汉字转换为拼音
引用自:http://www.cnblogs.com/gishawk/archive/
1
/// <summary>
2
/// 将汉字转换成为拼音
3
/// </summary>
4
public class Chs2Py
5
{
6
private static int[] pyvalue = new int[]{ -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,
7
-20242,-20230,-20051,-20036,-20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,
8
-19775,-19774,-19763,-19756,-19751,-19746,-19741,-19739,-19728, -19725,-19715,-19540,-19531,
9
-19525,-19515,-19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263, -19261,
10
-19249,-19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,
11
-19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,-18731,
12
-18722,-18710,-18697,-18696,-18526, -18518,-18501,-18490,-18478,-18463,-18448,-18447,-18446,
13
-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183,-18181,-18012,-17997,-17988,-17970,
14
-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,-17733,-17730,-17721,-17703,
15
-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,-17468,-17454,-17433,-17427,-17417,
16
-17202,-17185,-16983,-16970,-16942,-16915,-16733,-16708,-16706,-16689,-16664,-16657,-16647,
17
-16474,-16470,-16465,-16459,-16452,-16448,-16433,-16429,-16427,-16423,-16419,-16412,-16407,
18
-16403,-16401,-16393,-16220,-16216,-16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,
19
-16155,-15959,-15958,-15944,-15933,-15920,-15915,-15903,-15889,-15878, -15707,-15701,-15681,
20
-15667,-15661,-15659,-15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,
21
-15408,-15394,-15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,
22
-15150,-15149,-15144, -15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,
23
-14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,-14894,
24
-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668, -14663,-14654,-14645,-14630,
25
-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,-14170,-14159,-14151,
26
-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,-14109,-14099,-14097,-14094,
27
-14092,-14090, -14087,-14083,-13917,-13914,-13910,-13907,-13906,-13905,-13896,-13894,-13878,
28
-13870,-13859,-13847,-13831,-13658, -13611,-13601,-13406,-13404,-13400,-13398,-13395,-13391,
29
-13387,-13383,-13367,-13359,-13356,-13343,-13340,-13329,-13326,-13318,-13147,-13138,-13120,
30
-13107,-13096,-13095,-13091,-13076,-13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,
31
-12852,-12849,-12838,-12831,-12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,
32
-12346, -12320,-12300,-12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,
33
-11831,-11798,-11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,
34
-11067,-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,-10322,
36
-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254};
37
private static string[] pystr = 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"};
38
39
/// <summary>
40
/// 构造函数
41
/// </summary>
42
public Chs2Py()
43
{
44
}
45
46
/// <summary>
47
/// 静态转换方法 得到输入汉字字符串的对应拼音
48
/// </summary>
49
/// <param name="chrstr">汉字字符串</param>
50
/// <returns>返回对应的拼音</returns>
51
public static string Convert(string chrstr)
52
{
53
byte[] byteArray = new byte[2];
54
string returnStr = "";
55
int chrAsc = 0;
56
int i1 = 0;
57
int i2 = 0;
58
char[] nowChar = chrstr.ToCharArray();
59
for (int j = 0; j < nowChar.Length; j++)
60
{
61
byteArray = Encoding.Default.GetBytes(nowChar[j].ToString());
62
i1 = (short)byteArray[0];
63
i2 = (short)byteArray[1];
64
chrAsc = i1 * 256 + i2 - 65536;
65
if (chrAsc > 0 && chrAsc < 160)
66
{
67
returnStr += nowChar[j];
68
}
69
else
70
{
71
for (int i = (pyvalue.Length - 1); i >= 0; i--)
72
{
73
if (pyvalue[i] <= chrAsc)
74
{
75
returnStr += pystr[i];
76
break;
77
}
78
}
79
}
80
}
81
82
return returnStr;
83
}
84
85
/// <summary>
86
/// 得到汉字拼音缩写
87
/// </summary>
88
/// <param name="str">汉字字符串</param>
89
/// <returns>返回汉字字符串的的拼音缩写</returns>
90
public string GetPYString(string str)
91
{
92
string tempStr = "";
93
foreach (char c in str)
94
{
95
if ((int)c >= 33 && (int)c <= 126)
96
{
97
//字母和符号原样保留
98
tempStr += c.ToString();
99
}
100
else
101
{
102
//累加拼音声母
103
tempStr += GetPYChar(c.ToString());
104
}
105
}
106
107
return tempStr;
108
}
109
110
/// <summary>
111
/// 取单个字符的拼音字母
112
/// </summary>
113
/// <param name="c">汉字</param>
114
/// <returns>返回拼音字母</returns>
115
public string GetPYChar(string c)
116
{
117
byte[] byteArray = new byte[2];
118
byteArray = Encoding.Default.GetBytes(c);
119
int i = (short)(byteArray[0] - '\0') * 256 + (short)(byteArray[1] - '\0');
120
121
if (i < 0xB0A1) return "*";
122
if (i < 0xB0C5) return "a";
123
if (i < 0xB2C1) return "b";
124
if (i < 0xB4EE) return "c";
125
if (i < 0xB6EA) return "d";
126
if (i < 0xB7A2) return "e";
127
if (i < 0xB8C1) return "f";
128
if (i < 0xB9FE) return "g";
129
if (i < 0xBBF7) return "h";
130
if (i < 0xBFA6) return "j";
131
if (i < 0xC0AC) return "k";
132
if (i < 0xC2E8) return "l";
133
if (i < 0xC4C3) return "m";
134
if (i < 0xC5B6) return "n";
135
if (i < 0xC5BE) return "o";
136
if (i < 0xC6DA) return "p";
137
if (i < 0xC8BB) return "q";
138
if (i < 0xC8F6) return "r";
139
if (i < 0xCBFA) return "s";
140
if (i < 0xCDDA) return "t";
141
if (i < 0xCEF4) return "w";
142
if (i < 0xD1B9) return "x";
143
if (i < 0xD4D1) return "y";
144
if (i < 0xD7FA) return "z";
145
146
return "*";
147
}
148
}
/// <summary>2
/// 将汉字转换成为拼音3
/// </summary>4
public class Chs2Py5
{6
private static int[] pyvalue = new int[]{ -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,7
-20242,-20230,-20051,-20036,-20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,8
-19775,-19774,-19763,-19756,-19751,-19746,-19741,-19739,-19728, -19725,-19715,-19540,-19531,9
-19525,-19515,-19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263, -19261,10
-19249,-19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,11
-19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,-18731,12
-18722,-18710,-18697,-18696,-18526, -18518,-18501,-18490,-18478,-18463,-18448,-18447,-18446,13
-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183,-18181,-18012,-17997,-17988,-17970,14
-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,-17733,-17730,-17721,-17703,15
-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,-17468,-17454,-17433,-17427,-17417,16
-17202,-17185,-16983,-16970,-16942,-16915,-16733,-16708,-16706,-16689,-16664,-16657,-16647,17
-16474,-16470,-16465,-16459,-16452,-16448,-16433,-16429,-16427,-16423,-16419,-16412,-16407,18
-16403,-16401,-16393,-16220,-16216,-16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,19
-16155,-15959,-15958,-15944,-15933,-15920,-15915,-15903,-15889,-15878, -15707,-15701,-15681,20
-15667,-15661,-15659,-15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416, 21
-15408,-15394,-15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,22
-15150,-15149,-15144, -15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,23
-14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,-14894,24
-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668, -14663,-14654,-14645,-14630,25
-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,-14170,-14159,-14151,26
-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,-14109,-14099,-14097,-14094,27
-14092,-14090, -14087,-14083,-13917,-13914,-13910,-13907,-13906,-13905,-13896,-13894,-13878,28
-13870,-13859,-13847,-13831,-13658, -13611,-13601,-13406,-13404,-13400,-13398,-13395,-13391,29
-13387,-13383,-13367,-13359,-13356,-13343,-13340,-13329,-13326,-13318,-13147,-13138,-13120,30
-13107,-13096,-13095,-13091,-13076,-13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,31
-12852,-12849,-12838,-12831,-12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,32
-12346, -12320,-12300,-12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,33
-11831,-11798,-11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,34
-11067,-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,-10322,36
-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254};37
private static string[] pystr = 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"};38

39
/// <summary>40
/// 构造函数41
/// </summary>42
public Chs2Py()43
{ 44
}45

46
/// <summary>47
/// 静态转换方法 得到输入汉字字符串的对应拼音48
/// </summary>49
/// <param name="chrstr">汉字字符串</param>50
/// <returns>返回对应的拼音</returns>51
public static string Convert(string chrstr)52
{53
byte[] byteArray = new byte[2];54
string returnStr = "";55
int chrAsc = 0;56
int i1 = 0;57
int i2 = 0;58
char[] nowChar = chrstr.ToCharArray();59
for (int j = 0; j < nowChar.Length; j++)60
{61
byteArray = Encoding.Default.GetBytes(nowChar[j].ToString());62
i1 = (short)byteArray[0];63
i2 = (short)byteArray[1];64
chrAsc = i1 * 256 + i2 - 65536;65
if (chrAsc > 0 && chrAsc < 160)66
{67
returnStr += nowChar[j];68
}69
else70
{71
for (int i = (pyvalue.Length - 1); i >= 0; i--)72
{73
if (pyvalue[i] <= chrAsc)74
{75
returnStr += pystr[i];76
break;77
}78
}79
}80
}81

82
return returnStr;83
}84

85
/// <summary>86
/// 得到汉字拼音缩写87
/// </summary>88
/// <param name="str">汉字字符串</param>89
/// <returns>返回汉字字符串的的拼音缩写</returns>90
public string GetPYString(string str)91
{92
string tempStr = "";93
foreach (char c in str)94
{95
if ((int)c >= 33 && (int)c <= 126)96
{97
//字母和符号原样保留98
tempStr += c.ToString();99
}100
else101
{102
//累加拼音声母103
tempStr += GetPYChar(c.ToString());104
}105
}106

107
return tempStr;108
}109

110
/// <summary>111
/// 取单个字符的拼音字母112
/// </summary>113
/// <param name="c">汉字</param>114
/// <returns>返回拼音字母</returns>115
public string GetPYChar(string c)116
{117
byte[] byteArray = new byte[2];118
byteArray = Encoding.Default.GetBytes(c);119
int i = (short)(byteArray[0] - '\0') * 256 + (short)(byteArray[1] - '\0');120

121
if (i < 0xB0A1) return "*";122
if (i < 0xB0C5) return "a";123
if (i < 0xB2C1) return "b";124
if (i < 0xB4EE) return "c";125
if (i < 0xB6EA) return "d";126
if (i < 0xB7A2) return "e";127
if (i < 0xB8C1) return "f";128
if (i < 0xB9FE) return "g";129
if (i < 0xBBF7) return "h";130
if (i < 0xBFA6) return "j";131
if (i < 0xC0AC) return "k";132
if (i < 0xC2E8) return "l";133
if (i < 0xC4C3) return "m";134
if (i < 0xC5B6) return "n";135
if (i < 0xC5BE) return "o";136
if (i < 0xC6DA) return "p";137
if (i < 0xC8BB) return "q";138
if (i < 0xC8F6) return "r";139
if (i < 0xCBFA) return "s";140
if (i < 0xCDDA) return "t";141
if (i < 0xCEF4) return "w";142
if (i < 0xD1B9) return "x";143
if (i < 0xD4D1) return "y";144
if (i < 0xD7FA) return "z";145

146
return "*"; 147
}148
}


浙公网安备 33010602011771号