Josh Coalson | fda98fb | 2002-05-17 06:33:39 +0000 | [diff] [blame] | 1 | /* |
| 2 | * Copyright (C) 2001 Edmund Grimley Evans <edmundo@rano.org> |
| 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 2 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, write to the Free Software |
| 16 | * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
| 17 | */ |
| 18 | |
| 19 | #include <assert.h> |
| 20 | #include <string.h> |
| 21 | |
| 22 | #include "charset.h" |
| 23 | |
| 24 | void test_any(struct charset *charset) |
| 25 | { |
| 26 | int wc; |
| 27 | char s[2]; |
| 28 | |
| 29 | assert(charset); |
| 30 | |
| 31 | /* Decoder */ |
| 32 | |
| 33 | assert(charset_mbtowc(charset, 0, 0, 0) == 0); |
| 34 | assert(charset_mbtowc(charset, 0, 0, 1) == 0); |
| 35 | assert(charset_mbtowc(charset, 0, (char *)(-1), 0) == 0); |
| 36 | |
| 37 | assert(charset_mbtowc(charset, 0, "a", 0) == 0); |
| 38 | assert(charset_mbtowc(charset, 0, "", 1) == 0); |
| 39 | assert(charset_mbtowc(charset, 0, "b", 1) == 1); |
| 40 | assert(charset_mbtowc(charset, 0, "", 2) == 0); |
| 41 | assert(charset_mbtowc(charset, 0, "c", 2) == 1); |
| 42 | |
| 43 | wc = 'x'; |
| 44 | assert(charset_mbtowc(charset, &wc, "a", 0) == 0 && wc == 'x'); |
| 45 | assert(charset_mbtowc(charset, &wc, "", 1) == 0 && wc == 0); |
| 46 | assert(charset_mbtowc(charset, &wc, "b", 1) == 1 && wc == 'b'); |
| 47 | assert(charset_mbtowc(charset, &wc, "", 2) == 0 && wc == 0); |
| 48 | assert(charset_mbtowc(charset, &wc, "c", 2) == 1 && wc == 'c'); |
| 49 | |
| 50 | /* Encoder */ |
| 51 | |
| 52 | assert(charset_wctomb(charset, 0, 0) == 0); |
| 53 | |
| 54 | s[0] = s[1] = '.'; |
| 55 | assert(charset_wctomb(charset, s, 0) == 1 && |
| 56 | s[0] == '\0' && s[1] == '.'); |
| 57 | assert(charset_wctomb(charset, s, 'x') == 1 && |
| 58 | s[0] == 'x' && s[1] == '.'); |
| 59 | } |
| 60 | |
| 61 | void test_utf8() |
| 62 | { |
| 63 | struct charset *charset; |
| 64 | int wc; |
| 65 | char s[8]; |
| 66 | |
| 67 | charset = charset_find("UTF-8"); |
| 68 | test_any(charset); |
| 69 | |
| 70 | /* Decoder */ |
| 71 | wc = 0; |
| 72 | assert(charset_mbtowc(charset, &wc, "\177", 1) == 1 && wc == 127); |
| 73 | assert(charset_mbtowc(charset, &wc, "\200", 2) == -1); |
| 74 | assert(charset_mbtowc(charset, &wc, "\301\277", 9) == -1); |
| 75 | assert(charset_mbtowc(charset, &wc, "\302\200", 1) == -1); |
| 76 | assert(charset_mbtowc(charset, &wc, "\302\200", 2) == 2 && wc == 128); |
| 77 | assert(charset_mbtowc(charset, &wc, "\302\200", 3) == 2 && wc == 128); |
| 78 | assert(charset_mbtowc(charset, &wc, "\340\237\200", 9) == -1); |
| 79 | assert(charset_mbtowc(charset, &wc, "\340\240\200", 9) == 3 && |
| 80 | wc == 1 << 11); |
| 81 | assert(charset_mbtowc(charset, &wc, "\360\217\277\277", 9) == -1); |
| 82 | assert(charset_mbtowc(charset, &wc, "\360\220\200\200", 9) == 4 && |
| 83 | wc == 1 << 16); |
| 84 | assert(charset_mbtowc(charset, &wc, "\370\207\277\277\277", 9) == -1); |
| 85 | assert(charset_mbtowc(charset, &wc, "\370\210\200\200\200", 9) == 5 && |
| 86 | wc == 1 << 21); |
| 87 | assert(charset_mbtowc(charset, &wc, "\374\203\277\277\277\277", 9) == -1); |
| 88 | assert(charset_mbtowc(charset, &wc, "\374\204\200\200\200\200", 9) == 6 && |
| 89 | wc == 1 << 26); |
| 90 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\277\277", 9) == 6 && |
| 91 | wc == 0x7fffffff); |
| 92 | |
| 93 | assert(charset_mbtowc(charset, &wc, "\302\000", 2) == -1); |
| 94 | assert(charset_mbtowc(charset, &wc, "\302\300", 2) == -1); |
| 95 | assert(charset_mbtowc(charset, &wc, "\340\040\200", 9) == -1); |
| 96 | assert(charset_mbtowc(charset, &wc, "\340\340\200", 9) == -1); |
| 97 | assert(charset_mbtowc(charset, &wc, "\340\240\000", 9) == -1); |
| 98 | assert(charset_mbtowc(charset, &wc, "\340\240\300", 9) == -1); |
| 99 | assert(charset_mbtowc(charset, &wc, "\360\020\200\200", 9) == -1); |
| 100 | assert(charset_mbtowc(charset, &wc, "\360\320\200\200", 9) == -1); |
| 101 | assert(charset_mbtowc(charset, &wc, "\360\220\000\200", 9) == -1); |
| 102 | assert(charset_mbtowc(charset, &wc, "\360\220\300\200", 9) == -1); |
| 103 | assert(charset_mbtowc(charset, &wc, "\360\220\200\000", 9) == -1); |
| 104 | assert(charset_mbtowc(charset, &wc, "\360\220\200\300", 9) == -1); |
| 105 | assert(charset_mbtowc(charset, &wc, "\375\077\277\277\277\277", 9) == -1); |
| 106 | assert(charset_mbtowc(charset, &wc, "\375\377\277\277\277\277", 9) == -1); |
| 107 | assert(charset_mbtowc(charset, &wc, "\375\277\077\277\277\277", 9) == -1); |
| 108 | assert(charset_mbtowc(charset, &wc, "\375\277\377\277\277\277", 9) == -1); |
| 109 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\077\277", 9) == -1); |
| 110 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\377\277", 9) == -1); |
| 111 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\277\077", 9) == -1); |
| 112 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\277\377", 9) == -1); |
| 113 | |
| 114 | assert(charset_mbtowc(charset, &wc, "\376\277\277\277\277\277", 9) == -1); |
| 115 | assert(charset_mbtowc(charset, &wc, "\377\277\277\277\277\277", 9) == -1); |
| 116 | |
| 117 | /* Encoder */ |
| 118 | strcpy(s, "......."); |
| 119 | assert(charset_wctomb(charset, s, 1 << 31) == -1 && |
| 120 | !strcmp(s, ".......")); |
| 121 | assert(charset_wctomb(charset, s, 127) == 1 && |
| 122 | !strcmp(s, "\177......")); |
| 123 | assert(charset_wctomb(charset, s, 128) == 2 && |
| 124 | !strcmp(s, "\302\200.....")); |
| 125 | assert(charset_wctomb(charset, s, 0x7ff) == 2 && |
| 126 | !strcmp(s, "\337\277.....")); |
| 127 | assert(charset_wctomb(charset, s, 0x800) == 3 && |
| 128 | !strcmp(s, "\340\240\200....")); |
| 129 | assert(charset_wctomb(charset, s, 0xffff) == 3 && |
| 130 | !strcmp(s, "\357\277\277....")); |
| 131 | assert(charset_wctomb(charset, s, 0x10000) == 4 && |
| 132 | !strcmp(s, "\360\220\200\200...")); |
| 133 | assert(charset_wctomb(charset, s, 0x1fffff) == 4 && |
| 134 | !strcmp(s, "\367\277\277\277...")); |
| 135 | assert(charset_wctomb(charset, s, 0x200000) == 5 && |
| 136 | !strcmp(s, "\370\210\200\200\200..")); |
| 137 | assert(charset_wctomb(charset, s, 0x3ffffff) == 5 && |
| 138 | !strcmp(s, "\373\277\277\277\277..")); |
| 139 | assert(charset_wctomb(charset, s, 0x4000000) == 6 && |
| 140 | !strcmp(s, "\374\204\200\200\200\200.")); |
| 141 | assert(charset_wctomb(charset, s, 0x7fffffff) == 6 && |
| 142 | !strcmp(s, "\375\277\277\277\277\277.")); |
| 143 | } |
| 144 | |
| 145 | void test_ascii() |
| 146 | { |
| 147 | struct charset *charset; |
| 148 | int wc; |
| 149 | char s[3]; |
| 150 | |
| 151 | charset = charset_find("us-ascii"); |
| 152 | test_any(charset); |
| 153 | |
| 154 | /* Decoder */ |
| 155 | wc = 0; |
| 156 | assert(charset_mbtowc(charset, &wc, "\177", 2) == 1 && wc == 127); |
| 157 | assert(charset_mbtowc(charset, &wc, "\200", 2) == -1); |
| 158 | |
| 159 | /* Encoder */ |
| 160 | strcpy(s, ".."); |
| 161 | assert(charset_wctomb(charset, s, 256) == -1 && !strcmp(s, "..")); |
| 162 | assert(charset_wctomb(charset, s, 255) == -1); |
| 163 | assert(charset_wctomb(charset, s, 128) == -1); |
| 164 | assert(charset_wctomb(charset, s, 127) == 1 && !strcmp(s, "\177.")); |
| 165 | } |
| 166 | |
| 167 | void test_iso1() |
| 168 | { |
| 169 | struct charset *charset; |
| 170 | int wc; |
| 171 | char s[3]; |
| 172 | |
| 173 | charset = charset_find("iso-8859-1"); |
| 174 | test_any(charset); |
| 175 | |
| 176 | /* Decoder */ |
| 177 | wc = 0; |
| 178 | assert(charset_mbtowc(charset, &wc, "\302\200", 9) == 1 && wc == 0xc2); |
| 179 | |
| 180 | /* Encoder */ |
| 181 | strcpy(s, ".."); |
| 182 | assert(charset_wctomb(charset, s, 256) == -1 && !strcmp(s, "..")); |
| 183 | assert(charset_wctomb(charset, s, 255) == 1 && !strcmp(s, "\377.")); |
| 184 | assert(charset_wctomb(charset, s, 128) == 1 && !strcmp(s, "\200.")); |
| 185 | } |
| 186 | |
| 187 | void test_iso2() |
| 188 | { |
| 189 | struct charset *charset; |
| 190 | int wc; |
| 191 | char s[3]; |
| 192 | |
| 193 | charset = charset_find("iso-8859-2"); |
| 194 | test_any(charset); |
| 195 | |
| 196 | /* Decoder */ |
| 197 | wc = 0; |
| 198 | assert(charset_mbtowc(charset, &wc, "\302\200", 9) == 1 && wc == 0xc2); |
| 199 | assert(charset_mbtowc(charset, &wc, "\377", 2) == 1 && wc == 0x2d9); |
| 200 | |
| 201 | /* Encoder */ |
| 202 | strcpy(s, ".."); |
| 203 | assert(charset_wctomb(charset, s, 256) == -1 && !strcmp(s, "..")); |
| 204 | assert(charset_wctomb(charset, s, 255) == -1 && !strcmp(s, "..")); |
| 205 | assert(charset_wctomb(charset, s, 258) == 1 && !strcmp(s, "\303.")); |
| 206 | assert(charset_wctomb(charset, s, 128) == 1 && !strcmp(s, "\200.")); |
| 207 | } |
| 208 | |
| 209 | void test_convert() |
| 210 | { |
| 211 | const char *p; |
| 212 | char *q, *r; |
| 213 | char s[256]; |
| 214 | size_t n, n2; |
| 215 | int i; |
| 216 | |
| 217 | p = "\000x\302\200\375\277\277\277\277\277"; |
| 218 | assert(charset_convert("UTF-8", "UTF-8", p, 10, &q, &n) == 0 && |
| 219 | n == 10 && !strcmp(p, q)); |
| 220 | assert(charset_convert("UTF-8", "UTF-8", "x\301\277y", 4, &q, &n) == 2 && |
| 221 | n == 4 && !strcmp(q, "x##y")); |
| 222 | assert(charset_convert("UTF-8", "UTF-8", "x\301\277y", 4, 0, &n) == 2 && |
| 223 | n == 4); |
| 224 | assert(charset_convert("UTF-8", "UTF-8", "x\301\277y", 4, &q, 0) == 2 && |
| 225 | !strcmp(q, "x##y")); |
| 226 | assert(charset_convert("UTF-8", "iso-8859-1", |
| 227 | "\302\200\304\200x", 5, &q, &n) == 1 && |
| 228 | n == 3 && !strcmp(q, "\200?x")); |
| 229 | assert(charset_convert("iso-8859-1", "UTF-8", |
| 230 | "\000\200\377", 3, &q, &n) == 0 && |
| 231 | n == 5 && !memcmp(q, "\000\302\200\303\277", 5)); |
| 232 | assert(charset_convert("iso-8859-1", "iso-8859-1", |
| 233 | "\000\200\377", 3, &q, &n) == 0 && |
| 234 | n == 3 && !memcmp(q, "\000\200\377", 3)); |
| 235 | |
| 236 | assert(charset_convert("iso-8859-2", "utf-8", "\300", 1, &q, &n) == 0 && |
| 237 | n == 2 && !strcmp(q, "\305\224")); |
| 238 | assert(charset_convert("utf-8", "iso-8859-2", "\305\224", 2, &q, &n) == 0 && |
| 239 | n == 1 && !strcmp(q, "\300")); |
| 240 | |
| 241 | for (i = 0; i < 256; i++) |
| 242 | s[i] = i; |
| 243 | |
| 244 | assert(charset_convert("iso-8859-2", "utf-8", s, 256, &q, &n) == 0); |
| 245 | assert(charset_convert("utf-8", "iso-8859-2", q, n, &r, &n2) == 0); |
| 246 | assert(n2 == 256 && !memcmp(r, s, n2)); |
| 247 | } |
| 248 | |
| 249 | int main() |
| 250 | { |
| 251 | test_utf8(); |
| 252 | test_ascii(); |
| 253 | test_iso1(); |
| 254 | test_iso2(); |
| 255 | |
| 256 | test_convert(); |
| 257 | |
| 258 | return 0; |
| 259 | } |