前不久看到有的朋友實現對商品名稱拼音的錄入,發現他的實現方式是手動輸入的,—_—#、同志們,福利來了!數組
本文剛發佈時,只寫了一個實現方式,使用的是微軟的語言包,可是對多音字的效果不怎麼理想,甚至個別字會出現很詭異的錯誤,所以,如今擴展另外一個方法,手動實現。ide
方式1、使用微軟語言包
微軟爲了開發者實現國際化語言的互轉,提供了Microsoft Visual Studio International Pack,這個擴展包裏面有中文、日文、韓文、英語等各國語言包,並提供方法實現互轉、獲取拼音、獲取字數、甚至獲取筆畫數等等。佈局
[這種方式對多音字的效果不怎麼理想,可是,這個方法比較簡單,直接導入包就能夠了,所以,對於那些只須要個別語句進行處理的或者不注重多音字的,可使用這種方式,畢竟簡便嘛。]
在這裏示例講的是輸入漢字,獲取其拼音,獲取拼音和獲取拼音首字母實現效果分別以下:
首先,去微軟官網下載Microsoft Visual Studio International Pack語言包,下載地址分別以下:
Microsoft Visual Studio International Pack 1.0 SR1、Microsoft Visual Studio International Feature Pack 2.0
下載後分別是「vsintlpack1.zip」、「Vsintlpack2.msi」、雙擊「Vsintlpack2.msi」安裝、路徑隨意、可是要記得、由於一會要引用的、
安裝「Vsintlpack2.msi」以後、解壓「vsintlpack1.zip」、裏面包含七個語言包、
例如中文轉拼音「CHSPinYinConv.msi」、簡體繁體互轉「CHTCHSConv.msi」等等。。
在這裏咱們用到的是「CHSPinYinConv.msi」、雙擊安裝成功後、打開Visual Studio、新建一個WinForm項目、窗體佈局如上圖所示、
ui
首先:添加剛剛安裝的語言包引用:this
「D:\Program Files (x86)\Microsoft Visual Studio International Pack\Simplified Chinese Pin-Yin Conversion Library\ChnCharInfo.dll」編碼
默認是C盤、在這裏我安裝在D盤了,而後添加using引用:spa
1 using Microsoft.International.Converters.PinYinConverter;//導入拼音相關
建立獲取拼音的方法:code
1 /// <summary> 2 /// 漢字轉化爲拼音 3 /// </summary> 4 /// <param name="str">漢字</param> 5 /// <returns>全拼</returns> 6 public static string GetPinyin(string str) 7 { 8 string r = string.Empty; 9 foreach (char obj in str) 10 { 11 try 12 { 13 ChineseChar chineseChar = new ChineseChar(obj); 14 string t = chineseChar.Pinyins[0].ToString(); 15 r += t.Substring(0, t.Length - 1); 16 } 17 catch 18 { 19 r += obj.ToString(); 20 } 21 } 22 return r; 23 }
建立獲取漢字拼音首字母的方法:orm
1 /// <summary> 2 /// 漢字轉化爲拼音首字母 3 /// </summary> 4 /// <param name="str">漢字</param> 5 /// <returns>首字母</returns> 6 public static string GetFirstPinyin(string str) 7 { 8 string r = string.Empty; 9 foreach (char obj in str) 10 { 11 try 12 { 13 ChineseChar chineseChar = new ChineseChar(obj); 14 string t = chineseChar.Pinyins[0].ToString(); 15 r += t.Substring(0, 1); 16 } 17 catch 18 { 19 r += obj.ToString(); 20 } 21 } 22 return r; 23 }
而後在「轉拼音」按鈕的點擊事件中調用上述方法:blog
1 // 漢字轉拼音 2 private void btn_One_Click(object sender, EventArgs e) 3 { 4 string source = this.txt_ChineseCharacter_One.Text.Trim(); // 獲得輸入的源字符 5 string result = GetPinyin(source); // 調用方法,獲取拼音 6 this.txt_Pinyin_One.Text = result; 7 }
在「轉首字母」按鈕點擊事件中調用上述方法:
1 // 轉首字母 2 private void btn_Two_Click(object sender, EventArgs e) 3 { 4 string source = this.txt_ChineseCharacter_One.Text.Trim(); // 獲得輸入的源字符 5 string result = GetFirstPinyin(source); // 調用方法,獲取拼音 6 this.txt_Pinyin_One.Text = result; 7 }
到此,已經完成了80%,運行程序,你會發現,當點擊「轉拼音」的時候,結果是這樣子的:
並非我開始說的那種「Gu Ying」的效果啊、這是由於我在獲取拼音的時候簡單的處理了一下:
1 // 漢字轉拼音 2 private void btn_One_Click(object sender, EventArgs e) 3 { 4 string source = this.txt_ChineseCharacter_One.Text.Trim(); // 獲得輸入的源字符 5 6 string result = string.Empty; // 轉拼音的結果 7 string temp = string.Empty; // 下面foreach用到的臨時變量 8 foreach (char item in source) // 遍歷每一個源字符 9 { 10 temp = GetPinyin(item.ToString()); // 將每一個字符轉拼音 11 // 處理:獲取首字母大寫、其他字母小寫 12 result += (String.Format("{0}{1} ", temp.Substring(0, 1).ToUpper(), temp.Substring(1).ToLower())); 13 } 14 15 //string result = GetPinyin(source); // 調用方法,獲取拼音 16 this.txt_Pinyin_One.Text = result; 17 }
OK、到此、這個功能已經實現完成了,還有其他的語言包功能,和此相似,你們能夠百度「Microsoft Visual Studio International Pack使用」、各類語言之間的互轉及功能示例就出來了。
方式2、手動編碼實現
這種方式其實也不困難,說白了就是根據Unicode編碼值,定義對應的拼音數組或集合,而後實現此效果。
首先定義拼音區編碼數組:
1 //定義拼音區編碼數組 2 private static int[] getValue = new int[] 3 { 4 -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036, 5 -20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763, 6 -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515, 7 -19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249, 8 -19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006, 9 -19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735, 10 -18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,-18490,-18478,-18463,-18448, 11 -18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183, -18181,-18012, 12 -17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752, 13 -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482, 14 -17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733, 15 -16708,-16706,-16689,-16664,-16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448, 16 -16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216, 17 -16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,-16155,-15959,-15958,-15944, 18 -15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659, 19 -15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394, 20 -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150, 21 -15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109, 22 -14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902, 23 -14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654, 24 -14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345, 25 -14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112, 26 -14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907, 27 -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601, 28 -13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343, 29 -13340,-13329,-13326,-13318,-13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076, 30 -13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831, 31 -12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,-12346,-12320,-12300, 32 -12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798, 33 -11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067, 34 -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832, 35 -10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328, 36 -10322,-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254 37 };
而後定義拼音數組:
1 //定義拼音數組 2 private static string[] getName = new string[] 3 { 4 "A","Ai","An","Ang","Ao","Ba","Bai","Ban","Bang","Bao","Bei","Ben", 5 "Beng","Bi","Bian","Biao","Bie","Bin","Bing","Bo","Bu","Ba","Cai","Can", 6 "Cang","Cao","Ce","Ceng","Cha","Chai","Chan","Chang","Chao","Che","Chen","Cheng", 7 "Chi","Chong","Chou","Chu","Chuai","Chuan","Chuang","Chui","Chun","Chuo","Ci","Cong", 8 "Cou","Cu","Cuan","Cui","Cun","Cuo","Da","Dai","Dan","Dang","Dao","De", 9 "Deng","Di","Dian","Diao","Die","Ding","Diu","Dong","Dou","Du","Duan","Dui", 10 "Dun","Duo","E","En","Er","Fa","Fan","Fang","Fei","Fen","Feng","Fo", 11 "Fou","Fu","Ga","Gai","Gan","Gang","Gao","Ge","Gei","Gen","Geng","Gong", 12 "Gou","Gu","Gua","Guai","Guan","Guang","Gui","Gun","Guo","Ha","Hai","Han", 13 "Hang","Hao","He","Hei","Hen","Heng","Hong","Hou","Hu","Hua","Huai","Huan", 14 "Huang","Hui","Hun","Huo","Ji","Jia","Jian","Jiang","Jiao","Jie","Jin","Jing", 15 "Jiong","Jiu","Ju","Juan","Jue","Jun","Ka","Kai","Kan","Kang","Kao","Ke", 16 "Ken","Keng","Kong","Kou","Ku","Kua","Kuai","Kuan","Kuang","Kui","Kun","Kuo", 17 "La","Lai","Lan","Lang","Lao","Le","Lei","Leng","Li","Lia","Lian","Liang", 18 "Liao","Lie","Lin","Ling","Liu","Long","Lou","Lu","Lv","Luan","Lue","Lun", 19 "Luo","Ma","Mai","Man","Mang","Mao","Me","Mei","Men","Meng","Mi","Mian", 20 "Miao","Mie","Min","Ming","Miu","Mo","Mou","Mu","Na","Nai","Nan","Nang", 21 "Nao","Ne","Nei","Nen","Neng","Ni","Nian","Niang","Niao","Nie","Nin","Ning", 22 "Niu","Nong","Nu","Nv","Nuan","Nue","Nuo","O","Ou","Pa","Pai","Pan", 23 "Pang","Pao","Pei","Pen","Peng","Pi","Pian","Piao","Pie","Pin","Ping","Po", 24 "Pu","Qi","Qia","Qian","Qiang","Qiao","Qie","Qin","Qing","Qiong","Qiu","Qu", 25 "Quan","Que","Qun","Ran","Rang","Rao","Re","Ren","Reng","Ri","Rong","Rou", 26 "Ru","Ruan","Rui","Run","Ruo","Sa","Sai","San","Sang","Sao","Se","Sen", 27 "Seng","Sha","Shai","Shan","Shang","Shao","She","Shen","Sheng","Shi","Shou","Shu", 28 "Shua","Shuai","Shuan","Shuang","Shui","Shun","Shuo","Si","Song","Sou","Su","Suan", 29 "Sui","Sun","Suo","Ta","Tai","Tan","Tang","Tao","Te","Teng","Ti","Tian", 30 "Tiao","Tie","Ting","Tong","Tou","Tu","Tuan","Tui","Tun","Tuo","Wa","Wai", 31 "Wan","Wang","Wei","Wen","Weng","Wo","Wu","Xi","Xia","Xian","Xiang","Xiao", 32 "Xie","Xin","Xing","Xiong","Xiu","Xu","Xuan","Xue","Xun","Ya","Yan","Yang", 33 "Yao","Ye","Yi","Yin","Ying","Yo","Yong","You","Yu","Yuan","Yue","Yun", 34 "Za", "Zai","Zan","Zang","Zao","Ze","Zei","Zen","Zeng","Zha","Zhai","Zhan", 35 "Zhang","Zhao","Zhe","Zhen","Zheng","Zhi","Zhong","Zhou","Zhu","Zhua","Zhuai","Zhuan", 36 "Zhuang","Zhui","Zhun","Zhuo","Zi","Zong","Zou","Zu","Zuan","Zui","Zun","Zuo" 37 };
而後定義轉換字符串的方法:
1 /// <summary>漢字轉換成全拼的拼音</summary> 2 /// <param name="Chstr">漢字字符串</param> 3 /// <returns>轉換後的拼音字符串</returns> 4 public string StrConvertToPinyin(string Chstr) 5 { 6 Regex reg = new Regex("^[\u4e00-\u9fa5]$");//驗證是否輸入漢字 7 byte[] arr = new byte[2]; 8 string pystr = ""; 9 int asc = 0, M1 = 0, M2 = 0; 10 char[] mChar = Chstr.ToCharArray();//獲取漢字對應的字符數組 11 for (int j = 0; j < mChar.Length; j++) 12 { 13 //若是輸入的是漢字 14 if (reg.IsMatch(mChar[j].ToString())) 15 { 16 arr = System.Text.Encoding.Default.GetBytes(mChar[j].ToString()); 17 M1 = (short)(arr[0]); 18 M2 = (short)(arr[1]); 19 asc = M1 * 256 + M2 - 65536; 20 if (asc > 0 && asc < 160) 21 { 22 pystr += mChar[j]; 23 } 24 else 25 { 26 switch (asc) 27 { 28 case -9254: 29 pystr += "Zhen"; break; 30 case -8985: 31 pystr += "Qian"; break; 32 case -5463: 33 pystr += "Jia"; break; 34 case -8274: 35 pystr += "Ge"; break; 36 case -5448: 37 pystr += "Ga"; break; 38 case -5447: 39 pystr += "La"; break; 40 case -4649: 41 pystr += "Chen"; break; 42 case -5436: 43 pystr += "Mao"; break; 44 case -5213: 45 pystr += "Mao"; break; 46 case -3597: 47 pystr += "Die"; break; 48 case -5659: 49 pystr += "Tian"; break; 50 default: 51 for (int i = (getValue.Length - 1); i >= 0; i--) 52 { 53 if (getValue[i] <= asc) //判斷漢字的拼音區編碼是否在指定範圍內 54 { 55 pystr += getName[i];//若是不超出範圍則獲取對應的拼音 56 break; 57 } 58 } 59 break; 60 } 61 } 62 } 63 else //若是不是漢字 64 { 65 pystr += mChar[j].ToString();//若是不是漢字則返回 66 } 67 } 68 return pystr;//返回獲取到的漢字拼音 69 }
這種方法雖然也會對多音字的識別也不是很理想,可是這種方式畢竟是手動實現的,能夠手動控制,好比,「家長」,咱們想獲得的結果是「Jia Zhang」,可是生成的結果倒是「Jia Chang」、
對於這種包含多音字的詞組,咱們能夠另行控制,好比,定義一個多音字數組和其對應的不一樣詞組組合,在咱們進行轉換拼音的時候,判斷,若是是多音字,那麼在其詞組中找到對應的拼音便可。
相似於咱們作Web開發時的關鍵字過濾。
【來自:LonelyShadow http://www.cnblogs.com/LonelyShadow】