1 |
/* wptUTF8.cpp - UTF8 conversation |
2 |
* Copyright (C) 2002, 2004, 2005, 2006, 2009 Timo Schulz |
3 |
* |
4 |
* This file is part of WinPT. |
5 |
* |
6 |
* WinPT is free software; you can redistribute it and/or modify |
7 |
* it under the terms of the GNU General Public License as published by |
8 |
* the Free Software Foundation; either version 2 of the License, or |
9 |
* (at your option) any later version. |
10 |
* |
11 |
* WinPT is distributed in the hope that it will be useful, |
12 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
13 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
14 |
* GNU General Public License for more details. |
15 |
*/ |
16 |
#ifdef HAVE_CONFIG_H |
17 |
#include <config.h> |
18 |
#endif |
19 |
|
20 |
#include <windows.h> |
21 |
#include <stdlib.h> |
22 |
#include <stdio.h> |
23 |
#include <string.h> |
24 |
#include <ctype.h> |
25 |
|
26 |
#include "wptTypes.h" |
27 |
#include "wptErrors.h" |
28 |
|
29 |
|
30 |
/** |
31 |
* Converts the given intput string, which is encoded with the locale |
32 |
* setting, into UTF-8 representation. |
33 |
*/ |
34 |
char* |
35 |
native_to_utf8 (const char *string) |
36 |
{ |
37 |
wchar_t *result; |
38 |
char *native; |
39 |
int n; |
40 |
|
41 |
n = MultiByteToWideChar (GetACP (), 0, string, -1, NULL, 0); |
42 |
if (n < 0) |
43 |
return NULL; |
44 |
|
45 |
result = new wchar_t[n+1]; |
46 |
if (!result) |
47 |
BUG (0); |
48 |
|
49 |
n = MultiByteToWideChar (GetACP (), 0, string, -1, result, n); |
50 |
if (n < 0) { |
51 |
free_if_alloc (result); |
52 |
return NULL; |
53 |
} |
54 |
|
55 |
n = WideCharToMultiByte (CP_UTF8, 0, result, -1, NULL, 0, NULL, NULL); |
56 |
if (n < 0) |
57 |
return NULL; |
58 |
|
59 |
native = new char[n+1]; |
60 |
if (!native) |
61 |
BUG (0); |
62 |
|
63 |
n = WideCharToMultiByte (CP_UTF8, 0, result, -1, native, n, NULL, NULL); |
64 |
if (n < 0) { |
65 |
free_if_alloc (result); |
66 |
return NULL; |
67 |
} |
68 |
|
69 |
free_if_alloc (result); |
70 |
//native[n] = '\0'; |
71 |
return native; |
72 |
} |
73 |
|
74 |
|
75 |
/** |
76 |
* Converts the given string, which is encoded in UTF-8, |
77 |
* into the locale setting. |
78 |
*/ |
79 |
char* |
80 |
utf8_to_native (const char *string) |
81 |
{ |
82 |
wchar_t *result; |
83 |
char *native; |
84 |
int n; |
85 |
|
86 |
n = MultiByteToWideChar (CP_UTF8, 0, string, -1, NULL, 0); |
87 |
if (n < 0) |
88 |
return NULL; |
89 |
|
90 |
result = new wchar_t[n+1]; |
91 |
if (!result) |
92 |
BUG (0); |
93 |
|
94 |
n = MultiByteToWideChar (CP_UTF8, 0, string, -1, result, n); |
95 |
if (n < 0) { |
96 |
free_if_alloc (result); |
97 |
return NULL; |
98 |
} |
99 |
|
100 |
n = WideCharToMultiByte (GetACP (), 0, result, -1, NULL, 0, NULL, NULL); |
101 |
if (n < 0) |
102 |
return NULL; |
103 |
|
104 |
native = new char[n+1]; |
105 |
if (!native) |
106 |
BUG (0); |
107 |
|
108 |
n = WideCharToMultiByte (GetACP (), 0, result, -1, native, n, NULL, NULL); |
109 |
if (n < 0) { |
110 |
free_if_alloc (result); |
111 |
return NULL; |
112 |
} |
113 |
|
114 |
free_if_alloc (result); |
115 |
//native[n] = '\0'; |
116 |
return native; |
117 |
} |
118 |
|
119 |
|
120 |
/** |
121 |
* Returns -1 if the given string contains any 8-bit characters. |
122 |
* This is a helper to decide when to use UTF8 encoding. |
123 |
*/ |
124 |
int |
125 |
is_8bit_string (const char *str) |
126 |
{ |
127 |
for (size_t i = 0; i < strlen (str); i++) { |
128 |
if (str[i] & 0x80) |
129 |
return -1; |
130 |
} |
131 |
return 0; |
132 |
} |