2013年7月28日 星期日

中文轉拼音與Regex isMatch ToCharArray 運用

此程式為範例 中文字轉 羅馬  的效果 稱不上準確
而且資料不夠準確+完整 所以這範例只能讓使用者
知道運行原理  下一章將會補上 "中文轉羅馬的完整程式"
首先 先在 windows 設計模式 加入 2個 textbox
一個用於輸入文字叫 txt_Chinese
一個用於輸出文字叫 txt_PinYin

為了讓使用者 在輸入時 觸發!
因次我們必須讓 txt_Chinese這控制項觸發事件為TextChanged

Ps:在設計模式中 可以點選txt_Chinese然後右下角 有一個閃電
       並且挑選 需要的觸發事件 即可


因此我們就可以在每次輸入文字時 同時觸發程式!
來看程式碼吧!

 private void txt_Chinese_TextChanged(object sender, EventArgs e)
       {
           //呼叫PinYin.cs檔的GetABC方法並且帶入使用者輸入的"字"
            txt_PinYIn.Text = //呼叫拼音類的GetABC方法得到拼音字串
                new PinYin().GetABC(txt_Chinese.Text);
        }


當使用者開始輸入文字到txt_Chinese時將會觸發TextChanged事件
而我們由這事件的觸發 開始程序!
來看程式區塊中txt_PinYin.Text= new PinYin().GetABC(txt_Chinese.Text)
txt_PinYin.text輸出的結果
等於PinYin.cs檔案中的方法叫GetABC(?)
而GetABC(txt_Chinese.Text)
將傳送txt_Chinese.Text字串給 GetABC

接下來我們來瞧瞧使用者在txt_Chinese輸入的中文 送入GetABC(txt_Chinese)
會發生啥事  

看程式碼吧

 public string GetABC(string str)//str=控制項中的txt_Chinese.Text
    {
        //先宣告正規化 條件式驗證輸入是否為中文字
        Regex reg = new Regex("^[\u4e00-\u9fa5]$");//  \u4e00~\u9fa5是unicode中文範圍
        byte[] arr = new byte[2];//定義2byte字 節陣列 等等要存放unicode的
        string pystr = "";//定義字串變數用於返回拼音
        char[] mChar = str.ToCharArray();//取得中文字對應的字符陣列unicode 16bit會轉成10進位以char呈現
        return GetStr(mChar, pystr, reg, arr);//返回取得到的中文字拼音
    }

其實 註解已經 很清楚了 str是txt_Chinese
首先 建構 正規化Regex 函式 並且將要比對的規則運算式模式 套入方法中
Regex reg = new Regex("^[\u4e00-\u9fa5]$");
而字串中的\u4e00-\u9fa5 代表unicode中文範圍
正規化 將用來比對 使用者輸入是否是個中文字

再來宣告 byte陣列 2個  待會是要將中文的big碼
16Bit已各分8bit存入 byte中

二來
string pystr 是要將最終答案的結果回傳給初始呼叫副程式的地方

三來
char[] mChar = str.ToCharArray();
char 字元陣列利用ToCharArray()取str一個字元 並且陣列存入
如果str有兩字元 講會有 兩個char陣列

最後
return GetStr(mChar, pystr, reg, arr)
return 回傳給 TextChanged事件中 呼叫的副程式
但是
return 回傳是一個GetStr副程式
所以必須將GetStr裡的程序跑完才能回傳給TextChanged事件中的
GetABC(txt_Chinese.Text)
注意看 GetStr(mChar, pystr, reg, arr)方法中帶入的參數
我們下一段將介紹GetStr中的程序 
來看下面GetStr()程式碼

private string GetStr(char[] mChar, string pystr, Regex reg, byte[] arr)
    {
        int asc = 0, M1 = 0, M2 = 0;//宣告3個整數
        for (int j = 0; j < mChar.Length; j++)//mChar.Lenth看有幾個字char
        {
            if (reg.IsMatch(mChar[j].ToString()))//reg正規化條件中mChar的字是否府和unicode中文字範圍內
            {
                //假如mChar[j] = 陳, unicode 是38515  big 是B3AF  ,big碼將分成2位元組=179.175
                arr = System.Text.Encoding.Default.GetBytes(mChar[j].ToString());
                M1 = (short)(arr[0]);
                M2 = (short)(arr[1]);
                asc = M1 * 256 + M2 - 65536;
                if (asc > 0 && asc < 160)
                {
                    pystr += mChar[j];//條件相符直接印到pystr
                }
                else//不然 再進行選識
                {
                    switch (asc)
                    {
                        case -9254:
                            pystr += "Zhen"; break;
                        case -8985:
                            pystr += "Qian"; break;
                        case -5463:
                            pystr += "Jia"; break;
                        case -8274:
                            pystr += "Ge"; break;
                        case -5448:
                            pystr += "Ga"; break;
                        case -5447:
                            pystr += "La"; break;
                        case -4649:
                            pystr += "Chen"; break;
                        case -5436:
                            pystr += "Mao"; break;
                        case -5213:
                            pystr += "Mao"; break;
                        case -3597:
                            pystr += "Die"; break;
                        case -5659:
                            pystr += "Tian"; break;
                        default://casw 條件不府 再進行下列 比對
                            for (int i = (getValue.Length - 1); i >= 0; i--)
                            {   //比對(getValue[i]陣列中 有無小於或等於asc
                                if (getValue[i] <= asc)//判斷中文字的拼音區編碼是否在指定範圍內
                                {
                                    //比對成功的i值 直接對應getStr[i]中的答案 最後 印出
                                    pystr += getStr[i];//如果不超出範圍則取得對應的拼音
                                    break;
                                }
                            }
                            break;
                    }
                }
            }
            else//如果不是中文字
            {
                pystr += mChar[j].ToString();//如果不是中文字則返回
            }
        }
        return pystr;// 最後 回傳pystr給txt_PinYIn.Text
    }




一開始 for (int j = 0; j < mChar.Length; j++)
 迴圈中來判斷mChar幾個字

if (reg.IsMatch(mChar[j].ToString()))
是使用正規化來Match判斷mChar[j]是否是一個中文字元

條件達成後
arr = System.Text.Encoding.Default.GetBytes(mChar[j].ToString());
特別說一下
arr 目前是空的將可放入2個byte   而這2byte 取自於 中文字元big碼的2byte 16bit
System.Text.Encoding是因為沒有宣告命名空間所以重系統呼叫
而Default預設編碼為DBCS 取雙位元組 而.GetBytes是放進byte[]中!

再來後面的演算法 就無需再介紹
因為這字典檔 並非一個完整的羅馬字符
下面演算法 將不停比對 陣列中的數直 是否與字典檔案相同
字典檔案如下

 //定義拼音區編碼陣列
    private static int[] getValue = 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
            };
    //定義拼音陣列
    private static string[] getStr = 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"
           };



比對結果通常都 差很多~
比GOOGLE翻譯還差 所以不做介紹

下一章 將有完整的 中文轉羅馬拼音

沒有留言:

張貼留言