C++ 将汉字转换成汉语拼音全拼

#include <string>
using std::string;

string name[] = { "zuo", "zun", "zui", "zuan", "zu", "zou",
        "zong", "zi", "zhuo", "zhun", "zhui", "zhuang", "zhuan", "zhuai",
        "zhua", "zhu", "zhou", "zhong", "zhi", "zheng", "zhen", "zhe",
        "zhao", "zhang", "zhan", "zhai", "zha", "zeng", "zen", "zei", "ze",
        "zao", "zang", "zan", "zai", "za", "yun", "yue", "yuan", "yu",
        "you", "yong", "yo", "ying", "yin", "yi", "ye", "yao", "yang",
        "yan", "ya", "xun", "xue", "xuan", "xu", "xiu", "xiong", "xing",
        "xin", "xie", "xiao", "xiang", "xian", "xia", "xi", "wu", "wo",
        "weng", "wen", "wei", "wang", "wan", "wai", "wa", "tuo", "tun",
        "tui", "tuan", "tu", "tou", "tong", "ting", "tie", "tiao", "tian",
        "ti", "teng", "te", "tao", "tang", "tan", "tai", "ta", "suo",
        "sun", "sui", "suan", "su", "sou", "song", "si", "shuo", "shun",
        "shui", "shuang", "shuan", "shuai", "shua", "shu", "shou", "shi",
        "sheng", "shen", "she", "shao", "shang", "shan", "shai", "sha",
        "seng", "sen", "se", "sao", "sang", "san", "sai", "sa", "ruo",
        "run", "rui", "ruan", "ru", "rou", "rong", "ri", "reng", "ren",
        "re", "rao", "rang", "ran", "qun", "que", "quan", "qu", "qiu",
        "qiong", "qing", "qin", "qie", "qiao", "qiang", "qian", "qia",
        "qi", "pu", "po", "ping", "pin", "pie", "piao", "pian", "pi",
        "peng", "pen", "pei", "pao", "pang", "pan", "pai", "pa", "ou", "o",
        "nuo", "nue", "nuan", "nv", "nu", "nong", "niu", "ning", "nin",
        "nie", "niao", "niang", "nian", "ni", "neng", "nen", "nei", "ne",
        "nao", "nang", "nan", "nai", "na", "mu", "mou", "mo", "miu",
        "ming", "min", "mie", "miao", "mian", "mi", "meng", "men", "mei",
        "me", "mao", "mang", "man", "mai", "ma", "luo", "lun", "lue",
        "luan", "lv", "lu", "lou", "long", "liu", "ling", "lin", "lie",
        "liao", "liang", "lian", "lia", "li", "leng", "lei", "le", "lao",
        "lang", "lan", "lai", "la", "kuo", "kun", "kui", "kuang", "kuan",
        "kuai", "kua", "ku", "kou", "kong", "keng", "ken", "ke", "kao",
        "kang", "kan", "kai", "ka", "jun", "jue", "juan", "ju", "jiu",
        "jiong", "jing", "jin", "jie", "jiao", "jiang", "jian", "jia",
        "ji", "huo", "hun", "hui", "huang", "huan", "huai", "hua", "hu",
        "hou", "hong", "heng", "hen", "hei", "he", "hao", "hang", "han",
        "hai", "ha", "guo", "gun", "gui", "guang", "guan", "guai", "gua",
        "gu", "gou", "gong", "geng", "gen", "gei", "ge", "gao", "gang",
        "gan", "gai", "ga", "fu", "fou", "fo", "feng", "fen", "fei",
        "fang", "fan", "fa", "er", "en", "e", "duo", "dun", "dui", "duan",
        "du", "dou", "****", "diu", "ding", "die", "diao", "dian", "di",
        "deng", "de", "dao", "dang", "dan", "dai", "da", "cuo", "cun",
        "cui", "cuan", "cu", "cou", "cong", "ci", "chuo", "chun", "chui",
        "chuang", "chuan", "chuai", "chu", "chou", "chong", "chi", "cheng",
        "chen", "che", "chao", "chang", "chan", "chai", "cha", "ceng",
        "ce", "cao", "cang", "can", "cai", "ca", "bu", "bo", "bing", "bin",
        "bie", "biao", "bian", "bi", "beng", "ben", "bei", "bao", "bang",
        "ban", "bai", "ba", "ao", "ang", "an", "ai", "a" };
int code[] = { -10254, -10256, -10260, -10262, -10270,
        -10274, -10281, -10296, -10307, -10309, -10315, -10322, -10328,
        -10329, -10331, -10519, -10533, -10544, -10587, -10764, -10780,
        -10790, -10800, -10815, -10832, -10838, -11014, -11018, -11019,
        -11020, -11024, -11038, -11041, -11045, -11052, -11055, -11067,
        -11077, -11097, -11303, -11324, -11339, -11340, -11358, -11536,
        -11589, -11604, -11781, -11798, -11831, -11847, -11861, -11867,
        -12039, -12058, -12067, -12074, -12089, -12099, -12120, -12300,
        -12320, -12346, -12359, -12556, -12585, -12594, -12597, -12607,
        -12802, -12812, -12829, -12831, -12838, -12849, -12852, -12858,
        -12860, -12871, -12875, -12888, -13060, -13063, -13068, -13076,
        -13091, -13095, -13096, -13107, -13120, -13138, -13147, -13318,
        -13326, -13329, -13340, -13343, -13356, -13359, -13367, -13383,
        -13387, -13391, -13395, -13398, -13400, -13404, -13406, -13601,
        -13611, -13658, -13831, -13847, -13859, -13870, -13878, -13894,
        -13896, -13905, -13906, -13907, -13910, -13914, -13917, -14083,
        -14087, -14090, -14092, -14094, -14097, -14099, -14109, -14112,
        -14122, -14123, -14125, -14135, -14137, -14140, -14145, -14149,
        -14151, -14159, -14170, -14345, -14353, -14355, -14368, -14379,
        -14384, -14399, -14407, -14429, -14594, -14630, -14645, -14654,
        -14663, -14668, -14670, -14674, -14678, -14857, -14871, -14873,
        -14882, -14889, -14894, -14902, -14908, -14914, -14921, -14922,
        -14926, -14928, -14929, -14930, -14933, -14937, -14941, -15109,
        -15110, -15117, -15119, -15121, -15128, -15139, -15140, -15141,
        -15143, -15144, -15149, -15150, -15153, -15158, -15165, -15180,
        -15183, -15362, -15363, -15369, -15375, -15377, -15385, -15394,
        -15408, -15416, -15419, -15435, -15436, -15448, -15454, -15625,
        -15631, -15640, -15652, -15659, -15661, -15667, -15681, -15701,
        -15707, -15878, -15889, -15903, -15915, -15920, -15933, -15944,
        -15958, -15959, -16155, -16158, -16169, -16171, -16180, -16187,
        -16202, -16205, -16212, -16216, -16220, -16393, -16401, -16403,
        -16407, -16412, -16419, -16423, -16427, -16429, -16433, -16448,
        -16452, -16459, -16465, -16470, -16474, -16647, -16657, -16664,
        -16689, -16706, -16708, -16733, -16915, -16942, -16970, -16983,
        -17185, -17202, -17417, -17427, -17433, -17454, -17468, -17482,
        -17487, -17496, -17676, -17683, -17692, -17697, -17701, -17703,
        -17721, -17730, -17733, -17752, -17759, -17922, -17928, -17931,
        -17947, -17950, -17961, -17964, -17970, -17988, -17997, -18012,
        -18181, -18183, -18184, -18201, -18211, -18220, -18231, -18237,
        -18239, -18446, -18447, -18448, -18463, -18478, -18490, -18501,
        -18518, -18526, -18696, -18697, -18710, -18722, -18731, -18735,
        -18741, -18756, -18763, -18773, -18774, -18783, -18952, -18961,
        -18977, -18996, -19003, -19006, -19018, -19023, -19038, -19212,
        -19218, -19224, -19227, -19235, -19238, -19242, -19243, -19249,
        -19261, -19263, -19270, -19275, -19281, -19288, -19289, -19467,
        -19479, -19484, -19500, -19515, -19525, -19531, -19540, -19715,
        -19725, -19728, -19739, -19741, -19746, -19751, -19756, -19763,
        -19774, -19775, -19784, -19805, -19976, -19982, -19986, -19990,
        -20002, -20026, -20032, -20036, -20051, -20230, -20242, -20257,
        -20265, -20283, -20292, -20295, -20304, -20317, -20319 };

//==================================================================
/**
    功能:    将汉字转换成汉语拼音全拼,例如将“马兆瑞”转换成“mazhaorui”
    @param[in]    Chinese:要转换的汉字字符
    @param[out]    PinYin:转换后的拼音字符
    @par修改记录:
**/
//==================================================================
void GetPinYin(unsigned char* Chinese, string& PinYin)
{
    int chinese_str_len = strlen((char*)Chinese);
    for(int i = 0; i < chinese_str_len; i++)
    {
        if(Chinese[i] > 0 && Chinese[i] < 160)
        {
            PinYin += Chinese[i];
        }
        else
        {
            int ascii_code = Chinese[i]*256 + Chinese[i+1] - 256*256;
            ++i;
            if (ascii_code < -20319 || ascii_code > -10247) // 不知道的字符
            {
                PinYin += "?";
                continue;
            }

            for (int j = 0; j < 396; j++)
            {
                if (ascii_code >= code[j])
                {
                    PinYin += name[j];
                    break;
                }
            }
        }
    }
}

void main()
{
    unsigned char chinese[] = "马兆瑞";
    string pinyin;
    GetPinYin(chinese, pinyin);
    int dsa = 1;
}
时间: 2024-08-28 05:53:32

C++ 将汉字转换成汉语拼音全拼的相关文章

java把汉字转换成拼音

汉字转换成拼音工具类: 1 import net.sourceforge.pinyin4j.PinyinHelper; 2 import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType; 3 import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat; 4 import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;

基于jQuery实现汉字转换成拼音代码

基于jQuery实现汉字转换成拼音代码.这是一款基于jQuery.Hz2Py.js插件实现的汉字转拼音特效.效果图如下: 在线预览   源码下载 实现的代码. html代码: <br /> <br /> <br /> <br /> <br /> <center> 在这里输入汉字<br /> <textarea id="content"> </textarea><br /&g

php 将汉字转换成拼音的方法封装成工具包

php 将汉字转换成拼音的方法封装成工具包,代码如下: <?php class PinyinTool { private static $pylist = array( 'a'=>-20319,'ai'=>-20317,'an'=>-20304,'ang'=>-20295,'ao'=>-20292, 'ba'=>-20283,'bai'=>-20265,'ban'=>-20257,'bang'=>-20242,'bao'=>-20230,'

python把汉字转换成拼音实现程序

python把汉字转换成拼音实现程序 文章一个简洁干的汉字转拼音 程序,复制下载就可以直接使用,有需要的同学可以参考一下下. #coding:utf-8 #基于python2.6 table = 'a,-20319;ai,-20317;an,-20304;ang,-20295;ao,-20292;ba,-20283;bai,-20265;ban,-20257;bang,-20242;bao,-20230;bei,-20051;ben,-20036;beng,-20032;bi,-20026;bi

几个将汉字转换成拼音的在线工具

编程时,经常遇到由于汉字兼容性差带来的困扰.解决的方法之一就是使用汉语拼音来代替汉字,(使用英语翻译比较费时).将汉语转换成拼音的方法有很多,可以通过编程实现,比如借助于pinyin package,也可以使用现在工具,直接将汉语转化为拼音.需要注意的是,在汉字转化成拼音时,需要注意尽量不要保留声调,因为声调的兼容性也比较差. 支持不带声调的汉字转化成拼音的在线工具如下: http://www.atool.org/hanzi2pinyin.php http://zhongwenzhuanpiny

【原创】字符串工具类--获取汉字对应的拼音(全拼或首字母)

1.引入pinyin4j-2.5.0.jar包 2.代码实现: import java.util.regex.Matcher; import java.util.regex.Pattern; import net.sourceforge.pinyin4j.PinyinHelper; import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat; import net.sourceforge.pinyin4j.format.Hanyu

Python汉字转换成拼音

最近在使用Python做项目时,需要将汉字转化成对应的拼音.在Github上找到了一个现成的程序. Python汉字转拼音 使用实例如下: from pinyin import PinYin test = PinYin() test.load_word() print test.hanzi2pinyin(string='钓鱼岛是中国的') print test.hanzi2pinyin_split(string='钓鱼岛是中国的', split="-") 输出: ['diao', 'y

iOS中将汉字转换成拼音

NSMutableString *pinyin = [_name mutableCopy]; //转换成拼音 CFStringTransform((__bridge CFMutableStringRef)pinyin, NULL, kCFStringTransformMandarinLatin, NO); //去掉音调 CFStringTransform((__bridge CFMutableStringRef)pinyin, NULL, kCFStringTransformStripDiacr

汉字转换成拼音-pinyin4j.jar的使用

package com.mummy.page; import net.sourceforge.pinyin4j.PinyinHelper; import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType; import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat; import net.sourceforge.pinyin4j.format.HanyuPinyinToneTy