460b9539 |
1 | /* |
2 | * This file is part of DisOrder. |
3 | * Copyright (C) 2005 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 | |
21 | #include <config.h> |
22 | #include "types.h" |
23 | |
24 | #include <stdio.h> |
25 | #include <string.h> |
26 | #include <stdlib.h> |
27 | #include <errno.h> |
28 | #include <ctype.h> |
29 | |
30 | #include "utf8.h" |
31 | #include "mem.h" |
32 | #include "log.h" |
33 | #include "vector.h" |
34 | #include "charset.h" |
35 | #include "mime.h" |
36 | #include "hex.h" |
37 | #include "words.h" |
38 | |
39 | static int tests, errors; |
40 | |
41 | #define insist(expr) do { \ |
42 | if(!expr) { \ |
43 | ++errors; \ |
44 | fprintf(stderr, "%s:%d: error checking %s\n", \ |
45 | __FILE__, __LINE__, #expr); \ |
46 | } \ |
47 | ++tests; \ |
48 | } while(0) |
49 | |
50 | static const char *format(const char *s) { |
51 | struct dynstr d; |
52 | int c; |
53 | char buf[10]; |
54 | |
55 | dynstr_init(&d); |
56 | while((c = (unsigned char)*s++)) { |
57 | if(c >= ' ' && c <= '~') |
58 | dynstr_append(&d, c); |
59 | else { |
60 | sprintf(buf, "\\x%02X", (unsigned)c); |
61 | dynstr_append_string(&d, buf); |
62 | } |
63 | } |
64 | dynstr_terminate(&d); |
65 | return d.vec; |
66 | } |
67 | |
68 | #define check_string(GOT, WANT) do { \ |
69 | const char *g = GOT; \ |
70 | const char *w = WANT; \ |
71 | \ |
72 | if(w == 0) { \ |
73 | fprintf(stderr, "%s:%d: %s returned 0\n", \ |
74 | __FILE__, __LINE__, #GOT); \ |
75 | ++errors; \ |
76 | } else if(strcmp(w, g)) { \ |
77 | fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \ |
78 | __FILE__, __LINE__, #GOT, format(g), format(w)); \ |
79 | ++errors; \ |
80 | } \ |
81 | ++tests; \ |
82 | } while(0) |
83 | |
84 | static uint32_t *ucs4parse(const char *s) { |
85 | struct dynstr_ucs4 d; |
86 | char *e; |
87 | |
88 | dynstr_ucs4_init(&d); |
89 | while(*s) { |
90 | errno = 0; |
91 | dynstr_ucs4_append(&d, strtoul(s, &e, 0)); |
92 | if(errno) fatal(errno, "strtoul (%s)", s); |
93 | s = e; |
94 | } |
95 | dynstr_ucs4_terminate(&d); |
96 | return d.vec; |
97 | } |
98 | |
99 | static void test_utf8(void) { |
100 | /* Test validutf8, convert to UCS-4, check the answer is right, |
101 | * convert back to UTF-8, check we got to where we started */ |
102 | #define U8(CHARS, WORDS) do { \ |
103 | uint32_t *w = ucs4parse(WORDS); \ |
104 | uint32_t *ucs; \ |
105 | char *u8; \ |
106 | \ |
107 | insist(validutf8(CHARS)); \ |
108 | ucs = utf82ucs4(CHARS); \ |
109 | insist(ucs != 0); \ |
110 | insist(!ucs4cmp(w, ucs)); \ |
111 | u8 = ucs42utf8(ucs); \ |
112 | insist(u8 != 0); \ |
113 | insist(!strcmp(u8, CHARS)); \ |
114 | } while(0) |
115 | |
116 | /* empty string */ |
117 | |
118 | U8("", ""); |
119 | |
120 | /* ASCII characters */ |
121 | |
122 | U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~", |
123 | "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d " |
124 | "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a " |
125 | "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 " |
126 | "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 " |
127 | "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 " |
128 | "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e " |
129 | "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b " |
130 | "0x7c 0x7d 0x7e"); |
131 | 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", |
132 | "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 " |
133 | "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d " |
134 | "0x1e 0x1f 0x7f"); |
135 | |
136 | /* from RFC3629 */ |
137 | |
138 | /* UTF8-2 = %xC2-DF UTF8-tail */ |
139 | insist(!validutf8("\xC0\x80")); |
140 | insist(!validutf8("\xC1\x80")); |
141 | insist(!validutf8("\xC2\x7F")); |
142 | U8("\xC2\x80", "0x80"); |
143 | U8("\xDF\xBF", "0x7FF"); |
144 | insist(!validutf8("\xDF\xC0")); |
145 | |
146 | /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) / |
147 | * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail ) |
148 | */ |
149 | insist(!validutf8("\xE0\x9F\x80")); |
150 | U8("\xE0\xA0\x80", "0x800"); |
151 | U8("\xE0\xBF\xBF", "0xFFF"); |
152 | insist(!validutf8("\xE0\xC0\xBF")); |
153 | |
154 | insist(!validutf8("\xE1\x80\x7F")); |
155 | U8("\xE1\x80\x80", "0x1000"); |
156 | U8("\xEC\xBF\xBF", "0xCFFF"); |
157 | insist(!validutf8("\xEC\xC0\xBF")); |
158 | |
159 | U8("\xED\x80\x80", "0xD000"); |
160 | U8("\xED\x9F\xBF", "0xD7FF"); |
161 | insist(!validutf8("\xED\xA0\xBF")); |
162 | |
163 | insist(!validutf8("\xEE\x7f\x80")); |
164 | U8("\xEE\x80\x80", "0xE000"); |
165 | U8("\xEF\xBF\xBF", "0xFFFF"); |
166 | insist(!validutf8("\xEF\xC0\xBF")); |
167 | |
168 | /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) / |
169 | * %xF4 %x80-8F 2( UTF8-tail ) |
170 | */ |
171 | insist(!validutf8("\xF0\x8F\x80\x80")); |
172 | U8("\xF0\x90\x80\x80", "0x10000"); |
173 | U8("\xF0\xBF\xBF\xBF", "0x3FFFF"); |
174 | insist(!validutf8("\xF0\xC0\x80\x80")); |
175 | |
176 | insist(!validutf8("\xF1\x80\x80\x7F")); |
177 | U8("\xF1\x80\x80\x80", "0x40000"); |
178 | U8("\xF3\xBF\xBF\xBF", "0xFFFFF"); |
179 | insist(!validutf8("\xF3\xC0\x80\x80")); |
180 | |
181 | insist(!validutf8("\xF4\x80\x80\x7F")); |
182 | U8("\xF4\x80\x80\x80", "0x100000"); |
183 | U8("\xF4\x8F\xBF\xBF", "0x10FFFF"); |
184 | insist(!validutf8("\xF4\x90\x80\x80")); |
185 | |
186 | /* miscellaneous non-UTF-8 rubbish */ |
187 | insist(!validutf8("\x80")); |
188 | insist(!validutf8("\xBF")); |
189 | insist(!validutf8("\xC0")); |
190 | insist(!validutf8("\xC0\x7F")); |
191 | insist(!validutf8("\xC0\xC0")); |
192 | insist(!validutf8("\xE0")); |
193 | insist(!validutf8("\xE0\x7F")); |
194 | insist(!validutf8("\xE0\xC0")); |
195 | insist(!validutf8("\xE0\x80")); |
196 | insist(!validutf8("\xE0\x80\x7f")); |
197 | insist(!validutf8("\xE0\x80\xC0")); |
198 | insist(!validutf8("\xF0")); |
199 | insist(!validutf8("\xF0\x7F")); |
200 | insist(!validutf8("\xF0\xC0")); |
201 | insist(!validutf8("\xF0\x80")); |
202 | insist(!validutf8("\xF0\x80\x7f")); |
203 | insist(!validutf8("\xF0\x80\xC0")); |
204 | insist(!validutf8("\xF0\x80\x80\x7f")); |
205 | insist(!validutf8("\xF0\x80\x80\xC0")); |
206 | insist(!validutf8("\xF5\x80\x80\x80")); |
207 | insist(!validutf8("\xF8")); |
208 | } |
209 | |
210 | static void test_mime(void) { |
211 | char *t, *n, *v; |
212 | |
213 | t = n = v = 0; |
214 | insist(!mime_content_type("text/plain", &t, &n, &v)); |
215 | insist(!strcmp(t, "text/plain")); |
216 | insist(n == 0); |
217 | insist(v == 0); |
218 | |
219 | t = n = v = 0; |
220 | insist(!mime_content_type("TEXT ((nested) comment) /plain", &t, &n, &v)); |
221 | insist(!strcmp(t, "text/plain")); |
222 | insist(n == 0); |
223 | insist(v == 0); |
224 | |
225 | t = n = v = 0; |
226 | insist(!mime_content_type(" text/plain ; Charset=utf-8", &t, &n, &v)); |
227 | insist(!strcmp(t, "text/plain")); |
228 | insist(!strcmp(n, "charset")); |
229 | insist(!strcmp(v, "utf-8")); |
230 | |
231 | t = n = v = 0; |
232 | insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t, &n, &v)); |
233 | insist(!strcmp(t, "text/plain")); |
234 | insist(!strcmp(n, "charset")); |
235 | insist(!strcmp(v, "ISO-8859-1")); |
236 | |
237 | /* XXX mime_parse */ |
238 | /* XXX mime_multipart */ |
239 | /* XXX mime_rfc2388_content_disposition */ |
240 | |
241 | check_string(mime_qp(""), ""); |
242 | check_string(mime_qp("foobar"), "foobar"); |
243 | check_string(mime_qp("foo=20bar"), "foo bar"); |
244 | check_string(mime_qp("x \r\ny"), "x\r\ny"); |
245 | check_string(mime_qp("x=\r\ny"), "xy"); |
246 | check_string(mime_qp("x= \r\ny"), "xy"); |
247 | check_string(mime_qp("x =\r\ny"), "x y"); |
248 | check_string(mime_qp("x = \r\ny"), "x y"); |
249 | |
250 | /* from RFC2045 */ |
251 | check_string(mime_qp("Now's the time =\r\n" |
252 | "for all folk to come=\r\n" |
253 | " to the aid of their country."), |
254 | "Now's the time for all folk to come to the aid of their country."); |
255 | |
256 | check_string(mime_base64(""), ""); |
257 | check_string(mime_base64("BBBB"), "\x04\x10\x41"); |
258 | check_string(mime_base64("////"), "\xFF\xFF\xFF"); |
259 | check_string(mime_base64("//BB"), "\xFF\xF0\x41"); |
260 | check_string(mime_base64("BBBB//BB////"), |
261 | "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF"); |
262 | check_string(mime_base64("B B B B / / B B / / / /"), |
263 | "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF"); |
264 | check_string(mime_base64("B\r\nBBB.// B-B//~//"), |
265 | "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF"); |
266 | check_string(mime_base64("BBBB="), |
267 | "\x04\x10\x41"); |
268 | check_string(mime_base64("BBBBx="), /* not actually valid base64 */ |
269 | "\x04\x10\x41"); |
270 | check_string(mime_base64("BBBB BB=="), |
271 | "\x04\x10\x41" "\x04"); |
272 | check_string(mime_base64("BBBB BBB="), |
273 | "\x04\x10\x41" "\x04\x10"); |
274 | } |
275 | |
276 | static void test_hex(void) { |
277 | unsigned n; |
278 | static const unsigned char h[] = { 0x00, 0xFF, 0x80, 0x7F }; |
279 | uint8_t *u; |
280 | size_t ul; |
281 | |
282 | for(n = 0; n <= UCHAR_MAX; ++n) { |
283 | if(!isxdigit(n)) |
284 | insist(unhexdigitq(n) == -1); |
285 | } |
286 | insist(unhexdigitq('0') == 0); |
287 | insist(unhexdigitq('1') == 1); |
288 | insist(unhexdigitq('2') == 2); |
289 | insist(unhexdigitq('3') == 3); |
290 | insist(unhexdigitq('4') == 4); |
291 | insist(unhexdigitq('5') == 5); |
292 | insist(unhexdigitq('6') == 6); |
293 | insist(unhexdigitq('7') == 7); |
294 | insist(unhexdigitq('8') == 8); |
295 | insist(unhexdigitq('9') == 9); |
296 | insist(unhexdigitq('a') == 10); |
297 | insist(unhexdigitq('b') == 11); |
298 | insist(unhexdigitq('c') == 12); |
299 | insist(unhexdigitq('d') == 13); |
300 | insist(unhexdigitq('e') == 14); |
301 | insist(unhexdigitq('f') == 15); |
302 | insist(unhexdigitq('A') == 10); |
303 | insist(unhexdigitq('B') == 11); |
304 | insist(unhexdigitq('C') == 12); |
305 | insist(unhexdigitq('D') == 13); |
306 | insist(unhexdigitq('E') == 14); |
307 | insist(unhexdigitq('F') == 15); |
308 | check_string(hex(h, sizeof h), "00ff807f"); |
309 | check_string(hex(0, 0), ""); |
310 | u = unhex("00ff807f", &ul); |
311 | insist(ul == 4); |
312 | insist(memcmp(u, h, 4) == 0); |
313 | u = unhex("00FF807F", &ul); |
314 | insist(ul == 4); |
315 | insist(memcmp(u, h, 4) == 0); |
316 | u = unhex("", &ul); |
317 | insist(ul == 0); |
318 | fprintf(stderr, "2 ERROR reports expected:\n"); |
319 | insist(unhex("F", 0) == 0); |
320 | insist(unhex("az", 0) == 0); |
321 | } |
322 | |
323 | static void test_casefold(void) { |
324 | uint32_t c, l, u[2]; |
325 | const char *s, *ls; |
326 | |
327 | for(c = 1; c < 256; ++c) { |
328 | u[0] = c; |
329 | u[1] = 0; |
330 | s = ucs42utf8(u); |
331 | ls = casefold(s); |
332 | switch(c) { |
333 | default: |
334 | if((c >= 'A' && c <= 'Z') |
335 | || (c >= 0xC0 && c <= 0xDE && c != 0xD7)) |
336 | l = c ^ 0x20; |
337 | else |
338 | l = c; |
339 | break; |
340 | case 0xB5: /* MICRO SIGN */ |
341 | l = 0x3BC; /* GREEK SMALL LETTER MU */ |
342 | break; |
343 | case 0xDF: /* LATIN SMALL LETTER SHARP S */ |
344 | insist(!strcmp(ls, "ss")); |
345 | l = 0; |
346 | break; |
347 | } |
348 | if(l) { |
349 | u[0] = l; |
350 | u[1] = 0; |
351 | s = ucs42utf8(u); |
352 | if(strcmp(s, ls)) { |
353 | fprintf(stderr, "%s:%d: casefolding %#lx got '%s', expected '%s'\n", |
354 | __FILE__, __LINE__, (unsigned long)c, |
355 | format(ls), format(s)); |
356 | ++errors; |
357 | } |
358 | ++tests; |
359 | } |
360 | } |
361 | check_string(casefold(""), ""); |
362 | } |
363 | |
364 | int main(void) { |
365 | insist('\n' == 0x0A); |
366 | insist('\r' == 0x0D); |
367 | insist(' ' == 0x20); |
368 | insist('0' == 0x30); |
369 | insist('9' == 0x39); |
370 | insist('A' == 0x41); |
371 | insist('Z' == 0x5A); |
372 | insist('a' == 0x61); |
373 | insist('z' == 0x7A); |
374 | /* addr.c */ |
375 | /* asprintf.c */ |
376 | /* authhash.c */ |
377 | /* basen.c */ |
378 | /* charset.c */ |
379 | /* client.c */ |
380 | /* configuration.c */ |
381 | /* event.c */ |
382 | /* fprintf.c */ |
383 | /* hex.c */ |
384 | test_hex(); |
385 | /* inputline.c */ |
386 | /* kvp.c */ |
387 | /* log.c */ |
388 | /* mem.c */ |
389 | /* mime.c */ |
390 | test_mime(); |
391 | /* mixer.c */ |
392 | /* plugin.c */ |
393 | /* printf.c */ |
394 | /* queue.c */ |
395 | /* sink.c */ |
396 | /* snprintf.c */ |
397 | /* split.c */ |
398 | /* syscalls.c */ |
399 | /* table.c */ |
400 | /* utf8.c */ |
401 | test_utf8(); |
402 | /* vector.c */ |
403 | /* words.c */ |
404 | test_casefold(); |
405 | /* XXX words() */ |
406 | /* wstat.c */ |
407 | fprintf(stderr, "%d errors out of %d tests\n", errors, tests); |
408 | return !!errors; |
409 | } |
410 | |
411 | /* |
412 | Local Variables: |
413 | c-basic-offset:2 |
414 | comment-column:40 |
415 | End: |
416 | */ |
417 | |