trunk/Src/wptUTF8.cpp

/* wptUTF8.cpp - UTF8 conversation
 *      Copyright (C) 2002, 2004, 2005, 2006, 2009, 2012 Timo Schulz
 *
 * This file is part of WinPT.
 *
 * WinPT is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 * 
 * WinPT is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 */
#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#include <windows.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>

#include "wptTypes.h"
#include "wptErrors.h"


/* Byte order mark that is usually used to indicate that the following 
   data is encoded in UTF-8. */
BYTE UTF8_BOM[] = {0xEF, 0xBB, 0xBF};


/**
 * Convert the given intput string, which is encoded with the locale 
 * setting, into UTF-8 representation.
 */
char*
native_to_utf8 (const char *string)
{
    int n = MultiByteToWideChar (GetACP (), 0, string, -1, NULL, 0);
    if (n < 0)
        return NULL;

    wchar_t *result = new wchar_t[n+1];
    if (!result)
        BUG (0);

    n = MultiByteToWideChar (GetACP (), 0, string, -1, result, n);
    if (n < 0) {
        free_if_alloc (result);
        return NULL;
    }

    n = WideCharToMultiByte (CP_UTF8, 0, result, -1, NULL, 0, NULL, NULL);
    if (n < 0)
        return NULL;

    char *native = new char[n + 1];
    if (!native)
        BUG (0);
    memset(native, 0, n + 1);

    n = WideCharToMultiByte (CP_UTF8, 0, result, -1, native, n, NULL, NULL);
    if (n < 0) {
        free_if_alloc (result);
        return NULL;
    }

    free_if_alloc (result);
    return native;
}


/**
 * Convert an UTF-8 string into an UTF-16 string.
 */
wchar_t*
utf8_to_utf16(const char *string, size_t *retlen)
{
    int n = MultiByteToWideChar(CP_UTF8, 0, string, -1, NULL, 0);
    if (n < 0)
        return NULL;
    
    wchar_t *result = new wchar_t[n + 1];
    if (!result)
        BUG(0);
    
    n = MultiByteToWideChar(CP_UTF8, 0, string, -1, result, n);
    if (n < 0) {
        free_if_alloc(result);
        return NULL;
    }
    
    *retlen = n;
    return result;
}

    
/**
 * Convert the given string, which is encoded in UTF-8,
 * into the locale setting.
 */
char*
utf8_to_native (const char *string)
{
    int n = MultiByteToWideChar (CP_UTF8, 0, string, -1, NULL, 0);
    if (n < 0)
        return NULL;

    wchar_t *result = new wchar_t[n+1];
    if (!result)
        BUG (0);

    n = MultiByteToWideChar (CP_UTF8, 0, string, -1, result, n);
    if (n < 0) {
        free_if_alloc (result);
        return NULL;
    }

    n = WideCharToMultiByte (GetACP (), 0, result, -1, NULL, 0, NULL, NULL);
    if (n < 0)
        return NULL;

    char *native = new char[n + 1];
    if (!native)
        BUG (0);
    memset(native, 0, n + 1);

    n = WideCharToMultiByte (GetACP (), 0, result, -1, native, n, NULL, NULL);
    if (n < 0) {
        free_if_alloc (result);
        return NULL;
    }
    
    free_if_alloc (result);
    return native;
}


/**
 * Return -1 if the given string contains any 8-bit characters.
 * This is a helper to decide when to use UTF8 encoding.
 */
int
is_8bit_string (const char *str)
{
    for (size_t i = 0; i < strlen (str); i++) {
        if (str[i] & 0x80)
            return -1;
    }
    return 0;
}
1	twoaday	193	/* wptUTF8.cpp - UTF8 conversation
2	twoaday	456	* Copyright (C) 2002, 2004, 2005, 2006, 2009, 2012 Timo Schulz
3	twoaday	2	*
4	werner	36	* 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	twoaday	2	*/
16	werner	36	#ifdef HAVE_CONFIG_H
17			#include <config.h>
18			#endif
19
20	twoaday	2	#include <windows.h>
21	werner	36	#include <stdlib.h>
22	twoaday	2	#include <stdio.h>
23			#include <string.h>
24			#include <ctype.h>
25	werner	36
26			#include "wptTypes.h"
27	twoaday	2	#include "wptErrors.h"
28
29
30	twoaday	464	/* 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	twoaday	328	/**
36	twoaday	456	* Convert the given intput string, which is encoded with the locale
37	twoaday	328	* setting, into UTF-8 representation.
38			*/
39	twoaday	187	char*
40			native_to_utf8 (const char *string)
41	werner	36	{
42	twoaday	456	int n = MultiByteToWideChar (GetACP (), 0, string, -1, NULL, 0);
43	twoaday	187	if (n < 0)
44			return NULL;
45
46	twoaday	456	wchar_t *result = new wchar_t[n+1];
47	twoaday	187	if (!result)
48			BUG (0);
49
50			n = MultiByteToWideChar (GetACP (), 0, string, -1, result, n);
51			if (n < 0) {
52	twoaday	201	free_if_alloc (result);
53	twoaday	187	return NULL;
54	werner	36	}
55	twoaday	187
56			n = WideCharToMultiByte (CP_UTF8, 0, result, -1, NULL, 0, NULL, NULL);
57			if (n < 0)
58			return NULL;
59
60	twoaday	456	char *native = new char[n + 1];
61	twoaday	187	if (!native)
62			BUG (0);
63	twoaday	456	memset(native, 0, n + 1);
64	twoaday	187
65			n = WideCharToMultiByte (CP_UTF8, 0, result, -1, native, n, NULL, NULL);
66			if (n < 0) {
67	twoaday	201	free_if_alloc (result);
68	twoaday	187	return NULL;
69			}
70
71	twoaday	201	free_if_alloc (result);
72	twoaday	187	return native;
73	twoaday	128	}
74	werner	36
75	twoaday	185
76	twoaday	328	/**
77	twoaday	456	* 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	twoaday	328	* into the locale setting.
104			*/
105	twoaday	187	char*
106	twoaday	185	utf8_to_native (const char *string)
107	twoaday	2	{
108	twoaday	456	int n = MultiByteToWideChar (CP_UTF8, 0, string, -1, NULL, 0);
109	twoaday	185	if (n < 0)
110			return NULL;
111	twoaday	2
112	twoaday	456	wchar_t *result = new wchar_t[n+1];
113	twoaday	185	if (!result)
114			BUG (0);
115	twoaday	2
116	twoaday	185	n = MultiByteToWideChar (CP_UTF8, 0, string, -1, result, n);
117			if (n < 0) {
118	twoaday	328	free_if_alloc (result);
119	twoaday	185	return NULL;
120			}
121	twoaday	128
122	twoaday	185	n = WideCharToMultiByte (GetACP (), 0, result, -1, NULL, 0, NULL, NULL);
123			if (n < 0)
124			return NULL;
125	twoaday	2
126	twoaday	456	char *native = new char[n + 1];
127	twoaday	185	if (!native)
128			BUG (0);
129	twoaday	456	memset(native, 0, n + 1);
130	twoaday	2
131	twoaday	187	n = WideCharToMultiByte (GetACP (), 0, result, -1, native, n, NULL, NULL);
132	twoaday	185	if (n < 0) {
133	twoaday	328	free_if_alloc (result);
134	twoaday	185	return NULL;
135			}
136	twoaday	328
137			free_if_alloc (result);
138	twoaday	185	return native;
139	twoaday	2	}
140	werner	36
141
142	twoaday	328	/**
143	twoaday	456	* Return -1 if the given string contains any 8-bit characters.
144	twoaday	328	* This is a helper to decide when to use UTF8 encoding.
145			*/
146	werner	36	int
147	twoaday	193	is_8bit_string (const char *str)
148	werner	36	{
149	twoaday	328	for (size_t i = 0; i < strlen (str); i++) {
150	werner	36	if (str[i] & 0x80)
151			return -1;
152			}
153			return 0;
154	twoaday	128	}