Apache Lucene 评分原理及代码分析

hebwxw

　　在IndexSearcher类中有一个管理Lucene得分情况的方法，如下所示：



1 public Explanation explain(Weight weight, int doc) throws IOException {
2     return weight.explain(reader, doc);
3 }
　　返回的这个Explanation的实例解释了Lucene中Document的得分情况。我们可以测试一下，直观地感觉一下到底这个Explanation的实例都记录了一个Document的哪些信息。
　　写一个测试类，如下所示：



  1 package org.shirdrn.lucene.learn;
  2
  3 import java.io.IOException;
  4 import java.util.Date;
  5
  6 import net.teamhot.lucene.ThesaurusAnalyzer;
  7
  8 import org.apache.lucene.document.Document;
  9 import org.apache.lucene.document.Field;
10 import org.apache.lucene.index.CorruptIndexException;
11 import org.apache.lucene.index.IndexWriter;
12 import org.apache.lucene.index.Term;
13 import org.apache.lucene.index.TermDocs;
14 import org.apache.lucene.search.Explanation;
15 import org.apache.lucene.search.Hits;
16 import org.apache.lucene.search.IndexSearcher;
17 import org.apache.lucene.search.Query;
18 import org.apache.lucene.search.TermQuery;
19 import org.apache.lucene.store.LockObtainFailedException;
20
21 public class AboutLuceneScore {
22
23 private String path = "E:\\Lucene\\index";
24
25 public void createIndex(){
26    IndexWriter writer;
27    try {
28     writer = new IndexWriter(path,new ThesaurusAnalyzer(),true);
29   
30     Field fieldA = new Field("contents","一人",Field.Store.YES,Field.Index.TOKENIZED);
31     Document docA = new Document();
32     docA.add(fieldA);
33   
34     Field fieldB = new Field("contents","一人 之交 一人之交",Field.Store.YES,Field.Index.TOKENIZED);
35     Document docB = new Document();
36     docB.add(fieldB);
37   
38     Field fieldC = new Field("contents","一人 之下 一人之下",Field.Store.YES,Field.Index.TOKENIZED);
39     Document docC = new Document();
40     docC.add(fieldC);
41   
42     Field fieldD = new Field("contents","一人 做事 一人当 一人做事一人当",Field.Store.YES,Field.Index.TOKENIZED);
43     Document docD = new Document();
44     docD.add(fieldD);
45   
46     Field fieldE = new Field("contents","一人 做事 一人當 一人做事一人當",Field.Store.YES,Field.Index.TOKENIZED);
47     Document docE = new Document();
48     docE.add(fieldE);
49
50     writer.addDocument(docA);
51     writer.addDocument(docB);
52     writer.addDocument(docC);
53     writer.addDocument(docD);
54     writer.addDocument(docE);
55   
56     writer.close();
57    } catch (CorruptIndexException e) {
58     e.printStackTrace();
59    } catch (LockObtainFailedException e) {
60     e.printStackTrace();
61    } catch (IOException e) {
62     e.printStackTrace();
63    }
64 }
65
66 public static void main(String[] args) {
67    AboutLuceneScore aus = new AboutLuceneScore();
68    aus.createIndex();    // 建立索引
69    try {
70     String keyword = "一人";
71     Term term = new Term("contents",keyword);
72     Query query = new TermQuery(term);
73     IndexSearcher searcher = new IndexSearcher(aus.path);
74     Date startTime = new Date();
75     Hits hits = searcher.search(query);
76     TermDocs termDocs = searcher.getIndexReader().termDocs(term);
77     while(termDocs.next()){
78      System.out.print("搜索关键字在编号为 "+termDocs.doc());
79      System.out.println(" 的Document中出现过 "+termDocs.freq()+" 次");
80     }
81     System.out.println("********************************************************************");
82     for(int i=0;i