1 | /* $Id: utf8-win.cpp 96407 2022-08-22 17:43:14Z vboxsync $ */
|
---|
2 | /** @file
|
---|
3 | * IPRT - UTF8 helpers.
|
---|
4 | */
|
---|
5 |
|
---|
6 | /*
|
---|
7 | * Copyright (C) 2006-2022 Oracle and/or its affiliates.
|
---|
8 | *
|
---|
9 | * This file is part of VirtualBox base platform packages, as
|
---|
10 | * available from https://www.virtualbox.org.
|
---|
11 | *
|
---|
12 | * This program is free software; you can redistribute it and/or
|
---|
13 | * modify it under the terms of the GNU General Public License
|
---|
14 | * as published by the Free Software Foundation, in version 3 of the
|
---|
15 | * License.
|
---|
16 | *
|
---|
17 | * This program is distributed in the hope that it will be useful, but
|
---|
18 | * WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
---|
20 | * General Public License for more details.
|
---|
21 | *
|
---|
22 | * You should have received a copy of the GNU General Public License
|
---|
23 | * along with this program; if not, see <https://www.gnu.org/licenses>.
|
---|
24 | *
|
---|
25 | * The contents of this file may alternatively be used under the terms
|
---|
26 | * of the Common Development and Distribution License Version 1.0
|
---|
27 | * (CDDL), a copy of it is provided in the "COPYING.CDDL" file included
|
---|
28 | * in the VirtualBox distribution, in which case the provisions of the
|
---|
29 | * CDDL are applicable instead of those of the GPL.
|
---|
30 | *
|
---|
31 | * You may elect to license modified versions of this file under the
|
---|
32 | * terms and conditions of either the GPL or the CDDL or both.
|
---|
33 | *
|
---|
34 | * SPDX-License-Identifier: GPL-3.0-only OR CDDL-1.0
|
---|
35 | */
|
---|
36 |
|
---|
37 |
|
---|
38 | /*********************************************************************************************************************************
|
---|
39 | * Header Files *
|
---|
40 | *********************************************************************************************************************************/
|
---|
41 | #define LOG_GROUP RTLOGGROUP_UTF8
|
---|
42 | #include <iprt/win/windows.h>
|
---|
43 |
|
---|
44 | #include <iprt/string.h>
|
---|
45 | #include <iprt/alloc.h>
|
---|
46 | #include <iprt/assert.h>
|
---|
47 | #include <iprt/err.h>
|
---|
48 | #include <iprt/utf16.h>
|
---|
49 |
|
---|
50 |
|
---|
51 |
|
---|
52 | RTR3DECL(int) RTStrUtf8ToCurrentCPTag(char **ppszString, const char *pszString, const char *pszTag)
|
---|
53 | {
|
---|
54 | return RTStrUtf8ToCurrentCPExTag(ppszString, pszString, RTSTR_MAX, pszTag);
|
---|
55 | }
|
---|
56 |
|
---|
57 |
|
---|
58 | RTR3DECL(int) RTStrUtf8ToCurrentCPExTag(char **ppszString, const char *pszString, size_t cchString, const char *pszTag)
|
---|
59 | {
|
---|
60 | Assert(ppszString);
|
---|
61 | Assert(pszString);
|
---|
62 | *ppszString = NULL;
|
---|
63 |
|
---|
64 | /*
|
---|
65 | * If the ANSI codepage (CP_ACP) is UTF-8, no translation is needed.
|
---|
66 | * Same goes for empty strings.
|
---|
67 | */
|
---|
68 | if ( cchString == 0
|
---|
69 | || *pszString == '\0')
|
---|
70 | return RTStrDupNExTag(ppszString, pszString, 0, pszTag);
|
---|
71 | if (GetACP() == CP_UTF8)
|
---|
72 | {
|
---|
73 | int rc = RTStrValidateEncodingEx(pszString, cchString, 0);
|
---|
74 | AssertRCReturn(rc, rc);
|
---|
75 | return RTStrDupNExTag(ppszString, pszString, cchString, pszTag);
|
---|
76 | }
|
---|
77 |
|
---|
78 | /*
|
---|
79 | * Convert to wide char first.
|
---|
80 | */
|
---|
81 | PRTUTF16 pwszString = NULL;
|
---|
82 | int rc = RTStrToUtf16Ex(pszString, cchString, &pwszString, 0, NULL);
|
---|
83 | if (RT_FAILURE(rc))
|
---|
84 | return rc;
|
---|
85 |
|
---|
86 | /*
|
---|
87 | * First calc result string length.
|
---|
88 | */
|
---|
89 | int cbResult = WideCharToMultiByte(CP_ACP, 0, pwszString, -1, NULL, 0, NULL, NULL);
|
---|
90 | if (cbResult > 0)
|
---|
91 | {
|
---|
92 | /*
|
---|
93 | * Alloc space for result buffer.
|
---|
94 | */
|
---|
95 | LPSTR lpString = (LPSTR)RTMemTmpAllocTag(cbResult, pszTag);
|
---|
96 | if (lpString)
|
---|
97 | {
|
---|
98 | /*
|
---|
99 | * Do the translation.
|
---|
100 | */
|
---|
101 | if (WideCharToMultiByte(CP_ACP, 0, pwszString, -1, lpString, cbResult, NULL, NULL) > 0)
|
---|
102 | {
|
---|
103 | /* ok */
|
---|
104 | *ppszString = lpString;
|
---|
105 | RTMemTmpFree(pwszString);
|
---|
106 | return VINF_SUCCESS;
|
---|
107 | }
|
---|
108 |
|
---|
109 | /* translation error */
|
---|
110 | int iLastErr = GetLastError();
|
---|
111 | AssertMsgFailed(("Unicode to ACP translation failed. lasterr=%d\n", iLastErr));
|
---|
112 | rc = RTErrConvertFromWin32(iLastErr);
|
---|
113 | }
|
---|
114 | else
|
---|
115 | rc = VERR_NO_TMP_MEMORY;
|
---|
116 | RTMemTmpFree(lpString);
|
---|
117 | }
|
---|
118 | else
|
---|
119 | {
|
---|
120 | /* translation error */
|
---|
121 | int iLastErr = GetLastError();
|
---|
122 | AssertMsgFailed(("Unicode to ACP translation failed lasterr=%d\n", iLastErr));
|
---|
123 | rc = RTErrConvertFromWin32(iLastErr);
|
---|
124 | }
|
---|
125 | RTMemTmpFree(pwszString);
|
---|
126 | return rc;
|
---|
127 | }
|
---|
128 |
|
---|
129 | static int rtStrCPToUtf8Tag(char **ppszString, const char *pszString, uint32_t uCodePage, const char *pszTag)
|
---|
130 | {
|
---|
131 | Assert(ppszString);
|
---|
132 | Assert(pszString);
|
---|
133 | *ppszString = NULL;
|
---|
134 |
|
---|
135 | /*
|
---|
136 | * If the ANSI codepage (CP_ACP) is UTF-8, no translation is needed.
|
---|
137 | * Same goes for empty strings.
|
---|
138 | */
|
---|
139 | if (*pszString == '\0')
|
---|
140 | return RTStrDupExTag(ppszString, pszString, pszTag);
|
---|
141 | if (GetACP() == CP_UTF8)
|
---|
142 | {
|
---|
143 | int rc = RTStrValidateEncoding(pszString);
|
---|
144 | AssertRCReturn(rc, rc);
|
---|
145 | return RTStrDupExTag(ppszString, pszString, pszTag);
|
---|
146 | }
|
---|
147 |
|
---|
148 | /** @todo is there a quicker way? Currently: ACP -> UTF-16 -> UTF-8 */
|
---|
149 |
|
---|
150 | /*
|
---|
151 | * First calc result string length.
|
---|
152 | */
|
---|
153 | int rc;
|
---|
154 | int cwc = MultiByteToWideChar((UINT)uCodePage, 0, pszString, -1, NULL, 0);
|
---|
155 | if (cwc > 0)
|
---|
156 | {
|
---|
157 | /*
|
---|
158 | * Alloc space for result buffer.
|
---|
159 | */
|
---|
160 | PRTUTF16 pwszString = (PRTUTF16)RTMemTmpAlloc(cwc * sizeof(RTUTF16));
|
---|
161 | if (pwszString)
|
---|
162 | {
|
---|
163 | /*
|
---|
164 | * Do the translation.
|
---|
165 | */
|
---|
166 | if (MultiByteToWideChar((UINT)uCodePage, 0, pszString, -1, pwszString, cwc) > 0)
|
---|
167 | {
|
---|
168 | /*
|
---|
169 | * Now we got UTF-16, convert it to UTF-8
|
---|
170 | */
|
---|
171 | rc = RTUtf16ToUtf8(pwszString, ppszString);
|
---|
172 | RTMemTmpFree(pwszString);
|
---|
173 | return rc;
|
---|
174 | }
|
---|
175 | RTMemTmpFree(pwszString);
|
---|
176 | /* translation error */
|
---|
177 | int iLastErr = GetLastError();
|
---|
178 | AssertMsgFailed(("ACP to Unicode translation failed. lasterr=%d\n", iLastErr));
|
---|
179 | rc = RTErrConvertFromWin32(iLastErr);
|
---|
180 | }
|
---|
181 | else
|
---|
182 | rc = VERR_NO_TMP_MEMORY;
|
---|
183 | }
|
---|
184 | else
|
---|
185 | {
|
---|
186 | /* translation error */
|
---|
187 | int iLastErr = GetLastError();
|
---|
188 | AssertMsgFailed(("Unicode to ACP translation failed lasterr=%d\n", iLastErr));
|
---|
189 | rc = RTErrConvertFromWin32(iLastErr);
|
---|
190 | }
|
---|
191 | return rc;
|
---|
192 | }
|
---|
193 |
|
---|
194 |
|
---|
195 | RTR3DECL(int) RTStrCurrentCPToUtf8Tag(char **ppszString, const char *pszString, const char *pszTag)
|
---|
196 | {
|
---|
197 | return rtStrCPToUtf8Tag(ppszString, pszString, CP_ACP, pszTag);
|
---|
198 | }
|
---|
199 |
|
---|
200 |
|
---|
201 | RTR3DECL(int) RTStrConsoleCPToUtf8Tag(char **ppszString, const char *pszString, const char *pszTag)
|
---|
202 | {
|
---|
203 | return rtStrCPToUtf8Tag(ppszString, pszString, GetConsoleCP(), pszTag);
|
---|
204 | }
|
---|