C#_获取汉字拼音

时间:2022-12-25 22:55:32
using System;
using System.Collections.Generic;
using System.Text;
using System.Text.RegularExpressions;
namespace Ctr.Common.Tools
{
/// <summary>
/// 汉字转拼音静态类,包括功能全拼和缩写,方法全部是静态的
/// </summary>
public static class Chinese2Spell
{
#region 属性数据定义
/// <summary>
/// 汉字的机内码数组
/// </summary>
private static int[] pyValue = new int[]
{
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-, -,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-,
-,-,-,-,-,-,-,-,-,-,-,-
};
/// <summary>
/// 机内码对应的拼音数组
/// </summary>
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"
};
#endregion
#region 把汉字转换成拼音(全拼)无间隔符号
/// <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 static string Convert(string hzString)
{
// 匹配中文字符
Regex regex = new Regex("^["u4e00-"u9fa5]$");
byte[] array = new byte[];
string pyString = "";
int chrAsc = ;
int i1 = ;
int i2 = ;
char[] noWChar = hzString.ToCharArray();
for (int j = ; j < noWChar.Length; j++)
{
// 中文字符
if (regex.IsMatch(noWChar[j].ToString()))
{
array = System.Text.Encoding.Default.GetBytes(noWChar[j].ToString());
i1 = (short)(array[]);
i2 = (short)(array[]);
chrAsc = i1 * + i2 - ;
if (chrAsc > && chrAsc < )
{
pyString += noWChar[j];
}
else
{
// 修正部分文字
if (chrAsc == -) // 修正“圳”字
pyString += "Zhen";
else
{
for (int i = (pyValue.Length - ); i >= ; i--)
{
if (pyValue[i] <= chrAsc)
{
pyString += pyName[i];
break;
}
}
}
}
}
// 非中文字符
else
{
pyString += noWChar[j].ToString();
}
}
return pyString;
}
#endregion
#region 把汉字转换成拼音(全拼) 用空格间隔
/// <summary>
/// 把汉字转换成拼音(全拼)
/// </summary>
/// <param name="hzString">汉字字符串</param>
/// <returns>转换后的拼音(全拼)字符串</returns>
public static string ConvertWithBlank(string hzString)
{
// 匹配中文字符
Regex regex = new Regex("^["u4e00-"u9fa5]$");
byte[] array = new byte[];
string pyString = "";
int chrAsc = ;
int i1 = ;
int i2 = ;
char[] noWChar = hzString.ToCharArray();
for (int j = ; 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[]);
i2 = (short)(array[]);
chrAsc = i1 * + i2 - ;
if (chrAsc > && chrAsc < )
{
pyString = pyString + " " + noWChar[j];
}
else
{
// 修正部分文字
if (chrAsc == -) // 修正“圳”字
pyString = pyString + " " + "Zhen";
else
{
for (int i = (pyValue.Length - ); i >= ; i--)
{
if (pyValue[i] <= chrAsc)
{
pyString = pyString + " " + pyName[i];
break;
}
}
}
}
}
// 非中文字符
else
{
pyString = pyString +" "+ noWChar[j].ToString();
}
}
return pyString.Trim();
}
#endregion
#region 把汉字转换成拼音(全拼) 用特定的字符间隔
/// <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 static string ConvertWithSplitChar(string hzString,string splitChar)
{
// 匹配中文字符
Regex regex = new Regex("^["u4e00-"u9fa5]$");
byte[] array = new byte[];
string pyString = "";
int chrAsc = ;
int i1 = ;
int i2 = ;
char[] noWChar = hzString.ToCharArray();
for (int j = ; 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[]);
i2 = (short)(array[]);
chrAsc = i1 * + i2 - ;
if (chrAsc > && chrAsc < )
{
pyString = pyString + splitChar + noWChar[j];
}
else
{
// 修正部分文字
if (chrAsc == -) // 修正“圳”字
pyString = pyString + splitChar + "Zhen";
else
{
for (int i = (pyValue.Length - ); i >= ; i--)
{
if (pyValue[i] <= chrAsc)
{
pyString = pyString + splitChar + pyName[i];
break;
}
}
}
}
}
// 非中文字符
else
{
pyString = pyString + splitChar + noWChar[j].ToString();
}
}
char[] trimAChar = splitChar.ToCharArray();
return pyString.TrimStart(trimAChar);
}
#endregion
#region 汉字转拼音缩写 (字符串) (小写)
/// <summary>
/// 汉字转拼音缩写
/// </summary>
/// <param name="str">要转换的汉字字符串</param>
/// <returns>拼音缩写</returns>
public static string GetSpellStringLower(string str)
{
string tempStr = "";
foreach(char c in str)
{
if((int)c >= && (int)c <=)
{
//字母和符号原样保留
tempStr += c.ToString();
}
else
{
//累加拼音声母
tempStr += GetSpellCharLower(c.ToString());
}
}
return tempStr;
}
#endregion #region 汉字转拼音缩写 (字符串) (小写) (空格间隔)
/// <summary>
/// 汉字转拼音缩写 (字符串) (小写) (空格间隔)
/// </summary>
/// <param name="str">要转换的汉字字符串</param>
/// <returns>拼音缩写</returns>
public static string GetSpellStringLowerSplitWithBlank(string str)
{
string tempStr = "";
foreach (char c in str)
{
if ((int)c >= && (int)c <= )
{
//字母和符号原样保留
tempStr = tempStr + " " + c.ToString();
}
else
{
//累加拼音声母
tempStr = tempStr + " " + GetSpellCharLower(c.ToString());
}
}
return tempStr.Trim();
}
#endregion
#region 汉字转拼音缩写 (字符串)(大写)
/// <summary>
/// 汉字转拼音缩写 (大写)
/// </summary>
/// <param name="str">要转换的汉字字符串</param>
/// <returns>拼音缩写</returns>
public static string GetSpellStringSupper(string str)
{
string tempStr = "";
foreach (char c in str)
{
if ((int)c >= && (int)c <= )
{
//字母和符号原样保留
tempStr += c.ToString();
}
else
{
//累加拼音声母
tempStr += GetSpellCharSupper(c.ToString());
}
}
return tempStr;
}
#endregion
#region 汉字转拼音缩写 (字符串)(大写)(空格间隔)
/// <summary>
/// 汉字转拼音缩写 (字符串)(大写)(空格间隔)
/// </summary>
/// <param name="str">要转换的汉字字符串</param>
/// <returns>拼音缩写</returns>
public static string GetSpellStringSupperSplitWithBlank(string str)
{
string tempStr = "";
foreach (char c in str)
{
if ((int)c >= && (int)c <= )
{
//字母和符号原样保留
tempStr = tempStr + " " + c.ToString();
}
else
{
//累加拼音声母
tempStr = tempStr + " " + GetSpellCharSupper(c.ToString());
}
}
return tempStr.Trim();
}
#endregion
#region 取单个字符的拼音声母(字符)(大写)
/// <summary>
/// 取单个字符的拼音声母
/// </summary>
/// <param name="c">要转换的单个汉字</param>
/// <returns>拼音声母</returns>
public static string GetSpellCharSupper(string c)
{
byte[] array = new byte[];
array = System.Text.Encoding.Default.GetBytes(c);
int i = (short)(array[] - '"0') * + ((short)(array[] - '"0'));
if (i < 0xB0A1) return c;
if (i < 0xB0C5) return "A";
if (i < 0xB2C1) return "B";
if (i < 0xB4EE) return "C";
if (i < 0xB6EA) return "D";
if (i < 0xB7A2) return "E";
if (i < 0xB8C1) return "F";
if (i < 0xB9FE) return "G";
if (i < 0xBBF7) return "H";
if (i < 0xBFA6) return "J";
if (i < 0xC0AC) return "K";
if (i < 0xC2E8) return "L";
if (i < 0xC4C3) return "M";
if (i < 0xC5B6) return "N";
if (i < 0xC5BE) return "O";
if (i < 0xC6DA) return "P";
if (i < 0xC8BB) return "Q";
if (i < 0xC8F6) return "R";
if (i < 0xCBFA) return "S";
if (i < 0xCDDA) return "T";
if (i < 0xCEF4) return "W";
if (i < 0xD1B9) return "X";
if (i < 0xD4D1) return "Y";
if (i < 0xD7FA) return "Z";
return c;
}
#endregion
#region 取单个字符的拼音声母(字符)(小写)
/// <summary>
/// 取单个字符的拼音声母
/// </summary>
/// <param name="c">要转换的单个汉字</param>
/// <returns>拼音声母</returns>
public static string GetSpellCharLower(string c)
{
byte[] array = new byte[];
array = System.Text.Encoding.Default.GetBytes(c);
int i = (short)(array[] - '"0') * + ((short)(array[] - '"0'));
if (i < 0xB0A1) return c;
if (i < 0xB0C5) return "a";
if (i < 0xB2C1) return "b";
if (i < 0xB4EE) return "c";
if (i < 0xB6EA) return "d";
if (i < 0xB7A2) return "e";
if (i < 0xB8C1) return "f";
if (i < 0xB9FE) return "g";
if (i < 0xBBF7) return "h";
if (i < 0xBFA6) return "j";
if (i < 0xC0AC) return "k";
if (i < 0xC2E8) return "l";
if (i < 0xC4C3) return "m";
if (i < 0xC5B6) return "n";
if (i < 0xC5BE) return "o";
if (i < 0xC6DA) return "p";
if (i < 0xC8BB) return "q";
if (i < 0xC8F6) return "r";
if (i < 0xCBFA) return "s";
if (i < 0xCDDA) return "t";
if (i < 0xCEF4) return "w";
if (i < 0xD1B9) return "x";
if (i < 0xD4D1) return "y";
if (i < 0xD7FA) return "z";
return c;
}
#endregion
}
}