LuceneInAction-explain()理解搜索结果评分

来源：互联网发布：mirna数据库编辑：程序博客网时间：2024/06/05 15:52

Explainer.java

import org.apache.lucene.analysis.SimpleAnalyzer;import org.apache.lucene.document.Document;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.search.Explanation;import org.apache.lucene.search.TopDocs;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.store.Directory;import org.apache.lucene.util.Version;import java.io.File;// From chapter 3public class Explainer {  public static void main(String[] args) throws Exception {    String indexDir = "indexes/MeetLucene";    String queryExpression = "apache";    Directory directory = FSDirectory.open(new File(indexDir));    QueryParser parser = new QueryParser(Version.LUCENE_30,                                         "contents", new SimpleAnalyzer());    Query query = parser.parse(queryExpression);    System.out.println("Query: " + queryExpression);    IndexSearcher searcher = new IndexSearcher(directory);    TopDocs topDocs = searcher.search(query, 10);    for (ScoreDoc match : topDocs.scoreDocs) {      Explanation explanation         = searcher.explain(query, match.doc);     //#A      System.out.println("----------");      Document doc = searcher.doc(match.doc);      System.out.println(doc.get("filename"));      System.out.println(explanation.toString());  //#B    }    searcher.close();    directory.close();  }}/*#A Generate Explanation#B Output Explanation*/

结果：

Query: apache----------apache1.0.txt0.5776299 = (MATCH) fieldWeight(contents:apache in 0), product of:  3.8729835 = tf(termFreq(contents:apache)=15)  2.3862944 = idf(docFreq=3, maxDocs=16)  0.0625 = fieldNorm(field=contents, doc=0)----------apache1.1.txt0.49465272 = (MATCH) fieldWeight(contents:apache in 1), product of:  3.3166249 = tf(termFreq(contents:apache)=11)  2.3862944 = idf(docFreq=3, maxDocs=16)  0.0625 = fieldNorm(field=contents, doc=1)----------apache2.0.txt0.13050047 = (MATCH) fieldWeight(contents:apache in 2), product of:  2.0 = tf(termFreq(contents:apache)=4)  2.3862944 = idf(docFreq=3, maxDocs=16)  0.02734375 = fieldNorm(field=contents, doc=2)

0 0