tstUtf8.cpp@ 8245

Last change on this file since 8245 was 8245, checked in by vboxsync, 16 years ago
rebranding: IPRT files again.
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 29.1 KB

Line
1	/* $Id: tstUtf8.cpp 8245 2008-04-21 17:24:28Z vboxsync $ */
2	/** @file
3	* IPRT Testcase - UTF-8 and UTF-16 string conversions.
4	*/
5
6	/*
7	* Copyright (C) 2006-2007 Sun Microsystems, Inc.
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	* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa
27	* Clara, CA 95054 USA or visit http://www.sun.com if you need
28	* additional information or have any questions.
29	*/
30
31	/*******************************************************************************
32	* Header Files *
33	*******************************************************************************/
34	#include <iprt/string.h>
35	#include <iprt/uni.h>
36	#include <iprt/runtime.h>
37	#include <iprt/uuid.h>
38	#include <iprt/time.h>
39	#include <iprt/stream.h>
40	#include <iprt/alloc.h>
41	#include <iprt/assert.h>
42	#include <iprt/err.h>
43
44	#include <stdlib.h>
45
46
47	/*******************************************************************************
48	* Global Variables *
49	*******************************************************************************/
50	static int g_cErrors = 0;
51
52
53	/**
54	* Generate a random codepoint for simple UTF-16 encoding.
55	*/
56	static RTUTF16 GetRandUtf16(void)
57	{
58	RTUTF16 wc;
59	do
60	{
61	wc = (RTUTF16)((long long)rand() * 0xffff / RAND_MAX);
62	} while ((wc >= 0xd800 && wc <= 0xdfff) \|\| wc == 0);
63	return wc;
64	}
65
66
67	/**
68	*
69	*/
70	static void test1(void)
71	{
72	static const char s_szBadString1[] = "Bad \xe0\x13\x0";
73	static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
74	int rc;
75	char *pszUtf8;
76	char *pszCurrent;
77	PRTUTF16 pwsz;
78	PRTUTF16 pwszRand;
79
80	RTPrintf("tstUtf8: TEST 1\n");
81
82	/*
83	* Invalid UTF-8 to UCS-2 test.
84	*/
85	rc = RTStrToUtf16(s_szBadString1, &pwsz);
86	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
87	{
88	RTPrintf("tstUtf8: FAILURE - %d: Conversion of first bad UTF-8 string to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
89	__LINE__, rc);
90	g_cErrors++;
91	}
92	rc = RTStrToUtf16(s_szBadString2, &pwsz);
93	if (rc != VERR_NO_TRANSLATION && rc != VERR_INVALID_UTF8_ENCODING)
94	{
95	RTPrintf("tstUtf8: FAILURE - %d: Conversion of second bad UTF-8 strings to UTF-16 apparantly succeeded. It shouldn't. rc=%Vrc\n",
96	__LINE__, rc);
97	g_cErrors++;
98	}
99
100	/*
101	* Test current CP convertion.
102	*/
103	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
104	srand((unsigned)RTTimeNanoTS());
105	for (int i = 0; i < 30; i++)
106	pwszRand[i] = GetRandUtf16();
107	pwszRand[30] = 0;
108
109	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
110	if (rc == VINF_SUCCESS)
111	{
112	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
113	if (rc == VINF_SUCCESS)
114	{
115	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
116	if (rc == VINF_SUCCESS)
117	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
118	else
119	{
120	RTPrintf("tstUtf8: FAILURE - %d: The third 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 if (rc == VERR_NO_TRANSLATION)
126	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");
127	else
128	{
129	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
130	__LINE__, rc);
131	g_cErrors++;
132	}
133	}
134	else
135	{
136	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Vrc.\n",
137	__LINE__, rc);
138	g_cErrors++;
139	}
140
141	/*
142	* Generate a new random string.
143	*/
144	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
145	srand((unsigned)RTTimeNanoTS());
146	for (int i = 0; i < 30; i++)
147	pwszRand[i] = GetRandUtf16();
148	pwszRand[30] = 0;
149	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
150	if (rc == VINF_SUCCESS)
151	{
152	rc = RTStrToUtf16(pszUtf8, &pwsz);
153	if (rc == VINF_SUCCESS)
154	{
155	int i;
156	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
157	/* nothing */;
158	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
159	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
160	else
161	{
162	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.\n", __LINE__);
163	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
164	g_cErrors++;
165	}
166	}
167	else
168	{
169	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
170	__LINE__, rc);
171	g_cErrors++;
172	}
173	}
174	else
175	{
176	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Vrc.\n",
177	__LINE__, rc);
178	g_cErrors++;
179	}
180
181	/*
182	* Generate yet another random string and convert it to a buffer.
183	*/
184	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
185	srand((unsigned)RTTimeNanoTS());
186	for (int i = 0; i < 30; i++)
187	pwszRand[i] = GetRandUtf16();
188	pwszRand[30] = 0;
189
190	char szUtf8Array[120];
191	char *pszUtf8Array = szUtf8Array;
192	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
193	if (rc == 0)
194	{
195	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
196	if (rc == 0)
197	{
198	int i;
199	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++);
200	if (pwsz[i] == 0 && i >= 8)
201	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
202	else
203	{
204	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
205	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
206	g_cErrors++;
207	}
208	}
209	else
210	{
211	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
212	__LINE__, rc);
213	g_cErrors++;
214	}
215	}
216	else
217	{
218	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Vrc.\n",
219	__LINE__, rc);
220	g_cErrors++;
221	}
222
223	/*
224	* And again.
225	*/
226	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
227	srand((unsigned)RTTimeNanoTS());
228	for (int i = 0; i < 30; i++)
229	pwszRand[i] = GetRandUtf16();
230	pwszRand[30] = 0;
231
232	RTUTF16 wszBuf[70];
233	PRTUTF16 pwsz2Buf = wszBuf;
234	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
235	if (rc == 0)
236	{
237	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
238	if (rc == 0)
239	{
240	int i;
241	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++);
242	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
243	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
244	else
245	{
246	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
247	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
248	g_cErrors++;
249	}
250	}
251	else
252	{
253	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
254	__LINE__, rc);
255	g_cErrors++;
256	}
257	}
258	else
259	{
260	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
261	__LINE__, rc);
262	g_cErrors++;
263	}
264	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
265	srand((unsigned)RTTimeNanoTS());
266	for (int i = 0; i < 30; i++)
267	pwszRand[i] = GetRandUtf16();
268	pwszRand[30] = 0;
269
270	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
271	if (rc == VERR_BUFFER_OVERFLOW)
272	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
273	else
274	{
275	RTPrintf("tstUtf8: FAILURE - %d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
276	__LINE__, rc);
277	g_cErrors++;
278	}
279
280	/*
281	* last time...
282	*/
283	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
284	srand((unsigned)RTTimeNanoTS());
285	for (int i = 0; i < 30; i++)
286	pwszRand[i] = GetRandUtf16();
287	pwszRand[30] = 0;
288
289	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
290	if (rc == VINF_SUCCESS)
291	{
292	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
293	if (rc == VERR_BUFFER_OVERFLOW)
294	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
295	else
296	{
297	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",
298	__LINE__, rc);
299	g_cErrors++;
300	}
301	}
302	else
303	{
304	RTPrintf("tstUtf8: FAILURE - %d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Vrc.\n",
305	__LINE__, rc);
306	g_cErrors++;
307	}
308
309	}
310
311
312	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
313	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
314	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
315
316	static void whereami(int cBits, size_t off)
317	{
318	if (cBits == 8)
319	{
320	if (off < 0x7f)
321	RTPrintf("UTF-8 U+%#x\n", off + 1);
322	else if (off < 0xf7f)
323	RTPrintf("UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
324	else if (off < 0x27f7f)
325	RTPrintf("UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
326	else if (off < 0x2df79)
327	RTPrintf("UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
328	else if (off < 0x42df79)
329	RTPrintf("UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
330	else
331	RTPrintf("UTF-8 ???\n");
332	}
333	else if (cBits == 16)
334	{
335	if (off < 0xd7ff*2)
336	RTPrintf("UTF-16 U+%#x\n", off / 2 + 1);
337	else if (off < 0xf7fd*2)
338	RTPrintf("UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
339	else if (off < 0x20f7fd)
340	RTPrintf("UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
341	else
342	RTPrintf("UTF-16 ???\n");
343	}
344	else
345	{
346	if (off < (0xd800 - 1) * sizeof(RTUNICP))
347	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
348	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
349	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
350	else
351	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
352	}
353	}
354
355	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
356	{
357	const uint8_t pb1 = (const uint8_t )pv1;
358	const uint8_t pb2 = (const uint8_t )pv2;
359	for (size_t off = 0; off < cb; off++)
360	{
361	if (pb1[off] != pb2[off])
362	{
363	RTPrintf("mismatch at %#x: ", off);
364	whereami(cBits, off);
365	RTPrintf(" %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
366	RTPrintf("*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
367	RTPrintf(" %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
368	RTPrintf(" %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
369	RTPrintf(" %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
370	RTPrintf(" %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
371	RTPrintf(" %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
372	RTPrintf(" %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
373	RTPrintf(" %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
374	RTPrintf(" %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
375	RTPrintf(" %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
376	return 1;
377	}
378	}
379	return 0;
380	}
381
382
383	void InitStrings(void)
384	{
385	/*
386	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
387	*/
388	/* the simple code point array first */
389	unsigned i = 0;
390	RTUNICP uc = 1;
391	while (uc < 0xd800)
392	g_uszAll[i++] = uc++;
393	uc = 0xe000;
394	while (uc < 0xfffe)
395	g_uszAll[i++] = uc++;
396	uc = 0x10000;
397	while (uc < 0x110000)
398	g_uszAll[i++] = uc++;
399	g_uszAll[i++] = 0;
400	Assert(ELEMENTS(g_uszAll) == i);
401
402	/* the utf-16 one */
403	i = 0;
404	uc = 1;
405	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
406	while (uc < 0xd800)
407	g_wszAll[i++] = uc++;
408	uc = 0xe000;
409	//RTPrintf(" %#x=%#x", i, uc);
410	while (uc < 0xfffe)
411	g_wszAll[i++] = uc++;
412	uc = 0x10000;
413	//RTPrintf(" %#x=%#x", i, uc);
414	while (uc < 0x110000)
415	{
416	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
417	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
418	uc++;
419	}
420	//RTPrintf(" %#x=%#x\n", i, uc);
421	g_wszAll[i++] = '\0';
422	Assert(ELEMENTS(g_wszAll) == i);
423
424	/*
425	* The utf-8 one
426	*/
427	i = 0;
428	uc = 1;
429	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
430	while (uc < 0x80)
431	g_szAll[i++] = uc++;
432	//RTPrintf(" %#x=%#x", i, uc);
433	while (uc < 0x800)
434	{
435	g_szAll[i++] = 0xc0 \| (uc >> 6);
436	g_szAll[i++] = 0x80 \| (uc & 0x3f);
437	Assert(!((uc >> 6) & ~0x1f));
438	uc++;
439	}
440	//RTPrintf(" %#x=%#x", i, uc);
441	while (uc < 0xd800)
442	{
443	g_szAll[i++] = 0xe0 \| (uc >> 12);
444	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
445	g_szAll[i++] = 0x80 \| (uc & 0x3f);
446	Assert(!((uc >> 12) & ~0xf));
447	uc++;
448	}
449	uc = 0xe000;
450	//RTPrintf(" %#x=%#x", i, uc);
451	while (uc < 0xfffe)
452	{
453	g_szAll[i++] = 0xe0 \| (uc >> 12);
454	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
455	g_szAll[i++] = 0x80 \| (uc & 0x3f);
456	Assert(!((uc >> 12) & ~0xf));
457	uc++;
458	}
459	uc = 0x10000;
460	//RTPrintf(" %#x=%#x", i, uc);
461	while (uc < 0x110000)
462	{
463	g_szAll[i++] = 0xf0 \| (uc >> 18);
464	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
465	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
466	g_szAll[i++] = 0x80 \| (uc & 0x3f);
467	Assert(!((uc >> 18) & ~0x7));
468	uc++;
469	}
470	//RTPrintf(" %#x=%#x\n", i, uc);
471	g_szAll[i++] = '\0';
472	Assert(ELEMENTS(g_szAll) == i);
473	}
474
475
476	void test2(void)
477	{
478	RTPrintf("tstUtf8: TEST 2\n");
479
480	/*
481	* Convert to UTF-8 and back.
482	*/
483	RTPrintf("tstUtf8: #1: UTF-16 -> UTF-8 -> UTF-16...\n");
484	char *pszUtf8;
485	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
486	if (rc == VINF_SUCCESS)
487	{
488	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
489	{
490	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 mismatch!\n");
491	g_cErrors++;
492	}
493
494	PRTUTF16 pwszUtf16;
495	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
496	if (rc == VINF_SUCCESS)
497	{
498	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
499	{
500	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed compare!\n");
501	g_cErrors++;
502	}
503	RTUtf16Free(pwszUtf16);
504	}
505	else
506	{
507	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
508	g_cErrors++;
509	}
510	RTStrFree(pszUtf8);
511	}
512	else
513	{
514	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
515	g_cErrors++;
516	}
517
518
519	/*
520	* Convert to UTF-16 and back. (just in case the above test fails)
521	*/
522	RTPrintf("tstUtf8: #2: UTF-8 -> UTF-16 -> UTF-8...\n");
523	PRTUTF16 pwszUtf16;
524	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
525	if (rc == VINF_SUCCESS)
526	{
527	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
528	{
529	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed compare!\n");
530	g_cErrors++;
531	}
532
533	char *pszUtf8;
534	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
535	if (rc == VINF_SUCCESS)
536	{
537	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
538	{
539	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed compare!\n");
540	g_cErrors++;
541	}
542	RTStrFree(pszUtf8);
543	}
544	else
545	{
546	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
547	g_cErrors++;
548	}
549	RTUtf16Free(pwszUtf16);
550	}
551	else
552	{
553	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
554	g_cErrors++;
555	}
556
557	/*
558	* Convert UTF-8 to CPs.
559	*/
560	PRTUNICP paCps;
561	rc = RTStrToUni(g_szAll, &paCps);
562	if (rc == VINF_SUCCESS)
563	{
564	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
565	{
566	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
567	g_cErrors++;
568	}
569
570	size_t cCps;
571	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, ELEMENTS(g_uszAll), &cCps);
572	if (rc == VINF_SUCCESS)
573	{
574	if (cCps != ELEMENTS(g_uszAll) - 1)
575	{
576	RTPrintf("tstUtf8: FAILURE - the full #3+: wrong Code Point count %zu, expected %zu\n", cCps, ELEMENTS(g_uszAll) - 1);
577	g_cErrors++;
578	}
579	}
580	else
581	{
582	RTPrintf("tstUtf8: FAILURE - the full #3+: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
583	g_cErrors++;
584	}
585
586	/** @todo RTCpsToUtf8 or something. */
587	}
588	else
589	{
590	RTPrintf("tstUtf8: FAILURE - the full #3a: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
591	g_cErrors++;
592	}
593
594	/*
595	* Check the various string lengths.
596	*/
597	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
598	size_t cuc2 = RTUtf16Len(g_wszAll);
599	if (cuc1 != cuc2)
600	{
601	RTPrintf("tstUtf8: FAILURE - cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
602	g_cErrors++;
603	}
604	//size_t cuc3 = RTUniLen(g_uszAll);
605
606
607	/*
608	* Enumerate the strings.
609	*/
610	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
611	AssertRelease(pszPut1Base);
612	char *pszPut1 = pszPut1Base;
613	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
614	AssertRelease(pwszPut2Base);
615	PRTUTF16 pwszPut2 = pwszPut2Base;
616	const char *psz1 = g_szAll;
617	const char *psz2 = g_szAll;
618	PCRTUTF16 pwsz3 = g_wszAll;
619	PCRTUTF16 pwsz4 = g_wszAll;
620	for (;;)
621	{
622	/*
623	* getters
624	*/
625	RTUNICP uc1;
626	rc = RTStrGetCpEx(&psz1, &uc1);
627	if (RT_FAILURE(rc))
628	{
629	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, psz2);
630	whereami(8, psz2 - &g_szAll[0]);
631	g_cErrors++;
632	break;
633	}
634	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
635	if (pszPrev1 != psz2)
636	{
637	RTPrintf("tstUtf8: FAILURE - RTStrPrevCp returned %p expected %p!\n", pszPrev1, psz2);
638	whereami(8, psz2 - &g_szAll[0]);
639	g_cErrors++;
640	break;
641	}
642	RTUNICP uc2 = RTStrGetCp(psz2);
643	if (uc2 != uc1)
644	{
645	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc2, uc1);
646	whereami(8, psz2 - &g_szAll[0]);
647	g_cErrors++;
648	break;
649	}
650	psz2 = RTStrNextCp(psz2);
651	if (psz2 != psz1)
652	{
653	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetNext returned different next pointer!\n");
654	whereami(8, psz2 - &g_szAll[0]);
655	g_cErrors++;
656	break;
657	}
658
659	RTUNICP uc3;
660	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
661	if (RT_FAILURE(rc))
662	{
663	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, pwsz4);
664	whereami(16, pwsz4 - &g_wszAll[0]);
665	g_cErrors++;
666	break;
667	}
668	if (uc3 != uc2)
669	{
670	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc2);
671	whereami(16, pwsz4 - &g_wszAll[0]);
672	g_cErrors++;
673	break;
674	}
675	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
676	if (uc3 != uc4)
677	{
678	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc4);
679	whereami(16, pwsz4 - &g_wszAll[0]);
680	g_cErrors++;
681	break;
682	}
683	pwsz4 = RTUtf16NextCp(pwsz4);
684	if (pwsz4 != pwsz3)
685	{
686	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!\n");
687	whereami(8, pwsz4 - &g_wszAll[0]);
688	g_cErrors++;
689	break;
690	}
691
692
693	/*
694	* putters
695	*/
696	pszPut1 = RTStrPutCp(pszPut1, uc1);
697	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
698	{
699	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
700	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
701	whereami(8, psz2 - &g_szAll[0]);
702	g_cErrors++;
703	break;
704	}
705
706	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
707	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
708	{
709	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
710	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
711	whereami(8, pwsz4 - &g_wszAll[0]);
712	g_cErrors++;
713	break;
714	}
715
716
717	/* the end? */
718	if (!uc1)
719	break;
720	}
721
722	/* check output if we seems to have made it thru it all. */
723	if (psz2 == &g_szAll[sizeof(g_szAll)])
724	{
725	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
726	{
727	RTPrintf("tstUtf8: FAILURE - RTStrPutCp encoded the string incorrectly.\n");
728	g_cErrors++;
729	}
730	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
731	{
732	RTPrintf("tstUtf8: FAILURE - RTUtf16PutCp encoded the string incorrectly.\n");
733	g_cErrors++;
734	}
735	}
736
737	RTMemFree(pszPut1Base);
738	RTMemFree(pwszPut2Base);
739	}
740
741
742	/**
743	* Check case insensitivity.
744	*/
745	void test3(void)
746	{
747	RTPrintf("tstUtf8: TEST 3\n");
748
749	if ( RTUniCpToLower('a') != 'a'
750	\|\| RTUniCpToLower('A') != 'a'
751	\|\| RTUniCpToLower('b') != 'b'
752	\|\| RTUniCpToLower('B') != 'b'
753	\|\| RTUniCpToLower('Z') != 'z'
754	\|\| RTUniCpToLower('z') != 'z'
755	\|\| RTUniCpToUpper('c') != 'C'
756	\|\| RTUniCpToUpper('C') != 'C'
757	\|\| RTUniCpToUpper('z') != 'Z'
758	\|\| RTUniCpToUpper('Z') != 'Z')
759	{
760	RTPrintf("tstUtf8: FAILURE - RTUniToUpper/Lower failed basic tests.\n");
761	g_cErrors++;
762	}
763
764	if (RTUtf16ICmp(g_wszAll, g_wszAll))
765	{
766	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the basic test.\n");
767	g_cErrors++;
768	}
769
770	if (RTUtf16Cmp(g_wszAll, g_wszAll))
771	{
772	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the basic test.\n");
773	g_cErrors++;
774	}
775
776	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 };
777	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 };
778	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
779	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
780	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
781	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
782	)
783	{
784	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the alphabet test.\n");
785	g_cErrors++;
786	}
787
788	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
789	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
790	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
791	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
792	)
793	{
794	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the alphabet test.\n");
795	g_cErrors++;
796	}
797	}
798
799
800	/**
801	* Test the RTStr*Cmp functions.
802	*/
803	void TstRTStrXCmp(void)
804	{
805	RTPrintf("tstUtf8: TESTING RTStr*Cmp\n");
806	#define CHECK_DIFF(expr, op) \
807	do \
808	{ \
809	int iDiff = expr; \
810	if (!(iDiff op 0)) \
811	{ \
812	RTPrintf("tstUtf8(%d): failure - %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
813	g_cErrors++; \
814	} \
815	} while (0)
816
817	/** @todo test the non-ascii bits. */
818
819	CHECK_DIFF(RTStrCmp(NULL, NULL), == );
820	CHECK_DIFF(RTStrCmp(NULL, ""), < );
821	CHECK_DIFF(RTStrCmp("", NULL), > );
822	CHECK_DIFF(RTStrCmp("", ""), == );
823	CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
824	CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
825	CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
826	CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
827	CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
828	CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
829	CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
830
831
832	CHECK_DIFF(RTStrICmp(NULL, NULL), == );
833	CHECK_DIFF(RTStrICmp(NULL, ""), < );
834	CHECK_DIFF(RTStrICmp("", NULL), > );
835	CHECK_DIFF(RTStrICmp("", ""), == );
836	CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
837	CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
838	CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
839	CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
840	CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
841
842	CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), == );
843	CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
844	CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
845	CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
846	CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
847	CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
848	CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
849	}
850
851
852
853	/**
854	* Benchmark stuff.
855	*/
856	void Benchmarks(void)
857	{
858	RTPrintf("tstUtf8: BENCHMARKS\n");
859	static union
860	{
861	RTUTF16 wszBuf[sizeof(g_wszAll)];
862	char szBuf[sizeof(g_szAll)];
863	} s_Buf;
864
865	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
866	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
867	if (RT_SUCCESS(rc))
868	{
869	int i;
870	uint64_t u64Start = RTTimeNanoTS();
871	for (i = 0; i < 100; i++)
872	{
873	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, ELEMENTS(s_Buf.wszBuf), NULL);
874	if (RT_FAILURE(rc))
875	{
876	RTPrintf("tstUtf8: UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
877	break;
878	}
879	}
880	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
881	RTPrintf("tstUtf8: UTF-8 -> UTF-16: %d in %RI64ns\n", i, u64Elapsed);
882	}
883
884	char *psz = &s_Buf.szBuf[0];
885	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
886	if (RT_SUCCESS(rc))
887	{
888	int i;
889	uint64_t u64Start = RTTimeNanoTS();
890	for (i = 0; i < 100; i++)
891	{
892	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, ELEMENTS(s_Buf.szBuf), NULL);
893	if (RT_FAILURE(rc))
894	{
895	RTPrintf("tstUtf8: UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
896	break;
897	}
898	}
899	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
900	RTPrintf("tstUtf8: UTF-16 -> UTF-8: %d in %RI64ns\n", i, u64Elapsed);
901	}
902
903	}
904
905
906	int main()
907	{
908	RTR3Init(false);
909
910	InitStrings();
911	test1();
912	test2();
913	test3();
914	TstRTStrXCmp();
915	Benchmarks();
916
917	/*
918	* Summary
919	*/
920	if (!g_cErrors)
921	RTPrintf("tstUtf8: SUCCESS\n");
922	else
923	RTPrintf("tstUtf8: FAILURE - %d errors!\n", g_cErrors);
924
925	return !!g_cErrors;
926	}

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 8245

Download in other formats: