example2.c

   1 /* example2.c   Example code showing how to use punycode.
   2  * Copyright (C) 2002, 2003  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 /*
  24  * This file is derived from RFC 3492 written by Adam M. Costello.
  25  *
  26  * Disclaimer and license: Regarding this entire document or any
  27  * portion of it (including the pseudocode and C code), the author
  28  * makes no guarantees and is not responsible for any damage resulting
  29  * from its use.  The author grants irrevocable permission to anyone
  30  * to use, modify, and distribute it in any way that does not diminish
  31  * the rights of anyone else to use, modify, and distribute it,
  32  * provided that redistributed derivative works do not contain
  33  * misleading author or version information.  Derivative works need
  34  * not be licensed under similar terms.
  35  *
  36  */
  37
  38 #include <assert.h>
  39 #include <stdio.h>
  40 #include <stdlib.h>
  41 #include <string.h>
  42
  43 #include "punycode.h"
  44
  45 /* For testing, we'll just set some compile-time limits rather than */
  46 /* use malloc(), and set a compile-time option rather than using a  */
  47 /* command-line option.                                             */
  48
  49 enum
  50 {
  51   unicode_max_length = 256,
  52   ace_max_length = 256
  53 };
  54
  55 static void
  56 usage (char **argv)
  57 {
  58   fprintf (stderr,
  59            "\n"
  60            "%s -e reads code points and writes a Punycode string.\n"
  61            "%s -d reads a Punycode string and writes code points.\n"
  62            "\n"
  63            "Input and output are plain text in the native character set.\n"
  64            "Code points are in the form u+hex separated by whitespace.\n"
  65            "Although the specification allows Punycode strings to contain\n"
  66            "any characters from the ASCII repertoire, this test code\n"
  67            "supports only the printable characters, and needs the Punycode\n"
  68            "string to be followed by a newline.\n"
  69            "The case of the u in u+hex is the force-to-uppercase flag.\n",
  70            argv[0], argv[0]);
  71   exit (EXIT_FAILURE);
  72 }
  73
  74 static void
  75 fail (const char *msg)
  76 {
  77   fputs (msg, stderr);
  78   exit (EXIT_FAILURE);
  79 }
  80
  81 static const char too_big[] =
  82   "input or output is too large, recompile with larger limits\n";
  83 static const char invalid_input[] = "invalid input\n";
  84 static const char overflow[] = "arithmetic overflow\n";
  85 static const char io_error[] = "I/O error\n";
  86
  87
  88 /* The following string is used to convert printable */
  89 /* characters between ASCII and the native charset:  */
  90
  91 static const char print_ascii[] =
  92   "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n"
  93   "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n"
  94   " !\"#$%&'()*+,-./"
  95   "0123456789:;<=>?"
  96   "\x40""ABCDEFGHIJKLMNO"
  97   "PQRSTUVWXYZ[\\]^_" "`abcdefghijklmno" "pqrstuvwxyz{|}~\n";
  98
  99
 100 int
 101 main (int argc, char **argv)
 102 {
 103   int status;
 104   int r;
 105   size_t input_length, output_length, j;
 106   unsigned char case_flags[unicode_max_length];
 107
 108   if (argc != 2)
 109     usage (argv);
 110   if (argv[1][0] != '-')
 111     usage (argv);
 112   if (argv[1][2] != 0)
 113     usage (argv);
 114
 115   if (argv[1][1] == 'e')
 116     {
 117       unsigned long input[unicode_max_length];
 118       unsigned long codept;
 119       char output[ace_max_length + 1], uplus[3];
 120       int c;
 121
 122       /* Read the input code points: */
 123
 124       input_length = 0;
 125
 126       for (;;)
 127         {
 128           r = scanf ("%2s%lx", uplus, &codept);
 129           if (ferror (stdin))
 130             fail (io_error);
 131           if (r == EOF || r == 0)
 132             break;
 133
 134           if (r != 2 || uplus[1] != '+' || codept > (unsigned long) -1)
 135             {
 136               fail (invalid_input);
 137             }
 138
 139           if (input_length == unicode_max_length)
 140             fail (too_big);
 141
 142           if (uplus[0] == 'u')
 143             case_flags[input_length] = 0;
 144           else if (uplus[0] == 'U')
 145             case_flags[input_length] = 1;
 146           else
 147             fail (invalid_input);
 148
 149           input[input_length++] = codept;
 150         }
 151
 152       /* Encode: */
 153
 154       output_length = ace_max_length;
 155       status = punycode_encode (input_length, input, case_flags,
 156                                 &output_length, output);
 157       if (status == PUNYCODE_BAD_INPUT)
 158         fail (invalid_input);
 159       if (status == PUNYCODE_BIG_OUTPUT)
 160         fail (too_big);
 161       if (status == PUNYCODE_OVERFLOW)
 162         fail (overflow);
 163       assert (status == PUNYCODE_SUCCESS);
 164
 165       /* Convert to native charset and output: */
 166
 167       for (j = 0; j < output_length; ++j)
 168         {
 169           c = output[j];
 170           assert (c >= 0 && c <= 127);
 171           if (print_ascii[c] == 0)
 172             fail (invalid_input);
 173           output[j] = print_ascii[c];
 174         }
 175
 176       output[j] = 0;
 177       r = puts (output);
 178       if (r == EOF)
 179         fail (io_error);
 180       return EXIT_SUCCESS;
 181     }
 182
 183   if (argv[1][1] == 'd')
 184     {
 185       char input[ace_max_length + 2], *p, *pp;
 186       unsigned long output[unicode_max_length];
 187
 188       /* Read the Punycode input string and convert to ASCII: */
 189
 190       fgets (input, ace_max_length + 2, stdin);
 191       if (ferror (stdin))
 192         fail (io_error);
 193       if (feof (stdin))
 194         fail (invalid_input);
 195       input_length = strlen (input) - 1;
 196       if (input[input_length] != '\n')
 197         fail (too_big);
 198       input[input_length] = 0;
 199
 200       for (p = input; *p != 0; ++p)
 201         {
 202           pp = strchr (print_ascii, *p);
 203           if (pp == 0)
 204             fail (invalid_input);
 205           *p = pp - print_ascii;
 206         }
 207
 208       /* Decode: */
 209
 210       output_length = unicode_max_length;
 211       status = punycode_decode (input_length, input, &output_length,
 212                                 output, case_flags);
 213       if (status == PUNYCODE_BAD_INPUT)
 214         fail (invalid_input);
 215       if (status == PUNYCODE_BIG_OUTPUT)
 216         fail (too_big);
 217       if (status == PUNYCODE_OVERFLOW)
 218         fail (overflow);
 219       assert (status == PUNYCODE_SUCCESS);
 220
 221       /* Output the result: */
 222
 223       for (j = 0; j < output_length; ++j)
 224         {
 225           r = printf ("%s+%04lX\n",
 226                       case_flags[j] ? "U" : "u", (unsigned long) output[j]);
 227           if (r < 0)
 228             fail (io_error);
 229         }
 230
 231       return EXIT_SUCCESS;
 232     }
 233
 234   usage (argv);
 235   return EXIT_SUCCESS;          /* not reached, but quiets compiler warning */
 236
 237 }