Hash :
3603cb09
Author :
Date :
2015-02-10T23:13:49
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166
/*
* Copyright (C) the libgit2 contributors. All rights reserved.
*
* This file is part of libgit2, distributed under the GNU GPL v2 with
* a Linking Exception. For full terms see the included COPYING file.
*/
#include "common.h"
#include "utf-conv.h"
#ifndef WC_ERR_INVALID_CHARS
# define WC_ERR_INVALID_CHARS 0x80
#endif
GIT_INLINE(DWORD) get_wc_flags(void)
{
static char inited = 0;
static DWORD flags;
/* Invalid code point check supported on Vista+ only */
if (!inited) {
flags = git_has_win32_version(6, 0, 0) ? WC_ERR_INVALID_CHARS : 0;
inited = 1;
}
return flags;
}
GIT_INLINE(void) git__set_errno(void)
{
if (GetLastError() == ERROR_INSUFFICIENT_BUFFER)
errno = ENAMETOOLONG;
else
errno = EINVAL;
}
/**
* Converts a UTF-8 string to wide characters.
*
* @param dest The buffer to receive the wide string.
* @param dest_size The size of the buffer, in characters.
* @param src The UTF-8 string to convert.
* @return The length of the wide string, in characters (not counting the NULL terminator), or < 0 for failure
*/
int git__utf8_to_16(wchar_t *dest, size_t dest_size, const char *src)
{
int len;
/* Length of -1 indicates NULL termination of the input string. Subtract 1 from the result to
* turn 0 into -1 (an error code) and to not count the NULL terminator as part of the string's
* length. MultiByteToWideChar never returns int's minvalue, so underflow is not possible */
if ((len = MultiByteToWideChar(CP_UTF8, MB_ERR_INVALID_CHARS, src, -1, dest, (int)dest_size) - 1) < 0)
git__set_errno();
return len;
}
/**
* Converts a wide string to UTF-8.
*
* @param dest The buffer to receive the UTF-8 string.
* @param dest_size The size of the buffer, in bytes.
* @param src The wide string to convert.
* @return The length of the UTF-8 string, in bytes (not counting the NULL terminator), or < 0 for failure
*/
int git__utf16_to_8(char *dest, size_t dest_size, const wchar_t *src)
{
int len;
/* Length of -1 indicates NULL termination of the input string. Subtract 1 from the result to
* turn 0 into -1 (an error code) and to not count the NULL terminator as part of the string's
* length. WideCharToMultiByte never returns int's minvalue, so underflow is not possible */
if ((len = WideCharToMultiByte(CP_UTF8, get_wc_flags(), src, -1, dest, (int)dest_size, NULL, NULL) - 1) < 0)
git__set_errno();
return len;
}
/**
* Converts a UTF-8 string to wide characters.
* Memory is allocated to hold the converted string.
* The caller is responsible for freeing the string with git__free.
*
* @param dest Receives a pointer to the wide string.
* @param src The UTF-8 string to convert.
* @return The length of the wide string, in characters (not counting the NULL terminator), or < 0 for failure
*/
int git__utf8_to_16_alloc(wchar_t **dest, const char *src)
{
int utf16_size;
*dest = NULL;
/* Length of -1 indicates NULL termination of the input string */
utf16_size = MultiByteToWideChar(CP_UTF8, MB_ERR_INVALID_CHARS, src, -1, NULL, 0);
if (!utf16_size) {
git__set_errno();
return -1;
}
if (!(*dest = git__mallocarray(utf16_size, sizeof(wchar_t)))) {
errno = ENOMEM;
return -1;
}
utf16_size = MultiByteToWideChar(CP_UTF8, MB_ERR_INVALID_CHARS, src, -1, *dest, utf16_size);
if (!utf16_size) {
git__set_errno();
git__free(*dest);
*dest = NULL;
}
/* Subtract 1 from the result to turn 0 into -1 (an error code) and to not count the NULL
* terminator as part of the string's length. MultiByteToWideChar never returns int's minvalue,
* so underflow is not possible */
return utf16_size - 1;
}
/**
* Converts a wide string to UTF-8.
* Memory is allocated to hold the converted string.
* The caller is responsible for freeing the string with git__free.
*
* @param dest Receives a pointer to the UTF-8 string.
* @param src The wide string to convert.
* @return The length of the UTF-8 string, in bytes (not counting the NULL terminator), or < 0 for failure
*/
int git__utf16_to_8_alloc(char **dest, const wchar_t *src)
{
int utf8_size;
DWORD dwFlags = get_wc_flags();
*dest = NULL;
/* Length of -1 indicates NULL termination of the input string */
utf8_size = WideCharToMultiByte(CP_UTF8, dwFlags, src, -1, NULL, 0, NULL, NULL);
if (!utf8_size) {
git__set_errno();
return -1;
}
*dest = git__malloc(utf8_size);
if (!*dest) {
errno = ENOMEM;
return -1;
}
utf8_size = WideCharToMultiByte(CP_UTF8, dwFlags, src, -1, *dest, utf8_size, NULL, NULL);
if (!utf8_size) {
git__set_errno();
git__free(*dest);
*dest = NULL;
}
/* Subtract 1 from the result to turn 0 into -1 (an error code) and to not count the NULL
* terminator as part of the string's length. MultiByteToWideChar never returns int's minvalue,
* so underflow is not possible */
return utf8_size - 1;
}