C/c ++ uses Unicode and UTF8 to process Chinese strings to solve garbled characters

1. Description

If you do system programming on windows, you will inevitably encounter the problem of processing Chinese strings. Most of the time, Chinese characters are displayed in multi-byte encoding. To achieve better compatibility or some special requirements (such as displaying on a webpage .) It is often necessary to convert it to unicode or utf8 format.

2. Sample code

2.1 convert a Chinese string to Unicode

/*************************************** *********************************
* Int CN2Unicode (char * input, wchar_t * output)
* Function: convert Chinese characters to unicode characters
* Parameter: input, a Chinese string, output, and Unicode string
*
**************************************** *********************************/
Int CN2Unicode (char * input, wchar_t * output)
{
Int len = strlen (input );

// Wchar_t * out = (wchar_t *) malloc (len * sizeof (wchar_t ));

Len = MultiByteToWideChar (CP_ACP, 0, input,-1, output, MAX_PATH );

Return 1;
}

2.2 convert a Chinese string to utf8

/*************************************** *********************************
* Int CN2Utf8 (char * input, char * output)
* Function: converts a Chinese string to a UTF-8 string.
* Parameter: input, a Chinese string, output, and utf8 string
*
**************************************** ********************************/
Int CN2Utf8 (char * input, char * output)
{
Int len;
Wchar_t * out = (wchar_t *) malloc (len * sizeof (wchar_t ));

Len = MultiByteToWideChar (CP_ACP, 0, input,-1, out, strlen (input) + 1 );
WideCharToMultiByte (CP_UTF8, 0, out, wcslen (out), output, len, NULL, NULL );

Return 1;
}


C/C ++ Unicode to Utf8, Ansi to Unicode, and Ansi to Utf8

Sometimes you need to convert the ansi file content to utf8 encoding. After reading a row, convert the ansi string to utf8 and then write it into the file.


# Include <stdio. h>
# Include <stdlib. h>
# Include <string. h>
# Include <windows. h>
# Include <assert. h>

Char * Unicode2Utf8 (const char * unicode)
{
Int len;
Len = WideCharToMultiByte (CP_UTF8, 0, (const wchar_t *) unicode,-1, NULL, 0, NULL, NULL );
Char * szUtf8 = (char *) malloc (len + 1 );
Memset (szUtf8, 0, len + 1 );
WideCharToMultiByte (CP_UTF8, 0, (const wchar_t *) unicode,-1, szUtf8, len, NULL, NULL );
Return szUtf8;
}

Char * Ansi2Unicode (const char * str)
{
Int dwUnicodeLen = MultiByteToWideChar (CP_ACP, 0, str,-1, NULL, 0 );
If (! DwUnicodeLen)
    {
Return strdup (str );
    }
Size_t num = dwUnicodeLen * sizeof (wchar_t );
Wchar_t * pwText = (wchar_t *) malloc (num );
Memset (pwText, 0, num );
MultiByteToWideChar (CP_ACP, 0, str,-1, pwText, dwUnicodeLen );
Return (char *) pwText;
}

Char * ConvertAnsiToUtf8 (const char * str)
{
Char * unicode = Ansi2Unicode (str );
Char * utf8 = Unicode2Utf8 (unicode );
Free (unicode );
Return utf8;
}

Int main (int argc, char * argv [])
{
Printf ("Hello, world \ n ");
// 1. Construct an ansi file with the content "Chinese abc". Check the hex encoding.
// Ansi: D6 D0 CE C4 61 62 63
// Utf8: E4 B8 AD E6 96 87 61 62 63
Char ansi [] = {0xD6, 0xD0, 0xCE, 0xC4, 0x61,0x62,0x63,0 };
Char utf8 [] = {0xE4, 0xB8, 0xAD, 0xE6, 0x96,0x87,0x61,0x62,0x63,0 };
Char * str = ConvertAnsiToUtf8 (ansi );
Assert (! Strcmp (str, utf8 ));
Free (str );
Return 0;
}