| 1 |
/* wptUTF8.cpp - UTF8 conversation |
| 2 |
* Copyright (C) 2002, 2004, 2005, 2006, 2009, 2012 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 |
/* Byte order mark that is usually used to indicate that the following |
| 31 |
data is encoded in UTF-8. */ |
| 32 |
BYTE UTF8_BOM[] = {0xEF, 0xBB, 0xBF}; |
| 33 |
|
| 34 |
|
| 35 |
/** |
| 36 |
* Convert the given intput string, which is encoded with the locale |
| 37 |
* setting, into UTF-8 representation. |
| 38 |
*/ |
| 39 |
char* |
| 40 |
native_to_utf8 (const char *string) |
| 41 |
{ |
| 42 |
int n = MultiByteToWideChar (GetACP (), 0, string, -1, NULL, 0); |
| 43 |
if (n < 0) |
| 44 |
return NULL; |
| 45 |
|
| 46 |
wchar_t *result = new wchar_t[n+1]; |
| 47 |
if (!result) |
| 48 |
BUG (0); |
| 49 |
|
| 50 |
n = MultiByteToWideChar (GetACP (), 0, string, -1, result, n); |
| 51 |
if (n < 0) { |
| 52 |
free_if_alloc (result); |
| 53 |
return NULL; |
| 54 |
} |
| 55 |
|
| 56 |
n = WideCharToMultiByte (CP_UTF8, 0, result, -1, NULL, 0, NULL, NULL); |
| 57 |
if (n < 0) |
| 58 |
return NULL; |
| 59 |
|
| 60 |
char *native = new char[n + 1]; |
| 61 |
if (!native) |
| 62 |
BUG (0); |
| 63 |
memset(native, 0, n + 1); |
| 64 |
|
| 65 |
n = WideCharToMultiByte (CP_UTF8, 0, result, -1, native, n, NULL, NULL); |
| 66 |
if (n < 0) { |
| 67 |
free_if_alloc (result); |
| 68 |
return NULL; |
| 69 |
} |
| 70 |
|
| 71 |
free_if_alloc (result); |
| 72 |
return native; |
| 73 |
} |
| 74 |
|
| 75 |
|
| 76 |
/** |
| 77 |
* Convert an UTF-8 string into an UTF-16 string. |
| 78 |
*/ |
| 79 |
wchar_t* |
| 80 |
utf8_to_utf16(const char *string, size_t *retlen) |
| 81 |
{ |
| 82 |
int n = MultiByteToWideChar(CP_UTF8, 0, string, -1, NULL, 0); |
| 83 |
if (n < 0) |
| 84 |
return NULL; |
| 85 |
|
| 86 |
wchar_t *result = new wchar_t[n + 1]; |
| 87 |
if (!result) |
| 88 |
BUG(0); |
| 89 |
|
| 90 |
n = MultiByteToWideChar(CP_UTF8, 0, string, -1, result, n); |
| 91 |
if (n < 0) { |
| 92 |
free_if_alloc(result); |
| 93 |
return NULL; |
| 94 |
} |
| 95 |
|
| 96 |
*retlen = n; |
| 97 |
return result; |
| 98 |
} |
| 99 |
|
| 100 |
|
| 101 |
/** |
| 102 |
* Convert the given string, which is encoded in UTF-8, |
| 103 |
* into the locale setting. |
| 104 |
*/ |
| 105 |
char* |
| 106 |
utf8_to_native (const char *string) |
| 107 |
{ |
| 108 |
int n = MultiByteToWideChar (CP_UTF8, 0, string, -1, NULL, 0); |
| 109 |
if (n < 0) |
| 110 |
return NULL; |
| 111 |
|
| 112 |
wchar_t *result = new wchar_t[n+1]; |
| 113 |
if (!result) |
| 114 |
BUG (0); |
| 115 |
|
| 116 |
n = MultiByteToWideChar (CP_UTF8, 0, string, -1, result, n); |
| 117 |
if (n < 0) { |
| 118 |
free_if_alloc (result); |
| 119 |
return NULL; |
| 120 |
} |
| 121 |
|
| 122 |
n = WideCharToMultiByte (GetACP (), 0, result, -1, NULL, 0, NULL, NULL); |
| 123 |
if (n < 0) |
| 124 |
return NULL; |
| 125 |
|
| 126 |
char *native = new char[n + 1]; |
| 127 |
if (!native) |
| 128 |
BUG (0); |
| 129 |
memset(native, 0, n + 1); |
| 130 |
|
| 131 |
n = WideCharToMultiByte (GetACP (), 0, result, -1, native, n, NULL, NULL); |
| 132 |
if (n < 0) { |
| 133 |
free_if_alloc (result); |
| 134 |
return NULL; |
| 135 |
} |
| 136 |
|
| 137 |
free_if_alloc (result); |
| 138 |
return native; |
| 139 |
} |
| 140 |
|
| 141 |
|
| 142 |
/** |
| 143 |
* Return -1 if the given string contains any 8-bit characters. |
| 144 |
* This is a helper to decide when to use UTF8 encoding. |
| 145 |
*/ |
| 146 |
int |
| 147 |
is_8bit_string (const char *str) |
| 148 |
{ |
| 149 |
for (size_t i = 0; i < strlen (str); i++) { |
| 150 |
if (str[i] & 0x80) |
| 151 |
return -1; |
| 152 |
} |
| 153 |
return 0; |
| 154 |
} |
Parent Directory
| 
Revision Log