tstUtf8.cpp@ 25349

Last change on this file since 25349 was 25349, checked in by vboxsync, 15 years ago
iprt/ministring_cpp.h -> iprt/cpp/ministring.h
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 43.3 KB

Line
1	/* $Id: tstUtf8.cpp 25349 2009-12-13 17:23:32Z 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	#include <iprt/test.h>
44	#include <iprt/cpp/ministring.h>
45
46	#include <stdlib.h> /** @todo use our random. */
47
48
49
50	/**
51	* Generate a random codepoint for simple UTF-16 encoding.
52	*/
53	static RTUTF16 GetRandUtf16(void)
54	{
55	RTUTF16 wc;
56	do
57	{
58	wc = (RTUTF16)((long long)rand() * 0xffff / RAND_MAX);
59	} while ((wc >= 0xd800 && wc <= 0xdfff) \|\| wc == 0);
60	return wc;
61	}
62
63
64	/**
65	*
66	*/
67	static void test1(RTTEST hTest)
68	{
69	static const char s_szBadString1[] = "Bad \xe0\x13\x0";
70	static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
71	int rc;
72	char *pszUtf8;
73	char *pszCurrent;
74	PRTUTF16 pwsz;
75	PRTUTF16 pwszRand;
76
77	/*
78	* Invalid UTF-8 to UCS-2 test.
79	*/
80	RTTestSub(hTest, "Feeding bad UTF-8 to RTStrToUtf16");
81	rc = RTStrToUtf16(s_szBadString1, &pwsz);
82	RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION \|\| rc == VERR_INVALID_UTF8_ENCODING,
83	(hTest, "Conversion of first bad UTF-8 string to UTF-16 apparantly succeeded. It shouldn't. rc=%Rrc\n", rc));
84	rc = RTStrToUtf16(s_szBadString2, &pwsz);
85	RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION \|\| rc == VERR_INVALID_UTF8_ENCODING,
86	(hTest, "Conversion of second bad UTF-8 strings to UTF-16 apparantly succeeded. It shouldn't. rc=%Rrc\n", rc));
87
88	/*
89	* Test current CP convertion.
90	*/
91	RTTestSub(hTest, "Rand UTF-16 -> UTF-8 -> CP -> UTF-8");
92	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
93	srand((unsigned)RTTimeNanoTS());
94	for (int i = 0; i < 30; i++)
95	pwszRand[i] = GetRandUtf16();
96	pwszRand[30] = 0;
97
98	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
99	if (rc == VINF_SUCCESS)
100	{
101	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
102	if (rc == VINF_SUCCESS)
103	{
104	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
105	if (rc == VINF_SUCCESS)
106	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
107	else
108	RTTestFailed(hTest, "%d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
109	__LINE__, rc);
110	}
111	else if (rc == VERR_NO_TRANSLATION)
112	RTTestPassed(hTest, "The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 returned VERR_NO_TRANSLATION. This is probably as it should be.\n");
113	else
114	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
115	__LINE__, rc);
116	}
117	else
118	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
119	__LINE__, rc);
120
121	/*
122	* Generate a new random string.
123	*/
124	RTTestSub(hTest, "Random UTF-16 -> UTF-8 -> UTF-16");
125	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
126	srand((unsigned)RTTimeNanoTS());
127	for (int i = 0; i < 30; i++)
128	pwszRand[i] = GetRandUtf16();
129	pwszRand[30] = 0;
130	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
131	if (rc == VINF_SUCCESS)
132	{
133	rc = RTStrToUtf16(pszUtf8, &pwsz);
134	if (rc == VINF_SUCCESS)
135	{
136	int i;
137	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
138	/* nothing */;
139	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
140	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
141	else
142	{
143	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.", __LINE__);
144	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
145	}
146	}
147	else
148	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
149	__LINE__, rc);
150	}
151	else
152	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
153	__LINE__, rc);
154
155	/*
156	* Generate yet another random string and convert it to a buffer.
157	*/
158	RTTestSub(hTest, "Random RTUtf16ToUtf8Ex + RTStrToUtf16");
159	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
160	srand((unsigned)RTTimeNanoTS());
161	for (int i = 0; i < 30; i++)
162	pwszRand[i] = GetRandUtf16();
163	pwszRand[30] = 0;
164
165	char szUtf8Array[120];
166	char *pszUtf8Array = szUtf8Array;
167	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
168	if (rc == 0)
169	{
170	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
171	if (rc == 0)
172	{
173	int i;
174	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
175	;
176	if (pwsz[i] == 0 && i >= 8)
177	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
178	else
179	{
180	RTTestFailed(hTest, "%d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
181	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
182	}
183	}
184	else
185	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
186	}
187	else
188	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
189
190	/*
191	* And again.
192	*/
193	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
194	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
195	srand((unsigned)RTTimeNanoTS());
196	for (int i = 0; i < 30; i++)
197	pwszRand[i] = GetRandUtf16();
198	pwszRand[30] = 0;
199
200	RTUTF16 wszBuf[70];
201	PRTUTF16 pwsz2Buf = wszBuf;
202	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
203	if (rc == 0)
204	{
205	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
206	if (rc == 0)
207	{
208	int i;
209	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++)
210	;
211	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
212	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
213	else
214	{
215	RTTestFailed(hTest, "%d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
216	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
217	}
218	}
219	else
220	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
221	}
222	else
223	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
224	__LINE__, rc);
225	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
226	srand((unsigned)RTTimeNanoTS());
227	for (int i = 0; i < 30; i++)
228	pwszRand[i] = GetRandUtf16();
229	pwszRand[30] = 0;
230
231	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
232	if (rc == VERR_BUFFER_OVERFLOW)
233	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
234	else
235	RTTestFailed(hTest, "%d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
236	__LINE__, rc);
237
238	/*
239	* last time...
240	*/
241	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
242	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
243	srand((unsigned)RTTimeNanoTS());
244	for (int i = 0; i < 30; i++)
245	pwszRand[i] = GetRandUtf16();
246	pwszRand[30] = 0;
247
248	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
249	if (rc == VINF_SUCCESS)
250	{
251	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
252	if (rc == VERR_BUFFER_OVERFLOW)
253	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
254	else
255	RTTestFailed(hTest, "%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",
256	__LINE__, rc);
257	}
258	else
259	RTTestFailed(hTest, "%d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
260	__LINE__, rc);
261
262
263	RTTestSubDone(hTest);
264	}
265
266
267	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
268	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
269	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
270
271	static void whereami(int cBits, size_t off)
272	{
273	if (cBits == 8)
274	{
275	if (off < 0x7f)
276	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", off + 1);
277	else if (off < 0xf7f)
278	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
279	else if (off < 0x27f7f)
280	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
281	else if (off < 0x2df79)
282	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
283	else if (off < 0x42df79)
284	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
285	else
286	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 ???\n");
287	}
288	else if (cBits == 16)
289	{
290	if (off < 0xd7ff*2)
291	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", off / 2 + 1);
292	else if (off < 0xf7fd*2)
293	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
294	else if (off < 0x20f7fd)
295	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
296	else
297	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 ???\n");
298	}
299	else
300	{
301	if (off < (0xd800 - 1) * sizeof(RTUNICP))
302	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
303	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
304	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
305	else
306	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
307	}
308	}
309
310	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
311	{
312	const uint8_t pb1 = (const uint8_t )pv1;
313	const uint8_t pb2 = (const uint8_t )pv2;
314	for (size_t off = 0; off < cb; off++)
315	{
316	if (pb1[off] != pb2[off])
317	{
318	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "mismatch at %#x: ", off);
319	whereami(cBits, off);
320	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
321	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
322	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
323	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
324	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
325	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
326	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
327	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
328	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
329	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
330	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
331	return 1;
332	}
333	}
334	return 0;
335	}
336
337
338	void InitStrings()
339	{
340	/*
341	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
342	*/
343	/* the simple code point array first */
344	unsigned i = 0;
345	RTUNICP uc = 1;
346	while (uc < 0xd800)
347	g_uszAll[i++] = uc++;
348	uc = 0xe000;
349	while (uc < 0xfffe)
350	g_uszAll[i++] = uc++;
351	uc = 0x10000;
352	while (uc < 0x110000)
353	g_uszAll[i++] = uc++;
354	g_uszAll[i++] = 0;
355	Assert(RT_ELEMENTS(g_uszAll) == i);
356
357	/* the utf-16 one */
358	i = 0;
359	uc = 1;
360	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
361	while (uc < 0xd800)
362	g_wszAll[i++] = uc++;
363	uc = 0xe000;
364	//RTPrintf(" %#x=%#x", i, uc);
365	while (uc < 0xfffe)
366	g_wszAll[i++] = uc++;
367	uc = 0x10000;
368	//RTPrintf(" %#x=%#x", i, uc);
369	while (uc < 0x110000)
370	{
371	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
372	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
373	uc++;
374	}
375	//RTPrintf(" %#x=%#x\n", i, uc);
376	g_wszAll[i++] = '\0';
377	Assert(RT_ELEMENTS(g_wszAll) == i);
378
379	/*
380	* The utf-8 one
381	*/
382	i = 0;
383	uc = 1;
384	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
385	while (uc < 0x80)
386	g_szAll[i++] = uc++;
387	//RTPrintf(" %#x=%#x", i, uc);
388	while (uc < 0x800)
389	{
390	g_szAll[i++] = 0xc0 \| (uc >> 6);
391	g_szAll[i++] = 0x80 \| (uc & 0x3f);
392	Assert(!((uc >> 6) & ~0x1f));
393	uc++;
394	}
395	//RTPrintf(" %#x=%#x", i, uc);
396	while (uc < 0xd800)
397	{
398	g_szAll[i++] = 0xe0 \| (uc >> 12);
399	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
400	g_szAll[i++] = 0x80 \| (uc & 0x3f);
401	Assert(!((uc >> 12) & ~0xf));
402	uc++;
403	}
404	uc = 0xe000;
405	//RTPrintf(" %#x=%#x", i, uc);
406	while (uc < 0xfffe)
407	{
408	g_szAll[i++] = 0xe0 \| (uc >> 12);
409	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
410	g_szAll[i++] = 0x80 \| (uc & 0x3f);
411	Assert(!((uc >> 12) & ~0xf));
412	uc++;
413	}
414	uc = 0x10000;
415	//RTPrintf(" %#x=%#x", i, uc);
416	while (uc < 0x110000)
417	{
418	g_szAll[i++] = 0xf0 \| (uc >> 18);
419	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
420	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
421	g_szAll[i++] = 0x80 \| (uc & 0x3f);
422	Assert(!((uc >> 18) & ~0x7));
423	uc++;
424	}
425	//RTPrintf(" %#x=%#x\n", i, uc);
426	g_szAll[i++] = '\0';
427	Assert(RT_ELEMENTS(g_szAll) == i);
428	}
429
430
431	void test2(RTTEST hTest)
432	{
433	/*
434	* Convert to UTF-8 and back.
435	*/
436	RTTestSub(hTest, "UTF-16 -> UTF-8 -> UTF-16");
437	char *pszUtf8;
438	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
439	if (rc == VINF_SUCCESS)
440	{
441	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
442	RTTestFailed(hTest, "UTF-16 -> UTF-8 mismatch!");
443
444	PRTUTF16 pwszUtf16;
445	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
446	if (rc == VINF_SUCCESS)
447	{
448	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
449	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
450	RTUtf16Free(pwszUtf16);
451	}
452	else
453	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
454	RTStrFree(pszUtf8);
455	}
456	else
457	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
458
459
460	/*
461	* Convert to UTF-16 and back. (just in case the above test fails)
462	*/
463	RTTestSub(hTest, "UTF-8 -> UTF-16 -> UTF-8");
464	PRTUTF16 pwszUtf16;
465	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
466	if (rc == VINF_SUCCESS)
467	{
468	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
469	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
470
471	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
472	if (rc == VINF_SUCCESS)
473	{
474	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
475	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed compare!");
476	RTStrFree(pszUtf8);
477	}
478	else
479	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
480	RTUtf16Free(pwszUtf16);
481	}
482	else
483	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
484
485	/*
486	* Convert UTF-8 to CPs.
487	*/
488	RTTestSub(hTest, "UTF-8 -> UNI -> UTF-8");
489	PRTUNICP paCps;
490	rc = RTStrToUni(g_szAll, &paCps);
491	if (rc == VINF_SUCCESS)
492	{
493	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
494	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
495
496	size_t cCps;
497	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, RT_ELEMENTS(g_uszAll), &cCps);
498	if (rc == VINF_SUCCESS)
499	{
500	if (cCps != RT_ELEMENTS(g_uszAll) - 1)
501	RTTestFailed(hTest, "wrong Code Point count %zu, expected %zu\n", cCps, RT_ELEMENTS(g_uszAll) - 1);
502	}
503	else
504	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
505
506	/** @todo RTCpsToUtf8 or something. */
507	}
508	else
509	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
510
511	/*
512	* Check the various string lengths.
513	*/
514	RTTestSub(hTest, "Lengths");
515	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
516	size_t cuc2 = RTUtf16Len(g_wszAll);
517	if (cuc1 != cuc2)
518	RTTestFailed(hTest, "cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
519	//size_t cuc3 = RTUniLen(g_uszAll);
520
521
522	/*
523	* Enumerate the strings.
524	*/
525	RTTestSub(hTest, "Code Point Getters and Putters");
526	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
527	AssertRelease(pszPut1Base);
528	char *pszPut1 = pszPut1Base;
529	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
530	AssertRelease(pwszPut2Base);
531	PRTUTF16 pwszPut2 = pwszPut2Base;
532	const char *psz1 = g_szAll;
533	const char *psz2 = g_szAll;
534	PCRTUTF16 pwsz3 = g_wszAll;
535	PCRTUTF16 pwsz4 = g_wszAll;
536	for (;;)
537	{
538	/*
539	* getters
540	*/
541	RTUNICP uc1;
542	rc = RTStrGetCpEx(&psz1, &uc1);
543	if (RT_FAILURE(rc))
544	{
545	RTTestFailed(hTest, "RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs", rc, psz2);
546	whereami(8, psz2 - &g_szAll[0]);
547	break;
548	}
549	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
550	if (pszPrev1 != psz2)
551	{
552	RTTestFailed(hTest, "RTStrPrevCp returned %p expected %p!", pszPrev1, psz2);
553	whereami(8, psz2 - &g_szAll[0]);
554	break;
555	}
556	RTUNICP uc2 = RTStrGetCp(psz2);
557	if (uc2 != uc1)
558	{
559	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc2, uc1);
560	whereami(8, psz2 - &g_szAll[0]);
561	break;
562	}
563	psz2 = RTStrNextCp(psz2);
564	if (psz2 != psz1)
565	{
566	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetNext returned different next pointer!");
567	whereami(8, psz2 - &g_szAll[0]);
568	break;
569	}
570
571	RTUNICP uc3;
572	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
573	if (RT_FAILURE(rc))
574	{
575	RTTestFailed(hTest, "RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs", rc, pwsz4);
576	whereami(16, pwsz4 - &g_wszAll[0]);
577	break;
578	}
579	if (uc3 != uc2)
580	{
581	RTTestFailed(hTest, "RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc2);
582	whereami(16, pwsz4 - &g_wszAll[0]);
583	break;
584	}
585	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
586	if (uc3 != uc4)
587	{
588	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc4);
589	whereami(16, pwsz4 - &g_wszAll[0]);
590	break;
591	}
592	pwsz4 = RTUtf16NextCp(pwsz4);
593	if (pwsz4 != pwsz3)
594	{
595	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!");
596	whereami(8, pwsz4 - &g_wszAll[0]);
597	break;
598	}
599
600
601	/*
602	* putters
603	*/
604	pszPut1 = RTStrPutCp(pszPut1, uc1);
605	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
606	{
607	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
608	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
609	whereami(8, psz2 - &g_szAll[0]);
610	break;
611	}
612
613	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
614	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
615	{
616	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
617	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
618	whereami(8, pwsz4 - &g_wszAll[0]);
619	break;
620	}
621
622
623	/* the end? */
624	if (!uc1)
625	break;
626	}
627
628	/* check output if we seems to have made it thru it all. */
629	if (psz2 == &g_szAll[sizeof(g_szAll)])
630	{
631	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
632	RTTestFailed(hTest, "RTStrPutCp encoded the string incorrectly.");
633	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
634	RTTestFailed(hTest, "RTUtf16PutCp encoded the string incorrectly.");
635	}
636
637	RTMemFree(pszPut1Base);
638	RTMemFree(pwszPut2Base);
639
640	RTTestSubDone(hTest);
641	}
642
643
644	/**
645	* Check case insensitivity.
646	*/
647	void test3(RTTEST hTest)
648	{
649	RTTestSub(hTest, "Case Sensitivitity");
650
651	if ( RTUniCpToLower('a') != 'a'
652	\|\| RTUniCpToLower('A') != 'a'
653	\|\| RTUniCpToLower('b') != 'b'
654	\|\| RTUniCpToLower('B') != 'b'
655	\|\| RTUniCpToLower('Z') != 'z'
656	\|\| RTUniCpToLower('z') != 'z'
657	\|\| RTUniCpToUpper('c') != 'C'
658	\|\| RTUniCpToUpper('C') != 'C'
659	\|\| RTUniCpToUpper('z') != 'Z'
660	\|\| RTUniCpToUpper('Z') != 'Z')
661	RTTestFailed(hTest, "RTUniToUpper/Lower failed basic tests.\n");
662
663	if (RTUtf16ICmp(g_wszAll, g_wszAll))
664	RTTestFailed(hTest, "RTUtf16ICmp failed the basic test.\n");
665
666	if (RTUtf16Cmp(g_wszAll, g_wszAll))
667	RTTestFailed(hTest, "RTUtf16Cmp failed the basic test.\n");
668
669	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 };
670	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 };
671	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
672	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
673	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
674	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
675	)
676	RTTestFailed(hTest, "RTUtf16ICmp failed the alphabet test.\n");
677
678	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
679	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
680	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
681	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
682	)
683	RTTestFailed(hTest, "RTUtf16Cmp failed the alphabet test.\n");
684
685	RTTestSubDone(hTest);
686	}
687
688
689	/**
690	* Test the RTStr*Cmp functions.
691	*/
692	void TstRTStrXCmp(RTTEST hTest)
693	{
694	#define CHECK_DIFF(expr, op) \
695	do \
696	{ \
697	int iDiff = expr; \
698	if (!(iDiff op 0)) \
699	RTTestFailed(hTest, "%d: %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
700	} while (0)
701
702	/** @todo test the non-ascii bits. */
703
704	RTTestSub(hTest, "RTStrCmp");
705	CHECK_DIFF(RTStrCmp(NULL, NULL), == );
706	CHECK_DIFF(RTStrCmp(NULL, ""), < );
707	CHECK_DIFF(RTStrCmp("", NULL), > );
708	CHECK_DIFF(RTStrCmp("", ""), == );
709	CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
710	CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
711	CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
712	CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
713	CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
714	CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
715	CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
716
717
718	RTTestSub(hTest, "RTStrNCmp");
719	CHECK_DIFF(RTStrNCmp(NULL, NULL, RTSTR_MAX), == );
720	CHECK_DIFF(RTStrNCmp(NULL, "", RTSTR_MAX), < );
721	CHECK_DIFF(RTStrNCmp("", NULL, RTSTR_MAX), > );
722	CHECK_DIFF(RTStrNCmp("", "", RTSTR_MAX), == );
723	CHECK_DIFF(RTStrNCmp("abcdef", "abcdef", RTSTR_MAX), == );
724	CHECK_DIFF(RTStrNCmp("abcdef", "abcde", RTSTR_MAX), > );
725	CHECK_DIFF(RTStrNCmp("abcde", "abcdef", RTSTR_MAX), < );
726	CHECK_DIFF(RTStrNCmp("abcdeg", "abcdef", RTSTR_MAX), > );
727	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeg", RTSTR_MAX), < );
728	CHECK_DIFF(RTStrNCmp("abcdeF", "abcdef", RTSTR_MAX), < );
729	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", RTSTR_MAX), > );
730
731	CHECK_DIFF(RTStrNCmp("abcdef", "fedcba", 0), ==);
732	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 5), ==);
733	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 6), > );
734
735
736	RTTestSub(hTest, "RTStrICmp");
737	CHECK_DIFF(RTStrICmp(NULL, NULL), == );
738	CHECK_DIFF(RTStrICmp(NULL, ""), < );
739	CHECK_DIFF(RTStrICmp("", NULL), > );
740	CHECK_DIFF(RTStrICmp("", ""), == );
741	CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
742	CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
743	CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
744	CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
745	CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
746
747	CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), ==);
748	CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
749	CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
750	CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
751	CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
752	CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
753	CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
754
755
756
757	RTTestSub(hTest, "RTStrNICmp");
758	CHECK_DIFF(RTStrNICmp(NULL, NULL, RTSTR_MAX), == );
759	CHECK_DIFF(RTStrNICmp(NULL, "", RTSTR_MAX), < );
760	CHECK_DIFF(RTStrNICmp("", NULL, RTSTR_MAX), > );
761	CHECK_DIFF(RTStrNICmp("", "", RTSTR_MAX), == );
762	CHECK_DIFF(RTStrNICmp(NULL, NULL, 0), == );
763	CHECK_DIFF(RTStrNICmp(NULL, "", 0), == );
764	CHECK_DIFF(RTStrNICmp("", NULL, 0), == );
765	CHECK_DIFF(RTStrNICmp("", "", 0), == );
766	CHECK_DIFF(RTStrNICmp("abcdef", "abcdef", RTSTR_MAX), == );
767	CHECK_DIFF(RTStrNICmp("abcdef", "abcde", RTSTR_MAX), > );
768	CHECK_DIFF(RTStrNICmp("abcde", "abcdef", RTSTR_MAX), < );
769	CHECK_DIFF(RTStrNICmp("abcdeg", "abcdef", RTSTR_MAX), > );
770	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeg", RTSTR_MAX), < );
771
772	CHECK_DIFF(RTStrNICmp("abcdeF", "abcdef", RTSTR_MAX), ==);
773	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeF", RTSTR_MAX), ==);
774	CHECK_DIFF(RTStrNICmp("ABCDEF", "abcdef", RTSTR_MAX), ==);
775	CHECK_DIFF(RTStrNICmp("abcdef", "ABCDEF", RTSTR_MAX), ==);
776	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", RTSTR_MAX), ==);
777	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", RTSTR_MAX), > );
778	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", RTSTR_MAX), > ); /* diff performed on the lower case cp. */
779
780	CHECK_DIFF(RTStrNICmp("ABCDEF", "fedcba", 0), ==);
781	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 5), ==);
782	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", 5), ==);
783	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDe", 5), ==);
784	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDeF", 5), ==);
785	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDe", 5), ==);
786	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 6), > );
787	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", 6), > ); /* diff performed on the lower case cp. */
788	/* We should continue using byte comparison when we hit the invalid CP. Will assert in debug builds. */
789	// CHECK_DIFF(RTStrNICmp("AbCd\xff""eg", "aBcD\xff""eF", 6), ==);
790
791	RTTestSubDone(hTest);
792	}
793
794
795
796	/**
797	* Benchmark stuff.
798	*/
799	void Benchmarks(RTTEST hTest)
800	{
801	static union
802	{
803	RTUTF16 wszBuf[sizeof(g_wszAll)];
804	char szBuf[sizeof(g_szAll)];
805	} s_Buf;
806
807	RTTestSub(hTest, "Benchmarks");
808	/** @todo add RTTest* methods for reporting benchmark results. */
809	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTStrToUtf16Ex: "); /** @todo figure this stuff into the test framework. */
810	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
811	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
812	if (RT_SUCCESS(rc))
813	{
814	int i;
815	uint64_t u64Start = RTTimeNanoTS();
816	for (i = 0; i < 100; i++)
817	{
818	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
819	if (RT_FAILURE(rc))
820	{
821	RTTestFailed(hTest, "UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
822	break;
823	}
824	}
825	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
826	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
827	}
828
829	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTUtf16ToUtf8Ex: ");
830	char *psz = &s_Buf.szBuf[0];
831	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
832	if (RT_SUCCESS(rc))
833	{
834	int i;
835	uint64_t u64Start = RTTimeNanoTS();
836	for (i = 0; i < 100; i++)
837	{
838	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
839	if (RT_FAILURE(rc))
840	{
841	RTTestFailed(hTest, "UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
842	break;
843	}
844	}
845	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
846	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
847	}
848
849	RTTestSubDone(hTest);
850	}
851
852
853	/**
854	* Tests RTStrStr and RTStrIStr.
855	*/
856	static void testStrStr(RTTEST hTest)
857	{
858	#define CHECK_NULL(expr) \
859	do { \
860	const char *pszRet = expr; \
861	if (pszRet != NULL) \
862	RTTestFailed(hTest, "%d: %#x -> %s expected NULL", __LINE__, #expr, pszRet); \
863	} while (0)
864
865	#define CHECK(expr, expect) \
866	do { \
867	const char *pszRet = expr; \
868	if ( (pszRet != NULL && (expect) == NULL) \
869	\|\| (pszRet == NULL && (expect) != NULL) \
870	\|\| strcmp(pszRet, (expect)) \
871	) \
872	RTTestFailed(hTest, "%d: %#x -> %s expected %s", __LINE__, #expr, pszRet, (expect)); \
873	} while (0)
874
875
876	RTTestSub(hTest, "RTStrStr");
877	CHECK(RTStrStr("abcdef", ""), "abcdef");
878	CHECK_NULL(RTStrStr("abcdef", NULL));
879	CHECK_NULL(RTStrStr(NULL, ""));
880	CHECK_NULL(RTStrStr(NULL, NULL));
881	CHECK(RTStrStr("abcdef", "abcdef"), "abcdef");
882	CHECK(RTStrStr("abcdef", "b"), "bcdef");
883	CHECK(RTStrStr("abcdef", "bcdef"), "bcdef");
884	CHECK(RTStrStr("abcdef", "cdef"), "cdef");
885	CHECK(RTStrStr("abcdef", "cde"), "cdef");
886	CHECK(RTStrStr("abcdef", "cd"), "cdef");
887	CHECK(RTStrStr("abcdef", "c"), "cdef");
888	CHECK(RTStrStr("abcdef", "f"), "f");
889	CHECK(RTStrStr("abcdef", "ef"), "ef");
890	CHECK(RTStrStr("abcdef", "e"), "ef");
891	CHECK_NULL(RTStrStr("abcdef", "z"));
892	CHECK_NULL(RTStrStr("abcdef", "A"));
893	CHECK_NULL(RTStrStr("abcdef", "F"));
894
895	RTTestSub(hTest, "RTStrIStr");
896	CHECK(RTStrIStr("abcdef", ""), "abcdef");
897	CHECK_NULL(RTStrIStr("abcdef", NULL));
898	CHECK_NULL(RTStrIStr(NULL, ""));
899	CHECK_NULL(RTStrIStr(NULL, NULL));
900	CHECK(RTStrIStr("abcdef", "abcdef"), "abcdef");
901	CHECK(RTStrIStr("abcdef", "Abcdef"), "abcdef");
902	CHECK(RTStrIStr("abcdef", "ABcDeF"), "abcdef");
903	CHECK(RTStrIStr("abcdef", "b"), "bcdef");
904	CHECK(RTStrIStr("abcdef", "B"), "bcdef");
905	CHECK(RTStrIStr("abcdef", "bcdef"), "bcdef");
906	CHECK(RTStrIStr("abcdef", "BCdEf"), "bcdef");
907	CHECK(RTStrIStr("abcdef", "bCdEf"), "bcdef");
908	CHECK(RTStrIStr("abcdef", "bcdEf"), "bcdef");
909	CHECK(RTStrIStr("abcdef", "BcdEf"), "bcdef");
910	CHECK(RTStrIStr("abcdef", "cdef"), "cdef");
911	CHECK(RTStrIStr("abcdef", "cde"), "cdef");
912	CHECK(RTStrIStr("abcdef", "cd"), "cdef");
913	CHECK(RTStrIStr("abcdef", "c"), "cdef");
914	CHECK(RTStrIStr("abcdef", "f"), "f");
915	CHECK(RTStrIStr("abcdeF", "F"), "F");
916	CHECK(RTStrIStr("abcdef", "F"), "f");
917	CHECK(RTStrIStr("abcdef", "ef"), "ef");
918	CHECK(RTStrIStr("EeEef", "e"), "EeEef");
919	CHECK(RTStrIStr("EeEef", "E"), "EeEef");
920	CHECK(RTStrIStr("EeEef", "EE"), "EeEef");
921	CHECK(RTStrIStr("EeEef", "EEE"), "EeEef");
922	CHECK(RTStrIStr("EeEef", "EEEF"), "eEef");
923	CHECK_NULL(RTStrIStr("EeEef", "z"));
924
925	#undef CHECK
926	#undef CHECK_NULL
927	RTTestSubDone(hTest);
928	}
929
930
931	void testMinistring(RTTEST hTest)
932	{
933	RTTestSub(hTest, "class iprt::MiniString");
934
935	#define CHECK(expr) \
936	do { \
937	if (!(expr)) \
938	RTTestFailed(hTest, "%d: FAILED %s", __LINE__, #expr); \
939	} while (0)
940
941	#define CHECK_DUMP(expr, value) \
942	do { \
943	if (!(expr)) \
944	RTTestFailed(hTest, "%d: FAILED %s, got \"%s\"", __LINE__, #expr, value); \
945	} while (0)
946
947	#define CHECK_DUMP_I(expr) \
948	do { \
949	if (!(expr)) \
950	RTTestFailed(hTest, "%d: FAILED %s, got \"%d\"", __LINE__, #expr, expr); \
951	} while (0)
952
953	iprt::MiniString empty;
954	CHECK( (empty.length() == 0) );
955	CHECK( (empty.capacity() == 0) );
956
957	iprt::MiniString sixbytes("12345");
958	CHECK( (sixbytes.length() == 5) );
959	CHECK( (sixbytes.capacity() == 6) );
960
961	sixbytes.append("678");
962	CHECK( (sixbytes.length() == 8) );
963	CHECK( (sixbytes.capacity() == 9) );
964
965	char *psz = sixbytes.mutableRaw();
966	// 12345678
967	// ^
968	// 0123456
969	psz[6] = '\0';
970	sixbytes.jolt();
971	CHECK( (sixbytes.length() == 6) );
972	CHECK( (sixbytes.capacity() == 7) );
973
974	iprt::MiniString morebytes("tobereplaced");
975	morebytes = "newstring ";
976	morebytes.append(sixbytes);
977
978	CHECK_DUMP( (morebytes == "newstring 123456"), morebytes.c_str() );
979
980	iprt::MiniString third(morebytes);
981	third.reserve(100 * 1024); // 100 KB
982	CHECK_DUMP( (third == "newstring 123456"), morebytes.c_str() );
983	CHECK( (third.capacity() == 100 * 1024) );
984	CHECK( (third.length() == morebytes.length()) ); // must not have changed
985
986	iprt::MiniString copy1(morebytes);
987	iprt::MiniString copy2 = morebytes;
988	CHECK( (copy1 == copy2) );
989
990	copy1 = NULL;
991	CHECK( (copy1.length() == 0) );
992
993	copy1 = "";
994	CHECK( (copy1.length() == 0) );
995
996	CHECK( (iprt::MiniString("abc") < iprt::MiniString("def")) );
997	CHECK( (iprt::MiniString("abc") != iprt::MiniString("def")) );
998	CHECK_DUMP_I( (iprt::MiniString("def") > iprt::MiniString("abc")) );
999
1000	copy2.setNull();
1001	for (int i = 0;
1002	i < 100;
1003	++i)
1004	{
1005	copy2.reserve(50); // should be ignored after 50 loops
1006	copy2.append("1");
1007	}
1008	CHECK( (copy2.length() == 100) );
1009
1010	copy2.setNull();
1011	for (int i = 0;
1012	i < 100;
1013	++i)
1014	{
1015	copy2.reserve(50); // should be ignored after 50 loops
1016	copy2.append('1');
1017	}
1018	CHECK( (copy2.length() == 100) );
1019
1020	#undef CHECK
1021	}
1022
1023
1024	void testLatin1(RTTEST hTest)
1025	{
1026	RTTestSub(hTest, "Latin1 conversion functions");
1027
1028	/* Test Utf16 -> Latin1 */
1029	size_t cch_szAll = 0;
1030	size_t cbShort = RTUtf16CalcLatin1Len(g_wszAll);
1031	RTTEST_CHECK(hTest, cbShort == 0);
1032	int rc = RTUtf16CalcLatin1LenEx(g_wszAll, 255, &cch_szAll);
1033	RTTEST_CHECK(hTest, (cch_szAll == 255));
1034	rc = RTUtf16CalcLatin1LenEx(g_wszAll, RTSTR_MAX, &cch_szAll);
1035	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1036	char *psz = NULL;
1037	RTUTF16 wszShort[256] = { 0 };
1038	for (unsigned i = 0; i < 255; ++i)
1039	wszShort[i] = i + 1;
1040	cbShort = RTUtf16CalcLatin1Len(wszShort);
1041	RTTEST_CHECK(hTest, cbShort == 255);
1042	rc = RTUtf16ToLatin1(wszShort, &psz);
1043	RTTEST_CHECK_RC_OK(hTest, rc);
1044	if (RT_SUCCESS(rc))
1045	{
1046	RTTEST_CHECK(hTest, (strlen(psz) == 255));
1047	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1048	if (psz[i] != (char) j)
1049	{
1050	RTTestFailed(hTest, "conversion of g_wszAll to Latin1 failed at position %u\n", i);
1051	break;
1052	}
1053	}
1054	RTStrFree(psz);
1055	rc = RTUtf16ToLatin1(g_wszAll, &psz);
1056	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1057	char sz[512];
1058	char *psz2 = &sz[0];
1059	size_t cchActual = 0;
1060	rc = RTUtf16ToLatin1Ex(g_wszAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1061	&cchActual);
1062	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1063	RTTEST_CHECK_MSG(hTest, cchActual == 0,
1064	(hTest, "cchActual=%lu\n", cchActual));
1065	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz2, sizeof(sz),
1066	&cchActual);
1067	RTTEST_CHECK_RC_OK(hTest, rc);
1068	if (RT_SUCCESS(rc))
1069	{
1070	RTTEST_CHECK(hTest, (cchActual == 255));
1071	RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1072	for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1073	if (psz2[i] != (char) j)
1074	{
1075	RTTestFailed(hTest, "second conversion of g_wszAll to Latin1 failed at position %u\n", i);
1076	break;
1077	}
1078	}
1079	rc = RTUtf16ToLatin1Ex(g_wszAll, 128, &psz2, 128, &cchActual);
1080	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1081	RTTEST_CHECK_MSG(hTest, cchActual == 128,
1082	(hTest, "cchActual=%lu\n", cchActual));
1083	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz, 0, &cchActual);
1084	RTTEST_CHECK_RC_OK(hTest, rc);
1085	if (RT_SUCCESS(rc))
1086	{
1087	RTTEST_CHECK(hTest, (cchActual == 255));
1088	RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1089	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1090	if ( ((j < 0x100) && (psz[i] != (char) j))
1091	\|\| ((j > 0xff) && psz[i] != '?'))
1092	{
1093	RTTestFailed(hTest, "third conversion of g_wszAll to Latin1 failed at position %u\n", i);
1094	break;
1095	}
1096	}
1097	const char *pszBad = "H\0e\0l\0l\0o\0\0\xDC\0\xD8\0";
1098	rc = RTUtf16ToLatin1Ex((RTUTF16 *) pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1099	&cchActual);
1100	RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF16_ENCODING);
1101	RTStrFree(psz);
1102
1103	/* Test Latin1 -> Utf16 */
1104	const char *pszLat1 = "\x01\x20\x40\x80\x81";
1105	RTTEST_CHECK(hTest, (RTLatin1CalcUtf16Len(pszLat1) == 5));
1106	rc = RTLatin1CalcUtf16LenEx(pszLat1, 3, &cchActual);
1107	RTTEST_CHECK_RC_OK(hTest, rc);
1108	if (RT_SUCCESS(rc))
1109	RTTEST_CHECK(hTest, (cchActual == 3));
1110	rc = RTLatin1CalcUtf16LenEx(pszLat1, RTSTR_MAX, &cchActual);
1111	RTTEST_CHECK_RC_OK(hTest, rc);
1112	if (RT_SUCCESS(rc))
1113	RTTEST_CHECK(hTest, (cchActual == 5));
1114	RTUTF16 *pwc = NULL;
1115	RTUTF16 wc[6];
1116	RTUTF16 *pwc2 = &wc[0];
1117	size_t cwActual = 0;
1118	rc = RTLatin1ToUtf16(pszLat1, &pwc);
1119	RTTEST_CHECK_RC_OK(hTest, rc);
1120	if (RT_SUCCESS(rc))
1121	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1122	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1123	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1124	RTUtf16Free(pwc);
1125	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, &cwActual);
1126	RTTEST_CHECK_RC_OK(hTest, rc);
1127	if (RT_SUCCESS(rc))
1128	{
1129	RTTEST_CHECK(hTest, (cwActual == 5));
1130	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1131	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1132	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1133	}
1134	RTUtf16Free(pwc);
1135	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, NULL);
1136	RTTEST_CHECK_RC_OK(hTest, rc);
1137	if (RT_SUCCESS(rc))
1138	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1139	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1140	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1141	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc),
1142	&cwActual);
1143	RTTEST_CHECK_RC_OK(hTest, rc);
1144	if (RT_SUCCESS(rc))
1145	{
1146	RTTEST_CHECK(hTest, (cwActual == 5));
1147	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1148	&& (wc[2] == 0x40) && (wc[3] == 0x80)
1149	&& (wc[4] == 0x81) && (wc[5] == '\0'));
1150	}
1151	rc = RTLatin1ToUtf16Ex(pszLat1, 3, &pwc2, RT_ELEMENTS(wc),
1152	&cwActual);
1153	RTTEST_CHECK_RC_OK(hTest, rc);
1154	if (RT_SUCCESS(rc))
1155	{
1156	RTTEST_CHECK(hTest, (cwActual == 3));
1157	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1158	&& (wc[2] == 0x40) && (wc[3] == '\0'));
1159	}
1160	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc) - 1,
1161	&cwActual);
1162	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1163	/** @todo Either fix the documentation or fix the code - cchActual is
1164	* set to the number of bytes actually encoded. */
1165	RTTEST_CHECK(hTest, (cwActual == 5));
1166	RTTestSubDone(hTest);
1167	}
1168
1169
1170	static void testNoTransation(RTTEST hTest)
1171	{
1172
1173	/*
1174	* Try trigger a VERR_NO_TRANSLATION error in convert to
1175	* current CP to latin-1.
1176	*/
1177	const RTUTF16 s_swzTest1[] = { 0x2358, 0x2242, 0x2357, 0x2359, 0x22f9, 0x2c4e, 0x0030, 0x0060,
1178	0x0092, 0x00c1, 0x00f2, 0x1f80, 0x0088, 0x2c38, 0x2c30, 0x0000 };
1179	char *pszTest1;
1180	int rc = RTUtf16ToUtf8(s_swzTest1, &pszTest1);
1181	RTTESTI_CHECK_RC_RETV(rc, VINF_SUCCESS);
1182
1183	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTStrUtf8ToCurrentCP");
1184	char *pszOut;
1185	rc = RTStrUtf8ToCurrentCP(&pszOut, pszTest1);
1186	if (RT_SUCCESS(rc))
1187	{
1188	RTTESTI_CHECK(!strcmp(pszOut, pszTest1));
1189	RTTestIPrintf(RTTESTLVL_ALWAYS, "CurrentCP is UTF-8 or similar\n");
1190	RTStrFree(pszOut);
1191	}
1192	else
1193	RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1194
1195	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTUtf16ToLatin1");
1196	rc = RTUtf16ToLatin1(s_swzTest1, &pszOut);
1197	RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1198	if (RT_SUCCESS(rc))
1199	RTStrFree(pszOut);
1200
1201	RTStrFree(pszTest1);
1202	RTTestSubDone(hTest);
1203	}
1204
1205
1206	int main()
1207	{
1208	/*
1209	* Init the runtime, test and say hello.
1210	*/
1211	RTTEST hTest;
1212	int rc = RTTestInitAndCreate("tstUtf8", &hTest);
1213	if (rc)
1214	return rc;
1215	RTTestBanner(hTest);
1216
1217	/*
1218	* Run the test.
1219	*/
1220	InitStrings();
1221	test1(hTest);
1222	test2(hTest);
1223	test3(hTest);
1224	TstRTStrXCmp(hTest);
1225	testStrStr(hTest);
1226	testMinistring(hTest);
1227	testLatin1(hTest);
1228	testNoTransation(hTest);
1229
1230	Benchmarks(hTest);
1231
1232	/*
1233	* Summary
1234	*/
1235	return RTTestSummaryAndDestroy(hTest);
1236	}
1237

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 25349

Download in other formats: