两种将中文转成中文拼音的方法

最新推荐文章于 2024-05-10 10:58:55 发布

cpcpc

最新推荐文章于 2024-05-10 10:58:55 发布

阅读量4.2k

点赞数

分类专栏： C#基础文章标签： string regex constructor class byte dao

C#基础专栏收录该内容

17 篇文章 0 订阅

订阅专栏

两种将中文转成中文拼音的方法

个人倾向于使用第二种方法。

第一种：

   /// <summary>
/// Hz2Py 的摘要说明
/// </summary>
    public class Hz2Py
    {
        public Hz2Py()
        {
            //
            // TODO: 在此处添加构造函数逻辑
            //
        }
        private static int[] pyValue = new int[]{
    -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036,
    -20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763,
    -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515,
    -19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249,
    -19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,
    -19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,
    -18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,-18490,-18478,-18463,-18448,
    -18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183, -18181,-18012,
    -17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,
    -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,
    -17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733,
    -16708,-16706,-16689,-16664,-16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448,
    -16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216,
    -16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,-16155,-15959,-15958,-15944,
    -15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659,
    -15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394,
    -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150,
    -15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,
    -14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,
    -14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654,
    -14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,
    -14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,
    -14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907,
    -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601,
    -13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343,
    -13340,-13329,-13326,-13318,-13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076,
    -13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831,
    -12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,-12346,-12320,-12300,
    -12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798,
    -11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067,
    -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832,
    -10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328,
    -10322,-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254
    };

        private static string[] pyName = new string[]
    {
    "A","Ai","An","Ang","Ao","Ba","Bai","Ban","Bang","Bao","Bei","Ben",
    "Beng","Bi","Bian","Biao","Bie","Bin","Bing","Bo","Bu","Ba","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"
    };

        /// <summary>
        /// 把汉字转换成拼音(全拼)
        /// </summary>
        /// <param name="hzString">汉字字符串</param>
        /// <returns>转换后的拼音(全拼)字符串</returns>
        public string Convert(string hzString)
        {
            // 匹配中文字符
            Regex regex = new Regex("^[\u4e00-\u9fa5]{1}quot;);
            byte[] array = new byte[2];
            string pyString = "";
            int chrAsc = 0;
            int i1 = 0;
            int i2 = 0;
            char[] noWChar = hzString.ToCharArray();

            for(int j = 0; j < noWChar.Length; j++)
            {
                // 中文字符
                if(regex.IsMatch(noWChar[j].ToString()))
                {
                    array = System.Text.Encoding.Default.GetBytes(noWChar[j].ToString());
                    i1 = (short)(array[0]);
                    i2 = (short)(array[1]);
                    chrAsc = i1 * 256 + i2 - 65536;
                    if(chrAsc > 0 && chrAsc < 160)
                    {
                        pyString += noWChar[j];
                    }
                    else
                    {
                        // 修正部分文字
                        if(chrAsc == -9254) // 修正“圳”字
                            pyString += "Zhen";
                        else
                        {
                            for(int i = (pyValue.Length - 1); i >= 0; i--)
                            {
                                if(pyValue[i] <= chrAsc)
                                {
                                    pyString += pyName[i];
                                    break;
                                }
                            }
                        }
                    }
                }
                // 非中文字符
                else
                {
                    pyString += noWChar[j].ToString();
                }
            }
            return pyString;
        }     
    }

第二种：

using System;
using System.Collections.Generic;
using System.Text;
namespace FirstLetterOfPinyin
{
    class Program
    {
        static void Main(string[] args)
        {
            TestWrite("红豆");
            TestWrite("绿豆");
            TestWrite("惠普TX 1106", true);
            TestWrite("惠普TX 1106", false);
            Console.ReadKey();
        }
        static void TestWrite(String fChinese)
        {
            TestWrite(fChinese, false);
        }
        static void TestWrite(String fChinese, Boolean fReutrnEmptyWhenFailure)
        {
            Console.WriteLine(String.Format("{0}:{1}", fChinese
                , StringHelper.GetFirstLetterOfChinese(fChinese, fReutrnEmptyWhenFailure)));
        }
    }
    /// <summary>
    /// 失败时处理返回值的方式
    public partial class StringHelper
    {
        #region " LetterItem "
        private class LetterItem
        {
            private String fLetter;
            private Int64 fMinValue;
            private Int64 fMaxValue;
            public String Letter { get { return fLetter; } }
            public Int64 MinValue { get { return fMinValue; } }
            public Int64 MaxValue { get { return fMaxValue; } }
            public LetterItem(String fLetter, Int64 fMinValue, Int64 fMaxValue)
            {
                this.fLetter = fLetter;
                this.fMinValue = fMinValue;
                this.fMaxValue = fMaxValue;
            }
        }
        #endregion
        private static List<LetterItem> dictionaryLetter;
        #region " Constructor "
        static StringHelper()
        {
            dictionaryLetter = new List<LetterItem>();
            // 没有 U、V 
            dictionaryLetter.Add(new LetterItem("A", 45217, 45252));
            dictionaryLetter.Add(new LetterItem("B", 45253, 45760));
            dictionaryLetter.Add(new LetterItem("C", 45761, 46317));
            dictionaryLetter.Add(new LetterItem("D", 46318, 46825));
            dictionaryLetter.Add(new LetterItem("E", 46826, 47009));
            dictionaryLetter.Add(new LetterItem("F", 47010, 47296));
            dictionaryLetter.Add(new LetterItem("G", 47297, 47613));
            dictionaryLetter.Add(new LetterItem("H", 47614, 48118));
            dictionaryLetter.Add(new LetterItem("J", 48119, 49061));
            dictionaryLetter.Add(new LetterItem("K", 49062, 49323));
            dictionaryLetter.Add(new LetterItem("L", 49324, 49895));
            dictionaryLetter.Add(new LetterItem("M", 49896, 50370));
            dictionaryLetter.Add(new LetterItem("N", 50371, 50613));
            dictionaryLetter.Add(new LetterItem("O", 50614, 50621));
            dictionaryLetter.Add(new LetterItem("P", 50622, 50905));
            dictionaryLetter.Add(new LetterItem("Q", 50906, 51386));
            dictionaryLetter.Add(new LetterItem("R", 51387, 51445));
            dictionaryLetter.Add(new LetterItem("S", 51446, 52217));
            dictionaryLetter.Add(new LetterItem("T", 52218, 52697));
            dictionaryLetter.Add(new LetterItem("W", 52698, 52979));
            dictionaryLetter.Add(new LetterItem("X", 52980, 53640));
            dictionaryLetter.Add(new LetterItem("Y", 53689, 54480));
            dictionaryLetter.Add(new LetterItem("Z", 54481, 55289));
        }
        #endregion
        /// <summary>
        /// 获取一段中文中每个中文拼音的第一个字母
        /// </summary>
        /// <param name="fInputChinese">需要获取字母的中文</param>
        /// <returns>中文拼音的第一个字母</returns>
        public static string GetFirstLetterOfChinese(string fInputChinese)
        {
            return GetFirstLetterOfChinese(fInputChinese, false);
        }
        /// <summary>
        /// 获取一段中文中每个中文拼音的第一个字母
        /// </summary>
        /// <param name="fInputChinese">需要获取字母的中文</param>
        /// <param name="fReutrnEmptyWhenFailure">当输入不是中文时是否返回空值。True:返回空值；False：返回传入参数的大写</param>
        /// <returns>中文拼音的第一个字母</returns>
        public static string GetFirstLetterOfChinese(string fInputChinese, Boolean fReutrnEmptyWhenFailure)
        {
            string letters = "";
            
            foreach (char c in fInputChinese.ToCharArray())
                letters += GetFirstLetterOfPinyin(c.ToString(), fReutrnEmptyWhenFailure);
            return letters;
        }
        /// <summary>
        /// 获取一个中文拼音的第一个字母。
        /// </summary>
        /// <param name="fInputSingleChinese">需要获取字母的一个中文</param>
        /// <param name="fReutrnEmptyWhenFailure">当输入不是中文时是否返回空值。True:返回空值；False：返回传入参数的大写</param>
        /// <returns>中文拼音的第一个字母</returns>
        private static string GetFirstLetterOfPinyin(String fInputSingleChinese, Boolean fReutrnEmptyWhenFailure)
        {
            byte[] byteArray = System.Text.Encoding.Default.GetBytes(fInputSingleChinese);
            //如果是字母，则直接返回 
            if (byteArray.Length == 1)
            {
                return fReutrnEmptyWhenFailure
                    ? fInputSingleChinese.ToUpper() 
                    : String.Empty;
            }
            // 获取范围
            short minValue = (short)(byteArray[0]);
            short maxValue = (short)(byteArray[1]);
            Int64 value = minValue * 256 + maxValue;
            foreach (LetterItem letterItem in dictionaryLetter)
            {
                if (value >= letterItem.MinValue &&
                    value <= letterItem.MaxValue)
                    return letterItem.Letter;
            }
            return "?"; // 未知
        }
    }
}