1 | /* $Id: utf-16-latin-1.cpp 76553 2019-01-01 01:45:53Z vboxsync $ */
|
---|
2 | /** @file
|
---|
3 | * IPRT - Latin-1 and UTF-16.
|
---|
4 | */
|
---|
5 |
|
---|
6 | /*
|
---|
7 | * Copyright (C) 2006-2019 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/latin1.h>
|
---|
32 | #include "internal/iprt.h"
|
---|
33 |
|
---|
34 | #include <iprt/assert.h>
|
---|
35 | #include <iprt/err.h>
|
---|
36 | #include <iprt/mem.h>
|
---|
37 | #include <iprt/string.h>
|
---|
38 | #include <iprt/utf16.h>
|
---|
39 | #include <iprt/uni.h>
|
---|
40 | #include "internal/string.h"
|
---|
41 |
|
---|
42 |
|
---|
43 | /**
|
---|
44 | * Validate the UTF-16 encoding and calculates the length of a Latin1 encoding.
|
---|
45 | *
|
---|
46 | * @returns iprt status code.
|
---|
47 | * @param pwsz The UTF-16 string.
|
---|
48 | * @param cwc The max length of the UTF-16 string to consider.
|
---|
49 | * @param pcch Where to store the length (excluding '\\0') of the Latin1 string. (cch == cb, btw)
|
---|
50 | */
|
---|
51 | static int rtUtf16CalcLatin1Length(PCRTUTF16 pwsz, size_t cwc, size_t *pcch)
|
---|
52 | {
|
---|
53 | int rc = VINF_SUCCESS;
|
---|
54 | size_t cch = 0;
|
---|
55 | while (cwc > 0)
|
---|
56 | {
|
---|
57 | RTUTF16 wc = *pwsz++; cwc--;
|
---|
58 | if (!wc)
|
---|
59 | break;
|
---|
60 | else if (RT_LIKELY(wc < 0x100))
|
---|
61 | ++cch;
|
---|
62 | else
|
---|
63 | {
|
---|
64 | if (wc < 0xd800 || wc > 0xdfff)
|
---|
65 | {
|
---|
66 | if (wc >= 0xfffe)
|
---|
67 | {
|
---|
68 | RTStrAssertMsgFailed(("endian indicator! wc=%#x\n", wc));
|
---|
69 | rc = VERR_CODE_POINT_ENDIAN_INDICATOR;
|
---|
70 | break;
|
---|
71 | }
|
---|
72 | }
|
---|
73 | else
|
---|
74 | {
|
---|
75 | if (wc >= 0xdc00)
|
---|
76 | {
|
---|
77 | RTStrAssertMsgFailed(("Wrong 1st char in surrogate! wc=%#x\n", wc));
|
---|
78 | rc = VERR_INVALID_UTF16_ENCODING;
|
---|
79 | break;
|
---|
80 | }
|
---|
81 | if (cwc <= 0)
|
---|
82 | {
|
---|
83 | RTStrAssertMsgFailed(("Invalid length! wc=%#x\n", wc));
|
---|
84 | rc = VERR_INVALID_UTF16_ENCODING;
|
---|
85 | break;
|
---|
86 | }
|
---|
87 | wc = *pwsz++; cwc--;
|
---|
88 | if (wc < 0xdc00 || wc > 0xdfff)
|
---|
89 | {
|
---|
90 | RTStrAssertMsgFailed(("Wrong 2nd char in surrogate! wc=%#x\n", wc));
|
---|
91 | rc = VERR_INVALID_UTF16_ENCODING;
|
---|
92 | break;
|
---|
93 | }
|
---|
94 | }
|
---|
95 |
|
---|
96 | rc = VERR_NO_TRANSLATION;
|
---|
97 | break;
|
---|
98 | }
|
---|
99 | }
|
---|
100 |
|
---|
101 | /* done */
|
---|
102 | *pcch = cch;
|
---|
103 | return rc;
|
---|
104 | }
|
---|
105 |
|
---|
106 |
|
---|
107 | /**
|
---|
108 | * Recodes an valid UTF-16 string as Latin1.
|
---|
109 | *
|
---|
110 | * @returns iprt status code.
|
---|
111 | * @param pwsz The UTF-16 string.
|
---|
112 | * @param cwc The number of RTUTF16 characters to process from pwsz. The recoding
|
---|
113 | * will stop when cwc or '\\0' is reached.
|
---|
114 | * @param psz Where to store the Latin1 string.
|
---|
115 | * @param cch The size of the Latin1 buffer, excluding the terminator.
|
---|
116 | */
|
---|
117 | static int rtUtf16RecodeAsLatin1(PCRTUTF16 pwsz, size_t cwc, char *psz, size_t cch)
|
---|
118 | {
|
---|
119 | unsigned char *pch = (unsigned char *)psz;
|
---|
120 | int rc = VINF_SUCCESS;
|
---|
121 | while (cwc > 0)
|
---|
122 | {
|
---|
123 | RTUTF16 wc = *pwsz++; cwc--;
|
---|
124 | if (!wc)
|
---|
125 | break;
|
---|
126 | if (RT_LIKELY(wc < 0x100))
|
---|
127 | {
|
---|
128 | if (RT_UNLIKELY(cch < 1))
|
---|
129 | {
|
---|
130 | RTStrAssertMsgFailed(("Buffer overflow! 1\n"));
|
---|
131 | rc = VERR_BUFFER_OVERFLOW;
|
---|
132 | break;
|
---|
133 | }
|
---|
134 | cch--;
|
---|
135 | *pch++ = (unsigned char)wc;
|
---|
136 | }
|
---|
137 | else
|
---|
138 | {
|
---|
139 | if (wc < 0xd800 || wc > 0xdfff)
|
---|
140 | {
|
---|
141 | if (wc >= 0xfffe)
|
---|
142 | {
|
---|
143 | RTStrAssertMsgFailed(("endian indicator! wc=%#x\n", wc));
|
---|
144 | rc = VERR_CODE_POINT_ENDIAN_INDICATOR;
|
---|
145 | break;
|
---|
146 | }
|
---|
147 | }
|
---|
148 | else
|
---|
149 | {
|
---|
150 | if (wc >= 0xdc00)
|
---|
151 | {
|
---|
152 | RTStrAssertMsgFailed(("Wrong 1st char in surrogate! wc=%#x\n", wc));
|
---|
153 | rc = VERR_INVALID_UTF16_ENCODING;
|
---|
154 | break;
|
---|
155 | }
|
---|
156 | if (cwc <= 0)
|
---|
157 | {
|
---|
158 | RTStrAssertMsgFailed(("Invalid length! wc=%#x\n", wc));
|
---|
159 | rc = VERR_INVALID_UTF16_ENCODING;
|
---|
160 | break;
|
---|
161 | }
|
---|
162 | RTUTF16 wc2 = *pwsz++; cwc--;
|
---|
163 | if (wc2 < 0xdc00 || wc2 > 0xdfff)
|
---|
164 | {
|
---|
165 | RTStrAssertMsgFailed(("Wrong 2nd char in surrogate! wc=%#x\n", wc));
|
---|
166 | rc = VERR_INVALID_UTF16_ENCODING;
|
---|
167 | break;
|
---|
168 | }
|
---|
169 | }
|
---|
170 |
|
---|
171 | rc = VERR_NO_TRANSLATION;
|
---|
172 | break;
|
---|
173 | }
|
---|
174 | }
|
---|
175 |
|
---|
176 | /* done */
|
---|
177 | *pch = '\0';
|
---|
178 | return rc;
|
---|
179 | }
|
---|
180 |
|
---|
181 |
|
---|
182 | RTDECL(int) RTUtf16ToLatin1Tag(PCRTUTF16 pwszString, char **ppszString, const char *pszTag)
|
---|
183 | {
|
---|
184 | /*
|
---|
185 | * Validate input.
|
---|
186 | */
|
---|
187 | Assert(VALID_PTR(ppszString));
|
---|
188 | Assert(VALID_PTR(pwszString));
|
---|
189 | *ppszString = NULL;
|
---|
190 |
|
---|
191 | /*
|
---|
192 | * Validate the UTF-16 string and calculate the length of the UTF-8 encoding of it.
|
---|
193 | */
|
---|
194 | size_t cch;
|
---|
195 | int rc = rtUtf16CalcLatin1Length(pwszString, RTSTR_MAX, &cch);
|
---|
196 | if (RT_SUCCESS(rc))
|
---|
197 | {
|
---|
198 | /*
|
---|
199 | * Allocate buffer and recode it.
|
---|
200 | */
|
---|
201 | char *pszResult = (char *)RTMemAllocTag(cch + 1, pszTag);
|
---|
202 | if (pszResult)
|
---|
203 | {
|
---|
204 | rc = rtUtf16RecodeAsLatin1(pwszString, RTSTR_MAX, pszResult, cch);
|
---|
205 | if (RT_SUCCESS(rc))
|
---|
206 | {
|
---|
207 | *ppszString = pszResult;
|
---|
208 | return rc;
|
---|
209 | }
|
---|
210 |
|
---|
211 | RTMemFree(pszResult);
|
---|
212 | }
|
---|
213 | else
|
---|
214 | rc = VERR_NO_STR_MEMORY;
|
---|
215 | }
|
---|
216 | return rc;
|
---|
217 | }
|
---|
218 | RT_EXPORT_SYMBOL(RTUtf16ToLatin1Tag);
|
---|
219 |
|
---|
220 |
|
---|
221 | RTDECL(int) RTUtf16ToLatin1ExTag(PCRTUTF16 pwszString, size_t cwcString, char **ppsz, size_t cch, size_t *pcch, const char *pszTag)
|
---|
222 | {
|
---|
223 | /*
|
---|
224 | * Validate input.
|
---|
225 | */
|
---|
226 | AssertPtr(pwszString);
|
---|
227 | AssertPtr(ppsz);
|
---|
228 | AssertPtrNull(pcch);
|
---|
229 |
|
---|
230 | /*
|
---|
231 | * Validate the UTF-16 string and calculate the length of the Latin1 encoding of it.
|
---|
232 | */
|
---|
233 | size_t cchResult;
|
---|
234 | int rc = rtUtf16CalcLatin1Length(pwszString, cwcString, &cchResult);
|
---|
235 | if (RT_SUCCESS(rc))
|
---|
236 | {
|
---|
237 | if (pcch)
|
---|
238 | *pcch = cchResult;
|
---|
239 |
|
---|
240 | /*
|
---|
241 | * Check buffer size / Allocate buffer and recode it.
|
---|
242 | */
|
---|
243 | bool fShouldFree;
|
---|
244 | char *pszResult;
|
---|
245 | if (cch > 0 && *ppsz)
|
---|
246 | {
|
---|
247 | fShouldFree = false;
|
---|
248 | if (cch <= cchResult)
|
---|
249 | return VERR_BUFFER_OVERFLOW;
|
---|
250 | pszResult = *ppsz;
|
---|
251 | }
|
---|
252 | else
|
---|
253 | {
|
---|
254 | *ppsz = NULL;
|
---|
255 | fShouldFree = true;
|
---|
256 | cch = RT_MAX(cch, cchResult + 1);
|
---|
257 | pszResult = (char *)RTMemAllocTag(cch, pszTag);
|
---|
258 | }
|
---|
259 | if (pszResult)
|
---|
260 | {
|
---|
261 | rc = rtUtf16RecodeAsLatin1(pwszString, cwcString, pszResult, cch - 1);
|
---|
262 | if (RT_SUCCESS(rc))
|
---|
263 | {
|
---|
264 | *ppsz = pszResult;
|
---|
265 | return rc;
|
---|
266 | }
|
---|
267 |
|
---|
268 | if (fShouldFree)
|
---|
269 | RTMemFree(pszResult);
|
---|
270 | }
|
---|
271 | else
|
---|
272 | rc = VERR_NO_STR_MEMORY;
|
---|
273 | }
|
---|
274 | return rc;
|
---|
275 | }
|
---|
276 | RT_EXPORT_SYMBOL(RTUtf16ToLatin1ExTag);
|
---|
277 |
|
---|
278 |
|
---|
279 | RTDECL(size_t) RTUtf16CalcLatin1Len(PCRTUTF16 pwsz)
|
---|
280 | {
|
---|
281 | size_t cch;
|
---|
282 | int rc = rtUtf16CalcLatin1Length(pwsz, RTSTR_MAX, &cch);
|
---|
283 | return RT_SUCCESS(rc) ? cch : 0;
|
---|
284 | }
|
---|
285 | RT_EXPORT_SYMBOL(RTUtf16CalcLatin1Len);
|
---|
286 |
|
---|
287 |
|
---|
288 | RTDECL(int) RTUtf16CalcLatin1LenEx(PCRTUTF16 pwsz, size_t cwc, size_t *pcch)
|
---|
289 | {
|
---|
290 | size_t cch;
|
---|
291 | int rc = rtUtf16CalcLatin1Length(pwsz, cwc, &cch);
|
---|
292 | if (pcch)
|
---|
293 | *pcch = RT_SUCCESS(rc) ? cch : ~(size_t)0;
|
---|
294 | return rc;
|
---|
295 | }
|
---|
296 | RT_EXPORT_SYMBOL(RTUtf16CalcLatin1LenEx);
|
---|
297 |
|
---|
298 |
|
---|
299 | /**
|
---|
300 | * Calculates the UTF-16 length of a Latin1 string. In fact this is just the
|
---|
301 | * original length, but the function saves us nasty comments to that effect
|
---|
302 | * all over the place.
|
---|
303 | *
|
---|
304 | * @returns IPRT status code.
|
---|
305 | * @param psz Pointer to the Latin1 string.
|
---|
306 | * @param cch The max length of the string. (btw cch = cb)
|
---|
307 | * Use RTSTR_MAX if all of the string is to be examined.s
|
---|
308 | * @param pcwc Where to store the length of the UTF-16 string as a number of RTUTF16 characters.
|
---|
309 | */
|
---|
310 | static int rtLatin1CalcUtf16Length(const char *psz, size_t cch, size_t *pcwc)
|
---|
311 | {
|
---|
312 | *pcwc = RTStrNLen(psz, cch);
|
---|
313 | return VINF_SUCCESS;
|
---|
314 | }
|
---|
315 |
|
---|
316 |
|
---|
317 | /**
|
---|
318 | * Recodes a Latin1 string as UTF-16. This is just a case of expanding it to
|
---|
319 | * sixteen bits, as Unicode is a superset of Latin1.
|
---|
320 | *
|
---|
321 | * Since we know the input is valid, we do *not* perform length checks.
|
---|
322 | *
|
---|
323 | * @returns iprt status code.
|
---|
324 | * @param psz The Latin1 string to recode.
|
---|
325 | * @param cch The number of chars (the type char, so bytes if you like) to process of the Latin1 string.
|
---|
326 | * The recoding will stop when cch or '\\0' is reached. Pass RTSTR_MAX to process up to '\\0'.
|
---|
327 | * @param pwsz Where to store the UTF-16 string.
|
---|
328 | * @param cwc The number of RTUTF16 items the pwsz buffer can hold, excluding the terminator ('\\0').
|
---|
329 | */
|
---|
330 | static int rtLatin1RecodeAsUtf16(const char *psz, size_t cch, PRTUTF16 pwsz, size_t cwc)
|
---|
331 | {
|
---|
332 | int rc = VINF_SUCCESS;
|
---|
333 | const unsigned char *puch = (const unsigned char *)psz;
|
---|
334 | PRTUTF16 pwc = pwsz;
|
---|
335 | while (cch-- > 0)
|
---|
336 | {
|
---|
337 | /* read the next char and check for terminator. */
|
---|
338 | const unsigned char uch = *puch;
|
---|
339 | if (!uch)
|
---|
340 | break;
|
---|
341 |
|
---|
342 | /* check for output overflow */
|
---|
343 | if (RT_UNLIKELY(cwc < 1))
|
---|
344 | {
|
---|
345 | rc = VERR_BUFFER_OVERFLOW;
|
---|
346 | break;
|
---|
347 | }
|
---|
348 |
|
---|
349 | /* expand the code point */
|
---|
350 | *pwc++ = uch;
|
---|
351 | cwc--;
|
---|
352 | puch++;
|
---|
353 | }
|
---|
354 |
|
---|
355 | /* done */
|
---|
356 | *pwc = '\0';
|
---|
357 | return rc;
|
---|
358 | }
|
---|
359 |
|
---|
360 |
|
---|
361 | RTDECL(int) RTLatin1ToUtf16Tag(const char *pszString, PRTUTF16 *ppwszString, const char *pszTag)
|
---|
362 | {
|
---|
363 | /*
|
---|
364 | * Validate input.
|
---|
365 | */
|
---|
366 | Assert(VALID_PTR(ppwszString));
|
---|
367 | Assert(VALID_PTR(pszString));
|
---|
368 | *ppwszString = NULL;
|
---|
369 |
|
---|
370 | /*
|
---|
371 | * Validate the input and calculate the length of the UTF-16 string.
|
---|
372 | */
|
---|
373 | size_t cwc;
|
---|
374 | int rc = rtLatin1CalcUtf16Length(pszString, RTSTR_MAX, &cwc);
|
---|
375 | if (RT_SUCCESS(rc))
|
---|
376 | {
|
---|
377 | /*
|
---|
378 | * Allocate buffer.
|
---|
379 | */
|
---|
380 | PRTUTF16 pwsz = (PRTUTF16)RTMemAllocTag((cwc + 1) * sizeof(RTUTF16), pszTag);
|
---|
381 | if (pwsz)
|
---|
382 | {
|
---|
383 | /*
|
---|
384 | * Encode the UTF-16 string.
|
---|
385 | */
|
---|
386 | rc = rtLatin1RecodeAsUtf16(pszString, RTSTR_MAX, pwsz, cwc);
|
---|
387 | if (RT_SUCCESS(rc))
|
---|
388 | {
|
---|
389 | *ppwszString = pwsz;
|
---|
390 | return rc;
|
---|
391 | }
|
---|
392 | RTMemFree(pwsz);
|
---|
393 | }
|
---|
394 | else
|
---|
395 | rc = VERR_NO_UTF16_MEMORY;
|
---|
396 | }
|
---|
397 | return rc;
|
---|
398 | }
|
---|
399 | RT_EXPORT_SYMBOL(RTLatin1ToUtf16Tag);
|
---|
400 |
|
---|
401 |
|
---|
402 | RTDECL(int) RTLatin1ToUtf16ExTag(const char *pszString, size_t cchString,
|
---|
403 | PRTUTF16 *ppwsz, size_t cwc, size_t *pcwc, const char *pszTag)
|
---|
404 | {
|
---|
405 | /*
|
---|
406 | * Validate input.
|
---|
407 | */
|
---|
408 | Assert(VALID_PTR(pszString));
|
---|
409 | Assert(VALID_PTR(ppwsz));
|
---|
410 | Assert(!pcwc || VALID_PTR(pcwc));
|
---|
411 |
|
---|
412 | /*
|
---|
413 | * Validate the input and calculate the length of the UTF-16 string.
|
---|
414 | */
|
---|
415 | size_t cwcResult;
|
---|
416 | int rc = rtLatin1CalcUtf16Length(pszString, cchString, &cwcResult);
|
---|
417 | if (RT_SUCCESS(rc))
|
---|
418 | {
|
---|
419 | if (pcwc)
|
---|
420 | *pcwc = cwcResult;
|
---|
421 |
|
---|
422 | /*
|
---|
423 | * Check buffer size / Allocate buffer.
|
---|
424 | */
|
---|
425 | bool fShouldFree;
|
---|
426 | PRTUTF16 pwszResult;
|
---|
427 | if (cwc > 0 && *ppwsz)
|
---|
428 | {
|
---|
429 | fShouldFree = false;
|
---|
430 | if (cwc <= cwcResult)
|
---|
431 | return VERR_BUFFER_OVERFLOW;
|
---|
432 | pwszResult = *ppwsz;
|
---|
433 | }
|
---|
434 | else
|
---|
435 | {
|
---|
436 | *ppwsz = NULL;
|
---|
437 | fShouldFree = true;
|
---|
438 | cwc = RT_MAX(cwcResult + 1, cwc);
|
---|
439 | pwszResult = (PRTUTF16)RTMemAllocTag(cwc * sizeof(RTUTF16), pszTag);
|
---|
440 | }
|
---|
441 | if (pwszResult)
|
---|
442 | {
|
---|
443 | /*
|
---|
444 | * Encode the UTF-16 string.
|
---|
445 | */
|
---|
446 | rc = rtLatin1RecodeAsUtf16(pszString, cchString, pwszResult, cwc - 1);
|
---|
447 | if (RT_SUCCESS(rc))
|
---|
448 | {
|
---|
449 | *ppwsz = pwszResult;
|
---|
450 | return rc;
|
---|
451 | }
|
---|
452 | if (fShouldFree)
|
---|
453 | RTMemFree(pwszResult);
|
---|
454 | }
|
---|
455 | else
|
---|
456 | rc = VERR_NO_UTF16_MEMORY;
|
---|
457 | }
|
---|
458 | return rc;
|
---|
459 | }
|
---|
460 | RT_EXPORT_SYMBOL(RTLatin1ToUtf16ExTag);
|
---|
461 |
|
---|
462 |
|
---|
463 | RTDECL(size_t) RTLatin1CalcUtf16Len(const char *psz)
|
---|
464 | {
|
---|
465 | size_t cwc;
|
---|
466 | int rc = rtLatin1CalcUtf16Length(psz, RTSTR_MAX, &cwc);
|
---|
467 | return RT_SUCCESS(rc) ? cwc : 0;
|
---|
468 | }
|
---|
469 | RT_EXPORT_SYMBOL(RTLatin1CalcUtf16Len);
|
---|
470 |
|
---|
471 |
|
---|
472 | RTDECL(int) RTLatin1CalcUtf16LenEx(const char *psz, size_t cch, size_t *pcwc)
|
---|
473 | {
|
---|
474 | size_t cwc;
|
---|
475 | int rc = rtLatin1CalcUtf16Length(psz, cch, &cwc);
|
---|
476 | if (pcwc)
|
---|
477 | *pcwc = RT_SUCCESS(rc) ? cwc : ~(size_t)0;
|
---|
478 | return rc;
|
---|
479 | }
|
---|
480 | RT_EXPORT_SYMBOL(RTLatin1CalcUtf16LenEx);
|
---|
481 |
|
---|