tests/utf8-validate.c

   1 /* GLIB - Library of useful routines for C programming
   2  * Copyright (C) 2001 Matthias Clasen <matthiasc@poet.de>
   3  *
   4  * This library is free software; you can redistribute it and/or
   5  * modify it under the terms of the GNU Lesser General Public
   6  * License as published by the Free Software Foundation; either
   7  * version 2 of the License, or (at your option) any later version.
   8  *
   9  * This library 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 GNU
  12  * Lesser General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU Lesser General Public
  15  * License along with this library; if not, write to the
  16  * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  17  * Boston, MA 02111-1307, USA.
  18  */
  19
  20 #include "glib.h"
  21
  22 #define UNICODE_VALID(Char)                   \
  23     ((Char) < 0x110000 &&                     \
  24      (((Char) & 0xFFFFF800) != 0xD800) &&     \
  25      ((Char) < 0xFDD0 || (Char) > 0xFDEF) &&  \
  26      ((Char) & 0xFFFE) != 0xFFFE)
  27
  28
  29
  30 static gboolean any_failed = FALSE;
  31
  32 struct {
  33   const gchar *text;
  34   gint max_len;
  35   gint offset;
  36   gboolean valid;
  37 } test[] = {
  38   /* some tests to check max_len handling */
  39   /* length 1 */
  40   { "abcde", -1, 5, TRUE },
  41   { "abcde", 3, 3, TRUE },
  42   { "abcde", 5, 5, TRUE },
  43   { "abcde", 7, 5, FALSE },
  44   /* length 2 */
  45   { "\xc2\xa9\xc2\xa9\xc2\xa9", -1, 6, TRUE },
  46   { "\xc2\xa9\xc2\xa9\xc2\xa9",  1, 0, FALSE },
  47   { "\xc2\xa9\xc2\xa9\xc2\xa9",  2, 2, TRUE },
  48   { "\xc2\xa9\xc2\xa9\xc2\xa9",  3, 2, FALSE },
  49   { "\xc2\xa9\xc2\xa9\xc2\xa9",  4, 4, TRUE },
  50   { "\xc2\xa9\xc2\xa9\xc2\xa9",  5, 4, FALSE },
  51   { "\xc2\xa9\xc2\xa9\xc2\xa9",  6, 6, TRUE },
  52   { "\xc2\xa9\xc2\xa9\xc2\xa9",  7, 6, FALSE },
  53   /* length 3 */
  54   { "\xe2\x89\xa0\xe2\x89\xa0", -1, 6, TRUE },
  55   { "\xe2\x89\xa0\xe2\x89\xa0",  1, 0, FALSE },
  56   { "\xe2\x89\xa0\xe2\x89\xa0",  2, 0, FALSE },
  57   { "\xe2\x89\xa0\xe2\x89\xa0",  3, 3, TRUE },
  58   { "\xe2\x89\xa0\xe2\x89\xa0",  4, 3, FALSE },
  59   { "\xe2\x89\xa0\xe2\x89\xa0",  5, 3, FALSE },
  60   { "\xe2\x89\xa0\xe2\x89\xa0",  6, 6, TRUE },
  61   { "\xe2\x89\xa0\xe2\x89\xa0",  7, 6, FALSE },
  62
  63   /* examples from http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt */
  64   /* greek 'kosme' */
  65   { "\xce\xba\xe1\xbd\xb9\xcf\x83\xce\xbc\xce\xb5", -1, 11, TRUE },
  66   /* first sequence of each length */
  67   { "\x00", -1, 0, TRUE },
  68   { "\xc2\x80", -1, 2, TRUE },
  69   { "\xe0\xa0\x80", -1, 3, TRUE },
  70   { "\xf0\x90\x80\x80", -1, 4, TRUE },
  71   { "\xf8\x88\x80\x80\x80", -1, 0, FALSE },
  72   { "\xfc\x84\x80\x80\x80\x80", -1, 0, FALSE },
  73   /* last sequence of each length */
  74   { "\x7f", -1, 1, TRUE },
  75   { "\xdf\xbf", -1, 2, TRUE },
  76   { "\xef\xbf\xbf", -1, 0, FALSE },
  77   { "\xf7\xbf\xbf\xbf", -1, 0, FALSE },
  78   { "\xfb\xbf\xbf\xbf\xbf", -1, 0, FALSE },
  79   { "\xfd\xbf\xbf\xbf\xbf\xbf", -1, 0, FALSE },
  80   /* other boundary conditions */
  81   { "\xed\x9f\xbf", -1, 3, TRUE },
  82   { "\xee\x80\x80", -1, 3, TRUE },
  83   { "\xef\xbf\xbd", -1, 3, TRUE },
  84   { "\xf4\x8f\xbf\xbf", -1, 0, FALSE },
  85   { "\xf4\x90\x80\x80", -1, 0, FALSE },
  86   /* malformed sequences */
  87   /* continuation bytes */
  88   { "\x80", -1, 0, FALSE },
  89   { "\xbf", -1, 0, FALSE },
  90   { "\x80\xbf", -1, 0, FALSE },
  91   { "\x80\xbf\x80", -1, 0, FALSE },
  92   { "\x80\xbf\x80\xbf", -1, 0, FALSE },
  93   { "\x80\xbf\x80\xbf\x80", -1, 0, FALSE },
  94   { "\x80\xbf\x80\xbf\x80\xbf", -1, 0, FALSE },
  95   { "\x80\xbf\x80\xbf\x80\xbf\x80", -1, 0, FALSE },
  96
  97   /* all possible continuation byte */
  98   { "\x80", -1, 0, FALSE },
  99   { "\x81", -1, 0, FALSE },
 100   { "\x82", -1, 0, FALSE },
 101   { "\x83", -1, 0, FALSE },
 102   { "\x84", -1, 0, FALSE },
 103   { "\x85", -1, 0, FALSE },
 104   { "\x86", -1, 0, FALSE },
 105   { "\x87", -1, 0, FALSE },
 106   { "\x88", -1, 0, FALSE },
 107   { "\x89", -1, 0, FALSE },
 108   { "\x8a", -1, 0, FALSE },
 109   { "\x8b", -1, 0, FALSE },
 110   { "\x8c", -1, 0, FALSE },
 111   { "\x8d", -1, 0, FALSE },
 112   { "\x8e", -1, 0, FALSE },
 113   { "\x8f", -1, 0, FALSE },
 114   { "\x90", -1, 0, FALSE },
 115   { "\x91", -1, 0, FALSE },
 116   { "\x92", -1, 0, FALSE },
 117   { "\x93", -1, 0, FALSE },
 118   { "\x94", -1, 0, FALSE },
 119   { "\x95", -1, 0, FALSE },
 120   { "\x96", -1, 0, FALSE },
 121   { "\x97", -1, 0, FALSE },
 122   { "\x98", -1, 0, FALSE },
 123   { "\x99", -1, 0, FALSE },
 124   { "\x9a", -1, 0, FALSE },
 125   { "\x9b", -1, 0, FALSE },
 126   { "\x9c", -1, 0, FALSE },
 127   { "\x9d", -1, 0, FALSE },
 128   { "\x9e", -1, 0, FALSE },
 129   { "\x9f", -1, 0, FALSE },
 130   { "\xa0", -1, 0, FALSE },
 131   { "\xa1", -1, 0, FALSE },
 132   { "\xa2", -1, 0, FALSE },
 133   { "\xa3", -1, 0, FALSE },
 134   { "\xa4", -1, 0, FALSE },
 135   { "\xa5", -1, 0, FALSE },
 136   { "\xa6", -1, 0, FALSE },
 137   { "\xa7", -1, 0, FALSE },
 138   { "\xa8", -1, 0, FALSE },
 139   { "\xa9", -1, 0, FALSE },
 140   { "\xaa", -1, 0, FALSE },
 141   { "\xab", -1, 0, FALSE },
 142   { "\xac", -1, 0, FALSE },
 143   { "\xad", -1, 0, FALSE },
 144   { "\xae", -1, 0, FALSE },
 145   { "\xaf", -1, 0, FALSE },
 146   { "\xb0", -1, 0, FALSE },
 147   { "\xb1", -1, 0, FALSE },
 148   { "\xb2", -1, 0, FALSE },
 149   { "\xb3", -1, 0, FALSE },
 150   { "\xb4", -1, 0, FALSE },
 151   { "\xb5", -1, 0, FALSE },
 152   { "\xb6", -1, 0, FALSE },
 153   { "\xb7", -1, 0, FALSE },
 154   { "\xb8", -1, 0, FALSE },
 155   { "\xb9", -1, 0, FALSE },
 156   { "\xba", -1, 0, FALSE },
 157   { "\xbb", -1, 0, FALSE },
 158   { "\xbc", -1, 0, FALSE },
 159   { "\xbd", -1, 0, FALSE },
 160   { "\xbe", -1, 0, FALSE },
 161   { "\xbf", -1, 0, FALSE },
 162   /* lone start characters */
 163   { "\xc0\x20", -1, 0, FALSE },
 164   { "\xc1\x20", -1, 0, FALSE },
 165   { "\xc2\x20", -1, 0, FALSE },
 166   { "\xc3\x20", -1, 0, FALSE },
 167   { "\xc4\x20", -1, 0, FALSE },
 168   { "\xc5\x20", -1, 0, FALSE },
 169   { "\xc6\x20", -1, 0, FALSE },
 170   { "\xc7\x20", -1, 0, FALSE },
 171   { "\xc8\x20", -1, 0, FALSE },
 172   { "\xc9\x20", -1, 0, FALSE },
 173   { "\xca\x20", -1, 0, FALSE },
 174   { "\xcb\x20", -1, 0, FALSE },
 175   { "\xcc\x20", -1, 0, FALSE },
 176   { "\xcd\x20", -1, 0, FALSE },
 177   { "\xce\x20", -1, 0, FALSE },
 178   { "\xcf\x20", -1, 0, FALSE },
 179   { "\xd0\x20", -1, 0, FALSE },
 180   { "\xd1\x20", -1, 0, FALSE },
 181   { "\xd2\x20", -1, 0, FALSE },
 182   { "\xd3\x20", -1, 0, FALSE },
 183   { "\xd4\x20", -1, 0, FALSE },
 184   { "\xd5\x20", -1, 0, FALSE },
 185   { "\xd6\x20", -1, 0, FALSE },
 186   { "\xd7\x20", -1, 0, FALSE },
 187   { "\xd8\x20", -1, 0, FALSE },
 188   { "\xd9\x20", -1, 0, FALSE },
 189   { "\xda\x20", -1, 0, FALSE },
 190   { "\xdb\x20", -1, 0, FALSE },
 191   { "\xdc\x20", -1, 0, FALSE },
 192   { "\xdd\x20", -1, 0, FALSE },
 193   { "\xde\x20", -1, 0, FALSE },
 194   { "\xdf\x20", -1, 0, FALSE },
 195   { "\xe0\x20", -1, 0, FALSE },
 196   { "\xe1\x20", -1, 0, FALSE },
 197   { "\xe2\x20", -1, 0, FALSE },
 198   { "\xe3\x20", -1, 0, FALSE },
 199   { "\xe4\x20", -1, 0, FALSE },
 200   { "\xe5\x20", -1, 0, FALSE },
 201   { "\xe6\x20", -1, 0, FALSE },
 202   { "\xe7\x20", -1, 0, FALSE },
 203   { "\xe8\x20", -1, 0, FALSE },
 204   { "\xe9\x20", -1, 0, FALSE },
 205   { "\xea\x20", -1, 0, FALSE },
 206   { "\xeb\x20", -1, 0, FALSE },
 207   { "\xec\x20", -1, 0, FALSE },
 208   { "\xed\x20", -1, 0, FALSE },
 209   { "\xee\x20", -1, 0, FALSE },
 210   { "\xef\x20", -1, 0, FALSE },
 211   { "\xf0\x20", -1, 0, FALSE },
 212   { "\xf1\x20", -1, 0, FALSE },
 213   { "\xf2\x20", -1, 0, FALSE },
 214   { "\xf3\x20", -1, 0, FALSE },
 215   { "\xf4\x20", -1, 0, FALSE },
 216   { "\xf5\x20", -1, 0, FALSE },
 217   { "\xf6\x20", -1, 0, FALSE },
 218   { "\xf7\x20", -1, 0, FALSE },
 219   { "\xf8\x20", -1, 0, FALSE },
 220   { "\xf9\x20", -1, 0, FALSE },
 221   { "\xfa\x20", -1, 0, FALSE },
 222   { "\xfb\x20", -1, 0, FALSE },
 223   { "\xfc\x20", -1, 0, FALSE },
 224   { "\xfd\x20", -1, 0, FALSE },
 225   /* missing continuation bytes */
 226   { "\x20\xc0", -1, 1, FALSE },
 227   { "\x20\xe0\x80", -1, 1, FALSE },
 228   { "\x20\xf0\x80\x80", -1, 1, FALSE },
 229   { "\x20\xf8\x80\x80\x80", -1, 1, FALSE },
 230   { "\x20\xfc\x80\x80\x80\x80", -1, 1, FALSE },
 231   { "\x20\xdf", -1, 1, FALSE },
 232   { "\x20\xef\xbf", -1, 1, FALSE },
 233   { "\x20\xf7\xbf\xbf", -1, 1, FALSE },
 234   { "\x20\xfb\xbf\xbf\xbf", -1, 1, FALSE },
 235   { "\x20\xfd\xbf\xbf\xbf\xbf", -1, 1, FALSE },
 236   /* impossible bytes */
 237   { "\x20\xfe\x20", -1, 1, FALSE },
 238   { "\x20\xff\x20", -1, 1, FALSE },
 239   /* overlong sequences */
 240   { "\x20\xc0\xaf\x20", -1, 1, FALSE },
 241   { "\x20\xe0\x80\xaf\x20", -1, 1, FALSE },
 242   { "\x20\xf0\x80\x80\xaf\x20", -1, 1, FALSE },
 243   { "\x20\xf8\x80\x80\x80\xaf\x20", -1, 1, FALSE },
 244   { "\x20\xfc\x80\x80\x80\x80\xaf\x20", -1, 1, FALSE },
 245   { "\x20\xc1\xbf\x20", -1, 1, FALSE },
 246   { "\x20\xe0\x9f\xbf\x20", -1, 1, FALSE },
 247   { "\x20\xf0\x8f\xbf\xbf\x20", -1, 1, FALSE },
 248   { "\x20\xf8\x87\xbf\xbf\xbf\x20", -1, 1, FALSE },
 249   { "\x20\xfc\x83\xbf\xbf\xbf\xbf\x20", -1, 1, FALSE },
 250   { "\x20\xc0\x80\x20", -1, 1, FALSE },
 251   { "\x20\xe0\x80\x80\x20", -1, 1, FALSE },
 252   { "\x20\xf0\x80\x80\x80\x20", -1, 1, FALSE },
 253   { "\x20\xf8\x80\x80\x80\x80\x20", -1, 1, FALSE },
 254   { "\x20\xfc\x80\x80\x80\x80\x80\x20", -1, 1, FALSE },
 255   /* illegal code positions */
 256   { "\x20\xed\xa0\x80\x20", -1, 1, FALSE },
 257   { "\x20\xed\xad\xbf\x20", -1, 1, FALSE },
 258   { "\x20\xed\xae\x80\x20", -1, 1, FALSE },
 259   { "\x20\xed\xaf\xbf\x20", -1, 1, FALSE },
 260   { "\x20\xed\xb0\x80\x20", -1, 1, FALSE },
 261   { "\x20\xed\xbe\x80\x20", -1, 1, FALSE },
 262   { "\x20\xed\xbf\xbf\x20", -1, 1, FALSE },
 263   { "\x20\xed\xa0\x80\xed\xb0\x80\x20", -1, 1, FALSE },
 264   { "\x20\xed\xa0\x80\xed\xbf\xbf\x20", -1, 1, FALSE },
 265   { "\x20\xed\xad\xbf\xed\xb0\x80\x20", -1, 1, FALSE },
 266   { "\x20\xed\xad\xbf\xed\xbf\xbf\x20", -1, 1, FALSE },
 267   { "\x20\xed\xae\x80\xed\xb0\x80\x20", -1, 1, FALSE },
 268   { "\x20\xed\xae\x80\xed\xbf\xbf\x20", -1, 1, FALSE },
 269   { "\x20\xed\xaf\xbf\xed\xb0\x80\x20", -1, 1, FALSE },
 270   { "\x20\xed\xaf\xbf\xed\xbf\xbf\x20", -1, 1, FALSE },
 271   { "\x20\xef\xbf\xbe\x20", -1, 1, FALSE },
 272   { "\x20\xef\xbf\xbf\x20", -1, 1, FALSE },
 273
 274   { NULL, }
 275 };
 276
 277 static void
 278 do_test (gint         index,
 279          const gchar *text,
 280          gint         max_len,
 281          gint         offset,
 282          gboolean     valid)
 283 {
 284   const gchar *end;
 285   gboolean result;
 286
 287   result = g_utf8_validate (text, max_len, &end);
 288
 289   if (result != valid || end - text != offset)
 290     {
 291       GString *str;
 292       const gchar *p;
 293
 294       any_failed = TRUE;
 295
 296       str = g_string_new (0);
 297       for (p = text; *p; p++)
 298         g_string_append_printf (str, "\\x%02hhx", *p);
 299       g_print ("%d: g_utf8_validate (\"%s\", %d) failed, "
 300                "expected %s %d, got %s %d\n",
 301                index,
 302                str->str, max_len,
 303                valid ? "TRUE" : "FALSE", offset,
 304                result ? "TRUE" : "FALSE", (gint) (end - text));
 305       g_string_free (str, FALSE);
 306     }
 307 }
 308
 309 int
 310 main (int argc, char *argv[])
 311 {
 312   gint i;
 313
 314   for (i = 0; test[i].text; i++)
 315     do_test (i, test[i].text, test[i].max_len,
 316              test[i].offset, test[i].valid);
 317
 318   return any_failed ? 1 : 0;
 319 }