tstUtf8.cpp@ 16684

Last change on this file since 16684 was 14831, checked in by vboxsync, 16 years ago
whole bunch: avoid runtime.h, include individual headers indead.
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 31.8 KB

Line
1	/* $Id: tstUtf8.cpp 14831 2008-11-30 10:31:16Z 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/initterm.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=%Rrc\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=%Rrc\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 %Rrc.\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 %Rrc.\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 %Rrc.\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 %Rrc.\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 %Rrc.\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	;
201	if (pwsz[i] == 0 && i >= 8)
202	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
203	else
204	{
205	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
206	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
207	g_cErrors++;
208	}
209	}
210	else
211	{
212	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n",
213	__LINE__, rc);
214	g_cErrors++;
215	}
216	}
217	else
218	{
219	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n",
220	__LINE__, rc);
221	g_cErrors++;
222	}
223
224	/*
225	* And again.
226	*/
227	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
228	srand((unsigned)RTTimeNanoTS());
229	for (int i = 0; i < 30; i++)
230	pwszRand[i] = GetRandUtf16();
231	pwszRand[30] = 0;
232
233	RTUTF16 wszBuf[70];
234	PRTUTF16 pwsz2Buf = wszBuf;
235	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
236	if (rc == 0)
237	{
238	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
239	if (rc == 0)
240	{
241	int i;
242	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++)
243	;
244	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
245	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
246	else
247	{
248	RTPrintf("tstUtf8: FAILURE - %d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
249	RTPrintf("tstUtf8: First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
250	g_cErrors++;
251	}
252	}
253	else
254	{
255	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
256	__LINE__, rc);
257	g_cErrors++;
258	}
259	}
260	else
261	{
262	RTPrintf("tstUtf8: FAILURE - %d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
263	__LINE__, rc);
264	g_cErrors++;
265	}
266	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
267	srand((unsigned)RTTimeNanoTS());
268	for (int i = 0; i < 30; i++)
269	pwszRand[i] = GetRandUtf16();
270	pwszRand[30] = 0;
271
272	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
273	if (rc == VERR_BUFFER_OVERFLOW)
274	RTPrintf("tstUtf8: Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
275	else
276	{
277	RTPrintf("tstUtf8: FAILURE - %d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
278	__LINE__, rc);
279	g_cErrors++;
280	}
281
282	/*
283	* last time...
284	*/
285	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
286	srand((unsigned)RTTimeNanoTS());
287	for (int i = 0; i < 30; i++)
288	pwszRand[i] = GetRandUtf16();
289	pwszRand[30] = 0;
290
291	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
292	if (rc == VINF_SUCCESS)
293	{
294	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
295	if (rc == VERR_BUFFER_OVERFLOW)
296	RTPrintf("tstUtf8: Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
297	else
298	{
299	RTPrintf("tstUtf8: FAILURE - %d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer returned value %Rrc instead of VERR_BUFFER_OVERFLOW.\n",
300	__LINE__, rc);
301	g_cErrors++;
302	}
303	}
304	else
305	{
306	RTPrintf("tstUtf8: FAILURE - %d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
307	__LINE__, rc);
308	g_cErrors++;
309	}
310
311	}
312
313
314	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
315	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
316	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
317
318	static void whereami(int cBits, size_t off)
319	{
320	if (cBits == 8)
321	{
322	if (off < 0x7f)
323	RTPrintf("UTF-8 U+%#x\n", off + 1);
324	else if (off < 0xf7f)
325	RTPrintf("UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
326	else if (off < 0x27f7f)
327	RTPrintf("UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
328	else if (off < 0x2df79)
329	RTPrintf("UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
330	else if (off < 0x42df79)
331	RTPrintf("UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
332	else
333	RTPrintf("UTF-8 ???\n");
334	}
335	else if (cBits == 16)
336	{
337	if (off < 0xd7ff*2)
338	RTPrintf("UTF-16 U+%#x\n", off / 2 + 1);
339	else if (off < 0xf7fd*2)
340	RTPrintf("UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
341	else if (off < 0x20f7fd)
342	RTPrintf("UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
343	else
344	RTPrintf("UTF-16 ???\n");
345	}
346	else
347	{
348	if (off < (0xd800 - 1) * sizeof(RTUNICP))
349	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
350	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
351	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
352	else
353	RTPrintf("RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
354	}
355	}
356
357	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
358	{
359	const uint8_t pb1 = (const uint8_t )pv1;
360	const uint8_t pb2 = (const uint8_t )pv2;
361	for (size_t off = 0; off < cb; off++)
362	{
363	if (pb1[off] != pb2[off])
364	{
365	RTPrintf("mismatch at %#x: ", off);
366	whereami(cBits, off);
367	RTPrintf(" %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
368	RTPrintf("*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
369	RTPrintf(" %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
370	RTPrintf(" %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
371	RTPrintf(" %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
372	RTPrintf(" %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
373	RTPrintf(" %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
374	RTPrintf(" %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
375	RTPrintf(" %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
376	RTPrintf(" %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
377	RTPrintf(" %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
378	return 1;
379	}
380	}
381	return 0;
382	}
383
384
385	void InitStrings(void)
386	{
387	/*
388	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
389	*/
390	/* the simple code point array first */
391	unsigned i = 0;
392	RTUNICP uc = 1;
393	while (uc < 0xd800)
394	g_uszAll[i++] = uc++;
395	uc = 0xe000;
396	while (uc < 0xfffe)
397	g_uszAll[i++] = uc++;
398	uc = 0x10000;
399	while (uc < 0x110000)
400	g_uszAll[i++] = uc++;
401	g_uszAll[i++] = 0;
402	Assert(RT_ELEMENTS(g_uszAll) == i);
403
404	/* the utf-16 one */
405	i = 0;
406	uc = 1;
407	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
408	while (uc < 0xd800)
409	g_wszAll[i++] = uc++;
410	uc = 0xe000;
411	//RTPrintf(" %#x=%#x", i, uc);
412	while (uc < 0xfffe)
413	g_wszAll[i++] = uc++;
414	uc = 0x10000;
415	//RTPrintf(" %#x=%#x", i, uc);
416	while (uc < 0x110000)
417	{
418	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
419	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
420	uc++;
421	}
422	//RTPrintf(" %#x=%#x\n", i, uc);
423	g_wszAll[i++] = '\0';
424	Assert(RT_ELEMENTS(g_wszAll) == i);
425
426	/*
427	* The utf-8 one
428	*/
429	i = 0;
430	uc = 1;
431	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
432	while (uc < 0x80)
433	g_szAll[i++] = uc++;
434	//RTPrintf(" %#x=%#x", i, uc);
435	while (uc < 0x800)
436	{
437	g_szAll[i++] = 0xc0 \| (uc >> 6);
438	g_szAll[i++] = 0x80 \| (uc & 0x3f);
439	Assert(!((uc >> 6) & ~0x1f));
440	uc++;
441	}
442	//RTPrintf(" %#x=%#x", i, uc);
443	while (uc < 0xd800)
444	{
445	g_szAll[i++] = 0xe0 \| (uc >> 12);
446	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
447	g_szAll[i++] = 0x80 \| (uc & 0x3f);
448	Assert(!((uc >> 12) & ~0xf));
449	uc++;
450	}
451	uc = 0xe000;
452	//RTPrintf(" %#x=%#x", i, uc);
453	while (uc < 0xfffe)
454	{
455	g_szAll[i++] = 0xe0 \| (uc >> 12);
456	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
457	g_szAll[i++] = 0x80 \| (uc & 0x3f);
458	Assert(!((uc >> 12) & ~0xf));
459	uc++;
460	}
461	uc = 0x10000;
462	//RTPrintf(" %#x=%#x", i, uc);
463	while (uc < 0x110000)
464	{
465	g_szAll[i++] = 0xf0 \| (uc >> 18);
466	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
467	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
468	g_szAll[i++] = 0x80 \| (uc & 0x3f);
469	Assert(!((uc >> 18) & ~0x7));
470	uc++;
471	}
472	//RTPrintf(" %#x=%#x\n", i, uc);
473	g_szAll[i++] = '\0';
474	Assert(RT_ELEMENTS(g_szAll) == i);
475	}
476
477
478	void test2(void)
479	{
480	RTPrintf("tstUtf8: TEST 2\n");
481
482	/*
483	* Convert to UTF-8 and back.
484	*/
485	RTPrintf("tstUtf8: #1: UTF-16 -> UTF-8 -> UTF-16...\n");
486	char *pszUtf8;
487	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
488	if (rc == VINF_SUCCESS)
489	{
490	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
491	{
492	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 mismatch!\n");
493	g_cErrors++;
494	}
495
496	PRTUTF16 pwszUtf16;
497	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
498	if (rc == VINF_SUCCESS)
499	{
500	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
501	{
502	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed compare!\n");
503	g_cErrors++;
504	}
505	RTUtf16Free(pwszUtf16);
506	}
507	else
508	{
509	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
510	g_cErrors++;
511	}
512	RTStrFree(pszUtf8);
513	}
514	else
515	{
516	RTPrintf("tstUtf8: FAILURE - the full #1: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
517	g_cErrors++;
518	}
519
520
521	/*
522	* Convert to UTF-16 and back. (just in case the above test fails)
523	*/
524	RTPrintf("tstUtf8: #2: UTF-8 -> UTF-16 -> UTF-8...\n");
525	PRTUTF16 pwszUtf16;
526	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
527	if (rc == VINF_SUCCESS)
528	{
529	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
530	{
531	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed compare!\n");
532	g_cErrors++;
533	}
534
535	char *pszUtf8;
536	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
537	if (rc == VINF_SUCCESS)
538	{
539	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
540	{
541	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed compare!\n");
542	g_cErrors++;
543	}
544	RTStrFree(pszUtf8);
545	}
546	else
547	{
548	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-16 -> UTF-8 failed, rc=%Rrc.\n", rc);
549	g_cErrors++;
550	}
551	RTUtf16Free(pwszUtf16);
552	}
553	else
554	{
555	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
556	g_cErrors++;
557	}
558
559	/*
560	* Convert UTF-8 to CPs.
561	*/
562	PRTUNICP paCps;
563	rc = RTStrToUni(g_szAll, &paCps);
564	if (rc == VINF_SUCCESS)
565	{
566	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
567	{
568	RTPrintf("tstUtf8: FAILURE - the full #2: UTF-8 -> UTF-16 failed, rc=%Rrc.\n", rc);
569	g_cErrors++;
570	}
571
572	size_t cCps;
573	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, RT_ELEMENTS(g_uszAll), &cCps);
574	if (rc == VINF_SUCCESS)
575	{
576	if (cCps != RT_ELEMENTS(g_uszAll) - 1)
577	{
578	RTPrintf("tstUtf8: FAILURE - the full #3+: wrong Code Point count %zu, expected %zu\n", cCps, RT_ELEMENTS(g_uszAll) - 1);
579	g_cErrors++;
580	}
581	}
582	else
583	{
584	RTPrintf("tstUtf8: FAILURE - the full #3+: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
585	g_cErrors++;
586	}
587
588	/** @todo RTCpsToUtf8 or something. */
589	}
590	else
591	{
592	RTPrintf("tstUtf8: FAILURE - the full #3a: UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
593	g_cErrors++;
594	}
595
596	/*
597	* Check the various string lengths.
598	*/
599	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
600	size_t cuc2 = RTUtf16Len(g_wszAll);
601	if (cuc1 != cuc2)
602	{
603	RTPrintf("tstUtf8: FAILURE - cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
604	g_cErrors++;
605	}
606	//size_t cuc3 = RTUniLen(g_uszAll);
607
608
609	/*
610	* Enumerate the strings.
611	*/
612	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
613	AssertRelease(pszPut1Base);
614	char *pszPut1 = pszPut1Base;
615	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
616	AssertRelease(pwszPut2Base);
617	PRTUTF16 pwszPut2 = pwszPut2Base;
618	const char *psz1 = g_szAll;
619	const char *psz2 = g_szAll;
620	PCRTUTF16 pwsz3 = g_wszAll;
621	PCRTUTF16 pwsz4 = g_wszAll;
622	for (;;)
623	{
624	/*
625	* getters
626	*/
627	RTUNICP uc1;
628	rc = RTStrGetCpEx(&psz1, &uc1);
629	if (RT_FAILURE(rc))
630	{
631	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, psz2);
632	whereami(8, psz2 - &g_szAll[0]);
633	g_cErrors++;
634	break;
635	}
636	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
637	if (pszPrev1 != psz2)
638	{
639	RTPrintf("tstUtf8: FAILURE - RTStrPrevCp returned %p expected %p!\n", pszPrev1, psz2);
640	whereami(8, psz2 - &g_szAll[0]);
641	g_cErrors++;
642	break;
643	}
644	RTUNICP uc2 = RTStrGetCp(psz2);
645	if (uc2 != uc1)
646	{
647	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc2, uc1);
648	whereami(8, psz2 - &g_szAll[0]);
649	g_cErrors++;
650	break;
651	}
652	psz2 = RTStrNextCp(psz2);
653	if (psz2 != psz1)
654	{
655	RTPrintf("tstUtf8: FAILURE - RTStrGetCpEx and RTStrGetNext returned different next pointer!\n");
656	whereami(8, psz2 - &g_szAll[0]);
657	g_cErrors++;
658	break;
659	}
660
661	RTUNICP uc3;
662	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
663	if (RT_FAILURE(rc))
664	{
665	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs\n", rc, pwsz4);
666	whereami(16, pwsz4 - &g_wszAll[0]);
667	g_cErrors++;
668	break;
669	}
670	if (uc3 != uc2)
671	{
672	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc2);
673	whereami(16, pwsz4 - &g_wszAll[0]);
674	g_cErrors++;
675	break;
676	}
677	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
678	if (uc3 != uc4)
679	{
680	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp\n", uc3, uc4);
681	whereami(16, pwsz4 - &g_wszAll[0]);
682	g_cErrors++;
683	break;
684	}
685	pwsz4 = RTUtf16NextCp(pwsz4);
686	if (pwsz4 != pwsz3)
687	{
688	RTPrintf("tstUtf8: FAILURE - RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!\n");
689	whereami(8, pwsz4 - &g_wszAll[0]);
690	g_cErrors++;
691	break;
692	}
693
694
695	/*
696	* putters
697	*/
698	pszPut1 = RTStrPutCp(pszPut1, uc1);
699	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
700	{
701	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
702	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
703	whereami(8, psz2 - &g_szAll[0]);
704	g_cErrors++;
705	break;
706	}
707
708	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
709	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
710	{
711	RTPrintf("tstUtf8: FAILURE - RTStrPutCp is not at the same offset! %p != %p\n",
712	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
713	whereami(8, pwsz4 - &g_wszAll[0]);
714	g_cErrors++;
715	break;
716	}
717
718
719	/* the end? */
720	if (!uc1)
721	break;
722	}
723
724	/* check output if we seems to have made it thru it all. */
725	if (psz2 == &g_szAll[sizeof(g_szAll)])
726	{
727	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
728	{
729	RTPrintf("tstUtf8: FAILURE - RTStrPutCp encoded the string incorrectly.\n");
730	g_cErrors++;
731	}
732	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
733	{
734	RTPrintf("tstUtf8: FAILURE - RTUtf16PutCp encoded the string incorrectly.\n");
735	g_cErrors++;
736	}
737	}
738
739	RTMemFree(pszPut1Base);
740	RTMemFree(pwszPut2Base);
741	}
742
743
744	/**
745	* Check case insensitivity.
746	*/
747	void test3(void)
748	{
749	RTPrintf("tstUtf8: TEST 3\n");
750
751	if ( RTUniCpToLower('a') != 'a'
752	\|\| RTUniCpToLower('A') != 'a'
753	\|\| RTUniCpToLower('b') != 'b'
754	\|\| RTUniCpToLower('B') != 'b'
755	\|\| RTUniCpToLower('Z') != 'z'
756	\|\| RTUniCpToLower('z') != 'z'
757	\|\| RTUniCpToUpper('c') != 'C'
758	\|\| RTUniCpToUpper('C') != 'C'
759	\|\| RTUniCpToUpper('z') != 'Z'
760	\|\| RTUniCpToUpper('Z') != 'Z')
761	{
762	RTPrintf("tstUtf8: FAILURE - RTUniToUpper/Lower failed basic tests.\n");
763	g_cErrors++;
764	}
765
766	if (RTUtf16ICmp(g_wszAll, g_wszAll))
767	{
768	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the basic test.\n");
769	g_cErrors++;
770	}
771
772	if (RTUtf16Cmp(g_wszAll, g_wszAll))
773	{
774	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the basic test.\n");
775	g_cErrors++;
776	}
777
778	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 };
779	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 };
780	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
781	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
782	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
783	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
784	)
785	{
786	RTPrintf("tstUtf8: FAILURE - RTUtf16ICmp failed the alphabet test.\n");
787	g_cErrors++;
788	}
789
790	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
791	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
792	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
793	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
794	)
795	{
796	RTPrintf("tstUtf8: FAILURE - RTUtf16Cmp failed the alphabet test.\n");
797	g_cErrors++;
798	}
799	}
800
801
802	/**
803	* Test the RTStr*Cmp functions.
804	*/
805	void TstRTStrXCmp(void)
806	{
807	RTPrintf("tstUtf8: TEST 4 - RTStr*Cmp\n");
808	#define CHECK_DIFF(expr, op) \
809	do \
810	{ \
811	int iDiff = expr; \
812	if (!(iDiff op 0)) \
813	{ \
814	RTPrintf("tstUtf8(%d): failure - %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
815	g_cErrors++; \
816	} \
817	} while (0)
818
819	/** @todo test the non-ascii bits. */
820
821	CHECK_DIFF(RTStrCmp(NULL, NULL), == );
822	CHECK_DIFF(RTStrCmp(NULL, ""), < );
823	CHECK_DIFF(RTStrCmp("", NULL), > );
824	CHECK_DIFF(RTStrCmp("", ""), == );
825	CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
826	CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
827	CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
828	CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
829	CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
830	CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
831	CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
832
833
834	CHECK_DIFF(RTStrNCmp(NULL, NULL, RTSTR_MAX), == );
835	CHECK_DIFF(RTStrNCmp(NULL, "", RTSTR_MAX), < );
836	CHECK_DIFF(RTStrNCmp("", NULL, RTSTR_MAX), > );
837	CHECK_DIFF(RTStrNCmp("", "", RTSTR_MAX), == );
838	CHECK_DIFF(RTStrNCmp("abcdef", "abcdef", RTSTR_MAX), == );
839	CHECK_DIFF(RTStrNCmp("abcdef", "abcde", RTSTR_MAX), > );
840	CHECK_DIFF(RTStrNCmp("abcde", "abcdef", RTSTR_MAX), < );
841	CHECK_DIFF(RTStrNCmp("abcdeg", "abcdef", RTSTR_MAX), > );
842	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeg", RTSTR_MAX), < );
843	CHECK_DIFF(RTStrNCmp("abcdeF", "abcdef", RTSTR_MAX), < );
844	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", RTSTR_MAX), > );
845
846	CHECK_DIFF(RTStrNCmp("abcdef", "fedcba", 0), ==);
847	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 5), ==);
848	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 6), > );
849
850
851	CHECK_DIFF(RTStrICmp(NULL, NULL), == );
852	CHECK_DIFF(RTStrICmp(NULL, ""), < );
853	CHECK_DIFF(RTStrICmp("", NULL), > );
854	CHECK_DIFF(RTStrICmp("", ""), == );
855	CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
856	CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
857	CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
858	CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
859	CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
860
861	CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), ==);
862	CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
863	CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
864	CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
865	CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
866	CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
867	CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
868
869
870
871	CHECK_DIFF(RTStrNICmp(NULL, NULL, RTSTR_MAX), == );
872	CHECK_DIFF(RTStrNICmp(NULL, "", RTSTR_MAX), < );
873	CHECK_DIFF(RTStrNICmp("", NULL, RTSTR_MAX), > );
874	CHECK_DIFF(RTStrNICmp("", "", RTSTR_MAX), == );
875	CHECK_DIFF(RTStrNICmp(NULL, NULL, 0), == );
876	CHECK_DIFF(RTStrNICmp(NULL, "", 0), == );
877	CHECK_DIFF(RTStrNICmp("", NULL, 0), == );
878	CHECK_DIFF(RTStrNICmp("", "", 0), == );
879	CHECK_DIFF(RTStrNICmp("abcdef", "abcdef", RTSTR_MAX), == );
880	CHECK_DIFF(RTStrNICmp("abcdef", "abcde", RTSTR_MAX), > );
881	CHECK_DIFF(RTStrNICmp("abcde", "abcdef", RTSTR_MAX), < );
882	CHECK_DIFF(RTStrNICmp("abcdeg", "abcdef", RTSTR_MAX), > );
883	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeg", RTSTR_MAX), < );
884
885	CHECK_DIFF(RTStrNICmp("abcdeF", "abcdef", RTSTR_MAX), ==);
886	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeF", RTSTR_MAX), ==);
887	CHECK_DIFF(RTStrNICmp("ABCDEF", "abcdef", RTSTR_MAX), ==);
888	CHECK_DIFF(RTStrNICmp("abcdef", "ABCDEF", RTSTR_MAX), ==);
889	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", RTSTR_MAX), ==);
890	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", RTSTR_MAX), > );
891	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", RTSTR_MAX), > ); /* diff performed on the lower case cp. */
892
893	CHECK_DIFF(RTStrNICmp("ABCDEF", "fedcba", 0), ==);
894	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 5), ==);
895	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", 5), ==);
896	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDe", 5), ==);
897	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDeF", 5), ==);
898	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDe", 5), ==);
899	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 6), > );
900	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", 6), > ); /* diff performed on the lower case cp. */
901	/* We should continue using byte comparison when we hit the invalid CP. Will assert in debug builds. */
902	// CHECK_DIFF(RTStrNICmp("AbCd\xff""eg", "aBcD\xff""eF", 6), ==);
903	}
904
905
906
907	/**
908	* Benchmark stuff.
909	*/
910	void Benchmarks(void)
911	{
912	RTPrintf("tstUtf8: BENCHMARKS\n");
913	static union
914	{
915	RTUTF16 wszBuf[sizeof(g_wszAll)];
916	char szBuf[sizeof(g_szAll)];
917	} s_Buf;
918
919	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
920	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
921	if (RT_SUCCESS(rc))
922	{
923	int i;
924	uint64_t u64Start = RTTimeNanoTS();
925	for (i = 0; i < 100; i++)
926	{
927	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
928	if (RT_FAILURE(rc))
929	{
930	RTPrintf("tstUtf8: UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
931	break;
932	}
933	}
934	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
935	RTPrintf("tstUtf8: UTF-8 -> UTF-16: %d in %RI64ns\n", i, u64Elapsed);
936	}
937
938	char *psz = &s_Buf.szBuf[0];
939	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
940	if (RT_SUCCESS(rc))
941	{
942	int i;
943	uint64_t u64Start = RTTimeNanoTS();
944	for (i = 0; i < 100; i++)
945	{
946	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
947	if (RT_FAILURE(rc))
948	{
949	RTPrintf("tstUtf8: UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
950	break;
951	}
952	}
953	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
954	RTPrintf("tstUtf8: UTF-16 -> UTF-8: %d in %RI64ns\n", i, u64Elapsed);
955	}
956
957	}
958
959
960	int main()
961	{
962	RTR3Init();
963
964	InitStrings();
965	test1();
966	test2();
967	test3();
968	TstRTStrXCmp();
969	Benchmarks();
970
971	/*
972	* Summary
973	*/
974	if (!g_cErrors)
975	RTPrintf("tstUtf8: SUCCESS\n");
976	else
977	RTPrintf("tstUtf8: FAILURE - %d errors!\n", g_cErrors);
978
979	return !!g_cErrors;
980	}

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 16684

Download in other formats: