tstUtf8.cpp@ 67808

Last change on this file since 67808 was 66362, checked in by vboxsync, 8 years ago
IPRT: Adding RTStrICmpAscii (mirrors RTUtf16ICmpAscii).
Property svn:eol-style set to `native` Property svn:keywords set to `Id Revision`
File size: 55.3 KB

Line
1	/* $Id: tstUtf8.cpp 66362 2017-03-30 13:48:18Z vboxsync $ */
2	/** @file
3	* IPRT Testcase - UTF-8 and UTF-16 string conversions.
4	*/
5
6	/*
7	* Copyright (C) 2006-2016 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	/*********************************************************************************************************************************
29	* Header Files *
30	*********************************************************************************************************************************/
31	#include <iprt/string.h>
32
33	#include <iprt/alloc.h>
34	#include <iprt/assert.h>
35	#include <iprt/env.h>
36	#include <iprt/err.h>
37	#include <iprt/rand.h>
38	#include <iprt/stream.h>
39	#include <iprt/test.h>
40	#include <iprt/time.h>
41	#include <iprt/uni.h>
42	#include <iprt/uuid.h>
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)RTRandU32Ex(1, 0xfffd);
55	} while (wc >= 0xd800 && wc <= 0xdfff);
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 apparently 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 apparently succeeded. It shouldn't. rc=%Rrc\n", rc));
83
84	/*
85	* Test current CP conversion.
86	*/
87	RTTestSub(hTest, "Rand UTF-16 -> UTF-8 -> CP -> UTF-8");
88	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
89	for (int i = 0; i < 30; i++)
90	pwszRand[i] = GetRandUtf16();
91	pwszRand[30] = 0;
92
93	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
94	if (rc == VINF_SUCCESS)
95	{
96	rc = RTStrUtf8ToCurrentCP(&pszCurrent, pszUtf8);
97	if (rc == VINF_SUCCESS)
98	{
99	rc = RTStrCurrentCPToUtf8(&pszUtf8, pszCurrent);
100	if (rc == VINF_SUCCESS)
101	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> Current -> UTF-8 successful.\n");
102	else
103	RTTestFailed(hTest, "%d: The third part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
104	__LINE__, rc);
105	}
106	else if (rc == VERR_NO_TRANSLATION)
107	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");
108	else if (rc == VWRN_NO_TRANSLATION)
109	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");
110	else
111	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
112	__LINE__, rc);
113	}
114	else
115	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> Current -> UTF-8 failed with return value %Rrc.",
116	__LINE__, rc);
117
118	/*
119	* Generate a new random string.
120	*/
121	RTTestSub(hTest, "Random UTF-16 -> UTF-8 -> UTF-16");
122	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
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	for (int i = 0; i < 30; i++)
157	pwszRand[i] = GetRandUtf16();
158	pwszRand[30] = 0;
159
160	char szUtf8Array[120];
161	char *pszUtf8Array = szUtf8Array;
162	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 120, NULL);
163	if (rc == 0)
164	{
165	rc = RTStrToUtf16(pszUtf8Array, &pwsz);
166	if (rc == 0)
167	{
168	int i;
169	for (i = 0; pwszRand[i] == pwsz[i] && pwsz[i] != 0; i++)
170	;
171	if (pwsz[i] == 0 && i >= 8)
172	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 -> UTF-16 successful.\n");
173	else
174	{
175	RTTestFailed(hTest, "%d: Incorrect conversion of UTF-16 -> fixed length UTF-8 -> UTF-16.\n", __LINE__);
176	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz[i]);
177	}
178	}
179	else
180	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
181	}
182	else
183	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> fixed length UTF-8 -> UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
184
185	/*
186	* And again.
187	*/
188	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
189	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
190	for (int i = 0; i < 30; i++)
191	pwszRand[i] = GetRandUtf16();
192	pwszRand[30] = 0;
193
194	RTUTF16 wszBuf[70];
195	PRTUTF16 pwsz2Buf = wszBuf;
196	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
197	if (rc == 0)
198	{
199	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 70, NULL);
200	if (rc == 0)
201	{
202	int i;
203	for (i = 0; pwszRand[i] == pwsz2Buf[i] && pwsz2Buf[i] != 0; i++)
204	;
205	if (pwszRand[i] == 0 && pwsz2Buf[i] == 0)
206	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 successful.\n");
207	else
208	{
209	RTTestFailed(hTest, "%d: Incorrect conversion of random UTF-16 -> UTF-8 -> fixed length UTF-16.\n", __LINE__);
210	RTTestPrintf(hTest, RTTESTLVL_FAILURE, "First differing character is at position %d and has the value %x.\n", i, pwsz2Buf[i]);
211	}
212	}
213	else
214	RTTestFailed(hTest, "%d: The second part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n", __LINE__, rc);
215	}
216	else
217	RTTestFailed(hTest, "%d: The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
218	__LINE__, rc);
219	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
220	for (int i = 0; i < 30; i++)
221	pwszRand[i] = GetRandUtf16();
222	pwszRand[30] = 0;
223
224	rc = RTUtf16ToUtf8Ex(pwszRand, RTSTR_MAX, &pszUtf8Array, 20, NULL);
225	if (rc == VERR_BUFFER_OVERFLOW)
226	RTTestPassed(hTest, "Random UTF-16 -> fixed length UTF-8 with too short buffer successfully rejected.\n");
227	else
228	RTTestFailed(hTest, "%d: Random UTF-16 -> fixed length UTF-8 with too small buffer returned value %d instead of VERR_BUFFER_OVERFLOW.\n",
229	__LINE__, rc);
230
231	/*
232	* last time...
233	*/
234	RTTestSub(hTest, "Random RTUtf16ToUtf8 + RTStrToUtf16Ex");
235	pwszRand = (PRTUTF16)RTMemAlloc(31 * sizeof(*pwsz));
236	for (int i = 0; i < 30; i++)
237	pwszRand[i] = GetRandUtf16();
238	pwszRand[30] = 0;
239
240	rc = RTUtf16ToUtf8(pwszRand, &pszUtf8);
241	if (rc == VINF_SUCCESS)
242	{
243	rc = RTStrToUtf16Ex(pszUtf8, RTSTR_MAX, &pwsz2Buf, 20, NULL);
244	if (rc == VERR_BUFFER_OVERFLOW)
245	RTTestPassed(hTest, "Random UTF-16 -> UTF-8 -> fixed length UTF-16 with too short buffer successfully rejected.\n");
246	else
247	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",
248	__LINE__, rc);
249	}
250	else
251	RTTestFailed(hTest, "%d:The first part of random UTF-16 -> UTF-8 -> fixed length UTF-16 failed with return value %Rrc.\n",
252	__LINE__, rc);
253
254
255	RTTestSubDone(hTest);
256	}
257
258
259	static RTUNICP g_uszAll[0x110000 - 1 - 0x800 - 2 + 1];
260	static RTUTF16 g_wszAll[0xfffe - (0xe000 - 0xd800) + (0x110000 - 0x10000) * 2];
261	static char g_szAll[0x7f + (0x800 - 0x80) * 2 + (0xfffe - 0x800 - (0xe000 - 0xd800))* 3 + (0x110000 - 0x10000) * 4 + 1];
262
263	static void whereami(int cBits, size_t off)
264	{
265	if (cBits == 8)
266	{
267	if (off < 0x7f)
268	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", off + 1);
269	else if (off < 0xf7f)
270	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x7f) / 2 + 0x80);
271	else if (off < 0x27f7f)
272	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0xf7f) / 3 + 0x800);
273	else if (off < 0x2df79)
274	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x27f7f) / 3 + 0xe000);
275	else if (off < 0x42df79)
276	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 U+%#x\n", (off - 0x2df79) / 4 + 0x10000);
277	else
278	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-8 ???\n");
279	}
280	else if (cBits == 16)
281	{
282	if (off < 0xd7ff*2)
283	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", off / 2 + 1);
284	else if (off < 0xf7fd*2)
285	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xd7ff*2) / 2 + 0xe000);
286	else if (off < 0x20f7fd)
287	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 U+%#x\n", (off - 0xf7fd*2) / 4 + 0x10000);
288	else
289	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "UTF-16 ???\n");
290	}
291	else
292	{
293	if (off < (0xd800 - 1) * sizeof(RTUNICP))
294	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 1);
295	else if (off < (0xfffe - 0x800 - 1) * sizeof(RTUNICP))
296	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1);
297	else
298	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "RTUNICP U+%#x\n", off / sizeof(RTUNICP) + 0x800 + 1 + 2);
299	}
300	}
301
302	int mymemcmp(const void pv1, const void pv2, size_t cb, int cBits)
303	{
304	const uint8_t pb1 = (const uint8_t )pv1;
305	const uint8_t pb2 = (const uint8_t )pv2;
306	for (size_t off = 0; off < cb; off++)
307	{
308	if (pb1[off] != pb2[off])
309	{
310	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, "mismatch at %#x: ", off);
311	whereami(cBits, off);
312	if (off > 0)
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, pb1[off], pb2[off]);
315	for (size_t i = 1; i < 10; i++)
316	if (off + i < cb)
317	RTTestPrintf(NIL_RTTEST, RTTESTLVL_FAILURE, " %#x: %02x != %02x!\n", off+i, pb1[off+i], pb2[off+i]);
318	return 1;
319	}
320	}
321	return 0;
322	}
323
324
325	void InitStrings()
326	{
327	/*
328	* Generate unicode string containing all the legal UTF-16 codepoints, both UTF-16 and UTF-8 version.
329	*/
330	/* the simple code point array first */
331	unsigned i = 0;
332	RTUNICP uc = 1;
333	while (uc < 0xd800)
334	g_uszAll[i++] = uc++;
335	uc = 0xe000;
336	while (uc < 0xfffe)
337	g_uszAll[i++] = uc++;
338	uc = 0x10000;
339	while (uc < 0x110000)
340	g_uszAll[i++] = uc++;
341	g_uszAll[i++] = 0;
342	Assert(RT_ELEMENTS(g_uszAll) == i);
343
344	/* the utf-16 one */
345	i = 0;
346	uc = 1;
347	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
348	while (uc < 0xd800)
349	g_wszAll[i++] = uc++;
350	uc = 0xe000;
351	//RTPrintf(" %#x=%#x", i, uc);
352	while (uc < 0xfffe)
353	g_wszAll[i++] = uc++;
354	uc = 0x10000;
355	//RTPrintf(" %#x=%#x", i, uc);
356	while (uc < 0x110000)
357	{
358	g_wszAll[i++] = 0xd800 \| ((uc - 0x10000) >> 10);
359	g_wszAll[i++] = 0xdc00 \| ((uc - 0x10000) & 0x3ff);
360	uc++;
361	}
362	//RTPrintf(" %#x=%#x\n", i, uc);
363	g_wszAll[i++] = '\0';
364	Assert(RT_ELEMENTS(g_wszAll) == i);
365
366	/*
367	* The utf-8 one
368	*/
369	i = 0;
370	uc = 1;
371	//RTPrintf("tstUtf8: %#x=%#x", i, uc);
372	while (uc < 0x80)
373	g_szAll[i++] = uc++;
374	//RTPrintf(" %#x=%#x", i, uc);
375	while (uc < 0x800)
376	{
377	g_szAll[i++] = 0xc0 \| (uc >> 6);
378	g_szAll[i++] = 0x80 \| (uc & 0x3f);
379	Assert(!((uc >> 6) & ~0x1f));
380	uc++;
381	}
382	//RTPrintf(" %#x=%#x", i, uc);
383	while (uc < 0xd800)
384	{
385	g_szAll[i++] = 0xe0 \| (uc >> 12);
386	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
387	g_szAll[i++] = 0x80 \| (uc & 0x3f);
388	Assert(!((uc >> 12) & ~0xf));
389	uc++;
390	}
391	uc = 0xe000;
392	//RTPrintf(" %#x=%#x", i, uc);
393	while (uc < 0xfffe)
394	{
395	g_szAll[i++] = 0xe0 \| (uc >> 12);
396	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
397	g_szAll[i++] = 0x80 \| (uc & 0x3f);
398	Assert(!((uc >> 12) & ~0xf));
399	uc++;
400	}
401	uc = 0x10000;
402	//RTPrintf(" %#x=%#x", i, uc);
403	while (uc < 0x110000)
404	{
405	g_szAll[i++] = 0xf0 \| (uc >> 18);
406	g_szAll[i++] = 0x80 \| ((uc >> 12) & 0x3f);
407	g_szAll[i++] = 0x80 \| ((uc >> 6) & 0x3f);
408	g_szAll[i++] = 0x80 \| (uc & 0x3f);
409	Assert(!((uc >> 18) & ~0x7));
410	uc++;
411	}
412	//RTPrintf(" %#x=%#x\n", i, uc);
413	g_szAll[i++] = '\0';
414	Assert(RT_ELEMENTS(g_szAll) == i);
415	}
416
417
418	void test2(RTTEST hTest)
419	{
420	/*
421	* Convert to UTF-8 and back.
422	*/
423	RTTestSub(hTest, "UTF-16 -> UTF-8 -> UTF-16");
424	char *pszUtf8;
425	int rc = RTUtf16ToUtf8(&g_wszAll[0], &pszUtf8);
426	if (rc == VINF_SUCCESS)
427	{
428	pszUtf8[0] = 1;
429	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
430	RTTestFailed(hTest, "UTF-16 -> UTF-8 mismatch!");
431
432	PRTUTF16 pwszUtf16;
433	rc = RTStrToUtf16(pszUtf8, &pwszUtf16);
434	if (rc == VINF_SUCCESS)
435	{
436	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
437	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
438	RTUtf16Free(pwszUtf16);
439	}
440	else
441	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
442	RTStrFree(pszUtf8);
443	}
444	else
445	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
446
447
448	/*
449	* Convert to UTF-16 and back. (just in case the above test fails)
450	*/
451	RTTestSub(hTest, "UTF-8 -> UTF-16 -> UTF-8");
452	PRTUTF16 pwszUtf16;
453	rc = RTStrToUtf16(&g_szAll[0], &pwszUtf16);
454	if (rc == VINF_SUCCESS)
455	{
456	if (mymemcmp(pwszUtf16, g_wszAll, sizeof(g_wszAll), 16))
457	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed compare!");
458
459	rc = RTUtf16ToUtf8(pwszUtf16, &pszUtf8);
460	if (rc == VINF_SUCCESS)
461	{
462	if (mymemcmp(pszUtf8, g_szAll, sizeof(g_szAll), 8))
463	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed compare!");
464	RTStrFree(pszUtf8);
465	}
466	else
467	RTTestFailed(hTest, "UTF-16 -> UTF-8 failed, rc=%Rrc.", rc);
468	RTUtf16Free(pwszUtf16);
469	}
470	else
471	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
472
473	/*
474	* Convert UTF-8 to CPs.
475	*/
476	RTTestSub(hTest, "UTF-8 -> UNI -> UTF-8");
477	PRTUNICP paCps;
478	rc = RTStrToUni(g_szAll, &paCps);
479	if (rc == VINF_SUCCESS)
480	{
481	if (mymemcmp(paCps, g_uszAll, sizeof(g_uszAll), 32))
482	RTTestFailed(hTest, "UTF-8 -> UTF-16 failed, rc=%Rrc.", rc);
483
484	size_t cCps;
485	rc = RTStrToUniEx(g_szAll, RTSTR_MAX, &paCps, RT_ELEMENTS(g_uszAll), &cCps);
486	if (rc == VINF_SUCCESS)
487	{
488	if (cCps != RT_ELEMENTS(g_uszAll) - 1)
489	RTTestFailed(hTest, "wrong Code Point count %zu, expected %zu\n", cCps, RT_ELEMENTS(g_uszAll) - 1);
490	}
491	else
492	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
493
494	/** @todo RTCpsToUtf8 or something. */
495	}
496	else
497	RTTestFailed(hTest, "UTF-8 -> Code Points failed, rc=%Rrc.\n", rc);
498
499	/*
500	* Check the various string lengths.
501	*/
502	RTTestSub(hTest, "Lengths");
503	size_t cuc1 = RTStrCalcUtf16Len(g_szAll);
504	size_t cuc2 = RTUtf16Len(g_wszAll);
505	if (cuc1 != cuc2)
506	RTTestFailed(hTest, "cuc1=%zu != cuc2=%zu\n", cuc1, cuc2);
507	//size_t cuc3 = RTUniLen(g_uszAll);
508
509
510	/*
511	* Enumerate the strings.
512	*/
513	RTTestSub(hTest, "Code Point Getters and Putters");
514	char pszPut1Base = (char )RTMemAlloc(sizeof(g_szAll));
515	AssertRelease(pszPut1Base);
516	char *pszPut1 = pszPut1Base;
517	PRTUTF16 pwszPut2Base = (PRTUTF16)RTMemAlloc(sizeof(g_wszAll));
518	AssertRelease(pwszPut2Base);
519	PRTUTF16 pwszPut2 = pwszPut2Base;
520	const char *psz1 = g_szAll;
521	const char *psz2 = g_szAll;
522	PCRTUTF16 pwsz3 = g_wszAll;
523	PCRTUTF16 pwsz4 = g_wszAll;
524	for (;;)
525	{
526	/*
527	* getters
528	*/
529	RTUNICP uc1;
530	rc = RTStrGetCpEx(&psz1, &uc1);
531	if (RT_FAILURE(rc))
532	{
533	RTTestFailed(hTest, "RTStrGetCpEx failed with rc=%Rrc at %.10Rhxs", rc, psz2);
534	whereami(8, psz2 - &g_szAll[0]);
535	break;
536	}
537	char *pszPrev1 = RTStrPrevCp(g_szAll, psz1);
538	if (pszPrev1 != psz2)
539	{
540	RTTestFailed(hTest, "RTStrPrevCp returned %p expected %p!", pszPrev1, psz2);
541	whereami(8, psz2 - &g_szAll[0]);
542	break;
543	}
544	RTUNICP uc2 = RTStrGetCp(psz2);
545	if (uc2 != uc1)
546	{
547	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc2, uc1);
548	whereami(8, psz2 - &g_szAll[0]);
549	break;
550	}
551	psz2 = RTStrNextCp(psz2);
552	if (psz2 != psz1)
553	{
554	RTTestFailed(hTest, "RTStrGetCpEx and RTStrGetNext returned different next pointer!");
555	whereami(8, psz2 - &g_szAll[0]);
556	break;
557	}
558
559	RTUNICP uc3;
560	rc = RTUtf16GetCpEx(&pwsz3, &uc3);
561	if (RT_FAILURE(rc))
562	{
563	RTTestFailed(hTest, "RTUtf16GetCpEx failed with rc=%Rrc at %.10Rhxs", rc, pwsz4);
564	whereami(16, pwsz4 - &g_wszAll[0]);
565	break;
566	}
567	if (uc3 != uc2)
568	{
569	RTTestFailed(hTest, "RTUtf16GetCpEx and RTStrGetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc2);
570	whereami(16, pwsz4 - &g_wszAll[0]);
571	break;
572	}
573	RTUNICP uc4 = RTUtf16GetCp(pwsz4);
574	if (uc3 != uc4)
575	{
576	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetCp returned different CPs: %RTunicp != %RTunicp", uc3, uc4);
577	whereami(16, pwsz4 - &g_wszAll[0]);
578	break;
579	}
580	pwsz4 = RTUtf16NextCp(pwsz4);
581	if (pwsz4 != pwsz3)
582	{
583	RTTestFailed(hTest, "RTUtf16GetCpEx and RTUtf16GetNext returned different next pointer!");
584	whereami(8, pwsz4 - &g_wszAll[0]);
585	break;
586	}
587
588
589	/*
590	* putters
591	*/
592	pszPut1 = RTStrPutCp(pszPut1, uc1);
593	if (pszPut1 - pszPut1Base != psz1 - &g_szAll[0])
594	{
595	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
596	pszPut1 - pszPut1Base, psz1 - &g_szAll[0]);
597	whereami(8, psz2 - &g_szAll[0]);
598	break;
599	}
600
601	pwszPut2 = RTUtf16PutCp(pwszPut2, uc3);
602	if (pwszPut2 - pwszPut2Base != pwsz3 - &g_wszAll[0])
603	{
604	RTTestFailed(hTest, "RTStrPutCp is not at the same offset! %p != %p",
605	pwszPut2 - pwszPut2Base, pwsz3 - &g_wszAll[0]);
606	whereami(8, pwsz4 - &g_wszAll[0]);
607	break;
608	}
609
610
611	/* the end? */
612	if (!uc1)
613	break;
614	}
615
616	/* check output if we seems to have made it thru it all. */
617	if (psz2 == &g_szAll[sizeof(g_szAll)])
618	{
619	if (mymemcmp(pszPut1Base, g_szAll, sizeof(g_szAll), 8))
620	RTTestFailed(hTest, "RTStrPutCp encoded the string incorrectly.");
621	if (mymemcmp(pwszPut2Base, g_wszAll, sizeof(g_wszAll), 16))
622	RTTestFailed(hTest, "RTUtf16PutCp encoded the string incorrectly.");
623	}
624
625	RTMemFree(pszPut1Base);
626	RTMemFree(pwszPut2Base);
627
628	RTTestSubDone(hTest);
629	}
630
631
632	/**
633	* Check case insensitivity.
634	*/
635	void test3(RTTEST hTest)
636	{
637	RTTestSub(hTest, "Case Sensitivity");
638
639	if ( RTUniCpToLower('a') != 'a'
640	\|\| RTUniCpToLower('A') != 'a'
641	\|\| RTUniCpToLower('b') != 'b'
642	\|\| RTUniCpToLower('B') != 'b'
643	\|\| RTUniCpToLower('Z') != 'z'
644	\|\| RTUniCpToLower('z') != 'z'
645	\|\| RTUniCpToUpper('c') != 'C'
646	\|\| RTUniCpToUpper('C') != 'C'
647	\|\| RTUniCpToUpper('z') != 'Z'
648	\|\| RTUniCpToUpper('Z') != 'Z')
649	RTTestFailed(hTest, "RTUniToUpper/Lower failed basic tests.\n");
650
651	if (RTUtf16ICmp(g_wszAll, g_wszAll))
652	RTTestFailed(hTest, "RTUtf16ICmp failed the basic test.\n");
653
654	if (RTUtf16Cmp(g_wszAll, g_wszAll))
655	RTTestFailed(hTest, "RTUtf16Cmp failed the basic test.\n");
656
657	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 };
658	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 };
659	if ( RTUtf16ICmp(s_wszTst1b, s_wszTst1b)
660	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1a)
661	\|\| RTUtf16ICmp(s_wszTst1a, s_wszTst1b)
662	\|\| RTUtf16ICmp(s_wszTst1b, s_wszTst1a)
663	)
664	RTTestFailed(hTest, "RTUtf16ICmp failed the alphabet test.\n");
665
666	if ( RTUtf16Cmp(s_wszTst1b, s_wszTst1b)
667	\|\| RTUtf16Cmp(s_wszTst1a, s_wszTst1a)
668	\|\| !RTUtf16Cmp(s_wszTst1a, s_wszTst1b)
669	\|\| !RTUtf16Cmp(s_wszTst1b, s_wszTst1a)
670	)
671	RTTestFailed(hTest, "RTUtf16Cmp failed the alphabet test.\n");
672
673	RTTestSubDone(hTest);
674	}
675
676
677	/**
678	* Test the RTStr*Cmp functions.
679	*/
680	void TstRTStrXCmp(RTTEST hTest)
681	{
682	#define CHECK_DIFF(expr, op) \
683	do \
684	{ \
685	int iDiff = expr; \
686	if (!(iDiff op 0)) \
687	RTTestFailed(hTest, "%d: %d " #op " 0: %s\n", __LINE__, iDiff, #expr); \
688	} while (0)
689
690	/** @todo test the non-ascii bits. */
691
692	RTTestSub(hTest, "RTStrCmp");
693	CHECK_DIFF(RTStrCmp(NULL, NULL), == );
694	CHECK_DIFF(RTStrCmp(NULL, ""), < );
695	CHECK_DIFF(RTStrCmp("", NULL), > );
696	CHECK_DIFF(RTStrCmp("", ""), == );
697	CHECK_DIFF(RTStrCmp("abcdef", "abcdef"), == );
698	CHECK_DIFF(RTStrCmp("abcdef", "abcde"), > );
699	CHECK_DIFF(RTStrCmp("abcde", "abcdef"), < );
700	CHECK_DIFF(RTStrCmp("abcdeg", "abcdef"), > );
701	CHECK_DIFF(RTStrCmp("abcdef", "abcdeg"), < );
702	CHECK_DIFF(RTStrCmp("abcdeF", "abcdef"), < );
703	CHECK_DIFF(RTStrCmp("abcdef", "abcdeF"), > );
704
705
706	RTTestSub(hTest, "RTStrNCmp");
707	CHECK_DIFF(RTStrNCmp(NULL, NULL, RTSTR_MAX), == );
708	CHECK_DIFF(RTStrNCmp(NULL, "", RTSTR_MAX), < );
709	CHECK_DIFF(RTStrNCmp("", NULL, RTSTR_MAX), > );
710	CHECK_DIFF(RTStrNCmp("", "", RTSTR_MAX), == );
711	CHECK_DIFF(RTStrNCmp("abcdef", "abcdef", RTSTR_MAX), == );
712	CHECK_DIFF(RTStrNCmp("abcdef", "abcde", RTSTR_MAX), > );
713	CHECK_DIFF(RTStrNCmp("abcde", "abcdef", RTSTR_MAX), < );
714	CHECK_DIFF(RTStrNCmp("abcdeg", "abcdef", RTSTR_MAX), > );
715	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeg", RTSTR_MAX), < );
716	CHECK_DIFF(RTStrNCmp("abcdeF", "abcdef", RTSTR_MAX), < );
717	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", RTSTR_MAX), > );
718
719	CHECK_DIFF(RTStrNCmp("abcdef", "fedcba", 0), ==);
720	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 5), ==);
721	CHECK_DIFF(RTStrNCmp("abcdef", "abcdeF", 6), > );
722
723
724	RTTestSub(hTest, "RTStrICmp");
725	CHECK_DIFF(RTStrICmp(NULL, NULL), == );
726	CHECK_DIFF(RTStrICmp(NULL, ""), < );
727	CHECK_DIFF(RTStrICmp("", NULL), > );
728	CHECK_DIFF(RTStrICmp("", ""), == );
729	CHECK_DIFF(RTStrICmp("abcdef", "abcdef"), == );
730	CHECK_DIFF(RTStrICmp("abcdef", "abcde"), > );
731	CHECK_DIFF(RTStrICmp("abcde", "abcdef"), < );
732	CHECK_DIFF(RTStrICmp("abcdeg", "abcdef"), > );
733	CHECK_DIFF(RTStrICmp("abcdef", "abcdeg"), < );
734
735	CHECK_DIFF(RTStrICmp("abcdeF", "abcdef"), ==);
736	CHECK_DIFF(RTStrICmp("abcdef", "abcdeF"), ==);
737	CHECK_DIFF(RTStrICmp("ABCDEF", "abcdef"), ==);
738	CHECK_DIFF(RTStrICmp("abcdef", "ABCDEF"), ==);
739	CHECK_DIFF(RTStrICmp("AbCdEf", "aBcDeF"), ==);
740	CHECK_DIFF(RTStrICmp("AbCdEg", "aBcDeF"), > );
741	CHECK_DIFF(RTStrICmp("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
742
743
744	RTTestSub(hTest, "RTStrICmpAscii");
745	CHECK_DIFF(RTStrICmpAscii(NULL, NULL), == );
746	CHECK_DIFF(RTStrICmpAscii(NULL, ""), < );
747	CHECK_DIFF(RTStrICmpAscii("", NULL), > );
748	CHECK_DIFF(RTStrICmpAscii("", ""), == );
749	CHECK_DIFF(RTStrICmpAscii("abcdef", "abcdef"), == );
750	CHECK_DIFF(RTStrICmpAscii("abcdef", "abcde"), > );
751	CHECK_DIFF(RTStrICmpAscii("abcde", "abcdef"), < );
752	CHECK_DIFF(RTStrICmpAscii("abcdeg", "abcdef"), > );
753	CHECK_DIFF(RTStrICmpAscii("abcdef", "abcdeg"), < );
754
755	CHECK_DIFF(RTStrICmpAscii("abcdeF", "abcdef"), ==);
756	CHECK_DIFF(RTStrICmpAscii("abcdef", "abcdeF"), ==);
757	CHECK_DIFF(RTStrICmpAscii("ABCDEF", "abcdef"), ==);
758	CHECK_DIFF(RTStrICmpAscii("abcdef", "ABCDEF"), ==);
759	CHECK_DIFF(RTStrICmpAscii("AbCdEf", "aBcDeF"), ==);
760	CHECK_DIFF(RTStrICmpAscii("AbCdEg", "aBcDeF"), > );
761	CHECK_DIFF(RTStrICmpAscii("AbCdEG", "aBcDef"), > ); /* diff performed on the lower case cp. */
762
763
764	RTTestSub(hTest, "RTStrNICmp");
765	CHECK_DIFF(RTStrNICmp(NULL, NULL, RTSTR_MAX), == );
766	CHECK_DIFF(RTStrNICmp(NULL, "", RTSTR_MAX), < );
767	CHECK_DIFF(RTStrNICmp("", NULL, RTSTR_MAX), > );
768	CHECK_DIFF(RTStrNICmp("", "", RTSTR_MAX), == );
769	CHECK_DIFF(RTStrNICmp(NULL, NULL, 0), == );
770	CHECK_DIFF(RTStrNICmp(NULL, "", 0), == );
771	CHECK_DIFF(RTStrNICmp("", NULL, 0), == );
772	CHECK_DIFF(RTStrNICmp("", "", 0), == );
773	CHECK_DIFF(RTStrNICmp("abcdef", "abcdef", RTSTR_MAX), == );
774	CHECK_DIFF(RTStrNICmp("abcdef", "abcde", RTSTR_MAX), > );
775	CHECK_DIFF(RTStrNICmp("abcde", "abcdef", RTSTR_MAX), < );
776	CHECK_DIFF(RTStrNICmp("abcdeg", "abcdef", RTSTR_MAX), > );
777	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeg", RTSTR_MAX), < );
778
779	CHECK_DIFF(RTStrNICmp("abcdeF", "abcdef", RTSTR_MAX), ==);
780	CHECK_DIFF(RTStrNICmp("abcdef", "abcdeF", RTSTR_MAX), ==);
781	CHECK_DIFF(RTStrNICmp("ABCDEF", "abcdef", RTSTR_MAX), ==);
782	CHECK_DIFF(RTStrNICmp("abcdef", "ABCDEF", RTSTR_MAX), ==);
783	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", RTSTR_MAX), ==);
784	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", RTSTR_MAX), > );
785	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", RTSTR_MAX), > ); /* diff performed on the lower case cp. */
786
787	CHECK_DIFF(RTStrNICmp("ABCDEF", "fedcba", 0), ==);
788	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 5), ==);
789	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDeF", 5), ==);
790	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDe", 5), ==);
791	CHECK_DIFF(RTStrNICmp("AbCdE", "aBcDeF", 5), ==);
792	CHECK_DIFF(RTStrNICmp("AbCdEf", "aBcDe", 5), ==);
793	CHECK_DIFF(RTStrNICmp("AbCdEg", "aBcDeF", 6), > );
794	CHECK_DIFF(RTStrNICmp("AbCdEG", "aBcDef", 6), > ); /* diff performed on the lower case cp. */
795	/* We should continue using byte comparison when we hit the invalid CP. Will assert in debug builds. */
796	// CHECK_DIFF(RTStrNICmp("AbCd\xff""eg", "aBcD\xff""eF", 6), ==);
797
798	RTTestSubDone(hTest);
799	}
800
801
802
803	/**
804	* Check UTF-8 encoding purging.
805	*/
806	void TstRTStrPurgeEncoding(RTTEST hTest)
807	{
808	RTTestSub(hTest, "RTStrPurgeEncoding");
809
810	/*
811	* Test some good strings.
812	*/
813	char sz1[] = "1234567890wertyuiopsdfghjklzxcvbnm";
814	char sz1Copy[sizeof(sz1)];
815	memcpy(sz1Copy, sz1, sizeof(sz1));
816
817	RTTESTI_CHECK_RETV(RTStrPurgeEncoding(sz1) == 0);
818	RTTESTI_CHECK_RETV(!memcmp(sz1, sz1Copy, sizeof(sz1)));
819
820	char *pszAll = RTStrDup(g_szAll);
821	if (pszAll)
822	{
823	RTTESTI_CHECK(RTStrPurgeEncoding(pszAll) == 0);
824	RTTESTI_CHECK(!memcmp(pszAll, g_szAll, sizeof(g_szAll)));
825	RTStrFree(pszAll);
826	}
827
828	/*
829	* Test some bad stuff.
830	*/
831	struct
832	{
833	size_t cErrors;
834	unsigned char szIn[5];
835	const char *pszExpect;
836	} aTests[] =
837	{
838	{ 0, { '1', '2', '3', '4', '\0' }, "1234" },
839	{ 1, { 0x80, '2', '3', '4', '\0' }, "?234" },
840	{ 1, { '1', 0x80, '3', '4', '\0' }, "1?34" },
841	{ 1, { '1', '2', 0x80, '4', '\0' }, "12?4" },
842	{ 1, { '1', '2', '3', 0x80, '\0' }, "123?" },
843	{ 2, { 0x80, 0x81, '3', '4', '\0' }, "??34" },
844	{ 2, { '1', 0x80, 0x81, '4', '\0' }, "1??4" },
845	{ 2, { '1', '2', 0x80, 0x81, '\0' }, "12??" },
846	};
847	for (size_t i = 0; i < RT_ELEMENTS(aTests); i++)
848	{
849	size_t cErrors = RTStrPurgeEncoding((char *)aTests[i].szIn);
850	if (cErrors != aTests[i].cErrors)
851	RTTestFailed(hTest, "#%u: cErrors=%u expected %u\n", i, cErrors, aTests[i].cErrors);
852	else if (strcmp((char *)aTests[i].szIn, aTests[i].pszExpect))
853	RTTestFailed(hTest, "#%u: %.5Rhxs expected %.5Rhxs (%s)\n", i, aTests[i].szIn, aTests[i].pszExpect, aTests[i].pszExpect);
854	}
855
856	RTTestSubDone(hTest);
857	}
858
859
860	/**
861	* Check string sanitising.
862	*/
863	void TstRTStrPurgeComplementSet(RTTEST hTest)
864	{
865	RTTestSub(hTest, "RTStrPurgeComplementSet");
866	RTUNICP aCpSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
867	'\0' };
868	RTUNICP aCpBadSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
869	'7', '\0' }; /* Contains an incomplete pair. */
870	struct
871	{
872	const char *pcszIn;
873	const char *pcszOut;
874	PCRTUNICP pcCpSet;
875	char chReplacement;
876	ssize_t cExpected;
877	}
878	aTests[] =
879	{
880	{ "1234werttrew4321", "1234werttrew4321", aCpSet, '_', 0 },
881	{ "123654wert\xc2\xa2trew\xe2\x82\xac""4321",
882	"123_54wert__trew___4321", aCpSet, '_', 3 },
883	{ "hjhj8766", "????????", aCpSet, '?', 8 },
884	{ "123\xf0\xa4\xad\xa2""4", "123____4", aCpSet, '_', 1 },
885	{ "\xff", "\xff", aCpSet, '_', -1 },
886	{ "____", "____", aCpBadSet, '_', -1 }
887	};
888	enum { MAX_IN_STRING = 256 };
889
890	for (unsigned i = 0; i < RT_ELEMENTS(aTests); ++i)
891	{
892	char szCopy[MAX_IN_STRING];
893	ssize_t cReplacements;
894	AssertRC(RTStrCopy(szCopy, RT_ELEMENTS(szCopy), aTests[i].pcszIn));
895	RTTestDisableAssertions(hTest);
896	cReplacements = RTStrPurgeComplementSet(szCopy, aTests[i].pcCpSet, aTests[i].chReplacement);
897	RTTestRestoreAssertions(hTest);
898	if (cReplacements != aTests[i].cExpected)
899	RTTestFailed(hTest, "#%u: expected %lld, actual %lld\n", i,
900	(long long) aTests[i].cExpected,
901	(long long) cReplacements);
902	if (strcmp(aTests[i].pcszOut, szCopy))
903	RTTestFailed(hTest, "#%u: expected %s, actual %s\n", i,
904	aTests[i].pcszOut, szCopy);
905	}
906	}
907
908
909	/**
910	* Check string sanitising.
911	*/
912	void TstRTUtf16PurgeComplementSet(RTTEST hTest)
913	{
914	RTTestSub(hTest, "RTUtf16PurgeComplementSet");
915	RTUNICP aCpSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
916	'\0' };
917	RTUNICP aCpBadSet[] = { '1', '5', 'w', 'w', 'r', 'r', 'e', 'f', 't', 't',
918	'7', '\0' }; /* Contains an incomplete pair. */
919	struct
920	{
921	const char *pcszIn;
922	const char *pcszOut;
923	size_t cwc; /* Zero means the strings are Utf-8. */
924	PCRTUNICP pcCpSet;
925	char chReplacement;
926	ssize_t cExpected;
927	}
928	aTests[] =
929	{
930	{ "1234werttrew4321", "1234werttrew4321", 0, aCpSet, '_', 0 },
931	{ "123654wert\xc2\xa2trew\xe2\x82\xac""4321",
932	"123_54wert_trew_4321", 0, aCpSet, '_', 3 },
933	{ "hjhj8766", "????????", 0, aCpSet, '?', 8 },
934	{ "123\xf0\xa4\xad\xa2""4", "123__4", 0, aCpSet, '_', 1 },
935	{ "\xff\xff\0", "\xff\xff\0", 2, aCpSet, '_', -1 },
936	{ "\xff\xff\0", "\xff\xff\0", 2, aCpSet, '_', -1 },
937	{ "____", "____", 0, aCpBadSet, '_', -1 }
938	};
939	enum { MAX_IN_STRING = 256 };
940
941	for (unsigned i = 0; i < RT_ELEMENTS(aTests); ++i)
942	{
943	RTUTF16 wszInCopy[MAX_IN_STRING], *pwszInCopy = wszInCopy;
944	RTUTF16 wszOutCopy[MAX_IN_STRING], *pwszOutCopy = wszOutCopy;
945	ssize_t cReplacements;
946	if (!aTests[i].cwc)
947	{
948	AssertRC(RTStrToUtf16Ex(aTests[i].pcszIn, RTSTR_MAX, &pwszInCopy,
949	RT_ELEMENTS(wszInCopy), NULL));
950	AssertRC(RTStrToUtf16Ex(aTests[i].pcszOut, RTSTR_MAX, &pwszOutCopy,
951	RT_ELEMENTS(wszOutCopy), NULL));
952	}
953	else
954	{
955	Assert(aTests[i].cwc <= RT_ELEMENTS(wszInCopy));
956	memcpy(wszInCopy, aTests[i].pcszIn, aTests[i].cwc * 2);
957	memcpy(wszOutCopy, aTests[i].pcszOut, aTests[i].cwc * 2);
958	}
959
960	RTTestDisableAssertions(hTest);
961	cReplacements = RTUtf16PurgeComplementSet(wszInCopy, aTests[i].pcCpSet, aTests[i].chReplacement);
962	RTTestRestoreAssertions(hTest);
963
964	if (cReplacements != aTests[i].cExpected)
965	RTTestFailed(hTest, "#%u: expected %lld, actual %lld\n", i,
966	(long long) aTests[i].cExpected,
967	(long long) cReplacements);
968	if (RTUtf16Cmp(wszInCopy, wszOutCopy))
969	RTTestFailed(hTest, "#%u: expected %ls, actual %ls\n", i,
970	wszOutCopy, wszInCopy);
971	}
972	}
973
974
975	/**
976	* Benchmark stuff.
977	*/
978	void Benchmarks(RTTEST hTest)
979	{
980	static union
981	{
982	RTUTF16 wszBuf[sizeof(g_wszAll)];
983	char szBuf[sizeof(g_szAll)];
984	} s_Buf;
985
986	RTTestSub(hTest, "Benchmarks");
987	/** @todo add RTTest* methods for reporting benchmark results. */
988	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTStrToUtf16Ex: "); /** @todo figure this stuff into the test framework. */
989	PRTUTF16 pwsz = &s_Buf.wszBuf[0];
990	int rc = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), 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 = RTStrToUtf16Ex(&g_szAll[0], RTSTR_MAX, &pwsz, RT_ELEMENTS(s_Buf.wszBuf), NULL);
998	if (RT_FAILURE(rc))
999	{
1000	RTTestFailed(hTest, "UTF-8 -> UTF-16 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	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "Benchmarking RTUtf16ToUtf8Ex: ");
1009	char *psz = &s_Buf.szBuf[0];
1010	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
1011	if (RT_SUCCESS(rc))
1012	{
1013	int i;
1014	uint64_t u64Start = RTTimeNanoTS();
1015	for (i = 0; i < 100; i++)
1016	{
1017	rc = RTUtf16ToUtf8Ex(&g_wszAll[0], RTSTR_MAX, &psz, RT_ELEMENTS(s_Buf.szBuf), NULL);
1018	if (RT_FAILURE(rc))
1019	{
1020	RTTestFailed(hTest, "UTF-16 -> UTF-8 benchmark failed at i=%d, rc=%Rrc\n", i, rc);
1021	break;
1022	}
1023	}
1024	uint64_t u64Elapsed = RTTimeNanoTS() - u64Start;
1025	RTTestPrintf(hTest, RTTESTLVL_ALWAYS, "%d in %'RI64 ns\n", i, u64Elapsed);
1026	}
1027
1028	RTTestSubDone(hTest);
1029	}
1030
1031
1032	/**
1033	* Tests RTStrEnd
1034	*/
1035	static void testStrEnd(RTTEST hTest)
1036	{
1037	RTTestSub(hTest, "RTStrEnd");
1038
1039	static char const s_szEmpty[1] = "";
1040	RTTESTI_CHECK(RTStrEnd(s_szEmpty, 0) == NULL);
1041	RTTESTI_CHECK(RTStrEnd(s_szEmpty, 1) == &s_szEmpty[0]);
1042	for (size_t i = 0; i < _1M; i++)
1043	RTTESTI_CHECK(RTStrEnd(s_szEmpty, ~i) == &s_szEmpty[0]);
1044
1045	}
1046
1047
1048	/**
1049	* Tests RTStrStr and RTStrIStr.
1050	*/
1051	static void testStrStr(RTTEST hTest)
1052	{
1053	#define CHECK_NULL(expr) \
1054	do { \
1055	const char *pszRet = expr; \
1056	if (pszRet != NULL) \
1057	RTTestFailed(hTest, "%d: %#x -> %s expected NULL", __LINE__, #expr, pszRet); \
1058	} while (0)
1059
1060	#define CHECK(expr, expect) \
1061	do { \
1062	const char *pszRet = expr; \
1063	const char *pszExpect = (expect); \
1064	if ( (pszRet != NULL && pszExpect == NULL) \
1065	\|\| (pszRet == NULL && pszExpect != NULL) \
1066	\|\| strcmp(pszRet, pszExpect) \
1067	) \
1068	RTTestFailed(hTest, "%d: %#x -> %s expected %s", __LINE__, #expr, pszRet, pszExpect); \
1069	} while (0)
1070
1071
1072	RTTestSub(hTest, "RTStrStr");
1073	CHECK(RTStrStr("abcdef", ""), "abcdef");
1074	CHECK_NULL(RTStrStr("abcdef", NULL));
1075	CHECK_NULL(RTStrStr(NULL, ""));
1076	CHECK_NULL(RTStrStr(NULL, NULL));
1077	CHECK(RTStrStr("abcdef", "abcdef"), "abcdef");
1078	CHECK(RTStrStr("abcdef", "b"), "bcdef");
1079	CHECK(RTStrStr("abcdef", "bcdef"), "bcdef");
1080	CHECK(RTStrStr("abcdef", "cdef"), "cdef");
1081	CHECK(RTStrStr("abcdef", "cde"), "cdef");
1082	CHECK(RTStrStr("abcdef", "cd"), "cdef");
1083	CHECK(RTStrStr("abcdef", "c"), "cdef");
1084	CHECK(RTStrStr("abcdef", "f"), "f");
1085	CHECK(RTStrStr("abcdef", "ef"), "ef");
1086	CHECK(RTStrStr("abcdef", "e"), "ef");
1087	CHECK_NULL(RTStrStr("abcdef", "z"));
1088	CHECK_NULL(RTStrStr("abcdef", "A"));
1089	CHECK_NULL(RTStrStr("abcdef", "F"));
1090
1091	RTTestSub(hTest, "RTStrIStr");
1092	CHECK(RTStrIStr("abcdef", ""), "abcdef");
1093	CHECK_NULL(RTStrIStr("abcdef", NULL));
1094	CHECK_NULL(RTStrIStr(NULL, ""));
1095	CHECK_NULL(RTStrIStr(NULL, NULL));
1096	CHECK(RTStrIStr("abcdef", "abcdef"), "abcdef");
1097	CHECK(RTStrIStr("abcdef", "Abcdef"), "abcdef");
1098	CHECK(RTStrIStr("abcdef", "ABcDeF"), "abcdef");
1099	CHECK(RTStrIStr("abcdef", "b"), "bcdef");
1100	CHECK(RTStrIStr("abcdef", "B"), "bcdef");
1101	CHECK(RTStrIStr("abcdef", "bcdef"), "bcdef");
1102	CHECK(RTStrIStr("abcdef", "BCdEf"), "bcdef");
1103	CHECK(RTStrIStr("abcdef", "bCdEf"), "bcdef");
1104	CHECK(RTStrIStr("abcdef", "bcdEf"), "bcdef");
1105	CHECK(RTStrIStr("abcdef", "BcdEf"), "bcdef");
1106	CHECK(RTStrIStr("abcdef", "cdef"), "cdef");
1107	CHECK(RTStrIStr("abcdef", "cde"), "cdef");
1108	CHECK(RTStrIStr("abcdef", "cd"), "cdef");
1109	CHECK(RTStrIStr("abcdef", "c"), "cdef");
1110	CHECK(RTStrIStr("abcdef", "f"), "f");
1111	CHECK(RTStrIStr("abcdeF", "F"), "F");
1112	CHECK(RTStrIStr("abcdef", "F"), "f");
1113	CHECK(RTStrIStr("abcdef", "ef"), "ef");
1114	CHECK(RTStrIStr("EeEef", "e"), "EeEef");
1115	CHECK(RTStrIStr("EeEef", "E"), "EeEef");
1116	CHECK(RTStrIStr("EeEef", "EE"), "EeEef");
1117	CHECK(RTStrIStr("EeEef", "EEE"), "EeEef");
1118	CHECK(RTStrIStr("EeEef", "EEEF"), "eEef");
1119	CHECK_NULL(RTStrIStr("EeEef", "z"));
1120
1121	#undef CHECK
1122	#undef CHECK_NULL
1123	RTTestSubDone(hTest);
1124	}
1125
1126
1127	void testUtf8Latin1(RTTEST hTest)
1128	{
1129	RTTestSub(hTest, "Latin-1 <-> Utf-8 conversion functions");
1130
1131	/* Test Utf8 -> Latin1 */
1132	size_t cch_szAll = 0;
1133	size_t cbShort = RTStrCalcLatin1Len(g_szAll);
1134	RTTEST_CHECK(hTest, cbShort == 0);
1135	int rc = RTStrCalcLatin1LenEx(g_szAll, 383, &cch_szAll);
1136	RTTEST_CHECK(hTest, (cch_szAll == 255));
1137	rc = RTStrCalcLatin1LenEx(g_szAll, RTSTR_MAX, &cch_szAll);
1138	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1139	char *psz = NULL;
1140	char szShort[256] = { 0 };
1141	memcpy(szShort, g_szAll, 255);
1142	cbShort = RTStrCalcLatin1Len(szShort);
1143	RTTEST_CHECK(hTest, cbShort == 191);
1144	rc = RTStrToLatin1(szShort, &psz);
1145	RTTEST_CHECK_RC_OK(hTest, rc);
1146	if (RT_SUCCESS(rc))
1147	{
1148	RTTEST_CHECK(hTest, (strlen(psz) == 191));
1149	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1150	if (psz[i] != (char) j)
1151	{
1152	RTTestFailed(hTest, "conversion of g_szAll to Latin1 failed at position %u\n", i);
1153	break;
1154	}
1155	}
1156	RTStrFree(psz);
1157	rc = RTStrToLatin1(g_szAll, &psz);
1158	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1159	char sz[512];
1160	char *psz2 = &sz[0];
1161	size_t cchActual = 0;
1162	rc = RTStrToLatin1Ex(g_szAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1163	&cchActual);
1164	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1165	RTTEST_CHECK_MSG(hTest, cchActual == 0,
1166	(hTest, "cchActual=%lu\n", cchActual));
1167	rc = RTStrToLatin1Ex(g_szAll, 383, &psz2, sizeof(sz),
1168	&cchActual);
1169	RTTEST_CHECK_RC_OK(hTest, rc);
1170	if (RT_SUCCESS(rc))
1171	{
1172	RTTEST_CHECK(hTest, (cchActual == 255));
1173	RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1174	for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1175	if (psz2[i] != (char) j)
1176	{
1177	RTTestFailed(hTest, "second conversion of g_szAll to Latin1 failed at position %u\n", i);
1178	break;
1179	}
1180	}
1181	rc = RTStrToLatin1Ex(g_szAll, 129, &psz2, 128, &cchActual);
1182	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1183	RTTEST_CHECK_MSG(hTest, cchActual == 128,
1184	(hTest, "cchActual=%lu\n", cchActual));
1185	rc = RTStrToLatin1Ex(g_szAll, 383, &psz, 0, &cchActual);
1186	RTTEST_CHECK_RC_OK(hTest, rc);
1187	if (RT_SUCCESS(rc))
1188	{
1189	RTTEST_CHECK(hTest, (cchActual == 255));
1190	RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1191	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1192	if ( ((j < 0x100) && (psz[i] != (char) j))
1193	\|\| ((j > 0xff) && psz[i] != '?'))
1194	{
1195	RTTestFailed(hTest, "third conversion of g_szAll to Latin1 failed at position %u\n", i);
1196	break;
1197	}
1198	}
1199	const char *pszBad = "Hello\xDC\xD8";
1200	rc = RTStrToLatin1Ex(pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1201	&cchActual);
1202	RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF8_ENCODING);
1203	RTStrFree(psz);
1204
1205	/* Test Latin1 -> Utf8 */
1206	const char *pszLat1 = "\x01\x20\x40\x80\x81";
1207	RTTEST_CHECK(hTest, RTLatin1CalcUtf8Len(pszLat1) == 7);
1208	rc = RTLatin1CalcUtf8LenEx(pszLat1, 3, &cchActual);
1209	RTTEST_CHECK_RC_OK(hTest, rc);
1210	if (RT_SUCCESS(rc))
1211	RTTEST_CHECK(hTest, cchActual == 3);
1212	rc = RTLatin1CalcUtf8LenEx(pszLat1, RTSTR_MAX, &cchActual);
1213	RTTEST_CHECK_RC_OK(hTest, rc);
1214	if (RT_SUCCESS(rc))
1215	RTTEST_CHECK(hTest, cchActual == 7);
1216	char *pch = NULL;
1217	char ch[8];
1218	char *pch2 = &ch[0];
1219	cchActual = 0;
1220	rc = RTLatin1ToUtf8(pszLat1, &pch);
1221	RTTEST_CHECK_RC_OK(hTest, rc);
1222	if (RT_SUCCESS(rc))
1223	RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1224	RTStrFree(pch);
1225	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch, 0, &cchActual);
1226	RTTEST_CHECK_RC_OK(hTest, rc);
1227	if (RT_SUCCESS(rc))
1228	{
1229	RTTEST_CHECK(hTest, (cchActual == 7));
1230	RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1231	}
1232	RTStrFree(pch);
1233	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch, 0, NULL);
1234	RTTEST_CHECK_RC_OK(hTest, rc);
1235	if (RT_SUCCESS(rc))
1236	RTTEST_CHECK(hTest, !strcmp(pch, "\x01\x20\x40\xC2\x80\xC2\x81"));
1237	RTStrFree(pch);
1238	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch2, RT_ELEMENTS(ch),
1239	&cchActual);
1240	RTTEST_CHECK_RC_OK(hTest, rc);
1241	if (RT_SUCCESS(rc))
1242	{
1243	RTTEST_CHECK(hTest, (cchActual == 7));
1244	RTTEST_CHECK(hTest, !strcmp(pch2, "\x01\x20\x40\xC2\x80\xC2\x81"));
1245	}
1246	rc = RTLatin1ToUtf8Ex(pszLat1, 3, &pch2, RT_ELEMENTS(ch),
1247	&cchActual);
1248	RTTEST_CHECK_RC_OK(hTest, rc);
1249	if (RT_SUCCESS(rc))
1250	{
1251	RTTEST_CHECK(hTest, (cchActual == 3));
1252	RTTEST_CHECK(hTest, !strcmp(pch2, "\x01\x20\x40"));
1253	}
1254	rc = RTLatin1ToUtf8Ex(pszLat1, RTSTR_MAX, &pch2, RT_ELEMENTS(ch) - 1,
1255	&cchActual);
1256	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1257	RTTEST_CHECK(hTest, (cchActual == 7));
1258	RTTestSubDone(hTest);
1259	}
1260
1261
1262	void testUtf16Latin1(RTTEST hTest)
1263	{
1264	RTTestSub(hTest, "Latin-1 <-> Utf-16 conversion functions");
1265
1266	/* Test Utf16 -> Latin1 */
1267	size_t cch_szAll = 0;
1268	size_t cbShort = RTUtf16CalcLatin1Len(g_wszAll);
1269	RTTEST_CHECK(hTest, cbShort == 0);
1270	int rc = RTUtf16CalcLatin1LenEx(g_wszAll, 255, &cch_szAll);
1271	RTTEST_CHECK(hTest, (cch_szAll == 255));
1272	rc = RTUtf16CalcLatin1LenEx(g_wszAll, RTSTR_MAX, &cch_szAll);
1273	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1274	char *psz = NULL;
1275	RTUTF16 wszShort[256] = { 0 };
1276	for (unsigned i = 0; i < 255; ++i)
1277	wszShort[i] = i + 1;
1278	cbShort = RTUtf16CalcLatin1Len(wszShort);
1279	RTTEST_CHECK(hTest, cbShort == 255);
1280	rc = RTUtf16ToLatin1(wszShort, &psz);
1281	RTTEST_CHECK_RC_OK(hTest, rc);
1282	if (RT_SUCCESS(rc))
1283	{
1284	RTTEST_CHECK(hTest, (strlen(psz) == 255));
1285	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1286	if (psz[i] != (char) j)
1287	{
1288	RTTestFailed(hTest, "conversion of g_wszAll to Latin1 failed at position %u\n", i);
1289	break;
1290	}
1291	}
1292	RTStrFree(psz);
1293	rc = RTUtf16ToLatin1(g_wszAll, &psz);
1294	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1295	char sz[512];
1296	char *psz2 = &sz[0];
1297	size_t cchActual = 0;
1298	rc = RTUtf16ToLatin1Ex(g_wszAll, sizeof(sz) - 1, &psz2, sizeof(sz),
1299	&cchActual);
1300	RTTEST_CHECK_RC(hTest, rc, VERR_NO_TRANSLATION);
1301	RTTEST_CHECK_MSG(hTest, cchActual == 0,
1302	(hTest, "cchActual=%lu\n", cchActual));
1303	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz2, sizeof(sz),
1304	&cchActual);
1305	RTTEST_CHECK_RC_OK(hTest, rc);
1306	if (RT_SUCCESS(rc))
1307	{
1308	RTTEST_CHECK(hTest, (cchActual == 255));
1309	RTTEST_CHECK(hTest, (cchActual == strlen(sz)));
1310	for (unsigned i = 0, j = 1; psz2[i] != '\0'; ++i, ++j)
1311	if (psz2[i] != (char) j)
1312	{
1313	RTTestFailed(hTest, "second conversion of g_wszAll to Latin1 failed at position %u\n", i);
1314	break;
1315	}
1316	}
1317	rc = RTUtf16ToLatin1Ex(g_wszAll, 128, &psz2, 128, &cchActual);
1318	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1319	RTTEST_CHECK_MSG(hTest, cchActual == 128,
1320	(hTest, "cchActual=%lu\n", cchActual));
1321	rc = RTUtf16ToLatin1Ex(g_wszAll, 255, &psz, 0, &cchActual);
1322	RTTEST_CHECK_RC_OK(hTest, rc);
1323	if (RT_SUCCESS(rc))
1324	{
1325	RTTEST_CHECK(hTest, (cchActual == 255));
1326	RTTEST_CHECK(hTest, (cchActual == strlen(psz)));
1327	for (unsigned i = 0, j = 1; psz[i] != '\0'; ++i, ++j)
1328	if ( ((j < 0x100) && (psz[i] != (char) j))
1329	\|\| ((j > 0xff) && psz[i] != '?'))
1330	{
1331	RTTestFailed(hTest, "third conversion of g_wszAll to Latin1 failed at position %u\n", i);
1332	break;
1333	}
1334	}
1335	const char *pszBad = "H\0e\0l\0l\0o\0\0\xDC\0\xD8\0";
1336	rc = RTUtf16ToLatin1Ex((RTUTF16 *) pszBad, RTSTR_MAX, &psz2, sizeof(sz),
1337	&cchActual);
1338	RTTEST_CHECK_RC(hTest, rc, VERR_INVALID_UTF16_ENCODING);
1339	RTStrFree(psz);
1340
1341	/* Test Latin1 -> Utf16 */
1342	const char *pszLat1 = "\x01\x20\x40\x80\x81";
1343	RTTEST_CHECK(hTest, RTLatin1CalcUtf16Len(pszLat1) == 5);
1344	rc = RTLatin1CalcUtf16LenEx(pszLat1, 3, &cchActual);
1345	RTTEST_CHECK_RC_OK(hTest, rc);
1346	if (RT_SUCCESS(rc))
1347	RTTEST_CHECK(hTest, cchActual == 3);
1348	rc = RTLatin1CalcUtf16LenEx(pszLat1, RTSTR_MAX, &cchActual);
1349	RTTEST_CHECK_RC_OK(hTest, rc);
1350	if (RT_SUCCESS(rc))
1351	RTTEST_CHECK(hTest, cchActual == 5);
1352	RTUTF16 *pwc = NULL;
1353	RTUTF16 wc[6];
1354	RTUTF16 *pwc2 = &wc[0];
1355	size_t cwActual = 0;
1356	rc = RTLatin1ToUtf16(pszLat1, &pwc);
1357	RTTEST_CHECK_RC_OK(hTest, rc);
1358	if (RT_SUCCESS(rc))
1359	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1360	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1361	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1362	RTUtf16Free(pwc);
1363	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, &cwActual);
1364	RTTEST_CHECK_RC_OK(hTest, rc);
1365	if (RT_SUCCESS(rc))
1366	{
1367	RTTEST_CHECK(hTest, (cwActual == 5));
1368	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1369	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1370	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1371	}
1372	RTUtf16Free(pwc);
1373	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc, 0, NULL);
1374	RTTEST_CHECK_RC_OK(hTest, rc);
1375	if (RT_SUCCESS(rc))
1376	RTTEST_CHECK(hTest, (pwc[0] == 1) && (pwc[1] == 0x20)
1377	&& (pwc[2] == 0x40) && (pwc[3] == 0x80)
1378	&& (pwc[4] == 0x81) && (pwc[5] == '\0'));
1379	RTUtf16Free(pwc);
1380	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc),
1381	&cwActual);
1382	RTTEST_CHECK_RC_OK(hTest, rc);
1383	if (RT_SUCCESS(rc))
1384	{
1385	RTTEST_CHECK(hTest, (cwActual == 5));
1386	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1387	&& (wc[2] == 0x40) && (wc[3] == 0x80)
1388	&& (wc[4] == 0x81) && (wc[5] == '\0'));
1389	}
1390	rc = RTLatin1ToUtf16Ex(pszLat1, 3, &pwc2, RT_ELEMENTS(wc),
1391	&cwActual);
1392	RTTEST_CHECK_RC_OK(hTest, rc);
1393	if (RT_SUCCESS(rc))
1394	{
1395	RTTEST_CHECK(hTest, (cwActual == 3));
1396	RTTEST_CHECK(hTest, (wc[0] == 1) && (wc[1] == 0x20)
1397	&& (wc[2] == 0x40) && (wc[3] == '\0'));
1398	}
1399	rc = RTLatin1ToUtf16Ex(pszLat1, RTSTR_MAX, &pwc2, RT_ELEMENTS(wc) - 1,
1400	&cwActual);
1401	RTTEST_CHECK_RC(hTest, rc, VERR_BUFFER_OVERFLOW);
1402	RTTEST_CHECK(hTest, (cwActual == 5));
1403	RTTestSubDone(hTest);
1404	}
1405
1406
1407	static void testNoTransation(RTTEST hTest)
1408	{
1409	/*
1410	* Try trigger a VERR_NO_TRANSLATION error in convert to
1411	* current CP to latin-1.
1412	*/
1413	const RTUTF16 s_swzTest1[] = { 0x2358, 0x2242, 0x2357, 0x2359, 0x22f9, 0x2c4e, 0x0030, 0x0060,
1414	0x0092, 0x00c1, 0x00f2, 0x1f80, 0x0088, 0x2c38, 0x2c30, 0x0000 };
1415	char *pszTest1;
1416	int rc = RTUtf16ToUtf8(s_swzTest1, &pszTest1);
1417	RTTESTI_CHECK_RC_RETV(rc, VINF_SUCCESS);
1418
1419	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTStrUtf8ToCurrentCP");
1420	char *pszOut;
1421	rc = RTStrUtf8ToCurrentCP(&pszOut, pszTest1);
1422	if (rc == VINF_SUCCESS)
1423	{
1424	RTTESTI_CHECK(!strcmp(pszOut, pszTest1));
1425	RTTestIPrintf(RTTESTLVL_ALWAYS, "CurrentCP is UTF-8 or similar (LC_ALL=%s LANG=%s LC_CTYPE=%s)\n",
1426	RTEnvGet("LC_ALL"), RTEnvGet("LANG"), RTEnvGet("LC_CTYPE"));
1427	RTStrFree(pszOut);
1428	}
1429	else
1430	RTTESTI_CHECK_MSG(rc == VWRN_NO_TRANSLATION \|\| rc == VERR_NO_TRANSLATION, ("rc=%Rrc\n", rc));
1431
1432	RTTestSub(hTest, "VERR_NO_TRANSLATION/RTUtf16ToLatin1");
1433	rc = RTUtf16ToLatin1(s_swzTest1, &pszOut);
1434	RTTESTI_CHECK_RC(rc, VERR_NO_TRANSLATION);
1435	if (RT_SUCCESS(rc))
1436	RTStrFree(pszOut);
1437
1438	RTStrFree(pszTest1);
1439	RTTestSubDone(hTest);
1440	}
1441
1442	static void testGetPut(RTTEST hTest)
1443	{
1444	/*
1445	* Test RTStrPutCp, RTStrGetCp and RTStrGetCpEx.
1446	*/
1447	RTTestSub(hTest, "RTStrPutCp, RTStrGetCp and RTStrGetCpEx");
1448
1449	RTUNICP uc = 0;
1450	while (uc <= 0x10fffd)
1451	{
1452	/* Figure the range - skip illegal ranges. */
1453	RTUNICP ucFirst = uc;
1454	if (ucFirst - UINT32_C(0xd800) <= 0x7ff)
1455	ucFirst = 0xe000;
1456	else if (ucFirst == UINT32_C(0xfffe) \|\| ucFirst == UINT32_C(0xffff))
1457	ucFirst = 0x10000;
1458
1459	RTUNICP ucLast = ucFirst + 1023;
1460	if (ucLast - UINT32_C(0xd800) <= 0x7ff)
1461	ucLast = 0xd7ff;
1462	else if (ucLast == UINT32_C(0xfffe) \|\| ucLast == UINT32_C(0xffff))
1463	ucLast = 0xfffd;
1464
1465	/* Encode the range into a string, decode each code point as we go along. */
1466	char sz1[8192];
1467	char *pszDst = sz1;
1468	for (uc = ucFirst; uc <= ucLast; uc++)
1469	{
1470	char *pszBefore = pszDst;
1471	pszDst = RTStrPutCp(pszDst, uc);
1472	RTTESTI_CHECK(pszBefore - pszDst < 6);
1473
1474	RTUNICP uc2 = RTStrGetCp(pszBefore);
1475	RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1476
1477	const char *pszSrc = pszBefore;
1478	RTUNICP uc3 = 42;
1479	RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1480	RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1481	RTTESTI_CHECK_MSG(pszSrc == pszDst, ("pszSrc=%p pszDst=%p\n", pszSrc, pszDst));
1482	}
1483
1484	/* Decode and re-encode it. */
1485	const char *pszSrc = pszDst = sz1;
1486	for (uc = ucFirst; uc <= ucLast; uc++)
1487	{
1488	RTUNICP uc2 = RTStrGetCp(pszSrc);
1489	RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1490
1491	RTUNICP uc3 = 42;
1492	RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1493	RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1494
1495	pszDst = RTStrPutCp(pszDst, uc);
1496	RTTESTI_CHECK_MSG(pszSrc == pszDst, ("pszSrc=%p pszDst=%p\n", pszSrc, pszDst));
1497	pszSrc = pszDst;
1498	}
1499
1500	/* Decode and wipe it (checking compiler optimizations). */
1501	pszSrc = pszDst = sz1;
1502	for (uc = ucFirst; uc <= ucLast; uc++)
1503	{
1504	RTUNICP uc2 = RTStrGetCp(pszSrc);
1505	RTTESTI_CHECK_MSG(uc2 == uc, ("uc2=%#x uc=%#x\n", uc2, uc));
1506
1507	RTUNICP uc3 = 42;
1508	RTTESTI_CHECK_RC(RTStrGetCpEx(&pszSrc, &uc3), VINF_SUCCESS);
1509	RTTESTI_CHECK_MSG(uc3 == uc, ("uc3=%#x uc=%#x\n", uc3, uc));
1510
1511	pszDst = RTStrPutCp(pszDst, 0);
1512	}
1513
1514	/* advance */
1515	uc = ucLast + 1;
1516	}
1517
1518	}
1519
1520
1521	int main()
1522	{
1523	/*
1524	* Init the runtime, test and say hello.
1525	*/
1526	RTTEST hTest;
1527	RTEXITCODE rcExit = RTTestInitAndCreate("tstUtf8", &hTest);
1528	if (rcExit != RTEXITCODE_SUCCESS)
1529	return rcExit;
1530	RTTestBanner(hTest);
1531
1532	/*
1533	* Run the tests.
1534	*/
1535	InitStrings();
1536	test1(hTest);
1537	test2(hTest);
1538	test3(hTest);
1539	TstRTStrXCmp(hTest);
1540	TstRTStrPurgeEncoding(hTest);
1541	/* TstRTPurgeComplementSet test conditions which assert. /
1542	TstRTStrPurgeComplementSet(hTest);
1543	TstRTUtf16PurgeComplementSet(hTest);
1544	testStrEnd(hTest);
1545	testStrStr(hTest);
1546	testUtf8Latin1(hTest);
1547	testUtf16Latin1(hTest);
1548	testNoTransation(hTest);
1549	testGetPut(hTest);
1550
1551	Benchmarks(hTest);
1552
1553	/*
1554	* Summary
1555	*/
1556	return RTTestSummaryAndDestroy(hTest);
1557	}
1558

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

source: vbox/trunk/src/VBox/Runtime/testcase/tstUtf8.cpp@ 67808

Download in other formats: