char*
find_without_case (const char *content, const char *pkeywords) //如果是中文，原样输出 英文 则查找其在原文中到底具体字符的大小写
{
char *back = NULL;
if((is_english(pkeywords)))
{
back = get_exact_whatis(content, pkeywords);
}
return back;
} /* ----- end of function get_change_by_case ----- */
char *create_tidy_str(const char *fin_path, char **pbuf, int* plen)
{
FILE *fp_in, *fp_out;
fp_in = fopen(fin_path,"rb");
if(fp_in == NULL)
{
return;
}
fseek(fp_in, 0L, SEEK_END);
int size = ftell(fp_in);
fseek(fp_in, 0L, SEEK_SET);
char *buf,*buf2;
buf = (char*)malloc(size+1);
buf2 = (char*)malloc(size+1);
int len = fread(buf,1,size,fp_in);
buf[len] = '\0';
bzero(buf2,size+1);
char *p = buf;
char *p2 = buf2;
char *start = buf;
int n;
// 汉字或汉字之后EN_LENGHT个英文之内保留
do
{
// TODO is_chinese -> !is_ascii
if(is_chinese(p))
{
write_chinese(&p, &p2);
start = p;
}
else
{
//printf("end:0x%x,p:0x%x\n",buf+len,p);
// 非英文不保留,英文则保留有限位数
// TODO 判断英文不正确 会有一个英文多出来
if(!is_english(p))
{
start = buf;
p = forward_a_char(p);
}
else if(get_word_n(start, p - start) <= EN_LENGHT)
{
n = get_word_n(p, 1);
memcpy(p2, p, n);
p += n;
p2 += n;
}
else if(get_word_n(start, p - start) == EN_LENGHT + 1)
{
addsep(&p2);
p = forward_a_char(p);
}
else
{
p = forward_a_char(p);
}
}
}while(*p != '\0');
free(buf);
fclose(fp_in);
*pbuf = buf2;
*plen = strlen(buf2);
return *pbuf;
}
