ChineseParse.cs //分詞器
1 /**//// <summary>
2 /// 中文分詞器。
3 /// </summary>
4 public class ChineseParse
5 {
6 private static ChineseWordsHashCountSet _countTable;
7
8 static ChineseParse()
9 {
10 _countTable = new ChineseWordsHashCountSet();
11 InitFromFile("ChineseDictionary.txt");
12 }
13
14 /**//// <summary>
15 /// 從指定的文件中初始化中文詞語字典和字符串次數字典。
16 /// </summary>
17 /// <param name="fileName">文件名</param>
18 private static void InitFromFile(string fileName)
19 {
20 string path = Directory.GetCurrentDirectory() +@"\" + fileName;
21 if (File.Exists(path))
22 {
23 using (StreamReader sr = File.OpenText(path))
24 {
25 string s = "";
26 while ((s = sr.ReadLine()) != null)
27 {
28 ChineseWordUnit _tempUnit = InitUnit(s);
29 _countTable.InsertWord(_tempUnit.Word);
30 }
31 }
32 }
33 }
34
35 /**//// <summary>
36 /// 將一個字符串解析為ChineseWordUnit。
37 /// </summary>
38 /// <param name="s">字符串</param>
39 /// <returns>解析得到的ChineseWordUnit</returns>
40 private static ChineseWordUnit InitUnit(string s)
41 {
42 Regex reg = new Regex(@"\s+");
43 string[] temp = reg.Split(s);
44 if (temp.Length!=2)
45 {
46 throw new Exception("字符串解析錯誤："+s);
47 }
48 return new ChineseWordUnit(temp[0],Int32.Parse(temp[1]));
49 }
50
51 /**//// <summary>
52 /// 分析輸入的字符串，將其切割成一個個的詞語。
53 /// </summary>
54 /// <param name="s">待切割的字符串</param>
55 /// <returns>所切割得到的中文詞語數組</returns>
56 public static string[] ParseChinese(string s)
57 {
58 int _length = s.Length;
59 string _temp = String.Empty;
60 ArrayList _words = new ArrayList();
61
62 for(int i=0;i<s.Length;)
63 {
64 _temp = s.Substring(i,1);
65 if (_countTable.GetCount(_temp)>1)
66 {
67 int j=2;
68
69 for (;i+j<s.Length+1&&_countTable.GetCount(s.Substring(i,j))>0;j++)
70 {
71 }
72 _temp = s.Substring(i,j-1);
73 i = i + j - 2;
74 }
75 i++;
76 _words.Add(_temp);
77 }
78
79 string[] _tempStringArray = new string[_words.Count];
80 _words.CopyTo(_tempStringArray);
81 return _tempStringArray;
82 }
83 }
