examples/example2.c

   1 /* example2.c --- Example code showing how to use punycode.
   2  * Copyright (C) 2002, 2003, 2004  Simon Josefsson
   3  * Copyright (C) 2002  Adam M. Costello
   4  *
   5  * This file is part of GNU Libidn.
   6  *
   7  * GNU Libidn is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU Lesser General Public
   9  * License as published by the Free Software Foundation; either
  10  * version 2.1 of the License, or (at your option) any later version.
  11  *
  12  * GNU Libidn is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  15  * Lesser General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU Lesser General Public
  18  * License along with GNU Libidn; if not, write to the Free Software
  19  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  20  *
  21  */
  22
  23 #include <locale.h>             /* setlocale() */
  24
  25 /*
  26  * This file is derived from RFC 3492 written by Adam M. Costello.
  27  *
  28  * Disclaimer and license: Regarding this entire document or any
  29  * portion of it (including the pseudocode and C code), the author
  30  * makes no guarantees and is not responsible for any damage resulting
  31  * from its use.  The author grants irrevocable permission to anyone
  32  * to use, modify, and distribute it in any way that does not diminish
  33  * the rights of anyone else to use, modify, and distribute it,
  34  * provided that redistributed derivative works do not contain
  35  * misleading author or version information.  Derivative works need
  36  * not be licensed under similar terms.
  37  *
  38  */
  39
  40 #include <assert.h>
  41 #include <stdio.h>
  42 #include <stdlib.h>
  43 #include <string.h>
  44
  45 #include <punycode.h>
  46
  47 /* For testing, we'll just set some compile-time limits rather than */
  48 /* use malloc(), and set a compile-time option rather than using a  */
  49 /* command-line option.                                             */
  50
  51 enum
  52 {
  53   unicode_max_length = 256,
  54   ace_max_length = 256
  55 };
  56
  57 static void
  58 usage (char **argv)
  59 {
  60   fprintf (stderr,
  61            "\n"
  62            "%s -e reads code points and writes a Punycode string.\n"
  63            "%s -d reads a Punycode string and writes code points.\n"
  64            "\n"
  65            "Input and output are plain text in the native character set.\n"
  66            "Code points are in the form u+hex separated by whitespace.\n"
  67            "Although the specification allows Punycode strings to contain\n"
  68            "any characters from the ASCII repertoire, this test code\n"
  69            "supports only the printable characters, and needs the Punycode\n"
  70            "string to be followed by a newline.\n"
  71            "The case of the u in u+hex is the force-to-uppercase flag.\n",
  72            argv[0], argv[0]);
  73   exit (EXIT_FAILURE);
  74 }
  75
  76 static void
  77 fail (const char *msg)
  78 {
  79   fputs (msg, stderr);
  80   exit (EXIT_FAILURE);
  81 }
  82
  83 static const char too_big[] =
  84   "input or output is too large, recompile with larger limits\n";
  85 static const char invalid_input[] = "invalid input\n";
  86 static const char overflow[] = "arithmetic overflow\n";
  87 static const char io_error[] = "I/O error\n";
  88
  89 /* The following string is used to convert printable */
  90 /* characters between ASCII and the native charset:  */
  91
  92 static const char print_ascii[] = "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" " !\"#$%&'()*+,-./" "0123456789:;<=>?" "\0x40"  /* at sign */
  93   "ABCDEFGHIJKLMNO"
  94   "PQRSTUVWXYZ[\\]^_" "`abcdefghijklmno" "pqrstuvwxyz{|}~\n";
  95
  96 int
  97 main (int argc, char **argv)
  98 {
  99   enum punycode_status status;
 100   int r;
 101   size_t input_length, output_length, j;
 102   unsigned char case_flags[unicode_max_length];
 103
 104   setlocale (LC_ALL, "");
 105
 106   if (argc != 2)
 107     usage (argv);
 108   if (argv[1][0] != '-')
 109     usage (argv);
 110   if (argv[1][2] != 0)
 111     usage (argv);
 112
 113   if (argv[1][1] == 'e')
 114     {
 115       uint32_t input[unicode_max_length];
 116       unsigned long codept;
 117       char output[ace_max_length + 1], uplus[3];
 118       int c;
 119
 120       /* Read the input code points: */
 121
 122       input_length = 0;
 123
 124       for (;;)
 125         {
 126           r = scanf ("%2s%lx", uplus, &codept);
 127           if (ferror (stdin))
 128             fail (io_error);
 129           if (r == EOF || r == 0)
 130             break;
 131
 132           if (r != 2 || uplus[1] != '+' || codept > (uint32_t) - 1)
 133             {
 134               fail (invalid_input);
 135             }
 136
 137           if (input_length == unicode_max_length)
 138             fail (too_big);
 139
 140           if (uplus[0] == 'u')
 141             case_flags[input_length] = 0;
 142           else if (uplus[0] == 'U')
 143             case_flags[input_length] = 1;
 144           else
 145             fail (invalid_input);
 146
 147           input[input_length++] = codept;
 148         }
 149
 150       /* Encode: */
 151
 152       output_length = ace_max_length;
 153       status = punycode_encode (input_length, input, case_flags,
 154                                 &output_length, output);
 155       if (status == punycode_bad_input)
 156         fail (invalid_input);
 157       if (status == punycode_big_output)
 158         fail (too_big);
 159       if (status == punycode_overflow)
 160         fail (overflow);
 161       assert (status == punycode_success);
 162
 163       /* Convert to native charset and output: */
 164
 165       for (j = 0; j < output_length; ++j)
 166         {
 167           c = output[j];
 168           assert (c >= 0 && c <= 127);
 169           if (print_ascii[c] == 0)
 170             fail (invalid_input);
 171           output[j] = print_ascii[c];
 172         }
 173
 174       output[j] = 0;
 175       r = puts (output);
 176       if (r == EOF)
 177         fail (io_error);
 178       return EXIT_SUCCESS;
 179     }
 180
 181   if (argv[1][1] == 'd')
 182     {
 183       char input[ace_max_length + 2], *p, *pp;
 184       uint32_t output[unicode_max_length];
 185
 186       /* Read the Punycode input string and convert to ASCII: */
 187
 188       fgets (input, ace_max_length + 2, stdin);
 189       if (ferror (stdin))
 190         fail (io_error);
 191       if (feof (stdin))
 192         fail (invalid_input);
 193       input_length = strlen (input) - 1;
 194       if (input[input_length] != '\n')
 195         fail (too_big);
 196       input[input_length] = 0;
 197
 198       for (p = input; *p != 0; ++p)
 199         {
 200           pp = strchr (print_ascii, *p);
 201           if (pp == 0)
 202             fail (invalid_input);
 203           *p = pp - print_ascii;
 204         }
 205
 206       /* Decode: */
 207
 208       output_length = unicode_max_length;
 209       status = punycode_decode (input_length, input, &output_length,
 210                                 output, case_flags);
 211       if (status == punycode_bad_input)
 212         fail (invalid_input);
 213       if (status == punycode_big_output)
 214         fail (too_big);
 215       if (status == punycode_overflow)
 216         fail (overflow);
 217       assert (status == punycode_success);
 218
 219       /* Output the result: */
 220
 221       for (j = 0; j < output_length; ++j)
 222         {
 223           r = printf ("%s+%04lX\n",
 224                       case_flags[j] ? "U" : "u", (unsigned long) output[j]);
 225           if (r < 0)
 226             fail (io_error);
 227         }
 228
 229       return EXIT_SUCCESS;
 230     }
 231
 232   usage (argv);
 233   return EXIT_SUCCESS;          /* not reached, but quiets compiler warning */
 234 }