获取汉字的首字母

最新推荐文章于 2022-02-23 15:02:25 发布

gaopingli

最新推荐文章于 2022-02-23 15:02:25 发布

阅读量234

点赞数

文章标签： null c 算法

本文链接：https://blog.csdn.net/gaopingli/article/details/5223981

版权

为了实现基于首字母的查询，研究了下汉字获取首字母的算法，实现的代码如下：

///<定义 bool

typedef char bool;

#define TRUE 1

#define FALSE 1

static bool In(um_wchar   start,   um_wchar   end,   um_wchar   code)
{
    if (code   >=   start   &&   code   <=   end)
    {
        return   TRUE;
    }
    return   FALSE;
}

static char   convertToAlpha(wchar   n)
{
    if   (In(0xB0A1,0xB0C4,n))   return   'A';
    if   (In(0XB0C5,0XB2C0,n))   return   'B';
    if   (In(0xB2C1,0xB4ED,n))   return   'C';
    if   (In(0xB4EE,0xB6E9,n))   return   'D';
    if   (In(0xB6EA,0xB7A1,n))   return   'E';
    if   (In(0xB7A2,0xB8c0,n))   return   'F';
    if   (In(0xB8C1,0xB9FD,n))   return   'G';
    if   (In(0xB9FE,0xBBF6,n))   return   'H';
    if   (In(0xBBF7,0xBFA5,n))   return   'J';
    if   (In(0xBFA6,0xC0AB,n))   return   'K';
    if   (In(0xC0AC,0xC2E7,n))   return   'L';
    if   (In(0xC2E8,0xC4C2,n))   return   'M';
    if   (In(0xC4C3,0xC5B5,n))   return   'N';
    if   (In(0xC5B6,0xC5BD,n))   return   'O';
    if   (In(0xC5BE,0xC6D9,n))   return   'P';
    if   (In(0xC6DA,0xC8BA,n))   return   'Q';
    if   (In(0xC8BB,0xC8F5,n))   return   'R';
    if   (In(0xC8F6,0xCBF0,n))   return   'S';
    if   (In(0xCBFA,0xCDD9,n))   return   'T';
    if   (In(0xCDDA,0xCEF3,n))   return   'W';
    if   (In(0xCEF4,0xD188,n))   return   'X';
    if   (In(0xD1B9,0xD4D0,n))   return   'Y';
    if   (In(0xD4D1,0xD7F9,n))   return   'Z';
    return   '/0';
}

char* GetAlpha(char* gbkStr)
{

    char   chr[3];
    wchar   wchr   =   0;
    char*    alphaStr = UM_NULL;
    int       len;
    int         nIndex = 0; //首字母数组的长度索引
   int         i;

    if (!gbkStr)
    {
        return NULL;
    }
    len = strlen(gbkStr) + 1;
    if (len > 0)
    {
        alphaStr = malloc(len);
        if (alphaStr)
        {
            memset(alphaStr, 0x00, len);
        }

    }

    for (i = 0; i< len - 1;)
    {
        char tmpchar = '/0';

        if (gbkStr[i] > 0 && gbkStr[i] < 128) //非汉字
        {
            if (gbkStr[i] >= 'a' && gbkStr[i] <= 'z')
            {
                tmpchar = (char)(gbkStr[i] - 'a' + 'A');
                alphaStr[nIndex++] = tmpchar;
            }
            if (gbkStr[i] >= 'A' && gbkStr[i] <= 'Z')
            {
                tmpchar = gbkStr[i];
                alphaStr[nIndex++] = tmpchar;
            }
            ///<数字
            if (gbkStr[i] >= '0' && gbkStr[i] <= '9')
            {
                tmpchar = gbkStr[i];
                alphaStr[nIndex++] = tmpchar;
            }
            i++;
        }
        else //汉字
        {
            memset(chr,   0x00,   sizeof(char));
            chr[0]   =   gbkStr[i++];
            chr[1]   =   gbkStr[i++];
            chr[2]   =   '/0';

            wchr   =   0;
            wchr   =   (chr[0]   &   0xff)   <<   8;
            wchr   |= (chr[1]   &   0xff);

            tmpchar = convertToAlpha(wchar);
            if(tmpchar != '/0')
            {
                alphaStr[nIndex++] = tmpchar;
            }
        }
    }
    return alphaStr;
}