358 lines
6.1 KiB
C
358 lines
6.1 KiB
C
#include "char_encode.h"
|
||
#include "string.h"
|
||
#include "unigbk_table.h"
|
||
#include "mymem.h"
|
||
|
||
|
||
|
||
|
||
|
||
//Unicode转utf-8，返回值是下一个uni编码的指针
|
||
//本函数只能转换汉字，即输入的汉字固定为2个字节
|
||
//
|
||
//参数：uni_in，要转码的Unicode编码地址，高字节在前
|
||
//参数：utf8_out，转码后输出的utf8编码存储地址的指针，在转码后地址自动向后移编
|
||
//返回值：下一个Unicode编码地址
|
||
u8 *uni2utf8 (const u8 *uni_in,u8 **utf8_out)
|
||
{
|
||
u16 c=0;
|
||
if ((uni_in)&&(c=(uni_in[0]<<8)|uni_in[1],c))
|
||
{
|
||
if (c<0x80)
|
||
{
|
||
**utf8_out=c;
|
||
(*utf8_out)++;
|
||
return (u8*)uni_in+2;
|
||
}
|
||
else
|
||
{
|
||
(*utf8_out)[0]=0xe0;
|
||
(*utf8_out)[0]|=uni_in[0]>>4;
|
||
(*utf8_out)[1]=0x80;
|
||
(*utf8_out)[1]|=((uni_in[0]<<2)|(uni_in[1]>>6))&0x3f;
|
||
(*utf8_out)[2]=0x80;
|
||
(*utf8_out)[2]|=(uni_in[1])&0x3f;
|
||
(*utf8_out)+=3;
|
||
return (u8*)uni_in+2;
|
||
}
|
||
}
|
||
return 0;
|
||
}
|
||
|
||
|
||
|
||
//Unicode转utf-8，
|
||
void uni2utf8_str (u8 *uni_in,u8 *utf8_out)
|
||
{
|
||
u8 *pt_char_uni=uni_in;
|
||
u8 *pt_char_utf8=utf8_out;
|
||
|
||
//Unicode转UTF8
|
||
while(pt_char_uni)
|
||
{
|
||
pt_char_uni=uni2utf8(pt_char_uni,&pt_char_utf8);
|
||
}
|
||
pt_char_utf8[0]=0;
|
||
}
|
||
|
||
|
||
|
||
|
||
|
||
|
||
//utf-8转Unicode，返回值是下一个utf8编码的指针
|
||
//本函数只能转换汉字，即输入的汉字固定为3个字节
|
||
//
|
||
//参数：utf8_in，要转码的UTF8编码地址，高字节在前
|
||
//参数：uni_out，转码后输出的uni编码存储地址的指针，在转码后地址自动向后移编
|
||
//返回值：下一个utf8编码地址
|
||
u8 *utf82uni (const u8 *uft8_in,u8 **uni_out)
|
||
{
|
||
if ((uft8_in)&&(*uft8_in))
|
||
{
|
||
if (uft8_in[0]<0x80)
|
||
{
|
||
(*uni_out)[0]=0;
|
||
(*uni_out)[1]=*uft8_in;
|
||
(*uni_out)+=2;
|
||
return (u8*)uft8_in+1;
|
||
}
|
||
else
|
||
{
|
||
(*uni_out)[0]=uft8_in[0]<<4;
|
||
(*uni_out)[0]|=(uft8_in[1]>>2)&0x0f;
|
||
(*uni_out)[1]=(uft8_in[1]<<6);
|
||
(*uni_out)[1]|=(uft8_in[2])&0x3f;
|
||
(*uni_out)+=2;
|
||
return (u8*)uft8_in+3;
|
||
}
|
||
}
|
||
return 0;
|
||
}
|
||
|
||
|
||
|
||
|
||
//UTF8转Unicode
|
||
void utf82uni_str (u8 *uft8_in,u8 *uni_out)
|
||
{
|
||
u8 *pt_char_uni=uni_out;
|
||
u8 *pt_char_utf8=uft8_in;
|
||
|
||
//UTF8转Unicode
|
||
while(pt_char_utf8)
|
||
{
|
||
pt_char_utf8=utf82uni(pt_char_utf8,&pt_char_uni);
|
||
}
|
||
pt_char_uni[0]=0;
|
||
pt_char_uni[1]=0;
|
||
}
|
||
|
||
|
||
|
||
|
||
static int g_unigbk_size=0;
|
||
|
||
|
||
|
||
//GBK编码转Unicode编码
|
||
//高字节在前
|
||
u8 *gbk2uni (u8 *gbk_in,u8 **uni_out)
|
||
{
|
||
u16 t[2];
|
||
u16 c;
|
||
u32 i, li, hi;
|
||
u16 n;
|
||
unsigned int cout;
|
||
u32 gbk2uni_offset=0;
|
||
|
||
if (gbk_in==0||*gbk_in==0) return 0;
|
||
if (*gbk_in < 0x80)
|
||
{
|
||
(*uni_out)[0]=0; //输出高字节在前
|
||
(*uni_out)[1]=*gbk_in;
|
||
(*uni_out)+=2;
|
||
return gbk_in+1;
|
||
}
|
||
else
|
||
{
|
||
c=(gbk_in[0]<<8)|gbk_in[1];
|
||
if(!g_unigbk_size)//如果没打开UNIGBK.BIN.
|
||
{
|
||
g_unigbk_size=unigbk_open();
|
||
}
|
||
gbk2uni_offset=g_unigbk_size/2;
|
||
if(g_unigbk_size)//存在
|
||
{
|
||
/* Unicode to OEMCP */
|
||
hi=g_unigbk_size/2;//对半开.
|
||
hi =hi / 4 - 1;
|
||
li = 0;
|
||
for (n = 16; n; n--)
|
||
{
|
||
i = li + (hi - li) / 2;
|
||
cout=unigbk_read(i*4+gbk2uni_offset,&t,4);
|
||
if (c == t[0]) break;
|
||
if (c > t[0])li = i;
|
||
else hi = i;
|
||
}
|
||
c = n ? t[1] : 0;
|
||
}else c=0;
|
||
(*uni_out)[0]=c>>8; //输出高字节在前
|
||
(*uni_out)[1]=c&0xff;
|
||
*uni_out+=2;
|
||
return gbk_in+2;
|
||
}
|
||
//return 0;
|
||
}
|
||
|
||
|
||
|
||
|
||
|
||
|
||
//Unicode编码转GBK编码
|
||
//高字节在前
|
||
u8 *uni2gbk (u8 *uni_in,u8 **gbk_out)
|
||
{
|
||
u16 t[2];
|
||
u16 c;
|
||
u32 i, li, hi;
|
||
u16 n;
|
||
unsigned int cout;
|
||
u32 gbk2uni_offset=0;
|
||
|
||
if (uni_in==0||(c=(uni_in[0]<<8)|uni_in[1],c==0)) return 0;
|
||
if (c < 0x80)
|
||
{
|
||
(*gbk_out)[0]=c;
|
||
(*gbk_out)+=1;
|
||
return uni_in+2;
|
||
}
|
||
else
|
||
{
|
||
if(!g_unigbk_size)//如果没打开UNIGBK.BIN.
|
||
{
|
||
g_unigbk_size=unigbk_open();
|
||
}
|
||
gbk2uni_offset=0;
|
||
//因为在编码表文件中是低字节在前，这里重新指定c
|
||
//c=(uni_in[1]<<8)|uni_in[0];
|
||
if(g_unigbk_size)//存在
|
||
{
|
||
/* Unicode to OEMCP */
|
||
hi=g_unigbk_size/2;//对半开.
|
||
hi =hi / 4 - 1;
|
||
li = 0;
|
||
for (n = 16; n; n--)
|
||
{
|
||
i = li + (hi - li) / 2;
|
||
cout=unigbk_read(i*4+gbk2uni_offset,&t,4);
|
||
if (c == t[0]) break;
|
||
if (c > t[0])li = i;
|
||
else hi = i;
|
||
}
|
||
c = n ? t[1] : 0;
|
||
}else c=0;
|
||
(*gbk_out)[0]=c>>8; //输出高字节在前
|
||
(*gbk_out)[1]=c&0xff;
|
||
*gbk_out+=2;
|
||
return uni_in+2;
|
||
}
|
||
//return 0;
|
||
}
|
||
|
||
|
||
|
||
|
||
|
||
|
||
//GBK转Unicode
|
||
void gbk2uni_str (u8 *gbk_in,u8 *uni_out)
|
||
{
|
||
u8 *pt_char_gbk=gbk_in;
|
||
u8 *pt_char_uni=uni_out;
|
||
|
||
//GBK转Unicode
|
||
while(pt_char_gbk)
|
||
{
|
||
pt_char_gbk=gbk2uni(pt_char_gbk,&pt_char_uni);
|
||
}
|
||
pt_char_uni[0]=0;
|
||
pt_char_uni[1]=0;
|
||
}
|
||
|
||
|
||
|
||
|
||
|
||
|
||
//Unicode编码转GBK编码
|
||
//高字节在前
|
||
void uni2gbk_str (u8 *uni_in,u8 *gbk_out)
|
||
{
|
||
u8 *pt_char_gbk=gbk_out;
|
||
u8 *pt_char_uni=uni_in;
|
||
|
||
//Unicode转GBK
|
||
while (pt_char_uni)
|
||
{
|
||
pt_char_uni=uni2gbk(pt_char_uni,&pt_char_gbk);
|
||
}
|
||
pt_char_gbk[0]=0;
|
||
}
|
||
|
||
|
||
//GBK转UTF8
|
||
void gbk2utf8_str (u8 *gbk_in,u8 *utf8_out)
|
||
{
|
||
int str_size=strlen((const char *)gbk_in);
|
||
u8 *char_uni=mymalloc(str_size*3);
|
||
gbk2uni_str (gbk_in,char_uni);
|
||
uni2utf8_str (char_uni,utf8_out);
|
||
myfree(char_uni);
|
||
}
|
||
|
||
|
||
//UTF8转GBK
|
||
void utf82gbk_str (u8 *utf8_in,u8 *gbk_out)
|
||
{
|
||
int str_size=strlen((const char *)utf8_in);
|
||
u8 *char_uni=mymalloc(str_size*3);
|
||
utf82uni_str (utf8_in,char_uni);
|
||
uni2gbk_str (char_uni,gbk_out);
|
||
myfree(char_uni);
|
||
}
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
//汉字编码转化测试
|
||
//返回值
|
||
//0，测试成功，非0失败
|
||
int char_encode_test (char *str_input)
|
||
{
|
||
int str_size=strlen(str_input);
|
||
u8 *char_gbk=mymalloc (str_size*3);
|
||
u8 *char_uni=mymalloc (str_size*3);
|
||
u8 *char_utf8=mymalloc (str_size*3);
|
||
mymemset(char_gbk,0,str_size*3);
|
||
mymemset(char_uni,0,str_size*3);
|
||
mymemset(char_utf8,0,str_size*3);
|
||
u8 *pt_char_gbk=char_gbk;
|
||
u8 *pt_char_uni=char_uni;
|
||
u8 *pt_char_utf8=char_utf8;
|
||
|
||
mymemcpy (char_gbk,str_input,str_size);
|
||
|
||
//GBK转Unicode
|
||
while(pt_char_gbk)
|
||
{
|
||
pt_char_gbk=gbk2uni(pt_char_gbk,&pt_char_uni);
|
||
}
|
||
mymemset(char_gbk,0,str_size*3);
|
||
pt_char_gbk=char_gbk;
|
||
pt_char_uni=char_uni;
|
||
pt_char_utf8=char_utf8;
|
||
|
||
//Unicode转UTF8
|
||
while(pt_char_uni)
|
||
{
|
||
pt_char_uni=uni2utf8(pt_char_uni,&pt_char_utf8);
|
||
}
|
||
mymemset(char_uni,0,str_size*3);
|
||
pt_char_gbk=char_gbk;
|
||
pt_char_uni=char_uni;
|
||
pt_char_utf8=char_utf8;
|
||
|
||
//UTF8转Unicode
|
||
while(pt_char_utf8)
|
||
{
|
||
pt_char_utf8=utf82uni(pt_char_utf8,&pt_char_uni);
|
||
}
|
||
pt_char_gbk=char_gbk;
|
||
pt_char_uni=char_uni;
|
||
pt_char_utf8=char_utf8;
|
||
|
||
//Unicode转GBK
|
||
while (pt_char_uni)
|
||
{
|
||
pt_char_uni=uni2gbk(pt_char_uni,&pt_char_gbk);
|
||
}
|
||
|
||
int ret=strcmp((const char *)char_gbk,str_input);
|
||
myfree(char_gbk);
|
||
myfree(char_uni);
|
||
myfree(char_utf8);
|
||
return ret;
|
||
}
|
||
|
||
|
||
|
||
|
||
|
||
|