Lucene使用正则表达式查询

 

// 导入类包import org.apache.lucene.search.regex.*;



public static void regexQuery(String path) throws IOException
{
IndexWriter writer = new IndexWriter(path, new StandardAnalyzer(), true );
writer.setUseCompoundFile( false );

Document doc1 = new Document();
Document doc2 = new Document();
Document doc3 = new Document();

Field f1 = new Field( " url " ,
" http://www.abc.com/product?typeid=1&category=10&item=34 " ,
Field.Store.YES, Field.Index.TOKENIZED);
Field f2 = new Field( " url " ,
" http://www.def.com/product/show?typeid=3&catagory=10&item=23 " ,
Field.Store.YES, Field.Index.TOKENIZED);
Field f3 = new Field(
" url " ,
" http://www.ghi.com/product/list?catagory=4&typeid=19&order=32 " ,
Field.Store.YES, Field.Index.TOKENIZED);
doc1.add(f1);
doc2.add(f2);
doc3.add(f3);

writer.addDocument(doc1);
writer.addDocument(doc2);
writer.addDocument(doc3);

writer.close();

IndexSearcher searcher = new IndexSearcher(path);
// 创建一个正则表达式，用于匹配域名为abc.com的地址
String regex = " http://[a-z]{1,3}\.abc\.com/.* " ;

Term t = new Term( " url " , regex);

RegexQuery query = new RegexQuery(t);
Query q = new TermQuery( new Term( " url " , " http " ));
Hits hits = searcher.search(query);
for ( int i = 0 ; i < hits.length(); i ++ ) {
System.out.println(hits.doc(i));
}
searcher.close();
}

 

 

 

转载于:https://www.cnblogs.com/gaoyoubo/archive/2010/06/22/1965067.html