tstUtf8.cpp@ 7418

Last change on this file since 7418 was 7418, checked in by vboxsync, 17 years ago
UCS-2 -> UTF-16.
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 27.2 KB

Line
1	/* $Id: tstUtf8.cpp 7418 2008-03-10 16:01:58Z 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 (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	#include <iprt/uni.h>
32	#include <iprt/runtime.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
40	#include <stdlib.h>
41
42
43	/*******************************************************************************
44	* Global Variables *
45	*******************************************************************************/
46	static int g_cErrors = 0;
47
48
49	/**
50	* Generate a random codepoint for simple UTF-16 encoding.
51	*/
52	static RTUTF16 GetRandUtf16(void)
53	{
54	RTUTF16 wc;
55	do
56	{
57	wc = (RTUTF16)((long long)rand() * 0xffff / RAND_MAX);
58	} while ((wc >= 0xd800 && wc <= 0xdfff) \|\| wc == 0);
59	return wc;
60	}
61
62
63	/**
64	*
65	*/
66	static void test1(void)
67	{
68	static const char s_szBadString1[] = "Bad \xe0\x13\x0";
69	static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
70	int rc;
71	char *pszUtf8;
72	char *pszCurrent;
73	PRTUTF16 pwsz;
74	PRTUTF16 pwszRand;
75
76	RTPrintf("tstUtf8: TEST 1\n");
77
78	/*
79	* Invalid UTF-8 to UCS-2 test.
80	*/
81	rc = RTStrToUtf16(s_szBadString1, &pwsz);
82	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
83	{
84	RTPrintf("tstUtf8: FAILURE - %d: Conversion of first bad UTF-8 string to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
85	__LINE__, rc);
86	g_cErrors++;
87	}
88	rc = RTStrToUtf16(s_szBadString2, &pwsz);
89	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
90	{
91	RTPrintf("tstUtf8: FAILURE - %d: Conversion of second bad UTF-8 strings to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
92	__LINE__, rc);
93	g_cErrors++;
94	}
95
96	/*
97	* Test current CP convertion.
98	*/
99	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
100	srand((unsigned)RTTimeNanoTS());
101	for (int i = 0; i < 30; i++)
102	pwszRand[i] = GetRandUtf16();
103	pwszRand[30] = 0;
104
105	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
106	if (rc == VINF_SUCCESS)
107	{
108	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
109	if (rc == VINF_SUCCESS)
110	{
111	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
112	if (rc == VINF_SUCCESS)
113	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
114	else
115	{
116	RTPrintf("tstUtf8: FAILURE - %d: The third 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 if (rc == VERR_NO_TRANSLATION)
122	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");
123	else
124	{
125	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
126	__LINE__, rc);
127	g_cErrors++;
128	}
129	}
130	else
131	{
132	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
133	__LINE__, rc);
134	g_cErrors++;
135	}
136
137	/*
138	* Generate a new random string.
139	*/
140	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
141	srand((unsigned)RTTimeNanoTS());
142	for (int i = 0; i < 30; i++)
143	pwszRand[i] = GetRandUtf16();
144	pwszRand[30] = 0;
145	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
146	if (rc == VINF_SUCCESS)
147	{
148	rc = RTStrToUtf16(pszUtf8, &pwsz);
149	if (rc == VINF_SUCCESS)
150	{
151	int i;
152	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
153	/* nothing */;
154	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
155	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
156	else
157	{
158	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.\n", __LINE__);
159	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
160	g_cErrors++;
161	}
162	}
163	else
164	{
165	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
166	__LINE__, rc);
167	g_cErrors++;
168	}
169	}
170	else
171	{
172	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
173	__LINE__, rc);
174	g_cErrors++;
175	}
176
177	/*
178	* Generate yet another random string and convert it to a buffer.
179	*/
180	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
181	srand((unsigned)RTTimeNanoTS());
182	for (int i = 0; i < 30; i++)
183	pwszRand[i] = GetRandUtf16();
184	pwszRand[30] = 0;
185
186	char szUtf8Array[120];
187	char *pszUtf8Array = szUtf8Array;
188	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
189	if (rc == 0)
190	{
191	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
192	if (rc == 0)
193	{
194	int i;
195	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++);
196	if (pwsz[i] == 0 && i >= 8)
197	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
198	else
199	{
200	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
201	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
202	g_cErrors++;
203	}
204	}
205	else
206	{
207	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
208	__LINE__, rc);
209	g_cErrors++;
210	}
211	}
212	else
213	{
214	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
215	__LINE__, rc);
216	g_cErrors++;
217	}
218
219	/*
220	* And again.
221	*/
222	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
223	srand((unsigned)RTTimeNanoTS());
224	for (int i = 0; i < 30; i++)
225	pwszRand[i] = GetRandUtf16();
226	pwszRand[30] = 0;
227
228	RTUTF16 wszBuf[70];
229	PRTUTF16 pwsz2Buf = wszBuf;
230	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
231	if (rc == 0)
232	{
233	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
234	if (rc == 0)
235	{
236	int i;
237	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++);
238	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
239	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
240	else
241	{
242	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
243	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
244	g_cErrors++;
245	}
246	}
247	else
248	{
249	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
250	__LINE__, rc);
251	g_cErrors++;
252	}
253	}
254	else
255	{
256	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
257	__LINE__, rc);
258	g_cErrors++;
259	}
260	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
261	srand((unsigned)RTTimeNanoTS());
262	for (int i = 0; i < 30; i++)
263	pwszRand[i] = GetRandUtf16();
264	pwszRand[30] = 0;
265
266	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
267	if (rc == VERR_BUFFER_OVERFLOW)
268	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
269	else
270	{
271	RTPrintf("tstUtf8: FAILURE - %d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
272	__LINE__, rc);
273	g_cErrors++;
274	}
275
276	/*
277	* last time...
278	*/
279	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
280	srand((unsigned)RTTimeNanoTS());
281	for (int i = 0; i < 30; i++)
282	pwszRand[i] = GetRandUtf16();
283	pwszRand[30] = 0;
284
285	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
286	if (rc == VINF_SUCCESS)
287	{
288	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
289	if (rc == VERR_BUFFER_OVERFLOW)
290	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
291	else
292	{
293	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",
294	__LINE__, rc);
295	g_cErrors++;
296	}
297	}
298	else
299	{
300	RTPrintf("tstUtf8: FAILURE - %d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
301	__LINE__, rc);
302	g_cErrors++;
303	}
304
305	}
306
307
308	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
309	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
310	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
311
312	static void whereami(int cBits, size_t off)
313	{
314	if (cBits == 8)
315	{
316	if (off < 0x7f)
317	RTPrintf("UTF-8 U+%#x\n", off + 1);
318	else if (off < 0xf7f)
319	RTPrintf("UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
320	else if (off < 0x27f7f)
321	RTPrintf("UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
322	else if (off < 0x2df79)
323	RTPrintf("UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
324	else if (off < 0x42df79)
325	RTPrintf("UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
326	else
327	RTPrintf("UTF-8 ???\n");
328	}
329	else if (cBits == 16)
330	{
331	if (off < 0xd7ff*2)
332	RTPrintf("UTF-16 U+%#x\n", off / 2 + 1);
333	else if (off < 0xf7fd*2)
334	RTPrintf("UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
335	else if (off < 0x20f7fd)
336	RTPrintf("UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
337	else
338	RTPrintf("UTF-16 ???\n");
339	}
340	else
341	{
342	if (off < (0xd800 - 1) * sizeof(RTUNICP))
343	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
344	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
345	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
346	else
347	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
348	}
349	}
350
351	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
352	{
353	const uint8_t pb1 = (const uint8_t )pv1;
354	const uint8_t pb2 = (const uint8_t )pv2;
355	for (size_t off = 0; off < cb; off++)
356	{
357	if (pb1[off] != pb2[off])
358	{
359	RTPrintf("mismatch at %#x: ", off);
360	whereami(cBits, off);
361	RTPrintf(" %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
362	RTPrintf("*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
363	RTPrintf(" %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
364	RTPrintf(" %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
365	RTPrintf(" %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
366	RTPrintf(" %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
367	RTPrintf(" %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
368	RTPrintf(" %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
369	RTPrintf(" %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
370	RTPrintf(" %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
371	RTPrintf(" %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
372	return 1;
373	}
374	}
375	return 0;
376	}
377
378
379	void InitStrings(void)
380	{
381	/*
382	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
383	*/
384	/* the simple code point array first */
385	unsigned i = 0;
386	RTUNICP uc = 1;
387	while (uc < 0xd800)
388	g_uszAll[i++] = uc++;
389	uc = 0xe000;
390	while (uc < 0xfffe)
391	g_uszAll[i++] = uc++;
392	uc = 0x10000;
393	while (uc < 0x110000)
394	g_uszAll[i++] = uc++;
395	g_uszAll[i++] = 0;
396	Assert(ELEMENTS(g_uszAll) == i);
397
398	/* the utf-16 one */
399	i = 0;
400	uc = 1;
401	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
402	while (uc < 0xd800)
403	g_wszAll[i++] = uc++;
404	uc = 0xe000;
405	//RTPrintf(" %#x=%#x", i, uc);
406	while (uc < 0xfffe)
407	g_wszAll[i++] = uc++;
408	uc = 0x10000;
409	//RTPrintf(" %#x=%#x", i, uc);
410	while (uc < 0x110000)
411	{
412	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
413	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
414	uc++;
415	}
416	//RTPrintf(" %#x=%#x\n", i, uc);
417	g_wszAll[i++] = '\0';
418	Assert(ELEMENTS(g_wszAll) == i);
419
420	/*
421	* The utf-8 one
422	*/
423	i = 0;
424	uc = 1;
425	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
426	while (uc < 0x80)
427	g_szAll[i++] = uc++;
428	//RTPrintf(" %#x=%#x", i, uc);
429	while (uc < 0x800)
430	{
431	g_szAll[i++] = 0xc0 \| (uc >> 6);
432	g_szAll[i++] = 0x80 \| (uc & 0x3f);
433	Assert(!((uc >> 6) & ~0x1f));
434	uc++;
435	}
436	//RTPrintf(" %#x=%#x", i, uc);
437	while (uc < 0xd800)
438	{
439	g_szAll[i++] = 0xe0 \| (uc >> 12);
440	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
441	g_szAll[i++] = 0x80 \| (uc & 0x3f);
442	Assert(!((uc >> 12) & ~0xf));
443	uc++;
444	}
445	uc = 0xe000;
446	//RTPrintf(" %#x=%#x", i, uc);
447	while (uc < 0xfffe)
448	{
449	g_szAll[i++] = 0xe0 \| (uc >> 12);
450	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
451	g_szAll[i++] = 0x80 \| (uc & 0x3f);
452	Assert(!((uc >> 12) & ~0xf));
453	uc++;
454	}
455	uc = 0x10000;
456	//RTPrintf(" %#x=%#x", i, uc);
457	while (uc < 0x110000)
458	{
459	g_szAll[i++] = 0xf0 \| (uc >> 18);
460	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
461	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
462	g_szAll[i++] = 0x80 \| (uc & 0x3f);
463	Assert(!((uc >> 18) & ~0x7));
464	uc++;
465	}
466	//RTPrintf(" %#x=%#x\n", i, uc);
467	g_szAll[i++] = '\0';
468	Assert(ELEMENTS(g_szAll) == i);
469	}
470
471
472	void test2(void)
473	{
474	RTPrintf("tstUtf8: TEST 2\n");
475
476	/*
477	* Convert to UTF-8 and back.
478	*/
479	RTPrintf("tstUtf8: #1: UTF-16 -> UTF-8 -> UTF-16...\n");
480	char *pszUtf8;
481	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
482	if (rc == VINF_SUCCESS)
483	{
484	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
485	{
486	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 mismatch!\n");
487	g_cErrors++;
488	}
489
490	PRTUTF16 pwszUtf16;
491	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
492	if (rc == VINF_SUCCESS)
493	{
494	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
495	{
496	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed compare!\n");
497	g_cErrors++;
498	}
499	RTUtf16Free(pwszUtf16);
500	}
501	else
502	{
503	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
504	g_cErrors++;
505	}
506	RTStrFree(pszUtf8);
507	}
508	else
509	{
510	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
511	g_cErrors++;
512	}
513
514
515	/*
516	* Convert to UTF-16 and back. (just in case the above test fails)
517	*/
518	RTPrintf("tstUtf8: #2: UTF-8 -> UTF-16 -> UTF-8...\n");
519	PRTUTF16 pwszUtf16;
520	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
521	if (rc == VINF_SUCCESS)
522	{
523	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
524	{
525	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed compare!\n");
526	g_cErrors++;
527	}
528
529	char *pszUtf8;
530	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
531	if (rc == VINF_SUCCESS)
532	{
533	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
534	{
535	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed compare!\n");
536	g_cErrors++;
537	}
538	RTStrFree(pszUtf8);
539	}
540	else
541	{
542	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
543	g_cErrors++;
544	}
545	RTUtf16Free(pwszUtf16);
546	}
547	else
548	{
549	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
550	g_cErrors++;
551	}
552
553	/*
554	* Convert UTF-8 to CPs.
555	*/
556	PRTUNICP paCps;
557	rc = RTStrToUni(g_szAll, &paCps);
558	if (rc == VINF_SUCCESS)
559	{
560	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
561	{
562	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
563	g_cErrors++;
564	}
565
566	size_t cCps;
567	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, ELEMENTS(g_uszAll), &cCps);
568	if (rc == VINF_SUCCESS)
569	{
570	if (cCps != ELEMENTS(g_uszAll) - 1)
571	{
572	RTPrintf("tstUtf8: FAILURE - the full #3+: wrong Code Point count %zu, expected %zu\n", cCps, ELEMENTS(g_uszAll) - 1);
573	g_cErrors++;
574	}
575	}
576	else
577	{
578	RTPrintf("tstUtf8: FAILURE - the full #3+: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
579	g_cErrors++;
580	}
581
582	/** @todo RTCpsToUtf8 or something. */
583	}
584	else
585	{
586	RTPrintf("tstUtf8: FAILURE - the full #3a: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
587	g_cErrors++;
588	}
589
590	/*
591	* Check the various string lengths.
592	*/
593	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
594	size_t cuc2 = RTUtf16Len(g_wszAll);
595	if (cuc1 != cuc2)
596	{
597	RTPrintf("tstUtf8: FAILURE - cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
598	g_cErrors++;
599	}
600	//size_t cuc3 = RTUniLen(g_uszAll);
601
602
603	/*
604	* Enumerate the strings.
605	*/
606	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
607	AssertRelease(pszPut1Base);
608	char *pszPut1 = pszPut1Base;
609	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
610	AssertRelease(pwszPut2Base);
611	PRTUTF16 pwszPut2 = pwszPut2Base;
612	const char *psz1 = g_szAll;
613	const char *psz2 = g_szAll;
614	PCRTUTF16 pwsz3 = g_wszAll;
615	PCRTUTF16 pwsz4 = g_wszAll;
616	for (;;)
617	{
618	/*
619	* getters
620	*/
621	RTUNICP uc1;
622	rc = RTStrGetCpEx(&psz1, &uc1);
623	if (RT_FAILURE(rc))
624	{
625	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, psz2);
626	whereami(8, psz2 - &g_szAll[0]);
627	g_cErrors++;
628	break;
629	}
630	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
631	if (pszPrev1 != psz2)
632	{
633	RTPrintf("tstUtf8: FAILURE - RTStrPrevCp returned %p expected %p!\n", pszPrev1, psz2);
634	whereami(8, psz2 - &g_szAll[0]);
635	g_cErrors++;
636	break;
637	}
638	RTUNICP uc2 = RTStrGetCp(psz2);
639	if (uc2 != uc1)
640	{
641	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc2, uc1);
642	whereami(8, psz2 - &g_szAll[0]);
643	g_cErrors++;
644	break;
645	}
646	psz2 = RTStrNextCp(psz2);
647	if (psz2 != psz1)
648	{
649	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetNext returned different next pointer!\n");
650	whereami(8, psz2 - &g_szAll[0]);
651	g_cErrors++;
652	break;
653	}
654
655	RTUNICP uc3;
656	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
657	if (RT_FAILURE(rc))
658	{
659	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, pwsz4);
660	whereami(16, pwsz4 - &g_wszAll[0]);
661	g_cErrors++;
662	break;
663	}
664	if (uc3 != uc2)
665	{
666	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc2);
667	whereami(16, pwsz4 - &g_wszAll[0]);
668	g_cErrors++;
669	break;
670	}
671	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
672	if (uc3 != uc4)
673	{
674	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc4);
675	whereami(16, pwsz4 - &g_wszAll[0]);
676	g_cErrors++;
677	break;
678	}
679	pwsz4 = RTUtf16NextCp(pwsz4);
680	if (pwsz4 != pwsz3)
681	{
682	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!\n");
683	whereami(8, pwsz4 - &g_wszAll[0]);
684	g_cErrors++;
685	break;
686	}
687
688
689	/*
690	* putters
691	*/
692	pszPut1 = RTStrPutCp(pszPut1, uc1);
693	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
694	{
695	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
696	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
697	whereami(8, psz2 - &g_szAll[0]);
698	g_cErrors++;
699	break;
700	}
701
702	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
703	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
704	{
705	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
706	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
707	whereami(8, pwsz4 - &g_wszAll[0]);
708	g_cErrors++;
709	break;
710	}
711
712
713	/* the end? */
714	if (!uc1)
715	break;
716	}
717
718	/* check output if we seems to have made it thru it all. */
719	if (psz2 == &g_szAll[sizeof(g_szAll)])
720	{
721	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
722	{
723	RTPrintf("tstUtf8: FAILURE - RTStrPutCp encoded the string incorrectly.\n");
724	g_cErrors++;
725	}
726	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
727	{
728	RTPrintf("tstUtf8: FAILURE - RTUtf16PutCp encoded the string incorrectly.\n");
729	g_cErrors++;
730	}
731	}
732
733	RTMemFree(pszPut1Base);
734	RTMemFree(pwszPut2Base);
735	}
736
737
738	/**
739	* Check case insensitivity.
740	*/
741	void test3(void)
742	{
743	RTPrintf("tstUtf8: TEST 3\n");
744
745	if ( RTUniCpToLower('a') != 'a'
746	\|\| RTUniCpToLower('A') != 'a'
747	\|\| RTUniCpToLower('b') != 'b'
748	\|\| RTUniCpToLower('B') != 'b'
749	\|\| RTUniCpToLower('Z') != 'z'
750	\|\| RTUniCpToLower('z') != 'z'
751	\|\| RTUniCpToUpper('c') != 'C'
752	\|\| RTUniCpToUpper('C') != 'C'
753	\|\| RTUniCpToUpper('z') != 'Z'
754	\|\| RTUniCpToUpper('Z') != 'Z')
755	{
756	RTPrintf("tstUtf8: FAILURE - RTUniToUpper/Lower failed basic tests.\n");
757	g_cErrors++;
758	}
759
760	if (RTUtf16ICmp(g_wszAll, g_wszAll))
761	{
762	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the basic test.\n");
763	g_cErrors++;
764	}
765
766	if (RTUtf16Cmp(g_wszAll, g_wszAll))
767	{
768	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the basic test.\n");
769	g_cErrors++;
770	}
771
772	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 };
773	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 };
774	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
775	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
776	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
777	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
778	)
779	{
780	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the alphabet test.\n");
781	g_cErrors++;
782	}
783
784	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
785	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
786	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
787	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
788	)
789	{
790	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the alphabet test.\n");
791	g_cErrors++;
792	}
793	}
794
795
796	/**
797	* Benchmark stuff.
798	*/
799	void Benchmarks(void)
800	{
801	RTPrintf("tstUtf8: BENCHMARKS\n");
802	static union
803	{
804	RTUTF16 wszBuf[sizeof(g_wszAll)];
805	char szBuf[sizeof(g_szAll)];
806	} s_Buf;
807
808	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
809	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
810	if (RT_SUCCESS(rc))
811	{
812	int i;
813	uint64_t u64Start = RTTimeNanoTS();
814	for (i = 0; i < 100; i++)
815	{
816	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
817	if (RT_FAILURE(rc))
818	{
819	RTPrintf("tstUtf8: UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
820	break;
821	}
822	}
823	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
824	RTPrintf("tstUtf8: UTF-8 -> UTF-16: %d in %RI64ns\n", i, u64Elapsed);
825	}
826
827	char *psz = &s_Buf.szBuf[0];
828	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
829	if (RT_SUCCESS(rc))
830	{
831	int i;
832	uint64_t u64Start = RTTimeNanoTS();
833	for (i = 0; i < 100; i++)
834	{
835	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
836	if (RT_FAILURE(rc))
837	{
838	RTPrintf("tstUtf8: UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
839	break;
840	}
841	}
842	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
843	RTPrintf("tstUtf8: UTF-16 -> UTF-8: %d in %RI64ns\n", i, u64Elapsed);
844	}
845
846	}
847
848
849	int main()
850	{
851	RTR3Init(false);
852
853	InitStrings();
854	test1();
855	test2();
856	test3();
857	Benchmarks();
858
859	/*
860	* Summary
861	*/
862	if (!g_cErrors)
863	RTPrintf("tstUtf8: SUCCESS\n");
864	else
865	RTPrintf("tstUtf8: FAILURE - %d errors!\n", g_cErrors);
866
867	return !!g_cErrors;
868	}

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 7418

Download in other formats: