path: root/src/uniq.c

/* uniq -- remove duplicate lines from a sorted file
   Copyright (C) 1986-2017 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 "die.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"

#include "sort-uniq-keyfuncs.c"

/* 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")

/* 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'},
  {"key", required_argument, NULL, 'k'},
  {"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\
  -k, --key=...         see 'sort' for details\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);
}

static bool
strict_posix2 (void)
{
  int posix_ver = posix2_version ();
  return 200112 <= posix_ver && posix_ver < 200809;
}

/* 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:
      die (EXIT_FAILURE, 0, "%s: %s", opt, _(msgid));
    }

  return MIN (size, SIZE_MAX);
}

/* Output the line in line 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 line const *line,
           bool match, uintmax_t linecount, FILE *outfp, const char *outfile)
{
  if (! (linecount == 0 ? output_unique
         : !match ? output_first_repeated
         : output_later_repeated))
    return;

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

  fwrite (line->text, sizeof (char), line->length, outfp);
  fputc (eolchar, outfp);
}

/* 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)
{
  FILE *infp = xfopen (infile, "r");
  FILE *outfp = xfopen (STREQ(outfile,"-") ? NULL : outfile, "w");
  struct buffer buf;		/* Input buffer. */
  struct line temp;		/* Copy of previous line. */
  size_t alloc = 0;
  struct keyfield const *key = keylist;
  initbuf (&buf, sizeof (struct line),
           MAX (merge_buffer_size, sort_size));

  struct line const *line = buffer_linelim (&buf);
  struct line const *linebase = line - buf.nlines;

  bool the_same;    /* Is the line equal to the last one? */
  bool first_group_printed = false;
  uintmax_t match_count = 0;
  bool first_delimiter = true;

  temp.text = NULL;

  while (fillbuf (&buf, infp, infile))
    {
      line = buffer_linelim (&buf);
      linebase = line - buf.nlines;

      /* Check if the line saved from the old buffer contents is
         equal to the first line of the new buffer. */
      the_same = alloc && ! compare (&temp, line - 1);

      if (linebase < line)
        goto print_something_if_appropriate;

/*
        {
        found_disorder:
          {
            if (checkonly == 'c')
              {
                struct line const *disorder_line = line - 1;
                uintmax_t disorder_line_number =
                  buffer_linelim (&buf) - disorder_line + line_number;
                char hr_buf[INT_BUFSIZE_BOUND (disorder_line_number)];
                fprintf (stderr, _("%s: %s:%s: disorder: "),
                         program_name, file_name,
                         umaxtostr (disorder_line_number, hr_buf));
                write_line (disorder_line, stderr, _("standard error"));
              }

            ordered = false;
            break;
          }
        } */

      /* Compare each line in the buffer with its successor.  */
      while (linebase < --line)
        {
          the_same = ! compare (line, line - 1);

          print_something_if_appropriate:
            {

              if (output_unique && output_first_repeated && countmode == count_none)
                {
                  if (! the_same && grouping != GM_NONE
                      && (grouping == GM_PREPEND || grouping == GM_BOTH
                          || (first_group_printed && (grouping == GM_APPEND
                                                      || grouping == GM_SEPARATE))))
                    fputc (delimiter, outfp);

                  if (! the_same || grouping != GM_NONE)
                    {
                      write_line (line-1, outfp, outfile);

                      first_group_printed = true;
                    }
                }
              else
                {
                  match_count += the_same;

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

                  if (delimit_groups != DM_NONE)
                    {
                      if (! the_same)
                        {
                          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))
                            fputc (delimiter, outfp);
                        }
                    }

                  if (! the_same || output_later_repeated)
                    {
                      writeline (line-1, the_same, match_count, outfp, outfile);
                      if (! the_same)
                        match_count = 0;
                    }
                }
            }
        }

      /* Save the last line of the buffer.  */
      if (alloc < line->length)
        {
          do
            {
              alloc *= 2;
              if (! alloc)
                {
                  alloc = line->length;
                  break;
                }
            }
          while (alloc < line->length);

          free (temp.text);
          temp.text = xmalloc (alloc);
        }
      memcpy (temp.text, line->text, line->length);
      temp.length = line->length;
      if (key)
        {
          temp.keybeg = temp.text + (line->keybeg - line->text);
          temp.keylim = temp.text + (line->keylim - line->text);
        }
    }

  if (output_unique && output_first_repeated && countmode == count_none)
    {
      if ((grouping == GM_BOTH || grouping == GM_APPEND) && first_group_printed)
        fputc (delimiter, outfp);
    }
  else
    {
      writeline (line-1, false, match_count, outfp, outfile);
    }

  xfclose (infp, infile);
  xfclose (outfp, outfile);
  free (buf.buf);
  free (temp.text);
}

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:iks: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] == '+'
                && ! strict_posix2 ()
                && 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 'k':
          add_key();
          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;
}