tests/libpspp/encoding-guesser-test.c

   1 /* PSPP - a program for statistical analysis.
   2    Copyright (C) 2011 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation, either version 3 of the License, or
   7    (at your option) any later version.
   8
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <http://www.gnu.org/licenses/>. */
  16
  17 #include <config.h>
  18
  19 #include "libpspp/encoding-guesser.h"
  20
  21 #include <ctype.h>
  22 #include <stdio.h>
  23 #include <stdlib.h>
  24 #include <string.h>
  25
  26 #include "libpspp/i18n.h"
  27
  28 #include "gl/error.h"
  29 #include "gl/progname.h"
  30 #include "gl/xalloc.h"
  31
  32 static void
  33 usage (void)
  34 {
  35   printf ("usage: %s [OTHER_ENCODING] [BUFSIZE] < INPUT\n"
  36           "where OTHER_ENCODING is the fallback encoding (default taken\n"
  37           "                     from the current locale)\n"
  38           "  and BUFSIZE is the buffer size (default %d)\n",
  39           program_name, ENCODING_GUESS_MIN);
  40   exit (0);
  41 }
  42
  43 int
  44 main (int argc, char *argv[])
  45 {
  46   const char *encoding, *guess;
  47   char *buffer;
  48   int bufsize;
  49   size_t n;
  50   int i;
  51
  52   set_program_name (argv[0]);
  53
  54   i18n_init ();
  55
  56   encoding = NULL;
  57   bufsize = 0;
  58   for (i = 1; i < argc; i++)
  59     {
  60       const char *arg = argv[i];
  61       if (!strcmp (arg, "--help"))
  62         usage ();
  63       else if (isdigit (arg[0]) && bufsize == 0)
  64         {
  65           bufsize = atoi (arg);
  66           if (bufsize < ENCODING_GUESS_MIN)
  67             error (1, 0, "buffer size %s is less than minimum size %d",
  68                    arg, ENCODING_GUESS_MIN);
  69         }
  70       else if (!isdigit (arg[0]) && encoding == NULL)
  71         encoding = arg;
  72       else
  73         error (1, 0, "bad syntax; use `%s --help' for help", program_name);
  74     }
  75
  76   if (bufsize == 0)
  77     bufsize = ENCODING_GUESS_MIN;
  78
  79   buffer = xmalloc (bufsize);
  80
  81   n = fread (buffer, 1, bufsize, stdin);
  82   guess = encoding_guess_head_encoding (encoding, buffer, n);
  83   if (!strcmp (guess, "ASCII") && encoding_guess_encoding_is_auto (encoding))
  84     while (n > 0)
  85       {
  86         size_t n_ascii = encoding_guess_count_ascii (buffer, n);
  87         if (n == n_ascii)
  88           n = fread (buffer, 1, bufsize, stdin);
  89         else
  90           {
  91             memmove (buffer, buffer + n_ascii, n - n_ascii);
  92             n -= n_ascii;
  93             n += fread (buffer + n, 1, bufsize - n, stdin);
  94
  95             guess = encoding_guess_tail_encoding (encoding, buffer, n);
  96             break;
  97           }
  98       }
  99   puts (guess);
 100   free (buffer);
 101
 102   return 0;
 103 }