tstUtf8.cpp@ 3125

Last change on this file since 3125 was 2981, checked in by vboxsync, 17 years ago
InnoTek -> innotek: all the headers and comments.
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 26.9 KB

Line
1	/* $Id: tstUtf8.cpp 2981 2007-06-01 16:01:28Z 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	* If you received this file as part of a commercial VirtualBox
18	* distribution, then only the terms of your commercial VirtualBox
19	* license agreement apply instead of the previous paragraph.
20	*/
21
22	/*******************************************************************************
23	* Header Files *
24	*******************************************************************************/
25	#include <iprt/string.h>
26	#include <iprt/uni.h>
27	#include <iprt/runtime.h>
28	#include <iprt/uuid.h>
29	#include <iprt/time.h>
30	#include <iprt/stream.h>
31	#include <iprt/alloc.h>
32	#include <iprt/assert.h>
33	#include <iprt/err.h>
34
35	#include <stdlib.h>
36
37
38	/*******************************************************************************
39	* Global Variables *
40	*******************************************************************************/
41	static int g_cErrors = 0;
42
43
44	/**
45	* Generate a random codepoint for simple UTF-16 encoding.
46	*/
47	static RTUTF16 GetRandUcs2(void)
48	{
49	RTUTF16 wc;
50	do
51	{
52	wc = (RTUTF16)((long long)rand() * 0xffff / RAND_MAX);
53	} while ((wc >= 0xd800 && wc <= 0xdfff) \|\| wc == 0);
54	return wc;
55	}
56
57
58	/**
59	*
60	*/
61	static void test1(void)
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	RTPrintf("tstUtf8: TEST 1\n");
72
73	/*
74	* Invalid UTF-8 to UCS-2 test.
75	*/
76	rc = RTStrToUtf16(s_szBadString1, &pwsz);
77	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
78	{
79	RTPrintf("tstUtf8: FAILURE - %d: Conversion of first bad UTF-8 string to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
80	__LINE__, rc);
81	g_cErrors++;
82	}
83	rc = RTStrToUtf16(s_szBadString2, &pwsz);
84	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
85	{
86	RTPrintf("tstUtf8: FAILURE - %d: Conversion of second bad UTF-8 strings to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
87	__LINE__, rc);
88	g_cErrors++;
89	}
90
91	/*
92	* Test current CP convertion.
93	*/
94	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
95	srand((unsigned)RTTimeNanoTS());
96	for (int i = 0; i < 30; i++)
97	pwszRand[i] = GetRandUcs2();
98	pwszRand[30] = 0;
99
100	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
101	if (rc == VINF_SUCCESS)
102	{
103	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
104	if (rc == VINF_SUCCESS)
105	{
106	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
107	if (rc == VINF_SUCCESS)
108	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
109	else
110	{
111	RTPrintf("tstUtf8: FAILURE - %d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
112	__LINE__, rc);
113	g_cErrors++;
114	}
115	}
116	else if (rc == VERR_NO_TRANSLATION)
117	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");
118	else
119	{
120	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
121	__LINE__, rc);
122	g_cErrors++;
123	}
124	}
125	else
126	{
127	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
128	__LINE__, rc);
129	g_cErrors++;
130	}
131
132	/*
133	* Generate a new random string.
134	*/
135	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
136	srand((unsigned)RTTimeNanoTS());
137	for (int i = 0; i < 30; i++)
138	pwszRand[i] = GetRandUcs2();
139	pwszRand[30] = 0;
140	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
141	if (rc == VINF_SUCCESS)
142	{
143	rc = RTStrToUtf16(pszUtf8, &pwsz);
144	if (rc == VINF_SUCCESS)
145	{
146	int i;
147	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
148	/* nothing */;
149	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
150	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
151	else
152	{
153	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.\n", __LINE__);
154	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
155	g_cErrors++;
156	}
157	}
158	else
159	{
160	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
161	__LINE__, rc);
162	g_cErrors++;
163	}
164	}
165	else
166	{
167	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
168	__LINE__, rc);
169	g_cErrors++;
170	}
171
172	/*
173	* Generate yet another random string and convert it to a buffer.
174	*/
175	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
176	srand((unsigned)RTTimeNanoTS());
177	for (int i = 0; i < 30; i++)
178	pwszRand[i] = GetRandUcs2();
179	pwszRand[30] = 0;
180
181	char szUtf8Array[120];
182	char *pszUtf8Array = szUtf8Array;
183	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
184	if (rc == 0)
185	{
186	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
187	if (rc == 0)
188	{
189	int i;
190	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++);
191	if (pwsz[i] == 0 && i >= 8)
192	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
193	else
194	{
195	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
196	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
197	g_cErrors++;
198	}
199	}
200	else
201	{
202	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
203	__LINE__, rc);
204	g_cErrors++;
205	}
206	}
207	else
208	{
209	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
210	__LINE__, rc);
211	g_cErrors++;
212	}
213
214	/*
215	* And again.
216	*/
217	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
218	srand((unsigned)RTTimeNanoTS());
219	for (int i = 0; i < 30; i++)
220	pwszRand[i] = GetRandUcs2();
221	pwszRand[30] = 0;
222
223	RTUTF16 wszBuf[70];
224	PRTUTF16 pwsz2Buf = wszBuf;
225	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
226	if (rc == 0)
227	{
228	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
229	if (rc == 0)
230	{
231	int i;
232	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++);
233	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
234	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
235	else
236	{
237	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
238	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
239	g_cErrors++;
240	}
241	}
242	else
243	{
244	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
245	__LINE__, rc);
246	g_cErrors++;
247	}
248	}
249	else
250	{
251	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
252	__LINE__, rc);
253	g_cErrors++;
254	}
255	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
256	srand((unsigned)RTTimeNanoTS());
257	for (int i = 0; i < 30; i++)
258	pwszRand[i] = GetRandUcs2();
259	pwszRand[30] = 0;
260
261	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
262	if (rc == VERR_BUFFER_OVERFLOW)
263	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
264	else
265	{
266	RTPrintf("tstUtf8: FAILURE - %d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
267	__LINE__, rc);
268	g_cErrors++;
269	}
270
271	/*
272	* last time...
273	*/
274	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
275	srand((unsigned)RTTimeNanoTS());
276	for (int i = 0; i < 30; i++)
277	pwszRand[i] = GetRandUcs2();
278	pwszRand[30] = 0;
279
280	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
281	if (rc == VINF_SUCCESS)
282	{
283	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
284	if (rc == VERR_BUFFER_OVERFLOW)
285	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
286	else
287	{
288	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",
289	__LINE__, rc);
290	g_cErrors++;
291	}
292	}
293	else
294	{
295	RTPrintf("tstUtf8: FAILURE - %d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
296	__LINE__, rc);
297	g_cErrors++;
298	}
299
300	}
301
302
303	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
304	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
305	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
306
307	static void whereami(int cBits, size_t off)
308	{
309	if (cBits == 8)
310	{
311	if (off < 0x7f)
312	RTPrintf("UTF-8 U+%#x\n", off + 1);
313	else if (off < 0xf7f)
314	RTPrintf("UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
315	else if (off < 0x27f7f)
316	RTPrintf("UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
317	else if (off < 0x2df79)
318	RTPrintf("UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
319	else if (off < 0x42df79)
320	RTPrintf("UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
321	else
322	RTPrintf("UTF-8 ???\n");
323	}
324	else if (cBits == 16)
325	{
326	if (off < 0xd7ff*2)
327	RTPrintf("UTF-16 U+%#x\n", off / 2 + 1);
328	else if (off < 0xf7fd*2)
329	RTPrintf("UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
330	else if (off < 0x20f7fd)
331	RTPrintf("UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
332	else
333	RTPrintf("UTF-16 ???\n");
334	}
335	else
336	{
337	if (off < (0xd800 - 1) * sizeof(RTUNICP))
338	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
339	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
340	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
341	else
342	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
343	}
344	}
345
346	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
347	{
348	const uint8_t pb1 = (const uint8_t )pv1;
349	const uint8_t pb2 = (const uint8_t )pv2;
350	for (size_t off = 0; off < cb; off++)
351	{
352	if (pb1[off] != pb2[off])
353	{
354	RTPrintf("mismatch at %#x: ", off);
355	whereami(cBits, off);
356	RTPrintf(" %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
357	RTPrintf("*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
358	RTPrintf(" %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
359	RTPrintf(" %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
360	RTPrintf(" %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
361	RTPrintf(" %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
362	RTPrintf(" %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
363	RTPrintf(" %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
364	RTPrintf(" %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
365	RTPrintf(" %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
366	RTPrintf(" %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
367	return 1;
368	}
369	}
370	return 0;
371	}
372
373
374	void InitStrings(void)
375	{
376	/*
377	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
378	*/
379	/* the simple code point array first */
380	unsigned i = 0;
381	RTUNICP uc = 1;
382	while (uc < 0xd800)
383	g_uszAll[i++] = uc++;
384	uc = 0xe000;
385	while (uc < 0xfffe)
386	g_uszAll[i++] = uc++;
387	uc = 0x10000;
388	while (uc < 0x110000)
389	g_uszAll[i++] = uc++;
390	g_uszAll[i++] = 0;
391	Assert(ELEMENTS(g_uszAll) == i);
392
393	/* the utf-16 one */
394	i = 0;
395	uc = 1;
396	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
397	while (uc < 0xd800)
398	g_wszAll[i++] = uc++;
399	uc = 0xe000;
400	//RTPrintf(" %#x=%#x", i, uc);
401	while (uc < 0xfffe)
402	g_wszAll[i++] = uc++;
403	uc = 0x10000;
404	//RTPrintf(" %#x=%#x", i, uc);
405	while (uc < 0x110000)
406	{
407	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
408	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
409	uc++;
410	}
411	//RTPrintf(" %#x=%#x\n", i, uc);
412	g_wszAll[i++] = '\0';
413	Assert(ELEMENTS(g_wszAll) == i);
414
415	/*
416	* The utf-8 one
417	*/
418	i = 0;
419	uc = 1;
420	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
421	while (uc < 0x80)
422	g_szAll[i++] = uc++;
423	//RTPrintf(" %#x=%#x", i, uc);
424	while (uc < 0x800)
425	{
426	g_szAll[i++] = 0xc0 \| (uc >> 6);
427	g_szAll[i++] = 0x80 \| (uc & 0x3f);
428	Assert(!((uc >> 6) & ~0x1f));
429	uc++;
430	}
431	//RTPrintf(" %#x=%#x", i, uc);
432	while (uc < 0xd800)
433	{
434	g_szAll[i++] = 0xe0 \| (uc >> 12);
435	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
436	g_szAll[i++] = 0x80 \| (uc & 0x3f);
437	Assert(!((uc >> 12) & ~0xf));
438	uc++;
439	}
440	uc = 0xe000;
441	//RTPrintf(" %#x=%#x", i, uc);
442	while (uc < 0xfffe)
443	{
444	g_szAll[i++] = 0xe0 \| (uc >> 12);
445	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
446	g_szAll[i++] = 0x80 \| (uc & 0x3f);
447	Assert(!((uc >> 12) & ~0xf));
448	uc++;
449	}
450	uc = 0x10000;
451	//RTPrintf(" %#x=%#x", i, uc);
452	while (uc < 0x110000)
453	{
454	g_szAll[i++] = 0xf0 \| (uc >> 18);
455	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
456	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
457	g_szAll[i++] = 0x80 \| (uc & 0x3f);
458	Assert(!((uc >> 18) & ~0x7));
459	uc++;
460	}
461	//RTPrintf(" %#x=%#x\n", i, uc);
462	g_szAll[i++] = '\0';
463	Assert(ELEMENTS(g_szAll) == i);
464	}
465
466
467	void test2(void)
468	{
469	RTPrintf("tstUtf8: TEST 2\n");
470
471	/*
472	* Convert to UTF-8 and back.
473	*/
474	RTPrintf("tstUtf8: #1: UTF-16 -> UTF-8 -> UTF-16...\n");
475	char *pszUtf8;
476	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
477	if (rc == VINF_SUCCESS)
478	{
479	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
480	{
481	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 mismatch!\n");
482	g_cErrors++;
483	}
484
485	PRTUTF16 puszUcs2;
486	rc = RTStrToUtf16(pszUtf8, &puszUcs2);
487	if (rc == VINF_SUCCESS)
488	{
489	if (mymemcmp(puszUcs2, g_wszAll, sizeof(g_wszAll), 16))
490	{
491	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed compare!\n");
492	g_cErrors++;
493	}
494	RTUtf16Free(puszUcs2);
495	}
496	else
497	{
498	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
499	g_cErrors++;
500	}
501	RTStrFree(pszUtf8);
502	}
503	else
504	{
505	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
506	g_cErrors++;
507	}
508
509
510	/*
511	* Convert to UTF-16 and back. (just in case the above test fails)
512	*/
513	RTPrintf("tstUtf8: #2: UTF-8 -> UTF-16 -> UTF-8...\n");
514	PRTUTF16 puszUcs2;
515	rc = RTStrToUtf16(&g_szAll[0], &puszUcs2);
516	if (rc == VINF_SUCCESS)
517	{
518	if (mymemcmp(puszUcs2, g_wszAll, sizeof(g_wszAll), 16))
519	{
520	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed compare!\n");
521	g_cErrors++;
522	}
523
524	char *pszUtf8;
525	rc = RTUtf16ToUtf8(puszUcs2, &pszUtf8);
526	if (rc == VINF_SUCCESS)
527	{
528	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
529	{
530	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed compare!\n");
531	g_cErrors++;
532	}
533	RTStrFree(pszUtf8);
534	}
535	else
536	{
537	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
538	g_cErrors++;
539	}
540	RTStrUcs2Free(puszUcs2);
541	}
542	else
543	{
544	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
545	g_cErrors++;
546	}
547
548	/*
549	* Convert UTF-8 to CPs.
550	*/
551	PRTUNICP paCps;
552	rc = RTStrToUni(g_szAll, &paCps);
553	if (rc == VINF_SUCCESS)
554	{
555	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
556	{
557	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
558	g_cErrors++;
559	}
560
561	size_t cCps;
562	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, ELEMENTS(g_uszAll), &cCps);
563	if (rc == VINF_SUCCESS)
564	{
565	if (cCps != ELEMENTS(g_uszAll) - 1)
566	{
567	RTPrintf("tstUtf8: FAILURE - the full #3+: wrong Code Point count %zu, expected %zu\n", cCps, ELEMENTS(g_uszAll) - 1);
568	g_cErrors++;
569	}
570	}
571	else
572	{
573	RTPrintf("tstUtf8: FAILURE - the full #3+: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
574	g_cErrors++;
575	}
576
577	/** @todo RTCpsToUtf8 or something. */
578	}
579	else
580	{
581	RTPrintf("tstUtf8: FAILURE - the full #3a: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
582	g_cErrors++;
583	}
584
585	/*
586	* Check the various string lengths.
587	*/
588	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
589	size_t cuc2 = RTUtf16Len(g_wszAll);
590	if (cuc1 != cuc2)
591	{
592	RTPrintf("tstUtf8: FAILURE - cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
593	g_cErrors++;
594	}
595	//size_t cuc3 = RTUniLen(g_uszAll);
596
597
598	/*
599	* Enumerate the strings.
600	*/
601	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
602	AssertRelease(pszPut1Base);
603	char *pszPut1 = pszPut1Base;
604	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
605	AssertRelease(pwszPut2Base);
606	PRTUTF16 pwszPut2 = pwszPut2Base;
607	const char *psz1 = g_szAll;
608	const char *psz2 = g_szAll;
609	PCRTUTF16 pwsz3 = g_wszAll;
610	PCRTUTF16 pwsz4 = g_wszAll;
611	for (;;)
612	{
613	/*
614	* getters
615	*/
616	RTUNICP uc1;
617	rc = RTStrGetCpEx(&psz1, &uc1);
618	if (RT_FAILURE(rc))
619	{
620	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, psz2);
621	whereami(8, psz2 - &g_szAll[0]);
622	g_cErrors++;
623	break;
624	}
625	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
626	if (pszPrev1 != psz2)
627	{
628	RTPrintf("tstUtf8: FAILURE - RTStrPrevCp returned %p expected %p!\n", pszPrev1, psz2);
629	whereami(8, psz2 - &g_szAll[0]);
630	g_cErrors++;
631	break;
632	}
633	RTUNICP uc2 = RTStrGetCp(psz2);
634	if (uc2 != uc1)
635	{
636	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc2, uc1);
637	whereami(8, psz2 - &g_szAll[0]);
638	g_cErrors++;
639	break;
640	}
641	psz2 = RTStrNextCp(psz2);
642	if (psz2 != psz1)
643	{
644	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetNext returned different next pointer!\n");
645	whereami(8, psz2 - &g_szAll[0]);
646	g_cErrors++;
647	break;
648	}
649
650	RTUNICP uc3;
651	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
652	if (RT_FAILURE(rc))
653	{
654	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, pwsz4);
655	whereami(16, pwsz4 - &g_wszAll[0]);
656	g_cErrors++;
657	break;
658	}
659	if (uc3 != uc2)
660	{
661	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc2);
662	whereami(16, pwsz4 - &g_wszAll[0]);
663	g_cErrors++;
664	break;
665	}
666	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
667	if (uc3 != uc4)
668	{
669	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc4);
670	whereami(16, pwsz4 - &g_wszAll[0]);
671	g_cErrors++;
672	break;
673	}
674	pwsz4 = RTUtf16NextCp(pwsz4);
675	if (pwsz4 != pwsz3)
676	{
677	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!\n");
678	whereami(8, pwsz4 - &g_wszAll[0]);
679	g_cErrors++;
680	break;
681	}
682
683
684	/*
685	* putters
686	*/
687	pszPut1 = RTStrPutCp(pszPut1, uc1);
688	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
689	{
690	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
691	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
692	whereami(8, psz2 - &g_szAll[0]);
693	g_cErrors++;
694	break;
695	}
696
697	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
698	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
699	{
700	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
701	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
702	whereami(8, pwsz4 - &g_wszAll[0]);
703	g_cErrors++;
704	break;
705	}
706
707
708	/* the end? */
709	if (!uc1)
710	break;
711	}
712
713	/* check output if we seems to have made it thru it all. */
714	if (psz2 == &g_szAll[sizeof(g_szAll)])
715	{
716	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
717	{
718	RTPrintf("tstUtf8: FAILURE - RTStrPutCp encoded the string incorrectly.\n");
719	g_cErrors++;
720	}
721	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
722	{
723	RTPrintf("tstUtf8: FAILURE - RTUtf16PutCp encoded the string incorrectly.\n");
724	g_cErrors++;
725	}
726	}
727
728	RTMemFree(pszPut1Base);
729	RTMemFree(pwszPut2Base);
730	}
731
732
733	/**
734	* Check case insensitivity.
735	*/
736	void test3(void)
737	{
738	RTPrintf("tstUtf8: TEST 3\n");
739
740	if ( RTUniCpToLower('a') != 'a'
741	\|\| RTUniCpToLower('A') != 'a'
742	\|\| RTUniCpToLower('b') != 'b'
743	\|\| RTUniCpToLower('B') != 'b'
744	\|\| RTUniCpToLower('Z') != 'z'
745	\|\| RTUniCpToLower('z') != 'z'
746	\|\| RTUniCpToUpper('c') != 'C'
747	\|\| RTUniCpToUpper('C') != 'C'
748	\|\| RTUniCpToUpper('z') != 'Z'
749	\|\| RTUniCpToUpper('Z') != 'Z')
750	{
751	RTPrintf("tstUtf8: FAILURE - RTUniToUpper/Lower failed basic tests.\n");
752	g_cErrors++;
753	}
754
755	if (RTUtf16ICmp(g_wszAll, g_wszAll))
756	{
757	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the basic test.\n");
758	g_cErrors++;
759	}
760
761	if (RTUtf16Cmp(g_wszAll, g_wszAll))
762	{
763	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the basic test.\n");
764	g_cErrors++;
765	}
766
767	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 };
768	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 };
769	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
770	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
771	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
772	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
773	)
774	{
775	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the alphabet test.\n");
776	g_cErrors++;
777	}
778
779	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
780	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
781	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
782	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
783	)
784	{
785	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the alphabet test.\n");
786	g_cErrors++;
787	}
788	}
789
790
791	/**
792	* Benchmark stuff.
793	*/
794	void Benchmarks(void)
795	{
796	RTPrintf("tstUtf8: BENCHMARKS\n");
797	static union
798	{
799	RTUTF16 wszBuf[sizeof(g_wszAll)];
800	char szBuf[sizeof(g_szAll)];
801	} s_Buf;
802
803	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
804	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
805	if (RT_SUCCESS(rc))
806	{
807	int i;
808	uint64_t u64Start = RTTimeNanoTS();
809	for (i = 0; i < 100; i++)
810	{
811	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
812	if (RT_FAILURE(rc))
813	{
814	RTPrintf("tstUtf8: UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
815	break;
816	}
817	}
818	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
819	RTPrintf("tstUtf8: UTF-8 -> UTF-16: %d in %RI64ns\n", i, u64Elapsed);
820	}
821
822	char *psz = &s_Buf.szBuf[0];
823	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
824	if (RT_SUCCESS(rc))
825	{
826	int i;
827	uint64_t u64Start = RTTimeNanoTS();
828	for (i = 0; i < 100; i++)
829	{
830	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
831	if (RT_FAILURE(rc))
832	{
833	RTPrintf("tstUtf8: UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
834	break;
835	}
836	}
837	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
838	RTPrintf("tstUtf8: UTF-16 -> UTF-8: %d in %RI64ns\n", i, u64Elapsed);
839	}
840
841	}
842
843
844	int main()
845	{
846	RTR3Init(false);
847
848	InitStrings();
849	test1();
850	test2();
851	test3();
852	Benchmarks();
853
854	/*
855	* Summary
856	*/
857	if (!g_cErrors)
858	RTPrintf("tstUtf8: SUCCESS\n");
859	else
860	RTPrintf("tstUtf8: FAILURE - %d errors!\n", g_cErrors);
861
862	return !!g_cErrors;
863	}

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 3125

Download in other formats: