VirtualBox

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 43363

Last change on this file since 43363 was 40123, checked in by vboxsync, 13 years ago

Runtime/strings: add Utf-8 and Utf-16 sanitising to a white list of characters. Use ranges not individual code points for the white list.
  • Property svn:eol-style set to native
  • Property svn:keywords set to Id
File size: 54.7 KB
Line 
1/* $Id: tstUtf8.cpp 40123 2012-02-14 11:16:58Z vboxsync $ */
2/** @file
3 * IPRT Testcase - UTF-8 and UTF-16 string conversions.
4 */
5
6/*
7 * Copyright (C) 2006-2007 Oracle Corporation
8 *
9 * This file is part of VirtualBox Open Source Edition (OSE), as
10 * available from http://www.virtualbox.org. This file is free software;
11 * you can redistribute it and/or modify it under the terms of the GNU
12 * General Public License (GPL) as published by the Free Software
13 * Foundation, in version 2 as it comes in the "COPYING" file of the
14 * VirtualBox OSE distribution. VirtualBox OSE is distributed in the
15 * hope that it will be useful, but WITHOUT ANY WARRANTY of any kind.
16 *
17 * The contents of this file may alternatively be used under the terms
18 * of the Common Development and Distribution License Version 1.0
19 * (CDDL) only, as it comes in the "COPYING.CDDL" file of the
20 * VirtualBox OSE distribution, in which case the provisions of the
21 * CDDL are applicable instead of those of the GPL.
22 *
23 * You may elect to license modified versions of this file under the
24 * terms and conditions of either the GPL or the CDDL or both.
25 */
26
27/*******************************************************************************
28* Header Files *
29*******************************************************************************/
30#include <iprt/string.h>
31
32#include <iprt/uni.h>
33#include <iprt/uuid.h>
34#include <iprt/time.h>
35#include <iprt/stream.h>
36#include <iprt/alloc.h>
37#include <iprt/assert.h>
38#include <iprt/err.h>
39#include <iprt/rand.h>
40#include <iprt/test.h>
41
42
43
44/**
45 * Generate a random codepoint for simple UTF-16 encoding.
46 */
47static RTUTF16 GetRandUtf16(void)
48{
49 RTUTF16 wc;
50 do
51 {
52 wc = (RTUTF16)RTRandU32Ex(1, 0xffff);
53 } while (wc >= 0xd800 && wc <= 0xdfff);
54 return wc;
55}
56
57
58/**
59 *
60 */
61static void test1(RTTEST hTest)
62{
63 static const char s_szBadString1[] = "Bad \xe0\x13\x0";
64 static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
65 int rc;
66 char *pszUtf8;
67 char *pszCurrent;
68 PRTUTF16 pwsz;
69 PRTUTF16 pwszRand;
70
71 /*
72 * Invalid UTF-8 to UCS-2 test.
73 */
74 RTTestSub(hTest, "Feeding bad UTF-8 to RTStrToUtf16");
75 rc = RTStrToUtf16(s_szBadString1, &pwsz);
76 RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION || rc == VERR_INVALID_UTF8_ENCODING,
77 (hTest, "Conversion of first bad UTF-8 string to UTF-16 apparently succeeded. It shouldn't. rc=%Rrc\n", rc));
78 rc = RTStrToUtf16(s_szBadString2, &pwsz);
79 RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION || rc == VERR_INVALID_UTF8_ENCODING,
80 (hTest, "Conversion of second bad UTF-8 strings to UTF-16 apparently succeeded. It shouldn't. rc=%Rrc\n", rc));
81
82 /*
83 * Test current CP conversion.
84 */
85 RTTestSub(hTest, "Rand UTF-16 -> UTF-8 -> CP -> UTF-8");
86 pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
87 for (int i = 0; i < 30; i++)
88 pwszRand[i] = GetRandUtf16();
89 pwszRand[30] = 0;
90
91 rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
92 if (rc == VINF_SUCCESS)
93 {
94 rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
95 if (rc == VINF_SUCCESS)
96 {
97 rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
98 if (rc == VINF_SUCCESS)
99 RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
100 else
101 RTTestFailed(hTest, "%d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
102 __LINE__, rc);
103 }
104 else if (rc == VERR_NO_TRANSLATION)
105 RTTestPassed(hTest, "The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 returned VERR_NO_TRANSLATION. This is probably as it should be.\n");
106 else
107 RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
108 __LINE__, rc);
109 }
110 else
111 RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
112 __LINE__, rc);
113
114 /*
115 * Generate a new random string.
116 */
117 RTTestSub(hTest, "Random UTF-16 -> UTF-8 -> UTF-16");
118 pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
119 for (int i = 0; i < 30; i++)
120 pwszRand[i] = GetRandUtf16();
121 pwszRand[30] = 0;
122 rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
123 if (rc == VINF_SUCCESS)
124 {
125 rc = RTStrToUtf16(pszUtf8, &pwsz);
126 if (rc == VINF_SUCCESS)
127 {
128 int i;
129 for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
130 /* nothing */;
131 if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
132 RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
133 else
134 {
135 RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.", __LINE__);
136 RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
137 }
138 }
139 else
140 RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
141 __LINE__, rc);
142 }
143 else
144 RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
145 __LINE__, rc);
146
147 /*
148 * Generate yet another random string and convert it to a buffer.
149 */
150 RTTestSub(hTest, "Random RTUtf16ToUtf8Ex + RTStrToUtf16");
151 pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
152 for (int i = 0; i < 30; i++)
153 pwszRand[i] = GetRandUtf16();
154 pwszRand[30] = 0;
155
156 char szUtf8Array[120];
157 char *pszUtf8Array = szUtf8Array;
158 rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
159 if (rc == 0)
160 {
161 rc = RTStrToUtf16(pszUtf8Array, &pwsz);
162 if (rc == 0)
163 {
164 int i;
165 for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
166 ;
167 if (pwsz[i] == 0 && i >= 8)
168 RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
169 else
170 {
171 RTTestFailed(hTest, "%d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
172 RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
173 }
174 }
175 else
176 RTTestFailed(hTest, "%d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
177 }
178 else
179 RTTestFailed(hTest, "%d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
180
181 /*
182 * And again.
183 */
184 RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
185 pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
186 for (int i = 0; i < 30; i++)
187 pwszRand[i] = GetRandUtf16();
188 pwszRand[30] = 0;
189
190 RTUTF16 wszBuf[70];
191 PRTUTF16 pwsz2Buf = wszBuf;
192 rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
193 if (rc == 0)
194 {
195 rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
196 if (rc == 0)
197 {
198 int i;
199 for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++)
200 ;
201 if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
202 RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
203 else
204 {
205 RTTestFailed(hTest, "%d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
206 RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
207 }
208 }
209 else
210 RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
211 }
212 else
213 RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
214 __LINE__, rc);
215 pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
216 for (int i = 0; i < 30; i++)
217 pwszRand[i] = GetRandUtf16();
218 pwszRand[30] = 0;
219
220 rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
221 if (rc == VERR_BUFFER_OVERFLOW)
222 RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
223 else
224 RTTestFailed(hTest, "%d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
225 __LINE__, rc);
226
227 /*
228 * last time...
229 */
230 RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
231 pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
232 for (int i = 0; i < 30; i++)
233 pwszRand[i] = GetRandUtf16();
234 pwszRand[30] = 0;
235
236 rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
237 if (rc == VINF_SUCCESS)
238 {
239 rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
240 if (rc == VERR_BUFFER_OVERFLOW)
241 RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
242 else
243 RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer returned value %Rrc instead of VERR_BUFFER_OVERFLOW.\n",
244 __LINE__, rc);
245 }
246 else
247 RTTestFailed(hTest, "%d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
248 __LINE__, rc);
249
250
251 RTTestSubDone(hTest);
252}
253
254
255static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
256static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
257static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
258
259static void whereami(int cBits, size_t off)
260{
261 if (cBits == 8)
262 {
263 if (off < 0x7f)
264 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", off + 1);
265 else if (off < 0xf7f)
266 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
267 else if (off < 0x27f7f)
268 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
269 else if (off < 0x2df79)
270 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
271 else if (off < 0x42df79)
272 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
273 else
274 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 ???\n");
275 }
276 else if (cBits == 16)
277 {
278 if (off < 0xd7ff*2)
279 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", off / 2 + 1);
280 else if (off < 0xf7fd*2)
281 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
282 else if (off < 0x20f7fd)
283 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
284 else
285 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 ???\n");
286 }
287 else
288 {
289 if (off < (0xd800 - 1) * sizeof(RTUNICP))
290 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
291 else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
292 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
293 else
294 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
295 }
296}
297
298int mymemcmp(const void *pv1, const void *pv2, size_t cb, int cBits)
299{
300 const uint8_t *pb1 = (const uint8_t *)pv1;
301 const uint8_t *pb2 = (const uint8_t *)pv2;
302 for (size_t off = 0; off < cb; off++)
303 {
304 if (pb1[off] != pb2[off])
305 {
306 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "mismatch at %#x: ", off);
307 whereami(cBits, off);
308 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
309 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
310 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
311 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
312 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
313 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
314 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
315 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
316 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
317 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
318 RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
319 return 1;
320 }
321 }
322 return 0;
323}
324
325
326void InitStrings()
327{
328 /*
329 * Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
330 */
331 /* the simple code point array first */
332 unsigned i = 0;
333 RTUNICP uc = 1;
334 while (uc < 0xd800)
335 g_uszAll[i++] = uc++;
336 uc = 0xe000;
337 while (uc < 0xfffe)
338 g_uszAll[i++] = uc++;
339 uc = 0x10000;
340 while (uc < 0x110000)
341 g_uszAll[i++] = uc++;
342 g_uszAll[i++] = 0;
343 Assert(RT_ELEMENTS(g_uszAll) == i);
344
345 /* the utf-16 one */
346 i = 0;
347 uc = 1;
348 //RTPrintf("tstUtf8: %#x=%#x", i, uc);
349 while (uc < 0xd800)
350 g_wszAll[i++] = uc++;
351 uc = 0xe000;
352 //RTPrintf(" %#x=%#x", i, uc);
353 while (uc < 0xfffe)
354 g_wszAll[i++] = uc++;
355 uc = 0x10000;
356 //RTPrintf(" %#x=%#x", i, uc);
357 while (uc < 0x110000)
358 {
359 g_wszAll[i++] = 0xd800 | ((uc - 0x10000) >> 10);
360 g_wszAll[i++] = 0xdc00 | ((uc - 0x10000) & 0x3ff);
361 uc++;
362 }
363 //RTPrintf(" %#x=%#x\n", i, uc);
364 g_wszAll[i++] = '\0';
365 Assert(RT_ELEMENTS(g_wszAll) == i);
366
367 /*
368 * The utf-8 one
369 */
370 i = 0;
371 uc = 1;
372 //RTPrintf("tstUtf8: %#x=%#x", i, uc);
373 while (uc < 0x80)
374 g_szAll[i++] = uc++;
375 //RTPrintf(" %#x=%#x", i, uc);
376 while (uc < 0x800)
377 {
378 g_szAll[i++] = 0xc0 | (uc >> 6);
379 g_szAll[i++] = 0x80 | (uc & 0x3f);
380 Assert(!((uc >> 6) & ~0x1f));
381 uc++;
382 }
383 //RTPrintf(" %#x=%#x", i, uc);
384 while (uc < 0xd800)
385 {
386 g_szAll[i++] = 0xe0 | (uc >> 12);
387 g_szAll[i++] = 0x80 | ((uc >> 6) & 0x3f);
388 g_szAll[i++] = 0x80 | (uc & 0x3f);
389 Assert(!((uc >> 12) & ~0xf));
390 uc++;
391 }
392 uc = 0xe000;
393 //RTPrintf(" %#x=%#x", i, uc);
394 while (uc < 0xfffe)
395 {
396 g_szAll[i++] = 0xe0 | (uc >> 12);
397 g_szAll[i++] = 0x80 | ((uc >> 6) & 0x3f);
398 g_szAll[i++] = 0x80 | (uc & 0x3f);
399 Assert(!((uc >> 12) & ~0xf));
400 uc++;
401 }
402 uc = 0x10000;
403 //RTPrintf(" %#x=%#x", i, uc);
404 while (uc < 0x110000)
405 {
406 g_szAll[i++] = 0xf0 | (uc >> 18);
407 g_szAll[i++] = 0x80 | ((uc >> 12) & 0x3f);
408 g_szAll[i++] = 0x80 | ((uc >> 6) & 0x3f);
409 g_szAll[i++] = 0x80 | (uc & 0x3f);
410 Assert(!((uc >> 18) & ~0x7));
411 uc++;
412 }
413 //RTPrintf(" %#x=%#x\n", i, uc);
414 g_szAll[i++] = '\0';
415 Assert(RT_ELEMENTS(g_szAll) == i);
416}
417
418
419void test2(RTTEST hTest)
420{
421 /*
422 * Convert to UTF-8 and back.
423 */
424 RTTestSub(hTest, "UTF-16 -> UTF-8 -> UTF-16");
425 char *pszUtf8;
426 int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
427 if (rc == VINF_SUCCESS)
428 {
429 if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
430 RTTestFailed(hTest, "UTF-16 -> UTF-8 mismatch!");
431
432 PRTUTF16 pwszUtf16;
433 rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
434 if (rc == VINF_SUCCESS)
435 {
436 if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
437 RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
438 RTUtf16Free(pwszUtf16);
439 }
440 else
441 RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
442 RTStrFree(pszUtf8);
443 }
444 else
445 RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
446
447
448 /*
449 * Convert to UTF-16 and back. (just in case the above test fails)
450 */
451 RTTestSub(hTest, "UTF-8 -> UTF-16 -> UTF-8");
452 PRTUTF16 pwszUtf16;
453 rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
454 if (rc == VINF_SUCCESS)
455 {
456 if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
457 RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
458
459 rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
460 if (rc == VINF_SUCCESS)
461 {
462 if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
463 RTTestFailed(hTest, "UTF-16 -> UTF-8 failed compare!");
464 RTStrFree(pszUtf8);
465 }
466 else
467 RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
468 RTUtf16Free(pwszUtf16);
469 }
470 else
471 RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
472
473 /*
474 * Convert UTF-8 to CPs.
475 */
476 RTTestSub(hTest, "UTF-8 -> UNI -> UTF-8");
477 PRTUNICP paCps;
478 rc = RTStrToUni(g_szAll, &paCps);
479 if (rc == VINF_SUCCESS)
480 {
481 if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
482 RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
483
484 size_t cCps;
485 rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, RT_ELEMENTS(g_uszAll), &cCps);
486 if (rc == VINF_SUCCESS)
487 {
488 if (cCps != RT_ELEMENTS(g_uszAll) - 1)
489 RTTestFailed(hTest, "wrong Code Point count %zu, expected %zu\n", cCps, RT_ELEMENTS(g_uszAll) - 1);
490 }
491 else
492 RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
493
494 /** @todo RTCpsToUtf8 or something. */
495 }
496 else
497 RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
498
499 /*
500 * Check the various string lengths.
501 */
502 RTTestSub(hTest, "Lengths");
503 size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
504 size_t cuc2 = RTUtf16Len(g_wszAll);
505 if (cuc1 != cuc2)
506 RTTestFailed(hTest, "cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
507 //size_t cuc3 = RTUniLen(g_uszAll);
508
509
510 /*
511 * Enumerate the strings.
512 */
513 RTTestSub(hTest, "Code Point Getters and Putters");
514 char *pszPut1Base = (char *)RTMemAlloc(sizeof(g_szAll));
515 AssertRelease(pszPut1Base);
516 char *pszPut1 = pszPut1Base;
517 PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
518 AssertRelease(pwszPut2Base);
519 PRTUTF16 pwszPut2 = pwszPut2Base;
520 const char *psz1 = g_szAll;
521 const char *psz2 = g_szAll;
522 PCRTUTF16 pwsz3 = g_wszAll;
523 PCRTUTF16 pwsz4 = g_wszAll;
524 for (;;)
525 {
526 /*
527 * getters
528 */
529 RTUNICP uc1;
530 rc = RTStrGetCpEx(&psz1, &uc1);
531 if (RT_FAILURE(rc))
532 {
533 RTTestFailed(hTest, "RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs", rc, psz2);
534 whereami(8, psz2 - &g_szAll[0]);
535 break;
536 }
537 char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
538 if (pszPrev1 != psz2)
539 {
540 RTTestFailed(hTest, "RTStrPrevCp returned %p expected %p!", pszPrev1, psz2);
541 whereami(8, psz2 - &g_szAll[0]);
542 break;
543 }
544 RTUNICP uc2 = RTStrGetCp(psz2);
545 if (uc2 != uc1)
546 {
547 RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc2, uc1);
548 whereami(8, psz2 - &g_szAll[0]);
549 break;
550 }
551 psz2 = RTStrNextCp(psz2);
552 if (psz2 != psz1)
553 {
554 RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetNext returned different next pointer!");
555 whereami(8, psz2 - &g_szAll[0]);
556 break;
557 }
558
559 RTUNICP uc3;
560 rc = RTUtf16GetCpEx(&pwsz3, &uc3);
561 if (RT_FAILURE(rc))
562 {
563 RTTestFailed(hTest, "RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs", rc, pwsz4);
564 whereami(16, pwsz4 - &g_wszAll[0]);
565 break;
566 }
567 if (uc3 != uc2)
568 {
569 RTTestFailed(hTest, "RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc2);
570 whereami(16, pwsz4 - &g_wszAll[0]);
571 break;
572 }
573 RTUNICP uc4 = RTUtf16GetCp(pwsz4);
574 if (uc3 != uc4)
575 {
576 RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc4);
577 whereami(16, pwsz4 - &g_wszAll[0]);
578 break;
579 }
580 pwsz4 = RTUtf16NextCp(pwsz4);
581 if (pwsz4 != pwsz3)
582 {
583 RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!");
584 whereami(8, pwsz4 - &g_wszAll[0]);
585 break;
586 }
587
588
589 /*
590 * putters
591 */
592 pszPut1 = RTStrPutCp(pszPut1, uc1);
593 if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
594 {
595 RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
596 pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
597 whereami(8, psz2 - &g_szAll[0]);
598 break;
599 }
600
601 pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
602 if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
603 {
604 RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
605 pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
606 whereami(8, pwsz4 - &g_wszAll[0]);
607 break;
608 }
609
610
611 /* the end? */
612 if (!uc1)
613 break;
614 }
615
616 /* check output if we seems to have made it thru it all. */
617 if (psz2 == &g_szAll[sizeof(g_szAll)])
618 {
619 if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
620 RTTestFailed(hTest, "RTStrPutCp encoded the string incorrectly.");
621 if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
622 RTTestFailed(hTest, "RTUtf16PutCp encoded the string incorrectly.");
623 }
624
625 RTMemFree(pszPut1Base);
626 RTMemFree(pwszPut2Base);
627
628 RTTestSubDone(hTest);
629}
630
631
632/**
633 * Check case insensitivity.
634 */
635void test3(RTTEST hTest)
636{
637 RTTestSub(hTest, "Case Sensitivity");
638
639 if ( RTUniCpToLower('a') != 'a'
640 || RTUniCpToLower('A') != 'a'
641 || RTUniCpToLower('b') != 'b'
642 || RTUniCpToLower('B') != 'b'
643 || RTUniCpToLower('Z') != 'z'
644 || RTUniCpToLower('z') != 'z'
645 || RTUniCpToUpper('c') != 'C'
646 || RTUniCpToUpper('C') != 'C'
647 || RTUniCpToUpper('z') != 'Z'
648 || RTUniCpToUpper('Z') != 'Z')
649 RTTestFailed(hTest, "RTUniToUpper/Lower failed basic tests.\n");
650
651 if (RTUtf16ICmp(g_wszAll, g_wszAll))
652 RTTestFailed(hTest, "RTUtf16ICmp failed the basic test.\n");
653
654 if (RTUtf16Cmp(g_wszAll, g_wszAll))
655 RTTestFailed(hTest, "RTUtf16Cmp failed the basic test.\n");
656
657 static RTUTF16 s_wszTst1a[] = { 'a', 'B', 'c', 'D', 'E', 'f', 'g', 'h', 'i', 'j', 'K', 'L', 'm', 'N', 'o', 'P', 'q', 'r', 'S', 't', 'u', 'V', 'w', 'x', 'Y', 'Z', 0xc5, 0xc6, 0xf8, 0 };
658 static RTUTF16 s_wszTst1b[] = { 'A', 'B', 'c', 'd', 'e', 'F', 'G', 'h', 'i', 'J', 'k', 'l', 'M', 'n', 'O', 'p', 'Q', 'R', 's', 't', 'U', 'v', 'w', 'X', 'y', 'z', 0xe5, 0xe6, 0xd8, 0 };
659 if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
660 || RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
661 || RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
662 || RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
663 )
664 RTTestFailed(hTest, "RTUtf16ICmp failed the alphabet test.\n");
665
666 if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
667 || RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
668 || !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
669 || !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
670 )
671 RTTestFailed(hTest, "RTUtf16Cmp failed the alphabet test.\n");
672
673 RTTestSubDone(hTest);
674}
675
676
677/**
678 * Test the RTStr*Cmp functions.
679 */
680void TstRTStrXCmp(RTTEST hTest)
681{
682#define CHECK_DIFF(expr, op) \
683 do \
684 { \
685 int iDiff = expr; \
686 if (!(iDiff op 0)) \
687 RTTestFailed(hTest, "%d: %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
688 } while (0)
689
690/** @todo test the non-ascii bits. */
691
692 RTTestSub(hTest, "RTStrCmp");
693 CHECK_DIFF(RTStrCmp(NULL, NULL), == );
694 CHECK_DIFF(RTStrCmp(NULL, ""), < );
695 CHECK_DIFF(RTStrCmp("", NULL), > );
696 CHECK_DIFF(RTStrCmp("", ""), == );
697 CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
698 CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
699 CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
700 CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
701 CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
702 CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
703 CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
704
705
706 RTTestSub(hTest, "RTStrNCmp");
707 CHECK_DIFF(RTStrNCmp(NULL, NULL, RTSTR_MAX), == );
708 CHECK_DIFF(RTStrNCmp(NULL, "", RTSTR_MAX), < );
709 CHECK_DIFF(RTStrNCmp("", NULL, RTSTR_MAX), > );
710 CHECK_DIFF(RTStrNCmp("", "", RTSTR_MAX), == );
711 CHECK_DIFF(RTStrNCmp("abcdef", "abcdef", RTSTR_MAX), == );
712 CHECK_DIFF(RTStrNCmp("abcdef", "abcde", RTSTR_MAX), > );
713 CHECK_DIFF(RTStrNCmp("abcde", "abcdef", RTSTR_MAX), < );
714 CHECK_DIFF(RTStrNCmp("abcdeg", "abcdef", RTSTR_MAX), > );
715 CHECK_DIFF(RTStrNCmp("abcdef", "abcdeg", RTSTR_MAX), < );
716 CHECK_DIFF(RTStrNCmp("abcdeF", "abcdef", RTSTR_MAX), < );
717 CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", RTSTR_MAX), > );
718
719 CHECK_DIFF(RTStrNCmp("abcdef", "fedcba", 0), ==);
720 CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 5), ==);
721 CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 6), > );
722
723
724 RTTestSub(hTest, "RTStrICmp");
725 CHECK_DIFF(RTStrICmp(NULL, NULL), == );
726 CHECK_DIFF(RTStrICmp(NULL, ""), < );
727 CHECK_DIFF(RTStrICmp("", NULL), > );
728 CHECK_DIFF(RTStrICmp("", ""), == );
729 CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
730 CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
731 CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
732 CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
733 CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
734
735 CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), ==);
736 CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
737 CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
738 CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
739 CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
740 CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
741 CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
742
743
744
745 RTTestSub(hTest, "RTStrNICmp");
746 CHECK_DIFF(RTStrNICmp(NULL, NULL, RTSTR_MAX), == );
747 CHECK_DIFF(RTStrNICmp(NULL, "", RTSTR_MAX), < );
748 CHECK_DIFF(RTStrNICmp("", NULL, RTSTR_MAX), > );
749 CHECK_DIFF(RTStrNICmp("", "", RTSTR_MAX), == );
750 CHECK_DIFF(RTStrNICmp(NULL, NULL, 0), == );
751 CHECK_DIFF(RTStrNICmp(NULL, "", 0), == );
752 CHECK_DIFF(RTStrNICmp("", NULL, 0), == );
753 CHECK_DIFF(RTStrNICmp("", "", 0), == );
754 CHECK_DIFF(RTStrNICmp("abcdef", "abcdef", RTSTR_MAX), == );
755 CHECK_DIFF(RTStrNICmp("abcdef", "abcde", RTSTR_MAX), > );
756 CHECK_DIFF(RTStrNICmp("abcde", "abcdef", RTSTR_MAX), < );
757 CHECK_DIFF(RTStrNICmp("abcdeg", "abcdef", RTSTR_MAX), > );
758 CHECK_DIFF(RTStrNICmp("abcdef", "abcdeg", RTSTR_MAX), < );
759
760 CHECK_DIFF(RTStrNICmp("abcdeF", "abcdef", RTSTR_MAX), ==);
761 CHECK_DIFF(RTStrNICmp("abcdef", "abcdeF", RTSTR_MAX), ==);
762 CHECK_DIFF(RTStrNICmp("ABCDEF", "abcdef", RTSTR_MAX), ==);
763 CHECK_DIFF(RTStrNICmp("abcdef", "ABCDEF", RTSTR_MAX), ==);
764 CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", RTSTR_MAX), ==);
765 CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", RTSTR_MAX), > );
766 CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", RTSTR_MAX), > ); /* diff performed on the lower case cp. */
767
768 CHECK_DIFF(RTStrNICmp("ABCDEF", "fedcba", 0), ==);
769 CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 5), ==);
770 CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", 5), ==);
771 CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDe", 5), ==);
772 CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDeF", 5), ==);
773 CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDe", 5), ==);
774 CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 6), > );
775 CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", 6), > ); /* diff performed on the lower case cp. */
776 /* We should continue using byte comparison when we hit the invalid CP. Will assert in debug builds. */
777 // CHECK_DIFF(RTStrNICmp("AbCd\xff""eg", "aBcD\xff""eF", 6), ==);
778
779 RTTestSubDone(hTest);
780}
781
782
783
784/**
785 * Check UTF-8 encoding purging.
786 */
787void TstRTStrPurgeEncoding(RTTEST hTest)
788{
789 RTTestSub(hTest, "RTStrPurgeEncoding");
790
791 /*
792 * Test some good strings.
793 */
794 char sz1[] = "1234567890wertyuiopsdfghjklzxcvbnm";
795 char sz1Copy[sizeof(sz1)];
796 memcpy(sz1Copy, sz1, sizeof(sz1));
797
798 RTTESTI_CHECK_RETV(RTStrPurgeEncoding(sz1) == 0);
799 RTTESTI_CHECK_RETV(!memcmp(sz1, sz1Copy, sizeof(sz1)));
800
801 char *pszAll = RTStrDup(g_szAll);
802 if (pszAll)
803 {
804 RTTESTI_CHECK(RTStrPurgeEncoding(pszAll) == 0);
805 RTTESTI_CHECK(!memcmp(pszAll, g_szAll, sizeof(g_szAll)));
806 RTStrFree(pszAll);
807 }
808
809 /*
810 * Test some bad stuff.
811 */
812 struct
813 {
814 size_t cErrors;
815 unsigned char szIn[5];
816 const char *pszExpect;
817 } aTests[] =
818 {
819 { 0, { '1', '2', '3', '4', '\0' }, "1234" },
820 { 1, { 0x80, '2', '3', '4', '\0' }, "?234" },
821 { 1, { '1', 0x80, '3', '4', '\0' }, "1?34" },
822 { 1, { '1', '2', 0x80, '4', '\0' }, "12?4" },
823 { 1, { '1', '2', '3', 0x80, '\0' }, "123?" },
824 { 2, { 0x80, 0x81, '3', '4', '\0' }, "??34" },
825 { 2, { '1', 0x80, 0x81, '4', '\0' }, "1??4" },
826 { 2, { '1', '2', 0x80, 0x81, '\0' }, "12??" },
827 };
828 for (size_t i = 0; i < RT_ELEMENTS(aTests); i++)
829 {
830 size_t cErrors = RTStrPurgeEncoding((char *)aTests[i].szIn);
831 if (cErrors != aTests[i].cErrors)
832 RTTestFailed(hTest, "#%u: cErrors=%u expected %u\n", i, cErrors, aTests[i].cErrors);
833 else if (strcmp((char *)aTests[i].szIn, aTests[i].pszExpect))
834 RTTestFailed(hTest, "#%u: %.5Rhxs expected %.5Rhxs (%s)\n", i, aTests[i].szIn, aTests[i].pszExpect, aTests[i].pszExpect);
835 }
836
837 RTTestSubDone(hTest);
838}
839
840
841/**
842 * Check string sanitising.
843 */
844void TstRTStrPurgeComplementSet(RTTEST hTest)
845{
846 RTTestSub(hTest, "RTStrPurgeComplementSet");
847 RTUNICP aCpSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
848 '\0' };
849 RTUNICP aCpBadSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
850 '7', '\0' }; /* Contains an incomplete pair. */
851 struct
852 {
853 const char *pcszIn;
854 const char *pcszOut;
855 PCRTUNICP pcCpSet;
856 char chReplacement;
857 ssize_t cExpected;
858 }
859 aTests[] =
860 {
861 { "1234werttrew4321", "1234werttrew4321", aCpSet, '_', 0 },
862 { "123654wert\xc2\xa2trew\xe2\x82\xac""4321",
863 "123_54wert__trew___4321", aCpSet, '_', 3 },
864 { "hjhj8766", "????????", aCpSet, '?', 8 },
865 { "123\xf0\xa4\xad\xa2""4", "123____4", aCpSet, '_', 1 },
866 { "\xff", "\xff", aCpSet, '_', -1 },
867 { "____", "____", aCpBadSet, '_', -1 }
868 };
869 enum { MAX_IN_STRING = 256 };
870
871 for (unsigned i = 0; i < RT_ELEMENTS(aTests); ++i)
872 {
873 char szCopy[MAX_IN_STRING];
874 ssize_t cReplacements;
875 AssertRC(RTStrCopy(szCopy, RT_ELEMENTS(szCopy), aTests[i].pcszIn));
876 cReplacements = RTStrPurgeComplementSet(szCopy, aTests[i].pcCpSet,
877 aTests[i].chReplacement);
878 if (cReplacements != aTests[i].cExpected)
879 RTTestFailed(hTest, "#%u: expected %lld, actual %lld\n", i,
880 (long long) aTests[i].cExpected,
881 (long long) cReplacements);
882 if (strcmp(aTests[i].pcszOut, szCopy))
883 RTTestFailed(hTest, "#%u: expected %s, actual %s\n", i,
884 aTests[i].pcszOut, szCopy);
885 }
886}
887
888
889/**
890 * Check string sanitising.
891 */
892void TstRTUtf16PurgeComplementSet(RTTEST hTest)
893{
894 RTTestSub(hTest, "RTUtf16PurgeComplementSet");
895 RTUNICP aCpSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
896 '\0' };
897 RTUNICP aCpBadSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
898 '7', '\0' }; /* Contains an incomplete pair. */
899 struct
900 {
901 const char *pcszIn;
902 const char *pcszOut;
903 size_t cwc; /* Zero means the strings are Utf-8. */
904 PCRTUNICP pcCpSet;
905 char chReplacement;
906 ssize_t cExpected;
907 }
908 aTests[] =
909 {
910 { "1234werttrew4321", "1234werttrew4321", 0, aCpSet, '_', 0 },
911 { "123654wert\xc2\xa2trew\xe2\x82\xac""4321",
912 "123_54wert_trew_4321", 0, aCpSet, '_', 3 },
913 { "hjhj8766", "????????", 0, aCpSet, '?', 8 },
914 { "123\xf0\xa4\xad\xa2""4", "123__4", 0, aCpSet, '_', 1 },
915 { "\xff\xff\0", "\xff\xff\0", 2, aCpSet, '_', -1 },
916 { "\xff\xff\0", "\xff\xff\0", 2, aCpSet, '_', -1 },
917 { "____", "____", 0, aCpBadSet, '_', -1 }
918 };
919 enum { MAX_IN_STRING = 256 };
920
921 for (unsigned i = 0; i < RT_ELEMENTS(aTests); ++i)
922 {
923 RTUTF16 wszInCopy[MAX_IN_STRING], *pwszInCopy = wszInCopy;
924 RTUTF16 wszOutCopy[MAX_IN_STRING], *pwszOutCopy = wszOutCopy;
925 ssize_t cReplacements;
926 if (!aTests[i].cwc)
927 {
928 AssertRC(RTStrToUtf16Ex(aTests[i].pcszIn, RTSTR_MAX, &pwszInCopy,
929 RT_ELEMENTS(wszInCopy), NULL));
930 AssertRC(RTStrToUtf16Ex(aTests[i].pcszOut, RTSTR_MAX, &pwszOutCopy,
931 RT_ELEMENTS(wszOutCopy), NULL));
932 }
933 else
934 {
935 Assert(aTests[i].cwc <= RT_ELEMENTS(wszInCopy));
936 memcpy(wszInCopy, aTests[i].pcszIn, aTests[i].cwc * 2);
937 memcpy(wszOutCopy, aTests[i].pcszOut, aTests[i].cwc * 2);
938 }
939 cReplacements = RTUtf16PurgeComplementSet(wszInCopy, aTests[i].pcCpSet,
940 aTests[i].chReplacement);
941 if (cReplacements != aTests[i].cExpected)
942 RTTestFailed(hTest, "#%u: expected %lld, actual %lld\n", i,
943 (long long) aTests[i].cExpected,
944 (long long) cReplacements);
945 if (RTUtf16Cmp(wszInCopy, wszOutCopy))
946 RTTestFailed(hTest, "#%u: expected %ls, actual %ls\n", i,
947 wszOutCopy, wszInCopy);
948 }
949}
950
951
952/**
953 * Benchmark stuff.
954 */
955void Benchmarks(RTTEST hTest)
956{
957 static union
958 {
959 RTUTF16 wszBuf[sizeof(g_wszAll)];
960 char szBuf[sizeof(g_szAll)];
961 } s_Buf;
962
963 RTTestSub(hTest, "Benchmarks");
964/** @todo add RTTest* methods for reporting benchmark results. */
965 RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTStrToUtf16Ex: "); /** @todo figure this stuff into the test framework. */
966 PRTUTF16 pwsz = &s_Buf.wszBuf[0];
967 int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
968 if (RT_SUCCESS(rc))
969 {
970 int i;
971 uint64_t u64Start = RTTimeNanoTS();
972 for (i = 0; i < 100; i++)
973 {
974 rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
975 if (RT_FAILURE(rc))
976 {
977 RTTestFailed(hTest, "UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
978 break;
979 }
980 }
981 uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
982 RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
983 }
984
985 RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTUtf16ToUtf8Ex: ");
986 char *psz = &s_Buf.szBuf[0];
987 rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
988 if (RT_SUCCESS(rc))
989 {
990 int i;
991 uint64_t u64Start = RTTimeNanoTS();
992 for (i = 0; i < 100; i++)
993 {
994 rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
995 if (RT_FAILURE(rc))
996 {
997 RTTestFailed(hTest, "UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
998 break;
999 }
1000 }
1001 uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
1002 RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
1003 }
1004
1005 RTTestSubDone(hTest);
1006}
1007
1008
1009/**
1010 * Tests RTStrEnd
1011 */
1012static void testStrEnd(RTTEST hTest)
1013{
1014 RTTestSub(hTest, "RTStrEnd");
1015
1016 static char const s_szEmpty[1] = "";
1017 RTTESTI_CHECK(RTStrEnd(s_szEmpty, 0) == NULL);
1018 RTTESTI_CHECK(RTStrEnd(s_szEmpty, 1) == &s_szEmpty[0]);
1019 for (size_t i = 0; i < _1M; i++)
1020 RTTESTI_CHECK(RTStrEnd(s_szEmpty, ~i) == &s_szEmpty[0]);
1021
1022}
1023
1024
1025/**
1026 * Tests RTStrStr and RTStrIStr.
1027 */
1028static void testStrStr(RTTEST hTest)
1029{
1030#define CHECK_NULL(expr) \
1031 do { \
1032 const char *pszRet = expr; \
1033 if (pszRet != NULL) \
1034 RTTestFailed(hTest, "%d: %#x -> %s expected NULL", __LINE__, #expr, pszRet); \
1035 } while (0)
1036
1037#define CHECK(expr, expect) \
1038 do { \
1039 const char *pszRet = expr; \
1040 if ( (pszRet != NULL && (expect) == NULL) \
1041 || (pszRet == NULL && (expect) != NULL) \
1042 || strcmp(pszRet, (expect)) \
1043 ) \
1044 RTTestFailed(hTest, "%d: %#x -> %s expected %s", __LINE__, #expr, pszRet, (expect)); \
1045 } while (0)
1046
1047
1048 RTTestSub(hTest, "RTStrStr");
1049 CHECK(RTStrStr("abcdef", ""), "abcdef");
1050 CHECK_NULL(RTStrStr("abcdef", NULL));
1051 CHECK_NULL(RTStrStr(NULL, ""));
1052 CHECK_NULL(RTStrStr(NULL, NULL));
1053 CHECK(RTStrStr("abcdef", "abcdef"), "abcdef");
1054 CHECK(RTStrStr("abcdef", "b"), "bcdef");
1055 CHECK(RTStrStr("abcdef", "bcdef"), "bcdef");
1056 CHECK(RTStrStr("abcdef", "cdef"), "cdef");
1057 CHECK(RTStrStr("abcdef", "cde"), "cdef");
1058 CHECK(RTStrStr("abcdef", "cd"), "cdef");
1059 CHECK(RTStrStr("abcdef", "c"), "cdef");
1060 CHECK(RTStrStr("abcdef", "f"), "f");
1061 CHECK(RTStrStr("abcdef", "ef"), "ef");
1062 CHECK(RTStrStr("abcdef", "e"), "ef");
1063 CHECK_NULL(RTStrStr("abcdef", "z"));
1064 CHECK_NULL(RTStrStr("abcdef", "A"));
1065 CHECK_NULL(RTStrStr("abcdef", "F"));
1066
1067 RTTestSub(hTest, "RTStrIStr");
1068 CHECK(RTStrIStr("abcdef", ""), "abcdef");
1069 CHECK_NULL(RTStrIStr("abcdef", NULL));
1070 CHECK_NULL(RTStrIStr(NULL, ""));
1071 CHECK_NULL(RTStrIStr(NULL, NULL));
1072 CHECK(RTStrIStr("abcdef", "abcdef"), "abcdef");
1073 CHECK(RTStrIStr("abcdef", "Abcdef"), "abcdef");
1074 CHECK(RTStrIStr("abcdef", "ABcDeF"), "abcdef");
1075 CHECK(RTStrIStr("abcdef", "b"), "bcdef");
1076 CHECK(RTStrIStr("abcdef", "B"), "bcdef");
1077 CHECK(RTStrIStr("abcdef", "bcdef"), "bcdef");
1078 CHECK(RTStrIStr("abcdef", "BCdEf"), "bcdef");
1079 CHECK(RTStrIStr("abcdef", "bCdEf"), "bcdef");
1080 CHECK(RTStrIStr("abcdef", "bcdEf"), "bcdef");
1081 CHECK(RTStrIStr("abcdef", "BcdEf"), "bcdef");
1082 CHECK(RTStrIStr("abcdef", "cdef"), "cdef");
1083 CHECK(RTStrIStr("abcdef", "cde"), "cdef");
1084 CHECK(RTStrIStr("abcdef", "cd"), "cdef");
1085 CHECK(RTStrIStr("abcdef", "c"), "cdef");
1086 CHECK(RTStrIStr("abcdef", "f"), "f");
1087 CHECK(RTStrIStr("abcdeF", "F"), "F");
1088 CHECK(RTStrIStr("abcdef", "F"), "f");
1089 CHECK(RTStrIStr("abcdef", "ef"), "ef");
1090 CHECK(RTStrIStr("EeEef", "e"), "EeEef");
1091 CHECK(RTStrIStr("EeEef", "E"), "EeEef");
1092 CHECK(RTStrIStr("EeEef", "EE"), "EeEef");
1093 CHECK(RTStrIStr("EeEef", "EEE"), "EeEef");
1094 CHECK(RTStrIStr("EeEef", "EEEF"), "eEef");
1095 CHECK_NULL(RTStrIStr("EeEef", "z"));
1096
1097#undef CHECK
1098#undef CHECK_NULL
1099 RTTestSubDone(hTest);
1100}
1101
1102
1103void testUtf8Latin1(RTTEST hTest)
1104{
1105 RTTestSub(hTest, "Latin-1 <-> Utf-8 conversion functions");
1106
1107 /* Test Utf8 -> Latin1 */
1108 size_t cch_szAll = 0;
1109 size_t cbShort = RTStrCalcLatin1Len(g_szAll);
1110 RTTEST_CHECK(hTest, cbShort == 0);
1111 int rc = RTStrCalcLatin1LenEx(g_szAll, 383, &cch_szAll);
1112 RTTEST_CHECK(hTest, (cch_szAll == 255));
1113 rc = RTStrCalcLatin1LenEx(g_szAll, RTSTR_MAX, &cch_szAll);
1114 RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1115 char *psz = NULL;
1116 char szShort[256] = { 0 };
1117 memcpy(szShort, g_szAll, 255);
1118 cbShort = RTStrCalcLatin1Len(szShort);
1119 RTTEST_CHECK(hTest, cbShort == 191);
1120 rc = RTStrToLatin1(szShort, &psz);
1121 RTTEST_CHECK_RC_OK(hTest, rc);
1122 if (RT_SUCCESS(rc))
1123 {
1124 RTTEST_CHECK(hTest, (strlen(psz) == 191));
1125 for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1126 if (psz[i] != (char) j)
1127 {
1128 RTTestFailed(hTest, "conversion of g_szAll to Latin1 failed at position %u\n", i);
1129 break;
1130 }
1131 }
1132 RTStrFree(psz);
1133 rc = RTStrToLatin1(g_szAll, &psz);
1134 RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1135 char sz[512];
1136 char *psz2 = &sz[0];
1137 size_t cchActual = 0;
1138 rc = RTStrToLatin1Ex(g_szAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1139 &cchActual);
1140 RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1141 RTTEST_CHECK_MSG(hTest, cchActual == 0,
1142 (hTest, "cchActual=%lu\n", cchActual));
1143 rc = RTStrToLatin1Ex(g_szAll, 383, &psz2, sizeof(sz),
1144 &cchActual);
1145 RTTEST_CHECK_RC_OK(hTest, rc);
1146 if (RT_SUCCESS(rc))
1147 {
1148 RTTEST_CHECK(hTest, (cchActual == 255));
1149 RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1150 for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1151 if (psz2[i] != (char) j)
1152 {
1153 RTTestFailed(hTest, "second conversion of g_szAll to Latin1 failed at position %u\n", i);
1154 break;
1155 }
1156 }
1157 rc = RTStrToLatin1Ex(g_szAll, 129, &psz2, 128, &cchActual);
1158 RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1159 RTTEST_CHECK_MSG(hTest, cchActual == 128,
1160 (hTest, "cchActual=%lu\n", cchActual));
1161 rc = RTStrToLatin1Ex(g_szAll, 383, &psz, 0, &cchActual);
1162 RTTEST_CHECK_RC_OK(hTest, rc);
1163 if (RT_SUCCESS(rc))
1164 {
1165 RTTEST_CHECK(hTest, (cchActual == 255));
1166 RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1167 for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1168 if ( ((j < 0x100) && (psz[i] != (char) j))
1169 || ((j > 0xff) && psz[i] != '?'))
1170 {
1171 RTTestFailed(hTest, "third conversion of g_szAll to Latin1 failed at position %u\n", i);
1172 break;
1173 }
1174 }
1175 const char *pszBad = "Hello\xDC\xD8";
1176 rc = RTStrToLatin1Ex(pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1177 &cchActual);
1178 RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF8_ENCODING);
1179 RTStrFree(psz);
1180
1181 /* Test Latin1 -> Utf8 */
1182 const char *pszLat1 = "\x01\x20\x40\x80\x81";
1183 RTTEST_CHECK(hTest, RTLatin1CalcUtf8Len(pszLat1) == 7);
1184 rc = RTLatin1CalcUtf8LenEx(pszLat1, 3, &cchActual);
1185 RTTEST_CHECK_RC_OK(hTest, rc);
1186 if (RT_SUCCESS(rc))
1187 RTTEST_CHECK(hTest, cchActual == 3);
1188 rc = RTLatin1CalcUtf8LenEx(pszLat1, RTSTR_MAX, &cchActual);
1189 RTTEST_CHECK_RC_OK(hTest, rc);
1190 if (RT_SUCCESS(rc))
1191 RTTEST_CHECK(hTest, cchActual == 7);
1192 char *pch = NULL;
1193 char ch[8];
1194 char *pch2 = &ch[0];
1195 cchActual = 0;
1196 rc = RTLatin1ToUtf8(pszLat1, &pch);
1197 RTTEST_CHECK_RC_OK(hTest, rc);
1198 if (RT_SUCCESS(rc))
1199 RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1200 RTStrFree(pch);
1201 rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch, 0, &cchActual);
1202 RTTEST_CHECK_RC_OK(hTest, rc);
1203 if (RT_SUCCESS(rc))
1204 {
1205 RTTEST_CHECK(hTest, (cchActual == 7));
1206 RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1207 }
1208 RTStrFree(pch);
1209 rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch, 0, NULL);
1210 RTTEST_CHECK_RC_OK(hTest, rc);
1211 if (RT_SUCCESS(rc))
1212 RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1213 RTStrFree(pch);
1214 rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch2, RT_ELEMENTS(ch),
1215 &cchActual);
1216 RTTEST_CHECK_RC_OK(hTest, rc);
1217 if (RT_SUCCESS(rc))
1218 {
1219 RTTEST_CHECK(hTest, (cchActual == 7));
1220 RTTEST_CHECK(hTest, !strcmp(pch2, "\x01\x20\x40\xC2\x80\xC2\x81"));
1221 }
1222 rc = RTLatin1ToUtf8Ex(pszLat1, 3, &pch2, RT_ELEMENTS(ch),
1223 &cchActual);
1224 RTTEST_CHECK_RC_OK(hTest, rc);
1225 if (RT_SUCCESS(rc))
1226 {
1227 RTTEST_CHECK(hTest, (cchActual == 3));
1228 RTTEST_CHECK(hTest, !strcmp(pch2, "\x01\x20\x40"));
1229 }
1230 rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch2, RT_ELEMENTS(ch) - 1,
1231 &cchActual);
1232 RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1233 RTTEST_CHECK(hTest, (cchActual == 7));
1234 RTTestSubDone(hTest);
1235}
1236
1237
1238void testUtf16Latin1(RTTEST hTest)
1239{
1240 RTTestSub(hTest, "Latin-1 <-> Utf-16 conversion functions");
1241
1242 /* Test Utf16 -> Latin1 */
1243 size_t cch_szAll = 0;
1244 size_t cbShort = RTUtf16CalcLatin1Len(g_wszAll);
1245 RTTEST_CHECK(hTest, cbShort == 0);
1246 int rc = RTUtf16CalcLatin1LenEx(g_wszAll, 255, &cch_szAll);
1247 RTTEST_CHECK(hTest, (cch_szAll == 255));
1248 rc = RTUtf16CalcLatin1LenEx(g_wszAll, RTSTR_MAX, &cch_szAll);
1249 RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1250 char *psz = NULL;
1251 RTUTF16 wszShort[256] = { 0 };
1252 for (unsigned i = 0; i < 255; ++i)
1253 wszShort[i] = i + 1;
1254 cbShort = RTUtf16CalcLatin1Len(wszShort);
1255 RTTEST_CHECK(hTest, cbShort == 255);
1256 rc = RTUtf16ToLatin1(wszShort, &psz);
1257 RTTEST_CHECK_RC_OK(hTest, rc);
1258 if (RT_SUCCESS(rc))
1259 {
1260 RTTEST_CHECK(hTest, (strlen(psz) == 255));
1261 for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1262 if (psz[i] != (char) j)
1263 {
1264 RTTestFailed(hTest, "conversion of g_wszAll to Latin1 failed at position %u\n", i);
1265 break;
1266 }
1267 }
1268 RTStrFree(psz);
1269 rc = RTUtf16ToLatin1(g_wszAll, &psz);
1270 RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1271 char sz[512];
1272 char *psz2 = &sz[0];
1273 size_t cchActual = 0;
1274 rc = RTUtf16ToLatin1Ex(g_wszAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1275 &cchActual);
1276 RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1277 RTTEST_CHECK_MSG(hTest, cchActual == 0,
1278 (hTest, "cchActual=%lu\n", cchActual));
1279 rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz2, sizeof(sz),
1280 &cchActual);
1281 RTTEST_CHECK_RC_OK(hTest, rc);
1282 if (RT_SUCCESS(rc))
1283 {
1284 RTTEST_CHECK(hTest, (cchActual == 255));
1285 RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1286 for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1287 if (psz2[i] != (char) j)
1288 {
1289 RTTestFailed(hTest, "second conversion of g_wszAll to Latin1 failed at position %u\n", i);
1290 break;
1291 }
1292 }
1293 rc = RTUtf16ToLatin1Ex(g_wszAll, 128, &psz2, 128, &cchActual);
1294 RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1295 RTTEST_CHECK_MSG(hTest, cchActual == 128,
1296 (hTest, "cchActual=%lu\n", cchActual));
1297 rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz, 0, &cchActual);
1298 RTTEST_CHECK_RC_OK(hTest, rc);
1299 if (RT_SUCCESS(rc))
1300 {
1301 RTTEST_CHECK(hTest, (cchActual == 255));
1302 RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1303 for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1304 if ( ((j < 0x100) && (psz[i] != (char) j))
1305 || ((j > 0xff) && psz[i] != '?'))
1306 {
1307 RTTestFailed(hTest, "third conversion of g_wszAll to Latin1 failed at position %u\n", i);
1308 break;
1309 }
1310 }
1311 const char *pszBad = "H\0e\0l\0l\0o\0\0\xDC\0\xD8\0";
1312 rc = RTUtf16ToLatin1Ex((RTUTF16 *) pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1313 &cchActual);
1314 RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF16_ENCODING);
1315 RTStrFree(psz);
1316
1317 /* Test Latin1 -> Utf16 */
1318 const char *pszLat1 = "\x01\x20\x40\x80\x81";
1319 RTTEST_CHECK(hTest, RTLatin1CalcUtf16Len(pszLat1) == 5);
1320 rc = RTLatin1CalcUtf16LenEx(pszLat1, 3, &cchActual);
1321 RTTEST_CHECK_RC_OK(hTest, rc);
1322 if (RT_SUCCESS(rc))
1323 RTTEST_CHECK(hTest, cchActual == 3);
1324 rc = RTLatin1CalcUtf16LenEx(pszLat1, RTSTR_MAX, &cchActual);
1325 RTTEST_CHECK_RC_OK(hTest, rc);
1326 if (RT_SUCCESS(rc))
1327 RTTEST_CHECK(hTest, cchActual == 5);
1328 RTUTF16 *pwc = NULL;
1329 RTUTF16 wc[6];
1330 RTUTF16 *pwc2 = &wc[0];
1331 size_t cwActual = 0;
1332 rc = RTLatin1ToUtf16(pszLat1, &pwc);
1333 RTTEST_CHECK_RC_OK(hTest, rc);
1334 if (RT_SUCCESS(rc))
1335 RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1336 && (pwc[2] == 0x40) && (pwc[3] == 0x80)
1337 && (pwc[4] == 0x81) && (pwc[5] == '\0'));
1338 RTUtf16Free(pwc);
1339 rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, &cwActual);
1340 RTTEST_CHECK_RC_OK(hTest, rc);
1341 if (RT_SUCCESS(rc))
1342 {
1343 RTTEST_CHECK(hTest, (cwActual == 5));
1344 RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1345 && (pwc[2] == 0x40) && (pwc[3] == 0x80)
1346 && (pwc[4] == 0x81) && (pwc[5] == '\0'));
1347 }
1348 RTUtf16Free(pwc);
1349 rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, NULL);
1350 RTTEST_CHECK_RC_OK(hTest, rc);
1351 if (RT_SUCCESS(rc))
1352 RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1353 && (pwc[2] == 0x40) && (pwc[3] == 0x80)
1354 && (pwc[4] == 0x81) && (pwc[5] == '\0'));
1355 RTUtf16Free(pwc);
1356 rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc),
1357 &cwActual);
1358 RTTEST_CHECK_RC_OK(hTest, rc);
1359 if (RT_SUCCESS(rc))
1360 {
1361 RTTEST_CHECK(hTest, (cwActual == 5));
1362 RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1363 && (wc[2] == 0x40) && (wc[3] == 0x80)
1364 && (wc[4] == 0x81) && (wc[5] == '\0'));
1365 }
1366 rc = RTLatin1ToUtf16Ex(pszLat1, 3, &pwc2, RT_ELEMENTS(wc),
1367 &cwActual);
1368 RTTEST_CHECK_RC_OK(hTest, rc);
1369 if (RT_SUCCESS(rc))
1370 {
1371 RTTEST_CHECK(hTest, (cwActual == 3));
1372 RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1373 && (wc[2] == 0x40) && (wc[3] == '\0'));
1374 }
1375 rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc) - 1,
1376 &cwActual);
1377 RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1378 RTTEST_CHECK(hTest, (cwActual == 5));
1379 RTTestSubDone(hTest);
1380}
1381
1382
1383static void testNoTransation(RTTEST hTest)
1384{
1385 /*
1386 * Try trigger a VERR_NO_TRANSLATION error in convert to
1387 * current CP to latin-1.
1388 */
1389 const RTUTF16 s_swzTest1[] = { 0x2358, 0x2242, 0x2357, 0x2359, 0x22f9, 0x2c4e, 0x0030, 0x0060,
1390 0x0092, 0x00c1, 0x00f2, 0x1f80, 0x0088, 0x2c38, 0x2c30, 0x0000 };
1391 char *pszTest1;
1392 int rc = RTUtf16ToUtf8(s_swzTest1, &pszTest1);
1393 RTTESTI_CHECK_RC_RETV(rc, VINF_SUCCESS);
1394
1395 RTTestSub(hTest, "VERR_NO_TRANSLATION/RTStrUtf8ToCurrentCP");
1396 char *pszOut;
1397 rc = RTStrUtf8ToCurrentCP(&pszOut, pszTest1);
1398 if (RT_SUCCESS(rc))
1399 {
1400 RTTESTI_CHECK(!strcmp(pszOut, pszTest1));
1401 RTTestIPrintf(RTTESTLVL_ALWAYS, "CurrentCP is UTF-8 or similar\n");
1402 RTStrFree(pszOut);
1403 }
1404 else
1405 RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1406
1407 RTTestSub(hTest, "VERR_NO_TRANSLATION/RTUtf16ToLatin1");
1408 rc = RTUtf16ToLatin1(s_swzTest1, &pszOut);
1409 RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1410 if (RT_SUCCESS(rc))
1411 RTStrFree(pszOut);
1412
1413 RTStrFree(pszTest1);
1414 RTTestSubDone(hTest);
1415}
1416
1417static void testGetPut(RTTEST hTest)
1418{
1419 /*
1420 * Test RTStrPutCp, RTStrGetCp and RTStrGetCpEx.
1421 */
1422 RTTestSub(hTest, "RTStrPutCp, RTStrGetCp and RTStrGetCpEx");
1423
1424 RTUNICP uc = 0;
1425 while (uc <= 0x10fffd)
1426 {
1427 /* Figure the range - skip illegal ranges. */
1428 RTUNICP ucFirst = uc;
1429 if (ucFirst - UINT32_C(0xd800) <= 0x7ff)
1430 ucFirst = 0xe000;
1431 else if (ucFirst == UINT32_C(0xfffe) || ucFirst == UINT32_C(0xffff))
1432 ucFirst = 0x10000;
1433
1434 RTUNICP ucLast = ucFirst + 1023;
1435 if (ucLast - UINT32_C(0xd800) <= 0x7ff)
1436 ucLast = 0xd7ff;
1437 else if (ucLast == UINT32_C(0xfffe) || ucLast == UINT32_C(0xffff))
1438 ucLast = 0xfffd;
1439
1440 /* Encode the range into a string, decode each code point as we go along. */
1441 char sz1[8192];
1442 char *pszDst = sz1;
1443 for (uc = ucFirst; uc <= ucLast; uc++)
1444 {
1445 char *pszBefore = pszDst;
1446 pszDst = RTStrPutCp(pszDst, uc);
1447 RTTESTI_CHECK(pszBefore - pszDst < 6);
1448
1449 RTUNICP uc2 = RTStrGetCp(pszBefore);
1450 RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1451
1452 const char *pszSrc = pszBefore;
1453 RTUNICP uc3 = 42;
1454 RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1455 RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1456 RTTESTI_CHECK_MSG(pszSrc == pszDst, ("pszSrc=%p pszDst=%p\n", pszSrc, pszDst));
1457 }
1458
1459 /* Decode and re-encode it. */
1460 const char *pszSrc = pszDst = sz1;
1461 for (uc = ucFirst; uc <= ucLast; uc++)
1462 {
1463 RTUNICP uc2 = RTStrGetCp(pszSrc);
1464 RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1465
1466 RTUNICP uc3 = 42;
1467 RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1468 RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1469
1470 pszDst = RTStrPutCp(pszDst, uc);
1471 RTTESTI_CHECK_MSG(pszSrc == pszDst, ("pszSrc=%p pszDst=%p\n", pszSrc, pszDst));
1472 pszSrc = pszDst;
1473 }
1474
1475 /* Decode and wipe it (checking compiler optimizations). */
1476 pszSrc = pszDst = sz1;
1477 for (uc = ucFirst; uc <= ucLast; uc++)
1478 {
1479 RTUNICP uc2 = RTStrGetCp(pszSrc);
1480 RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1481
1482 RTUNICP uc3 = 42;
1483 RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1484 RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1485
1486 pszDst = RTStrPutCp(pszDst, 0);
1487 }
1488
1489 /* advance */
1490 uc = ucLast + 1;
1491 }
1492
1493}
1494
1495
1496int main()
1497{
1498 /*
1499 * Init the runtime, test and say hello.
1500 */
1501 RTTEST hTest;
1502 RTEXITCODE rcExit = RTTestInitAndCreate("tstUtf8", &hTest);
1503 if (rcExit != RTEXITCODE_SUCCESS)
1504 return rcExit;
1505 RTTestBanner(hTest);
1506
1507 /*
1508 * Run the tests.
1509 */
1510 InitStrings();
1511 test1(hTest);
1512 test2(hTest);
1513 test3(hTest);
1514 TstRTStrXCmp(hTest);
1515 TstRTStrPurgeEncoding(hTest);
1516 /* TstRT*PurgeComplementSet test conditions which assert. */
1517 bool fAreQuiet = RTAssertAreQuiet(), fMayPanic = RTAssertMayPanic();
1518 RTAssertSetQuiet(true);
1519 RTAssertSetMayPanic(false);
1520 TstRTStrPurgeComplementSet(hTest);
1521 TstRTUtf16PurgeComplementSet(hTest);
1522 RTAssertSetQuiet(fAreQuiet);
1523 RTAssertSetMayPanic(fMayPanic);
1524 testStrEnd(hTest);
1525 testStrStr(hTest);
1526 testUtf8Latin1(hTest);
1527 testUtf16Latin1(hTest);
1528 testNoTransation(hTest);
1529 testGetPut(hTest);
1530
1531 Benchmarks(hTest);
1532
1533 /*
1534 * Summary
1535 */
1536 return RTTestSummaryAndDestroy(hTest);
1537}
1538
Note: See TracBrowser for help on using the repository browser.

© 2024 Oracle Support Privacy / Do Not Sell My Info Terms of Use Trademark Policy Automated Access Etiquette