summaryrefslogtreecommitdiff
path: root/src/wc.c
blob: 412bda0db540ffc7d0387c7414f30a23f7b9b9b0 (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
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
/* wc - print the number of lines, words, and bytes in files
   Copyright (C) 1985-2016 Free Software Foundation, Inc.

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

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

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

/* Written by Paul Rubin, phr@ocf.berkeley.edu
   and David MacKenzie, djm@gnu.ai.mit.edu. */

#include <config.h>

#include <stdio.h>
#include <assert.h>
#include <getopt.h>
#include <sys/types.h>
#include <wchar.h>
#include <wctype.h>

#include "system.h"
#include "argv-iter.h"
#include "die.h"
#include "error.h"
#include "fadvise.h"
#include "mbchar.h"
#include "physmem.h"
#include "readtokens0.h"
#include "safe-read.h"
#include "stat-size.h"
#include "xfreopen.h"

#if !defined iswspace && !HAVE_ISWSPACE
# define iswspace(wc) \
    ((wc) == to_uchar (wc) && isspace (to_uchar (wc)))
#endif

/* The official name of this program (e.g., no 'g' prefix).  */
#define PROGRAM_NAME "wc"

#define AUTHORS \
  proper_name ("Paul Rubin"), \
  proper_name ("David MacKenzie")

/* Size of atomic reads. */
#define BUFFER_SIZE (16 * 1024)

/* Cumulative number of lines, words, chars and bytes in all files so far.
   max_line_length is the maximum over all files processed so far.  */
static uintmax_t total_lines;
static uintmax_t total_words;
static uintmax_t total_chars;
static uintmax_t total_bytes;
static uintmax_t max_line_length;

/* Which counts to print. */
static bool print_lines, print_words, print_chars, print_bytes;
static bool print_linelength;

/* The print width of each count.  */
static int number_width;

/* True if we have ever read the standard input. */
static bool have_read_stdin;

/* The result of calling fstat or stat on a file descriptor or file.  */
struct fstatus
{
  /* If positive, fstat or stat has not been called yet.  Otherwise,
     this is the value returned from fstat or stat.  */
  int failed;

  /* If FAILED is zero, this is the file's status.  */
  struct stat st;
};

/* For long options that have no equivalent short option, use a
   non-character as a pseudo short option, starting with CHAR_MAX + 1.  */
enum
{
  FILES0_FROM_OPTION = CHAR_MAX + 1
};

static struct option const longopts[] =
{
  {"bytes", no_argument, NULL, 'c'},
  {"chars", no_argument, NULL, 'm'},
  {"lines", no_argument, NULL, 'l'},
  {"words", no_argument, NULL, 'w'},
  {"files0-from", required_argument, NULL, FILES0_FROM_OPTION},
  {"max-line-length", no_argument, NULL, 'L'},
  {GETOPT_HELP_OPTION_DECL},
  {GETOPT_VERSION_OPTION_DECL},
  {NULL, 0, NULL, 0}
};

void
usage (int status)
{
  if (status != EXIT_SUCCESS)
    emit_try_help ();
  else
    {
      printf (_("\
Usage: %s [OPTION]... [FILE]...\n\
  or:  %s [OPTION]... --files0-from=F\n\
"),
              program_name, program_name);
      fputs (_("\
Print newline, word, and byte counts for each FILE, and a total line if\n\
more than one FILE is specified.  A word is a non-zero-length sequence of\n\
characters delimited by white space.\n\
"), stdout);

      emit_stdin_note ();

      fputs (_("\
\n\
The options below may be used to select which counts are printed, always in\n\
the following order: newline, word, character, byte, maximum line length.\n\
  -c, --bytes            print the byte counts\n\
  -m, --chars            print the character counts\n\
  -l, --lines            print the newline counts\n\
"), stdout);
      fputs (_("\
      --files0-from=F    read input from the files specified by\n\
                           NUL-terminated names in file F;\n\
                           If F is - then read names from standard input\n\
  -L, --max-line-length  print the maximum display width\n\
  -w, --words            print the word counts\n\
"), stdout);
      fputs (HELP_OPTION_DESCRIPTION, stdout);
      fputs (VERSION_OPTION_DESCRIPTION, stdout);
      emit_ancillary_info (PROGRAM_NAME);
    }
  exit (status);
}

/* FILE is the name of the file (or NULL for standard input)
   associated with the specified counters.  */
static void
write_counts (uintmax_t lines,
              uintmax_t words,
              uintmax_t chars,
              uintmax_t bytes,
              uintmax_t linelength,
              const char *file)
{
  static char const format_sp_int[] = " %*s";
  char const *format_int = format_sp_int + 1;
  char buf[INT_BUFSIZE_BOUND (uintmax_t)];

  if (print_lines)
    {
      printf (format_int, number_width, umaxtostr (lines, buf));
      format_int = format_sp_int;
    }
  if (print_words)
    {
      printf (format_int, number_width, umaxtostr (words, buf));
      format_int = format_sp_int;
    }
  if (print_chars)
    {
      printf (format_int, number_width, umaxtostr (chars, buf));
      format_int = format_sp_int;
    }
  if (print_bytes)
    {
      printf (format_int, number_width, umaxtostr (bytes, buf));
      format_int = format_sp_int;
    }
  if (print_linelength)
    {
      printf (format_int, number_width, umaxtostr (linelength, buf));
    }
  if (file)
    printf (" %s", strchr (file, '\n') ? quotef (file) : file);
  putchar ('\n');
}

/* Count words.  FILE_X is the name of the file (or NULL for standard
   input) that is open on descriptor FD.  *FSTATUS is its status.
   CURRENT_POS is the current file offset if known, negative if unknown.
   Return true if successful.  */
static bool
wc (int fd, char const *file_x, struct fstatus *fstatus, off_t current_pos)
{
  bool ok = true;
  char buf[BUFFER_SIZE + 1];
  size_t bytes_read;
  uintmax_t lines, words, chars, bytes, linelength;
  bool count_bytes, count_chars, count_complicated;
  char const *file = file_x ? file_x : _("standard input");

  lines = words = chars = bytes = linelength = 0;

  /* If in the current locale, chars are equivalent to bytes, we prefer
     counting bytes, because that's easier.  */
#if MB_LEN_MAX > 1
  if (MB_CUR_MAX > 1)
    {
      count_bytes = print_bytes;
      count_chars = print_chars;
    }
  else
#endif
    {
      count_bytes = print_bytes || print_chars;
      count_chars = false;
    }
  count_complicated = print_words || print_linelength;

  /* Advise the kernel of our access pattern only if we will read().  */
  if (!count_bytes || count_chars || print_lines || count_complicated)
    fdadvise (fd, 0, 0, FADVISE_SEQUENTIAL);

  /* When counting only bytes, save some line- and word-counting
     overhead.  If FD is a 'regular' Unix file, using lseek is enough
     to get its 'size' in bytes.  Otherwise, read blocks of BUFFER_SIZE
     bytes at a time until EOF.  Note that the 'size' (number of bytes)
     that wc reports is smaller than stats.st_size when the file is not
     positioned at its beginning.  That's why the lseek calls below are
     necessary.  For example the command
     '(dd ibs=99k skip=1 count=0; ./wc -c) < /etc/group'
     should make wc report '0' bytes.  */

  if (count_bytes && !count_chars && !print_lines && !count_complicated)
    {
      if (0 < fstatus->failed)
        fstatus->failed = fstat (fd, &fstatus->st);

      /* For sized files, seek to one st_blksize before EOF rather than to EOF.
         This works better for files in proc-like file systems where
         the size is only approximate.  */
      if (! fstatus->failed && usable_st_size (&fstatus->st)
          && 0 <= fstatus->st.st_size)
        {
          size_t end_pos = fstatus->st.st_size;
          off_t hi_pos = end_pos - end_pos % (ST_BLKSIZE (fstatus->st) + 1);
          if (current_pos < 0)
            current_pos = lseek (fd, 0, SEEK_CUR);
          if (0 <= current_pos && current_pos < hi_pos
              && 0 <= lseek (fd, hi_pos, SEEK_CUR))
            bytes = hi_pos - current_pos;
        }

      fdadvise (fd, 0, 0, FADVISE_SEQUENTIAL);
      while ((bytes_read = safe_read (fd, buf, BUFFER_SIZE)) > 0)
        {
          if (bytes_read == SAFE_READ_ERROR)
            {
              error (0, errno, "%s", quotef (file));
              ok = false;
              break;
            }
          bytes += bytes_read;
        }
    }
  else if (!count_chars && !count_complicated)
    {
      /* Use a separate loop when counting only lines or lines and bytes --
         but not chars or words.  */
      bool long_lines = false;
      while ((bytes_read = safe_read (fd, buf, BUFFER_SIZE)) > 0)
        {
          if (bytes_read == SAFE_READ_ERROR)
            {
              error (0, errno, "%s", quotef (file));
              ok = false;
              break;
            }

          bytes += bytes_read;

          char *p = buf;
          char *end = p + bytes_read;
          uintmax_t plines = lines;

          if (! long_lines)
            {
              /* Avoid function call overhead for shorter lines.  */
              while (p != end)
                lines += *p++ == '\n';
            }
          else
            {
              /* memchr is more efficient with longer lines.  */
              while ((p = memchr (p, '\n', end - p)))
                {
                  ++p;
                  ++lines;
                }
            }

          /* If the average line length in the block is >= 15, then use
             memchr for the next block, where system specific optimizations
             may outweigh function call overhead.
             FIXME: This line length was determined in 2015, on both
             x86_64 and ppc64, but it's worth re-evaluating in future with
             newer compilers, CPUs, or memchr() implementations etc.  */
          if (lines - plines <= bytes_read / 15)
            long_lines = true;
          else
            long_lines = false;
        }
    }
#if MB_LEN_MAX > 1
# define SUPPORT_OLD_MBRTOWC 1
  else if (MB_CUR_MAX > 1)
    {
      bool in_word = false;
      uintmax_t linepos = 0;
      mbstate_t state = { 0, };
      bool in_shift = false;
# if SUPPORT_OLD_MBRTOWC
      /* Back-up the state before each multibyte character conversion and
         move the last incomplete character of the buffer to the front
         of the buffer.  This is needed because we don't know whether
         the 'mbrtowc' function updates the state when it returns -2, --
         this is the ISO C 99 and glibc-2.2 behaviour - or not - amended
         ANSI C, glibc-2.1 and Solaris 5.7 behaviour.  We don't have an
         autoconf test for this, yet.  */
      size_t prev = 0; /* number of bytes carried over from previous round */
# else
      const size_t prev = 0;
# endif

      while ((bytes_read = safe_read (fd, buf + prev, BUFFER_SIZE - prev)) > 0)
        {
          const char *p;
# if SUPPORT_OLD_MBRTOWC
          mbstate_t backup_state;
# endif
          if (bytes_read == SAFE_READ_ERROR)
            {
              error (0, errno, "%s", quotef (file));
              ok = false;
              break;
            }

          bytes += bytes_read;
          p = buf;
          bytes_read += prev;
          do
            {
              wchar_t wide_char;
              size_t n;

              if (!in_shift && is_basic (*p))
                {
                  /* Handle most ASCII characters quickly, without calling
                     mbrtowc().  */
                  n = 1;
                  wide_char = *p;
                }
              else
                {
                  in_shift = true;
# if SUPPORT_OLD_MBRTOWC
                  backup_state = state;
# endif
                  n = mbrtowc (&wide_char, p, bytes_read, &state);
                  if (n == (size_t) -2)
                    {
# if SUPPORT_OLD_MBRTOWC
                      state = backup_state;
# endif
                      break;
                    }
                  if (n == (size_t) -1)
                    {
                      /* Remember that we read a byte, but don't complain
                         about the error.  Because of the decoding error,
                         this is a considered to be byte but not a
                         character (that is, chars is not incremented).  */
                      p++;
                      bytes_read--;
                      continue;
                    }
                  if (mbsinit (&state))
                    in_shift = false;
                  if (n == 0)
                    {
                      wide_char = 0;
                      n = 1;
                    }
                }
              p += n;
              bytes_read -= n;
              chars++;
              switch (wide_char)
                {
                case '\n':
                  lines++;
                  /* Fall through. */
                case '\r':
                case '\f':
                  if (linepos > linelength)
                    linelength = linepos;
                  linepos = 0;
                  goto mb_word_separator;
                case '\t':
                  linepos += 8 - (linepos % 8);
                  goto mb_word_separator;
                case ' ':
                  linepos++;
                  /* Fall through. */
                case '\v':
                mb_word_separator:
                  words += in_word;
                  in_word = false;
                  break;
                default:
                  if (iswprint (wide_char))
                    {
                      int width = wcwidth (wide_char);
                      if (width > 0)
                        linepos += width;
                      if (iswspace (wide_char))
                        goto mb_word_separator;
                      in_word = true;
                    }
                  break;
                }
            }
          while (bytes_read > 0);

# if SUPPORT_OLD_MBRTOWC
          if (bytes_read > 0)
            {
              if (bytes_read == BUFFER_SIZE)
                {
                  /* Encountered a very long redundant shift sequence.  */
                  p++;
                  bytes_read--;
                }
              memmove (buf, p, bytes_read);
            }
          prev = bytes_read;
# endif
        }
      if (linepos > linelength)
        linelength = linepos;
      words += in_word;
    }
#endif
  else
    {
      bool in_word = false;
      uintmax_t linepos = 0;

      while ((bytes_read = safe_read (fd, buf, BUFFER_SIZE)) > 0)
        {
          const char *p = buf;
          if (bytes_read == SAFE_READ_ERROR)
            {
              error (0, errno, "%s", quotef (file));
              ok = false;
              break;
            }

          bytes += bytes_read;
          do
            {
              switch (*p++)
                {
                case '\n':
                  lines++;
                  /* Fall through. */
                case '\r':
                case '\f':
                  if (linepos > linelength)
                    linelength = linepos;
                  linepos = 0;
                  goto word_separator;
                case '\t':
                  linepos += 8 - (linepos % 8);
                  goto word_separator;
                case ' ':
                  linepos++;
                  /* Fall through. */
                case '\v':
                word_separator:
                  words += in_word;
                  in_word = false;
                  break;
                default:
                  if (isprint (to_uchar (p[-1])))
                    {
                      linepos++;
                      if (isspace (to_uchar (p[-1])))
                        goto word_separator;
                      in_word = true;
                    }
                  break;
                }
            }
          while (--bytes_read);
        }
      if (linepos > linelength)
        linelength = linepos;
      words += in_word;
    }

  if (count_chars < print_chars)
    chars = bytes;

  write_counts (lines, words, chars, bytes, linelength, file_x);
  total_lines += lines;
  total_words += words;
  total_chars += chars;
  total_bytes += bytes;
  if (linelength > max_line_length)
    max_line_length = linelength;

  return ok;
}

static bool
wc_file (char const *file, struct fstatus *fstatus)
{
  if (! file || STREQ (file, "-"))
    {
      have_read_stdin = true;
      if (O_BINARY && ! isatty (STDIN_FILENO))
        xfreopen (NULL, "rb", stdin);
      return wc (STDIN_FILENO, file, fstatus, -1);
    }
  else
    {
      int fd = open (file, O_RDONLY | O_BINARY);
      if (fd == -1)
        {
          error (0, errno, "%s", quotef (file));
          return false;
        }
      else
        {
          bool ok = wc (fd, file, fstatus, 0);
          if (close (fd) != 0)
            {
              error (0, errno, "%s", quotef (file));
              return false;
            }
          return ok;
        }
    }
}

/* Return the file status for the NFILES files addressed by FILE.
   Optimize the case where only one number is printed, for just one
   file; in that case we can use a print width of 1, so we don't need
   to stat the file.  Handle the case of (nfiles == 0) in the same way;
   that happens when we don't know how long the list of file names will be.  */

static struct fstatus *
get_input_fstatus (size_t nfiles, char *const *file)
{
  struct fstatus *fstatus = xnmalloc (nfiles ? nfiles : 1, sizeof *fstatus);

  if (nfiles == 0
      || (nfiles == 1
          && ((print_lines + print_words + print_chars
               + print_bytes + print_linelength)
              == 1)))
    fstatus[0].failed = 1;
  else
    {
      size_t i;

      for (i = 0; i < nfiles; i++)
        fstatus[i].failed = (! file[i] || STREQ (file[i], "-")
                             ? fstat (STDIN_FILENO, &fstatus[i].st)
                             : stat (file[i], &fstatus[i].st));
    }

  return fstatus;
}

/* Return a print width suitable for the NFILES files whose status is
   recorded in FSTATUS.  Optimize the same special case that
   get_input_fstatus optimizes.  */

static int _GL_ATTRIBUTE_PURE
compute_number_width (size_t nfiles, struct fstatus const *fstatus)
{
  int width = 1;

  if (0 < nfiles && fstatus[0].failed <= 0)
    {
      int minimum_width = 1;
      uintmax_t regular_total = 0;
      size_t i;

      for (i = 0; i < nfiles; i++)
        if (! fstatus[i].failed)
          {
            if (S_ISREG (fstatus[i].st.st_mode))
              regular_total += fstatus[i].st.st_size;
            else
              minimum_width = 7;
          }

      for (; 10 <= regular_total; regular_total /= 10)
        width++;
      if (width < minimum_width)
        width = minimum_width;
    }

  return width;
}


int
main (int argc, char **argv)
{
  bool ok;
  int optc;
  size_t nfiles;
  char **files;
  char *files_from = NULL;
  struct fstatus *fstatus;
  struct Tokens tok;

  initialize_main (&argc, &argv);
  set_program_name (argv[0]);
  setlocale (LC_ALL, "");
  bindtextdomain (PACKAGE, LOCALEDIR);
  textdomain (PACKAGE);

  atexit (close_stdout);

  /* Line buffer stdout to ensure lines are written atomically and immediately
     so that processes running in parallel do not intersperse their output.  */
  setvbuf (stdout, NULL, _IOLBF, 0);

  print_lines = print_words = print_chars = print_bytes = false;
  print_linelength = false;
  total_lines = total_words = total_chars = total_bytes = max_line_length = 0;

  while ((optc = getopt_long (argc, argv, "clLmw", longopts, NULL)) != -1)
    switch (optc)
      {
      case 'c':
        print_bytes = true;
        break;

      case 'm':
        print_chars = true;
        break;

      case 'l':
        print_lines = true;
        break;

      case 'w':
        print_words = true;
        break;

      case 'L':
        print_linelength = true;
        break;

      case FILES0_FROM_OPTION:
        files_from = optarg;
        break;

      case_GETOPT_HELP_CHAR;

      case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);

      default:
        usage (EXIT_FAILURE);
      }

  if (! (print_lines || print_words || print_chars || print_bytes
         || print_linelength))
    print_lines = print_words = print_bytes = true;

  bool read_tokens = false;
  struct argv_iterator *ai;
  if (files_from)
    {
      FILE *stream;

      /* When using --files0-from=F, you may not specify any files
         on the command-line.  */
      if (optind < argc)
        {
          error (0, 0, _("extra operand %s"), quoteaf (argv[optind]));
          fprintf (stderr, "%s\n",
                   _("file operands cannot be combined with --files0-from"));
          usage (EXIT_FAILURE);
        }

      if (STREQ (files_from, "-"))
        stream = stdin;
      else
        {
          stream = fopen (files_from, "r");
          if (stream == NULL)
            die (EXIT_FAILURE, errno, _("cannot open %s for reading"),
                 quoteaf (files_from));
        }

      /* Read the file list into RAM if we can detect its size and that
         size is reasonable.  Otherwise, we'll read a name at a time.  */
      struct stat st;
      if (fstat (fileno (stream), &st) == 0
          && S_ISREG (st.st_mode)
          && st.st_size <= MIN (10 * 1024 * 1024, physmem_available () / 2))
        {
          read_tokens = true;
          readtokens0_init (&tok);
          if (! readtokens0 (stream, &tok) || fclose (stream) != 0)
            die (EXIT_FAILURE, 0, _("cannot read file names from %s"),
                 quoteaf (files_from));
          files = tok.tok;
          nfiles = tok.n_tok;
          ai = argv_iter_init_argv (files);
        }
      else
        {
          files = NULL;
          nfiles = 0;
          ai = argv_iter_init_stream (stream);
        }
    }
  else
    {
      static char *stdin_only[] = { NULL };
      files = (optind < argc ? argv + optind : stdin_only);
      nfiles = (optind < argc ? argc - optind : 1);
      ai = argv_iter_init_argv (files);
    }

  if (!ai)
    xalloc_die ();

  fstatus = get_input_fstatus (nfiles, files);
  number_width = compute_number_width (nfiles, fstatus);

  int i;
  ok = true;
  for (i = 0; /* */; i++)
    {
      bool skip_file = false;
      enum argv_iter_err ai_err;
      char *file_name = argv_iter (ai, &ai_err);
      if (!file_name)
        {
          switch (ai_err)
            {
            case AI_ERR_EOF:
              goto argv_iter_done;
            case AI_ERR_READ:
              error (0, errno, _("%s: read error"),
                     quotef (files_from));
              ok = false;
              goto argv_iter_done;
            case AI_ERR_MEM:
              xalloc_die ();
            default:
              assert (!"unexpected error code from argv_iter");
            }
        }
      if (files_from && STREQ (files_from, "-") && STREQ (file_name, "-"))
        {
          /* Give a better diagnostic in an unusual case:
             printf - | wc --files0-from=- */
          error (0, 0, _("when reading file names from stdin, "
                         "no file name of %s allowed"),
                 quoteaf (file_name));
          skip_file = true;
        }

      if (!file_name[0])
        {
          /* Diagnose a zero-length file name.  When it's one
             among many, knowing the record number may help.
             FIXME: currently print the record number only with
             --files0-from=FILE.  Maybe do it for argv, too?  */
          if (files_from == NULL)
            error (0, 0, "%s", _("invalid zero-length file name"));
          else
            {
              /* Using the standard 'filename:line-number:' prefix here is
                 not totally appropriate, since NUL is the separator, not NL,
                 but it might be better than nothing.  */
              unsigned long int file_number = argv_iter_n_args (ai);
              error (0, 0, "%s:%lu: %s", quotef (files_from),
                     file_number, _("invalid zero-length file name"));
            }
          skip_file = true;
        }

      if (skip_file)
        ok = false;
      else
        ok &= wc_file (file_name, &fstatus[nfiles ? i : 0]);
    }
 argv_iter_done:

  /* No arguments on the command line is fine.  That means read from stdin.
     However, no arguments on the --files0-from input stream is an error
     means don't read anything.  */
  if (ok && !files_from && argv_iter_n_args (ai) == 0)
    ok &= wc_file (NULL, &fstatus[0]);

  if (read_tokens)
    readtokens0_free (&tok);

  if (1 < argv_iter_n_args (ai))
    write_counts (total_lines, total_words, total_chars, total_bytes,
                  max_line_length, _("total"));

  argv_iter_free (ai);

  free (fstatus);

  if (have_read_stdin && close (STDIN_FILENO) != 0)
    die (EXIT_FAILURE, errno, "-");

  return ok ? EXIT_SUCCESS : EXIT_FAILURE;
}