lucene + IKAnalyzer 中文分词及索引,简单实例

1. import org.apache.lucene.document.Document;   
2. import org.apache.lucene.document.Field;   
3. import org.apache.lucene.document.DateTools;   
4. import org.apache.lucene.index.IndexWriter;   
5. import org.apache.lucene.queryParser.QueryParser;   
6. import org.apache.lucene.search.Hits;   
7. import org.apache.lucene.search.IndexSearcher;   
8. import org.apache.lucene.search.Query;   
9. import org.apache.lucene.store.Directory;   
10. import org.apache.lucene.store.FSDirectory;   
11. import org.mira.lucene.analysis.IK_CAnalyzer;   
12.   
13. import java.io.File;   
14. import java.io.FileNotFoundException;   
15. import java.io.IOException;   
16. import java.io.FileReader;   
17. import java.util.Date;   
18.   
19. public class Searcher {   
20.     private static String INDEX_DIR = Searcher.class.getResource("/").getPath()+"/data/index";//"c://lucene//index";   
21.     private static String DOC_DIR =   Searcher.class.getResource("/").getPath();//"c://lucene//doc";   
22.     public static void main(String[] args) throws Exception {   
23.          String queryString;   
24.          queryString = "测试";   
25.          File indexDir = new File(INDEX_DIR);   
26.          File docDir = new File(DOC_DIR);   
27.          Date start = new Date();   
28.         //必须先建索引   
29.         try {   
30.              IndexWriter writer = new IndexWriter(INDEX_DIR, new IK_CAnalyzer(), true);   
31.              System.out.println("Indexing to directory '" + INDEX_DIR + "'...");   
32.              indexDocs(writer, docDir);   
33.              System.out.println("Optimizing...");   
34.              writer.optimize();   
35.              writer.close();   
36.              Date end = new Date();   
37.              System.out.println(end.getTime() - start.getTime() + " total milliseconds");   
38.   
39.          } catch (IOException e) {   
40.              System.out.println(" caught a " + e.getClass() +   
41.                     "/n with message: " + e.getMessage());   
42.          }   
43.         if (!indexDir.exists() || !indexDir.isDirectory()) {   
44.             throw new Exception(indexDir   
45.                      + " does not exist or is not a directory.");   
46.          }   
47.          search(indexDir, queryString);   
48.      }   
49.   
50.     private static void indexDocs(IndexWriter writer, File file)   
51.             throws IOException {   
52.         if (file.canRead()) {   
53.             if (file.isDirectory()) {   
54.                  String[] files = file.list();   
55.                 if (files != null) {   
56.                     for (int i = 0; i < files.length; i++) {   
57.                          indexDocs(writer, new File(file, files[i]));   
58.                      }   
59.                  }   
60.              } else {   
61.                  System.out.println("adding " + file);   
62.                 try {   
63.                      writer.addDocument(getDocument(file));   
64.                  }   
65.                 catch (FileNotFoundException fnfe) {   
66.                     //   
67.                  }   
68.              }   
69.          }   
70.      }   
71.   
72.     private static Document getDocument(File f)   
73.             throws java.io.FileNotFoundException {   
74.          Document doc = new Document();   
75.          doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.UN_TOKENIZED));   
76.          doc.add(new Field("modified",   
77.                  DateTools.timeToString(f.lastModified(), DateTools.Resolution.MINUTE),   
78.                  Field.Store.YES, Field.Index.UN_TOKENIZED));   
79.          doc.add(new Field("contents", new FileReader(f)));   
80.         return doc;   
81.      }   
82.   
83.     public static void search(File indexDir, String q) throws Exception {   
84.          Directory fsDir = FSDirectory.getDirectory(indexDir);   
85.          IndexSearcher is = new IndexSearcher(fsDir);// ① 打开索引   
86.          Query query = new QueryParser("contents", new IK_CAnalyzer()).parse(q); // ② 分析查询   
87.         long start = new Date().getTime();   
88.          Hits hits = is.search(query);// ③ 搜索索引   
89.         long end = new Date().getTime();   
90.          System.err.println("Found " + hits.length() + " document(s) (in "  
91.                  + (end - start) + "milliseconds) that matched query" + q + ":");   
92.         for (int i = 0; i < hits.length(); i++) {   
93.              Document doc = hits.doc(i); // ④ 得到匹配的文档   
94.              System.out.println("file: " + doc.get("path"));   
95.          }   
96.      }   
97. }   
98. 正向全切分分词器：org.mira.lucene.analysis.IK_CAnalyzer（适合建索引时使用）
    
    正向最大全切分分词器：org.mira.lucene.analysis.MIK_CAnalyzer（适合用户输入检索时使用）

来源：http://hi.baidu.com/happy19840402/blog/item/7f48ce2e462aff554fc226d6.html