Lucene正则表达式查询RegenxQuery

1 /*
2 * 正则表达式查询
3 */
4
5
6 import java.io.IOException;
7
8 import org.apache.lucene.analysis.standard.StandardAnalyzer;
9 import org.apache.lucene.document.Document;
10 import org.apache.lucene.document.Field;
11 import org.apache.lucene.index.IndexWriter;
12 import org.apache.lucene.index.Term;
13 import org.apache.lucene.search.Hits;
14 import org.apache.lucene.search.IndexSearcher;
15 import org.apache.lucene.search.regex.RegexQuery; //第三方插件RegexQuery其jar为lucene-regex-2.9.4.jar
16
17
18
19 public class RegexQueryTest {
20
21 private static final String INDEX_STORE_PATH&＃61;"d:\\testRegexQuery";
22
23 public static void main(String[] args) throws IOException
24 {
25 //索引
26 indexwriter(INDEX_STORE_PATH);
27 System.out.println("建立索引完毕&＃xff01;");
28 //查询
29 search(INDEX_STORE_PATH);
30 System.out.println("检索完毕&＃xff01;");
31 }
32
33 //建立索引
34 public static void indexwriter(String path) throws IOException
35 {
36 IndexWriter writer&＃61;new IndexWriter( path ,new StandardAnalyzer(),true);
37 writer.setUseCompoundFile(false);
38 //创建三个文档
39 Document doc1&＃61;new Document();
40 Document doc2&＃61;new Document();
41 Document doc3&＃61;new Document();
42 Document doc4&＃61;new Document();
43 //构建三个URL地址用于正则匹配
44 Field f1&＃61;new Field("url","http://www.abc/com/profuct?type&＃61;1& cate&＃61;5",Field.Store.YES,
45 Field.Index.UN_TOKENIZED);
46 Field f2&＃61;new Field("url","http://def.com/product?type&＃61;5",Field.Store.YES,
47 Field.Index.UN_TOKENIZED);
48 Field f3&＃61;new Field("url","http://ghi/product?type&＃61;x",Field.Store.YES,
49 Field.Index.UN_TOKENIZED);
50 Field f4&＃61;new Field("url","http://xxx.abc/con/profuct?type&＃61;1& cate&＃61;5",Field.Store.YES,
51 Field.Index.UN_TOKENIZED);
52
53 doc1.add(f1);
54 doc2.add(f2);
55 doc3.add(f3);
56 doc4.add(f4);
57 writer.addDocument(doc1);
58 writer.addDocument(doc2);
59 writer.addDocument(doc3);
60 writer.addDocument(doc4);
61
62 //close
63 writer.close();
64 }
65
66 //查询函数
67 public static void search(String path) throws IOException
68 {
69 IndexSearcher searcher&＃61;new IndexSearcher(path);
70 //创建正则表达式
71 String regex&＃61;"].*";
72 //构建Term
73 Term term&＃61;new Term("url",regex);
74
75 RegexQuery query&＃61;new RegexQuery(term);
76
77 Hits hits&＃61;searcher.search(query);
78 for(int i&＃61;0;i)
79 System.out.println(hits.doc(i));
80 }
81 }