此代码属改造而来,没有太深的技术难度,仅仅是排除了原来代码的错误、增加了一些常规需求。目前此类可以实现的功能如下:
1、对中文字符串进行拼音转换的基本功能
2、支持并可自定义拼音单词间的分隔符
3、支持并可自定义是否将拼音单词首字母大写
4、支持并可自定义多音词预定音
5、支持并可自定义转换过程中要排除解析的字符,例如中文标点
输出示例:
引发 system.Web.UI.Control.Init 事件以对页进行初始化
Yin-Fa system.Web.UI.Control.Init Shi-Jian-Yi-Dui-Ye-Jin-Xing-Chu-Shi-Hua
Hello!重庆和深圳的特色各是什么呢?
Hello!Chong Qing He Shen Zhen De Te Se Ge Shi ShenMe Ne ?
代码如下:
/**//// <summary>
/// 汉字转拼音工具。
/// </summary>
public sealed class CHS2PinYin
{
/**//// <summary>
/// 包含字符 ASC 码的整形数组。
/// </summary>
private static int[] pv = 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};
/**//// <summary>
/// 包含汉字拼音的字符串数组。
/// </summary>
private static string[] ps = new string[] ...{ "a", "ai", "an", "ang", "ao", "ba", "bai", "ban", "bang", "bao", "bei", "ben", "beng", "bi", "bian", "biao", "bie", "bin", "bing", "bo", "bu", "ca", "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>
/// 包含要排除处理的字符的字符串数组。
/// </summary>
private static string[] bd = new string[] ...{ ",", "。", "“", "”", "‘", "’", "¥", "$", "(", "「", "『", ")", "」", "』", "[", "〖", "【", "]", "〗", "】", "—", "…", "《", "<", "》", ">" };
private static Hashtable _Phrase;
/**//// <summary>
/// 设置或获取包含列外词组读音的键/值对的组合。
/// </summary>
public static Hashtable Phrase
...{
get
...{
if (_Phrase == null)
...{
_Phrase = new Hashtable();
_Phrase.Add("重庆", "Chong Qing");
_Phrase.Add("深圳", "Shen Zhen");
_Phrase.Add("什么", "Shen Me");
}
return _Phrase;
}
set ...{ _Phrase = value; }
}
/**//// <summary>
/// 将指定中文字符串转换为拼音形式。
/// </summary>
/// <param name="chs">要转换的中文字符串。</param>
/// <param name="separator">连接拼音之间的分隔符。</param>
/// <param name="initialCap">指定是否将首字母大写。</param>
/// <returns>包含中文字符串的拼音的字符串。</returns>
public static string Convert(string chs, string separator, bool initialCap)
...{
if (chs == null || chs.Length == 0) return "";
if (separator == null || separator.Length == 0) separator = "";
// 例外词组
foreach (DictionaryEntry de in CHS2PinYin.Phrase)
...{
chs = chs.Replace(de.Key.ToString(), String.Format(" {0} ", de.Value.ToString().Replace(" ", separator)));
}
byte[] array = new byte[2];
string returnstr = "";
int chrasc = 0;
int i1 = 0;
int i2 = 0;
bool b = false;
char[] nowchar = chs.ToCharArray();
CultureInfo ci = Thread.CurrentThread.CurrentCulture;
TextInfo ti = ci.TextInfo;
for (int j = 0; j < nowchar.Length; j++)
...{
array = Encoding.Default.GetBytes(nowchar[j].ToString());
string s = nowchar[j].ToString(); ;
if (array.Length == 1)
...{
b = true;
returnstr += s;
}
else
...{
if (s == "?")
...{
if (returnstr == "" || b == true) returnstr += s;
else returnstr += separator + s;
continue;
}
i1 = (short)(array[0]);
i2 = (short)(array[1]);
chrasc = i1 * 256 + i2 - 65536;
for (int i = (pv.Length - 1); i >= 0; i--)
...{
if (pv <= chrasc)
...{
s = ps;
if (initialCap == true) s = ti.ToTitleCase(s);
if (returnstr == "" || b == true) returnstr += s;
else returnstr += separator + s;
break;
}
}
b = false;
}
}
returnstr = returnstr.Replace(" ", separator);
return returnstr;
}
/**//// <summary>
/// 将指定中文字符串转换为拼音形式。
/// </summary>
/// <param name="chs">要转换的中文字符串。</param>
/// <param name="separator">连接拼音之间的分隔符。</param>
/// <returns>包含中文字符串的拼音的字符串。</returns>
public static string Convert(string chs, string separator)
...{
return CHS2PinYin.Convert(chs, separator, false);
}
/**//// <summary>
/// 将指定中文字符串转换为拼音形式。
/// </summary>
/// <param name="chs">要转换的中文字符串。</param>
/// <param name="initialCap">指定是否将首字母大写。</param>
/// <returns>包含中文字符串的拼音的字符串。</returns>
public static string Convert(string chs, bool initialCap)
{
return CHS2PinYin.Convert(chs, "", initialCap);
}
/**//// <summary>
/// 将指定中文字符串转换为拼音形式。
/// </summary>
/// <param name="chs">要转换的中文字符串。</param>
/// <returns>包含中文字符串的拼音的字符串。</returns>
public static string Convert(string chs)
...{
return CHS2PinYin.Convert(chs, "");
}
}
原文地址:http://tech.ddvip.com/2008-10/122483878282708.html