| 1 | /* |
| 2 | * This file is part of DisOrder. |
| 3 | * Copyright (C) 2005, 2007 Richard Kettlewell |
| 4 | * |
| 5 | * This program is free software; you can redistribute it and/or modify |
| 6 | * it under the terms of the GNU General Public License as published by |
| 7 | * the Free Software Foundation; either version 2 of the License, or |
| 8 | * (at your option) any later version. |
| 9 | * |
| 10 | * This program is distributed in the hope that it will be useful, but |
| 11 | * WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 13 | * General Public License for more details. |
| 14 | * |
| 15 | * You should have received a copy of the GNU General Public License |
| 16 | * along with this program; if not, write to the Free Software |
| 17 | * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 |
| 18 | * USA |
| 19 | */ |
| 20 | /** @file lib/test.c @brief Library tests */ |
| 21 | |
| 22 | #include <config.h> |
| 23 | #include "types.h" |
| 24 | |
| 25 | #include <stdio.h> |
| 26 | #include <string.h> |
| 27 | #include <stdlib.h> |
| 28 | #include <errno.h> |
| 29 | #include <ctype.h> |
| 30 | #include <assert.h> |
| 31 | |
| 32 | #include "utf8.h" |
| 33 | #include "mem.h" |
| 34 | #include "log.h" |
| 35 | #include "vector.h" |
| 36 | #include "charset.h" |
| 37 | #include "mime.h" |
| 38 | #include "hex.h" |
| 39 | #include "words.h" |
| 40 | #include "heap.h" |
| 41 | |
| 42 | static int tests, errors; |
| 43 | |
| 44 | /** @brief Checks that @p expr is nonzero */ |
| 45 | #define insist(expr) do { \ |
| 46 | if(!(expr)) { \ |
| 47 | ++errors; \ |
| 48 | fprintf(stderr, "%s:%d: error checking %s\n", \ |
| 49 | __FILE__, __LINE__, #expr); \ |
| 50 | } \ |
| 51 | ++tests; \ |
| 52 | } while(0) |
| 53 | |
| 54 | static const char *format(const char *s) { |
| 55 | struct dynstr d; |
| 56 | int c; |
| 57 | char buf[10]; |
| 58 | |
| 59 | dynstr_init(&d); |
| 60 | while((c = (unsigned char)*s++)) { |
| 61 | if(c >= ' ' && c <= '~') |
| 62 | dynstr_append(&d, c); |
| 63 | else { |
| 64 | sprintf(buf, "\\x%02X", (unsigned)c); |
| 65 | dynstr_append_string(&d, buf); |
| 66 | } |
| 67 | } |
| 68 | dynstr_terminate(&d); |
| 69 | return d.vec; |
| 70 | } |
| 71 | |
| 72 | #define check_string(GOT, WANT) do { \ |
| 73 | const char *g = GOT; \ |
| 74 | const char *w = WANT; \ |
| 75 | \ |
| 76 | if(w == 0) { \ |
| 77 | fprintf(stderr, "%s:%d: %s returned 0\n", \ |
| 78 | __FILE__, __LINE__, #GOT); \ |
| 79 | ++errors; \ |
| 80 | } else if(strcmp(w, g)) { \ |
| 81 | fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \ |
| 82 | __FILE__, __LINE__, #GOT, format(g), format(w)); \ |
| 83 | ++errors; \ |
| 84 | } \ |
| 85 | ++tests; \ |
| 86 | } while(0) |
| 87 | |
| 88 | static uint32_t *ucs4parse(const char *s) { |
| 89 | struct dynstr_ucs4 d; |
| 90 | char *e; |
| 91 | |
| 92 | dynstr_ucs4_init(&d); |
| 93 | while(*s) { |
| 94 | errno = 0; |
| 95 | dynstr_ucs4_append(&d, strtoul(s, &e, 0)); |
| 96 | if(errno) fatal(errno, "strtoul (%s)", s); |
| 97 | s = e; |
| 98 | } |
| 99 | dynstr_ucs4_terminate(&d); |
| 100 | return d.vec; |
| 101 | } |
| 102 | |
| 103 | static void test_utf8(void) { |
| 104 | /* Test validutf8, convert to UCS-4, check the answer is right, |
| 105 | * convert back to UTF-8, check we got to where we started */ |
| 106 | #define U8(CHARS, WORDS) do { \ |
| 107 | uint32_t *w = ucs4parse(WORDS); \ |
| 108 | uint32_t *ucs; \ |
| 109 | char *u8; \ |
| 110 | \ |
| 111 | insist(validutf8(CHARS)); \ |
| 112 | ucs = utf82ucs4(CHARS); \ |
| 113 | insist(ucs != 0); \ |
| 114 | insist(!ucs4cmp(w, ucs)); \ |
| 115 | u8 = ucs42utf8(ucs); \ |
| 116 | insist(u8 != 0); \ |
| 117 | insist(!strcmp(u8, CHARS)); \ |
| 118 | } while(0) |
| 119 | |
| 120 | fprintf(stderr, "test_utf8\n"); |
| 121 | |
| 122 | /* empty string */ |
| 123 | |
| 124 | U8("", ""); |
| 125 | |
| 126 | /* ASCII characters */ |
| 127 | |
| 128 | U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~", |
| 129 | "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d " |
| 130 | "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a " |
| 131 | "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 " |
| 132 | "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 " |
| 133 | "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 " |
| 134 | "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e " |
| 135 | "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b " |
| 136 | "0x7c 0x7d 0x7e"); |
| 137 | U8("\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\177", |
| 138 | "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 " |
| 139 | "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d " |
| 140 | "0x1e 0x1f 0x7f"); |
| 141 | |
| 142 | /* from RFC3629 */ |
| 143 | |
| 144 | /* UTF8-2 = %xC2-DF UTF8-tail */ |
| 145 | insist(!validutf8("\xC0\x80")); |
| 146 | insist(!validutf8("\xC1\x80")); |
| 147 | insist(!validutf8("\xC2\x7F")); |
| 148 | U8("\xC2\x80", "0x80"); |
| 149 | U8("\xDF\xBF", "0x7FF"); |
| 150 | insist(!validutf8("\xDF\xC0")); |
| 151 | |
| 152 | /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) / |
| 153 | * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail ) |
| 154 | */ |
| 155 | insist(!validutf8("\xE0\x9F\x80")); |
| 156 | U8("\xE0\xA0\x80", "0x800"); |
| 157 | U8("\xE0\xBF\xBF", "0xFFF"); |
| 158 | insist(!validutf8("\xE0\xC0\xBF")); |
| 159 | |
| 160 | insist(!validutf8("\xE1\x80\x7F")); |
| 161 | U8("\xE1\x80\x80", "0x1000"); |
| 162 | U8("\xEC\xBF\xBF", "0xCFFF"); |
| 163 | insist(!validutf8("\xEC\xC0\xBF")); |
| 164 | |
| 165 | U8("\xED\x80\x80", "0xD000"); |
| 166 | U8("\xED\x9F\xBF", "0xD7FF"); |
| 167 | insist(!validutf8("\xED\xA0\xBF")); |
| 168 | |
| 169 | insist(!validutf8("\xEE\x7f\x80")); |
| 170 | U8("\xEE\x80\x80", "0xE000"); |
| 171 | U8("\xEF\xBF\xBF", "0xFFFF"); |
| 172 | insist(!validutf8("\xEF\xC0\xBF")); |
| 173 | |
| 174 | /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) / |
| 175 | * %xF4 %x80-8F 2( UTF8-tail ) |
| 176 | */ |
| 177 | insist(!validutf8("\xF0\x8F\x80\x80")); |
| 178 | U8("\xF0\x90\x80\x80", "0x10000"); |
| 179 | U8("\xF0\xBF\xBF\xBF", "0x3FFFF"); |
| 180 | insist(!validutf8("\xF0\xC0\x80\x80")); |
| 181 | |
| 182 | insist(!validutf8("\xF1\x80\x80\x7F")); |
| 183 | U8("\xF1\x80\x80\x80", "0x40000"); |
| 184 | U8("\xF3\xBF\xBF\xBF", "0xFFFFF"); |
| 185 | insist(!validutf8("\xF3\xC0\x80\x80")); |
| 186 | |
| 187 | insist(!validutf8("\xF4\x80\x80\x7F")); |
| 188 | U8("\xF4\x80\x80\x80", "0x100000"); |
| 189 | U8("\xF4\x8F\xBF\xBF", "0x10FFFF"); |
| 190 | insist(!validutf8("\xF4\x90\x80\x80")); |
| 191 | |
| 192 | /* miscellaneous non-UTF-8 rubbish */ |
| 193 | insist(!validutf8("\x80")); |
| 194 | insist(!validutf8("\xBF")); |
| 195 | insist(!validutf8("\xC0")); |
| 196 | insist(!validutf8("\xC0\x7F")); |
| 197 | insist(!validutf8("\xC0\xC0")); |
| 198 | insist(!validutf8("\xE0")); |
| 199 | insist(!validutf8("\xE0\x7F")); |
| 200 | insist(!validutf8("\xE0\xC0")); |
| 201 | insist(!validutf8("\xE0\x80")); |
| 202 | insist(!validutf8("\xE0\x80\x7f")); |
| 203 | insist(!validutf8("\xE0\x80\xC0")); |
| 204 | insist(!validutf8("\xF0")); |
| 205 | insist(!validutf8("\xF0\x7F")); |
| 206 | insist(!validutf8("\xF0\xC0")); |
| 207 | insist(!validutf8("\xF0\x80")); |
| 208 | insist(!validutf8("\xF0\x80\x7f")); |
| 209 | insist(!validutf8("\xF0\x80\xC0")); |
| 210 | insist(!validutf8("\xF0\x80\x80\x7f")); |
| 211 | insist(!validutf8("\xF0\x80\x80\xC0")); |
| 212 | insist(!validutf8("\xF5\x80\x80\x80")); |
| 213 | insist(!validutf8("\xF8")); |
| 214 | } |
| 215 | |
| 216 | static void test_mime(void) { |
| 217 | char *t, *n, *v; |
| 218 | |
| 219 | fprintf(stderr, "test_mime\n"); |
| 220 | |
| 221 | t = n = v = 0; |
| 222 | insist(!mime_content_type("text/plain", &t, &n, &v)); |
| 223 | insist(!strcmp(t, "text/plain")); |
| 224 | insist(n == 0); |
| 225 | insist(v == 0); |
| 226 | |
| 227 | t = n = v = 0; |
| 228 | insist(!mime_content_type("TEXT ((nested) comment) /plain", &t, &n, &v)); |
| 229 | insist(!strcmp(t, "text/plain")); |
| 230 | insist(n == 0); |
| 231 | insist(v == 0); |
| 232 | |
| 233 | t = n = v = 0; |
| 234 | insist(!mime_content_type(" text/plain ; Charset=utf-8", &t, &n, &v)); |
| 235 | insist(!strcmp(t, "text/plain")); |
| 236 | insist(!strcmp(n, "charset")); |
| 237 | insist(!strcmp(v, "utf-8")); |
| 238 | |
| 239 | t = n = v = 0; |
| 240 | insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t, &n, &v)); |
| 241 | insist(!strcmp(t, "text/plain")); |
| 242 | insist(!strcmp(n, "charset")); |
| 243 | insist(!strcmp(v, "ISO-8859-1")); |
| 244 | |
| 245 | /* XXX mime_parse */ |
| 246 | /* XXX mime_multipart */ |
| 247 | /* XXX mime_rfc2388_content_disposition */ |
| 248 | |
| 249 | check_string(mime_qp(""), ""); |
| 250 | check_string(mime_qp("foobar"), "foobar"); |
| 251 | check_string(mime_qp("foo=20bar"), "foo bar"); |
| 252 | check_string(mime_qp("x \r\ny"), "x\r\ny"); |
| 253 | check_string(mime_qp("x=\r\ny"), "xy"); |
| 254 | check_string(mime_qp("x= \r\ny"), "xy"); |
| 255 | check_string(mime_qp("x =\r\ny"), "x y"); |
| 256 | check_string(mime_qp("x = \r\ny"), "x y"); |
| 257 | |
| 258 | /* from RFC2045 */ |
| 259 | check_string(mime_qp("Now's the time =\r\n" |
| 260 | "for all folk to come=\r\n" |
| 261 | " to the aid of their country."), |
| 262 | "Now's the time for all folk to come to the aid of their country."); |
| 263 | |
| 264 | check_string(mime_base64(""), ""); |
| 265 | check_string(mime_base64("BBBB"), "\x04\x10\x41"); |
| 266 | check_string(mime_base64("////"), "\xFF\xFF\xFF"); |
| 267 | check_string(mime_base64("//BB"), "\xFF\xF0\x41"); |
| 268 | check_string(mime_base64("BBBB//BB////"), |
| 269 | "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF"); |
| 270 | check_string(mime_base64("B B B B / / B B / / / /"), |
| 271 | "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF"); |
| 272 | check_string(mime_base64("B\r\nBBB.// B-B//~//"), |
| 273 | "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF"); |
| 274 | check_string(mime_base64("BBBB="), |
| 275 | "\x04\x10\x41"); |
| 276 | check_string(mime_base64("BBBBx="), /* not actually valid base64 */ |
| 277 | "\x04\x10\x41"); |
| 278 | check_string(mime_base64("BBBB BB=="), |
| 279 | "\x04\x10\x41" "\x04"); |
| 280 | check_string(mime_base64("BBBB BBB="), |
| 281 | "\x04\x10\x41" "\x04\x10"); |
| 282 | } |
| 283 | |
| 284 | static void test_hex(void) { |
| 285 | unsigned n; |
| 286 | static const unsigned char h[] = { 0x00, 0xFF, 0x80, 0x7F }; |
| 287 | uint8_t *u; |
| 288 | size_t ul; |
| 289 | |
| 290 | fprintf(stderr, "test_hex\n"); |
| 291 | |
| 292 | for(n = 0; n <= UCHAR_MAX; ++n) { |
| 293 | if(!isxdigit(n)) |
| 294 | insist(unhexdigitq(n) == -1); |
| 295 | } |
| 296 | insist(unhexdigitq('0') == 0); |
| 297 | insist(unhexdigitq('1') == 1); |
| 298 | insist(unhexdigitq('2') == 2); |
| 299 | insist(unhexdigitq('3') == 3); |
| 300 | insist(unhexdigitq('4') == 4); |
| 301 | insist(unhexdigitq('5') == 5); |
| 302 | insist(unhexdigitq('6') == 6); |
| 303 | insist(unhexdigitq('7') == 7); |
| 304 | insist(unhexdigitq('8') == 8); |
| 305 | insist(unhexdigitq('9') == 9); |
| 306 | insist(unhexdigitq('a') == 10); |
| 307 | insist(unhexdigitq('b') == 11); |
| 308 | insist(unhexdigitq('c') == 12); |
| 309 | insist(unhexdigitq('d') == 13); |
| 310 | insist(unhexdigitq('e') == 14); |
| 311 | insist(unhexdigitq('f') == 15); |
| 312 | insist(unhexdigitq('A') == 10); |
| 313 | insist(unhexdigitq('B') == 11); |
| 314 | insist(unhexdigitq('C') == 12); |
| 315 | insist(unhexdigitq('D') == 13); |
| 316 | insist(unhexdigitq('E') == 14); |
| 317 | insist(unhexdigitq('F') == 15); |
| 318 | check_string(hex(h, sizeof h), "00ff807f"); |
| 319 | check_string(hex(0, 0), ""); |
| 320 | u = unhex("00ff807f", &ul); |
| 321 | insist(ul == 4); |
| 322 | insist(memcmp(u, h, 4) == 0); |
| 323 | u = unhex("00FF807F", &ul); |
| 324 | insist(ul == 4); |
| 325 | insist(memcmp(u, h, 4) == 0); |
| 326 | u = unhex("", &ul); |
| 327 | insist(ul == 0); |
| 328 | fprintf(stderr, "2 ERROR reports expected {\n"); |
| 329 | insist(unhex("F", 0) == 0); |
| 330 | insist(unhex("az", 0) == 0); |
| 331 | fprintf(stderr, "}\n"); |
| 332 | } |
| 333 | |
| 334 | static void test_casefold(void) { |
| 335 | uint32_t c, l, u[2]; |
| 336 | const char *s, *ls; |
| 337 | |
| 338 | fprintf(stderr, "test_casefold\n"); |
| 339 | |
| 340 | for(c = 1; c < 256; ++c) { |
| 341 | u[0] = c; |
| 342 | u[1] = 0; |
| 343 | s = ucs42utf8(u); |
| 344 | ls = casefold(s); |
| 345 | switch(c) { |
| 346 | default: |
| 347 | if((c >= 'A' && c <= 'Z') |
| 348 | || (c >= 0xC0 && c <= 0xDE && c != 0xD7)) |
| 349 | l = c ^ 0x20; |
| 350 | else |
| 351 | l = c; |
| 352 | break; |
| 353 | #if 0 |
| 354 | /* unidata-based case folding doens't support special cases */ |
| 355 | case 0xB5: /* MICRO SIGN */ |
| 356 | l = 0x39C; /* GREEK SMALL LETTER MU */ |
| 357 | break; |
| 358 | case 0xDF: /* LATIN SMALL LETTER SHARP S */ |
| 359 | insist(!strcmp(ls, "ss")); |
| 360 | l = 0; |
| 361 | break; |
| 362 | #endif |
| 363 | } |
| 364 | if(l) { |
| 365 | u[0] = l; |
| 366 | u[1] = 0; |
| 367 | s = ucs42utf8(u); |
| 368 | if(strcmp(s, ls)) { |
| 369 | fprintf(stderr, "%s:%d: casefolding %#lx got '%s', expected '%s'\n", |
| 370 | __FILE__, __LINE__, (unsigned long)c, |
| 371 | format(ls), format(s)); |
| 372 | ++errors; |
| 373 | } |
| 374 | ++tests; |
| 375 | } |
| 376 | } |
| 377 | check_string(casefold(""), ""); |
| 378 | } |
| 379 | |
| 380 | /** @brief Less-than comparison function for integer heap */ |
| 381 | static inline int int_lt(int a, int b) { return a < b; } |
| 382 | |
| 383 | /** @struct iheap |
| 384 | * @brief A heap with @c int elements */ |
| 385 | HEAP_TYPE(iheap, int, int_lt); |
| 386 | HEAP_DEFINE(iheap, int, int_lt); |
| 387 | |
| 388 | /** @brief Tests for @ref heap.h */ |
| 389 | static void test_heap(void) { |
| 390 | struct iheap h[1]; |
| 391 | int n; |
| 392 | int last = -1; |
| 393 | |
| 394 | fprintf(stderr, "test_heap\n"); |
| 395 | |
| 396 | iheap_init(h); |
| 397 | for(n = 0; n < 1000; ++n) |
| 398 | iheap_insert(h, random() % 100); |
| 399 | for(n = 0; n < 1000; ++n) { |
| 400 | const int latest = iheap_remove(h); |
| 401 | if(last > latest) |
| 402 | fprintf(stderr, "should have %d <= %d\n", last, latest); |
| 403 | insist(last <= latest); |
| 404 | last = latest; |
| 405 | } |
| 406 | putchar('\n'); |
| 407 | } |
| 408 | |
| 409 | int main(void) { |
| 410 | insist('\n' == 0x0A); |
| 411 | insist('\r' == 0x0D); |
| 412 | insist(' ' == 0x20); |
| 413 | insist('0' == 0x30); |
| 414 | insist('9' == 0x39); |
| 415 | insist('A' == 0x41); |
| 416 | insist('Z' == 0x5A); |
| 417 | insist('a' == 0x61); |
| 418 | insist('z' == 0x7A); |
| 419 | /* addr.c */ |
| 420 | /* asprintf.c */ |
| 421 | /* authhash.c */ |
| 422 | /* basen.c */ |
| 423 | /* charset.c */ |
| 424 | /* client.c */ |
| 425 | /* configuration.c */ |
| 426 | /* event.c */ |
| 427 | /* fprintf.c */ |
| 428 | /* heap.c */ |
| 429 | test_heap(); |
| 430 | /* hex.c */ |
| 431 | test_hex(); |
| 432 | /* inputline.c */ |
| 433 | /* kvp.c */ |
| 434 | /* log.c */ |
| 435 | /* mem.c */ |
| 436 | /* mime.c */ |
| 437 | test_mime(); |
| 438 | /* mixer.c */ |
| 439 | /* plugin.c */ |
| 440 | /* printf.c */ |
| 441 | /* queue.c */ |
| 442 | /* sink.c */ |
| 443 | /* snprintf.c */ |
| 444 | /* split.c */ |
| 445 | /* syscalls.c */ |
| 446 | /* table.c */ |
| 447 | /* utf8.c */ |
| 448 | test_utf8(); |
| 449 | /* vector.c */ |
| 450 | /* words.c */ |
| 451 | test_casefold(); |
| 452 | /* XXX words() */ |
| 453 | /* wstat.c */ |
| 454 | fprintf(stderr, "%d errors out of %d tests\n", errors, tests); |
| 455 | return !!errors; |
| 456 | } |
| 457 | |
| 458 | /* |
| 459 | Local Variables: |
| 460 | c-basic-offset:2 |
| 461 | comment-column:40 |
| 462 | End: |
| 463 | */ |
| 464 | |