RegexQuery正则表达式源代码

package query;


import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;


public class RegexQuery {


public static void main(String[] args) {
// TODO 自动生成的方法存根
IndexWriter writer = new IndexWriter(INDEX_STORE_PATH, new StandardAnalyzer(), true);
writer.setUseCompoundFile(false);
//创建8个文档
Document doc1 = new Document();
Document doc2 = new Document();
Document doc3 = new Document();


Field f1 = new Field("content", "word",Field.Store.YES, Field.Index.TOKENIZED);
Field f2 = new Field("content", "work",Field.Store.YES, Field.Index.TOKENIZED);
Field f3 = new Field("content", "world",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(INDEX_STORE_PATH);

//构建1个个正则表达式，用于匹配所有域名abc.com的地址
String regex = "http://[a-z]{1,3}\\.abc\\.com/.*";

//构成term
Term t = new Term("url", regex);

//创建正则查询
RegexQuery query = new RegexQuery(t);

//打印查询结果
Hits hits = searcher.search(query);
for(int i = 0; i < hits.length(); i++){
System.out.println(hits.doc(i));
}




}


}