Encoding: utf8, UCS...

I recently learned encoding.

The following addresses can be used to learn related knowledge.

Http://dev.csdn.net/develop/article/69/69883.shtm

Http://dev.csdn.net/develop/article/72/72888.shtm

This section describes the UTF-8 encoding.

When the content to be expressed is 7 bits, use one byte: 0 ********. The first 0 is the flag, the remaining space can represent the content of ASCII 0-127.
When the content to be represented is between 8 and 11 bits, two bytes are used: 110*10*10 of the First and Second bytes is the flag.
When the content to be represented is 12 to 16 bits, it uses three Bytes: 1110*10*10 * Like the above, 1110 of the first byte and 10 of the second and third byte are flags, and the remaining space can represent Chinese characters.
And so on:
Four bytes: 11110*10*10*10*10 ******
Five Bytes: 111110*10*10*10*10*10*10 ******
Six Bytes: 1111110*10*10*10*10*10*10*10 ******
........................................ .....

I wrote the following code for conversion:

Conversion between UCs and utf8

Int ucs2utf8 (wchar_t * pucs, unsigned char * putf8)
{
Int ucslen = 0, utf8len = 0, I;
Unsigned char * ptemputf8 = NULL;
Ucslen = wcslen (pucs );

If (pucs = NULL | putf8 = NULL)
Return-1;
 
Ptemputf8 = putf8;
For (I = 0; I <ucslen; I ++)
{
If (pucs [I] <= 0x007f) // 1 byte 0 xxxxxxx
{
* (Ptemputf8 ++) = lobyte (pucs [I]);
Utf8len ++;
}
Else if (pucs [I] <= 0x07ff) // 2 bytes 110 XXXXX 10 xxxxxx
{
* (Ptemputf8 ++) = hibyte (pucs [I] <2) & 0x3f | 0xc0;
* (Ptemputf8 ++) = lobyte (pucs [I] & 0x3f) | 0x80;
Utf8len + = 2;
}
Else // 3 bytes 1110 XXXX 10 xxxxxx 10 xxxxxx
{
* (Ptemputf8 ++) = hibyte (pucs [I]> 4) | 0xe0;
* (Ptemputf8 ++) = hibyte (pucs [I] <2) & 0x3f | 0x80;
* (Ptemputf8 ++) = lobyte (pucs [I]) & 0x3f | 0x80;
Utf8len + = 3;
}
}
 
Return utf8len;
}
Int utf82ucs (unsigned char * putf8, wchar_t * pucs)
{
Int ucslen = 0, I;
Unsigned char * ptempucs = NULL;
Unsigned char * ptemputf8 = NULL;

If (pucs = NULL | putf8 = NULL)
Return-1;
Ucslen = multibytetowidechar (cp_utf8, 0, putf8,-1, null, 0 );
Ucslen --;
Ptempucs = (char *) pucs;
Ptemputf8 = putf8;
For (I = 0; I <ucslen; I ++)
{
If (* ptemputf8) <= 0x7f) // 1 byte
{
* (Ptempucs + 1) = 0x00;
* Ptempucs = * (ptemputf8 ++ );
Ptempucos + = 2;
}
Else if (* ptemputf8)> = 0xc0 & (* ptemputf8) <= 0xdf) // 2 bytes
{
* (Ptempucs + 1) = (* ptemputf8)> 2) & 0x07;
* Ptempucs = (* ptemputf8) <6) | (* (ptemputf8 + 1) & 0x3f );
Ptemputf8 + = 2;
Ptempucos + = 2;
}
Else // 3 bytes
{
* (Ptempucs + 1) = (* ptemputf8) <4) | (* (ptemputf8 + 1)> 2) & 0x0f );
Ptemputf8 ++;
* Ptempucs = (* ptemputf8) <6) | (* (ptemputf8 + 1) & 0x3f );
Ptemputf8 + = 2;
Ptempucos + = 2;
}
}
Return ucslen;
}

Other encoding and UCS Conversion

Int toucs (unsigned char * P, wchar_t * pucs, int codePage)
{
Int Len = 0;

If (pucs = NULL | P = NULL)
Return-1;
Len = multibytetowidechar (codePage, 0, P,-1, null, 0 );
Multibytetowidechar (codePage, 0, P,-1, pucs, Len );
Return Len;
}

Int ucsto (wchar_t * pucs, char * P, int codePage)
{
Int Len = 0;
 
If (pucs = NULL | pbig5 = NULL)
Return-1;

Len = widechartomultibyte (codePage, 0, pucs,-1, null, 0, null, null );
Widechartomultibyte (codePage, 0, pucs,-1, P, Len, null, null );
Len --;
Return Len;
}

Here codePage is defined as follows in msdn

Bit	Code Page	Description
ANSI
0	1252	Latin 1
1	1250	Latin 2: Eastern Europe
2	1251	Cyrillic
3	1253	Greek
4	1254	Turkish
5	1255	Hebrew
6	1256	Arabic
7	1257	Baltic
8	1258	Vietnam
9-15		Reserved For ANSI
ANSI And OEM
16	874	Thai
17	932	Japan, shift-JIS
18	936	English: Simplified chars-PRC and Singapore
19	949	Korean uniied hangeul code (hangeul tonghabhyung code)
20	950	Chinese: Traditional chars-Hong Kong SAR, PRC and Taiwan
21	1361	Korean (johab)
22-29		Reserved for alternate ANSI and OEM
30-31		Reserved by system.
OEM
32-46		Reserved for OEM
47	1258	Vietnam
48	869	IBM Greek
49	866	MS-DOS Russian
50	865	MS-DOS Nordic
51	864	Arabic
52	863	MS-DOS (Canadian French)
53	862	Hebrew
54	861	MS-DOS Icelandic
55	860	MS-DOS (Portuguese)
56	857	IBM Turkish
57	855	IBM Cyrillic; primarily Russian
58	852	Latin 2
59	775	Baltic
60	737	Greek; former 437g
61	708	Arabic; ASMO 708
62	850	Western European/Latin 1
63	437	Us