|
1
23
24
25 package org.apache.slide.index;
26
27 import java.io.FileReader  ;
28 import java.io.IOException ;
29 import java.io.Reader ;
30 import java.util.HashSet ;
31 import java.util.Iterator ;
32 import java.util.Set ;
33
34 import org.apache.lucene.analysis.Analyzer;
35 import org.apache.lucene.analysis.standard.StandardAnalyzer;
36 import org.apache.lucene.document.Document;
37 import org.apache.lucene.document.Field;
38 import org.apache.lucene.index.IndexReader;
39 import org.apache.lucene.index.IndexWriter;
40 import org.apache.lucene.index.Term;
41 import org.apache.lucene.queryParser.QueryParser;
42 import org.apache.lucene.search.Hits;
43 import org.apache.lucene.search.IndexSearcher;
44 import org.apache.lucene.search.Query;
45 import org.apache.lucene.search.Searcher;
46 import org.apache.lucene.store.Directory;
47 import org.apache.lucene.store.FSDirectory;
48
49
55 public class LuceneIndexer
56 {
57 private static final String DOC_ID = "documentId";
58
59
60 private String indexDb;
61
62
63 public LuceneIndexer (String indexDb)
64 {
65 this.indexDb = indexDb;
66 }
67
68
69
78 public void removeIndex (String docId) throws IOException
79 {
80 Directory directory = FSDirectory.getDirectory (indexDb, false);
81 IndexReader reader = IndexReader.open(directory);
82
83 Term deleteTerm = new Term(DOC_ID, docId);
84 reader.delete(deleteTerm);
85 reader.close();
86 directory.close();
87 }
88
89
98 public void index (String docId, Reader reader)
99 throws Exception
100 {
101 IndexWriter writer =
102 new IndexWriter(indexDb, new StandardAnalyzer(), false);
103
104
106 Document doc = new Document();
107 doc.add (Field.Text ("contents", reader));
108 Field field = new Field(DOC_ID, docId, true, true, true);
109 doc.add(field);
110 writer.addDocument(doc);
111 writer.optimize();
112 writer.close();
113 }
114
115 private static Reader getReader (String file) throws IOException
116 {
117 FileReader reader = new FileReader (file);
118 return reader;
119 }
120
121 private Set contains(String stringToFind) throws Exception
122 {
123 Set resultSet = new HashSet ();
124 Searcher searcher = new IndexSearcher (indexDb);
125 Analyzer analyzer = new StandardAnalyzer();
126
127 Query query = QueryParser.parse(stringToFind, "contents", analyzer);
128
129 Hits hits = searcher.search(query);
130
131 int noOfHits = hits.length();
132 for (int i = 0; i < noOfHits; i++)
133 {
134 Document doc = hits.doc(i);
135 String docId = doc.get(DOC_ID);
136 resultSet.add(docId);
137 }
138 searcher.close();
139 return resultSet;
140 }
141
142
143
153 public static void main(String [] args) throws Exception
154 {
155 String INDEX_DB ="D:\\projects\\tmp\\index";
156
157 LuceneIndexer indexer = new LuceneIndexer (INDEX_DB);
158
159 IndexWriter writer =
160 new IndexWriter(INDEX_DB, new StandardAnalyzer(), true);
161
162 writer.close();
163
164 String ottoFile = "otto.txt";
165 new LuceneIndexer (INDEX_DB).index (ottoFile, getReader(ottoFile));
166
167 System.out.println("expect one element otto.txt");
168 displayResult(indexer.contains("otto"));
169
170 new LuceneIndexer (INDEX_DB).index("fritz.txt", getReader("fritz.txt"));
171 System.out.println("expect fritz.txt");
172 displayResult(indexer.contains("fritz"));
173
174 System.out.println("expect fritz.txt and otto.txt");
175 displayResult(indexer.contains("Hallo"));
176
177 new LuceneIndexer (INDEX_DB).removeIndex ("otto.txt");
178
179 System.out.println("expect fritz.txt");
180 displayResult (indexer.contains("Hallo"));
181
182 System.out.println("expect null");
183 displayResult (indexer.contains("otto"));
184
185 new LuceneIndexer (INDEX_DB).removeIndex ("fritz.txt");
186
187 System.out.println("expect null");
188 displayResult(indexer.contains("fritz"));
189 }
190
191 private static void displayResult(Set result)
192 {
193 for (Iterator iter = result.iterator(); iter.hasNext();)
194 {
195 String element = (String ) iter.next();
196 System.out.println(element);
197 }
198
199 }
200 }
201 |
Popular Tags |
Java API By Example, From Geeks To Geeks.