lucene in action_index and search

  1 /**
  2  * 
  3  */
  4 package com.b510.index;
  5 
  6 import java.io.File;
  7 import java.io.FileFilter;
  8 import java.io.FileReader;
  9 
 10 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 11 import org.apache.lucene.document.Document;
 12 import org.apache.lucene.document.Field;
 13 import org.apache.lucene.index.IndexWriter;
 14 import org.apache.lucene.store.Directory;
 15 import org.apache.lucene.store.FSDirectory;
 16 import org.apache.lucene.util.Version;
 17 
 18 /**
 19  * 建立索引
 20  * 
 21  * @author hongten(hongtenzone@foxmail.com)<br>
 22  * @date 2013-4-5
 23  */
 24 public class Indexer {
 25 
 26     public static void main(String[] args) throws Exception {
 27         if (args.length != 2) {
 28             throw new IllegalArgumentException("Usage: java " + Indexer.class.getName() + " <index dir><data dir>");
 29         }
 30         // 在指定目录创建索引
 31         String indexDir = args[0];
 32         String dataDir = args[1];
 33 
 34         long start = System.currentTimeMillis();
 35         Indexer index = new Indexer(indexDir);
 36         int numIndexed;
 37         try {
 38             numIndexed = index.index(dataDir, new TextFilesFilter());
 39         } finally {
 40             index.close();
 41         }
 42         long end = System.currentTimeMillis();
 43 
 44         System.out.println("indexing " + numIndexed + " files took " + (end - start) + " millseconds!");
 45     }
 46 
 47     private IndexWriter writer;
 48 
 49     @SuppressWarnings("deprecation")
 50     public Indexer(String indexDir) throws Exception {
 51         Directory dir = FSDirectory.open(new File(indexDir));
 52         // create lucene index writer
 53         writer = new IndexWriter(dir, new StandardAnalyzer(Version.LUCENE_35), true, IndexWriter.MaxFieldLength.UNLIMITED);
 54     }
 55 
 56     /**
 57      * close the IndexWriter
 58      * 
 59      * @throws Exception
 60      */
 61     public void close() throws Exception {
 62         writer.close();
 63     }
 64 
 65     /**
 66      * 返回被索引文件数
 67      * 
 68      * @param dataDir
 69      *            文件目录
 70      * @param filter
 71      * @return
 72      * @throws Exception
 73      */
 74     public int index(String dataDir, FileFilter filter) throws Exception {
 75         File[] files = new File(dataDir).listFiles();
 76 
 77         for (File f : files) {
 78             if (!f.isDirectory() && !f.isHidden() && f.exists() && f.canRead() && (filter == null || filter.accept(f))) {
 79                 indexFile(f);
 80             }
 81         }
 82         // 返回被索引的文档数目
 83         return writer.numDocs();
 84     }
 85 
 86     /**
 87      * 向lucene中添加文档
 88      * 
 89      * @param f
 90      *            文档
 91      * @throws Exception
 92      */
 93     private void indexFile(File f) throws Exception {
 94         System.out.println("Indexing " + f.getCanonicalPath());
 95         Document doc = getDocument(f);
 96         writer.addDocument(doc);
 97     }
 98 
 99     /**
100      * 添加索引
101      * 
102      * @param f
103      *            被索引的文件
104      * @return
105      * @throws Exception
106      */
107     protected Document getDocument(File f) throws Exception {
108         Document doc = new Document();
109         doc.add(new Field("contents", new FileReader(f)));
110         doc.add(new Field("filename", f.getName(), Field.Store.YES, Field.Index.NOT_ANALYZED));
111         doc.add(new Field("fullpath", f.getCanonicalPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
112         return doc;
113     }
114 
115     /**
116      * 只索引.txt文件，采用FileFilter
117      * 
118      * @author hongten(hongtenzone@foxmail.com)<br>
119      * @date 2013-4-5
120      */
121     private static class TextFilesFilter implements FileFilter {
122         @Override
123         public boolean accept(File pathname) {
124             return pathname.getName().toLowerCase().endsWith(".txt");
125         }
126     }
127 
128 }

 1 /**
 2  * 
 3  */
 4 package com.b510.search;
 5 
 6 import java.io.File;
 7 import java.io.IOException;
 8 
 9 import org.apache.lucene.analysis.standard.StandardAnalyzer;
10 import org.apache.lucene.document.Document;
11 import org.apache.lucene.queryParser.ParseException;
12 import org.apache.lucene.queryParser.QueryParser;
13 import org.apache.lucene.search.IndexSearcher;
14 import org.apache.lucene.search.Query;
15 import org.apache.lucene.search.ScoreDoc;
16 import org.apache.lucene.search.TopDocs;
17 import org.apache.lucene.store.Directory;
18 import org.apache.lucene.store.FSDirectory;
19 import org.apache.lucene.util.Version;
20 
21 import com.b510.index.Indexer;
22 
23 /**
24  * 搜索功能
25  * @author hongten(hongtenzone@foxmail.com)<br>
26  * @date 2013-4-5
27  */
28 public class Searcher {
29 
30     public static void main(String[] args) throws IllegalArgumentException, IOException, ParseException {
31         if (args.length != 2) {
32             throw new IllegalArgumentException("Usage: java " + Indexer.class.getName() + " <index dir><data dir>");
33         }
34         // 在指定目录创建索引
35         String indexDir = args[0];
36         String q = args[1];
37 
38         search(indexDir, q);
39     }
40 
41     /**
42      * 搜索
43      * @param indexDir 搜索目录
44      * @param q 关键字
45      * @throws IOException
46      * @throws ParseException
47      */
48     public static void search(String indexDir, String q) throws IOException, ParseException {
49         Directory dir = FSDirectory.open(new File(indexDir));
50         IndexSearcher is = new IndexSearcher(dir);
51         
52         QueryParser parser = new QueryParser(Version.LUCENE_35,"contents",new StandardAnalyzer(Version.LUCENE_35));
53         Query query = parser.parse(q);
54         long start = System.currentTimeMillis();
55         TopDocs hits = is.search(query, 10);
56         long end = System.currentTimeMillis();
57         
58         System.out.println("Found "+hits.totalHits + " document(s) (in " + (end - start) +" millsecondes) that matched query '"+ q+"':");
59         
60         for(ScoreDoc scoreDoc : hits.scoreDocs){
61             Document doc = is.doc(scoreDoc.doc);
62             System.out.println(doc.get("fullpath"));
63         }
64         
65         is.close();
66     }
67 }