1/* Test of conversion of multibyte character to wide character. 2 Copyright (C) 2008, 2009, 2010 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/* Written by Bruno Haible <bruno@clisp.org>, 2008. */ 18 19#include <config.h> 20 21#include <wchar.h> 22 23#include "signature.h" 24SIGNATURE_CHECK (mbrtowc, size_t, (wchar_t *, char const *, size_t, 25 mbstate_t *)); 26 27#include <locale.h> 28#include <stdio.h> 29#include <string.h> 30 31#include "macros.h" 32 33int 34main (int argc, char *argv[]) 35{ 36 mbstate_t state; 37 wchar_t wc; 38 size_t ret; 39 40 /* configure should already have checked that the locale is supported. */ 41 if (setlocale (LC_ALL, "") == NULL) 42 return 1; 43 44 /* Test zero-length input. */ 45 { 46 memset (&state, '\0', sizeof (mbstate_t)); 47 wc = (wchar_t) 0xBADFACE; 48 ret = mbrtowc (&wc, "x", 0, &state); 49 /* gnulib's implementation returns (size_t)(-2). 50 The AIX 5.1 implementation returns (size_t)(-1). 51 glibc's implementation returns 0. */ 52 ASSERT (ret == (size_t)(-2) || ret == (size_t)(-1) || ret == 0); 53 ASSERT (mbsinit (&state)); 54 } 55 56 /* Test NUL byte input. */ 57 { 58 memset (&state, '\0', sizeof (mbstate_t)); 59 wc = (wchar_t) 0xBADFACE; 60 ret = mbrtowc (&wc, "", 1, &state); 61 ASSERT (ret == 0); 62 ASSERT (wc == 0); 63 ASSERT (mbsinit (&state)); 64 ret = mbrtowc (NULL, "", 1, &state); 65 ASSERT (ret == 0); 66 ASSERT (mbsinit (&state)); 67 } 68 69 /* Test single-byte input. */ 70 { 71 int c; 72 char buf[1]; 73 74 memset (&state, '\0', sizeof (mbstate_t)); 75 for (c = 0; c < 0x100; c++) 76 switch (c) 77 { 78 case '\t': case '\v': case '\f': 79 case ' ': case '!': case '"': case '#': case '%': 80 case '&': case '\'': case '(': case ')': case '*': 81 case '+': case ',': case '-': case '.': case '/': 82 case '0': case '1': case '2': case '3': case '4': 83 case '5': case '6': case '7': case '8': case '9': 84 case ':': case ';': case '<': case '=': case '>': 85 case '?': 86 case 'A': case 'B': case 'C': case 'D': case 'E': 87 case 'F': case 'G': case 'H': case 'I': case 'J': 88 case 'K': case 'L': case 'M': case 'N': case 'O': 89 case 'P': case 'Q': case 'R': case 'S': case 'T': 90 case 'U': case 'V': case 'W': case 'X': case 'Y': 91 case 'Z': 92 case '[': case '\\': case ']': case '^': case '_': 93 case 'a': case 'b': case 'c': case 'd': case 'e': 94 case 'f': case 'g': case 'h': case 'i': case 'j': 95 case 'k': case 'l': case 'm': case 'n': case 'o': 96 case 'p': case 'q': case 'r': case 's': case 't': 97 case 'u': case 'v': case 'w': case 'x': case 'y': 98 case 'z': case '{': case '|': case '}': case '~': 99 /* c is in the ISO C "basic character set". */ 100 buf[0] = c; 101 wc = (wchar_t) 0xBADFACE; 102 ret = mbrtowc (&wc, buf, 1, &state); 103 ASSERT (ret == 1); 104 ASSERT (wc == c); 105 ASSERT (mbsinit (&state)); 106 ret = mbrtowc (NULL, buf, 1, &state); 107 ASSERT (ret == 1); 108 ASSERT (mbsinit (&state)); 109 break; 110 } 111 } 112 113 /* Test special calling convention, passing a NULL pointer. */ 114 { 115 memset (&state, '\0', sizeof (mbstate_t)); 116 wc = (wchar_t) 0xBADFACE; 117 ret = mbrtowc (&wc, NULL, 5, &state); 118 ASSERT (ret == 0); 119 ASSERT (wc == (wchar_t) 0xBADFACE); 120 ASSERT (mbsinit (&state)); 121 } 122 123 if (argc > 1) 124 switch (argv[1][0]) 125 { 126 case '1': 127 /* Locale encoding is ISO-8859-1 or ISO-8859-15. */ 128 { 129 char input[] = "B\374\337er"; /* "B����er" */ 130 memset (&state, '\0', sizeof (mbstate_t)); 131 132 wc = (wchar_t) 0xBADFACE; 133 ret = mbrtowc (&wc, input, 1, &state); 134 ASSERT (ret == 1); 135 ASSERT (wc == 'B'); 136 ASSERT (mbsinit (&state)); 137 input[0] = '\0'; 138 139 wc = (wchar_t) 0xBADFACE; 140 ret = mbrtowc (&wc, input + 1, 1, &state); 141 ASSERT (ret == 1); 142 ASSERT (wctob (wc) == (unsigned char) '\374'); 143 ASSERT (mbsinit (&state)); 144 input[1] = '\0'; 145 146 wc = (wchar_t) 0xBADFACE; 147 ret = mbrtowc (&wc, input + 2, 3, &state); 148 ASSERT (ret == 1); 149 ASSERT (wctob (wc) == (unsigned char) '\337'); 150 ASSERT (mbsinit (&state)); 151 input[2] = '\0'; 152 153 wc = (wchar_t) 0xBADFACE; 154 ret = mbrtowc (&wc, input + 3, 2, &state); 155 ASSERT (ret == 1); 156 ASSERT (wc == 'e'); 157 ASSERT (mbsinit (&state)); 158 input[3] = '\0'; 159 160 wc = (wchar_t) 0xBADFACE; 161 ret = mbrtowc (&wc, input + 4, 1, &state); 162 ASSERT (ret == 1); 163 ASSERT (wc == 'r'); 164 ASSERT (mbsinit (&state)); 165 } 166 return 0; 167 168 case '2': 169 /* Locale encoding is UTF-8. */ 170 { 171 char input[] = "B\303\274\303\237er"; /* "B����er" */ 172 memset (&state, '\0', sizeof (mbstate_t)); 173 174 wc = (wchar_t) 0xBADFACE; 175 ret = mbrtowc (&wc, input, 1, &state); 176 ASSERT (ret == 1); 177 ASSERT (wc == 'B'); 178 ASSERT (mbsinit (&state)); 179 input[0] = '\0'; 180 181 wc = (wchar_t) 0xBADFACE; 182 ret = mbrtowc (&wc, input + 1, 1, &state); 183 ASSERT (ret == (size_t)(-2)); 184 ASSERT (wc == (wchar_t) 0xBADFACE); 185 ASSERT (!mbsinit (&state)); 186 input[1] = '\0'; 187 188 wc = (wchar_t) 0xBADFACE; 189 ret = mbrtowc (&wc, input + 2, 5, &state); 190 ASSERT (ret == 1); 191 ASSERT (wctob (wc) == EOF); 192 ASSERT (mbsinit (&state)); 193 input[2] = '\0'; 194 195 wc = (wchar_t) 0xBADFACE; 196 ret = mbrtowc (&wc, input + 3, 4, &state); 197 ASSERT (ret == 2); 198 ASSERT (wctob (wc) == EOF); 199 ASSERT (mbsinit (&state)); 200 input[3] = '\0'; 201 input[4] = '\0'; 202 203 wc = (wchar_t) 0xBADFACE; 204 ret = mbrtowc (&wc, input + 5, 2, &state); 205 ASSERT (ret == 1); 206 ASSERT (wc == 'e'); 207 ASSERT (mbsinit (&state)); 208 input[5] = '\0'; 209 210 wc = (wchar_t) 0xBADFACE; 211 ret = mbrtowc (&wc, input + 6, 1, &state); 212 ASSERT (ret == 1); 213 ASSERT (wc == 'r'); 214 ASSERT (mbsinit (&state)); 215 } 216 return 0; 217 218 case '3': 219 /* Locale encoding is EUC-JP. */ 220 { 221 char input[] = "<\306\374\313\334\270\354>"; /* "<���������>" */ 222 memset (&state, '\0', sizeof (mbstate_t)); 223 224 wc = (wchar_t) 0xBADFACE; 225 ret = mbrtowc (&wc, input, 1, &state); 226 ASSERT (ret == 1); 227 ASSERT (wc == '<'); 228 ASSERT (mbsinit (&state)); 229 input[0] = '\0'; 230 231 wc = (wchar_t) 0xBADFACE; 232 ret = mbrtowc (&wc, input + 1, 2, &state); 233 ASSERT (ret == 2); 234 ASSERT (wctob (wc) == EOF); 235 ASSERT (mbsinit (&state)); 236 input[1] = '\0'; 237 input[2] = '\0'; 238 239 wc = (wchar_t) 0xBADFACE; 240 ret = mbrtowc (&wc, input + 3, 1, &state); 241 ASSERT (ret == (size_t)(-2)); 242 ASSERT (wc == (wchar_t) 0xBADFACE); 243 ASSERT (!mbsinit (&state)); 244 input[3] = '\0'; 245 246 wc = (wchar_t) 0xBADFACE; 247 ret = mbrtowc (&wc, input + 4, 4, &state); 248 ASSERT (ret == 1); 249 ASSERT (wctob (wc) == EOF); 250 ASSERT (mbsinit (&state)); 251 input[4] = '\0'; 252 253 wc = (wchar_t) 0xBADFACE; 254 ret = mbrtowc (&wc, input + 5, 3, &state); 255 ASSERT (ret == 2); 256 ASSERT (wctob (wc) == EOF); 257 ASSERT (mbsinit (&state)); 258 input[5] = '\0'; 259 input[6] = '\0'; 260 261 wc = (wchar_t) 0xBADFACE; 262 ret = mbrtowc (&wc, input + 7, 1, &state); 263 ASSERT (ret == 1); 264 ASSERT (wc == '>'); 265 ASSERT (mbsinit (&state)); 266 } 267 return 0; 268 269 case '4': 270 /* Locale encoding is GB18030. */ 271 { 272 char input[] = "B\250\271\201\060\211\070er"; /* "B����er" */ 273 memset (&state, '\0', sizeof (mbstate_t)); 274 275 wc = (wchar_t) 0xBADFACE; 276 ret = mbrtowc (&wc, input, 1, &state); 277 ASSERT (ret == 1); 278 ASSERT (wc == 'B'); 279 ASSERT (mbsinit (&state)); 280 input[0] = '\0'; 281 282 wc = (wchar_t) 0xBADFACE; 283 ret = mbrtowc (&wc, input + 1, 1, &state); 284 ASSERT (ret == (size_t)(-2)); 285 ASSERT (wc == (wchar_t) 0xBADFACE); 286 ASSERT (!mbsinit (&state)); 287 input[1] = '\0'; 288 289 wc = (wchar_t) 0xBADFACE; 290 ret = mbrtowc (&wc, input + 2, 7, &state); 291 ASSERT (ret == 1); 292 ASSERT (wctob (wc) == EOF); 293 ASSERT (mbsinit (&state)); 294 input[2] = '\0'; 295 296 wc = (wchar_t) 0xBADFACE; 297 ret = mbrtowc (&wc, input + 3, 6, &state); 298 ASSERT (ret == 4); 299 ASSERT (wctob (wc) == EOF); 300 ASSERT (mbsinit (&state)); 301 input[3] = '\0'; 302 input[4] = '\0'; 303 input[5] = '\0'; 304 input[6] = '\0'; 305 306 wc = (wchar_t) 0xBADFACE; 307 ret = mbrtowc (&wc, input + 7, 2, &state); 308 ASSERT (ret == 1); 309 ASSERT (wc == 'e'); 310 ASSERT (mbsinit (&state)); 311 input[5] = '\0'; 312 313 wc = (wchar_t) 0xBADFACE; 314 ret = mbrtowc (&wc, input + 8, 1, &state); 315 ASSERT (ret == 1); 316 ASSERT (wc == 'r'); 317 ASSERT (mbsinit (&state)); 318 } 319 return 0; 320 } 321 322 return 1; 323} 324