]>
Commit | Line | Data |
---|---|---|
b75a7d8f A |
1 | /* |
2 | ****************************************************************************** | |
3 | * | |
4 | * Copyright (C) 2002-2003, International Business Machines | |
5 | * Corporation and others. All Rights Reserved. | |
6 | * | |
7 | ****************************************************************************** | |
8 | * file name: custrtst.c | |
9 | * encoding: US-ASCII | |
10 | * tab size: 8 (not used) | |
11 | * indentation:4 | |
12 | * | |
13 | * created on: 2002oct09 | |
14 | * created by: Markus W. Scherer | |
15 | * | |
16 | * Tests of ustring.h Unicode string API functions. | |
17 | */ | |
18 | ||
19 | #include "unicode/utypes.h" | |
20 | #include "unicode/ustring.h" | |
21 | #include "unicode/uloc.h" | |
22 | #include "unicode/ucnv.h" | |
23 | #include "unicode/uiter.h" | |
24 | #include "cintltst.h" | |
25 | #include "cucdtst.h" | |
26 | #include <string.h> | |
27 | #include <stdlib.h> | |
28 | ||
29 | #define LENGTHOF(array) (sizeof(array)/sizeof((array)[0])) | |
30 | ||
31 | /* get the sign of an integer */ | |
32 | #define _SIGN(value) ((value)==0 ? 0 : ((int32_t)(value)>>31)|1) | |
33 | ||
34 | /* test setup --------------------------------------------------------------- */ | |
35 | ||
36 | static void setUpDataTable(void); | |
37 | static void TestStringCopy(void); | |
38 | static void TestStringFunctions(void); | |
39 | static void TestStringSearching(void); | |
40 | static void TestSurrogateSearching(void); | |
41 | static void TestUnescape(void); | |
42 | static void TestCountChar32(void); | |
43 | static void TestUCharIterator(void); | |
44 | static void TestUNormIterator(void); | |
45 | ||
46 | void addUStringTest(TestNode** root); | |
47 | ||
48 | void addUStringTest(TestNode** root) | |
49 | { | |
50 | addTest(root, &TestStringCopy, "tsutil/custrtst/TestStringCopy"); | |
51 | addTest(root, &TestStringFunctions, "tsutil/custrtst/TestStringFunctions"); | |
52 | addTest(root, &TestStringSearching, "tsutil/custrtst/TestStringSearching"); | |
53 | addTest(root, &TestSurrogateSearching, "tsutil/custrtst/TestSurrogateSearching"); | |
54 | addTest(root, &TestUnescape, "tsutil/custrtst/TestUnescape"); | |
55 | addTest(root, &TestCountChar32, "tsutil/custrtst/TestCountChar32"); | |
56 | addTest(root, &TestUCharIterator, "tsutil/custrtst/TestUCharIterator"); | |
57 | addTest(root, &TestUNormIterator, "tsutil/custrtst/TestUNormIterator"); | |
58 | ||
59 | /* cstrcase.c functions, declared in cucdtst.h */ | |
60 | addTest(root, &TestCaseLower, "tsutil/custrtst/TestCaseLower"); | |
61 | addTest(root, &TestCaseUpper, "tsutil/custrtst/TestCaseUpper"); | |
62 | #if !UCONFIG_NO_BREAK_ITERATION | |
63 | addTest(root, &TestCaseTitle, "tsutil/custrtst/TestCaseTitle"); | |
64 | #endif | |
65 | addTest(root, &TestCaseFolding, "tsutil/custrtst/TestCaseFolding"); | |
66 | addTest(root, &TestCaseCompare, "tsutil/custrtst/TestCaseCompare"); | |
67 | } | |
68 | ||
69 | /* test data for TestStringFunctions ---------------------------------------- */ | |
70 | ||
71 | UChar*** dataTable = NULL; | |
72 | ||
73 | static const char* raw[3][4] = { | |
74 | ||
75 | /* First String */ | |
76 | { "English_", "French_", "Croatian_", "English_"}, | |
77 | /* Second String */ | |
78 | { "United States", "France", "Croatia", "Unites States"}, | |
79 | ||
80 | /* Concatenated string */ | |
81 | { "English_United States", "French_France", "Croatian_Croatia", "English_United States"} | |
82 | }; | |
83 | ||
84 | static void setUpDataTable() | |
85 | { | |
86 | int32_t i,j; | |
87 | if(dataTable == NULL) { | |
88 | dataTable = (UChar***)calloc(sizeof(UChar**),3); | |
89 | ||
90 | for (i = 0; i < 3; i++) { | |
91 | dataTable[i] = (UChar**)calloc(sizeof(UChar*),4); | |
92 | for (j = 0; j < 4; j++){ | |
93 | dataTable[i][j] = (UChar*) malloc(sizeof(UChar)*(strlen(raw[i][j])+1)); | |
94 | u_uastrcpy(dataTable[i][j],raw[i][j]); | |
95 | } | |
96 | } | |
97 | } | |
98 | } | |
99 | ||
100 | static void cleanUpDataTable() | |
101 | { | |
102 | int32_t i,j; | |
103 | if(dataTable != NULL) { | |
104 | for (i=0; i<3; i++) { | |
105 | for(j = 0; j<4; j++) { | |
106 | free(dataTable[i][j]); | |
107 | } | |
108 | free(dataTable[i]); | |
109 | } | |
110 | free(dataTable); | |
111 | } | |
112 | dataTable = NULL; | |
113 | } | |
114 | ||
115 | /*Tests for u_strcat(),u_strcmp(), u_strlen(), u_strcpy(),u_strncat(),u_strncmp(),u_strncpy, u_uastrcpy(),u_austrcpy(), u_uastrncpy(); */ | |
116 | static void TestStringFunctions() | |
117 | { | |
118 | int32_t i,j,k; | |
119 | UChar temp[512]; | |
120 | UChar nullTemp[512]; | |
121 | char test[512]; | |
122 | char tempOut[512]; | |
123 | ||
124 | setUpDataTable(); | |
125 | ||
126 | log_verbose("Testing u_strlen()\n"); | |
127 | if( u_strlen(dataTable[0][0])!= u_strlen(dataTable[0][3]) || u_strlen(dataTable[0][0]) == u_strlen(dataTable[0][2])) | |
128 | log_err("There is an error in u_strlen()"); | |
129 | ||
130 | log_verbose("Testing u_memcpy() and u_memcmp()\n"); | |
131 | ||
132 | for(i=0;i<3;++i) | |
133 | { | |
134 | for(j=0;j<4;++j) | |
135 | { | |
136 | log_verbose("Testing %s\n", u_austrcpy(tempOut, dataTable[i][j])); | |
137 | temp[0] = 0; | |
138 | temp[7] = 0xA4; /* Mark the end */ | |
139 | u_memcpy(temp,dataTable[i][j], 7); | |
140 | ||
141 | if(temp[7] != 0xA4) | |
142 | log_err("an error occured in u_memcpy()\n"); | |
143 | if(u_memcmp(temp, dataTable[i][j], 7)!=0) | |
144 | log_err("an error occured in u_memcpy() or u_memcmp()\n"); | |
145 | } | |
146 | } | |
147 | if(u_memcmp(dataTable[0][0], dataTable[1][1], 7)==0) | |
148 | log_err("an error occured in u_memcmp()\n"); | |
149 | ||
150 | log_verbose("Testing u_memset()\n"); | |
151 | nullTemp[0] = 0; | |
152 | nullTemp[7] = 0; | |
153 | u_memset(nullTemp, 0xa4, 7); | |
154 | for (i = 0; i < 7; i++) { | |
155 | if(nullTemp[i] != 0xa4) { | |
156 | log_err("an error occured in u_memset()\n"); | |
157 | } | |
158 | } | |
159 | if(nullTemp[7] != 0) { | |
160 | log_err("u_memset() went too far\n"); | |
161 | } | |
162 | ||
163 | u_memset(nullTemp, 0, 7); | |
164 | nullTemp[7] = 0xa4; | |
165 | temp[7] = 0; | |
166 | u_memcpy(temp,nullTemp, 7); | |
167 | if(u_memcmp(temp, nullTemp, 7)!=0 || temp[7]!=0) | |
168 | log_err("an error occured in u_memcpy() or u_memcmp()\n"); | |
169 | ||
170 | ||
171 | log_verbose("Testing u_memmove()\n"); | |
172 | for (i = 0; i < 7; i++) { | |
173 | temp[i] = (UChar)i; | |
174 | } | |
175 | u_memmove(temp + 1, temp, 7); | |
176 | if(temp[0] != 0) { | |
177 | log_err("an error occured in u_memmove()\n"); | |
178 | } | |
179 | for (i = 1; i <= 7; i++) { | |
180 | if(temp[i] != (i - 1)) { | |
181 | log_err("an error occured in u_memmove()\n"); | |
182 | } | |
183 | } | |
184 | ||
185 | log_verbose("Testing u_strcpy() and u_strcmp()\n"); | |
186 | ||
187 | for(i=0;i<3;++i) | |
188 | { | |
189 | for(j=0;j<4;++j) | |
190 | { | |
191 | log_verbose("Testing %s\n", u_austrcpy(tempOut, dataTable[i][j])); | |
192 | temp[0] = 0; | |
193 | u_strcpy(temp,dataTable[i][j]); | |
194 | ||
195 | if(u_strcmp(temp,dataTable[i][j])!=0) | |
196 | log_err("something threw an error in u_strcpy() or u_strcmp()\n"); | |
197 | } | |
198 | } | |
199 | if(u_strcmp(dataTable[0][0], dataTable[1][1])==0) | |
200 | log_err("an error occured in u_memcmp()\n"); | |
201 | ||
202 | log_verbose("testing u_strcat()\n"); | |
203 | i=0; | |
204 | for(j=0; j<2;++j) | |
205 | { | |
206 | u_uastrcpy(temp, ""); | |
207 | u_strcpy(temp,dataTable[i][j]); | |
208 | u_strcat(temp,dataTable[i+1][j]); | |
209 | if(u_strcmp(temp,dataTable[i+2][j])!=0) | |
210 | log_err("something threw an error in u_strcat()\n"); | |
211 | ||
212 | } | |
213 | log_verbose("Testing u_strncmp()\n"); | |
214 | for(i=0,j=0;j<4; ++j) | |
215 | { | |
216 | k=u_strlen(dataTable[i][j]); | |
217 | if(u_strncmp(dataTable[i][j],dataTable[i+2][j],k)!=0) | |
218 | log_err("Something threw an error in u_strncmp\n"); | |
219 | } | |
220 | if(u_strncmp(dataTable[0][0], dataTable[1][1], 7)==0) | |
221 | log_err("an error occured in u_memcmp()\n"); | |
222 | ||
223 | ||
224 | log_verbose("Testing u_strncat\n"); | |
225 | for(i=0,j=0;j<4; ++j) | |
226 | { | |
227 | k=u_strlen(dataTable[i][j]); | |
228 | ||
229 | u_uastrcpy(temp,""); | |
230 | ||
231 | if(u_strcmp(u_strncat(temp,dataTable[i+2][j],k),dataTable[i][j])!=0) | |
232 | log_err("something threw an error in u_strncat or u_uastrcpy()\n"); | |
233 | ||
234 | } | |
235 | ||
236 | log_verbose("Testing u_strncpy() and u_uastrcpy()\n"); | |
237 | for(i=2,j=0;j<4; ++j) | |
238 | { | |
239 | k=u_strlen(dataTable[i][j]); | |
240 | u_strncpy(temp, dataTable[i][j],k); | |
241 | temp[k] = 0xa4; | |
242 | ||
243 | if(u_strncmp(temp, dataTable[i][j],k)!=0) | |
244 | log_err("something threw an error in u_strncpy()\n"); | |
245 | ||
246 | if(temp[k] != 0xa4) | |
247 | log_err("something threw an error in u_strncpy()\n"); | |
248 | ||
249 | u_memset(temp, 0x3F, (sizeof(temp) / sizeof(UChar)) - 1); | |
250 | u_uastrncpy(temp, raw[i][j], k-1); | |
251 | if(u_strncmp(temp, dataTable[i][j],k-1)!=0) | |
252 | log_err("something threw an error in u_uastrncpy(k-1)\n"); | |
253 | ||
254 | if(temp[k-1] != 0x3F) | |
255 | log_err("something threw an error in u_uastrncpy(k-1)\n"); | |
256 | ||
257 | u_memset(temp, 0x3F, (sizeof(temp) / sizeof(UChar)) - 1); | |
258 | u_uastrncpy(temp, raw[i][j], k+1); | |
259 | if(u_strcmp(temp, dataTable[i][j])!=0) | |
260 | log_err("something threw an error in u_uastrncpy(k+1)\n"); | |
261 | ||
262 | if(temp[k] != 0) | |
263 | log_err("something threw an error in u_uastrncpy(k+1)\n"); | |
264 | ||
265 | u_memset(temp, 0x3F, (sizeof(temp) / sizeof(UChar)) - 1); | |
266 | u_uastrncpy(temp, raw[i][j], k); | |
267 | if(u_strncmp(temp, dataTable[i][j], k)!=0) | |
268 | log_err("something threw an error in u_uastrncpy(k)\n"); | |
269 | ||
270 | if(temp[k] != 0x3F) | |
271 | log_err("something threw an error in u_uastrncpy(k)\n"); | |
272 | } | |
273 | ||
274 | log_verbose("Testing u_strchr() and u_memchr()\n"); | |
275 | ||
276 | for(i=2,j=0;j<4;j++) | |
277 | { | |
278 | UChar saveVal = dataTable[i][j][0]; | |
279 | UChar *findPtr = u_strchr(dataTable[i][j], 0x005F); | |
280 | int32_t dataSize = (int32_t)(u_strlen(dataTable[i][j]) + 1); | |
281 | ||
282 | log_verbose("%s ", u_austrcpy(tempOut, findPtr)); | |
283 | ||
284 | if (findPtr == NULL || *findPtr != 0x005F) { | |
285 | log_err("u_strchr can't find '_' in the string\n"); | |
286 | } | |
287 | ||
288 | findPtr = u_strchr32(dataTable[i][j], 0x005F); | |
289 | if (findPtr == NULL || *findPtr != 0x005F) { | |
290 | log_err("u_strchr32 can't find '_' in the string\n"); | |
291 | } | |
292 | ||
293 | findPtr = u_strchr(dataTable[i][j], 0); | |
294 | if (findPtr != (&(dataTable[i][j][dataSize - 1]))) { | |
295 | log_err("u_strchr can't find NULL in the string\n"); | |
296 | } | |
297 | ||
298 | findPtr = u_strchr32(dataTable[i][j], 0); | |
299 | if (findPtr != (&(dataTable[i][j][dataSize - 1]))) { | |
300 | log_err("u_strchr32 can't find NULL in the string\n"); | |
301 | } | |
302 | ||
303 | findPtr = u_memchr(dataTable[i][j], 0, dataSize); | |
304 | if (findPtr != (&(dataTable[i][j][dataSize - 1]))) { | |
305 | log_err("u_memchr can't find NULL in the string\n"); | |
306 | } | |
307 | ||
308 | findPtr = u_memchr32(dataTable[i][j], 0, dataSize); | |
309 | if (findPtr != (&(dataTable[i][j][dataSize - 1]))) { | |
310 | log_err("u_memchr32 can't find NULL in the string\n"); | |
311 | } | |
312 | ||
313 | dataTable[i][j][0] = 0; | |
314 | /* Make sure we skip over the NULL termination */ | |
315 | findPtr = u_memchr(dataTable[i][j], 0x005F, dataSize); | |
316 | if (findPtr == NULL || *findPtr != 0x005F) { | |
317 | log_err("u_memchr can't find '_' in the string\n"); | |
318 | } | |
319 | ||
320 | findPtr = u_memchr32(dataTable[i][j], 0x005F, dataSize); | |
321 | if (findPtr == NULL || *findPtr != 0x005F) { | |
322 | log_err("u_memchr32 can't find '_' in the string\n"); | |
323 | } | |
324 | findPtr = u_memchr32(dataTable[i][j], 0xFFFD, dataSize); | |
325 | if (findPtr != NULL) { | |
326 | log_err("Should have found NULL when the character is not there.\n"); | |
327 | } | |
328 | dataTable[i][j][0] = saveVal; /* Put it back for the other tests */ | |
329 | } | |
330 | ||
331 | /* | |
332 | * test that u_strchr32() | |
333 | * does not find surrogate code points when they are part of matched pairs | |
334 | * (= part of supplementary code points) | |
335 | * Jitterbug 1542 | |
336 | */ | |
337 | { | |
338 | static const UChar s[]={ | |
339 | /* 0 1 2 3 4 5 6 7 8 9 */ | |
340 | 0x0061, 0xd841, 0xdc02, 0xd841, 0x0062, 0xdc02, 0xd841, 0xdc02, 0x0063, 0 | |
341 | }; | |
342 | ||
343 | if(u_strchr32(s, 0xd841)!=(s+3) || u_strchr32(s, 0xdc02)!=(s+5)) { | |
344 | log_err("error: u_strchr32(surrogate) finds a partial supplementary code point\n"); | |
345 | } | |
346 | if(u_memchr32(s, 0xd841, 9)!=(s+3) || u_memchr32(s, 0xdc02, 9)!=(s+5)) { | |
347 | log_err("error: u_memchr32(surrogate) finds a partial supplementary code point\n"); | |
348 | } | |
349 | } | |
350 | ||
351 | log_verbose("Testing u_austrcpy()"); | |
352 | u_austrcpy(test,dataTable[0][0]); | |
353 | if(strcmp(test,raw[0][0])!=0) | |
354 | log_err("There is an error in u_austrcpy()"); | |
355 | ||
356 | ||
357 | log_verbose("Testing u_strtok_r()"); | |
358 | { | |
359 | const char tokString[] = " , 1 2 3 AHHHHH! 5.5 6 7 , 8\n"; | |
360 | const char *tokens[] = {",", "1", "2", "3", "AHHHHH!", "5.5", "6", "7", "8\n"}; | |
361 | UChar delimBuf[sizeof(test)]; | |
362 | UChar currTokenBuf[sizeof(tokString)]; | |
363 | UChar *state; | |
364 | uint32_t currToken = 0; | |
365 | UChar *ptr; | |
366 | ||
367 | u_uastrcpy(temp, tokString); | |
368 | u_uastrcpy(delimBuf, " "); | |
369 | ||
370 | ptr = u_strtok_r(temp, delimBuf, &state); | |
371 | u_uastrcpy(delimBuf, " ,"); | |
372 | while (ptr != NULL) { | |
373 | u_uastrcpy(currTokenBuf, tokens[currToken]); | |
374 | if (u_strcmp(ptr, currTokenBuf) != 0) { | |
375 | log_err("u_strtok_r mismatch at %d. Got: %s, Expected: %s\n", currToken, ptr, tokens[currToken]); | |
376 | } | |
377 | ptr = u_strtok_r(NULL, delimBuf, &state); | |
378 | currToken++; | |
379 | } | |
380 | ||
381 | if (currToken != sizeof(tokens)/sizeof(tokens[0])) { | |
382 | log_err("Didn't get correct number of tokens\n"); | |
383 | } | |
384 | state = delimBuf; /* Give it an "invalid" saveState */ | |
385 | u_uastrcpy(currTokenBuf, ""); | |
386 | if (u_strtok_r(currTokenBuf, delimBuf, &state) != NULL) { | |
387 | log_err("Didn't get NULL for empty string\n"); | |
388 | } | |
389 | if (state != NULL) { | |
390 | log_err("State should be NULL for empty string\n"); | |
391 | } | |
392 | state = delimBuf; /* Give it an "invalid" saveState */ | |
393 | u_uastrcpy(currTokenBuf, ", ,"); | |
394 | if (u_strtok_r(currTokenBuf, delimBuf, &state) != NULL) { | |
395 | log_err("Didn't get NULL for a string of delimiters\n"); | |
396 | } | |
397 | if (state != NULL) { | |
398 | log_err("State should be NULL for a string of delimiters\n"); | |
399 | } | |
400 | ||
401 | state = delimBuf; /* Give it an "invalid" saveState */ | |
402 | u_uastrcpy(currTokenBuf, "q, ,"); | |
403 | if (u_strtok_r(currTokenBuf, delimBuf, &state) == NULL) { | |
404 | log_err("Got NULL for a string that does not begin with delimiters\n"); | |
405 | } | |
406 | if (u_strtok_r(NULL, delimBuf, &state) != NULL) { | |
407 | log_err("Didn't get NULL for a string that ends in delimiters\n"); | |
408 | } | |
409 | if (state != NULL) { | |
410 | log_err("State should be NULL for empty string\n"); | |
411 | } | |
412 | ||
413 | state = delimBuf; /* Give it an "invalid" saveState */ | |
414 | u_uastrcpy(currTokenBuf, tokString); | |
415 | u_uastrcpy(temp, tokString); | |
416 | u_uastrcpy(delimBuf, "q"); /* Give it a delimiter that it can't find. */ | |
417 | ptr = u_strtok_r(currTokenBuf, delimBuf, &state); | |
418 | if (ptr == NULL || u_strcmp(ptr, temp) != 0) { | |
419 | log_err("Should have recieved the same string when there are no delimiters\n"); | |
420 | } | |
421 | if (u_strtok_r(NULL, delimBuf, &state) != NULL) { | |
422 | log_err("Should not have found another token in a one token string\n"); | |
423 | } | |
424 | } | |
425 | ||
426 | /* test u_strcmpCodePointOrder() */ | |
427 | { | |
428 | /* these strings are in ascending order */ | |
429 | static const UChar strings[][4]={ | |
430 | { 0x61, 0 }, /* U+0061 */ | |
431 | { 0x20ac, 0xd801, 0 }, /* U+20ac U+d801 */ | |
432 | { 0x20ac, 0xd800, 0xdc00, 0 }, /* U+20ac U+10000 */ | |
433 | { 0xd800, 0 }, /* U+d800 */ | |
434 | { 0xd800, 0xff61, 0 }, /* U+d800 U+ff61 */ | |
435 | { 0xdfff, 0 }, /* U+dfff */ | |
436 | { 0xff61, 0xdfff, 0 }, /* U+ff61 U+dfff */ | |
437 | { 0xff61, 0xd800, 0xdc02, 0 }, /* U+ff61 U+10002 */ | |
438 | { 0xd800, 0xdc02, 0 }, /* U+10002 */ | |
439 | { 0xd84d, 0xdc56, 0 } /* U+23456 */ | |
440 | }; | |
441 | ||
442 | UCharIterator iter1, iter2; | |
443 | int32_t len1, len2, r1, r2; | |
444 | ||
445 | for(i=0; i<(sizeof(strings)/sizeof(strings[0])-1); ++i) { | |
446 | if(u_strcmpCodePointOrder(strings[i], strings[i+1])>=0) { | |
447 | log_err("error: u_strcmpCodePointOrder() fails for string %d and the following one\n", i); | |
448 | } | |
449 | if(u_strncmpCodePointOrder(strings[i], strings[i+1], 10)>=0) { | |
450 | log_err("error: u_strncmpCodePointOrder() fails for string %d and the following one\n", i); | |
451 | } | |
452 | ||
453 | /* There are at least 2 UChars in each string - verify that strncmp()==memcmp(). */ | |
454 | if(u_strncmpCodePointOrder(strings[i], strings[i+1], 2)!=u_memcmpCodePointOrder(strings[i], strings[i+1], 2)) { | |
455 | log_err("error: u_strncmpCodePointOrder(2)!=u_memcmpCodePointOrder(2) for string %d and the following one\n", i); | |
456 | } | |
457 | ||
458 | /* test u_strCompare(TRUE) */ | |
459 | len1=u_strlen(strings[i]); | |
460 | len2=u_strlen(strings[i+1]); | |
461 | if( u_strCompare(strings[i], -1, strings[i+1], -1, TRUE)>=0 || | |
462 | u_strCompare(strings[i], -1, strings[i+1], len2, TRUE)>=0 || | |
463 | u_strCompare(strings[i], len1, strings[i+1], -1, TRUE)>=0 || | |
464 | u_strCompare(strings[i], len1, strings[i+1], len2, TRUE)>=0 | |
465 | ) { | |
466 | log_err("error: u_strCompare(code point order) fails for string %d and the following one\n", i); | |
467 | } | |
468 | ||
469 | /* test u_strCompare(FALSE) */ | |
470 | r1=u_strCompare(strings[i], -1, strings[i+1], -1, FALSE); | |
471 | r2=u_strcmp(strings[i], strings[i+1]); | |
472 | if(_SIGN(r1)!=_SIGN(r2)) { | |
473 | log_err("error: u_strCompare(code unit order)!=u_strcmp() for string %d and the following one\n", i); | |
474 | } | |
475 | ||
476 | /* test u_strCompareIter() */ | |
477 | uiter_setString(&iter1, strings[i], len1); | |
478 | uiter_setString(&iter2, strings[i+1], len2); | |
479 | if(u_strCompareIter(&iter1, &iter2, TRUE)>=0) { | |
480 | log_err("error: u_strCompareIter(code point order) fails for string %d and the following one\n", i); | |
481 | } | |
482 | r1=u_strCompareIter(&iter1, &iter2, FALSE); | |
483 | if(_SIGN(r1)!=_SIGN(u_strcmp(strings[i], strings[i+1]))) { | |
484 | log_err("error: u_strCompareIter(code unit order)!=u_strcmp() for string %d and the following one\n", i); | |
485 | } | |
486 | } | |
487 | } | |
488 | ||
489 | cleanUpDataTable(); | |
490 | } | |
491 | ||
492 | static void TestStringSearching() | |
493 | { | |
494 | const UChar testString[] = {0x0061, 0x0062, 0x0063, 0x0064, 0x0064, 0x0061, 0}; | |
495 | const UChar testSurrogateString[] = {0xdbff, 0x0061, 0x0062, 0xdbff, 0xdfff, 0x0063, 0x0064, 0x0064, 0xdbff, 0xdfff, 0xdb00, 0xdf00, 0x0061, 0}; | |
496 | const UChar surrMatchSet1[] = {0xdbff, 0xdfff, 0}; | |
497 | const UChar surrMatchSet2[] = {0x0061, 0x0062, 0xdbff, 0xdfff, 0}; | |
498 | const UChar surrMatchSet3[] = {0xdb00, 0xdf00, 0xdbff, 0xdfff, 0}; | |
499 | const UChar surrMatchSet4[] = {0x0000}; | |
500 | const UChar surrMatchSetBad[] = {0xdbff, 0x0061, 0}; | |
501 | const UChar surrMatchSetBad2[] = {0x0061, 0xdbff, 0}; | |
502 | const UChar surrMatchSetBad3[] = {0xdbff, 0x0061, 0x0062, 0xdbff, 0xdfff, 0}; /* has partial surrogate */ | |
503 | const UChar | |
504 | empty[] = { 0 }, | |
505 | a[] = { 0x61, 0 }, | |
506 | ab[] = { 0x61, 0x62, 0 }, | |
507 | ba[] = { 0x62, 0x61, 0 }, | |
508 | abcd[] = { 0x61, 0x62, 0x63, 0x64, 0 }, | |
509 | cd[] = { 0x63, 0x64, 0 }, | |
510 | dc[] = { 0x64, 0x63, 0 }, | |
511 | cdh[] = { 0x63, 0x64, 0x68, 0 }, | |
512 | f[] = { 0x66, 0 }, | |
513 | fg[] = { 0x66, 0x67, 0 }, | |
514 | gf[] = { 0x67, 0x66, 0 }; | |
515 | ||
516 | log_verbose("Testing u_strpbrk()"); | |
517 | ||
518 | if (u_strpbrk(testString, a) != &testString[0]) { | |
519 | log_err("u_strpbrk couldn't find first letter a.\n"); | |
520 | } | |
521 | if (u_strpbrk(testString, dc) != &testString[2]) { | |
522 | log_err("u_strpbrk couldn't find d or c.\n"); | |
523 | } | |
524 | if (u_strpbrk(testString, cd) != &testString[2]) { | |
525 | log_err("u_strpbrk couldn't find c or d.\n"); | |
526 | } | |
527 | if (u_strpbrk(testString, cdh) != &testString[2]) { | |
528 | log_err("u_strpbrk couldn't find c, d or h.\n"); | |
529 | } | |
530 | if (u_strpbrk(testString, f) != NULL) { | |
531 | log_err("u_strpbrk didn't return NULL for \"f\".\n"); | |
532 | } | |
533 | if (u_strpbrk(testString, fg) != NULL) { | |
534 | log_err("u_strpbrk didn't return NULL for \"fg\".\n"); | |
535 | } | |
536 | if (u_strpbrk(testString, gf) != NULL) { | |
537 | log_err("u_strpbrk didn't return NULL for \"gf\".\n"); | |
538 | } | |
539 | if (u_strpbrk(testString, empty) != NULL) { | |
540 | log_err("u_strpbrk didn't return NULL for \"\".\n"); | |
541 | } | |
542 | ||
543 | log_verbose("Testing u_strpbrk() with surrogates"); | |
544 | ||
545 | if (u_strpbrk(testSurrogateString, a) != &testSurrogateString[1]) { | |
546 | log_err("u_strpbrk couldn't find first letter a.\n"); | |
547 | } | |
548 | if (u_strpbrk(testSurrogateString, dc) != &testSurrogateString[5]) { | |
549 | log_err("u_strpbrk couldn't find d or c.\n"); | |
550 | } | |
551 | if (u_strpbrk(testSurrogateString, cd) != &testSurrogateString[5]) { | |
552 | log_err("u_strpbrk couldn't find c or d.\n"); | |
553 | } | |
554 | if (u_strpbrk(testSurrogateString, cdh) != &testSurrogateString[5]) { | |
555 | log_err("u_strpbrk couldn't find c, d or h.\n"); | |
556 | } | |
557 | if (u_strpbrk(testSurrogateString, f) != NULL) { | |
558 | log_err("u_strpbrk didn't return NULL for \"f\".\n"); | |
559 | } | |
560 | if (u_strpbrk(testSurrogateString, fg) != NULL) { | |
561 | log_err("u_strpbrk didn't return NULL for \"fg\".\n"); | |
562 | } | |
563 | if (u_strpbrk(testSurrogateString, gf) != NULL) { | |
564 | log_err("u_strpbrk didn't return NULL for \"gf\".\n"); | |
565 | } | |
566 | if (u_strpbrk(testSurrogateString, surrMatchSet1) != &testSurrogateString[3]) { | |
567 | log_err("u_strpbrk couldn't find \"0xdbff, 0xdfff\".\n"); | |
568 | } | |
569 | if (u_strpbrk(testSurrogateString, surrMatchSet2) != &testSurrogateString[1]) { | |
570 | log_err("u_strpbrk couldn't find \"0xdbff, a, b, 0xdbff, 0xdfff\".\n"); | |
571 | } | |
572 | if (u_strpbrk(testSurrogateString, surrMatchSet3) != &testSurrogateString[3]) { | |
573 | log_err("u_strpbrk couldn't find \"0xdb00, 0xdf00, 0xdbff, 0xdfff\".\n"); | |
574 | } | |
575 | if (u_strpbrk(testSurrogateString, surrMatchSet4) != NULL) { | |
576 | log_err("u_strpbrk should have returned NULL for empty string.\n"); | |
577 | } | |
578 | if (u_strpbrk(testSurrogateString, surrMatchSetBad) != &testSurrogateString[0]) { | |
579 | log_err("u_strpbrk should have found bad surrogate.\n"); | |
580 | } | |
581 | ||
582 | log_verbose("Testing u_strcspn()"); | |
583 | ||
584 | if (u_strcspn(testString, a) != 0) { | |
585 | log_err("u_strcspn couldn't find first letter a.\n"); | |
586 | } | |
587 | if (u_strcspn(testString, dc) != 2) { | |
588 | log_err("u_strcspn couldn't find d or c.\n"); | |
589 | } | |
590 | if (u_strcspn(testString, cd) != 2) { | |
591 | log_err("u_strcspn couldn't find c or d.\n"); | |
592 | } | |
593 | if (u_strcspn(testString, cdh) != 2) { | |
594 | log_err("u_strcspn couldn't find c, d or h.\n"); | |
595 | } | |
596 | if (u_strcspn(testString, f) != u_strlen(testString)) { | |
597 | log_err("u_strcspn didn't return NULL for \"f\".\n"); | |
598 | } | |
599 | if (u_strcspn(testString, fg) != u_strlen(testString)) { | |
600 | log_err("u_strcspn didn't return NULL for \"fg\".\n"); | |
601 | } | |
602 | if (u_strcspn(testString, gf) != u_strlen(testString)) { | |
603 | log_err("u_strcspn didn't return NULL for \"gf\".\n"); | |
604 | } | |
605 | ||
606 | log_verbose("Testing u_strcspn() with surrogates"); | |
607 | ||
608 | if (u_strcspn(testSurrogateString, a) != 1) { | |
609 | log_err("u_strcspn couldn't find first letter a.\n"); | |
610 | } | |
611 | if (u_strcspn(testSurrogateString, dc) != 5) { | |
612 | log_err("u_strcspn couldn't find d or c.\n"); | |
613 | } | |
614 | if (u_strcspn(testSurrogateString, cd) != 5) { | |
615 | log_err("u_strcspn couldn't find c or d.\n"); | |
616 | } | |
617 | if (u_strcspn(testSurrogateString, cdh) != 5) { | |
618 | log_err("u_strcspn couldn't find c, d or h.\n"); | |
619 | } | |
620 | if (u_strcspn(testSurrogateString, f) != u_strlen(testSurrogateString)) { | |
621 | log_err("u_strcspn didn't return NULL for \"f\".\n"); | |
622 | } | |
623 | if (u_strcspn(testSurrogateString, fg) != u_strlen(testSurrogateString)) { | |
624 | log_err("u_strcspn didn't return NULL for \"fg\".\n"); | |
625 | } | |
626 | if (u_strcspn(testSurrogateString, gf) != u_strlen(testSurrogateString)) { | |
627 | log_err("u_strcspn didn't return NULL for \"gf\".\n"); | |
628 | } | |
629 | if (u_strcspn(testSurrogateString, surrMatchSet1) != 3) { | |
630 | log_err("u_strcspn couldn't find \"0xdbff, 0xdfff\".\n"); | |
631 | } | |
632 | if (u_strcspn(testSurrogateString, surrMatchSet2) != 1) { | |
633 | log_err("u_strcspn couldn't find \"a, b, 0xdbff, 0xdfff\".\n"); | |
634 | } | |
635 | if (u_strcspn(testSurrogateString, surrMatchSet3) != 3) { | |
636 | log_err("u_strcspn couldn't find \"0xdb00, 0xdf00, 0xdbff, 0xdfff\".\n"); | |
637 | } | |
638 | if (u_strcspn(testSurrogateString, surrMatchSet4) != u_strlen(testSurrogateString)) { | |
639 | log_err("u_strcspn should have returned strlen for empty string.\n"); | |
640 | } | |
641 | ||
642 | ||
643 | log_verbose("Testing u_strspn()"); | |
644 | ||
645 | if (u_strspn(testString, a) != 1) { | |
646 | log_err("u_strspn couldn't skip first letter a.\n"); | |
647 | } | |
648 | if (u_strspn(testString, ab) != 2) { | |
649 | log_err("u_strspn couldn't skip a or b.\n"); | |
650 | } | |
651 | if (u_strspn(testString, ba) != 2) { | |
652 | log_err("u_strspn couldn't skip a or b.\n"); | |
653 | } | |
654 | if (u_strspn(testString, f) != 0) { | |
655 | log_err("u_strspn didn't return 0 for \"f\".\n"); | |
656 | } | |
657 | if (u_strspn(testString, dc) != 0) { | |
658 | log_err("u_strspn couldn't find first letter a (skip d or c).\n"); | |
659 | } | |
660 | if (u_strspn(testString, abcd) != u_strlen(testString)) { | |
661 | log_err("u_strspn couldn't skip over the whole string.\n"); | |
662 | } | |
663 | if (u_strspn(testString, empty) != 0) { | |
664 | log_err("u_strspn should have returned 0 for empty string.\n"); | |
665 | } | |
666 | ||
667 | log_verbose("Testing u_strspn() with surrogates"); | |
668 | if (u_strspn(testSurrogateString, surrMatchSetBad) != 2) { | |
669 | log_err("u_strspn couldn't skip 0xdbff or a.\n"); | |
670 | } | |
671 | if (u_strspn(testSurrogateString, surrMatchSetBad2) != 2) { | |
672 | log_err("u_strspn couldn't skip 0xdbff or a.\n"); | |
673 | } | |
674 | if (u_strspn(testSurrogateString, f) != 0) { | |
675 | log_err("u_strspn couldn't skip d or c (skip first letter).\n"); | |
676 | } | |
677 | if (u_strspn(testSurrogateString, dc) != 0) { | |
678 | log_err("u_strspn couldn't skip d or c (skip first letter).\n"); | |
679 | } | |
680 | if (u_strspn(testSurrogateString, cd) != 0) { | |
681 | log_err("u_strspn couldn't skip d or c (skip first letter).\n"); | |
682 | } | |
683 | if (u_strspn(testSurrogateString, testSurrogateString) != u_strlen(testSurrogateString)) { | |
684 | log_err("u_strspn couldn't skip whole string.\n"); | |
685 | } | |
686 | if (u_strspn(testSurrogateString, surrMatchSet1) != 0) { | |
687 | log_err("u_strspn couldn't skip \"0xdbff, 0xdfff\" (get first letter).\n"); | |
688 | } | |
689 | if (u_strspn(testSurrogateString, surrMatchSetBad3) != 5) { | |
690 | log_err("u_strspn couldn't skip \"0xdbff, a, b, 0xdbff, 0xdfff\".\n"); | |
691 | } | |
692 | if (u_strspn(testSurrogateString, surrMatchSet4) != 0) { | |
693 | log_err("u_strspn should have returned 0 for empty string.\n"); | |
694 | } | |
695 | } | |
696 | ||
697 | /* | |
698 | * All binary Unicode string searches should behave the same for equivalent input. | |
699 | * See Jitterbug 2145. | |
700 | * There are some new functions, too - just test them all. | |
701 | */ | |
702 | static void | |
703 | TestSurrogateSearching() { | |
704 | static const UChar s[]={ | |
705 | /* 0 1 2 3 4 5 6 7 8 9 10 11 */ | |
706 | 0x61, 0xd801, 0xdc02, 0x61, 0xdc02, 0x61, 0xd801, 0x61, 0xd801, 0xdc02, 0x61, 0 | |
707 | }, sub_a[]={ | |
708 | 0x61, 0 | |
709 | }, sub_b[]={ | |
710 | 0x62, 0 | |
711 | }, sub_lead[]={ | |
712 | 0xd801, 0 | |
713 | }, sub_trail[]={ | |
714 | 0xdc02, 0 | |
715 | }, sub_supp[]={ | |
716 | 0xd801, 0xdc02, 0 | |
717 | }, sub_supp2[]={ | |
718 | 0xd801, 0xdc03, 0 | |
719 | }, sub_a_lead[]={ | |
720 | 0x61, 0xd801, 0 | |
721 | }, sub_trail_a[]={ | |
722 | 0xdc02, 0x61, 0 | |
723 | }, sub_aba[]={ | |
724 | 0x61, 0x62, 0x61, 0 | |
725 | }; | |
726 | static const UChar a=0x61, b=0x62, lead=0xd801, trail=0xdc02, nul=0; | |
727 | static const UChar32 supp=0x10402, supp2=0x10403, ill=0x123456; | |
728 | ||
729 | const UChar *first, *last; | |
730 | ||
731 | /* search for NUL code point: find end of string */ | |
732 | first=s+u_strlen(s); | |
733 | ||
734 | if( | |
735 | first!=u_strchr(s, nul) || | |
736 | first!=u_strchr32(s, nul) || | |
737 | first!=u_memchr(s, nul, LENGTHOF(s)) || | |
738 | first!=u_memchr32(s, nul, LENGTHOF(s)) || | |
739 | first!=u_strrchr(s, nul) || | |
740 | first!=u_strrchr32(s, nul) || | |
741 | first!=u_memrchr(s, nul, LENGTHOF(s)) || | |
742 | first!=u_memrchr32(s, nul, LENGTHOF(s)) | |
743 | ) { | |
744 | log_err("error: one of the u_str[|mem][r]chr[32](s, nul) does not find the terminator of s\n"); | |
745 | } | |
746 | ||
747 | /* search for empty substring: find beginning of string */ | |
748 | if( | |
749 | s!=u_strstr(s, &nul) || | |
750 | s!=u_strFindFirst(s, -1, &nul, -1) || | |
751 | s!=u_strFindFirst(s, -1, &nul, 0) || | |
752 | s!=u_strFindFirst(s, LENGTHOF(s), &nul, -1) || | |
753 | s!=u_strFindFirst(s, LENGTHOF(s), &nul, 0) || | |
754 | s!=u_strrstr(s, &nul) || | |
755 | s!=u_strFindLast(s, -1, &nul, -1) || | |
756 | s!=u_strFindLast(s, -1, &nul, 0) || | |
757 | s!=u_strFindLast(s, LENGTHOF(s), &nul, -1) || | |
758 | s!=u_strFindLast(s, LENGTHOF(s), &nul, 0) | |
759 | ) { | |
760 | log_err("error: one of the u_str[str etc](s, \"\") does not find s itself\n"); | |
761 | } | |
762 | ||
763 | /* find 'a' in s[1..10[ */ | |
764 | first=s+3; | |
765 | last=s+7; | |
766 | if( | |
767 | first!=u_strchr(s+1, a) || | |
768 | first!=u_strchr32(s+1, a) || | |
769 | first!=u_memchr(s+1, a, 9) || | |
770 | first!=u_memchr32(s+1, a, 9) || | |
771 | first!=u_strstr(s+1, sub_a) || | |
772 | first!=u_strFindFirst(s+1, -1, sub_a, -1) || | |
773 | first!=u_strFindFirst(s+1, -1, &a, 1) || | |
774 | first!=u_strFindFirst(s+1, 9, sub_a, -1) || | |
775 | first!=u_strFindFirst(s+1, 9, &a, 1) || | |
776 | (s+10)!=u_strrchr(s+1, a) || | |
777 | (s+10)!=u_strrchr32(s+1, a) || | |
778 | last!=u_memrchr(s+1, a, 9) || | |
779 | last!=u_memrchr32(s+1, a, 9) || | |
780 | (s+10)!=u_strrstr(s+1, sub_a) || | |
781 | (s+10)!=u_strFindLast(s+1, -1, sub_a, -1) || | |
782 | (s+10)!=u_strFindLast(s+1, -1, &a, 1) || | |
783 | last!=u_strFindLast(s+1, 9, sub_a, -1) || | |
784 | last!=u_strFindLast(s+1, 9, &a, 1) | |
785 | ) { | |
786 | log_err("error: one of the u_str[chr etc]('a') does not find the correct place\n"); | |
787 | } | |
788 | ||
789 | /* do not find 'b' in s[1..10[ */ | |
790 | if( | |
791 | NULL!=u_strchr(s+1, b) || | |
792 | NULL!=u_strchr32(s+1, b) || | |
793 | NULL!=u_memchr(s+1, b, 9) || | |
794 | NULL!=u_memchr32(s+1, b, 9) || | |
795 | NULL!=u_strstr(s+1, sub_b) || | |
796 | NULL!=u_strFindFirst(s+1, -1, sub_b, -1) || | |
797 | NULL!=u_strFindFirst(s+1, -1, &b, 1) || | |
798 | NULL!=u_strFindFirst(s+1, 9, sub_b, -1) || | |
799 | NULL!=u_strFindFirst(s+1, 9, &b, 1) || | |
800 | NULL!=u_strrchr(s+1, b) || | |
801 | NULL!=u_strrchr32(s+1, b) || | |
802 | NULL!=u_memrchr(s+1, b, 9) || | |
803 | NULL!=u_memrchr32(s+1, b, 9) || | |
804 | NULL!=u_strrstr(s+1, sub_b) || | |
805 | NULL!=u_strFindLast(s+1, -1, sub_b, -1) || | |
806 | NULL!=u_strFindLast(s+1, -1, &b, 1) || | |
807 | NULL!=u_strFindLast(s+1, 9, sub_b, -1) || | |
808 | NULL!=u_strFindLast(s+1, 9, &b, 1) | |
809 | ) { | |
810 | log_err("error: one of the u_str[chr etc]('b') incorrectly finds something\n"); | |
811 | } | |
812 | ||
813 | /* do not find a non-code point in s[1..10[ */ | |
814 | if( | |
815 | NULL!=u_strchr32(s+1, ill) || | |
816 | NULL!=u_memchr32(s+1, ill, 9) || | |
817 | NULL!=u_strrchr32(s+1, ill) || | |
818 | NULL!=u_memrchr32(s+1, ill, 9) | |
819 | ) { | |
820 | log_err("error: one of the u_str[chr etc](illegal code point) incorrectly finds something\n"); | |
821 | } | |
822 | ||
823 | /* find U+d801 in s[1..10[ */ | |
824 | first=s+6; | |
825 | if( | |
826 | first!=u_strchr(s+1, lead) || | |
827 | first!=u_strchr32(s+1, lead) || | |
828 | first!=u_memchr(s+1, lead, 9) || | |
829 | first!=u_memchr32(s+1, lead, 9) || | |
830 | first!=u_strstr(s+1, sub_lead) || | |
831 | first!=u_strFindFirst(s+1, -1, sub_lead, -1) || | |
832 | first!=u_strFindFirst(s+1, -1, &lead, 1) || | |
833 | first!=u_strFindFirst(s+1, 9, sub_lead, -1) || | |
834 | first!=u_strFindFirst(s+1, 9, &lead, 1) || | |
835 | first!=u_strrchr(s+1, lead) || | |
836 | first!=u_strrchr32(s+1, lead) || | |
837 | first!=u_memrchr(s+1, lead, 9) || | |
838 | first!=u_memrchr32(s+1, lead, 9) || | |
839 | first!=u_strrstr(s+1, sub_lead) || | |
840 | first!=u_strFindLast(s+1, -1, sub_lead, -1) || | |
841 | first!=u_strFindLast(s+1, -1, &lead, 1) || | |
842 | first!=u_strFindLast(s+1, 9, sub_lead, -1) || | |
843 | first!=u_strFindLast(s+1, 9, &lead, 1) | |
844 | ) { | |
845 | log_err("error: one of the u_str[chr etc](U+d801) does not find the correct place\n"); | |
846 | } | |
847 | ||
848 | /* find U+dc02 in s[1..10[ */ | |
849 | first=s+4; | |
850 | if( | |
851 | first!=u_strchr(s+1, trail) || | |
852 | first!=u_strchr32(s+1, trail) || | |
853 | first!=u_memchr(s+1, trail, 9) || | |
854 | first!=u_memchr32(s+1, trail, 9) || | |
855 | first!=u_strstr(s+1, sub_trail) || | |
856 | first!=u_strFindFirst(s+1, -1, sub_trail, -1) || | |
857 | first!=u_strFindFirst(s+1, -1, &trail, 1) || | |
858 | first!=u_strFindFirst(s+1, 9, sub_trail, -1) || | |
859 | first!=u_strFindFirst(s+1, 9, &trail, 1) || | |
860 | first!=u_strrchr(s+1, trail) || | |
861 | first!=u_strrchr32(s+1, trail) || | |
862 | first!=u_memrchr(s+1, trail, 9) || | |
863 | first!=u_memrchr32(s+1, trail, 9) || | |
864 | first!=u_strrstr(s+1, sub_trail) || | |
865 | first!=u_strFindLast(s+1, -1, sub_trail, -1) || | |
866 | first!=u_strFindLast(s+1, -1, &trail, 1) || | |
867 | first!=u_strFindLast(s+1, 9, sub_trail, -1) || | |
868 | first!=u_strFindLast(s+1, 9, &trail, 1) | |
869 | ) { | |
870 | log_err("error: one of the u_str[chr etc](U+dc02) does not find the correct place\n"); | |
871 | } | |
872 | ||
873 | /* find U+10402 in s[1..10[ */ | |
874 | first=s+1; | |
875 | last=s+8; | |
876 | if( | |
877 | first!=u_strchr32(s+1, supp) || | |
878 | first!=u_memchr32(s+1, supp, 9) || | |
879 | first!=u_strstr(s+1, sub_supp) || | |
880 | first!=u_strFindFirst(s+1, -1, sub_supp, -1) || | |
881 | first!=u_strFindFirst(s+1, -1, sub_supp, 2) || | |
882 | first!=u_strFindFirst(s+1, 9, sub_supp, -1) || | |
883 | first!=u_strFindFirst(s+1, 9, sub_supp, 2) || | |
884 | last!=u_strrchr32(s+1, supp) || | |
885 | last!=u_memrchr32(s+1, supp, 9) || | |
886 | last!=u_strrstr(s+1, sub_supp) || | |
887 | last!=u_strFindLast(s+1, -1, sub_supp, -1) || | |
888 | last!=u_strFindLast(s+1, -1, sub_supp, 2) || | |
889 | last!=u_strFindLast(s+1, 9, sub_supp, -1) || | |
890 | last!=u_strFindLast(s+1, 9, sub_supp, 2) | |
891 | ) { | |
892 | log_err("error: one of the u_str[chr etc](U+10402) does not find the correct place\n"); | |
893 | } | |
894 | ||
895 | /* do not find U+10402 in a single UChar */ | |
896 | if( | |
897 | NULL!=u_memchr32(s+1, supp, 1) || | |
898 | NULL!=u_strFindFirst(s+1, 1, sub_supp, -1) || | |
899 | NULL!=u_strFindFirst(s+1, 1, sub_supp, 2) || | |
900 | NULL!=u_memrchr32(s+1, supp, 1) || | |
901 | NULL!=u_strFindLast(s+1, 1, sub_supp, -1) || | |
902 | NULL!=u_strFindLast(s+1, 1, sub_supp, 2) || | |
903 | NULL!=u_memrchr32(s+2, supp, 1) || | |
904 | NULL!=u_strFindLast(s+2, 1, sub_supp, -1) || | |
905 | NULL!=u_strFindLast(s+2, 1, sub_supp, 2) | |
906 | ) { | |
907 | log_err("error: one of the u_str[chr etc](U+10402) incorrectly finds a supplementary c.p. in a single UChar\n"); | |
908 | } | |
909 | ||
910 | /* do not find U+10403 in s[1..10[ */ | |
911 | if( | |
912 | NULL!=u_strchr32(s+1, supp2) || | |
913 | NULL!=u_memchr32(s+1, supp2, 9) || | |
914 | NULL!=u_strstr(s+1, sub_supp2) || | |
915 | NULL!=u_strFindFirst(s+1, -1, sub_supp2, -1) || | |
916 | NULL!=u_strFindFirst(s+1, -1, sub_supp2, 2) || | |
917 | NULL!=u_strFindFirst(s+1, 9, sub_supp2, -1) || | |
918 | NULL!=u_strFindFirst(s+1, 9, sub_supp2, 2) || | |
919 | NULL!=u_strrchr32(s+1, supp2) || | |
920 | NULL!=u_memrchr32(s+1, supp2, 9) || | |
921 | NULL!=u_strrstr(s+1, sub_supp2) || | |
922 | NULL!=u_strFindLast(s+1, -1, sub_supp2, -1) || | |
923 | NULL!=u_strFindLast(s+1, -1, sub_supp2, 2) || | |
924 | NULL!=u_strFindLast(s+1, 9, sub_supp2, -1) || | |
925 | NULL!=u_strFindLast(s+1, 9, sub_supp2, 2) | |
926 | ) { | |
927 | log_err("error: one of the u_str[chr etc](U+10403) incorrectly finds something\n"); | |
928 | } | |
929 | ||
930 | /* find <0061 d801> in s[1..10[ */ | |
931 | first=s+5; | |
932 | if( | |
933 | first!=u_strstr(s+1, sub_a_lead) || | |
934 | first!=u_strFindFirst(s+1, -1, sub_a_lead, -1) || | |
935 | first!=u_strFindFirst(s+1, -1, sub_a_lead, 2) || | |
936 | first!=u_strFindFirst(s+1, 9, sub_a_lead, -1) || | |
937 | first!=u_strFindFirst(s+1, 9, sub_a_lead, 2) || | |
938 | first!=u_strrstr(s+1, sub_a_lead) || | |
939 | first!=u_strFindLast(s+1, -1, sub_a_lead, -1) || | |
940 | first!=u_strFindLast(s+1, -1, sub_a_lead, 2) || | |
941 | first!=u_strFindLast(s+1, 9, sub_a_lead, -1) || | |
942 | first!=u_strFindLast(s+1, 9, sub_a_lead, 2) | |
943 | ) { | |
944 | log_err("error: one of the u_str[str etc](<0061 d801>) does not find the correct place\n"); | |
945 | } | |
946 | ||
947 | /* find <dc02 0061> in s[1..10[ */ | |
948 | first=s+4; | |
949 | if( | |
950 | first!=u_strstr(s+1, sub_trail_a) || | |
951 | first!=u_strFindFirst(s+1, -1, sub_trail_a, -1) || | |
952 | first!=u_strFindFirst(s+1, -1, sub_trail_a, 2) || | |
953 | first!=u_strFindFirst(s+1, 9, sub_trail_a, -1) || | |
954 | first!=u_strFindFirst(s+1, 9, sub_trail_a, 2) || | |
955 | first!=u_strrstr(s+1, sub_trail_a) || | |
956 | first!=u_strFindLast(s+1, -1, sub_trail_a, -1) || | |
957 | first!=u_strFindLast(s+1, -1, sub_trail_a, 2) || | |
958 | first!=u_strFindLast(s+1, 9, sub_trail_a, -1) || | |
959 | first!=u_strFindLast(s+1, 9, sub_trail_a, 2) | |
960 | ) { | |
961 | log_err("error: one of the u_str[str etc](<dc02 0061>) does not find the correct place\n"); | |
962 | } | |
963 | ||
964 | /* do not find "aba" in s[1..10[ */ | |
965 | if( | |
966 | NULL!=u_strstr(s+1, sub_aba) || | |
967 | NULL!=u_strFindFirst(s+1, -1, sub_aba, -1) || | |
968 | NULL!=u_strFindFirst(s+1, -1, sub_aba, 3) || | |
969 | NULL!=u_strFindFirst(s+1, 9, sub_aba, -1) || | |
970 | NULL!=u_strFindFirst(s+1, 9, sub_aba, 3) || | |
971 | NULL!=u_strrstr(s+1, sub_aba) || | |
972 | NULL!=u_strFindLast(s+1, -1, sub_aba, -1) || | |
973 | NULL!=u_strFindLast(s+1, -1, sub_aba, 3) || | |
974 | NULL!=u_strFindLast(s+1, 9, sub_aba, -1) || | |
975 | NULL!=u_strFindLast(s+1, 9, sub_aba, 3) | |
976 | ) { | |
977 | log_err("error: one of the u_str[str etc](\"aba\") incorrectly finds something\n"); | |
978 | } | |
979 | } | |
980 | ||
981 | static void TestStringCopy() | |
982 | { | |
983 | UChar temp[40]; | |
984 | UChar *result=0; | |
985 | UChar subString[5]; | |
986 | UChar uchars[]={0x61, 0x62, 0x63, 0x00}; | |
987 | char charOut[40]; | |
988 | char chars[]="abc"; /* needs default codepage */ | |
989 | ||
990 | log_verbose("Testing u_uastrncpy() and u_uastrcpy()"); | |
991 | ||
992 | u_uastrcpy(temp, "abc"); | |
993 | if(u_strcmp(temp, uchars) != 0) { | |
994 | log_err("There is an error in u_uastrcpy() Expected %s Got %s\n", austrdup(uchars), austrdup(temp)); | |
995 | } | |
996 | ||
997 | temp[0] = 0xFB; /* load garbage into it */ | |
998 | temp[1] = 0xFB; | |
999 | temp[2] = 0xFB; | |
1000 | temp[3] = 0xFB; | |
1001 | ||
1002 | u_uastrncpy(temp, "abcabcabc", 3); | |
1003 | if(u_strncmp(uchars, temp, 3) != 0){ | |
1004 | log_err("There is an error in u_uastrncpy() Expected %s Got %s\n", austrdup(uchars), austrdup(temp)); | |
1005 | } | |
1006 | if(temp[3] != 0xFB) { | |
1007 | log_err("u_uastrncpy wrote past it's bounds. Expected undisturbed byte at 3\n"); | |
1008 | } | |
1009 | ||
1010 | charOut[0] = (char)0x7B; /* load garbage into it */ | |
1011 | charOut[1] = (char)0x7B; | |
1012 | charOut[2] = (char)0x7B; | |
1013 | charOut[3] = (char)0x7B; | |
1014 | ||
1015 | temp[0] = 0x0061; | |
1016 | temp[1] = 0x0062; | |
1017 | temp[2] = 0x0063; | |
1018 | temp[3] = 0x0061; | |
1019 | temp[4] = 0x0062; | |
1020 | temp[5] = 0x0063; | |
1021 | temp[6] = 0x0000; | |
1022 | ||
1023 | u_austrncpy(charOut, temp, 3); | |
1024 | if(strncmp(chars, charOut, 3) != 0){ | |
1025 | log_err("There is an error in u_austrncpy() Expected %s Got %s\n", austrdup(uchars), austrdup(temp)); | |
1026 | } | |
1027 | if(charOut[3] != (char)0x7B) { | |
1028 | log_err("u_austrncpy wrote past it's bounds. Expected undisturbed byte at 3\n"); | |
1029 | } | |
1030 | ||
1031 | /*Testing u_strchr()*/ | |
1032 | log_verbose("Testing u_strchr\n"); | |
1033 | temp[0]=0x42; | |
1034 | temp[1]=0x62; | |
1035 | temp[2]=0x62; | |
1036 | temp[3]=0x63; | |
1037 | temp[4]=0xd841; | |
1038 | temp[5]=0xd841; | |
1039 | temp[6]=0xdc02; | |
1040 | temp[7]=0; | |
1041 | result=u_strchr(temp, (UChar)0x62); | |
1042 | if(result != temp+1){ | |
1043 | log_err("There is an error in u_strchr() Expected match at position 1 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1044 | } | |
1045 | /*Testing u_strstr()*/ | |
1046 | log_verbose("Testing u_strstr\n"); | |
1047 | subString[0]=0x62; | |
1048 | subString[1]=0x63; | |
1049 | subString[2]=0; | |
1050 | result=u_strstr(temp, subString); | |
1051 | if(result != temp+2){ | |
1052 | log_err("There is an error in u_strstr() Expected match at position 2 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1053 | } | |
1054 | result=u_strstr(temp, subString+2); /* subString+2 is an empty string */ | |
1055 | if(result != temp){ | |
1056 | log_err("There is an error in u_strstr() Expected match at position 0 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1057 | } | |
1058 | result=u_strstr(subString, temp); | |
1059 | if(result != NULL){ | |
1060 | log_err("There is an error in u_strstr() Expected NULL \"not found\" Got non-NULL \"found\" result\n"); | |
1061 | } | |
1062 | ||
1063 | /*Testing u_strchr32*/ | |
1064 | log_verbose("Testing u_strchr32\n"); | |
1065 | result=u_strchr32(temp, (UChar32)0x62); | |
1066 | if(result != temp+1){ | |
1067 | log_err("There is an error in u_strchr32() Expected match at position 1 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1068 | } | |
1069 | result=u_strchr32(temp, (UChar32)0xfb); | |
1070 | if(result != NULL){ | |
1071 | log_err("There is an error in u_strchr32() Expected NULL \"not found\" Got non-NULL \"found\" result\n"); | |
1072 | } | |
1073 | result=u_strchr32(temp, (UChar32)0x20402); | |
1074 | if(result != temp+5){ | |
1075 | log_err("There is an error in u_strchr32() Expected match at position 5 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1076 | } | |
1077 | ||
1078 | temp[7]=0xfc00; | |
1079 | result=u_memchr32(temp, (UChar32)0x20402, 7); | |
1080 | if(result != temp+5){ | |
1081 | log_err("There is an error in u_memchr32() Expected match at position 5 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1082 | } | |
1083 | result=u_memchr32(temp, (UChar32)0x20402, 6); | |
1084 | if(result != NULL){ | |
1085 | log_err("There is an error in u_memchr32() Expected no match Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1086 | } | |
1087 | result=u_memchr32(temp, (UChar32)0x20402, 1); | |
1088 | if(result != NULL){ | |
1089 | log_err("There is an error in u_memchr32() Expected no match Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1090 | } | |
1091 | result=u_memchr32(temp, (UChar32)0xfc00, 8); | |
1092 | if(result != temp+7){ | |
1093 | log_err("There is an error in u_memchr32() Expected match at position 7 Got %ld (pointer 0x%lx)\n", result-temp, result); | |
1094 | } | |
1095 | } | |
1096 | ||
1097 | /* test u_unescape() and u_unescapeAt() ------------------------------------- */ | |
1098 | ||
1099 | static void | |
1100 | TestUnescape() { | |
1101 | static UChar buffer[200]; | |
1102 | ||
1103 | static const char* input = | |
1104 | "Sch\\u00f6nes Auto: \\u20ac 11240.\\fPrivates Zeichen: \\U00102345\\e\\cC\\n \\x1b\\x{263a}"; | |
1105 | ||
1106 | static const UChar expect[]={ | |
1107 | 0x53, 0x63, 0x68, 0xf6, 0x6e, 0x65, 0x73, 0x20, 0x41, 0x75, 0x74, 0x6f, 0x3a, 0x20, | |
1108 | 0x20ac, 0x20, 0x31, 0x31, 0x32, 0x34, 0x30, 0x2e, 0x0c, | |
1109 | 0x50, 0x72, 0x69, 0x76, 0x61, 0x74, 0x65, 0x73, 0x20, | |
1110 | 0x5a, 0x65, 0x69, 0x63, 0x68, 0x65, 0x6e, 0x3a, 0x20, 0xdbc8, 0xdf45, 0x1b, 0x03, 0x0a, 0x20, 0x1b, 0x263A, 0 | |
1111 | }; | |
1112 | static const int32_t explength = sizeof(expect)/sizeof(expect[0])-1; | |
1113 | int32_t length; | |
1114 | ||
1115 | /* test u_unescape() */ | |
1116 | length=u_unescape(input, buffer, sizeof(buffer)/sizeof(buffer[0])); | |
1117 | if(length!=explength || u_strcmp(buffer, expect)!=0) { | |
1118 | log_err("failure in u_unescape(): length %d!=%d and/or incorrect result string\n", length, | |
1119 | explength); | |
1120 | } | |
1121 | ||
1122 | /* try preflighting */ | |
1123 | length=u_unescape(input, NULL, sizeof(buffer)/sizeof(buffer[0])); | |
1124 | if(length!=explength || u_strcmp(buffer, expect)!=0) { | |
1125 | log_err("failure in u_unescape(preflighting): length %d!=%d\n", length, explength); | |
1126 | } | |
1127 | ||
1128 | /* ### TODO: test u_unescapeAt() */ | |
1129 | } | |
1130 | ||
1131 | /* test code point counting functions --------------------------------------- */ | |
1132 | ||
1133 | /* reference implementation of u_strHasMoreChar32Than() */ | |
1134 | static int32_t | |
1135 | _refStrHasMoreChar32Than(const UChar *s, int32_t length, int32_t number) { | |
1136 | int32_t count=u_countChar32(s, length); | |
1137 | return count>number; | |
1138 | } | |
1139 | ||
1140 | /* compare the real function against the reference */ | |
1141 | static void | |
1142 | _testStrHasMoreChar32Than(const UChar *s, int32_t i, int32_t length, int32_t number) { | |
1143 | if(u_strHasMoreChar32Than(s, length, number)!=_refStrHasMoreChar32Than(s, length, number)) { | |
1144 | log_err("u_strHasMoreChar32Than(s+%d, %d, %d)=%hd is wrong\n", | |
1145 | i, length, number, u_strHasMoreChar32Than(s, length, number)); | |
1146 | } | |
1147 | } | |
1148 | ||
1149 | static void | |
1150 | TestCountChar32() { | |
1151 | static const UChar string[]={ | |
1152 | 0x61, 0x62, 0xd800, 0xdc00, | |
1153 | 0xd801, 0xdc01, 0x63, 0xd802, | |
1154 | 0x64, 0xdc03, 0x65, 0x66, | |
1155 | 0xd804, 0xdc04, 0xd805, 0xdc05, | |
1156 | 0x67 | |
1157 | }; | |
1158 | UChar buffer[100]; | |
1159 | int32_t i, length, number; | |
1160 | ||
1161 | /* test u_strHasMoreChar32Than() with length>=0 */ | |
1162 | length=LENGTHOF(string); | |
1163 | while(length>=0) { | |
1164 | for(i=0; i<=length; ++i) { | |
1165 | for(number=-1; number<=((length-i)+2); ++number) { | |
1166 | _testStrHasMoreChar32Than(string+i, i, length-i, number); | |
1167 | } | |
1168 | } | |
1169 | --length; | |
1170 | } | |
1171 | ||
1172 | /* test u_strHasMoreChar32Than() with NUL-termination (length=-1) */ | |
1173 | length=LENGTHOF(string); | |
1174 | u_memcpy(buffer, string, length); | |
1175 | while(length>=0) { | |
1176 | buffer[length]=0; | |
1177 | for(i=0; i<=length; ++i) { | |
1178 | for(number=-1; number<=((length-i)+2); ++number) { | |
1179 | _testStrHasMoreChar32Than(string+i, i, -1, number); | |
1180 | } | |
1181 | } | |
1182 | --length; | |
1183 | } | |
1184 | ||
1185 | /* test u_strHasMoreChar32Than() with NULL string (bad input) */ | |
1186 | for(length=-1; length<=1; ++length) { | |
1187 | for(i=0; i<=length; ++i) { | |
1188 | for(number=-2; number<=2; ++number) { | |
1189 | _testStrHasMoreChar32Than(NULL, 0, length, number); | |
1190 | } | |
1191 | } | |
1192 | } | |
1193 | } | |
1194 | ||
1195 | /* UCharIterator ------------------------------------------------------------ */ | |
1196 | ||
1197 | /* | |
1198 | * Compare results from two iterators, should be same. | |
1199 | * Assume that the text is not empty and that | |
1200 | * iteration start==0 and iteration limit==length. | |
1201 | */ | |
1202 | static void | |
1203 | compareIterators(UCharIterator *iter1, const char *n1, | |
1204 | UCharIterator *iter2, const char *n2) { | |
1205 | int32_t i, pos1, pos2, middle, length; | |
1206 | UChar32 c1, c2; | |
1207 | ||
1208 | /* compare lengths */ | |
1209 | length=iter1->getIndex(iter1, UITER_LENGTH); | |
1210 | pos2=iter2->getIndex(iter2, UITER_LENGTH); | |
1211 | if(length!=pos2) { | |
1212 | log_err("%s->getIndex(length)=%d != %d=%s->getIndex(length)\n", n1, length, pos2, n2); | |
1213 | return; | |
1214 | } | |
1215 | ||
1216 | /* set into the middle */ | |
1217 | middle=length/2; | |
1218 | ||
1219 | pos1=iter1->move(iter1, middle, UITER_ZERO); | |
1220 | if(pos1!=middle) { | |
1221 | log_err("%s->move(from 0 to middle %d)=%d does not move to the middle\n", n1, middle, pos1); | |
1222 | return; | |
1223 | } | |
1224 | ||
1225 | pos2=iter2->move(iter2, middle, UITER_ZERO); | |
1226 | if(pos2!=middle) { | |
1227 | log_err("%s->move(from 0 to middle %d)=%d does not move to the middle\n", n2, middle, pos2); | |
1228 | return; | |
1229 | } | |
1230 | ||
1231 | /* test current() */ | |
1232 | c1=iter1->current(iter1); | |
1233 | c2=iter2->current(iter2); | |
1234 | if(c1!=c2) { | |
1235 | log_err("%s->current()=U+%04x != U+%04x=%s->current() at middle=%d\n", n1, c1, c2, n2, middle); | |
1236 | return; | |
1237 | } | |
1238 | ||
1239 | /* move forward 3 UChars */ | |
1240 | for(i=0; i<3; ++i) { | |
1241 | c1=iter1->next(iter1); | |
1242 | c2=iter2->next(iter2); | |
1243 | if(c1!=c2) { | |
1244 | log_err("%s->next()=U+%04x != U+%04x=%s->next() at %d (started in middle)\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1245 | return; | |
1246 | } | |
1247 | } | |
1248 | ||
1249 | /* move backward 5 UChars */ | |
1250 | for(i=0; i<5; ++i) { | |
1251 | c1=iter1->previous(iter1); | |
1252 | c2=iter2->previous(iter2); | |
1253 | if(c1!=c2) { | |
1254 | log_err("%s->previous()=U+%04x != U+%04x=%s->previous() at %d (started in middle)\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1255 | return; | |
1256 | } | |
1257 | } | |
1258 | ||
1259 | /* iterate forward from the beginning */ | |
1260 | pos1=iter1->move(iter1, 0, UITER_START); | |
1261 | if(pos1<0) { | |
1262 | log_err("%s->move(start) failed\n", n1); | |
1263 | return; | |
1264 | } | |
1265 | if(!iter1->hasNext(iter1)) { | |
1266 | log_err("%s->hasNext() at the start returns FALSE\n", n1); | |
1267 | return; | |
1268 | } | |
1269 | ||
1270 | pos2=iter2->move(iter2, 0, UITER_START); | |
1271 | if(pos2<0) { | |
1272 | log_err("%s->move(start) failed\n", n2); | |
1273 | return; | |
1274 | } | |
1275 | if(!iter2->hasNext(iter2)) { | |
1276 | log_err("%s->hasNext() at the start returns FALSE\n", n2); | |
1277 | return; | |
1278 | } | |
1279 | ||
1280 | do { | |
1281 | c1=iter1->next(iter1); | |
1282 | c2=iter2->next(iter2); | |
1283 | if(c1!=c2) { | |
1284 | log_err("%s->next()=U+%04x != U+%04x=%s->next() at %d\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1285 | return; | |
1286 | } | |
1287 | } while(c1>=0); | |
1288 | ||
1289 | if(iter1->hasNext(iter1)) { | |
1290 | log_err("%s->hasNext() at the end returns TRUE\n", n1); | |
1291 | return; | |
1292 | } | |
1293 | if(iter2->hasNext(iter2)) { | |
1294 | log_err("%s->hasNext() at the end returns TRUE\n", n2); | |
1295 | return; | |
1296 | } | |
1297 | ||
1298 | /* back to the middle */ | |
1299 | pos1=iter1->move(iter1, middle, UITER_ZERO); | |
1300 | if(pos1!=middle) { | |
1301 | log_err("%s->move(from end to middle %d)=%d does not move to the middle\n", n1, middle, pos1); | |
1302 | return; | |
1303 | } | |
1304 | ||
1305 | pos2=iter2->move(iter2, middle, UITER_ZERO); | |
1306 | if(pos2!=middle) { | |
1307 | log_err("%s->move(from end to middle %d)=%d does not move to the middle\n", n2, middle, pos2); | |
1308 | return; | |
1309 | } | |
1310 | ||
1311 | /* move to index 1 */ | |
1312 | pos1=iter1->move(iter1, 1, UITER_ZERO); | |
1313 | if(pos1!=1) { | |
1314 | log_err("%s->move(from middle %d to 1)=%d does not move to 1\n", n1, middle, pos1); | |
1315 | return; | |
1316 | } | |
1317 | ||
1318 | pos2=iter2->move(iter2, 1, UITER_ZERO); | |
1319 | if(pos2!=1) { | |
1320 | log_err("%s->move(from middle %d to 1)=%d does not move to 1\n", n2, middle, pos2); | |
1321 | return; | |
1322 | } | |
1323 | ||
1324 | /* iterate backward from the end */ | |
1325 | pos1=iter1->move(iter1, 0, UITER_LIMIT); | |
1326 | if(pos1<0) { | |
1327 | log_err("%s->move(limit) failed\n", n1); | |
1328 | return; | |
1329 | } | |
1330 | if(!iter1->hasPrevious(iter1)) { | |
1331 | log_err("%s->hasPrevious() at the end returns FALSE\n", n1); | |
1332 | return; | |
1333 | } | |
1334 | ||
1335 | pos2=iter2->move(iter2, 0, UITER_LIMIT); | |
1336 | if(pos2<0) { | |
1337 | log_err("%s->move(limit) failed\n", n2); | |
1338 | return; | |
1339 | } | |
1340 | if(!iter2->hasPrevious(iter2)) { | |
1341 | log_err("%s->hasPrevious() at the end returns FALSE\n", n2); | |
1342 | return; | |
1343 | } | |
1344 | ||
1345 | do { | |
1346 | c1=iter1->previous(iter1); | |
1347 | c2=iter2->previous(iter2); | |
1348 | if(c1!=c2) { | |
1349 | log_err("%s->previous()=U+%04x != U+%04x=%s->previous() at %d\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1350 | return; | |
1351 | } | |
1352 | } while(c1>=0); | |
1353 | ||
1354 | if(iter1->hasPrevious(iter1)) { | |
1355 | log_err("%s->hasPrevious() at the start returns TRUE\n", n1); | |
1356 | return; | |
1357 | } | |
1358 | if(iter2->hasPrevious(iter2)) { | |
1359 | log_err("%s->hasPrevious() at the start returns TRUE\n", n2); | |
1360 | return; | |
1361 | } | |
1362 | } | |
1363 | ||
1364 | /* | |
1365 | * Test the iterator's getState() and setState() functions. | |
1366 | * iter1 and iter2 must be set up for the same iterator type and the same string | |
1367 | * but may be physically different structs (different addresses). | |
1368 | * | |
1369 | * Assume that the text is not empty and that | |
1370 | * iteration start==0 and iteration limit==length. | |
1371 | * It must be 2<=middle<=length-2. | |
1372 | */ | |
1373 | static void | |
1374 | testIteratorState(UCharIterator *iter1, UCharIterator *iter2, const char *n, int32_t middle) { | |
1375 | UChar32 u[4]; | |
1376 | ||
1377 | UErrorCode errorCode; | |
1378 | UChar32 c; | |
1379 | uint32_t state; | |
1380 | int32_t i, j; | |
1381 | ||
1382 | /* get four UChars from the middle of the string */ | |
1383 | iter1->move(iter1, middle-2, UITER_ZERO); | |
1384 | for(i=0; i<4; ++i) { | |
1385 | c=iter1->next(iter1); | |
1386 | if(c<0) { | |
1387 | /* the test violates the assumptions, see comment above */ | |
1388 | log_err("test error: %s[%d]=%d\n", n, middle-2+i, c); | |
1389 | return; | |
1390 | } | |
1391 | u[i]=c; | |
1392 | } | |
1393 | ||
1394 | /* move to the middle and get the state */ | |
1395 | iter1->move(iter1, -2, UITER_CURRENT); | |
1396 | state=uiter_getState(iter1); | |
1397 | ||
1398 | /* set the state into the second iterator and compare the results */ | |
1399 | errorCode=U_ZERO_ERROR; | |
1400 | uiter_setState(iter2, state, &errorCode); | |
1401 | if(U_FAILURE(errorCode)) { | |
1402 | log_err("%s->setState(0x%x) failed: %s\n", n, state, u_errorName(errorCode)); | |
1403 | return; | |
1404 | } | |
1405 | ||
1406 | c=iter2->current(iter2); | |
1407 | if(c!=u[2]) { | |
1408 | log_err("%s->current(at %d)=U+%04x!=U+%04x\n", n, middle, c, u[2]); | |
1409 | } | |
1410 | ||
1411 | c=iter2->previous(iter2); | |
1412 | if(c!=u[1]) { | |
1413 | log_err("%s->previous(at %d)=U+%04x!=U+%04x\n", n, middle-1, c, u[1]); | |
1414 | } | |
1415 | ||
1416 | iter2->move(iter2, 2, UITER_CURRENT); | |
1417 | c=iter2->next(iter2); | |
1418 | if(c!=u[3]) { | |
1419 | log_err("%s->next(at %d)=U+%04x!=U+%04x\n", n, middle+1, c, u[3]); | |
1420 | } | |
1421 | ||
1422 | iter2->move(iter2, -3, UITER_CURRENT); | |
1423 | c=iter2->previous(iter2); | |
1424 | if(c!=u[0]) { | |
1425 | log_err("%s->previous(at %d)=U+%04x!=U+%04x\n", n, middle-2, c, u[0]); | |
1426 | } | |
1427 | ||
1428 | /* move the second iterator back to the middle */ | |
1429 | iter2->move(iter2, 1, UITER_CURRENT); | |
1430 | iter2->next(iter2); | |
1431 | ||
1432 | /* check that both are in the middle */ | |
1433 | i=iter1->getIndex(iter1, UITER_CURRENT); | |
1434 | j=iter2->getIndex(iter2, UITER_CURRENT); | |
1435 | if(i!=middle) { | |
1436 | log_err("%s->getIndex(current)=%d!=%d as expected\n", n, i, middle); | |
1437 | } | |
1438 | if(i!=j) { | |
1439 | log_err("%s->getIndex(current)=%d!=%d after setState()\n", n, j, i); | |
1440 | } | |
1441 | ||
1442 | /* compare lengths */ | |
1443 | i=iter1->getIndex(iter1, UITER_LENGTH); | |
1444 | j=iter2->getIndex(iter2, UITER_LENGTH); | |
1445 | if(i!=j) { | |
1446 | log_err("%s->getIndex(length)=%d!=%d before/after setState()\n", n, i, j); | |
1447 | } | |
1448 | } | |
1449 | ||
1450 | static void | |
1451 | TestUCharIterator() { | |
1452 | static const UChar text[]={ | |
1453 | 0x61, 0x62, 0x63, 0xd801, 0xdffd, 0x78, 0x79, 0x7a, 0 | |
1454 | }; | |
1455 | char bytes[40]; | |
1456 | ||
1457 | UCharIterator iter, iter1, iter2; | |
1458 | UConverter *cnv; | |
1459 | UErrorCode errorCode; | |
1460 | int32_t length; | |
1461 | ||
1462 | /* simple API/code coverage - test NOOP UCharIterator */ | |
1463 | uiter_setString(&iter, NULL, 0); | |
1464 | if( iter.current(&iter)!=-1 || iter.next(&iter)!=-1 || iter.previous(&iter)!=-1 || | |
1465 | iter.move(&iter, 1, UITER_CURRENT) || iter.getIndex(&iter, UITER_CURRENT)!=0 || | |
1466 | iter.hasNext(&iter) || iter.hasPrevious(&iter) | |
1467 | ) { | |
1468 | log_err("NOOP UCharIterator behaves unexpectedly\n"); | |
1469 | } | |
1470 | ||
1471 | /* test get/set state */ | |
1472 | length=LENGTHOF(text)-1; | |
1473 | uiter_setString(&iter1, text, -1); | |
1474 | uiter_setString(&iter2, text, length); | |
1475 | testIteratorState(&iter1, &iter2, "UTF16IteratorState", length/2); | |
1476 | testIteratorState(&iter1, &iter2, "UTF16IteratorStatePlus1", length/2+1); | |
1477 | ||
1478 | /* compare the same string between UTF-16 and UTF-8 UCharIterators ------ */ | |
1479 | errorCode=U_ZERO_ERROR; | |
1480 | u_strToUTF8(bytes, sizeof(bytes), &length, text, -1, &errorCode); | |
1481 | if(U_FAILURE(errorCode)) { | |
1482 | log_err("u_strToUTF8() failed, %s\n", u_errorName(errorCode)); | |
1483 | return; | |
1484 | } | |
1485 | ||
1486 | uiter_setString(&iter1, text, -1); | |
1487 | uiter_setUTF8(&iter2, bytes, length); | |
1488 | compareIterators(&iter1, "UTF16Iterator", &iter2, "UTF8Iterator"); | |
1489 | ||
1490 | /* try again with length=-1 */ | |
1491 | uiter_setUTF8(&iter2, bytes, -1); | |
1492 | compareIterators(&iter1, "UTF16Iterator", &iter2, "UTF8Iterator_1"); | |
1493 | ||
1494 | /* test get/set state */ | |
1495 | length=LENGTHOF(text)-1; | |
1496 | uiter_setUTF8(&iter1, bytes, -1); | |
1497 | testIteratorState(&iter1, &iter2, "UTF8IteratorState", length/2); | |
1498 | testIteratorState(&iter1, &iter2, "UTF8IteratorStatePlus1", length/2+1); | |
1499 | ||
1500 | /* compare the same string between UTF-16 and UTF-16BE UCharIterators --- */ | |
1501 | errorCode=U_ZERO_ERROR; | |
1502 | cnv=ucnv_open("UTF-16BE", &errorCode); | |
1503 | length=ucnv_fromUChars(cnv, bytes, sizeof(bytes), text, -1, &errorCode); | |
1504 | ucnv_close(cnv); | |
1505 | if(U_FAILURE(errorCode)) { | |
1506 | log_err("ucnv_fromUChars(UTF-16BE) failed, %s\n", u_errorName(errorCode)); | |
1507 | return; | |
1508 | } | |
1509 | ||
1510 | /* terminate with a _pair_ of 0 bytes - a UChar NUL in UTF-16BE (length is known to be ok) */ | |
1511 | bytes[length]=bytes[length+1]=0; | |
1512 | ||
1513 | uiter_setString(&iter1, text, -1); | |
1514 | uiter_setUTF16BE(&iter2, bytes, length); | |
1515 | compareIterators(&iter1, "UTF16Iterator", &iter2, "UTF16BEIterator"); | |
1516 | ||
1517 | /* try again with length=-1 */ | |
1518 | uiter_setUTF16BE(&iter2, bytes, -1); | |
1519 | compareIterators(&iter1, "UTF16Iterator", &iter2, "UTF16BEIterator_1"); | |
1520 | ||
1521 | /* try again after moving the bytes up one, and with length=-1 */ | |
1522 | memmove(bytes+1, bytes, length+2); | |
1523 | uiter_setUTF16BE(&iter2, bytes+1, -1); | |
1524 | compareIterators(&iter1, "UTF16Iterator", &iter2, "UTF16BEIteratorMoved1"); | |
1525 | ||
1526 | /* ### TODO test other iterators: CharacterIterator, Replaceable */ | |
1527 | } | |
1528 | ||
1529 | #if UCONFIG_NO_COLLATION | |
1530 | ||
1531 | static void | |
1532 | TestUNormIterator() { | |
1533 | /* test nothing */ | |
1534 | } | |
1535 | ||
1536 | #else | |
1537 | ||
1538 | #include "unicode/unorm.h" | |
1539 | #include "unorm_it.h" | |
1540 | ||
1541 | /* | |
1542 | * Compare results from two iterators, should be same. | |
1543 | * Assume that the text is not empty and that | |
1544 | * iteration start==0 and iteration limit==length. | |
1545 | * | |
1546 | * Modified version of compareIterators() but does not assume that indexes | |
1547 | * are available. | |
1548 | */ | |
1549 | static void | |
1550 | compareIterNoIndexes(UCharIterator *iter1, const char *n1, | |
1551 | UCharIterator *iter2, const char *n2, | |
1552 | int32_t middle) { | |
1553 | uint32_t state; | |
1554 | int32_t i; | |
1555 | UChar32 c1, c2; | |
1556 | UErrorCode errorCode; | |
1557 | ||
1558 | /* set into the middle */ | |
1559 | iter1->move(iter1, middle, UITER_ZERO); | |
1560 | iter2->move(iter2, middle, UITER_ZERO); | |
1561 | ||
1562 | /* test current() */ | |
1563 | c1=iter1->current(iter1); | |
1564 | c2=iter2->current(iter2); | |
1565 | if(c1!=c2) { | |
1566 | log_err("%s->current()=U+%04x != U+%04x=%s->current() at middle=%d\n", n1, c1, c2, n2, middle); | |
1567 | return; | |
1568 | } | |
1569 | ||
1570 | /* move forward 3 UChars */ | |
1571 | for(i=0; i<3; ++i) { | |
1572 | c1=iter1->next(iter1); | |
1573 | c2=iter2->next(iter2); | |
1574 | if(c1!=c2) { | |
1575 | log_err("%s->next()=U+%04x != U+%04x=%s->next() at %d (started in middle)\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1576 | return; | |
1577 | } | |
1578 | } | |
1579 | ||
1580 | /* move backward 5 UChars */ | |
1581 | for(i=0; i<5; ++i) { | |
1582 | c1=iter1->previous(iter1); | |
1583 | c2=iter2->previous(iter2); | |
1584 | if(c1!=c2) { | |
1585 | log_err("%s->previous()=U+%04x != U+%04x=%s->previous() at %d (started in middle)\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1586 | return; | |
1587 | } | |
1588 | } | |
1589 | ||
1590 | /* iterate forward from the beginning */ | |
1591 | iter1->move(iter1, 0, UITER_START); | |
1592 | if(!iter1->hasNext(iter1)) { | |
1593 | log_err("%s->hasNext() at the start returns FALSE\n", n1); | |
1594 | return; | |
1595 | } | |
1596 | ||
1597 | iter2->move(iter2, 0, UITER_START); | |
1598 | if(!iter2->hasNext(iter2)) { | |
1599 | log_err("%s->hasNext() at the start returns FALSE\n", n2); | |
1600 | return; | |
1601 | } | |
1602 | ||
1603 | do { | |
1604 | c1=iter1->next(iter1); | |
1605 | c2=iter2->next(iter2); | |
1606 | if(c1!=c2) { | |
1607 | log_err("%s->next()=U+%04x != U+%04x=%s->next() at %d\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1608 | return; | |
1609 | } | |
1610 | } while(c1>=0); | |
1611 | ||
1612 | if(iter1->hasNext(iter1)) { | |
1613 | log_err("%s->hasNext() at the end returns TRUE\n", n1); | |
1614 | return; | |
1615 | } | |
1616 | if(iter2->hasNext(iter2)) { | |
1617 | log_err("%s->hasNext() at the end returns TRUE\n", n2); | |
1618 | return; | |
1619 | } | |
1620 | ||
1621 | /* back to the middle */ | |
1622 | iter1->move(iter1, middle, UITER_ZERO); | |
1623 | iter2->move(iter2, middle, UITER_ZERO); | |
1624 | ||
1625 | /* try get/set state */ | |
1626 | while((state=uiter_getState(iter2))==UITER_NO_STATE) { | |
1627 | if(!iter2->hasNext(iter2)) { | |
1628 | log_err("%s has no known state from middle=%d to the end\n", n2, middle); | |
1629 | return; | |
1630 | } | |
1631 | iter2->next(iter2); | |
1632 | } | |
1633 | ||
1634 | errorCode=U_ZERO_ERROR; | |
1635 | ||
1636 | c2=iter2->current(iter2); | |
1637 | iter2->move(iter2, 0, UITER_ZERO); | |
1638 | uiter_setState(iter2, state, &errorCode); | |
1639 | c1=iter2->current(iter2); | |
1640 | if(U_FAILURE(errorCode) || c1!=c2) { | |
1641 | log_err("%s->current() differs across get/set state, U+%04x vs. U+%04x\n", n2, c2, c1); | |
1642 | return; | |
1643 | } | |
1644 | ||
1645 | c2=iter2->previous(iter2); | |
1646 | iter2->move(iter2, 0, UITER_ZERO); | |
1647 | uiter_setState(iter2, state, &errorCode); | |
1648 | c1=iter2->previous(iter2); | |
1649 | if(U_FAILURE(errorCode) || c1!=c2) { | |
1650 | log_err("%s->previous() differs across get/set state, U+%04x vs. U+%04x\n", n2, c2, c1); | |
1651 | return; | |
1652 | } | |
1653 | ||
1654 | /* iterate backward from the end */ | |
1655 | iter1->move(iter1, 0, UITER_LIMIT); | |
1656 | if(!iter1->hasPrevious(iter1)) { | |
1657 | log_err("%s->hasPrevious() at the end returns FALSE\n", n1); | |
1658 | return; | |
1659 | } | |
1660 | ||
1661 | iter2->move(iter2, 0, UITER_LIMIT); | |
1662 | if(!iter2->hasPrevious(iter2)) { | |
1663 | log_err("%s->hasPrevious() at the end returns FALSE\n", n2); | |
1664 | return; | |
1665 | } | |
1666 | ||
1667 | do { | |
1668 | c1=iter1->previous(iter1); | |
1669 | c2=iter2->previous(iter2); | |
1670 | if(c1!=c2) { | |
1671 | log_err("%s->previous()=U+%04x != U+%04x=%s->previous() at %d\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT)); | |
1672 | return; | |
1673 | } | |
1674 | } while(c1>=0); | |
1675 | ||
1676 | if(iter1->hasPrevious(iter1)) { | |
1677 | log_err("%s->hasPrevious() at the start returns TRUE\n", n1); | |
1678 | return; | |
1679 | } | |
1680 | if(iter2->hasPrevious(iter2)) { | |
1681 | log_err("%s->hasPrevious() at the start returns TRUE\n", n2); | |
1682 | return; | |
1683 | } | |
1684 | } | |
1685 | ||
1686 | /* n2 must have a digit 1 at the end, will be incremented with the normalization mode */ | |
1687 | static void | |
1688 | testUNormIteratorWithText(const UChar *text, int32_t textLength, int32_t middle, | |
1689 | const char *name1, const char *n2) { | |
1690 | UChar buffer[300]; | |
1691 | char name2[40]; | |
1692 | ||
1693 | UCharIterator iter1, iter2, *iter; | |
1694 | UNormIterator *uni; | |
1695 | ||
1696 | UNormalizationMode mode; | |
1697 | UErrorCode errorCode; | |
1698 | int32_t length; | |
1699 | ||
1700 | /* open a normalizing iterator */ | |
1701 | errorCode=U_ZERO_ERROR; | |
1702 | uni=unorm_openIter(NULL, 0, &errorCode); | |
1703 | if(U_FAILURE(errorCode)) { | |
1704 | log_err("unorm_openIter() fails: %s\n", u_errorName(errorCode)); | |
1705 | return; | |
1706 | } | |
1707 | ||
1708 | /* set iterator 2 to the original text */ | |
1709 | uiter_setString(&iter2, text, textLength); | |
1710 | ||
1711 | strcpy(name2, n2); | |
1712 | ||
1713 | /* test the normalizing iterator for each mode */ | |
1714 | for(mode=UNORM_NONE; mode<UNORM_MODE_COUNT; ++mode) { | |
1715 | length=unorm_normalize(text, textLength, mode, 0, buffer, LENGTHOF(buffer), &errorCode); | |
1716 | if(U_FAILURE(errorCode)) { | |
1717 | log_err("unorm_normalize(mode %d) failed: %s\n", mode, u_errorName(errorCode)); | |
1718 | break; | |
1719 | } | |
1720 | ||
1721 | /* set iterator 1 to the normalized text */ | |
1722 | uiter_setString(&iter1, buffer, length); | |
1723 | ||
1724 | /* set the normalizing iterator to use iter2 */ | |
1725 | iter=unorm_setIter(uni, &iter2, mode, &errorCode); | |
1726 | if(U_FAILURE(errorCode)) { | |
1727 | log_err("unorm_setIter(mode %d) failed: %s\n", mode, u_errorName(errorCode)); | |
1728 | break; | |
1729 | } | |
1730 | ||
1731 | compareIterNoIndexes(&iter1, name1, iter, name2, middle); | |
1732 | ++name2[strlen(name2)-1]; | |
1733 | } | |
1734 | ||
1735 | unorm_closeIter(uni); | |
1736 | } | |
1737 | ||
1738 | static void | |
1739 | TestUNormIterator() { | |
1740 | static const UChar text[]={ /* must contain <00C5 0327> see u_strchr() below */ | |
1741 | 0x61, /* 'a' */ | |
1742 | 0xe4, 0x61, 0x308, /* variations of 'a'+umlaut */ | |
1743 | 0xc5, 0x327, 0x41, 0x30a, 0x327, 0x41, 0x327, 0x30a, /* variations of 'A'+ring+cedilla */ | |
1744 | 0xfb03, 0xfb00, 0x69, 0x66, 0x66, 0x69, 0x66, 0xfb01 /* variations of 'ffi' */ | |
1745 | }; | |
1746 | static const UChar surrogateText[]={ | |
1747 | 0x6e, 0xd900, 0x6a, 0xdc00, 0xd900, 0xdc00, 0x61 | |
1748 | }; | |
1749 | ||
1750 | UChar longText[300]; | |
1751 | int32_t i, middle, length; | |
1752 | ||
1753 | length=LENGTHOF(text); | |
1754 | testUNormIteratorWithText(text, length, length/2, "UCharIter", "UNormIter1"); | |
1755 | testUNormIteratorWithText(text, length, length, "UCharIterEnd", "UNormIterEnd1"); | |
1756 | ||
1757 | /* test again, this time with an insane string to cause internal buffer overflows */ | |
1758 | middle=u_strchr(text, 0x327)-text; /* see comment at text[] */ | |
1759 | memcpy(longText, text, middle*U_SIZEOF_UCHAR); | |
1760 | for(i=0; i<150; ++i) { | |
1761 | longText[middle+i]=0x30a; /* insert many rings between 'A-ring' and cedilla */ | |
1762 | } | |
1763 | memcpy(longText+middle+i, text+middle, (LENGTHOF(text)-middle)*U_SIZEOF_UCHAR); | |
1764 | ||
1765 | length=LENGTHOF(text)+i; | |
1766 | testUNormIteratorWithText(longText, length, length/2, "UCharIterLong", "UNormIterLong1"); | |
1767 | testUNormIteratorWithText(longText, length, length, "UCharIterLongEnd", "UNormIterLongEnd1"); | |
1768 | ||
1769 | length=LENGTHOF(surrogateText); | |
1770 | testUNormIteratorWithText(surrogateText, length, length/2, "UCharIterSurr", "UNormIterSurr1"); | |
1771 | testUNormIteratorWithText(surrogateText, length, length, "UCharIterSurrEnd", "UNormIterSurrEnd1"); | |
1772 | } | |
1773 | ||
1774 | #endif |