booleanQuery termQuery 例子

阅读更多

转自：http://zhxmyself.iteye.com/blog/466066

 

 

 

 

应用BooleanQuery进行组合查询时,条件之间的关系是由类BooleanClause.Occur控制的,BooleanClause.Occur中提供了三个参数值进行控制,分别是BooleanClause.Occur.MUST 
BooleanClause.Occur.MUST_NOT 
BooleanClause.Occur.SHOULD 

它们的组合关系代表的意思如下: 
1、MUST和MUST表示“与”的关系，即“并集”。 
2、MUST和MUST_NOT前者包含后者不包含。 
3、MUST_NOT和MUST_NOT没意义 
4、SHOULD与MUST表示MUST，SHOULD失去意义； 
5、SHOUlD与MUST_NOT相当于MUST与MUST_NOT。 
6、SHOULD与SHOULD表示“或”的概念。 

BooleanQuery的条件生成方法如下： 
Term term1 = new Term(FIELD_CONTENT,"共"); 
TermQuery q1 = new TermQuery(term1); 
BooleanQuery booleanQuery = new BooleanQuery(); 
booleanQuery.add(q1, BooleanClause.Occur.MUST); 

package com.zhx.test;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.LockObtainFailedException;

public class BooleanQuerySearcher {

    /**
     * @param args
     */
    public static void main(String[] args) {
         //索引目录
         String IDNEX_PATH = "Z:/data/paoding/test_index";
         //字段名
         String FIELD_NAME = "field_name";
         //字段名
         String FIELD_CONTENT = "field_content";
            //获取Paoding中文分词器
            Analyzer analyzer = new StandardAnalyzer();
            //建立索引
            IndexWriter writer;
            try {
                writer = new IndexWriter(IDNEX_PATH, analyzer, true,new IndexWriter.MaxFieldLength(10));

                Document doc = new Document();
                Field field = new Field(FIELD_NAME, "第一条记录", Field.Store.YES,
                        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                doc.add(field);
                field = new Field(FIELD_CONTENT, "中华人民共和国", Field.Store.YES,
                        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                doc.add(field);
                writer.addDocument(doc);

                doc = new Document();
                field = new Field(FIELD_NAME, "第二条记录", Field.Store.YES,
                        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                doc.add(field);
                field = new Field(FIELD_CONTENT, "人民共和国", Field.Store.YES,
                        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                doc.add(field);
                writer.addDocument(doc);
                writer.close();
                System.out.println("Indexed success!");

                //检索
                IndexReader reader = IndexReader.open(IDNEX_PATH);
                //生成查询条件
                Term term1 = new Term(FIELD_CONTENT,"共");
                Term term2 = new Term(FIELD_CONTENT,"人");
                Term term3 = new Term(FIELD_NAME,"二");
                TermQuery q1 = new TermQuery(term1);
                TermQuery q2 = new TermQuery(term2);
                TermQuery q3 = new TermQuery(term3);
                BooleanQuery booleanQuery = new BooleanQuery();
                booleanQuery.add(q1, BooleanClause.Occur.MUST);
                booleanQuery.add(q2, BooleanClause.Occur.MUST);
                booleanQuery.add(q3, BooleanClause.Occur.MUST_NOT);
                Searcher searcher = new IndexSearcher(reader);
                TopDocs topDocs = searcher.search(booleanQuery,10);
                if (topDocs.totalHits == 0) {
                    System.out.println("topDocs.totalHits = 0");
                } else{
                    ScoreDoc[] scoreDocs = topDocs.scoreDocs;
                    for(int i=0;i
                        int docId = scoreDocs[i].doc;
                        Document document = searcher.doc(docId);
                        System.out.println("记录"+i+":"+document.get(FIELD_NAME)+" "+document.get(FIELD_CONTENT));
                    }
                }
                reader.close();
            } catch (CorruptIndexException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            } catch (LockObtainFailedException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }

    }

}