.  ====================== */

/* If true extract all strings.  */
static bool extract_all = false;

static hash_table keywords;
static bool default_keywords = true;


void
x_scheme_extract_all ()
{
  extract_all = true;
}


void
x_scheme_keyword (const char *name)
{
  if (name == NULL)
    default_keywords = false;
  else
    {
      const char *end;
      struct callshape shape;
      const char *colon;

      if (keywords.table == NULL)
	hash_init (&keywords, 100);

      split_keywordspec (name, &end, &shape);

      /* The characters between name and end should form a valid Lisp symbol.
	 Extract the symbol name part.  */
      colon = strchr (name, ':');
      if (colon != NULL && colon < end)
	{
	  name = colon + 1;
	  if (name < end && *name == ':')
	    name++;
	  colon = strchr (name, ':');
	  if (colon != NULL && colon < end)
	    return;
	}

      insert_keyword_callshape (&keywords, name, end - name, &shape);
    }
}

/* Finish initializing the keywords hash table.
   Called after argument processing, before each file is processed.  */
static void
init_keywords ()
{
  if (default_keywords)
    {
      /* When adding new keywords here, also update the documentation in
	 xgettext.texi!  */
      x_scheme_keyword ("gettext");		/* libguile/i18n.c */
      x_scheme_keyword ("ngettext:1,2");	/* libguile/i18n.c */
      x_scheme_keyword ("gettext-noop");
      default_keywords = false;
    }
}

void
init_flag_table_scheme ()
{
  xgettext_record_flag ("gettext:1:pass-scheme-format");
  xgettext_record_flag ("ngettext:1:pass-scheme-format");
  xgettext_record_flag ("ngettext:2:pass-scheme-format");
  xgettext_record_flag ("gettext-noop:1:pass-scheme-format");
  xgettext_record_flag ("format:2:scheme-format");
}


/* ======================== Reading of characters.  ======================== */

/* Real filename, used in error messages about the input file.  */
static const char *real_file_name;

/* Logical filename and line number, used to label the extracted messages.  */
static char *logical_file_name;
static int line_number;

/* The input file stream.  */
static FILE *fp;


/* Fetch the next character from the input file.  */
static int
do_getc ()
{
  int c = getc (fp);

  if (c == EOF)
    {
      if (ferror (fp))
	error (EXIT_FAILURE, errno, _("\
error while reading \"%s\""), real_file_name);
    }
  else if (c == '\n')
   line_number++;

  return c;
}

/* Put back the last fetched character, not EOF.  */
static void
do_ungetc (int c)
{
  if (c == '\n')
    line_number--;
  ungetc (c, fp);
}


/* ========================== Reading of tokens.  ========================== */


/* A token consists of a sequence of characters.  */
struct token
{
  int allocated;		/* number of allocated 'token_char's */
  int charcount;		/* number of used 'token_char's */
  char *chars;			/* the token's constituents */
};

/* Initialize a 'struct token'.  */
static inline void
init_token (struct token *tp)
{
  tp->allocated = 10;
  tp->chars = (char *) xmalloc (tp->allocated * sizeof (char));
  tp->charcount = 0;
}

/* Free the memory pointed to by a 'struct token'.  */
static inline void
free_token (struct token *tp)
{
  free (tp->chars);
}

/* Ensure there is enough room in the token for one more character.  */
static inline void
grow_token (struct token *tp)
{
  if (tp->charcount == tp->allocated)
    {
      tp->allocated *= 2;
      tp->chars = (char *) xrealloc (tp->chars, tp->allocated * sizeof (char));
    }
}

/* Read the next token.  'first' is the first character, which has already
   been read.  */
static void
read_token (struct token *tp, int first)
{
  init_token (tp);

  grow_token (tp);
  tp->chars[tp->charcount++] = first;

  for (;;)
    {
      int c = do_getc ();

      if (c == EOF)
	break;
      if (c == ' ' || c == '\r' || c == '\f' || c == '\t' || c == '\n'
	  || c == '"' || c == '(' || c == ')' || c == ';')
	{
	  do_ungetc (c);
	  break;
	}
      grow_token (tp);
      tp->chars[tp->charcount++] = c;
    }
}

/* Tests if a token represents an integer.
   Taken from guile-1.6.4/libguile/numbers.c:scm_istr2int().  */
static inline bool
is_integer_syntax (const char *str, int len, int radix)
{
  const char *p = str;
  const char *p_end = str + len;

  /* The accepted syntax is
       ['+'|'-'] DIGIT+
     where DIGIT is a hexadecimal digit whose value is below radix.  */

  if (p == p_end)
    return false;
  if (*p == '+' || *p == '-')
    {
      p++;
      if (p == p_end)
	return false;
    }
  do
    {
      int c = *p++;

      if (c >= '0' && c <= '9')
	c = c - '0';
      else if (c >= 'A' && c <= 'F')
	c = c - 'A' + 10;
      else if (c >= 'a' && c <= 'f')
	c = c - 'a' + 10;
      else
	return false;
      if (c >= radix)
	return false;
    }
  while (p < p_end);
  return true;
}

/* Tests if a token represents a rational, floating-point or complex number.
   If unconstrained is false, only real numbers are accepted; otherwise,
   complex numbers are accepted as well.
   Taken from guile-1.6.4/libguile/numbers.c:scm_istr2flo().  */
static inline bool
is_other_number_syntax (const char *str, int len, int radix, bool unconstrained)
{
  const char *p = str;
  const char *p_end = str + len;
  bool seen_sign;
  bool seen_digits;

  /* The accepted syntaxes are:
     for a floating-point number:
       ['+'|'-'] DIGIT+ [EXPONENT]
       ['+'|'-'] DIGIT* '.' DIGIT+ [EXPONENT]
       where EXPONENT ::= ['d'|'e'|'f'|'l'|'s'] DIGIT+
       (Dot and exponent are allowed only if radix is 10.)
     for a rational number:
       ['+'|'-'] DIGIT+ '/' DIGIT+
     for a complex number:
       REAL-NUMBER {'+'|'-'} REAL-NUMBER-WITHOUT-SIGN 'i'
       REAL-NUMBER {'+'|'-'} 'i'
       {'+'|'-'} REAL-NUMBER-WITHOUT-SIGN 'i'
       {'+'|'-'} 'i'
       REAL-NUMBER '@' REAL-NUMBER
   */
  if (p == p_end)
    return false;
  /* Parse leading sign.  */
  seen_sign = false;
  if (*p == '+' || *p == '-')
    {
      p++;
      if (p == p_end)
	return false;
      seen_sign = true;
      /* Recognize complex number syntax: {'+'|'-'} 'i'  */
      if (unconstrained && (*p == 'I' || *p == 'i') && p + 1 == p_end)
	return true;
    }
  /* Parse digits before dot or exponent or slash.  */
  seen_digits = false;
  do
    {
      int c = *p;

      if (c >= '0' && c <= '9')
	c = c - '0';
      else if (c >= 'A' && c <= 'F')
	{
	  if (c >= 'D' && radix == 10) /* exponent? */
	    break;
	  c = c - 'A' + 10;
	}
      else if (c >= 'a' && c <= 'f')
	{
	  if (c >= 'd' && radix == 10) /* exponent? */
	    break;
	  c = c - 'a' + 10;
	}
      else
	break;
      if (c >= radix)
	return false;
      seen_digits = true;
      p++;
    }
  while (p < p_end);
  /* If p == p_end, we know that seen_digits = true, and the number is an
     integer without exponent.  */
  if (p < p_end)
    {
      /* If we have no digits so far, we need a decimal point later.  */
      if (!seen_digits && !(*p == '.' && radix == 10))
	return false;
      /* Trailing '#' signs are equivalent to zeroes.  */
      while (p < p_end && *p == '#')
	p++;
      if (p < p_end)
	{
	  if (*p == '/')
	    {
	      /* Parse digits after the slash.  */
	      bool all_zeroes = true;
	      p++;
	      for (; p < p_end; p++)
		{
		  int c = *p;

		  if (c >= '0' && c <= '9')
		    c = c - '0';
		  else if (c >= 'A' && c <= 'F')
		    c = c - 'A' + 10;
		  else if (c >= 'a' && c <= 'f')
		    c = c - 'a' + 10;
		  else
		    break;
		  if (c >= radix)
		    return false;
		  if (c != 0)
		    all_zeroes = false;
		}
	      /* A zero denominator is not allowed.  */
	      if (all_zeroes)
		return false;
	      /* Trailing '#' signs are equivalent to zeroes.  */
	      while (p < p_end && *p == '#')
		p++;
	    }
	  else
	    {
	      if (*p == '.')
		{
		  /* Decimal point notation.  */
		  if (radix != 10)
		    return false;
		  /* Parse digits after the decimal point.  */
		  p++;
		  for (; p < p_end; p++)
		    {
		      int c = *p;

		      if (c >= '0' && c <= '9')
			seen_digits = true;
		      else
			break;
		    }
		  /* Digits are required before or after the decimal point.  */
		  if (!seen_digits)
		    return false;
		  /* Trailing '#' signs are equivalent to zeroes.  */
		  while (p < p_end && *p == '#')
		    p++;
		}
	      if (p < p_end)
		{
		  /* Parse exponent.  */
		  switch (*p)
		    {
		    case 'D': case 'd':
		    case 'E': case 'e':
		    case 'F': case 'f':
		    case 'L': case 'l':
		    case 'S': case 's':
		      if (radix != 10)
			return false;
		      p++;
		      if (p == p_end)
			return false;
		      if (*p == '+' || *p == '-')
			{
			  p++;
			  if (p == p_end)
			    return false;
			}
		      if (!(*p >= '0' && *p <= '9'))
			return false;
		      for (;;)
			{
			  p++;
			  if (p == p_end)
			    break;
			  if (!(*p >= '0' && *p <= '9'))
			    break;
			}
		      break;
		    default:
		      break;
		    }
		}
	    }
	}
    }
  if (p == p_end)
    return true;
  /* Recognize complex number syntax.  */
  if (unconstrained)
    {
      /* Recognize the syntax  {'+'|'-'} REAL-NUMBER-WITHOUT-SIGN 'i'  */
      if (seen_sign && (*p == 'I' || *p == 'i') && p + 1 == p_end)
	return true;
      /* Recognize the syntaxes
	   REAL-NUMBER {'+'|'-'} REAL-NUMBER-WITHOUT-SIGN 'i'
	   REAL-NUMBER {'+'|'-'} 'i'
       */
      if (*p == '+' || *p == '-')
	return (p_end[-1] == 'I' || p_end[-1] == 'i')
		&& (p + 1 == p_end - 1
		    || is_other_number_syntax (p, p_end - 1 - p, radix, false));
      /* Recognize the syntax  REAL-NUMBER '@' REAL-NUMBER  */
      if (*p == '@')
	{
	  p++;
	  return is_other_number_syntax (p, p_end - p, radix, false);
	}
    }
  return false;
}

/* Tests if a token represents a number.
   Taken from guile-1.6.4/libguile/numbers.c:scm_istring2number().  */
static bool
is_number (const struct token *tp)
{
  const char *str = tp->chars;
  int len = tp->charcount;
  int radix = 10;
  enum { unknown, exact, inexact } exactness = unknown;
  bool seen_radix_prefix = false;
  bool seen_exactness_prefix = false;

  if (len == 1)
    if (*str == '+' || *str == '-')
      return false;
  while (len >= 2 && *str == '#')
    {
      switch (str[1])
	{
	case 'B': case 'b':
	  if (seen_radix_prefix)
	    return false;
	  radix = 2;
	  seen_radix_prefix = true;
	  break;
	case 'O': case 'o':
	  if (seen_radix_prefix)
	    return false;
	  radix = 8;
	  seen_radix_prefix = true;
	  break;
	case 'D': case 'd':
	  if (seen_radix_prefix)
	    return false;
	  radix = 10;
	  seen_radix_prefix = true;
	  break;
	case 'X': case 'x':
	  if (seen_radix_prefix)
	    return false;
	  radix = 16;
	  seen_radix_prefix = true;
	  break;
	case 'E': case 'e':
	  if (seen_exactness_prefix)
	    return false;
	  exactness = exact;
	  seen_exactness_prefix = true;
	  break;
	case 'I': case 'i':
	  if (seen_exactness_prefix)
	    return false;
	  exactness = inexact;
	  seen_exactness_prefix = true;
	  break;
	default:
	  return false;
	}
      str += 2;
      len -= 2;
    }
  if (exactness != inexact)
    {
      /* Try to parse an integer.  */
      if (is_integer_syntax (str, len, 10))
	return true;
      /* FIXME: Other Scheme implementations support exact rational numbers
	 or exact complex numbers.  */
    }
  if (exactness != exact)
    {
      /* Try to parse a rational, floating-point or complex number.  */
      if (is_other_number_syntax (str, len, 10, true))
	return true;
    }
  return false;
}


/* ========================= Accumulating comments ========================= */


static char *buffer;
static size_t bufmax;
static size_t buflen;

static inline void
comment_start ()
{
  buflen = 0;
}

static inline void
comment_add (int c)
{
  if (buflen >= bufmax)
    {
      bufmax = 2 * bufmax + 10;
      buffer = xrealloc (buffer, bufmax);
    }
  buffer[buflen++] = c;
}

static inline void
comment_line_end (size_t chars_to_remove)
{
  buflen -= chars_to_remove;
  while (buflen >= 1
	 && (buffer[buflen - 1] == ' ' || buffer[buflen - 1] == '\t'))
    --buflen;
  if (chars_to_remove == 0 && buflen >= bufmax)
    {
      bufmax = 2 * bufmax + 10;
      buffer = xrealloc (buffer, bufmax);
    }
  buffer[buflen] = '\0';
  savable_comment_add (buffer);
}


/* These are for tracking whether comments count as immediately before
   keyword.  */
static int last_comment_line;
static int last_non_comment_line;


/* ========================= Accumulating messages ========================= */


static message_list_ty *mlp;


/* ========================== Reading of objects.  ========================= */


/* We are only interested in symbols (e.g. gettext or ngettext) and strings.
   Other objects need not to be represented precisely.  */
enum object_type
{
  t_symbol,	/* symbol */
  t_string,	/* string */
  t_other,	/* other kind of real object */
  t_dot,	/* '.' pseudo object */
  t_close,	/* ')' pseudo object */
  t_eof		/* EOF marker */
};

struct object
{
  enum object_type type;
  struct token *token;		/* for t_symbol and t_string */
  int line_number_at_start;	/* for t_string */
};

/* Free the memory pointed to by a 'struct object'.  */
static inline void
free_object (struct object *op)
{
  if (op->type == t_symbol || op->type == t_string)
    {
      free_token (op->token);
      free (op->token);
    }
}

/* Convert a t_symbol/t_string token to a char*.  */
static char *
string_of_object (const struct object *op)
{
  char *str;
  int n;

  if (!(op->type == t_symbol || op->type == t_string))
    abort ();
  n = op->token->charcount;
  str = (char *) xmalloc (n + 1);
  memcpy (str, op->token->chars, n);
  str[n] = '\0';
  return str;
}

/* Context lookup table.  */
static flag_context_list_table_ty *flag_context_list_table;

/* Read the next object.  */
static void
read_object (struct object *op, flag_context_ty outer_context)
{
  for (;;)
    {
      int c = do_getc ();

      switch (c)
	{
	case EOF:
	  op->type = t_eof;
	  return;

	case ' ': case '\r': case '\f': case '\t':
	  continue;

	case '\n':
	  /* Comments assumed to be grouped with a message must immediately
	     precede it, with no non-whitespace token on a line between
	     both.  */
	  if (last_non_comment_line > last_comment_line)
	    savable_comment_reset ();
	  continue;

	case ';':
	  {
	    bool all_semicolons = true;

	    last_comment_line = line_number;
	    comment_start ();
	    for (;;)
	      {
		c = do_getc ();
		if (c == EOF || c == '\n')
		  break;
		if (c != ';')
		  all_semicolons = false;
		if (!all_semicolons)
		  {
		    /* We skip all leading white space, but not EOLs.  */
		    if (!(buflen == 0 && (c == ' ' || c == '\t')))
		      comment_add (c);
		  }
	      }
	    comment_line_end (0);
	    continue;
	  }

	case '(':
	  {
	     int arg = 0;		/* Current argument number.  */
	     flag_context_list_iterator_ty context_iter;
	    const struct callshapes *shapes = NULL;
	    struct arglist_parser *argparser = NULL;

	     for (;; arg++)
	       {
		struct object inner;
		flag_context_ty inner_context;

		if (arg == 0)
		  inner_context = null_context;
		else
		  inner_context =
		    inherited_context (outer_context,
				       flag_context_list_iterator_advance (
					 &context_iter));

		read_object (&inner, inner_context);

		/* Recognize end of list.  */
		if (inner.type == t_close)
		  {
		    op->type = t_other;
		    last_non_comment_line = line_number;
		    if (argparser != NULL)
		      arglist_parser_done (argparser, arg);
		    return;
		  }

		/* Dots are not allowed in every position.
		   But be tolerant.  */

		/* EOF inside list is illegal.
		   But be tolerant.  */
		if (inner.type == t_eof)
		  break;

		if (arg == 0)
		  {
		    /* This is the function position.  */
		    if (inner.type == t_symbol)
		      {
			char *symbol_name = string_of_object (&inner);
			void *keyword_value;

			if (hash_find_entry (&keywords,
					     symbol_name, strlen (symbol_name),
					     &keyword_value)
			    == 0)
			  shapes = (const struct callshapes *) keyword_value;

			argparser = arglist_parser_alloc (mlp, shapes);

			context_iter =
			  flag_context_list_iterator (
			    flag_context_list_table_lookup (
			      flag_context_list_table,
			      symbol_name, strlen (symbol_name)));

			free (symbol_name);
		      }
		    else
		      context_iter = null_context_list_iterator;
		  }
		else
		  {
		    /* These are the argument positions.  */
		    if (argparser != NULL && inner.type == t_string)
		      arglist_parser_remember (argparser, arg,
					       string_of_object (&inner),
					       inner_context,
					       logical_file_name,
					       inner.line_number_at_start,
					       savable_comment);
		  }

		free_object (&inner);
	      }
	    if (argparser != NULL)
	      arglist_parser_done (argparser, arg);
	  }
	  op->type = t_other;
	  last_non_comment_line = line_number;
	  return;

	case ')':
	  /* Tell the caller about the end of list.
	     Unmatched closing parenthesis is illegal.
	     But be tolerant.  */
	  op->type = t_close;
	  last_non_comment_line = line_number;
	  return;

	case ',':
	  {
	    int c = do_getc ();
	    /* The ,@ handling inside lists is wrong anyway, because
	       ,@form expands to an unknown number of elements.  */
	    if (c != EOF && c != '@')
	      do_ungetc (c);
	  }
	  /*FALLTHROUGH*/
	case '\'':
	case '`':
	  {
	    struct object inner;

	    read_object (&inner, null_context);

	    /* Dots and EOF are not allowed here.  But be tolerant.  */

	    free_object (&inner);

	    op->type = t_other;
	    last_non_comment_line = line_number;
	    return;
	  }

	case '#':
	  /* Dispatch macro handling.  */
	  {
	    c = do_getc ();
	    if (c == EOF)
	      /* Invalid input.  Be tolerant, no error message.  */
	      {
		op->type = t_other;
		return;
	      }

	    switch (c)
	      {
	      case '(': /* Vector */
		do_ungetc (c);
		{
		  struct object inner;
		  read_object (&inner, null_context);
		  /* Dots and EOF are not allowed here.
		     But be tolerant.  */
		  free_object (&inner);
		  op->type = t_other;
		  last_non_comment_line = line_number;
		  return;
		}

	      case 'T': case 't': /* Boolean true */
	      case 'F': case 'f': /* Boolean false */
		op->type = t_other;
		last_non_comment_line = line_number;
		return;

	      case 'B': case 'b':
	      case 'O': case 'o':
	      case 'D': case 'd':
	      case 'X': case 'x':
	      case 'E': case 'e':
	      case 'I': case 'i':
		{
		  struct token token;
		  do_ungetc (c);
		  read_token (&token, '#');
		  if (is_number (&token))
		    {
		      /* A number.  */
		      free_token (&token);
		      op->type = t_other;
		      last_non_comment_line = line_number;
		      return;
		    }
		  else
		    {
		      if (token.charcount == 2
			  && (token.chars[1] == 'e' || token.chars[1] == 'i'))
			{
			  c = do_getc ();
			  if (c != EOF)
			    do_ungetc (c);
			  if (c == '(')
			    /* Homogenous vector syntax, see arrays.scm.  */
			    case 'a':	/* Vectors of char */
			    case 'c':	/* Vectors of complex */
			  /*case 'e':*/	/* Vectors of long */
			    case 'h':	/* Vectors of short */
			  /*case 'i':*/	/* Vectors of double-float */
			    case 'l':	/* Vectors of long long */
			    case 's':	/* Vectors of single-float */
			    case 'u':	/* Vectors of unsigned long */
			    case 'y':	/* Vectors of byte */
			      {
				struct object inner;
				read_object (&inner, null_context);
				/* Dots and EOF are not allowed here.
				   But be tolerant.  */
				free_token (&token);
				free_object (&inner);
				op->type = t_other;
				last_non_comment_line = line_number;
				return;
			      }
			}
		      /* Unknown # object.  But be tolerant.  */
		      free_token (&token);
		      op->type = t_other;
		      last_non_comment_line = line_number;
		      return;
		    }
		}

	      case '!':
		/* Block comment '#! ... \n!#\n'.  We don't extract it
		   because it's only used to introduce scripts on Unix.  */
		{
		  int last1 = 0;
		  int last2 = 0;
		  int last3 = 0;

		  for (;;)
		    {
		      c = do_getc ();
		      if (c == EOF)
			/* EOF is not allowed here.  But be tolerant.  */
			break;
		      if (last3 == '\n' && last2 == '!' && last1 == '#'
			  && c == '\n')
			break;
		      last3 = last2;
		      last2 = last1;
		      last1 = c;
		    }
		  continue;
		}

	      case '*':
		/* Bit vector.  */
		{
		  struct token token;
		  read_token (&token, c);
		  /* The token should consists only of '0' and '1', except
		     for the initial '*'.  But be tolerant.  */
		  free_token (&token);
		  op->type = t_other;
		  last_non_comment_line = line_number;
		  return;
		}

	      case '{':
		/* Symbol with multiple escapes: #{...}#  */
		{
		  op->token = (struct token *) xmalloc (sizeof (struct token));

		  init_token (op->token);

		  for (;;)
		    {
		      c = do_getc ();

		      if (c == EOF)
			break;
		      if (c == '\\')
			{
			  c = do_getc ();
			  if (c == EOF)
			    break;
			}
		      else if (c == '}')
			{
			  c = do_getc ();
			  if (c == '#')
			    break;
			  if (c != EOF)
			    do_ungetc (c);
			  c = '}';
			}
		      grow_token (op->token);
		      op->token->chars[op->token->charcount++] = c;
		    }

		  op->type = t_symbol;
		  last_non_comment_line = line_number;
		  return;
		}

	      case '\\':
		/* Character.  */
		{
		  struct token token;
		  c = do_getc ();
		  if (c != EOF)
		    {
		      read_token (&token, c);
		      free_token (&token);
		    }
		  op->type = t_other;
		  last_non_comment_line = line_number;
		  return;
		}

	      case ':': /* Keyword.  */
	      case '&': /* Deprecated keyword, installed in optargs.scm.  */
		{
		  struct token token;
		  read_token (&token, '-');
		  free_token (&token);
		  op->type = t_other;
		  last_non_comment_line = line_number;
		  return;
		}

	      /* The following are installed through read-hash-extend.  */

	      /* arrays.scm */
	      case '0': case '1': case '2': case '3': case '4':
	      case '5': case '6': case '7': case '8': case '9':
		/* Multidimensional array syntax: #nx(...) where
		     n ::= DIGIT+
		     x ::= {'a'|'b'|'c'|'e'|'i'|'s'|'u'}
		 */
		do
		  c = do_getc ();
		while (c >= '0' && c <= '9');
		/* c should be one of {'a'|'b'|'c'|'e'|'i'|'s'|'u'}.
		   But be tolerant.  */
		/*FALLTHROUGH*/
	      case '\'': /* boot-9.scm */
	      case '.': /* boot-9.scm */
	      case ',': /* srfi-10.scm */
		{
		  struct object inner;
		  read_object (&inner, null_context);
		  /* Dots and EOF are not allowed here.
		     But be tolerant.  */
		  free_object (&inner);
		  op->type = t_other;
		  last_non_comment_line = line_number;
		  return;
		}

	      default:
		/* Unknown.  */
		op->type = t_other;
		last_non_comment_line = line_number;
		return;
	      }
	    /*NOTREACHED*/
	    abort ();
	  }

	case '"':
	  {
	    op->token = (struct token *) xmalloc (sizeof (struct token));
	    init_token (op->token);
	    op->line_number_at_start = line_number;
	    for (;;)
	      {
		int c = do_getc ();
		if (c == EOF)
		  /* Invalid input.  Be tolerant, no error message.  */
		  break;
		if (c == '"')
		  break;
		if (c == '\\')
		  {
		    c = do_getc ();
		    if (c == EOF)
		      /* Invalid input.  Be tolerant, no error message.  */
		      break;
		    switch (c)
		      {
		      case '\n':
			continue;
		      case '0':
			c = '\0';
			break;
		      case 'a':
			c = '\a';
			break;
		      case 'f':
			c = '\f';
			break;
		      case 'n':
			c = '\n';
			break;
		      case 'r':
			c = '\r';
			break;
		      case 't':
			c = '\t';
			break;
		      case 'v':
			c = '\v';
			break;
		      default:
			break;
		      }
		  }
		grow_token (op->token);
		op->token->chars[op->token->charcount++] = c;
	      }
	    op->type = t_string;

	    if (extract_all)
	      {
		lex_pos_ty pos;

		pos.file_name = logical_file_name;
		pos.line_number = op->line_number_at_start;
		remember_a_message (mlp, NULL, string_of_object (op),
				    null_context, &pos, savable_comment);
	      }
	    last_non_comment_line = line_number;
	    return;
	  }

	case '0': case '1': case '2': case '3': case '4':
	case '5': case '6': case '7': case '8': case '9':
	case '+': case '-': case '.':
	  /* Read a number or symbol token.  */
	  op->token = (struct token *) xmalloc (sizeof (struct token));
	  read_token (op->token, c);
	  if (op->token->charcount == 1 && op->token->chars[0] == '.')
	    {
	      free_token (op->token);
	      free (op->token);
	      op->type = t_dot;
	    }
	  else if (is_number (op->token))
	    {
	      /* A number.  */
	      free_token (op->token);
	      free (op->token);
	      op->type = t_other;
	    }
	  else
	    {
	      /* A symbol.  */
	      op->type = t_symbol;
	    }
	  last_non_comment_line = line_number;
	  return;

	case ':':
	default:
	  /* Read a symbol token.  */
	  op->token = (struct token *) xmalloc (sizeof (struct token));
	  read_token (op->token, c);
	  op->type = t_symbol;
	  last_non_comment_line = line_number;
	  return;
	}
    }
}


void
extract_scheme (FILE *f,
		const char *real_filename, const char *logical_filename,
		flag_context_list_table_ty *flag_table,
		msgdomain_list_ty *mdlp)
{
  mlp = mdlp->item[0]->messages;

  fp = f;
  real_file_name = real_filename;
  logical_file_name = xstrdup (logical_filename);
  line_number = 1;

  last_comment_line = -1;
  last_non_comment_line = -1;

  flag_context_list_table = flag_table;

  init_keywords ();

  /* Eat tokens until eof is seen.  When read_object returns
     due to an unbalanced closing parenthesis, just restart it.  */
  do
    {
      struct object toplevel_object;

      read_object (&toplevel_object, null_context);

      if (toplevel_object.type == t_eof)
	break;

      free_object (&toplevel_object);
    }
  while (!feof (fp));

  /* Close scanner.  */
  fp = NULL;
  real_file_name = NULL;
  logical_file_name = NULL;
  line_number = 0;
}