tstUtf8.cpp@ 46072

Last change on this file since 46072 was 45262, checked in by vboxsync, 12 years ago
tstUtf8: Another VERR_NO_TRANSLATE/VWRN_NO_TRANSLATE hack.
Property svn:eol-style set to `native` Property svn:keywords set to `Id`
File size: 55.1 KB

Line
1	/* $Id: tstUtf8.cpp 45262 2013-03-31 04:20:26Z vboxsync $ */
2	/** @file
3	* IPRT Testcase - UTF-8 and UTF-16 string conversions.
4	*/
5
6	/*
7	* Copyright (C) 2006-2013 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
32	#include <iprt/alloc.h>
33	#include <iprt/assert.h>
34	#include <iprt/env.h>
35	#include <iprt/err.h>
36	#include <iprt/rand.h>
37	#include <iprt/stream.h>
38	#include <iprt/test.h>
39	#include <iprt/time.h>
40	#include <iprt/uni.h>
41	#include <iprt/uuid.h>
42
43
44
45	/**
46	* Generate a random codepoint for simple UTF-16 encoding.
47	*/
48	static RTUTF16 GetRandUtf16(void)
49	{
50	RTUTF16 wc;
51	do
52	{
53	wc = (RTUTF16)RTRandU32Ex(1, 0xfffd);
54	} while (wc >= 0xd800 && wc <= 0xdfff);
55	return wc;
56	}
57
58
59	/**
60	*
61	*/
62	static void test1(RTTEST hTest)
63	{
64	static const char s_szBadString1[] = "Bad \xe0\x13\x0";
65	static const char s_szBadString2[] = "Bad \xef\xbf\xc3";
66	int rc;
67	char *pszUtf8;
68	char *pszCurrent;
69	PRTUTF16 pwsz;
70	PRTUTF16 pwszRand;
71
72	/*
73	* Invalid UTF-8 to UCS-2 test.
74	*/
75	RTTestSub(hTest, "Feeding bad UTF-8 to RTStrToUtf16");
76	rc = RTStrToUtf16(s_szBadString1, &pwsz);
77	RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION \|\| rc == VERR_INVALID_UTF8_ENCODING,
78	(hTest, "Conversion of first bad UTF-8 string to UTF-16 apparently succeeded. It shouldn't. rc=%Rrc\n", rc));
79	rc = RTStrToUtf16(s_szBadString2, &pwsz);
80	RTTEST_CHECK_MSG(hTest, rc == VERR_NO_TRANSLATION \|\| rc == VERR_INVALID_UTF8_ENCODING,
81	(hTest, "Conversion of second bad UTF-8 strings to UTF-16 apparently succeeded. It shouldn't. rc=%Rrc\n", rc));
82
83	/*
84	* Test current CP conversion.
85	*/
86	RTTestSub(hTest, "Rand UTF-16 -> UTF-8 -> CP -> UTF-8");
87	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
88	for (int i = 0; i < 30; i++)
89	pwszRand[i] = GetRandUtf16();
90	pwszRand[30] = 0;
91
92	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
93	if (rc == VINF_SUCCESS)
94	{
95	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
96	if (rc == VINF_SUCCESS)
97	{
98	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
99	if (rc == VINF_SUCCESS)
100	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
101	else
102	RTTestFailed(hTest, "%d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
103	__LINE__, rc);
104	}
105	else if (rc == VERR_NO_TRANSLATION)
106	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");
107	else if (rc == VWRN_NO_TRANSLATION)
108	RTTestPassed(hTest, "The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 returned VWRN_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	for (int i = 0; i < 30; i++)
123	pwszRand[i] = GetRandUtf16();
124	pwszRand[30] = 0;
125	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
126	if (rc == VINF_SUCCESS)
127	{
128	rc = RTStrToUtf16(pszUtf8, &pwsz);
129	if (rc == VINF_SUCCESS)
130	{
131	int i;
132	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
133	/* nothing */;
134	if (pwszRand[i] == pwsz[i] && pwsz[i] == 0)
135	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> UTF-16 successful.\n");
136	else
137	{
138	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed.", __LINE__);
139	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
140	}
141	}
142	else
143	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
144	__LINE__, rc);
145	}
146	else
147	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> UTF-16 failed with return value %Rrc.",
148	__LINE__, rc);
149
150	/*
151	* Generate yet another random string and convert it to a buffer.
152	*/
153	RTTestSub(hTest, "Random RTUtf16ToUtf8Ex + RTStrToUtf16");
154	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
155	for (int i = 0; i < 30; i++)
156	pwszRand[i] = GetRandUtf16();
157	pwszRand[30] = 0;
158
159	char szUtf8Array[120];
160	char *pszUtf8Array = szUtf8Array;
161	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
162	if (rc == 0)
163	{
164	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
165	if (rc == 0)
166	{
167	int i;
168	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
169	;
170	if (pwsz[i] == 0 && i >= 8)
171	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
172	else
173	{
174	RTTestFailed(hTest, "%d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
175	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
176	}
177	}
178	else
179	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
180	}
181	else
182	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
183
184	/*
185	* And again.
186	*/
187	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
188	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
189	for (int i = 0; i < 30; i++)
190	pwszRand[i] = GetRandUtf16();
191	pwszRand[30] = 0;
192
193	RTUTF16 wszBuf[70];
194	PRTUTF16 pwsz2Buf = wszBuf;
195	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
196	if (rc == 0)
197	{
198	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
199	if (rc == 0)
200	{
201	int i;
202	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++)
203	;
204	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
205	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
206	else
207	{
208	RTTestFailed(hTest, "%d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
209	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
210	}
211	}
212	else
213	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
214	}
215	else
216	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
217	__LINE__, rc);
218	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
219	for (int i = 0; i < 30; i++)
220	pwszRand[i] = GetRandUtf16();
221	pwszRand[30] = 0;
222
223	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
224	if (rc == VERR_BUFFER_OVERFLOW)
225	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
226	else
227	RTTestFailed(hTest, "%d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
228	__LINE__, rc);
229
230	/*
231	* last time...
232	*/
233	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
234	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
235	for (int i = 0; i < 30; i++)
236	pwszRand[i] = GetRandUtf16();
237	pwszRand[30] = 0;
238
239	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
240	if (rc == VINF_SUCCESS)
241	{
242	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
243	if (rc == VERR_BUFFER_OVERFLOW)
244	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
245	else
246	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",
247	__LINE__, rc);
248	}
249	else
250	RTTestFailed(hTest, "%d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
251	__LINE__, rc);
252
253
254	RTTestSubDone(hTest);
255	}
256
257
258	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
259	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
260	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
261
262	static void whereami(int cBits, size_t off)
263	{
264	if (cBits == 8)
265	{
266	if (off < 0x7f)
267	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", off + 1);
268	else if (off < 0xf7f)
269	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
270	else if (off < 0x27f7f)
271	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
272	else if (off < 0x2df79)
273	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
274	else if (off < 0x42df79)
275	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
276	else
277	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 ???\n");
278	}
279	else if (cBits == 16)
280	{
281	if (off < 0xd7ff*2)
282	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", off / 2 + 1);
283	else if (off < 0xf7fd*2)
284	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
285	else if (off < 0x20f7fd)
286	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
287	else
288	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 ???\n");
289	}
290	else
291	{
292	if (off < (0xd800 - 1) * sizeof(RTUNICP))
293	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
294	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
295	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
296	else
297	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
298	}
299	}
300
301	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
302	{
303	const uint8_t pb1 = (const uint8_t )pv1;
304	const uint8_t pb2 = (const uint8_t )pv2;
305	for (size_t off = 0; off < cb; off++)
306	{
307	if (pb1[off] != pb2[off])
308	{
309	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "mismatch at %#x: ", off);
310	whereami(cBits, off);
311	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off-1, pb1[off-1], pb2[off-1]);
312	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "*%#x: %02x != %02x!\n", off, pb1[off], pb2[off]);
313	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+1, pb1[off+1], pb2[off+1]);
314	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+2, pb1[off+2], pb2[off+2]);
315	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+3, pb1[off+3], pb2[off+3]);
316	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+4, pb1[off+4], pb2[off+4]);
317	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+5, pb1[off+5], pb2[off+5]);
318	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+6, pb1[off+6], pb2[off+6]);
319	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+7, pb1[off+7], pb2[off+7]);
320	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+8, pb1[off+8], pb2[off+8]);
321	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+9, pb1[off+9], pb2[off+9]);
322	return 1;
323	}
324	}
325	return 0;
326	}
327
328
329	void InitStrings()
330	{
331	/*
332	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
333	*/
334	/* the simple code point array first */
335	unsigned i = 0;
336	RTUNICP uc = 1;
337	while (uc < 0xd800)
338	g_uszAll[i++] = uc++;
339	uc = 0xe000;
340	while (uc < 0xfffe)
341	g_uszAll[i++] = uc++;
342	uc = 0x10000;
343	while (uc < 0x110000)
344	g_uszAll[i++] = uc++;
345	g_uszAll[i++] = 0;
346	Assert(RT_ELEMENTS(g_uszAll) == i);
347
348	/* the utf-16 one */
349	i = 0;
350	uc = 1;
351	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
352	while (uc < 0xd800)
353	g_wszAll[i++] = uc++;
354	uc = 0xe000;
355	//RTPrintf(" %#x=%#x", i, uc);
356	while (uc < 0xfffe)
357	g_wszAll[i++] = uc++;
358	uc = 0x10000;
359	//RTPrintf(" %#x=%#x", i, uc);
360	while (uc < 0x110000)
361	{
362	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
363	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
364	uc++;
365	}
366	//RTPrintf(" %#x=%#x\n", i, uc);
367	g_wszAll[i++] = '\0';
368	Assert(RT_ELEMENTS(g_wszAll) == i);
369
370	/*
371	* The utf-8 one
372	*/
373	i = 0;
374	uc = 1;
375	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
376	while (uc < 0x80)
377	g_szAll[i++] = uc++;
378	//RTPrintf(" %#x=%#x", i, uc);
379	while (uc < 0x800)
380	{
381	g_szAll[i++] = 0xc0 \| (uc >> 6);
382	g_szAll[i++] = 0x80 \| (uc & 0x3f);
383	Assert(!((uc >> 6) & ~0x1f));
384	uc++;
385	}
386	//RTPrintf(" %#x=%#x", i, uc);
387	while (uc < 0xd800)
388	{
389	g_szAll[i++] = 0xe0 \| (uc >> 12);
390	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
391	g_szAll[i++] = 0x80 \| (uc & 0x3f);
392	Assert(!((uc >> 12) & ~0xf));
393	uc++;
394	}
395	uc = 0xe000;
396	//RTPrintf(" %#x=%#x", i, uc);
397	while (uc < 0xfffe)
398	{
399	g_szAll[i++] = 0xe0 \| (uc >> 12);
400	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
401	g_szAll[i++] = 0x80 \| (uc & 0x3f);
402	Assert(!((uc >> 12) & ~0xf));
403	uc++;
404	}
405	uc = 0x10000;
406	//RTPrintf(" %#x=%#x", i, uc);
407	while (uc < 0x110000)
408	{
409	g_szAll[i++] = 0xf0 \| (uc >> 18);
410	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
411	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
412	g_szAll[i++] = 0x80 \| (uc & 0x3f);
413	Assert(!((uc >> 18) & ~0x7));
414	uc++;
415	}
416	//RTPrintf(" %#x=%#x\n", i, uc);
417	g_szAll[i++] = '\0';
418	Assert(RT_ELEMENTS(g_szAll) == i);
419	}
420
421
422	void test2(RTTEST hTest)
423	{
424	/*
425	* Convert to UTF-8 and back.
426	*/
427	RTTestSub(hTest, "UTF-16 -> UTF-8 -> UTF-16");
428	char *pszUtf8;
429	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
430	if (rc == VINF_SUCCESS)
431	{
432	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
433	RTTestFailed(hTest, "UTF-16 -> UTF-8 mismatch!");
434
435	PRTUTF16 pwszUtf16;
436	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
437	if (rc == VINF_SUCCESS)
438	{
439	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
440	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
441	RTUtf16Free(pwszUtf16);
442	}
443	else
444	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
445	RTStrFree(pszUtf8);
446	}
447	else
448	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
449
450
451	/*
452	* Convert to UTF-16 and back. (just in case the above test fails)
453	*/
454	RTTestSub(hTest, "UTF-8 -> UTF-16 -> UTF-8");
455	PRTUTF16 pwszUtf16;
456	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
457	if (rc == VINF_SUCCESS)
458	{
459	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
460	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
461
462	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
463	if (rc == VINF_SUCCESS)
464	{
465	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
466	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed compare!");
467	RTStrFree(pszUtf8);
468	}
469	else
470	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
471	RTUtf16Free(pwszUtf16);
472	}
473	else
474	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
475
476	/*
477	* Convert UTF-8 to CPs.
478	*/
479	RTTestSub(hTest, "UTF-8 -> UNI -> UTF-8");
480	PRTUNICP paCps;
481	rc = RTStrToUni(g_szAll, &paCps);
482	if (rc == VINF_SUCCESS)
483	{
484	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
485	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
486
487	size_t cCps;
488	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, RT_ELEMENTS(g_uszAll), &cCps);
489	if (rc == VINF_SUCCESS)
490	{
491	if (cCps != RT_ELEMENTS(g_uszAll) - 1)
492	RTTestFailed(hTest, "wrong Code Point count %zu, expected %zu\n", cCps, RT_ELEMENTS(g_uszAll) - 1);
493	}
494	else
495	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
496
497	/** @todo RTCpsToUtf8 or something. */
498	}
499	else
500	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
501
502	/*
503	* Check the various string lengths.
504	*/
505	RTTestSub(hTest, "Lengths");
506	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
507	size_t cuc2 = RTUtf16Len(g_wszAll);
508	if (cuc1 != cuc2)
509	RTTestFailed(hTest, "cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
510	//size_t cuc3 = RTUniLen(g_uszAll);
511
512
513	/*
514	* Enumerate the strings.
515	*/
516	RTTestSub(hTest, "Code Point Getters and Putters");
517	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
518	AssertRelease(pszPut1Base);
519	char *pszPut1 = pszPut1Base;
520	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
521	AssertRelease(pwszPut2Base);
522	PRTUTF16 pwszPut2 = pwszPut2Base;
523	const char *psz1 = g_szAll;
524	const char *psz2 = g_szAll;
525	PCRTUTF16 pwsz3 = g_wszAll;
526	PCRTUTF16 pwsz4 = g_wszAll;
527	for (;;)
528	{
529	/*
530	* getters
531	*/
532	RTUNICP uc1;
533	rc = RTStrGetCpEx(&psz1, &uc1);
534	if (RT_FAILURE(rc))
535	{
536	RTTestFailed(hTest, "RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs", rc, psz2);
537	whereami(8, psz2 - &g_szAll[0]);
538	break;
539	}
540	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
541	if (pszPrev1 != psz2)
542	{
543	RTTestFailed(hTest, "RTStrPrevCp returned %p expected %p!", pszPrev1, psz2);
544	whereami(8, psz2 - &g_szAll[0]);
545	break;
546	}
547	RTUNICP uc2 = RTStrGetCp(psz2);
548	if (uc2 != uc1)
549	{
550	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc2, uc1);
551	whereami(8, psz2 - &g_szAll[0]);
552	break;
553	}
554	psz2 = RTStrNextCp(psz2);
555	if (psz2 != psz1)
556	{
557	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetNext returned different next pointer!");
558	whereami(8, psz2 - &g_szAll[0]);
559	break;
560	}
561
562	RTUNICP uc3;
563	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
564	if (RT_FAILURE(rc))
565	{
566	RTTestFailed(hTest, "RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs", rc, pwsz4);
567	whereami(16, pwsz4 - &g_wszAll[0]);
568	break;
569	}
570	if (uc3 != uc2)
571	{
572	RTTestFailed(hTest, "RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc2);
573	whereami(16, pwsz4 - &g_wszAll[0]);
574	break;
575	}
576	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
577	if (uc3 != uc4)
578	{
579	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc4);
580	whereami(16, pwsz4 - &g_wszAll[0]);
581	break;
582	}
583	pwsz4 = RTUtf16NextCp(pwsz4);
584	if (pwsz4 != pwsz3)
585	{
586	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!");
587	whereami(8, pwsz4 - &g_wszAll[0]);
588	break;
589	}
590
591
592	/*
593	* putters
594	*/
595	pszPut1 = RTStrPutCp(pszPut1, uc1);
596	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
597	{
598	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
599	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
600	whereami(8, psz2 - &g_szAll[0]);
601	break;
602	}
603
604	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
605	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
606	{
607	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
608	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
609	whereami(8, pwsz4 - &g_wszAll[0]);
610	break;
611	}
612
613
614	/* the end? */
615	if (!uc1)
616	break;
617	}
618
619	/* check output if we seems to have made it thru it all. */
620	if (psz2 == &g_szAll[sizeof(g_szAll)])
621	{
622	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
623	RTTestFailed(hTest, "RTStrPutCp encoded the string incorrectly.");
624	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
625	RTTestFailed(hTest, "RTUtf16PutCp encoded the string incorrectly.");
626	}
627
628	RTMemFree(pszPut1Base);
629	RTMemFree(pwszPut2Base);
630
631	RTTestSubDone(hTest);
632	}
633
634
635	/**
636	* Check case insensitivity.
637	*/
638	void test3(RTTEST hTest)
639	{
640	RTTestSub(hTest, "Case Sensitivity");
641
642	if ( RTUniCpToLower('a') != 'a'
643	\|\| RTUniCpToLower('A') != 'a'
644	\|\| RTUniCpToLower('b') != 'b'
645	\|\| RTUniCpToLower('B') != 'b'
646	\|\| RTUniCpToLower('Z') != 'z'
647	\|\| RTUniCpToLower('z') != 'z'
648	\|\| RTUniCpToUpper('c') != 'C'
649	\|\| RTUniCpToUpper('C') != 'C'
650	\|\| RTUniCpToUpper('z') != 'Z'
651	\|\| RTUniCpToUpper('Z') != 'Z')
652	RTTestFailed(hTest, "RTUniToUpper/Lower failed basic tests.\n");
653
654	if (RTUtf16ICmp(g_wszAll, g_wszAll))
655	RTTestFailed(hTest, "RTUtf16ICmp failed the basic test.\n");
656
657	if (RTUtf16Cmp(g_wszAll, g_wszAll))
658	RTTestFailed(hTest, "RTUtf16Cmp failed the basic test.\n");
659
660	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 };
661	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 };
662	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
663	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
664	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
665	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
666	)
667	RTTestFailed(hTest, "RTUtf16ICmp failed the alphabet test.\n");
668
669	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
670	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
671	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
672	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
673	)
674	RTTestFailed(hTest, "RTUtf16Cmp failed the alphabet test.\n");
675
676	RTTestSubDone(hTest);
677	}
678
679
680	/**
681	* Test the RTStr*Cmp functions.
682	*/
683	void TstRTStrXCmp(RTTEST hTest)
684	{
685	#define CHECK_DIFF(expr, op) \
686	do \
687	{ \
688	int iDiff = expr; \
689	if (!(iDiff op 0)) \
690	RTTestFailed(hTest, "%d: %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
691	} while (0)
692
693	/** @todo test the non-ascii bits. */
694
695	RTTestSub(hTest, "RTStrCmp");
696	CHECK_DIFF(RTStrCmp(NULL, NULL), == );
697	CHECK_DIFF(RTStrCmp(NULL, ""), < );
698	CHECK_DIFF(RTStrCmp("", NULL), > );
699	CHECK_DIFF(RTStrCmp("", ""), == );
700	CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
701	CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
702	CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
703	CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
704	CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
705	CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
706	CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
707
708
709	RTTestSub(hTest, "RTStrNCmp");
710	CHECK_DIFF(RTStrNCmp(NULL, NULL, RTSTR_MAX), == );
711	CHECK_DIFF(RTStrNCmp(NULL, "", RTSTR_MAX), < );
712	CHECK_DIFF(RTStrNCmp("", NULL, RTSTR_MAX), > );
713	CHECK_DIFF(RTStrNCmp("", "", RTSTR_MAX), == );
714	CHECK_DIFF(RTStrNCmp("abcdef", "abcdef", RTSTR_MAX), == );
715	CHECK_DIFF(RTStrNCmp("abcdef", "abcde", RTSTR_MAX), > );
716	CHECK_DIFF(RTStrNCmp("abcde", "abcdef", RTSTR_MAX), < );
717	CHECK_DIFF(RTStrNCmp("abcdeg", "abcdef", RTSTR_MAX), > );
718	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeg", RTSTR_MAX), < );
719	CHECK_DIFF(RTStrNCmp("abcdeF", "abcdef", RTSTR_MAX), < );
720	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", RTSTR_MAX), > );
721
722	CHECK_DIFF(RTStrNCmp("abcdef", "fedcba", 0), ==);
723	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 5), ==);
724	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 6), > );
725
726
727	RTTestSub(hTest, "RTStrICmp");
728	CHECK_DIFF(RTStrICmp(NULL, NULL), == );
729	CHECK_DIFF(RTStrICmp(NULL, ""), < );
730	CHECK_DIFF(RTStrICmp("", NULL), > );
731	CHECK_DIFF(RTStrICmp("", ""), == );
732	CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
733	CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
734	CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
735	CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
736	CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
737
738	CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), ==);
739	CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
740	CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
741	CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
742	CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
743	CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
744	CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
745
746
747
748	RTTestSub(hTest, "RTStrNICmp");
749	CHECK_DIFF(RTStrNICmp(NULL, NULL, RTSTR_MAX), == );
750	CHECK_DIFF(RTStrNICmp(NULL, "", RTSTR_MAX), < );
751	CHECK_DIFF(RTStrNICmp("", NULL, RTSTR_MAX), > );
752	CHECK_DIFF(RTStrNICmp("", "", RTSTR_MAX), == );
753	CHECK_DIFF(RTStrNICmp(NULL, NULL, 0), == );
754	CHECK_DIFF(RTStrNICmp(NULL, "", 0), == );
755	CHECK_DIFF(RTStrNICmp("", NULL, 0), == );
756	CHECK_DIFF(RTStrNICmp("", "", 0), == );
757	CHECK_DIFF(RTStrNICmp("abcdef", "abcdef", RTSTR_MAX), == );
758	CHECK_DIFF(RTStrNICmp("abcdef", "abcde", RTSTR_MAX), > );
759	CHECK_DIFF(RTStrNICmp("abcde", "abcdef", RTSTR_MAX), < );
760	CHECK_DIFF(RTStrNICmp("abcdeg", "abcdef", RTSTR_MAX), > );
761	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeg", RTSTR_MAX), < );
762
763	CHECK_DIFF(RTStrNICmp("abcdeF", "abcdef", RTSTR_MAX), ==);
764	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeF", RTSTR_MAX), ==);
765	CHECK_DIFF(RTStrNICmp("ABCDEF", "abcdef", RTSTR_MAX), ==);
766	CHECK_DIFF(RTStrNICmp("abcdef", "ABCDEF", RTSTR_MAX), ==);
767	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", RTSTR_MAX), ==);
768	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", RTSTR_MAX), > );
769	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", RTSTR_MAX), > ); /* diff performed on the lower case cp. */
770
771	CHECK_DIFF(RTStrNICmp("ABCDEF", "fedcba", 0), ==);
772	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 5), ==);
773	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", 5), ==);
774	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDe", 5), ==);
775	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDeF", 5), ==);
776	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDe", 5), ==);
777	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 6), > );
778	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", 6), > ); /* diff performed on the lower case cp. */
779	/* We should continue using byte comparison when we hit the invalid CP. Will assert in debug builds. */
780	// CHECK_DIFF(RTStrNICmp("AbCd\xff""eg", "aBcD\xff""eF", 6), ==);
781
782	RTTestSubDone(hTest);
783	}
784
785
786
787	/**
788	* Check UTF-8 encoding purging.
789	*/
790	void TstRTStrPurgeEncoding(RTTEST hTest)
791	{
792	RTTestSub(hTest, "RTStrPurgeEncoding");
793
794	/*
795	* Test some good strings.
796	*/
797	char sz1[] = "1234567890wertyuiopsdfghjklzxcvbnm";
798	char sz1Copy[sizeof(sz1)];
799	memcpy(sz1Copy, sz1, sizeof(sz1));
800
801	RTTESTI_CHECK_RETV(RTStrPurgeEncoding(sz1) == 0);
802	RTTESTI_CHECK_RETV(!memcmp(sz1, sz1Copy, sizeof(sz1)));
803
804	char *pszAll = RTStrDup(g_szAll);
805	if (pszAll)
806	{
807	RTTESTI_CHECK(RTStrPurgeEncoding(pszAll) == 0);
808	RTTESTI_CHECK(!memcmp(pszAll, g_szAll, sizeof(g_szAll)));
809	RTStrFree(pszAll);
810	}
811
812	/*
813	* Test some bad stuff.
814	*/
815	struct
816	{
817	size_t cErrors;
818	unsigned char szIn[5];
819	const char *pszExpect;
820	} aTests[] =
821	{
822	{ 0, { '1', '2', '3', '4', '\0' }, "1234" },
823	{ 1, { 0x80, '2', '3', '4', '\0' }, "?234" },
824	{ 1, { '1', 0x80, '3', '4', '\0' }, "1?34" },
825	{ 1, { '1', '2', 0x80, '4', '\0' }, "12?4" },
826	{ 1, { '1', '2', '3', 0x80, '\0' }, "123?" },
827	{ 2, { 0x80, 0x81, '3', '4', '\0' }, "??34" },
828	{ 2, { '1', 0x80, 0x81, '4', '\0' }, "1??4" },
829	{ 2, { '1', '2', 0x80, 0x81, '\0' }, "12??" },
830	};
831	for (size_t i = 0; i < RT_ELEMENTS(aTests); i++)
832	{
833	size_t cErrors = RTStrPurgeEncoding((char *)aTests[i].szIn);
834	if (cErrors != aTests[i].cErrors)
835	RTTestFailed(hTest, "#%u: cErrors=%u expected %u\n", i, cErrors, aTests[i].cErrors);
836	else if (strcmp((char *)aTests[i].szIn, aTests[i].pszExpect))
837	RTTestFailed(hTest, "#%u: %.5Rhxs expected %.5Rhxs (%s)\n", i, aTests[i].szIn, aTests[i].pszExpect, aTests[i].pszExpect);
838	}
839
840	RTTestSubDone(hTest);
841	}
842
843
844	/**
845	* Check string sanitising.
846	*/
847	void TstRTStrPurgeComplementSet(RTTEST hTest)
848	{
849	RTTestSub(hTest, "RTStrPurgeComplementSet");
850	RTUNICP aCpSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
851	'\0' };
852	RTUNICP aCpBadSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
853	'7', '\0' }; /* Contains an incomplete pair. */
854	struct
855	{
856	const char *pcszIn;
857	const char *pcszOut;
858	PCRTUNICP pcCpSet;
859	char chReplacement;
860	ssize_t cExpected;
861	}
862	aTests[] =
863	{
864	{ "1234werttrew4321", "1234werttrew4321", aCpSet, '_', 0 },
865	{ "123654wert\xc2\xa2trew\xe2\x82\xac""4321",
866	"123_54wert__trew___4321", aCpSet, '_', 3 },
867	{ "hjhj8766", "????????", aCpSet, '?', 8 },
868	{ "123\xf0\xa4\xad\xa2""4", "123____4", aCpSet, '_', 1 },
869	{ "\xff", "\xff", aCpSet, '_', -1 },
870	{ "____", "____", aCpBadSet, '_', -1 }
871	};
872	enum { MAX_IN_STRING = 256 };
873
874	for (unsigned i = 0; i < RT_ELEMENTS(aTests); ++i)
875	{
876	char szCopy[MAX_IN_STRING];
877	ssize_t cReplacements;
878	AssertRC(RTStrCopy(szCopy, RT_ELEMENTS(szCopy), aTests[i].pcszIn));
879	cReplacements = RTStrPurgeComplementSet(szCopy, aTests[i].pcCpSet,
880	aTests[i].chReplacement);
881	if (cReplacements != aTests[i].cExpected)
882	RTTestFailed(hTest, "#%u: expected %lld, actual %lld\n", i,
883	(long long) aTests[i].cExpected,
884	(long long) cReplacements);
885	if (strcmp(aTests[i].pcszOut, szCopy))
886	RTTestFailed(hTest, "#%u: expected %s, actual %s\n", i,
887	aTests[i].pcszOut, szCopy);
888	}
889	}
890
891
892	/**
893	* Check string sanitising.
894	*/
895	void TstRTUtf16PurgeComplementSet(RTTEST hTest)
896	{
897	RTTestSub(hTest, "RTUtf16PurgeComplementSet");
898	RTUNICP aCpSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
899	'\0' };
900	RTUNICP aCpBadSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
901	'7', '\0' }; /* Contains an incomplete pair. */
902	struct
903	{
904	const char *pcszIn;
905	const char *pcszOut;
906	size_t cwc; /* Zero means the strings are Utf-8. */
907	PCRTUNICP pcCpSet;
908	char chReplacement;
909	ssize_t cExpected;
910	}
911	aTests[] =
912	{
913	{ "1234werttrew4321", "1234werttrew4321", 0, aCpSet, '_', 0 },
914	{ "123654wert\xc2\xa2trew\xe2\x82\xac""4321",
915	"123_54wert_trew_4321", 0, aCpSet, '_', 3 },
916	{ "hjhj8766", "????????", 0, aCpSet, '?', 8 },
917	{ "123\xf0\xa4\xad\xa2""4", "123__4", 0, aCpSet, '_', 1 },
918	{ "\xff\xff\0", "\xff\xff\0", 2, aCpSet, '_', -1 },
919	{ "\xff\xff\0", "\xff\xff\0", 2, aCpSet, '_', -1 },
920	{ "____", "____", 0, aCpBadSet, '_', -1 }
921	};
922	enum { MAX_IN_STRING = 256 };
923
924	for (unsigned i = 0; i < RT_ELEMENTS(aTests); ++i)
925	{
926	RTUTF16 wszInCopy[MAX_IN_STRING], *pwszInCopy = wszInCopy;
927	RTUTF16 wszOutCopy[MAX_IN_STRING], *pwszOutCopy = wszOutCopy;
928	ssize_t cReplacements;
929	if (!aTests[i].cwc)
930	{
931	AssertRC(RTStrToUtf16Ex(aTests[i].pcszIn, RTSTR_MAX, &pwszInCopy,
932	RT_ELEMENTS(wszInCopy), NULL));
933	AssertRC(RTStrToUtf16Ex(aTests[i].pcszOut, RTSTR_MAX, &pwszOutCopy,
934	RT_ELEMENTS(wszOutCopy), NULL));
935	}
936	else
937	{
938	Assert(aTests[i].cwc <= RT_ELEMENTS(wszInCopy));
939	memcpy(wszInCopy, aTests[i].pcszIn, aTests[i].cwc * 2);
940	memcpy(wszOutCopy, aTests[i].pcszOut, aTests[i].cwc * 2);
941	}
942	cReplacements = RTUtf16PurgeComplementSet(wszInCopy, aTests[i].pcCpSet,
943	aTests[i].chReplacement);
944	if (cReplacements != aTests[i].cExpected)
945	RTTestFailed(hTest, "#%u: expected %lld, actual %lld\n", i,
946	(long long) aTests[i].cExpected,
947	(long long) cReplacements);
948	if (RTUtf16Cmp(wszInCopy, wszOutCopy))
949	RTTestFailed(hTest, "#%u: expected %ls, actual %ls\n", i,
950	wszOutCopy, wszInCopy);
951	}
952	}
953
954
955	/**
956	* Benchmark stuff.
957	*/
958	void Benchmarks(RTTEST hTest)
959	{
960	static union
961	{
962	RTUTF16 wszBuf[sizeof(g_wszAll)];
963	char szBuf[sizeof(g_szAll)];
964	} s_Buf;
965
966	RTTestSub(hTest, "Benchmarks");
967	/** @todo add RTTest* methods for reporting benchmark results. */
968	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTStrToUtf16Ex: "); /** @todo figure this stuff into the test framework. */
969	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
970	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
971	if (RT_SUCCESS(rc))
972	{
973	int i;
974	uint64_t u64Start = RTTimeNanoTS();
975	for (i = 0; i < 100; i++)
976	{
977	rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
978	if (RT_FAILURE(rc))
979	{
980	RTTestFailed(hTest, "UTF-8 -> UTF-16 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
981	break;
982	}
983	}
984	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
985	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
986	}
987
988	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTUtf16ToUtf8Ex: ");
989	char *psz = &s_Buf.szBuf[0];
990	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
991	if (RT_SUCCESS(rc))
992	{
993	int i;
994	uint64_t u64Start = RTTimeNanoTS();
995	for (i = 0; i < 100; i++)
996	{
997	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
998	if (RT_FAILURE(rc))
999	{
1000	RTTestFailed(hTest, "UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
1001	break;
1002	}
1003	}
1004	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
1005	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
1006	}
1007
1008	RTTestSubDone(hTest);
1009	}
1010
1011
1012	/**
1013	* Tests RTStrEnd
1014	*/
1015	static void testStrEnd(RTTEST hTest)
1016	{
1017	RTTestSub(hTest, "RTStrEnd");
1018
1019	static char const s_szEmpty[1] = "";
1020	RTTESTI_CHECK(RTStrEnd(s_szEmpty, 0) == NULL);
1021	RTTESTI_CHECK(RTStrEnd(s_szEmpty, 1) == &s_szEmpty[0]);
1022	for (size_t i = 0; i < _1M; i++)
1023	RTTESTI_CHECK(RTStrEnd(s_szEmpty, ~i) == &s_szEmpty[0]);
1024
1025	}
1026
1027
1028	/**
1029	* Tests RTStrStr and RTStrIStr.
1030	*/
1031	static void testStrStr(RTTEST hTest)
1032	{
1033	#define CHECK_NULL(expr) \
1034	do { \
1035	const char *pszRet = expr; \
1036	if (pszRet != NULL) \
1037	RTTestFailed(hTest, "%d: %#x -> %s expected NULL", __LINE__, #expr, pszRet); \
1038	} while (0)
1039
1040	#define CHECK(expr, expect) \
1041	do { \
1042	const char *pszRet = expr; \
1043	if ( (pszRet != NULL && (expect) == NULL) \
1044	\|\| (pszRet == NULL && (expect) != NULL) \
1045	\|\| strcmp(pszRet, (expect)) \
1046	) \
1047	RTTestFailed(hTest, "%d: %#x -> %s expected %s", __LINE__, #expr, pszRet, (expect)); \
1048	} while (0)
1049
1050
1051	RTTestSub(hTest, "RTStrStr");
1052	CHECK(RTStrStr("abcdef", ""), "abcdef");
1053	CHECK_NULL(RTStrStr("abcdef", NULL));
1054	CHECK_NULL(RTStrStr(NULL, ""));
1055	CHECK_NULL(RTStrStr(NULL, NULL));
1056	CHECK(RTStrStr("abcdef", "abcdef"), "abcdef");
1057	CHECK(RTStrStr("abcdef", "b"), "bcdef");
1058	CHECK(RTStrStr("abcdef", "bcdef"), "bcdef");
1059	CHECK(RTStrStr("abcdef", "cdef"), "cdef");
1060	CHECK(RTStrStr("abcdef", "cde"), "cdef");
1061	CHECK(RTStrStr("abcdef", "cd"), "cdef");
1062	CHECK(RTStrStr("abcdef", "c"), "cdef");
1063	CHECK(RTStrStr("abcdef", "f"), "f");
1064	CHECK(RTStrStr("abcdef", "ef"), "ef");
1065	CHECK(RTStrStr("abcdef", "e"), "ef");
1066	CHECK_NULL(RTStrStr("abcdef", "z"));
1067	CHECK_NULL(RTStrStr("abcdef", "A"));
1068	CHECK_NULL(RTStrStr("abcdef", "F"));
1069
1070	RTTestSub(hTest, "RTStrIStr");
1071	CHECK(RTStrIStr("abcdef", ""), "abcdef");
1072	CHECK_NULL(RTStrIStr("abcdef", NULL));
1073	CHECK_NULL(RTStrIStr(NULL, ""));
1074	CHECK_NULL(RTStrIStr(NULL, NULL));
1075	CHECK(RTStrIStr("abcdef", "abcdef"), "abcdef");
1076	CHECK(RTStrIStr("abcdef", "Abcdef"), "abcdef");
1077	CHECK(RTStrIStr("abcdef", "ABcDeF"), "abcdef");
1078	CHECK(RTStrIStr("abcdef", "b"), "bcdef");
1079	CHECK(RTStrIStr("abcdef", "B"), "bcdef");
1080	CHECK(RTStrIStr("abcdef", "bcdef"), "bcdef");
1081	CHECK(RTStrIStr("abcdef", "BCdEf"), "bcdef");
1082	CHECK(RTStrIStr("abcdef", "bCdEf"), "bcdef");
1083	CHECK(RTStrIStr("abcdef", "bcdEf"), "bcdef");
1084	CHECK(RTStrIStr("abcdef", "BcdEf"), "bcdef");
1085	CHECK(RTStrIStr("abcdef", "cdef"), "cdef");
1086	CHECK(RTStrIStr("abcdef", "cde"), "cdef");
1087	CHECK(RTStrIStr("abcdef", "cd"), "cdef");
1088	CHECK(RTStrIStr("abcdef", "c"), "cdef");
1089	CHECK(RTStrIStr("abcdef", "f"), "f");
1090	CHECK(RTStrIStr("abcdeF", "F"), "F");
1091	CHECK(RTStrIStr("abcdef", "F"), "f");
1092	CHECK(RTStrIStr("abcdef", "ef"), "ef");
1093	CHECK(RTStrIStr("EeEef", "e"), "EeEef");
1094	CHECK(RTStrIStr("EeEef", "E"), "EeEef");
1095	CHECK(RTStrIStr("EeEef", "EE"), "EeEef");
1096	CHECK(RTStrIStr("EeEef", "EEE"), "EeEef");
1097	CHECK(RTStrIStr("EeEef", "EEEF"), "eEef");
1098	CHECK_NULL(RTStrIStr("EeEef", "z"));
1099
1100	#undef CHECK
1101	#undef CHECK_NULL
1102	RTTestSubDone(hTest);
1103	}
1104
1105
1106	void testUtf8Latin1(RTTEST hTest)
1107	{
1108	RTTestSub(hTest, "Latin-1 <-> Utf-8 conversion functions");
1109
1110	/* Test Utf8 -> Latin1 */
1111	size_t cch_szAll = 0;
1112	size_t cbShort = RTStrCalcLatin1Len(g_szAll);
1113	RTTEST_CHECK(hTest, cbShort == 0);
1114	int rc = RTStrCalcLatin1LenEx(g_szAll, 383, &cch_szAll);
1115	RTTEST_CHECK(hTest, (cch_szAll == 255));
1116	rc = RTStrCalcLatin1LenEx(g_szAll, RTSTR_MAX, &cch_szAll);
1117	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1118	char *psz = NULL;
1119	char szShort[256] = { 0 };
1120	memcpy(szShort, g_szAll, 255);
1121	cbShort = RTStrCalcLatin1Len(szShort);
1122	RTTEST_CHECK(hTest, cbShort == 191);
1123	rc = RTStrToLatin1(szShort, &psz);
1124	RTTEST_CHECK_RC_OK(hTest, rc);
1125	if (RT_SUCCESS(rc))
1126	{
1127	RTTEST_CHECK(hTest, (strlen(psz) == 191));
1128	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1129	if (psz[i] != (char) j)
1130	{
1131	RTTestFailed(hTest, "conversion of g_szAll to Latin1 failed at position %u\n", i);
1132	break;
1133	}
1134	}
1135	RTStrFree(psz);
1136	rc = RTStrToLatin1(g_szAll, &psz);
1137	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1138	char sz[512];
1139	char *psz2 = &sz[0];
1140	size_t cchActual = 0;
1141	rc = RTStrToLatin1Ex(g_szAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1142	&cchActual);
1143	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1144	RTTEST_CHECK_MSG(hTest, cchActual == 0,
1145	(hTest, "cchActual=%lu\n", cchActual));
1146	rc = RTStrToLatin1Ex(g_szAll, 383, &psz2, sizeof(sz),
1147	&cchActual);
1148	RTTEST_CHECK_RC_OK(hTest, rc);
1149	if (RT_SUCCESS(rc))
1150	{
1151	RTTEST_CHECK(hTest, (cchActual == 255));
1152	RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1153	for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1154	if (psz2[i] != (char) j)
1155	{
1156	RTTestFailed(hTest, "second conversion of g_szAll to Latin1 failed at position %u\n", i);
1157	break;
1158	}
1159	}
1160	rc = RTStrToLatin1Ex(g_szAll, 129, &psz2, 128, &cchActual);
1161	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1162	RTTEST_CHECK_MSG(hTest, cchActual == 128,
1163	(hTest, "cchActual=%lu\n", cchActual));
1164	rc = RTStrToLatin1Ex(g_szAll, 383, &psz, 0, &cchActual);
1165	RTTEST_CHECK_RC_OK(hTest, rc);
1166	if (RT_SUCCESS(rc))
1167	{
1168	RTTEST_CHECK(hTest, (cchActual == 255));
1169	RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1170	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1171	if ( ((j < 0x100) && (psz[i] != (char) j))
1172	\|\| ((j > 0xff) && psz[i] != '?'))
1173	{
1174	RTTestFailed(hTest, "third conversion of g_szAll to Latin1 failed at position %u\n", i);
1175	break;
1176	}
1177	}
1178	const char *pszBad = "Hello\xDC\xD8";
1179	rc = RTStrToLatin1Ex(pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1180	&cchActual);
1181	RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF8_ENCODING);
1182	RTStrFree(psz);
1183
1184	/* Test Latin1 -> Utf8 */
1185	const char *pszLat1 = "\x01\x20\x40\x80\x81";
1186	RTTEST_CHECK(hTest, RTLatin1CalcUtf8Len(pszLat1) == 7);
1187	rc = RTLatin1CalcUtf8LenEx(pszLat1, 3, &cchActual);
1188	RTTEST_CHECK_RC_OK(hTest, rc);
1189	if (RT_SUCCESS(rc))
1190	RTTEST_CHECK(hTest, cchActual == 3);
1191	rc = RTLatin1CalcUtf8LenEx(pszLat1, RTSTR_MAX, &cchActual);
1192	RTTEST_CHECK_RC_OK(hTest, rc);
1193	if (RT_SUCCESS(rc))
1194	RTTEST_CHECK(hTest, cchActual == 7);
1195	char *pch = NULL;
1196	char ch[8];
1197	char *pch2 = &ch[0];
1198	cchActual = 0;
1199	rc = RTLatin1ToUtf8(pszLat1, &pch);
1200	RTTEST_CHECK_RC_OK(hTest, rc);
1201	if (RT_SUCCESS(rc))
1202	RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1203	RTStrFree(pch);
1204	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch, 0, &cchActual);
1205	RTTEST_CHECK_RC_OK(hTest, rc);
1206	if (RT_SUCCESS(rc))
1207	{
1208	RTTEST_CHECK(hTest, (cchActual == 7));
1209	RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1210	}
1211	RTStrFree(pch);
1212	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch, 0, NULL);
1213	RTTEST_CHECK_RC_OK(hTest, rc);
1214	if (RT_SUCCESS(rc))
1215	RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1216	RTStrFree(pch);
1217	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch2, RT_ELEMENTS(ch),
1218	&cchActual);
1219	RTTEST_CHECK_RC_OK(hTest, rc);
1220	if (RT_SUCCESS(rc))
1221	{
1222	RTTEST_CHECK(hTest, (cchActual == 7));
1223	RTTEST_CHECK(hTest, !strcmp(pch2, "\x01\x20\x40\xC2\x80\xC2\x81"));
1224	}
1225	rc = RTLatin1ToUtf8Ex(pszLat1, 3, &pch2, RT_ELEMENTS(ch),
1226	&cchActual);
1227	RTTEST_CHECK_RC_OK(hTest, rc);
1228	if (RT_SUCCESS(rc))
1229	{
1230	RTTEST_CHECK(hTest, (cchActual == 3));
1231	RTTEST_CHECK(hTest, !strcmp(pch2, "\x01\x20\x40"));
1232	}
1233	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch2, RT_ELEMENTS(ch) - 1,
1234	&cchActual);
1235	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1236	RTTEST_CHECK(hTest, (cchActual == 7));
1237	RTTestSubDone(hTest);
1238	}
1239
1240
1241	void testUtf16Latin1(RTTEST hTest)
1242	{
1243	RTTestSub(hTest, "Latin-1 <-> Utf-16 conversion functions");
1244
1245	/* Test Utf16 -> Latin1 */
1246	size_t cch_szAll = 0;
1247	size_t cbShort = RTUtf16CalcLatin1Len(g_wszAll);
1248	RTTEST_CHECK(hTest, cbShort == 0);
1249	int rc = RTUtf16CalcLatin1LenEx(g_wszAll, 255, &cch_szAll);
1250	RTTEST_CHECK(hTest, (cch_szAll == 255));
1251	rc = RTUtf16CalcLatin1LenEx(g_wszAll, RTSTR_MAX, &cch_szAll);
1252	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1253	char *psz = NULL;
1254	RTUTF16 wszShort[256] = { 0 };
1255	for (unsigned i = 0; i < 255; ++i)
1256	wszShort[i] = i + 1;
1257	cbShort = RTUtf16CalcLatin1Len(wszShort);
1258	RTTEST_CHECK(hTest, cbShort == 255);
1259	rc = RTUtf16ToLatin1(wszShort, &psz);
1260	RTTEST_CHECK_RC_OK(hTest, rc);
1261	if (RT_SUCCESS(rc))
1262	{
1263	RTTEST_CHECK(hTest, (strlen(psz) == 255));
1264	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1265	if (psz[i] != (char) j)
1266	{
1267	RTTestFailed(hTest, "conversion of g_wszAll to Latin1 failed at position %u\n", i);
1268	break;
1269	}
1270	}
1271	RTStrFree(psz);
1272	rc = RTUtf16ToLatin1(g_wszAll, &psz);
1273	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1274	char sz[512];
1275	char *psz2 = &sz[0];
1276	size_t cchActual = 0;
1277	rc = RTUtf16ToLatin1Ex(g_wszAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1278	&cchActual);
1279	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1280	RTTEST_CHECK_MSG(hTest, cchActual == 0,
1281	(hTest, "cchActual=%lu\n", cchActual));
1282	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz2, sizeof(sz),
1283	&cchActual);
1284	RTTEST_CHECK_RC_OK(hTest, rc);
1285	if (RT_SUCCESS(rc))
1286	{
1287	RTTEST_CHECK(hTest, (cchActual == 255));
1288	RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1289	for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1290	if (psz2[i] != (char) j)
1291	{
1292	RTTestFailed(hTest, "second conversion of g_wszAll to Latin1 failed at position %u\n", i);
1293	break;
1294	}
1295	}
1296	rc = RTUtf16ToLatin1Ex(g_wszAll, 128, &psz2, 128, &cchActual);
1297	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1298	RTTEST_CHECK_MSG(hTest, cchActual == 128,
1299	(hTest, "cchActual=%lu\n", cchActual));
1300	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz, 0, &cchActual);
1301	RTTEST_CHECK_RC_OK(hTest, rc);
1302	if (RT_SUCCESS(rc))
1303	{
1304	RTTEST_CHECK(hTest, (cchActual == 255));
1305	RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1306	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1307	if ( ((j < 0x100) && (psz[i] != (char) j))
1308	\|\| ((j > 0xff) && psz[i] != '?'))
1309	{
1310	RTTestFailed(hTest, "third conversion of g_wszAll to Latin1 failed at position %u\n", i);
1311	break;
1312	}
1313	}
1314	const char *pszBad = "H\0e\0l\0l\0o\0\0\xDC\0\xD8\0";
1315	rc = RTUtf16ToLatin1Ex((RTUTF16 *) pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1316	&cchActual);
1317	RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF16_ENCODING);
1318	RTStrFree(psz);
1319
1320	/* Test Latin1 -> Utf16 */
1321	const char *pszLat1 = "\x01\x20\x40\x80\x81";
1322	RTTEST_CHECK(hTest, RTLatin1CalcUtf16Len(pszLat1) == 5);
1323	rc = RTLatin1CalcUtf16LenEx(pszLat1, 3, &cchActual);
1324	RTTEST_CHECK_RC_OK(hTest, rc);
1325	if (RT_SUCCESS(rc))
1326	RTTEST_CHECK(hTest, cchActual == 3);
1327	rc = RTLatin1CalcUtf16LenEx(pszLat1, RTSTR_MAX, &cchActual);
1328	RTTEST_CHECK_RC_OK(hTest, rc);
1329	if (RT_SUCCESS(rc))
1330	RTTEST_CHECK(hTest, cchActual == 5);
1331	RTUTF16 *pwc = NULL;
1332	RTUTF16 wc[6];
1333	RTUTF16 *pwc2 = &wc[0];
1334	size_t cwActual = 0;
1335	rc = RTLatin1ToUtf16(pszLat1, &pwc);
1336	RTTEST_CHECK_RC_OK(hTest, rc);
1337	if (RT_SUCCESS(rc))
1338	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1339	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1340	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1341	RTUtf16Free(pwc);
1342	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, &cwActual);
1343	RTTEST_CHECK_RC_OK(hTest, rc);
1344	if (RT_SUCCESS(rc))
1345	{
1346	RTTEST_CHECK(hTest, (cwActual == 5));
1347	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1348	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1349	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1350	}
1351	RTUtf16Free(pwc);
1352	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, NULL);
1353	RTTEST_CHECK_RC_OK(hTest, rc);
1354	if (RT_SUCCESS(rc))
1355	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1356	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1357	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1358	RTUtf16Free(pwc);
1359	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc),
1360	&cwActual);
1361	RTTEST_CHECK_RC_OK(hTest, rc);
1362	if (RT_SUCCESS(rc))
1363	{
1364	RTTEST_CHECK(hTest, (cwActual == 5));
1365	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1366	&& (wc[2] == 0x40) && (wc[3] == 0x80)
1367	&& (wc[4] == 0x81) && (wc[5] == '\0'));
1368	}
1369	rc = RTLatin1ToUtf16Ex(pszLat1, 3, &pwc2, RT_ELEMENTS(wc),
1370	&cwActual);
1371	RTTEST_CHECK_RC_OK(hTest, rc);
1372	if (RT_SUCCESS(rc))
1373	{
1374	RTTEST_CHECK(hTest, (cwActual == 3));
1375	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1376	&& (wc[2] == 0x40) && (wc[3] == '\0'));
1377	}
1378	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc) - 1,
1379	&cwActual);
1380	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1381	RTTEST_CHECK(hTest, (cwActual == 5));
1382	RTTestSubDone(hTest);
1383	}
1384
1385
1386	static void testNoTransation(RTTEST hTest)
1387	{
1388	/*
1389	* Try trigger a VERR_NO_TRANSLATION error in convert to
1390	* current CP to latin-1.
1391	*/
1392	const RTUTF16 s_swzTest1[] = { 0x2358, 0x2242, 0x2357, 0x2359, 0x22f9, 0x2c4e, 0x0030, 0x0060,
1393	0x0092, 0x00c1, 0x00f2, 0x1f80, 0x0088, 0x2c38, 0x2c30, 0x0000 };
1394	char *pszTest1;
1395	int rc = RTUtf16ToUtf8(s_swzTest1, &pszTest1);
1396	RTTESTI_CHECK_RC_RETV(rc, VINF_SUCCESS);
1397
1398	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTStrUtf8ToCurrentCP");
1399	char *pszOut;
1400	rc = RTStrUtf8ToCurrentCP(&pszOut, pszTest1);
1401	if (rc == VINF_SUCCESS)
1402	{
1403	RTTESTI_CHECK(!strcmp(pszOut, pszTest1));
1404	RTTestIPrintf(RTTESTLVL_ALWAYS, "CurrentCP is UTF-8 or similar (LC_ALL=%s LANG=%s LC_CTYPE=%s)\n",
1405	RTEnvGet("LC_ALL"), RTEnvGet("LANG"), RTEnvGet("LC_CTYPE"));
1406	RTStrFree(pszOut);
1407	}
1408	else
1409	RTTESTI_CHECK_MSG(rc == VWRN_NO_TRANSLATION \|\| rc == VERR_NO_TRANSLATION, ("rc=%Rrc\n", rc));
1410
1411	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTUtf16ToLatin1");
1412	rc = RTUtf16ToLatin1(s_swzTest1, &pszOut);
1413	RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1414	if (RT_SUCCESS(rc))
1415	RTStrFree(pszOut);
1416
1417	RTStrFree(pszTest1);
1418	RTTestSubDone(hTest);
1419	}
1420
1421	static void testGetPut(RTTEST hTest)
1422	{
1423	/*
1424	* Test RTStrPutCp, RTStrGetCp and RTStrGetCpEx.
1425	*/
1426	RTTestSub(hTest, "RTStrPutCp, RTStrGetCp and RTStrGetCpEx");
1427
1428	RTUNICP uc = 0;
1429	while (uc <= 0x10fffd)
1430	{
1431	/* Figure the range - skip illegal ranges. */
1432	RTUNICP ucFirst = uc;
1433	if (ucFirst - UINT32_C(0xd800) <= 0x7ff)
1434	ucFirst = 0xe000;
1435	else if (ucFirst == UINT32_C(0xfffe) \|\| ucFirst == UINT32_C(0xffff))
1436	ucFirst = 0x10000;
1437
1438	RTUNICP ucLast = ucFirst + 1023;
1439	if (ucLast - UINT32_C(0xd800) <= 0x7ff)
1440	ucLast = 0xd7ff;
1441	else if (ucLast == UINT32_C(0xfffe) \|\| ucLast == UINT32_C(0xffff))
1442	ucLast = 0xfffd;
1443
1444	/* Encode the range into a string, decode each code point as we go along. */
1445	char sz1[8192];
1446	char *pszDst = sz1;
1447	for (uc = ucFirst; uc <= ucLast; uc++)
1448	{
1449	char *pszBefore = pszDst;
1450	pszDst = RTStrPutCp(pszDst, uc);
1451	RTTESTI_CHECK(pszBefore - pszDst < 6);
1452
1453	RTUNICP uc2 = RTStrGetCp(pszBefore);
1454	RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1455
1456	const char *pszSrc = pszBefore;
1457	RTUNICP uc3 = 42;
1458	RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1459	RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1460	RTTESTI_CHECK_MSG(pszSrc == pszDst, ("pszSrc=%p pszDst=%p\n", pszSrc, pszDst));
1461	}
1462
1463	/* Decode and re-encode it. */
1464	const char *pszSrc = pszDst = sz1;
1465	for (uc = ucFirst; uc <= ucLast; uc++)
1466	{
1467	RTUNICP uc2 = RTStrGetCp(pszSrc);
1468	RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1469
1470	RTUNICP uc3 = 42;
1471	RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1472	RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1473
1474	pszDst = RTStrPutCp(pszDst, uc);
1475	RTTESTI_CHECK_MSG(pszSrc == pszDst, ("pszSrc=%p pszDst=%p\n", pszSrc, pszDst));
1476	pszSrc = pszDst;
1477	}
1478
1479	/* Decode and wipe it (checking compiler optimizations). */
1480	pszSrc = pszDst = sz1;
1481	for (uc = ucFirst; uc <= ucLast; uc++)
1482	{
1483	RTUNICP uc2 = RTStrGetCp(pszSrc);
1484	RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1485
1486	RTUNICP uc3 = 42;
1487	RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1488	RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1489
1490	pszDst = RTStrPutCp(pszDst, 0);
1491	}
1492
1493	/* advance */
1494	uc = ucLast + 1;
1495	}
1496
1497	}
1498
1499
1500	int main()
1501	{
1502	/*
1503	* Init the runtime, test and say hello.
1504	*/
1505	RTTEST hTest;
1506	RTEXITCODE rcExit = RTTestInitAndCreate("tstUtf8", &hTest);
1507	if (rcExit != RTEXITCODE_SUCCESS)
1508	return rcExit;
1509	RTTestBanner(hTest);
1510
1511	/*
1512	* Run the tests.
1513	*/
1514	InitStrings();
1515	test1(hTest);
1516	test2(hTest);
1517	test3(hTest);
1518	TstRTStrXCmp(hTest);
1519	TstRTStrPurgeEncoding(hTest);
1520	/* TstRTPurgeComplementSet test conditions which assert. /
1521	bool fAreQuiet = RTAssertAreQuiet(), fMayPanic = RTAssertMayPanic();
1522	RTAssertSetQuiet(true);
1523	RTAssertSetMayPanic(false);
1524	TstRTStrPurgeComplementSet(hTest);
1525	TstRTUtf16PurgeComplementSet(hTest);
1526	RTAssertSetQuiet(fAreQuiet);
1527	RTAssertSetMayPanic(fMayPanic);
1528	testStrEnd(hTest);
1529	testStrStr(hTest);
1530	testUtf8Latin1(hTest);
1531	testUtf16Latin1(hTest);
1532	testNoTransation(hTest);
1533	testGetPut(hTest);
1534
1535	Benchmarks(hTest);
1536
1537	/*
1538	* Summary
1539	*/
1540	return RTTestSummaryAndDestroy(hTest);
1541	}
1542

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 46072

Download in other formats: