summaryrefslogtreecommitdiff
path: root/src/uniq.c
blob: 0e118da9d1cf902129ad3d3a197c4f749b946dad (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
/* uniq -- remove duplicate lines from a sorted file
   Copyright (C) 1986-2016 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 Richard M. Stallman and David MacKenzie. */

#include <config.h>

#include <getopt.h>
#include <sys/types.h>

#include "system.h"
#include "argmatch.h"
#include "linebuffer.h"
#include "error.h"
#include "fadvise.h"
#include "hard-locale.h"
#include "posixver.h"
#include "stdio--.h"
#include "xmemcoll.h"
#include "xstrtol.h"
#include "memcasecmp.h"
#include "quote.h"

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

#define AUTHORS \
  proper_name ("Richard M. Stallman"), \
  proper_name ("David MacKenzie")

#define SWAP_LINES(A, B)			\
  do						\
    {						\
      struct linebuffer *_tmp;			\
      _tmp = (A);				\
      (A) = (B);				\
      (B) = _tmp;				\
    }						\
  while (0)

/* True if the LC_COLLATE locale is hard.  */
static bool hard_LC_COLLATE;

/* Number of fields to skip on each line when doing comparisons. */
static size_t skip_fields;

/* Number of chars to skip after skipping any fields. */
static size_t skip_chars;

/* Number of chars to compare. */
static size_t check_chars;

enum countmode
{
  count_occurrences,		/* -c Print count before output lines. */
  count_none			/* Default.  Do not print counts. */
};

/* Whether and how to precede the output lines with a count of the number of
   times they occurred in the input. */
static enum countmode countmode;

/* Which lines to output: unique lines, the first of a group of
   repeated lines, and the second and subsequented of a group of
   repeated lines.  */
static bool output_unique;
static bool output_first_repeated;
static bool output_later_repeated;

/* If true, ignore case when comparing.  */
static bool ignore_case;

enum delimit_method
{
  /* No delimiters output.  --all-repeated[=none] */
  DM_NONE,

  /* Delimiter precedes all groups.  --all-repeated=prepend */
  DM_PREPEND,

  /* Delimit all groups.  --all-repeated=separate */
  DM_SEPARATE
};

static char const *const delimit_method_string[] =
{
  "none", "prepend", "separate", NULL
};

static enum delimit_method const delimit_method_map[] =
{
  DM_NONE, DM_PREPEND, DM_SEPARATE
};

/* Select whether/how to delimit groups of duplicate lines.  */
static enum delimit_method delimit_groups;

enum grouping_method
{
  /* No grouping, when "--group" isn't used */
  GM_NONE,

  /* Delimiter preceges all groups.  --group=prepend */
  GM_PREPEND,

  /* Delimiter follows all groups.   --group=append */
  GM_APPEND,

  /* Delimiter between groups.    --group[=separate] */
  GM_SEPARATE,

  /* Delimiter before and after each group. --group=both */
  GM_BOTH
};

static char const *const grouping_method_string[] =
{
  "prepend", "append", "separate", "both", NULL
};

static enum grouping_method const grouping_method_map[] =
{
  GM_PREPEND, GM_APPEND, GM_SEPARATE, GM_BOTH
};

static enum grouping_method grouping = GM_NONE;

enum
{
  GROUP_OPTION = CHAR_MAX + 1
};

static struct option const longopts[] =
{
  {"count", no_argument, NULL, 'c'},
  {"repeated", no_argument, NULL, 'd'},
  {"all-repeated", optional_argument, NULL, 'D'},
  {"group", optional_argument, NULL, GROUP_OPTION},
  {"ignore-case", no_argument, NULL, 'i'},
  {"unique", no_argument, NULL, 'u'},
  {"skip-fields", required_argument, NULL, 'f'},
  {"skip-chars", required_argument, NULL, 's'},
  {"check-chars", required_argument, NULL, 'w'},
  {"zero-terminated", no_argument, NULL, 'z'},
  {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]... [INPUT [OUTPUT]]\n\
"),
              program_name);
      fputs (_("\
Filter adjacent matching lines from INPUT (or standard input),\n\
writing to OUTPUT (or standard output).\n\
\n\
With no options, matching lines are merged to the first occurrence.\n\
"), stdout);

      emit_mandatory_arg_note ();

     fputs (_("\
  -c, --count           prefix lines by the number of occurrences\n\
  -d, --repeated        only print duplicate lines, one for each group\n\
"), stdout);
     fputs (_("\
  -D                    print all duplicate lines\n\
      --all-repeated[=METHOD]  like -D, but allow separating groups\n\
                                 with an empty line;\n\
                                 METHOD={none(default),prepend,separate}\n\
"), stdout);
     fputs (_("\
  -f, --skip-fields=N   avoid comparing the first N fields\n\
"), stdout);
     fputs (_("\
      --group[=METHOD]  show all items, separating groups with an empty line;\n\
                          METHOD={separate(default),prepend,append,both}\n\
"), stdout);
     fputs (_("\
  -i, --ignore-case     ignore differences in case when comparing\n\
  -s, --skip-chars=N    avoid comparing the first N characters\n\
  -u, --unique          only print unique lines\n\
"), stdout);
      fputs (_("\
  -z, --zero-terminated     line delimiter is NUL, not newline\n\
"), stdout);
     fputs (_("\
  -w, --check-chars=N   compare no more than N characters in lines\n\
"), stdout);
     fputs (HELP_OPTION_DESCRIPTION, stdout);
     fputs (VERSION_OPTION_DESCRIPTION, stdout);
     fputs (_("\
\n\
A field is a run of blanks (usually spaces and/or TABs), then non-blank\n\
characters.  Fields are skipped before chars.\n\
"), stdout);
     fputs (_("\
\n\
Note: 'uniq' does not detect repeated lines unless they are adjacent.\n\
You may want to sort the input first, or use 'sort -u' without 'uniq'.\n\
Also, comparisons honor the rules specified by 'LC_COLLATE'.\n\
"), stdout);
      emit_ancillary_info (PROGRAM_NAME);
    }
  exit (status);
}

/* Convert OPT to size_t, reporting an error using MSGID if OPT is
   invalid.  Silently convert too-large values to SIZE_MAX.  */

static size_t
size_opt (char const *opt, char const *msgid)
{
  unsigned long int size;
  verify (SIZE_MAX <= ULONG_MAX);

  switch (xstrtoul (opt, NULL, 10, &size, ""))
    {
    case LONGINT_OK:
    case LONGINT_OVERFLOW:
      break;

    default:
      error (EXIT_FAILURE, 0, "%s: %s", opt, _(msgid));
    }

  return MIN (size, SIZE_MAX);
}

/* Given a linebuffer LINE,
   return a pointer to the beginning of the line's field to be compared. */

static char * _GL_ATTRIBUTE_PURE
find_field (struct linebuffer const *line)
{
  size_t count;
  char const *lp = line->buffer;
  size_t size = line->length - 1;
  size_t i = 0;

  for (count = 0; count < skip_fields && i < size; count++)
    {
      while (i < size && field_sep (lp[i]))
        i++;
      while (i < size && !field_sep (lp[i]))
        i++;
    }

  i += MIN (skip_chars, size - i);

  return line->buffer + i;
}

/* Return false if two strings OLD and NEW match, true if not.
   OLD and NEW point not to the beginnings of the lines
   but rather to the beginnings of the fields to compare.
   OLDLEN and NEWLEN are their lengths. */

static bool
different (char *old, char *new, size_t oldlen, size_t newlen)
{
  if (check_chars < oldlen)
    oldlen = check_chars;
  if (check_chars < newlen)
    newlen = check_chars;

  if (ignore_case)
    {
      /* FIXME: This should invoke strcoll somehow.  */
      return oldlen != newlen || memcasecmp (old, new, oldlen);
    }
  else if (hard_LC_COLLATE)
    return xmemcoll (old, oldlen, new, newlen) != 0;
  else
    return oldlen != newlen || memcmp (old, new, oldlen);
}

/* Output the line in linebuffer LINE to standard output
   provided that the switches say it should be output.
   MATCH is true if the line matches the previous line.
   If requested, print the number of times it occurred, as well;
   LINECOUNT + 1 is the number of times that the line occurred. */

static void
writeline (struct linebuffer const *line,
           bool match, uintmax_t linecount)
{
  if (! (linecount == 0 ? output_unique
         : !match ? output_first_repeated
         : output_later_repeated))
    return;

  if (countmode == count_occurrences)
    printf ("%7" PRIuMAX " ", linecount + 1);

  fwrite (line->buffer, sizeof (char), line->length, stdout);
}

/* Process input file INFILE with output to OUTFILE.
   If either is "-", use the standard I/O stream for it instead. */

static void
check_file (const char *infile, const char *outfile, char delimiter)
{
  struct linebuffer lb1, lb2;
  struct linebuffer *thisline, *prevline;

  if (! (STREQ (infile, "-") || freopen (infile, "r", stdin)))
    error (EXIT_FAILURE, errno, "%s", quotef (infile));
  if (! (STREQ (outfile, "-") || freopen (outfile, "w", stdout)))
    error (EXIT_FAILURE, errno, "%s", quotef (outfile));

  fadvise (stdin, FADVISE_SEQUENTIAL);

  thisline = &lb1;
  prevline = &lb2;

  initbuffer (thisline);
  initbuffer (prevline);

  /* The duplication in the following 'if' and 'else' blocks is an
     optimization to distinguish between when we can print input
     lines immediately (1. & 2.) or not.

     1. --group => all input lines are printed.
        checking for unique/duplicated lines is used only for printing
        group separators.

     2. The default case in which none of these options has been specified:
          --count, --repeated,  --all-repeated, --unique
        In the default case, this optimization lets uniq output each different
        line right away, without waiting to see if the next one is different.

     3. All other cases.
  */
  if (output_unique && output_first_repeated && countmode == count_none)
    {
      char *prevfield IF_LINT ( = NULL);
      size_t prevlen IF_LINT ( = 0);
      bool first_group_printed = false;

      while (!feof (stdin))
        {
          char *thisfield;
          size_t thislen;
          bool new_group;

          if (readlinebuffer_delim (thisline, stdin, delimiter) == 0)
            break;

          thisfield = find_field (thisline);
          thislen = thisline->length - 1 - (thisfield - thisline->buffer);

          new_group = (prevline->length == 0
                       || different (thisfield, prevfield, thislen, prevlen));

          if (new_group && grouping != GM_NONE
              && (grouping == GM_PREPEND || grouping == GM_BOTH
                  || (first_group_printed && (grouping == GM_APPEND
                                              || grouping == GM_SEPARATE))))
            putchar (delimiter);

          if (new_group || grouping != GM_NONE)
            {
              fwrite (thisline->buffer, sizeof (char),
                      thisline->length, stdout);

              SWAP_LINES (prevline, thisline);
              prevfield = thisfield;
              prevlen = thislen;
              first_group_printed = true;
            }
        }
      if ((grouping == GM_BOTH || grouping == GM_APPEND) && first_group_printed)
        putchar (delimiter);
    }
  else
    {
      char *prevfield;
      size_t prevlen;
      uintmax_t match_count = 0;
      bool first_delimiter = true;

      if (readlinebuffer_delim (prevline, stdin, delimiter) == 0)
        goto closefiles;
      prevfield = find_field (prevline);
      prevlen = prevline->length - 1 - (prevfield - prevline->buffer);

      while (!feof (stdin))
        {
          bool match;
          char *thisfield;
          size_t thislen;
          if (readlinebuffer_delim (thisline, stdin, delimiter) == 0)
            {
              if (ferror (stdin))
                goto closefiles;
              break;
            }
          thisfield = find_field (thisline);
          thislen = thisline->length - 1 - (thisfield - thisline->buffer);
          match = !different (thisfield, prevfield, thislen, prevlen);
          match_count += match;

          if (match_count == UINTMAX_MAX)
            {
              if (count_occurrences)
                error (EXIT_FAILURE, 0, _("too many repeated lines"));
              match_count--;
            }

          if (delimit_groups != DM_NONE)
            {
              if (!match)
                {
                  if (match_count) /* a previous match */
                    first_delimiter = false; /* Only used when DM_SEPARATE */
                }
              else if (match_count == 1)
                {
                  if ((delimit_groups == DM_PREPEND)
                      || (delimit_groups == DM_SEPARATE
                          && !first_delimiter))
                    putchar (delimiter);
                }
            }

          if (!match || output_later_repeated)
            {
              writeline (prevline, match, match_count);
              SWAP_LINES (prevline, thisline);
              prevfield = thisfield;
              prevlen = thislen;
              if (!match)
                match_count = 0;
            }
        }

      writeline (prevline, false, match_count);
    }

 closefiles:
  if (ferror (stdin) || fclose (stdin) != 0)
    error (EXIT_FAILURE, 0, _("error reading %s"), quoteaf (infile));

  /* stdout is handled via the atexit-invoked close_stdout function.  */

  free (lb1.buffer);
  free (lb2.buffer);
}

enum Skip_field_option_type
  {
    SFO_NONE,
    SFO_OBSOLETE,
    SFO_NEW
  };

int
main (int argc, char **argv)
{
  int optc = 0;
  bool posixly_correct = (getenv ("POSIXLY_CORRECT") != NULL);
  enum Skip_field_option_type skip_field_option_type = SFO_NONE;
  unsigned int nfiles = 0;
  char const *file[2];
  char delimiter = '\n';	/* change with --zero-terminated, -z */
  bool output_option_used = false;   /* if true, one of -u/-d/-D/-c was used */

  file[0] = file[1] = "-";
  initialize_main (&argc, &argv);
  set_program_name (argv[0]);
  setlocale (LC_ALL, "");
  bindtextdomain (PACKAGE, LOCALEDIR);
  textdomain (PACKAGE);
  hard_LC_COLLATE = hard_locale (LC_COLLATE);

  atexit (close_stdout);

  skip_chars = 0;
  skip_fields = 0;
  check_chars = SIZE_MAX;
  output_unique = output_first_repeated = true;
  output_later_repeated = false;
  countmode = count_none;
  delimit_groups = DM_NONE;

  while (true)
    {
      /* Parse an operand with leading "+" as a file after "--" was
         seen; or if pedantic and a file was seen; or if not
         obsolete.  */

      if (optc == -1
          || (posixly_correct && nfiles != 0)
          || ((optc = getopt_long (argc, argv,
                                   "-0123456789Dcdf:is:uw:z", longopts, NULL))
              == -1))
        {
          if (argc <= optind)
            break;
          if (nfiles == 2)
            {
              error (0, 0, _("extra operand %s"), quote (argv[optind]));
              usage (EXIT_FAILURE);
            }
          file[nfiles++] = argv[optind++];
        }
      else switch (optc)
        {
        case 1:
          {
            unsigned long int size;
            if (optarg[0] == '+'
                && posix2_version () < 200112
                && xstrtoul (optarg, NULL, 10, &size, "") == LONGINT_OK
                && size <= SIZE_MAX)
              skip_chars = size;
            else if (nfiles == 2)
              {
                error (0, 0, _("extra operand %s"), quote (optarg));
                usage (EXIT_FAILURE);
              }
            else
              file[nfiles++] = optarg;
          }
          break;

        case '0':
        case '1':
        case '2':
        case '3':
        case '4':
        case '5':
        case '6':
        case '7':
        case '8':
        case '9':
          {
            if (skip_field_option_type == SFO_NEW)
              skip_fields = 0;

            if (!DECIMAL_DIGIT_ACCUMULATE (skip_fields, optc - '0', size_t))
              skip_fields = SIZE_MAX;

            skip_field_option_type = SFO_OBSOLETE;
          }
          break;

        case 'c':
          countmode = count_occurrences;
          output_option_used = true;
          break;

        case 'd':
          output_unique = false;
          output_option_used = true;
          break;

        case 'D':
          output_unique = false;
          output_later_repeated = true;
          if (optarg == NULL)
            delimit_groups = DM_NONE;
          else
            delimit_groups = XARGMATCH ("--all-repeated", optarg,
                                        delimit_method_string,
                                        delimit_method_map);
          output_option_used = true;
          break;

        case GROUP_OPTION:
          if (optarg == NULL)
            grouping = GM_SEPARATE;
          else
            grouping = XARGMATCH ("--group", optarg,
                                  grouping_method_string,
                                  grouping_method_map);
          break;

        case 'f':
          skip_field_option_type = SFO_NEW;
          skip_fields = size_opt (optarg,
                                  N_("invalid number of fields to skip"));
          break;

        case 'i':
          ignore_case = true;
          break;

        case 's':
          skip_chars = size_opt (optarg,
                                 N_("invalid number of bytes to skip"));
          break;

        case 'u':
          output_first_repeated = false;
          output_option_used = true;
          break;

        case 'w':
          check_chars = size_opt (optarg,
                                  N_("invalid number of bytes to compare"));
          break;

        case 'z':
          delimiter = '\0';
          break;

        case_GETOPT_HELP_CHAR;

        case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);

        default:
          usage (EXIT_FAILURE);
        }
    }

  /* Note we could allow --group with -D at least, and that would
     avoid the need to specify a grouping method to --all-repeated.
     It was thought best to avoid deprecating those parameters though
     and keep --group separate to other options.  */
  if (grouping != GM_NONE && output_option_used)
    {
      error (0, 0, _("--group is mutually exclusive with -c/-d/-D/-u"));
      usage (EXIT_FAILURE);
    }

  if (grouping != GM_NONE && countmode != count_none)
    {
      error (0, 0,
           _("grouping and printing repeat counts is meaningless"));
      usage (EXIT_FAILURE);
    }

  if (countmode == count_occurrences && output_later_repeated)
    {
      error (0, 0,
           _("printing all duplicated lines and repeat counts is meaningless"));
      usage (EXIT_FAILURE);
    }

  check_file (file[0], file[1], delimiter);

  return EXIT_SUCCESS;
}