Lucene自定义评分查询

最新推荐文章于 2025-08-12 11:12:45 发布

转载最新推荐文章于 2025-08-12 11:12:45 发布 · 577 阅读

文章标签：

#lucene #filenames #subquery #query #float #class

Luence 专栏收录该内容

24 篇文章

订阅专栏

本文介绍了一种使用自定义评分算法优化Lucene搜索的方法，通过结合原有查询和额外评分域，实现更精确的搜索结果排序。重点展示了如何创建自定义评分查询、评分提供者以及在搜索过程中应用这些组件，最终输出包含评分信息的搜索结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package com.lucene.score;

import java.io.IOException;
import java.sql.Date;
import java.text.SimpleDateFormat;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.FieldCache;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.function.CustomScoreProvider;
import org.apache.lucene.search.function.CustomScoreQuery;
import org.apache.lucene.search.function.FieldScoreQuery;
import org.apache.lucene.search.function.FieldScoreQuery.Type;
import org.apache.lucene.search.function.ValueSourceQuery;

import com.lucene.search.IndexUtils;

public class MyCustomScore {
     public void searchByScoreQuery() {
         try {
             IndexSearcher searcher = new IndexSearcher(
                     IndexReader.open(IndexUtils.getDirectory()));
             Query q = new TermQuery(new Term("content", "1"));
             // 1.创建评分域
             FieldScoreQuery fieldScoreQuery = new FieldScoreQuery("size",
                     Type.INT);
             // 2.根据评分域和原有的query创建自定义的query对象
             // 2.1 创建MyCustomScoreQuery继承CustomScoreQuery
             // 2.2重写getCustomScoreProvider方法
             // 2.3创建MyCustomScoreProvider继承CustomScoreProvider
             // 2.4重写customScore方法,自定义评分算法
             MyCustomScoreQuery query = new MyCustomScoreQuery(q,
                     fieldScoreQuery);
             TopDocs docs=searcher.search(query, 30);
             // 输出信息
             ScoreDoc[] sds = docs.scoreDocs;
             Document d = null;
             SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss");
             for (ScoreDoc s : sds) {
                 d = searcher.doc(s.doc);
                 System.out.println(s.doc + "->" + s.score + "->"
                         + d.get("filename") + "->" + d.get("size") + "->"
                         + sdf.format(new Date(Long.valueOf(d.get("date")))));
             }

         } catch (CorruptIndexException e) {
             e.printStackTrace();
         } catch (IOException e) {
             e.printStackTrace();
         }
     }
}

@SuppressWarnings("serial")
class MyCustomScoreQuery extends CustomScoreQuery {

     public MyCustomScoreQuery(Query subQuery, ValueSourceQuery valSrcQuery) {
         super(subQuery, valSrcQuery);
     }

     @Override
     protected CustomScoreProvider getCustomScoreProvider(IndexReader reader)
             throws IOException {
         // 默认情况评分是根据原有的评分*传入进来的评分
         //return super.getCustomScoreProvider(reader);

         return new MyCustomScoreProvider(reader);
     }
}

class MyCustomScoreProvider extends CustomScoreProvider {

     String[] filenames = null;

     public MyCustomScoreProvider(IndexReader reader) {
         super(reader);
         try {
             filenames = FieldCache.DEFAULT.getStrings(reader, "filename");
         } catch (IOException e) {
             e.printStackTrace();
         }
     }

     @Override
     public float customScore(int doc, float subQueryScore, float valSrcScore)
             throws IOException {
         // 根据doc获取文件名
         String filename = filenames[doc];
         //判断文件后缀是否为txt结尾,是把评分*10 否则/10
         if (filename.endsWith(".txt")) {
             return subQueryScore * 10;
         } else {
             return subQueryScore / 10;
         }
     }

}

 @Test
    public void test01(){
        MyCustomScore score=new MyCustomScore();
        score.searchByScoreQuery();
    }