tstUtf8.cpp@ 4968

Last change on this file since 4968 was 4071, checked in by vboxsync, 17 years ago
Biggest check-in ever. New source code headers for all (C) innotek files.
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 26.7 KB

Line
1	/* $Id: tstUtf8.cpp 4071 2007-08-07 17:07:59Z vboxsync $ */
2	/** @file
3	* innotek Portable Runtime Testcase - UTF-8 and UTF-16 string conversions.
4	*/
5
6	/*
7	* Copyright (C) 2006-2007 innotek GmbH
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 as published by the Free Software Foundation,
13	* in version 2 as it comes in the "COPYING" file of the VirtualBox OSE
14	* distribution. VirtualBox OSE is distributed in the hope that it will
15	* be useful, but WITHOUT ANY WARRANTY of any kind.
16	*/
17
18	/*******************************************************************************
19	* Header Files *
20	*******************************************************************************/
21	#include <iprt/string.h>
22	#include <iprt/uni.h>
23	#include <iprt/runtime.h>
24	#include <iprt/uuid.h>
25	#include <iprt/time.h>
26	#include <iprt/stream.h>
27	#include <iprt/alloc.h>
28	#include <iprt/assert.h>
29	#include <iprt/err.h>
30
31	#include <stdlib.h>
32
33
34	/*******************************************************************************
35	* Global Variables *
36	*******************************************************************************/
37	static int g_cErrors = 0;
38
39
40	/**
41	* Generate a random codepoint for simple UTF-16 encoding.
42	*/
43	static RTUTF16 GetRandUcs2(void)
44	{
45	RTUTF16 wc;
46	do
47	{
48	wc = (RTUTF16)((long long)rand() * 0xffff / RAND_MAX);
49	} while ((wc >= 0xd800 && wc <= 0xdfff) \|\| wc == 0);
50	return wc;
51	}
52
53
54	/**
55	*
56	*/
57	static void test1(void)
58	{
59	static const char s_szBadString1[] = "Bad \xe0\x13\x0";
60	static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
61	int rc;
62	char *pszUtf8;
63	char *pszCurrent;
64	PRTUTF16 pwsz;
65	PRTUTF16 pwszRand;
66
67	RTPrintf("tstUtf8: TEST 1\n");
68
69	/*
70	* Invalid UTF-8 to UCS-2 test.
71	*/
72	rc = RTStrToUtf16(s_szBadString1, &pwsz);
73	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
74	{
75	RTPrintf("tstUtf8: FAILURE - %d: Conversion of first bad UTF-8 string to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
76	__LINE__, rc);
77	g_cErrors++;
78	}
79	rc = RTStrToUtf16(s_szBadString2, &pwsz);
80	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
81	{
82	RTPrintf("tstUtf8: FAILURE - %d: Conversion of second bad UTF-8 strings to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
83	__LINE__, rc);
84	g_cErrors++;
85	}
86
87	/*
88	* Test current CP convertion.
89	*/
90	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
91	srand((unsigned)RTTimeNanoTS());
92	for (int i = 0; i < 30; i++)
93	pwszRand[i] = GetRandUcs2();
94	pwszRand[30] = 0;
95
96	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
97	if (rc == VINF_SUCCESS)
98	{
99	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
100	if (rc == VINF_SUCCESS)
101	{
102	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
103	if (rc == VINF_SUCCESS)
104	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
105	else
106	{
107	RTPrintf("tstUtf8: FAILURE - %d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
108	__LINE__, rc);
109	g_cErrors++;
110	}
111	}
112	else if (rc == VERR_NO_TRANSLATION)
113	RTPrintf("tstUtf8: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 returned VERR_NO_TRANSLATION. This is probably as it should be.\n");
114	else
115	{
116	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
117	__LINE__, rc);
118	g_cErrors++;
119	}
120	}
121	else
122	{
123	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
124	__LINE__, rc);
125	g_cErrors++;
126	}
127
128	/*
129	* Generate a new random string.
130	*/
131	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
132	srand((unsigned)RTTimeNanoTS());
133	for (int i = 0; i < 30; i++)
134	pwszRand[i] = GetRandUcs2();
135	pwszRand[30] = 0;
136	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
137	if (rc == VINF_SUCCESS)
138	{
139	rc = RTStrToUtf16(pszUtf8, &pwsz);
140	if (rc == VINF_SUCCESS)
141	{
142	int i;
143	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
144	/* nothing */;
145	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
146	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
147	else
148	{
149	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.\n", __LINE__);
150	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
151	g_cErrors++;
152	}
153	}
154	else
155	{
156	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
157	__LINE__, rc);
158	g_cErrors++;
159	}
160	}
161	else
162	{
163	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
164	__LINE__, rc);
165	g_cErrors++;
166	}
167
168	/*
169	* Generate yet another random string and convert it to a buffer.
170	*/
171	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
172	srand((unsigned)RTTimeNanoTS());
173	for (int i = 0; i < 30; i++)
174	pwszRand[i] = GetRandUcs2();
175	pwszRand[30] = 0;
176
177	char szUtf8Array[120];
178	char *pszUtf8Array = szUtf8Array;
179	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
180	if (rc == 0)
181	{
182	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
183	if (rc == 0)
184	{
185	int i;
186	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++);
187	if (pwsz[i] == 0 && i >= 8)
188	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
189	else
190	{
191	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
192	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
193	g_cErrors++;
194	}
195	}
196	else
197	{
198	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
199	__LINE__, rc);
200	g_cErrors++;
201	}
202	}
203	else
204	{
205	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
206	__LINE__, rc);
207	g_cErrors++;
208	}
209
210	/*
211	* And again.
212	*/
213	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
214	srand((unsigned)RTTimeNanoTS());
215	for (int i = 0; i < 30; i++)
216	pwszRand[i] = GetRandUcs2();
217	pwszRand[30] = 0;
218
219	RTUTF16 wszBuf[70];
220	PRTUTF16 pwsz2Buf = wszBuf;
221	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
222	if (rc == 0)
223	{
224	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
225	if (rc == 0)
226	{
227	int i;
228	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++);
229	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
230	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
231	else
232	{
233	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
234	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
235	g_cErrors++;
236	}
237	}
238	else
239	{
240	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
241	__LINE__, rc);
242	g_cErrors++;
243	}
244	}
245	else
246	{
247	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
248	__LINE__, rc);
249	g_cErrors++;
250	}
251	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
252	srand((unsigned)RTTimeNanoTS());
253	for (int i = 0; i < 30; i++)
254	pwszRand[i] = GetRandUcs2();
255	pwszRand[30] = 0;
256
257	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
258	if (rc == VERR_BUFFER_OVERFLOW)
259	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
260	else
261	{
262	RTPrintf("tstUtf8: FAILURE - %d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
263	__LINE__, rc);
264	g_cErrors++;
265	}
266
267	/*
268	* last time...
269	*/
270	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
271	srand((unsigned)RTTimeNanoTS());
272	for (int i = 0; i < 30; i++)
273	pwszRand[i] = GetRandUcs2();
274	pwszRand[30] = 0;
275
276	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
277	if (rc == VINF_SUCCESS)
278	{
279	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
280	if (rc == VERR_BUFFER_OVERFLOW)
281	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
282	else
283	{
284	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer returned value %Vrc instead of VERR_BUFFER_OVERFLOW.\n",
285	__LINE__, rc);
286	g_cErrors++;
287	}
288	}
289	else
290	{
291	RTPrintf("tstUtf8: FAILURE - %d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
292	__LINE__, rc);
293	g_cErrors++;
294	}
295
296	}
297
298
299	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
300	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
301	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
302
303	static void whereami(int cBits, size_t off)
304	{
305	if (cBits == 8)
306	{
307	if (off < 0x7f)
308	RTPrintf("UTF-8 U+%#x\n", off + 1);
309	else if (off < 0xf7f)
310	RTPrintf("UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
311	else if (off < 0x27f7f)
312	RTPrintf("UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
313	else if (off < 0x2df79)
314	RTPrintf("UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
315	else if (off < 0x42df79)
316	RTPrintf("UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
317	else
318	RTPrintf("UTF-8 ???\n");
319	}
320	else if (cBits == 16)
321	{
322	if (off < 0xd7ff*2)
323	RTPrintf("UTF-16 U+%#x\n", off / 2 + 1);
324	else if (off < 0xf7fd*2)
325	RTPrintf("UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
326	else if (off < 0x20f7fd)
327	RTPrintf("UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
328	else
329	RTPrintf("UTF-16 ???\n");
330	}
331	else
332	{
333	if (off < (0xd800 - 1) * sizeof(RTUNICP))
334	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
335	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
336	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
337	else
338	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
339	}
340	}
341
342	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
343	{
344	const uint8_t pb1 = (const uint8_t )pv1;
345	const uint8_t pb2 = (const uint8_t )pv2;
346	for (size_t off = 0; off < cb; off++)
347	{
348	if (pb1[off] != pb2[off])
349	{
350	RTPrintf("mismatch at %#x: ", off);
351	whereami(cBits, off);
352	RTPrintf(" %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
353	RTPrintf("*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
354	RTPrintf(" %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
355	RTPrintf(" %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
356	RTPrintf(" %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
357	RTPrintf(" %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
358	RTPrintf(" %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
359	RTPrintf(" %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
360	RTPrintf(" %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
361	RTPrintf(" %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
362	RTPrintf(" %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
363	return 1;
364	}
365	}
366	return 0;
367	}
368
369
370	void InitStrings(void)
371	{
372	/*
373	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
374	*/
375	/* the simple code point array first */
376	unsigned i = 0;
377	RTUNICP uc = 1;
378	while (uc < 0xd800)
379	g_uszAll[i++] = uc++;
380	uc = 0xe000;
381	while (uc < 0xfffe)
382	g_uszAll[i++] = uc++;
383	uc = 0x10000;
384	while (uc < 0x110000)
385	g_uszAll[i++] = uc++;
386	g_uszAll[i++] = 0;
387	Assert(ELEMENTS(g_uszAll) == i);
388
389	/* the utf-16 one */
390	i = 0;
391	uc = 1;
392	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
393	while (uc < 0xd800)
394	g_wszAll[i++] = uc++;
395	uc = 0xe000;
396	//RTPrintf(" %#x=%#x", i, uc);
397	while (uc < 0xfffe)
398	g_wszAll[i++] = uc++;
399	uc = 0x10000;
400	//RTPrintf(" %#x=%#x", i, uc);
401	while (uc < 0x110000)
402	{
403	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
404	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
405	uc++;
406	}
407	//RTPrintf(" %#x=%#x\n", i, uc);
408	g_wszAll[i++] = '\0';
409	Assert(ELEMENTS(g_wszAll) == i);
410
411	/*
412	* The utf-8 one
413	*/
414	i = 0;
415	uc = 1;
416	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
417	while (uc < 0x80)
418	g_szAll[i++] = uc++;
419	//RTPrintf(" %#x=%#x", i, uc);
420	while (uc < 0x800)
421	{
422	g_szAll[i++] = 0xc0 \| (uc >> 6);
423	g_szAll[i++] = 0x80 \| (uc & 0x3f);
424	Assert(!((uc >> 6) & ~0x1f));
425	uc++;
426	}
427	//RTPrintf(" %#x=%#x", i, uc);
428	while (uc < 0xd800)
429	{
430	g_szAll[i++] = 0xe0 \| (uc >> 12);
431	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
432	g_szAll[i++] = 0x80 \| (uc & 0x3f);
433	Assert(!((uc >> 12) & ~0xf));
434	uc++;
435	}
436	uc = 0xe000;
437	//RTPrintf(" %#x=%#x", i, uc);
438	while (uc < 0xfffe)
439	{
440	g_szAll[i++] = 0xe0 \| (uc >> 12);
441	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
442	g_szAll[i++] = 0x80 \| (uc & 0x3f);
443	Assert(!((uc >> 12) & ~0xf));
444	uc++;
445	}
446	uc = 0x10000;
447	//RTPrintf(" %#x=%#x", i, uc);
448	while (uc < 0x110000)
449	{
450	g_szAll[i++] = 0xf0 \| (uc >> 18);
451	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
452	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
453	g_szAll[i++] = 0x80 \| (uc & 0x3f);
454	Assert(!((uc >> 18) & ~0x7));
455	uc++;
456	}
457	//RTPrintf(" %#x=%#x\n", i, uc);
458	g_szAll[i++] = '\0';
459	Assert(ELEMENTS(g_szAll) == i);
460	}
461
462
463	void test2(void)
464	{
465	RTPrintf("tstUtf8: TEST 2\n");
466
467	/*
468	* Convert to UTF-8 and back.
469	*/
470	RTPrintf("tstUtf8: #1: UTF-16 -> UTF-8 -> UTF-16...\n");
471	char *pszUtf8;
472	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
473	if (rc == VINF_SUCCESS)
474	{
475	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
476	{
477	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 mismatch!\n");
478	g_cErrors++;
479	}
480
481	PRTUTF16 puszUcs2;
482	rc = RTStrToUtf16(pszUtf8, &puszUcs2);
483	if (rc == VINF_SUCCESS)
484	{
485	if (mymemcmp(puszUcs2, g_wszAll, sizeof(g_wszAll), 16))
486	{
487	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed compare!\n");
488	g_cErrors++;
489	}
490	RTUtf16Free(puszUcs2);
491	}
492	else
493	{
494	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
495	g_cErrors++;
496	}
497	RTStrFree(pszUtf8);
498	}
499	else
500	{
501	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
502	g_cErrors++;
503	}
504
505
506	/*
507	* Convert to UTF-16 and back. (just in case the above test fails)
508	*/
509	RTPrintf("tstUtf8: #2: UTF-8 -> UTF-16 -> UTF-8...\n");
510	PRTUTF16 puszUcs2;
511	rc = RTStrToUtf16(&g_szAll[0], &puszUcs2);
512	if (rc == VINF_SUCCESS)
513	{
514	if (mymemcmp(puszUcs2, g_wszAll, sizeof(g_wszAll), 16))
515	{
516	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed compare!\n");
517	g_cErrors++;
518	}
519
520	char *pszUtf8;
521	rc = RTUtf16ToUtf8(puszUcs2, &pszUtf8);
522	if (rc == VINF_SUCCESS)
523	{
524	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
525	{
526	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed compare!\n");
527	g_cErrors++;
528	}
529	RTStrFree(pszUtf8);
530	}
531	else
532	{
533	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
534	g_cErrors++;
535	}
536	RTStrUcs2Free(puszUcs2);
537	}
538	else
539	{
540	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
541	g_cErrors++;
542	}
543
544	/*
545	* Convert UTF-8 to CPs.
546	*/
547	PRTUNICP paCps;
548	rc = RTStrToUni(g_szAll, &paCps);
549	if (rc == VINF_SUCCESS)
550	{
551	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
552	{
553	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
554	g_cErrors++;
555	}
556
557	size_t cCps;
558	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, ELEMENTS(g_uszAll), &cCps);
559	if (rc == VINF_SUCCESS)
560	{
561	if (cCps != ELEMENTS(g_uszAll) - 1)
562	{
563	RTPrintf("tstUtf8: FAILURE - the full #3+: wrong Code Point count %zu, expected %zu\n", cCps, ELEMENTS(g_uszAll) - 1);
564	g_cErrors++;
565	}
566	}
567	else
568	{
569	RTPrintf("tstUtf8: FAILURE - the full #3+: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
570	g_cErrors++;
571	}
572
573	/** @todo RTCpsToUtf8 or something. */
574	}
575	else
576	{
577	RTPrintf("tstUtf8: FAILURE - the full #3a: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
578	g_cErrors++;
579	}
580
581	/*
582	* Check the various string lengths.
583	*/
584	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
585	size_t cuc2 = RTUtf16Len(g_wszAll);
586	if (cuc1 != cuc2)
587	{
588	RTPrintf("tstUtf8: FAILURE - cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
589	g_cErrors++;
590	}
591	//size_t cuc3 = RTUniLen(g_uszAll);
592
593
594	/*
595	* Enumerate the strings.
596	*/
597	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
598	AssertRelease(pszPut1Base);
599	char *pszPut1 = pszPut1Base;
600	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
601	AssertRelease(pwszPut2Base);
602	PRTUTF16 pwszPut2 = pwszPut2Base;
603	const char *psz1 = g_szAll;
604	const char *psz2 = g_szAll;
605	PCRTUTF16 pwsz3 = g_wszAll;
606	PCRTUTF16 pwsz4 = g_wszAll;
607	for (;;)
608	{
609	/*
610	* getters
611	*/
612	RTUNICP uc1;
613	rc = RTStrGetCpEx(&psz1, &uc1);
614	if (RT_FAILURE(rc))
615	{
616	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, psz2);
617	whereami(8, psz2 - &g_szAll[0]);
618	g_cErrors++;
619	break;
620	}
621	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
622	if (pszPrev1 != psz2)
623	{
624	RTPrintf("tstUtf8: FAILURE - RTStrPrevCp returned %p expected %p!\n", pszPrev1, psz2);
625	whereami(8, psz2 - &g_szAll[0]);
626	g_cErrors++;
627	break;
628	}
629	RTUNICP uc2 = RTStrGetCp(psz2);
630	if (uc2 != uc1)
631	{
632	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc2, uc1);
633	whereami(8, psz2 - &g_szAll[0]);
634	g_cErrors++;
635	break;
636	}
637	psz2 = RTStrNextCp(psz2);
638	if (psz2 != psz1)
639	{
640	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetNext returned different next pointer!\n");
641	whereami(8, psz2 - &g_szAll[0]);
642	g_cErrors++;
643	break;
644	}
645
646	RTUNICP uc3;
647	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
648	if (RT_FAILURE(rc))
649	{
650	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, pwsz4);
651	whereami(16, pwsz4 - &g_wszAll[0]);
652	g_cErrors++;
653	break;
654	}
655	if (uc3 != uc2)
656	{
657	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc2);
658	whereami(16, pwsz4 - &g_wszAll[0]);
659	g_cErrors++;
660	break;
661	}
662	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
663	if (uc3 != uc4)
664	{
665	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc4);
666	whereami(16, pwsz4 - &g_wszAll[0]);
667	g_cErrors++;
668	break;
669	}
670	pwsz4 = RTUtf16NextCp(pwsz4);
671	if (pwsz4 != pwsz3)
672	{
673	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!\n");
674	whereami(8, pwsz4 - &g_wszAll[0]);
675	g_cErrors++;
676	break;
677	}
678
679
680	/*
681	* putters
682	*/
683	pszPut1 = RTStrPutCp(pszPut1, uc1);
684	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
685	{
686	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
687	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
688	whereami(8, psz2 - &g_szAll[0]);
689	g_cErrors++;
690	break;
691	}
692
693	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
694	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
695	{
696	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
697	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
698	whereami(8, pwsz4 - &g_wszAll[0]);
699	g_cErrors++;
700	break;
701	}
702
703
704	/* the end? */
705	if (!uc1)
706	break;
707	}
708
709	/* check output if we seems to have made it thru it all. */
710	if (psz2 == &g_szAll[sizeof(g_szAll)])
711	{
712	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
713	{
714	RTPrintf("tstUtf8: FAILURE - RTStrPutCp encoded the string incorrectly.\n");
715	g_cErrors++;
716	}
717	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
718	{
719	RTPrintf("tstUtf8: FAILURE - RTUtf16PutCp encoded the string incorrectly.\n");
720	g_cErrors++;
721	}
722	}
723
724	RTMemFree(pszPut1Base);
725	RTMemFree(pwszPut2Base);
726	}
727
728
729	/**
730	* Check case insensitivity.
731	*/
732	void test3(void)
733	{
734	RTPrintf("tstUtf8: TEST 3\n");
735
736	if ( RTUniCpToLower('a') != 'a'
737	\|\| RTUniCpToLower('A') != 'a'
738	\|\| RTUniCpToLower('b') != 'b'
739	\|\| RTUniCpToLower('B') != 'b'
740	\|\| RTUniCpToLower('Z') != 'z'
741	\|\| RTUniCpToLower('z') != 'z'
742	\|\| RTUniCpToUpper('c') != 'C'
743	\|\| RTUniCpToUpper('C') != 'C'
744	\|\| RTUniCpToUpper('z') != 'Z'
745	\|\| RTUniCpToUpper('Z') != 'Z')
746	{
747	RTPrintf("tstUtf8: FAILURE - RTUniToUpper/Lower failed basic tests.\n");
748	g_cErrors++;
749	}
750
751	if (RTUtf16ICmp(g_wszAll, g_wszAll))
752	{
753	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the basic test.\n");
754	g_cErrors++;
755	}
756
757	if (RTUtf16Cmp(g_wszAll, g_wszAll))
758	{
759	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the basic test.\n");
760	g_cErrors++;
761	}
762
763	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 };
764	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 };
765	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
766	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
767	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
768	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
769	)
770	{
771	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the alphabet test.\n");
772	g_cErrors++;
773	}
774
775	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
776	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
777	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
778	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
779	)
780	{
781	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the alphabet test.\n");
782	g_cErrors++;
783	}
784	}
785
786
787	/**
788	* Benchmark stuff.
789	*/
790	void Benchmarks(void)
791	{
792	RTPrintf("tstUtf8: BENCHMARKS\n");
793	static union
794	{
795	RTUTF16 wszBuf[sizeof(g_wszAll)];
796	char szBuf[sizeof(g_szAll)];
797	} s_Buf;
798
799	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
800	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
801	if (RT_SUCCESS(rc))
802	{
803	int i;
804	uint64_t u64Start = RTTimeNanoTS();
805	for (i = 0; i < 100; i++)
806	{
807	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
808	if (RT_FAILURE(rc))
809	{
810	RTPrintf("tstUtf8: UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
811	break;
812	}
813	}
814	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
815	RTPrintf("tstUtf8: UTF-8 -> UTF-16: %d in %RI64ns\n", i, u64Elapsed);
816	}
817
818	char *psz = &s_Buf.szBuf[0];
819	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
820	if (RT_SUCCESS(rc))
821	{
822	int i;
823	uint64_t u64Start = RTTimeNanoTS();
824	for (i = 0; i < 100; i++)
825	{
826	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
827	if (RT_FAILURE(rc))
828	{
829	RTPrintf("tstUtf8: UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
830	break;
831	}
832	}
833	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
834	RTPrintf("tstUtf8: UTF-16 -> UTF-8: %d in %RI64ns\n", i, u64Elapsed);
835	}
836
837	}
838
839
840	int main()
841	{
842	RTR3Init(false);
843
844	InitStrings();
845	test1();
846	test2();
847	test3();
848	Benchmarks();
849
850	/*
851	* Summary
852	*/
853	if (!g_cErrors)
854	RTPrintf("tstUtf8: SUCCESS\n");
855	else
856	RTPrintf("tstUtf8: FAILURE - %d errors!\n", g_cErrors);
857
858	return !!g_cErrors;
859	}

Note: See TracBrowser for help on using the repository browser.

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 4968

Download in other formats: