tstUtf8.cpp@ 30016

Last change on this file since 30016 was 28800, checked in by vboxsync, 14 years ago
Automated rebranding to Oracle copyright/license strings via filemuncher
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 43.1 KB

Line
1	/* $Id: tstUtf8.cpp 28800 2010-04-27 08:22:32Z vboxsync $ */
2	/** @file
3	* IPRT Testcase - UTF-8 and UTF-16 string conversions.
4	*/
5
6	/*
7	* Copyright (C) 2006-2007 Oracle Corporation
8	*
9	* This file is part of VirtualBox Open Source Edition (OSE), as
10	* available from http://www.virtualbox.org. This file is free software;
11	* you can redistribute it and/or modify it under the terms of the GNU
12	* General Public License (GPL) as published by the Free Software
13	* Foundation, in version 2 as it comes in the "COPYING" file of the
14	* VirtualBox OSE distribution. VirtualBox OSE is distributed in the
15	* hope that it will be useful, but WITHOUT ANY WARRANTY of any kind.
16	*
17	* The contents of this file may alternatively be used under the terms
18	* of the Common Development and Distribution License Version 1.0
19	* (CDDL) only, as it comes in the "COPYING.CDDL" file of the
20	* VirtualBox OSE distribution, in which case the provisions of the
21	* CDDL are applicable instead of those of the GPL.
22	*
23	* You may elect to license modified versions of this file under the
24	* terms and conditions of either the GPL or the CDDL or both.
25	*/
26
27	/*******************************************************************************
28	* Header Files *
29	*******************************************************************************/
30	#include <iprt/string.h>
31	#include <iprt/uni.h>
32	#include <iprt/initterm.h>
33	#include <iprt/uuid.h>
34	#include <iprt/time.h>
35	#include <iprt/stream.h>
36	#include <iprt/alloc.h>
37	#include <iprt/assert.h>
38	#include <iprt/err.h>
39	#include <iprt/test.h>
40	#include <iprt/cpp/ministring.h>
41
42	#include <stdlib.h> /** @todo use our random. */
43
44
45
46	/**
47	* Generate a random codepoint for simple UTF-16 encoding.
48	*/
49	static RTUTF16 GetRandUtf16(void)
50	{
51	RTUTF16 wc;
52	do
53	{
54	wc = (RTUTF16)((long long)rand() * 0xffff / RAND_MAX);
55	} while ((wc >= 0xd800 && wc <= 0xdfff) \|\| wc == 0);
56	return wc;
57	}
58
59
60	/**
61	*
62	*/
63	static void test1(RTTEST hTest)
64	{
65	static const char s_szBadString1[] = "Bad \xe0\x13\x0";
66	static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
67	int rc;
68	char *pszUtf8;
69	char *pszCurrent;
70	PRTUTF16 pwsz;
71	PRTUTF16 pwszRand;
72
73	/*
74	* Invalid UTF-8 to UCS-2 test.
75	*/
76	RTTestSub(hTest, "Feeding bad UTF-8 to RTStrToUtf16");
77	rc = RTStrToUtf16(s_szBadString1, &pwsz);
78	RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION \|\| rc == VERR_INVALID_UTF8_ENCODING,
79	(hTest, "Conversion of first bad UTF-8 string to UTF-16 apparantly succeeded. It shouldn't. rc=%Rrc\n", rc));
80	rc = RTStrToUtf16(s_szBadString2, &pwsz);
81	RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION \|\| rc == VERR_INVALID_UTF8_ENCODING,
82	(hTest, "Conversion of second bad UTF-8 strings to UTF-16 apparantly succeeded. It shouldn't. rc=%Rrc\n", rc));
83
84	/*
85	* Test current CP convertion.
86	*/
87	RTTestSub(hTest, "Rand UTF-16 -> UTF-8 -> CP -> UTF-8");
88	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
89	srand((unsigned)RTTimeNanoTS());
90	for (int i = 0; i < 30; i++)
91	pwszRand[i] = GetRandUtf16();
92	pwszRand[30] = 0;
93
94	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
95	if (rc == VINF_SUCCESS)
96	{
97	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
98	if (rc == VINF_SUCCESS)
99	{
100	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
101	if (rc == VINF_SUCCESS)
102	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
103	else
104	RTTestFailed(hTest, "%d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
105	__LINE__, rc);
106	}
107	else if (rc == VERR_NO_TRANSLATION)
108	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");
109	else
110	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
111	__LINE__, rc);
112	}
113	else
114	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
115	__LINE__, rc);
116
117	/*
118	* Generate a new random string.
119	*/
120	RTTestSub(hTest, "Random UTF-16 -> UTF-8 -> UTF-16");
121	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
122	srand((unsigned)RTTimeNanoTS());
123	for (int i = 0; i < 30; i++)
124	pwszRand[i] = GetRandUtf16();
125	pwszRand[30] = 0;
126	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
127	if (rc == VINF_SUCCESS)
128	{
129	rc = RTStrToUtf16(pszUtf8, &pwsz);
130	if (rc == VINF_SUCCESS)
131	{
132	int i;
133	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
134	/* nothing */;
135	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
136	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
137	else
138	{
139	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.", __LINE__);
140	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
141	}
142	}
143	else
144	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
145	__LINE__, rc);
146	}
147	else
148	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
149	__LINE__, rc);
150
151	/*
152	* Generate yet another random string and convert it to a buffer.
153	*/
154	RTTestSub(hTest, "Random RTUtf16ToUtf8Ex + RTStrToUtf16");
155	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
156	srand((unsigned)RTTimeNanoTS());
157	for (int i = 0; i < 30; i++)
158	pwszRand[i] = GetRandUtf16();
159	pwszRand[30] = 0;
160
161	char szUtf8Array[120];
162	char *pszUtf8Array = szUtf8Array;
163	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
164	if (rc == 0)
165	{
166	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
167	if (rc == 0)
168	{
169	int i;
170	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
171	;
172	if (pwsz[i] == 0 && i >= 8)
173	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
174	else
175	{
176	RTTestFailed(hTest, "%d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
177	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
178	}
179	}
180	else
181	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
182	}
183	else
184	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
185
186	/*
187	* And again.
188	*/
189	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
190	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
191	srand((unsigned)RTTimeNanoTS());
192	for (int i = 0; i < 30; i++)
193	pwszRand[i] = GetRandUtf16();
194	pwszRand[30] = 0;
195
196	RTUTF16 wszBuf[70];
197	PRTUTF16 pwsz2Buf = wszBuf;
198	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
199	if (rc == 0)
200	{
201	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
202	if (rc == 0)
203	{
204	int i;
205	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++)
206	;
207	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
208	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
209	else
210	{
211	RTTestFailed(hTest, "%d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
212	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
213	}
214	}
215	else
216	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
217	}
218	else
219	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
220	__LINE__, rc);
221	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
222	srand((unsigned)RTTimeNanoTS());
223	for (int i = 0; i < 30; i++)
224	pwszRand[i] = GetRandUtf16();
225	pwszRand[30] = 0;
226
227	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
228	if (rc == VERR_BUFFER_OVERFLOW)
229	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
230	else
231	RTTestFailed(hTest, "%d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
232	__LINE__, rc);
233
234	/*
235	* last time...
236	*/
237	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
238	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
239	srand((unsigned)RTTimeNanoTS());
240	for (int i = 0; i < 30; i++)
241	pwszRand[i] = GetRandUtf16();
242	pwszRand[30] = 0;
243
244	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
245	if (rc == VINF_SUCCESS)
246	{
247	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
248	if (rc == VERR_BUFFER_OVERFLOW)
249	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
250	else
251	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",
252	__LINE__, rc);
253	}
254	else
255	RTTestFailed(hTest, "%d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
256	__LINE__, rc);
257
258
259	RTTestSubDone(hTest);
260	}
261
262
263	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
264	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
265	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
266
267	static void whereami(int cBits, size_t off)
268	{
269	if (cBits == 8)
270	{
271	if (off < 0x7f)
272	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", off + 1);
273	else if (off < 0xf7f)
274	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
275	else if (off < 0x27f7f)
276	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
277	else if (off < 0x2df79)
278	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
279	else if (off < 0x42df79)
280	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
281	else
282	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 ???\n");
283	}
284	else if (cBits == 16)
285	{
286	if (off < 0xd7ff*2)
287	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", off / 2 + 1);
288	else if (off < 0xf7fd*2)
289	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
290	else if (off < 0x20f7fd)
291	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
292	else
293	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 ???\n");
294	}
295	else
296	{
297	if (off < (0xd800 - 1) * sizeof(RTUNICP))
298	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
299	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
300	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
301	else
302	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
303	}
304	}
305
306	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
307	{
308	const uint8_t pb1 = (const uint8_t )pv1;
309	const uint8_t pb2 = (const uint8_t )pv2;
310	for (size_t off = 0; off < cb; off++)
311	{
312	if (pb1[off] != pb2[off])
313	{
314	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "mismatch at %#x: ", off);
315	whereami(cBits, off);
316	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
317	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
318	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
319	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
320	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
321	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
322	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
323	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
324	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
325	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
326	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
327	return 1;
328	}
329	}
330	return 0;
331	}
332
333
334	void InitStrings()
335	{
336	/*
337	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
338	*/
339	/* the simple code point array first */
340	unsigned i = 0;
341	RTUNICP uc = 1;
342	while (uc < 0xd800)
343	g_uszAll[i++] = uc++;
344	uc = 0xe000;
345	while (uc < 0xfffe)
346	g_uszAll[i++] = uc++;
347	uc = 0x10000;
348	while (uc < 0x110000)
349	g_uszAll[i++] = uc++;
350	g_uszAll[i++] = 0;
351	Assert(RT_ELEMENTS(g_uszAll) == i);
352
353	/* the utf-16 one */
354	i = 0;
355	uc = 1;
356	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
357	while (uc < 0xd800)
358	g_wszAll[i++] = uc++;
359	uc = 0xe000;
360	//RTPrintf(" %#x=%#x", i, uc);
361	while (uc < 0xfffe)
362	g_wszAll[i++] = uc++;
363	uc = 0x10000;
364	//RTPrintf(" %#x=%#x", i, uc);
365	while (uc < 0x110000)
366	{
367	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
368	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
369	uc++;
370	}
371	//RTPrintf(" %#x=%#x\n", i, uc);
372	g_wszAll[i++] = '\0';
373	Assert(RT_ELEMENTS(g_wszAll) == i);
374
375	/*
376	* The utf-8 one
377	*/
378	i = 0;
379	uc = 1;
380	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
381	while (uc < 0x80)
382	g_szAll[i++] = uc++;
383	//RTPrintf(" %#x=%#x", i, uc);
384	while (uc < 0x800)
385	{
386	g_szAll[i++] = 0xc0 \| (uc >> 6);
387	g_szAll[i++] = 0x80 \| (uc & 0x3f);
388	Assert(!((uc >> 6) & ~0x1f));
389	uc++;
390	}
391	//RTPrintf(" %#x=%#x", i, uc);
392	while (uc < 0xd800)
393	{
394	g_szAll[i++] = 0xe0 \| (uc >> 12);
395	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
396	g_szAll[i++] = 0x80 \| (uc & 0x3f);
397	Assert(!((uc >> 12) & ~0xf));
398	uc++;
399	}
400	uc = 0xe000;
401	//RTPrintf(" %#x=%#x", i, uc);
402	while (uc < 0xfffe)
403	{
404	g_szAll[i++] = 0xe0 \| (uc >> 12);
405	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
406	g_szAll[i++] = 0x80 \| (uc & 0x3f);
407	Assert(!((uc >> 12) & ~0xf));
408	uc++;
409	}
410	uc = 0x10000;
411	//RTPrintf(" %#x=%#x", i, uc);
412	while (uc < 0x110000)
413	{
414	g_szAll[i++] = 0xf0 \| (uc >> 18);
415	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
416	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
417	g_szAll[i++] = 0x80 \| (uc & 0x3f);
418	Assert(!((uc >> 18) & ~0x7));
419	uc++;
420	}
421	//RTPrintf(" %#x=%#x\n", i, uc);
422	g_szAll[i++] = '\0';
423	Assert(RT_ELEMENTS(g_szAll) == i);
424	}
425
426
427	void test2(RTTEST hTest)
428	{
429	/*
430	* Convert to UTF-8 and back.
431	*/
432	RTTestSub(hTest, "UTF-16 -> UTF-8 -> UTF-16");
433	char *pszUtf8;
434	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
435	if (rc == VINF_SUCCESS)
436	{
437	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
438	RTTestFailed(hTest, "UTF-16 -> UTF-8 mismatch!");
439
440	PRTUTF16 pwszUtf16;
441	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
442	if (rc == VINF_SUCCESS)
443	{
444	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
445	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
446	RTUtf16Free(pwszUtf16);
447	}
448	else
449	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
450	RTStrFree(pszUtf8);
451	}
452	else
453	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
454
455
456	/*
457	* Convert to UTF-16 and back. (just in case the above test fails)
458	*/
459	RTTestSub(hTest, "UTF-8 -> UTF-16 -> UTF-8");
460	PRTUTF16 pwszUtf16;
461	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
462	if (rc == VINF_SUCCESS)
463	{
464	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
465	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
466
467	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
468	if (rc == VINF_SUCCESS)
469	{
470	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
471	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed compare!");
472	RTStrFree(pszUtf8);
473	}
474	else
475	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
476	RTUtf16Free(pwszUtf16);
477	}
478	else
479	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
480
481	/*
482	* Convert UTF-8 to CPs.
483	*/
484	RTTestSub(hTest, "UTF-8 -> UNI -> UTF-8");
485	PRTUNICP paCps;
486	rc = RTStrToUni(g_szAll, &paCps);
487	if (rc == VINF_SUCCESS)
488	{
489	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
490	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
491
492	size_t cCps;
493	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, RT_ELEMENTS(g_uszAll), &cCps);
494	if (rc == VINF_SUCCESS)
495	{
496	if (cCps != RT_ELEMENTS(g_uszAll) - 1)
497	RTTestFailed(hTest, "wrong Code Point count %zu, expected %zu\n", cCps, RT_ELEMENTS(g_uszAll) - 1);
498	}
499	else
500	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
501
502	/** @todo RTCpsToUtf8 or something. */
503	}
504	else
505	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
506
507	/*
508	* Check the various string lengths.
509	*/
510	RTTestSub(hTest, "Lengths");
511	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
512	size_t cuc2 = RTUtf16Len(g_wszAll);
513	if (cuc1 != cuc2)
514	RTTestFailed(hTest, "cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
515	//size_t cuc3 = RTUniLen(g_uszAll);
516
517
518	/*
519	* Enumerate the strings.
520	*/
521	RTTestSub(hTest, "Code Point Getters and Putters");
522	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
523	AssertRelease(pszPut1Base);
524	char *pszPut1 = pszPut1Base;
525	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
526	AssertRelease(pwszPut2Base);
527	PRTUTF16 pwszPut2 = pwszPut2Base;
528	const char *psz1 = g_szAll;
529	const char *psz2 = g_szAll;
530	PCRTUTF16 pwsz3 = g_wszAll;
531	PCRTUTF16 pwsz4 = g_wszAll;
532	for (;;)
533	{
534	/*
535	* getters
536	*/
537	RTUNICP uc1;
538	rc = RTStrGetCpEx(&psz1, &uc1);
539	if (RT_FAILURE(rc))
540	{
541	RTTestFailed(hTest, "RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs", rc, psz2);
542	whereami(8, psz2 - &g_szAll[0]);
543	break;
544	}
545	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
546	if (pszPrev1 != psz2)
547	{
548	RTTestFailed(hTest, "RTStrPrevCp returned %p expected %p!", pszPrev1, psz2);
549	whereami(8, psz2 - &g_szAll[0]);
550	break;
551	}
552	RTUNICP uc2 = RTStrGetCp(psz2);
553	if (uc2 != uc1)
554	{
555	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc2, uc1);
556	whereami(8, psz2 - &g_szAll[0]);
557	break;
558	}
559	psz2 = RTStrNextCp(psz2);
560	if (psz2 != psz1)
561	{
562	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetNext returned different next pointer!");
563	whereami(8, psz2 - &g_szAll[0]);
564	break;
565	}
566
567	RTUNICP uc3;
568	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
569	if (RT_FAILURE(rc))
570	{
571	RTTestFailed(hTest, "RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs", rc, pwsz4);
572	whereami(16, pwsz4 - &g_wszAll[0]);
573	break;
574	}
575	if (uc3 != uc2)
576	{
577	RTTestFailed(hTest, "RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc2);
578	whereami(16, pwsz4 - &g_wszAll[0]);
579	break;
580	}
581	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
582	if (uc3 != uc4)
583	{
584	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc4);
585	whereami(16, pwsz4 - &g_wszAll[0]);
586	break;
587	}
588	pwsz4 = RTUtf16NextCp(pwsz4);
589	if (pwsz4 != pwsz3)
590	{
591	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!");
592	whereami(8, pwsz4 - &g_wszAll[0]);
593	break;
594	}
595
596
597	/*
598	* putters
599	*/
600	pszPut1 = RTStrPutCp(pszPut1, uc1);
601	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
602	{
603	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
604	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
605	whereami(8, psz2 - &g_szAll[0]);
606	break;
607	}
608
609	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
610	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
611	{
612	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
613	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
614	whereami(8, pwsz4 - &g_wszAll[0]);
615	break;
616	}
617
618
619	/* the end? */
620	if (!uc1)
621	break;
622	}
623
624	/* check output if we seems to have made it thru it all. */
625	if (psz2 == &g_szAll[sizeof(g_szAll)])
626	{
627	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
628	RTTestFailed(hTest, "RTStrPutCp encoded the string incorrectly.");
629	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
630	RTTestFailed(hTest, "RTUtf16PutCp encoded the string incorrectly.");
631	}
632
633	RTMemFree(pszPut1Base);
634	RTMemFree(pwszPut2Base);
635
636	RTTestSubDone(hTest);
637	}
638
639
640	/**
641	* Check case insensitivity.
642	*/
643	void test3(RTTEST hTest)
644	{
645	RTTestSub(hTest, "Case Sensitivitity");
646
647	if ( RTUniCpToLower('a') != 'a'
648	\|\| RTUniCpToLower('A') != 'a'
649	\|\| RTUniCpToLower('b') != 'b'
650	\|\| RTUniCpToLower('B') != 'b'
651	\|\| RTUniCpToLower('Z') != 'z'
652	\|\| RTUniCpToLower('z') != 'z'
653	\|\| RTUniCpToUpper('c') != 'C'
654	\|\| RTUniCpToUpper('C') != 'C'
655	\|\| RTUniCpToUpper('z') != 'Z'
656	\|\| RTUniCpToUpper('Z') != 'Z')
657	RTTestFailed(hTest, "RTUniToUpper/Lower failed basic tests.\n");
658
659	if (RTUtf16ICmp(g_wszAll, g_wszAll))
660	RTTestFailed(hTest, "RTUtf16ICmp failed the basic test.\n");
661
662	if (RTUtf16Cmp(g_wszAll, g_wszAll))
663	RTTestFailed(hTest, "RTUtf16Cmp failed the basic test.\n");
664
665	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 };
666	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 };
667	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
668	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
669	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
670	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
671	)
672	RTTestFailed(hTest, "RTUtf16ICmp failed the alphabet test.\n");
673
674	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
675	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
676	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
677	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
678	)
679	RTTestFailed(hTest, "RTUtf16Cmp failed the alphabet test.\n");
680
681	RTTestSubDone(hTest);
682	}
683
684
685	/**
686	* Test the RTStr*Cmp functions.
687	*/
688	void TstRTStrXCmp(RTTEST hTest)
689	{
690	#define CHECK_DIFF(expr, op) \
691	do \
692	{ \
693	int iDiff = expr; \
694	if (!(iDiff op 0)) \
695	RTTestFailed(hTest, "%d: %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
696	} while (0)
697
698	/** @todo test the non-ascii bits. */
699
700	RTTestSub(hTest, "RTStrCmp");
701	CHECK_DIFF(RTStrCmp(NULL, NULL), == );
702	CHECK_DIFF(RTStrCmp(NULL, ""), < );
703	CHECK_DIFF(RTStrCmp("", NULL), > );
704	CHECK_DIFF(RTStrCmp("", ""), == );
705	CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
706	CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
707	CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
708	CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
709	CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
710	CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
711	CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
712
713
714	RTTestSub(hTest, "RTStrNCmp");
715	CHECK_DIFF(RTStrNCmp(NULL, NULL, RTSTR_MAX), == );
716	CHECK_DIFF(RTStrNCmp(NULL, "", RTSTR_MAX), < );
717	CHECK_DIFF(RTStrNCmp("", NULL, RTSTR_MAX), > );
718	CHECK_DIFF(RTStrNCmp("", "", RTSTR_MAX), == );
719	CHECK_DIFF(RTStrNCmp("abcdef", "abcdef", RTSTR_MAX), == );
720	CHECK_DIFF(RTStrNCmp("abcdef", "abcde", RTSTR_MAX), > );
721	CHECK_DIFF(RTStrNCmp("abcde", "abcdef", RTSTR_MAX), < );
722	CHECK_DIFF(RTStrNCmp("abcdeg", "abcdef", RTSTR_MAX), > );
723	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeg", RTSTR_MAX), < );
724	CHECK_DIFF(RTStrNCmp("abcdeF", "abcdef", RTSTR_MAX), < );
725	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", RTSTR_MAX), > );
726
727	CHECK_DIFF(RTStrNCmp("abcdef", "fedcba", 0), ==);
728	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 5), ==);
729	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 6), > );
730
731
732	RTTestSub(hTest, "RTStrICmp");
733	CHECK_DIFF(RTStrICmp(NULL, NULL), == );
734	CHECK_DIFF(RTStrICmp(NULL, ""), < );
735	CHECK_DIFF(RTStrICmp("", NULL), > );
736	CHECK_DIFF(RTStrICmp("", ""), == );
737	CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
738	CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
739	CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
740	CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
741	CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
742
743	CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), ==);
744	CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
745	CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
746	CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
747	CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
748	CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
749	CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
750
751
752
753	RTTestSub(hTest, "RTStrNICmp");
754	CHECK_DIFF(RTStrNICmp(NULL, NULL, RTSTR_MAX), == );
755	CHECK_DIFF(RTStrNICmp(NULL, "", RTSTR_MAX), < );
756	CHECK_DIFF(RTStrNICmp("", NULL, RTSTR_MAX), > );
757	CHECK_DIFF(RTStrNICmp("", "", RTSTR_MAX), == );
758	CHECK_DIFF(RTStrNICmp(NULL, NULL, 0), == );
759	CHECK_DIFF(RTStrNICmp(NULL, "", 0), == );
760	CHECK_DIFF(RTStrNICmp("", NULL, 0), == );
761	CHECK_DIFF(RTStrNICmp("", "", 0), == );
762	CHECK_DIFF(RTStrNICmp("abcdef", "abcdef", RTSTR_MAX), == );
763	CHECK_DIFF(RTStrNICmp("abcdef", "abcde", RTSTR_MAX), > );
764	CHECK_DIFF(RTStrNICmp("abcde", "abcdef", RTSTR_MAX), < );
765	CHECK_DIFF(RTStrNICmp("abcdeg", "abcdef", RTSTR_MAX), > );
766	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeg", RTSTR_MAX), < );
767
768	CHECK_DIFF(RTStrNICmp("abcdeF", "abcdef", RTSTR_MAX), ==);
769	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeF", RTSTR_MAX), ==);
770	CHECK_DIFF(RTStrNICmp("ABCDEF", "abcdef", RTSTR_MAX), ==);
771	CHECK_DIFF(RTStrNICmp("abcdef", "ABCDEF", RTSTR_MAX), ==);
772	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", RTSTR_MAX), ==);
773	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", RTSTR_MAX), > );
774	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", RTSTR_MAX), > ); /* diff performed on the lower case cp. */
775
776	CHECK_DIFF(RTStrNICmp("ABCDEF", "fedcba", 0), ==);
777	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 5), ==);
778	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", 5), ==);
779	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDe", 5), ==);
780	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDeF", 5), ==);
781	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDe", 5), ==);
782	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 6), > );
783	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", 6), > ); /* diff performed on the lower case cp. */
784	/* We should continue using byte comparison when we hit the invalid CP. Will assert in debug builds. */
785	// CHECK_DIFF(RTStrNICmp("AbCd\xff""eg", "aBcD\xff""eF", 6), ==);
786
787	RTTestSubDone(hTest);
788	}
789
790
791
792	/**
793	* Benchmark stuff.
794	*/
795	void Benchmarks(RTTEST hTest)
796	{
797	static union
798	{
799	RTUTF16 wszBuf[sizeof(g_wszAll)];
800	char szBuf[sizeof(g_szAll)];
801	} s_Buf;
802
803	RTTestSub(hTest, "Benchmarks");
804	/** @todo add RTTest* methods for reporting benchmark results. */
805	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTStrToUtf16Ex: "); /** @todo figure this stuff into the test framework. */
806	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
807	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
808	if (RT_SUCCESS(rc))
809	{
810	int i;
811	uint64_t u64Start = RTTimeNanoTS();
812	for (i = 0; i < 100; i++)
813	{
814	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
815	if (RT_FAILURE(rc))
816	{
817	RTTestFailed(hTest, "UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
818	break;
819	}
820	}
821	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
822	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
823	}
824
825	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTUtf16ToUtf8Ex: ");
826	char *psz = &s_Buf.szBuf[0];
827	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
828	if (RT_SUCCESS(rc))
829	{
830	int i;
831	uint64_t u64Start = RTTimeNanoTS();
832	for (i = 0; i < 100; i++)
833	{
834	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
835	if (RT_FAILURE(rc))
836	{
837	RTTestFailed(hTest, "UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
838	break;
839	}
840	}
841	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
842	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
843	}
844
845	RTTestSubDone(hTest);
846	}
847
848
849	/**
850	* Tests RTStrStr and RTStrIStr.
851	*/
852	static void testStrStr(RTTEST hTest)
853	{
854	#define CHECK_NULL(expr) \
855	do { \
856	const char *pszRet = expr; \
857	if (pszRet != NULL) \
858	RTTestFailed(hTest, "%d: %#x -> %s expected NULL", __LINE__, #expr, pszRet); \
859	} while (0)
860
861	#define CHECK(expr, expect) \
862	do { \
863	const char *pszRet = expr; \
864	if ( (pszRet != NULL && (expect) == NULL) \
865	\|\| (pszRet == NULL && (expect) != NULL) \
866	\|\| strcmp(pszRet, (expect)) \
867	) \
868	RTTestFailed(hTest, "%d: %#x -> %s expected %s", __LINE__, #expr, pszRet, (expect)); \
869	} while (0)
870
871
872	RTTestSub(hTest, "RTStrStr");
873	CHECK(RTStrStr("abcdef", ""), "abcdef");
874	CHECK_NULL(RTStrStr("abcdef", NULL));
875	CHECK_NULL(RTStrStr(NULL, ""));
876	CHECK_NULL(RTStrStr(NULL, NULL));
877	CHECK(RTStrStr("abcdef", "abcdef"), "abcdef");
878	CHECK(RTStrStr("abcdef", "b"), "bcdef");
879	CHECK(RTStrStr("abcdef", "bcdef"), "bcdef");
880	CHECK(RTStrStr("abcdef", "cdef"), "cdef");
881	CHECK(RTStrStr("abcdef", "cde"), "cdef");
882	CHECK(RTStrStr("abcdef", "cd"), "cdef");
883	CHECK(RTStrStr("abcdef", "c"), "cdef");
884	CHECK(RTStrStr("abcdef", "f"), "f");
885	CHECK(RTStrStr("abcdef", "ef"), "ef");
886	CHECK(RTStrStr("abcdef", "e"), "ef");
887	CHECK_NULL(RTStrStr("abcdef", "z"));
888	CHECK_NULL(RTStrStr("abcdef", "A"));
889	CHECK_NULL(RTStrStr("abcdef", "F"));
890
891	RTTestSub(hTest, "RTStrIStr");
892	CHECK(RTStrIStr("abcdef", ""), "abcdef");
893	CHECK_NULL(RTStrIStr("abcdef", NULL));
894	CHECK_NULL(RTStrIStr(NULL, ""));
895	CHECK_NULL(RTStrIStr(NULL, NULL));
896	CHECK(RTStrIStr("abcdef", "abcdef"), "abcdef");
897	CHECK(RTStrIStr("abcdef", "Abcdef"), "abcdef");
898	CHECK(RTStrIStr("abcdef", "ABcDeF"), "abcdef");
899	CHECK(RTStrIStr("abcdef", "b"), "bcdef");
900	CHECK(RTStrIStr("abcdef", "B"), "bcdef");
901	CHECK(RTStrIStr("abcdef", "bcdef"), "bcdef");
902	CHECK(RTStrIStr("abcdef", "BCdEf"), "bcdef");
903	CHECK(RTStrIStr("abcdef", "bCdEf"), "bcdef");
904	CHECK(RTStrIStr("abcdef", "bcdEf"), "bcdef");
905	CHECK(RTStrIStr("abcdef", "BcdEf"), "bcdef");
906	CHECK(RTStrIStr("abcdef", "cdef"), "cdef");
907	CHECK(RTStrIStr("abcdef", "cde"), "cdef");
908	CHECK(RTStrIStr("abcdef", "cd"), "cdef");
909	CHECK(RTStrIStr("abcdef", "c"), "cdef");
910	CHECK(RTStrIStr("abcdef", "f"), "f");
911	CHECK(RTStrIStr("abcdeF", "F"), "F");
912	CHECK(RTStrIStr("abcdef", "F"), "f");
913	CHECK(RTStrIStr("abcdef", "ef"), "ef");
914	CHECK(RTStrIStr("EeEef", "e"), "EeEef");
915	CHECK(RTStrIStr("EeEef", "E"), "EeEef");
916	CHECK(RTStrIStr("EeEef", "EE"), "EeEef");
917	CHECK(RTStrIStr("EeEef", "EEE"), "EeEef");
918	CHECK(RTStrIStr("EeEef", "EEEF"), "eEef");
919	CHECK_NULL(RTStrIStr("EeEef", "z"));
920
921	#undef CHECK
922	#undef CHECK_NULL
923	RTTestSubDone(hTest);
924	}
925
926
927	void testMinistring(RTTEST hTest)
928	{
929	RTTestSub(hTest, "class iprt::MiniString");
930
931	#define CHECK(expr) \
932	do { \
933	if (!(expr)) \
934	RTTestFailed(hTest, "%d: FAILED %s", __LINE__, #expr); \
935	} while (0)
936
937	#define CHECK_DUMP(expr, value) \
938	do { \
939	if (!(expr)) \
940	RTTestFailed(hTest, "%d: FAILED %s, got \"%s\"", __LINE__, #expr, value); \
941	} while (0)
942
943	#define CHECK_DUMP_I(expr) \
944	do { \
945	if (!(expr)) \
946	RTTestFailed(hTest, "%d: FAILED %s, got \"%d\"", __LINE__, #expr, expr); \
947	} while (0)
948
949	iprt::MiniString empty;
950	CHECK( (empty.length() == 0) );
951	CHECK( (empty.capacity() == 0) );
952
953	iprt::MiniString sixbytes("12345");
954	CHECK( (sixbytes.length() == 5) );
955	CHECK( (sixbytes.capacity() == 6) );
956
957	sixbytes.append("678");
958	CHECK( (sixbytes.length() == 8) );
959	CHECK( (sixbytes.capacity() == 9) );
960
961	char *psz = sixbytes.mutableRaw();
962	// 12345678
963	// ^
964	// 0123456
965	psz[6] = '\0';
966	sixbytes.jolt();
967	CHECK( (sixbytes.length() == 6) );
968	CHECK( (sixbytes.capacity() == 7) );
969
970	iprt::MiniString morebytes("tobereplaced");
971	morebytes = "newstring ";
972	morebytes.append(sixbytes);
973
974	CHECK_DUMP( (morebytes == "newstring 123456"), morebytes.c_str() );
975
976	iprt::MiniString third(morebytes);
977	third.reserve(100 * 1024); // 100 KB
978	CHECK_DUMP( (third == "newstring 123456"), morebytes.c_str() );
979	CHECK( (third.capacity() == 100 * 1024) );
980	CHECK( (third.length() == morebytes.length()) ); // must not have changed
981
982	iprt::MiniString copy1(morebytes);
983	iprt::MiniString copy2 = morebytes;
984	CHECK( (copy1 == copy2) );
985
986	copy1 = NULL;
987	CHECK( (copy1.length() == 0) );
988
989	copy1 = "";
990	CHECK( (copy1.length() == 0) );
991
992	CHECK( (iprt::MiniString("abc") < iprt::MiniString("def")) );
993	CHECK( (iprt::MiniString("abc") != iprt::MiniString("def")) );
994	CHECK_DUMP_I( (iprt::MiniString("def") > iprt::MiniString("abc")) );
995
996	copy2.setNull();
997	for (int i = 0;
998	i < 100;
999	++i)
1000	{
1001	copy2.reserve(50); // should be ignored after 50 loops
1002	copy2.append("1");
1003	}
1004	CHECK( (copy2.length() == 100) );
1005
1006	copy2.setNull();
1007	for (int i = 0;
1008	i < 100;
1009	++i)
1010	{
1011	copy2.reserve(50); // should be ignored after 50 loops
1012	copy2.append('1');
1013	}
1014	CHECK( (copy2.length() == 100) );
1015
1016	#undef CHECK
1017	}
1018
1019
1020	void testLatin1(RTTEST hTest)
1021	{
1022	RTTestSub(hTest, "Latin1 conversion functions");
1023
1024	/* Test Utf16 -> Latin1 */
1025	size_t cch_szAll = 0;
1026	size_t cbShort = RTUtf16CalcLatin1Len(g_wszAll);
1027	RTTEST_CHECK(hTest, cbShort == 0);
1028	int rc = RTUtf16CalcLatin1LenEx(g_wszAll, 255, &cch_szAll);
1029	RTTEST_CHECK(hTest, (cch_szAll == 255));
1030	rc = RTUtf16CalcLatin1LenEx(g_wszAll, RTSTR_MAX, &cch_szAll);
1031	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1032	char *psz = NULL;
1033	RTUTF16 wszShort[256] = { 0 };
1034	for (unsigned i = 0; i < 255; ++i)
1035	wszShort[i] = i + 1;
1036	cbShort = RTUtf16CalcLatin1Len(wszShort);
1037	RTTEST_CHECK(hTest, cbShort == 255);
1038	rc = RTUtf16ToLatin1(wszShort, &psz);
1039	RTTEST_CHECK_RC_OK(hTest, rc);
1040	if (RT_SUCCESS(rc))
1041	{
1042	RTTEST_CHECK(hTest, (strlen(psz) == 255));
1043	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1044	if (psz[i] != (char) j)
1045	{
1046	RTTestFailed(hTest, "conversion of g_wszAll to Latin1 failed at position %u\n", i);
1047	break;
1048	}
1049	}
1050	RTStrFree(psz);
1051	rc = RTUtf16ToLatin1(g_wszAll, &psz);
1052	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1053	char sz[512];
1054	char *psz2 = &sz[0];
1055	size_t cchActual = 0;
1056	rc = RTUtf16ToLatin1Ex(g_wszAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1057	&cchActual);
1058	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1059	RTTEST_CHECK_MSG(hTest, cchActual == 0,
1060	(hTest, "cchActual=%lu\n", cchActual));
1061	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz2, sizeof(sz),
1062	&cchActual);
1063	RTTEST_CHECK_RC_OK(hTest, rc);
1064	if (RT_SUCCESS(rc))
1065	{
1066	RTTEST_CHECK(hTest, (cchActual == 255));
1067	RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1068	for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1069	if (psz2[i] != (char) j)
1070	{
1071	RTTestFailed(hTest, "second conversion of g_wszAll to Latin1 failed at position %u\n", i);
1072	break;
1073	}
1074	}
1075	rc = RTUtf16ToLatin1Ex(g_wszAll, 128, &psz2, 128, &cchActual);
1076	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1077	RTTEST_CHECK_MSG(hTest, cchActual == 128,
1078	(hTest, "cchActual=%lu\n", cchActual));
1079	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz, 0, &cchActual);
1080	RTTEST_CHECK_RC_OK(hTest, rc);
1081	if (RT_SUCCESS(rc))
1082	{
1083	RTTEST_CHECK(hTest, (cchActual == 255));
1084	RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1085	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1086	if ( ((j < 0x100) && (psz[i] != (char) j))
1087	\|\| ((j > 0xff) && psz[i] != '?'))
1088	{
1089	RTTestFailed(hTest, "third conversion of g_wszAll to Latin1 failed at position %u\n", i);
1090	break;
1091	}
1092	}
1093	const char *pszBad = "H\0e\0l\0l\0o\0\0\xDC\0\xD8\0";
1094	rc = RTUtf16ToLatin1Ex((RTUTF16 *) pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1095	&cchActual);
1096	RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF16_ENCODING);
1097	RTStrFree(psz);
1098
1099	/* Test Latin1 -> Utf16 */
1100	const char *pszLat1 = "\x01\x20\x40\x80\x81";
1101	RTTEST_CHECK(hTest, (RTLatin1CalcUtf16Len(pszLat1) == 5));
1102	rc = RTLatin1CalcUtf16LenEx(pszLat1, 3, &cchActual);
1103	RTTEST_CHECK_RC_OK(hTest, rc);
1104	if (RT_SUCCESS(rc))
1105	RTTEST_CHECK(hTest, (cchActual == 3));
1106	rc = RTLatin1CalcUtf16LenEx(pszLat1, RTSTR_MAX, &cchActual);
1107	RTTEST_CHECK_RC_OK(hTest, rc);
1108	if (RT_SUCCESS(rc))
1109	RTTEST_CHECK(hTest, (cchActual == 5));
1110	RTUTF16 *pwc = NULL;
1111	RTUTF16 wc[6];
1112	RTUTF16 *pwc2 = &wc[0];
1113	size_t cwActual = 0;
1114	rc = RTLatin1ToUtf16(pszLat1, &pwc);
1115	RTTEST_CHECK_RC_OK(hTest, rc);
1116	if (RT_SUCCESS(rc))
1117	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1118	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1119	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1120	RTUtf16Free(pwc);
1121	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, &cwActual);
1122	RTTEST_CHECK_RC_OK(hTest, rc);
1123	if (RT_SUCCESS(rc))
1124	{
1125	RTTEST_CHECK(hTest, (cwActual == 5));
1126	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1127	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1128	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1129	}
1130	RTUtf16Free(pwc);
1131	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, NULL);
1132	RTTEST_CHECK_RC_OK(hTest, rc);
1133	if (RT_SUCCESS(rc))
1134	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1135	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1136	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1137	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc),
1138	&cwActual);
1139	RTTEST_CHECK_RC_OK(hTest, rc);
1140	if (RT_SUCCESS(rc))
1141	{
1142	RTTEST_CHECK(hTest, (cwActual == 5));
1143	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1144	&& (wc[2] == 0x40) && (wc[3] == 0x80)
1145	&& (wc[4] == 0x81) && (wc[5] == '\0'));
1146	}
1147	rc = RTLatin1ToUtf16Ex(pszLat1, 3, &pwc2, RT_ELEMENTS(wc),
1148	&cwActual);
1149	RTTEST_CHECK_RC_OK(hTest, rc);
1150	if (RT_SUCCESS(rc))
1151	{
1152	RTTEST_CHECK(hTest, (cwActual == 3));
1153	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1154	&& (wc[2] == 0x40) && (wc[3] == '\0'));
1155	}
1156	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc) - 1,
1157	&cwActual);
1158	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1159	/** @todo Either fix the documentation or fix the code - cchActual is
1160	* set to the number of bytes actually encoded. */
1161	RTTEST_CHECK(hTest, (cwActual == 5));
1162	RTTestSubDone(hTest);
1163	}
1164
1165
1166	static void testNoTransation(RTTEST hTest)
1167	{
1168
1169	/*
1170	* Try trigger a VERR_NO_TRANSLATION error in convert to
1171	* current CP to latin-1.
1172	*/
1173	const RTUTF16 s_swzTest1[] = { 0x2358, 0x2242, 0x2357, 0x2359, 0x22f9, 0x2c4e, 0x0030, 0x0060,
1174	0x0092, 0x00c1, 0x00f2, 0x1f80, 0x0088, 0x2c38, 0x2c30, 0x0000 };
1175	char *pszTest1;
1176	int rc = RTUtf16ToUtf8(s_swzTest1, &pszTest1);
1177	RTTESTI_CHECK_RC_RETV(rc, VINF_SUCCESS);
1178
1179	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTStrUtf8ToCurrentCP");
1180	char *pszOut;
1181	rc = RTStrUtf8ToCurrentCP(&pszOut, pszTest1);
1182	if (RT_SUCCESS(rc))
1183	{
1184	RTTESTI_CHECK(!strcmp(pszOut, pszTest1));
1185	RTTestIPrintf(RTTESTLVL_ALWAYS, "CurrentCP is UTF-8 or similar\n");
1186	RTStrFree(pszOut);
1187	}
1188	else
1189	RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1190
1191	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTUtf16ToLatin1");
1192	rc = RTUtf16ToLatin1(s_swzTest1, &pszOut);
1193	RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1194	if (RT_SUCCESS(rc))
1195	RTStrFree(pszOut);
1196
1197	RTStrFree(pszTest1);
1198	RTTestSubDone(hTest);
1199	}
1200
1201
1202	int main()
1203	{
1204	/*
1205	* Init the runtime, test and say hello.
1206	*/
1207	RTTEST hTest;
1208	int rc = RTTestInitAndCreate("tstUtf8", &hTest);
1209	if (rc)
1210	return rc;
1211	RTTestBanner(hTest);
1212
1213	/*
1214	* Run the test.
1215	*/
1216	InitStrings();
1217	test1(hTest);
1218	test2(hTest);
1219	test3(hTest);
1220	TstRTStrXCmp(hTest);
1221	testStrStr(hTest);
1222	testMinistring(hTest);
1223	testLatin1(hTest);
1224	testNoTransation(hTest);
1225
1226	Benchmarks(hTest);
1227
1228	/*
1229	* Summary
1230	*/
1231	return RTTestSummaryAndDestroy(hTest);
1232	}
1233

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 30016

Download in other formats: