summaryrefslogtreecommitdiff
path: root/src/uniq.c
blob: 4ae509f0303e0aaed07e9d7c63053ef2281d5657 (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
/* uniq -- remove duplicate lines from a sorted file
   Copyright (C) 86, 91, 1995-2004 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 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */

/* Written by Richard Stallman and David MacKenzie. */

#include <config.h>

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

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

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

#define AUTHORS "Richard Stallman", "David MacKenzie"

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

/* The name this program was run with. */
char *program_name;

/* 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", 0
};

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;

static struct option const longopts[] =
{
  {"count", no_argument, NULL, 'c'},
  {"repeated", no_argument, NULL, 'd'},
  {"all-repeated", optional_argument, NULL, 'D'},
  {"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'},
  {GETOPT_HELP_OPTION_DECL},
  {GETOPT_VERSION_OPTION_DECL},
  {NULL, 0, NULL, 0}
};

void
usage (int status)
{
  if (status != EXIT_SUCCESS)
    fprintf (stderr, _("Try `%s --help' for more information.\n"),
	     program_name);
  else
    {
      printf (_("\
Usage: %s [OPTION]... [INPUT [OUTPUT]]\n\
"),
	      program_name);
      fputs (_("\
Discard all but one of successive identical lines from INPUT (or\n\
standard input), writing to OUTPUT (or standard output).\n\
\n\
"), stdout);
     fputs (_("\
Mandatory arguments to long options are mandatory for short options too.\n\
"), stdout);
     fputs (_("\
  -c, --count           prefix lines by the number of occurrences\n\
  -d, --repeated        only print duplicate lines\n\
"), stdout);
     fputs (_("\
  -D, --all-repeated[=delimit-method] print all duplicate lines\n\
                        delimit-method={none(default),prepend,separate}\n\
                        Delimiting is done with blank lines.\n\
  -f, --skip-fields=N   avoid comparing the first N fields\n\
  -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 (_("\
  -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 whitespace, then non-whitespace characters.\n\
Fields are skipped before chars.\n\
"), stdout);
      printf (_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
    }
  exit (status);
}

/* Convert OPT to size_t, reporting an error using MSGID if it does
   not fit.  */

static size_t
size_opt (char const *opt, char const *msgid)
{
  unsigned long int size;
  if (xstrtoul (opt, NULL, 10, &size, "") != LONGINT_OK
      || SIZE_MAX < size)
    error (EXIT_FAILURE, 0, "%s: %s", opt, _(msgid));
  return size;
}

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

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

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

  for (count = 0; count < skip_chars && i < size; count++)
    i++;

  return lp + 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 (HAVE_SETLOCALE && 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 stream STREAM
   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, FILE *stream,
	   bool match, uintmax_t linecount)
{
  if (! (linecount == 0 ? output_unique
	 : !match ? output_first_repeated
	 : output_later_repeated))
    return;

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

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

/* 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)
{
  FILE *istream;
  FILE *ostream;
  struct linebuffer lb1, lb2;
  struct linebuffer *thisline, *prevline;

  if (STREQ (infile, "-"))
    istream = stdin;
  else
    istream = fopen (infile, "r");
  if (istream == NULL)
    error (EXIT_FAILURE, errno, "%s", infile);

  if (STREQ (outfile, "-"))
    ostream = stdout;
  else
    ostream = fopen (outfile, "w");
  if (ostream == NULL)
    error (EXIT_FAILURE, errno, "%s", outfile);

  thisline = &lb1;
  prevline = &lb2;

  initbuffer (thisline);
  initbuffer (prevline);

  /* The duplication in the following `if' and `else' blocks is an
     optimization to distinguish the common case (in which none of
     the following options has been specified: --count, -repeated,
     --all-repeated, --unique) from the others.  In the common case,
     this optimization lets uniq output each different line right away,
     without waiting to see if the next one is different.  */

  if (output_unique && output_first_repeated && countmode == count_none)
    {
      char *prevfield IF_LINT (= NULL);
      size_t prevlen IF_LINT (= 0);

      while (!feof (istream))
	{
	  char *thisfield;
	  size_t thislen;
	  if (readlinebuffer (thisline, istream) == 0)
	    break;
	  thisfield = find_field (thisline);
	  thislen = thisline->length - 1 - (thisfield - thisline->buffer);
	  if (prevline->length == 0
	      || different (thisfield, prevfield, thislen, prevlen))
	    {
	      fwrite (thisline->buffer, sizeof (char),
		      thisline->length, ostream);

	      SWAP_LINES (prevline, thisline);
	      prevfield = thisfield;
	      prevlen = thislen;
	    }
	}
    }
  else
    {
      char *prevfield;
      size_t prevlen;
      uintmax_t match_count = 0;
      bool first_delimiter = true;

      if (readlinebuffer (prevline, istream) == 0)
	goto closefiles;
      prevfield = find_field (prevline);
      prevlen = prevline->length - 1 - (prevfield - prevline->buffer);

      while (!feof (istream))
	{
	  bool match;
	  char *thisfield;
	  size_t thislen;
	  if (readlinebuffer (thisline, istream) == 0)
	    {
	      if (ferror (istream))
		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))
		    putc ('\n', ostream);
		}
	    }

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

      writeline (prevline, ostream, false, match_count);
    }

 closefiles:
  if (ferror (istream) || fclose (istream) == EOF)
    error (EXIT_FAILURE, errno, _("error reading %s"), infile);

  if (ferror (ostream))
    error (EXIT_FAILURE, 0, _("error writing %s"), outfile);
  /* Close ostream only if it's not stdout -- the latter is closed
     via the atexit-invoked close_stdout.  */
  if (ostream != stdout && fclose (ostream) != 0)
    error (EXIT_FAILURE, errno, _("error writing %s"), outfile);

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

int
main (int argc, char **argv)
{
  int optc = 0;
  bool posixly_correct = (getenv ("POSIXLY_CORRECT") != NULL);
  bool obsolete_skip_fields = false;
  int nfiles = 0;
  char const *file[2];

  file[0] = file[1] = "-";
  initialize_main (&argc, &argv);
  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;

  for (;;)
    {
      /* 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:", 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':
	  {
	    size_t s = skip_fields;
	    skip_fields = s * 10 + optc - '0';
	    if (SIZE_MAX / 10 < s || skip_fields < s)
	      error (EXIT_FAILURE, 0, "%s",
		     _("invalid number of fields to skip"));
	    obsolete_skip_fields = true;
	  }
	  break;

	case 'c':
	  countmode = count_occurrences;
	  break;

	case 'd':
	  output_unique = false;
	  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);
	  break;

	case 'f':		/* Like '-#'. */
	  skip_fields = size_opt (optarg,
				  N_("invalid number of fields to skip"));
	  break;

	case 'i':
	  ignore_case = true;
	  break;

	case 's':		/* Like '+#'. */
	  skip_chars = size_opt (optarg,
				 N_("invalid number of bytes to skip"));
	  break;

	case 'u':
	  output_first_repeated = false;
	  break;

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

	case_GETOPT_HELP_CHAR;

	case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);

	default:
	  usage (EXIT_FAILURE);
	}
    }

  if (obsolete_skip_fields && 200112 <= posix2_version ())
    {
      error (0, 0, _("`-%lu' option is obsolete; use `-f %lu'"),
	     (unsigned long int) skip_fields, (unsigned long int) skip_fields);
      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]);

  exit (EXIT_SUCCESS);
}