sort.c

Linux.Programming.by example 的源代码绝对经典

    {
      int i = n_temp_files;
      struct tempnode *node;
      char **tempfiles = (char **) xmalloc (n_temp_files * sizeof (char *));
      for (node = temphead; i > 0; node = node->next)
	tempfiles[--i] = node->name;
      merge (tempfiles, n_temp_files, NMERGE, output_file);
      free ((char *) tempfiles);
    }
}

/* Insert key KEY at the end of the key list.  */

static void
insertkey (struct keyfield *key)
{
  struct keyfield **p;

  for (p = &keylist; *p; p = &(*p)->next)
    continue;
  *p = key;
  key->next = NULL;
}

/* Report a bad field specification SPEC, with extra info MSGID.  */

static void badfieldspec (char const *, char const *)
     ATTRIBUTE_NORETURN;
static void
badfieldspec (char const *spec, char const *msgid)
{
  error (SORT_FAILURE, 0, _("%s: invalid field specification `%s'"),
	 _(msgid), spec);
  abort ();
}

/* Parse the leading integer in STRING and store the resulting value
   (which must fit into size_t) into *VAL.  Return the address of the
   suffix after the integer.  If MSGID is NULL, return NULL after
   failure; otherwise, report MSGID and exit on failure.  */

static char const *
parse_field_count (char const *string, size_t *val, char const *msgid)
{
  char *suffix;
  uintmax_t n;

  switch (xstrtoumax (string, &suffix, 10, &n, ""))
    {
    case LONGINT_OK:
    case LONGINT_INVALID_SUFFIX_CHAR:
      *val = n;
      if (*val == n)
	break;
      /* Fall through.  */
    case LONGINT_OVERFLOW:
      if (msgid)
	error (SORT_FAILURE, 0, _("%s: count `%.*s' too large"),
	       _(msgid), (int) (suffix - string), string);
      return NULL;

    case LONGINT_INVALID:
      if (msgid)
	error (SORT_FAILURE, 0, _("%s: invalid count at start of `%s'"),
	       _(msgid), string);
      return NULL;
    }

  return suffix;
}

/* Handle interrupts and hangups. */

static void
sighandler (int sig)
{
#ifndef SA_NOCLDSTOP
  signal (sig, SIG_IGN);
#endif

  cleanup ();

#ifdef SA_NOCLDSTOP
  {
    struct sigaction sigact;

    sigact.sa_handler = SIG_DFL;
    sigemptyset (&sigact.sa_mask);
    sigact.sa_flags = 0;
    sigaction (sig, &sigact, NULL);
  }
#else
  signal (sig, SIG_DFL);
#endif

  raise (sig);
}

/* Set the ordering options for KEY specified in S.
   Return the address of the first character in S that
   is not a valid ordering option.
   BLANKTYPE is the kind of blanks that 'b' should skip. */

static char *
set_ordering (register const char *s, struct keyfield *key,
	      enum blanktype blanktype)
{
  while (*s)
    {
      switch (*s)
	{
	case 'b':
	  if (blanktype == bl_start || blanktype == bl_both)
	    key->skipsblanks = 1;
	  if (blanktype == bl_end || blanktype == bl_both)
	    key->skipeblanks = 1;
	  break;
	case 'd':
	  key->ignore = nondictionary;
	  break;
	case 'f':
	  key->translate = fold_toupper;
	  break;
	case 'g':
	  key->general_numeric = 1;
	  break;
	case 'i':
	  key->ignore = nonprinting;
	  break;
	case 'M':
	  key->month = 1;
	  break;
	case 'n':
	  key->numeric = 1;
	  break;
	case 'r':
	  key->reverse = 1;
	  break;
	default:
	  return (char *) s;
	}
      ++s;
    }
  return (char *) s;
}

static struct keyfield *
new_key (void)
{
  struct keyfield *key = (struct keyfield *) xcalloc (1, sizeof *key);
  key->eword = -1;
  return key;
}

int
main (int argc, char **argv)
{
  struct keyfield *key;
  struct keyfield gkey;
  char const *s;
  int c = 0;
  int checkonly = 0, mergeonly = 0, nfiles = 0;
  int posix_pedantic = (getenv ("POSIXLY_CORRECT") != NULL);
  bool obsolete_usage = (posix2_version () < 200112);
  char const *short_options = (obsolete_usage
			       ? COMMON_SHORT_OPTIONS "y::"
			       : COMMON_SHORT_OPTIONS "y:");
  char *minus = "-", **files;
  char const *outfile = minus;
  static int const sigs[] = { SIGHUP, SIGINT, SIGPIPE, SIGTERM };
  unsigned nsigs = sizeof sigs / sizeof *sigs;
#ifdef SA_NOCLDSTOP
  struct sigaction oldact, newact;
#endif

  program_name = argv[0];
  setlocale (LC_ALL, "");
  bindtextdomain (PACKAGE, LOCALEDIR);
  textdomain (PACKAGE);

  atexit (cleanup);

  hard_LC_COLLATE = hard_locale (LC_COLLATE);
#if HAVE_NL_LANGINFO
  hard_LC_TIME = hard_locale (LC_TIME);
#endif

#if HAVE_SETLOCALE
  /* Let's get locale's representation of the decimal point */
  {
    struct lconv *lconvp = localeconv ();

    /* If the locale doesn't define a decimal point, or if the decimal
       point is multibyte, use the C decimal point.  We don't support
       multibyte decimal points yet.  */
    decimal_point = *lconvp->decimal_point;
    if (! decimal_point || lconvp->decimal_point[1])
      decimal_point = C_DECIMAL_POINT;

    /* We don't support multibyte thousands separators yet.  */
    th_sep = *lconvp->thousands_sep;
    if (! th_sep || lconvp->thousands_sep[1])
      th_sep = CHAR_MAX + 1;
  }
#endif

  have_read_stdin = 0;
  inittables ();

  /* Change the way library functions fail.  */
  xalloc_exit_failure = SORT_FAILURE;
  xmemcoll_exit_failure = SORT_FAILURE;

#ifdef SA_NOCLDSTOP
  {
    unsigned i;
    sigemptyset (&caught_signals);
    for (i = 0; i < nsigs; i++)
      sigaddset (&caught_signals, sigs[i]);
    newact.sa_handler = sighandler;
    newact.sa_mask = caught_signals;
    newact.sa_flags = 0;
  }
#endif

  {
    unsigned i;
    for (i = 0; i < nsigs; i++)
      {
	int sig = sigs[i];
#ifdef SA_NOCLDSTOP
	sigaction (sig, NULL, &oldact);
	if (oldact.sa_handler != SIG_IGN)
	  sigaction (sig, &newact, NULL);
#else
	if (signal (sig, SIG_IGN) != SIG_IGN)
	  signal (sig, sighandler);
#endif
      }
  }

  gkey.sword = gkey.eword = -1;
  gkey.ignore = NULL;
  gkey.translate = NULL;
  gkey.numeric = gkey.general_numeric = gkey.month = gkey.reverse = 0;
  gkey.skipsblanks = gkey.skipeblanks = 0;

  files = (char **) xmalloc (sizeof (char *) * argc);

  for (;;)
    {
      /* Parse an operand as a file after "--" was seen; or if
         pedantic and a file was seen, unless the POSIX version
         predates 1003.1-2001 and -c was not seen and the operand is
         "-o FILE" or "-oFILE".  */

      if (c == -1
	  || (posix_pedantic && nfiles != 0
	      && ! (obsolete_usage
		    && ! checkonly
		    && optind != argc
		    && argv[optind][0] == '-' && argv[optind][1] == 'o'
		    && (argv[optind][2] || optind + 1 != argc)))
	  || ((c = getopt_long (argc, argv, short_options,
				long_options, NULL))
	      == -1))
	{
	  if (optind == argc)
	    break;
	  files[nfiles++] = argv[optind++];
	}
      else switch (c)
	{
	case 1:
	  key = NULL;
	  if (obsolete_usage && optarg[0] == '+')
	    {
	      /* Treat +POS1 [-POS2] as a key if possible; but silently
		 treat an operand as a file if it is not a valid +POS1.  */
	      key = new_key ();
	      s = parse_field_count (optarg + 1, &key->sword, NULL);
	      if (s && *s == '.')
		s = parse_field_count (s + 1, &key->schar, NULL);
	      if (! (key->sword | key->schar))
		key->sword = -1;
	      if (! s || *set_ordering (s, key, bl_start))
		{
		  free (key);
		  key = NULL;
		}
	      else
		{
		  if (optind != argc && argv[optind][0] == '-'
		      && ISDIGIT (argv[optind][1]))
		    {
		      char const *optarg1 = argv[optind++];
		      s = parse_field_count (optarg1 + 1, &key->eword,
					     N_("invalid number after `-'"));
		      if (*s == '.')
			s = parse_field_count (s + 1, &key->echar,
					       N_("invalid number after `.'"));
		      if (*set_ordering (s, key, bl_end))
			badfieldspec (optarg1,
				      N_("stray character in field spec"));
		    }
		  insertkey (key);
		}
	    }
	  if (! key)
	    files[nfiles++] = optarg;
	  break;

	case 'b':
	case 'd':
	case 'f':
	case 'g':
	case 'i':
	case 'M':
	case 'n':
	case 'r':
	  {
	    char str[2];
	    str[0] = c;
	    str[1] = '\0';
	    set_ordering (str, &gkey, bl_both);
	  }
	  break;

	case 'c':
	  checkonly = 1;
	  break;

	case 'k':
	  key = new_key ();

	  /* Get POS1. */
	  s = parse_field_count (optarg, &key->sword,
				 N_("invalid number at field start"));
	  if (! key->sword--)
	    {
	      /* Provoke with `sort -k0' */
	      badfieldspec (optarg, N_("field number is zero"));
	    }
	  if (*s == '.')
	    {
	      s = parse_field_count (s + 1, &key->schar,
				     N_("invalid number after `.'"));
	      if (! key->schar--)
		{
		  /* Provoke with `sort -k1.0' */
		  badfieldspec (optarg, N_("character offset is zero"));
		}
	    }
	  if (! (key->sword | key->schar))
	    key->sword = -1;
	  s = set_ordering (s, key, bl_start);
	  if (*s != ',')
	    {
	      key->eword = -1;
	      key->echar = 0;
	    }
	  else
	    {
	      /* Get POS2. */
	      s = parse_field_count (s + 1, &key->eword,
				     N_("invalid number after `,'"));
	      if (! key->eword--)
		{
		  /* Provoke with `sort -k1,0' */
		  badfieldspec (optarg, N_("field number is zero"));
		}
	      if (*s == '.')
		s = parse_field_count (s + 1, &key->echar,
				       N_("invalid number after `.'"));
	      else
		{
		  /* `-k 2,3' is equivalent to `+1 -3'.  */
		  key->eword++;
		}
	      s = set_ordering (s, key, bl_end);
	    }
	  if (*s)
	    badfieldspec (optarg, N_("stray character in field spec"));
	  insertkey (key);
	  break;

	case 'm':
	  mergeonly = 1;
	  break;

	case 'o':
	  outfile = optarg;
	  break;

	case 's':
	  stable = 1;
	  break;

	case 'S':
	  specify_sort_size (optarg);
	  break;

	case 't':
	  tab = optarg[0];
	  if (tab && optarg[1])
	    {
	      /* Provoke with `sort -txx'.  Complain about
		 "multi-character tab" instead of "multibyte tab", so
		 that the diagnostic's wording does not need to be
		 changed once multibyte characters are supported.  */
	      error (SORT_FAILURE, 0, _("multi-character tab `%s'"), optarg);
	    }
	  break;

	case 'T':
	  add_temp_dir (optarg);
	  break;

	case 'u':
	  unique = 1;
	  break;

	case 'y':
	  /* Accept and ignore e.g. -y0 for compatibility with Solaris
	     2.x through Solaris 7.  -y is marked as obsolete starting
	     with Solaris 8.  */
	  break;

	case 'z':
	  eolchar = 0;
	  break;

	case_GETOPT_HELP_CHAR;

	case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);

	default:
	  usage (SORT_FAILURE);
	}
    }

  /* Inheritance of global options to individual keys. */
  for (key = keylist; key; key = key->next)
    if (!key->ignore && !key->translate && !key->skipsblanks && !key->reverse
	&& !key->skipeblanks && !key->month && !key->numeric
	&& !key->general_numeric)
      {
	key->ignore = gkey.ignore;
	key->translate = gkey.translate;
	key->skipsblanks = gkey.skipsblanks;
	key->skipeblanks = gkey.skipeblanks;
	key->month = gkey.month;
	key->numeric = gkey.numeric;
	key->general_numeric = gkey.general_numeric;
	key->reverse = gkey.reverse;
      }

  if (!keylist && (gkey.ignore || gkey.translate || gkey.skipsblanks
		   || gkey.skipeblanks || gkey.month || gkey.numeric
		   || gkey.general_numeric))
    insertkey (&gkey);
  reverse = gkey.reverse;

  if (temp_dir_count == 0)
    {
      char const *tmp_dir = getenv ("TMPDIR");
      add_temp_dir (tmp_dir ? tmp_dir : DEFAULT_TMPDIR);
    }

  if (nfiles == 0)
    {
      nfiles = 1;
      files = &minus;
    }

  if (checkonly)
    {
      if (nfiles > 1)
	error (SORT_FAILURE, 0, _("extra operand `%s' not allowed with -c"),
	       files[1]);

      /* POSIX requires that sort return 1 IFF invoked with -c and the
	 input is not properly sorted.  */
      exit (check (files, nfiles) == 0 ? EXIT_SUCCESS : SORT_OUT_OF_ORDER);
    }

  if (mergeonly)
    {
      int max_merge = first_same_file (files, MIN (nfiles, NMERGE), outfile);
      merge (files, nfiles, max_merge, outfile);
    }
  else
    sort (files, nfiles, outfile);

  if (have_read_stdin && fclose (stdin) == EOF)
    die (_("close failed"), "-");

  exit (EXIT_SUCCESS);
}