中英混串转拼音源码

Myth丶恋晨 2022-08-03 11:48 92阅读 0赞

/* 本程序只对GB2312编码有效 */
    
    
    /* 汉字读音分界点处的码值数组 */
    static const unsigned short code_pin[] = {
        0xb0a1,0xb0a3,0xb0b0,0xb0b9,0xb0bc,0xb0c5,0xb0d7,0xb0df,0xb0ee,0xb0fa,0xb1ad,0xb1bc,0xb1c0,0xb1c6,
        0xb1de,0xb1ea,0xb1ee,0xb1f2,0xb1f8,0xb2a3,0xb2b8,0xb2c1,0xb2c2,0xb2cd,0xb2d4,0xb2d9,0xb2de,0xb2e3,
        0xb2e5,0xb2f0,0xb2f3,0xb2fd,0xb3ac,0xb3b5,0xb3bb,0xb3c5,0xb3d4,0xb3e4,0xb3e9,0xb3f5,0xb4a7,0xb4a8,
        0xb4af,0xb4b5,0xb4ba,0xb4c1,0xb4c3,0xb4cf,0xb4d5,0xb4d6,0xb4da,0xb4dd,0xb4e5,0xb4e8,0xb4ee,0xb4f4,
        0xb5a2,0xb5b1,0xb5b6,0xb5c2,0xb5c5,0xb5cc,0xb5df,0xb5ef,0xb5f8,0xb6a1,0xb6aa,0xb6ab,0xb6b5,0xb6bc,
        0xb6cb,0xb6d1,0xb6d5,0xb6de,0xb6ea,0xb6f7,0xb6f8,0xb7a2,0xb7aa,0xb7bb,0xb7c6,0xb7d2,0xb7e1,0xb7f0,
        0xb7f1,0xb7f2,0xb8c1,0xb8c3,0xb8c9,0xb8d4,0xb8dd,0xb8e7,0xb8f8,0xb8f9,0xb8fb,0xb9a4,0xb9b3,0xb9bc,
        0xb9ce,0xb9d4,0xb9d7,0xb9e2,0xb9e5,0xb9f5,0xb9f8,0xb9fe,0xbaa1,0xbaa8,0xbabb,0xbabe,0xbac7,0xbad9,
        0xbadb,0xbadf,0xbae4,0xbaed,0xbaf4,0xbba8,0xbbb1,0xbbb6,0xbbc4,0xbbd2,0xbbe7,0xbbed,0xbbf7,0xbcce,
        0xbcdf,0xbda9,0xbdb6,0xbdd2,0xbded,0xbea3,0xbebc,0xbebe,0xbecf,0xbee8,0xbeef,0xbef9,0xbfa6,0xbfaa,
        0xbfaf,0xbfb5,0xbfbc,0xbfc0,0xbfcf,0xbfd3,0xbfd5,0xbfd9,0xbfdd,0xbfe4,0xbfe9,0xbfed,0xbfef,0xbff7,
        0xc0a4,0xc0a8,0xc0ac,0xc0b3,0xc0b6,0xc0c5,0xc0cc,0xc0d5,0xc0d7,0xc0e2,0xc0e5,0xc1a9,0xc1aa,0xc1b8,
        0xc1c3,0xc1d0,0xc1d5,0xc1e1,0xc1ef,0xc1fa,0xc2a5,0xc2ab,0xc2bf,0xc2cd,0xc2d3,0xc2d5,0xc2dc,0xc2e8,
        0xc2f1,0xc2f7,0xc3a2,0xc3a8,0xc3b4,0xc3b5,0xc3c5,0xc3c8,0xc3d0,0xc3de,0xc3e7,0xc3ef,0xc3f1,0xc3f7,
        0xc3fd,0xc3fe,0xc4b1,0xc4b4,0xc4c3,0xc4ca,0xc4cf,0xc4d2,0xc4d3,0xc4d8,0xc4d9,0xc4db,0xc4dc,0xc4dd,
        0xc4e8,0xc4ef,0xc4f1,0xc4f3,0xc4fa,0xc4fb,0xc5a3,0xc5a7,0xc5ab,0xc5ae,0xc5af,0xc5b0,0xc5b2,0xc5b6,
        0xc5b7,0xc5be,0xc5c4,0xc5ca,0xc5d2,0xc5d7,0xc5de,0xc5e7,0xc5e9,0xc5f7,0xc6aa,0xc6ae,0xc6b2,0xc6b4,
        0xc6b9,0xc6c2,0xc6cb,0xc6da,0xc6fe,0xc7a3,0xc7b9,0xc7c1,0xc7d0,0xc7d5,0xc7e0,0xc7ed,0xc7ef,0xc7f7,
        0xc8a6,0xc8b1,0xc8b9,0xc8bb,0xc8bf,0xc8c4,0xc8c7,0xc8c9,0xc8d3,0xc8d5,0xc8d6,0xc8e0,0xc8e3,0xc8ed,
        0xc8ef,0xc8f2,0xc8f4,0xc8f6,0xc8f9,0xc8fd,0xc9a3,0xc9a6,0xc9aa,0xc9ad,0xc9ae,0xc9af,0xc9b8,0xc9ba,
        0xc9ca,0xc9d2,0xc9dd,0xc9e9,0xc9f9,0xcaa6,0xcad5,0xcadf,0xcba2,0xcba4,0xcba8,0xcbaa,0xcbad,0xcbb1,
        0xcbb5,0xcbb9,0xcbc9,0xcbd1,0xcbd4,0xcbe1,0xcbe4,0xcbef,0xcbf2,0xcbfa,0xcca5,0xccae,0xccc0,0xcccd,
        0xccd8,0xccd9,0xccdd,0xccec,0xccf4,0xccf9,0xccfc,0xcda8,0xcdb5,0xcdb9,0xcdc4,0xcdc6,0xcdcc,0xcdcf,
        0xcdda,0xcde1,0xcde3,0xcdf4,0xcdfe,0xcec1,0xcecb,0xcece,0xced7,0xcef4,0xcfb9,0xcfc6,0xcfe0,0xcff4,
        0xd0a8,0xd0bd,0xd0c7,0xd0d6,0xd0dd,0xd0e6,0xd0f9,0xd1a5,0xd1ab,0xd1b9,0xd1c9,0xd1ea,0xd1fb,0xd2ac,
        0xd2bb,0xd2f0,0xd3a2,0xd3b4,0xd3b5,0xd3c4,0xd3d9,0xd4a7,0xd4bb,0xd4c5,0xd4d1,0xd4d4,0xd4db,0xd4df,
        0xd4e2,0xd4f0,0xd4f4,0xd4f5,0xd4f6,0xd4fa,0xd5aa,0xd5b0,0xd5c1,0xd5d0,0xd5da,0xd5e4,0xd5f4,0xd6a5,
        0xd6d0,0xd6db,0xd6e9,0xd7a5,0xd7a7,0xd7a8,0xd7ae,0xd7b5,0xd7bb,0xd7bd,0xd7c8,0xd7d7,0xd7de,0xd7e2,
        0xd7ea,0xd7ec,0xd7f0,0xd7f2 };
    
    /* 汉字读音数组 */
    static const char *str_pin[] = {
        "a","ai","an","ang","ao","ba","bai","ban","bang","bao","bei","ben","beng","bi","bian","biao",
        "bie","bin","bing","bo","bu","ca","cai","can","cang","cao","ce","ceng","cha","chai","chan",
        "chang","chao","che","chen","cheng","chi","chong","chou","chu","chuai","chuan","chuang","chui",
        "chun","chuo","ci","cong","cou","cu","cuan","cui","cun","cuo","da","dai","dan","dang","dao",
        "de","deng","di","dian","diao","die","ding","diu","dong","dou","du","duan","dui","dun","duo",
        "e","en","er","fa","fan","fang","fei","fen","feng","fo","fou","fu","ga","gai","gan","gang",
        "gao","ge","gei","gen","geng","gong","gou","gu","gua","guai","guan","guang","gui","gun",
        "guo","ha","hai","han","hang","hao","he","hei","hen","heng","hong","hou","hu","hua","huai",
        "huan","huang","hui","hun","huo","ji","jia","jian","jiang","jiao","jie","jin","jing",
        "jiong","jiu","ju","juan","jue","jun","ka","kai","kan","kang","kao","ke","ken","keng",
        "kong","kou","ku","kua","kuai","kuan","kuang","kui","kun","kuo","la","lai","lan","lang",
        "lao","le","lei","leng","li","lia","lian","liang","liao","lie","lin","ling","liu","long","lou",
        "lu","lv","luan","lue","lun","luo","ma","mai","man","mang","mao","me","mei","men","meng",
        "mi","mian","miao","mie","min","ming","miu","mo","mou","mu","na","nai","nan","nang","nao","ne",
        "nei","nen","neng","ni","nian","niang","niao","nie","nin","ning","niu","nong","nu","nv","nuan",
        "nue","nuo","o","ou","pa","pai","pan","pang","pao","pei","pen","peng","pi","pian","piao","pie",
        "pin","ping","po","pu","qi","qia","qian","qiang","qiao","qie","qin","qing","qiong","qiu","qu",
        "quan","que","qun","ran","rang","rao","re","ren","reng","ri","rong","rou","ru","ruan","rui",
        "run","ruo","sa","sai","san","sang","sao","se","sen","seng","sha","shai","shan","shang","shao",
        "she","shen","sheng","shi","shou","shu","shua","shuai","shuan","shuang","shui","shun","shuo",
        "si","song","sou","su","suan","sui","sun","suo","ta","tai","tan","tang","tao","te","teng",
        "ti","tian","tiao","tie","ting","tong","tou","tu","tuan","tui","tun","tuo","wa","wai","wan",
        "wang","wei","wen","weng","wo","wu","xi","xia","xian","xiang","xiao","xie","xin","xing",
        "xiong","xiu","xu","xuan","xue","xun","ya","yan","yang","yao","ye","yi","yin","ying","yo",
        "yong","you","yu","yuan","yue","yun","za","zai","zan","zang","zao","ze","zei","zen","zeng",
        "zha","zhai","zhan","zhang","zhao","zhe","zhen","zheng","zhi","zhong","zhou","zhu","zhua",
        "zhuai","zhuan","zhuang","zhui","zhun","zhuo","zi","zong","zou","zu","zuan","zui","zun","zuo"};
    
    /* 数组长度 */
    static const size_t SIZE_ARRAY = sizeof(code_pin) / sizeof(short);
    
    
    #include <iostream>
    #include <string>
    
    using std::string;
    using std::cout;
    using std::endl;
    
    /* 获取一个汉字的拼音 */
    const char* get_pin(unsigned short char_zh)
    {
        size_t low = 0, high = SIZE_ARRAY - 1;
        size_t index;
        while (high - low != 1)/* 类似，但不是折半查找 */
        {
            index = (low + high) / 2;
            if (char_zh == code_pin[index]) return str_pin[index];
            if (char_zh > code_pin[index]) low = index;
            else high = index;
        }
        return str_pin[char_zh >= code_pin[high] ? high : low];   
    }
    
    /* 将中英混合字符串转化成拼音形式 */
    string str_to_pin(string const &input)
    {
        string result ;// 返回值
        unsigned short char_zh;// 迭代汉字
        const size_t INPUT_LEN = input.length();
        unsigned char high_byte, low_byte;// 汉字的高低字节
        for (size_t i = 0; i < INPUT_LEN; ++i)
        {
            high_byte = input[i];
            if (high_byte < 0x80) result.append(1, high_byte);
            else
            {
                low_byte = input[++i];
                char_zh = (high_byte << 8 ) + low_byte;
                result.append(get_pin(char_zh));
            }
        }
        return result;
    }
    
    /* 将中英混合字符串转化成拼音形式，每个拼音后跟一个空格 */
    string str_to_pin_space(string const &input)
    {
        string result;// 返回值
        unsigned short char_zh;// 迭代汉字
        const size_t INPUT_LEN = input.length();
        unsigned char high_byte, low_byte;// 汉字的高低字节
        for (size_t i = 0; i < INPUT_LEN; ++i)
        {
            high_byte = input[i];
            if(high_byte < 0x80)
            {
                if (i > 0 && input[i-1] < 0) result.append(1, ' ');
                result.append(1, high_byte);
            }
            else
            {
                if(i > 0) result.append(1, ' ');
                low_byte = input[++i];
                char_zh = (high_byte << 8 ) + low_byte ;
                result.append(get_pin(char_zh));
            }
        }
        return result;
    }
    
    /* 
       将中英及数字混合串转化成拼音，且每一连续部分之间放置一个空格。
       输入必须满足只有上述三种字符的情况，正确性需要由调用端保证。 
    */
    string str_to_pin_space_(string const &input)
    {
        string result(1, ' ') ;// 返回值，以一个空格初始化
        unsigned short char_zh;// 迭代汉字
        const size_t INPUT_LEN = input.length();
        unsigned char high_byte, low_byte;// 汉字的高低字节
        for (size_t i = 0; i < INPUT_LEN; ++i)
        {
            high_byte = input[i] ;
            if (high_byte < 58)// 数字字符
            {
                if (i > 0 && (input[i-1] < 0 || input[i-1] > 57))
                {
                    result.append(1, ' ');
                }
                result.append(1, high_byte);
            }
            else if (high_byte > 64 && high_byte < 123)// 英文字符
            {
                if (i > 0 && (input[i-1] < 0 || input[i-1] < 58))
                {
                    result.append(1, ' ');
                }
                result.append(1, high_byte);
            }
            else// 汉字字符
            {
                if(i > 0) result.append(1, ' ');
                low_byte = input[++i];// 低字节被赋值
                char_zh = (high_byte << 8 ) + low_byte ;
                result.append(get_pin(char_zh));
            }
        }
        return result;
    }
    
    /* 测试代码 */
    int main()
    {
        cout << str_to_pin_space_("zhonghua人民dfd啊a152左边35gdaf共和国") << endl;
        return 0;
    }