Lucene笔记05-Lucene索引加权操作和Luke的简单演示

一、给索引加权

package com.wsy;

import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class IndexUtil {
    private String[] ids = {"1", "2", "3", "4", "5", "6"};
    private String[] emails = {"a@a.com", "b@b.com", "c@c.com", "d@d.com", "e@e.com", "f@f.com"};
    private String[] contents = {"content 1", "content 2", "content 3", "content 4", "content 5", "content 6"};
    private int[] attachFiles = {1, 2, 3, 4, 5, 6};
    private String[] names = {"qianyi", "zhaoer", "zhangsan", "lisi", "wangwu", "liuliu"};
    private Directory directory = null;
    private Map<String, Float> scores = new HashMap<>();

    public IndexUtil() {
        try {
            // 设置加权，默认权重是1.0，数值越大权重越高
            scores.put("a.com",1.5f);
            scores.put("b.com",1.6f);
            scores.put("c.com",1.7f);
            scores.put("d.com",1.8f);
            scores.put("e.com",1.9f);
            scores.put("f.com",2.0f);
            directory = FSDirectory.open(new File("E:\\Lucene\\IndexLibrary"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public void index() {
        IndexWriter indexWriter = null;
        try {
            indexWriter = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
            Document document = null;
            for (int i = 0; i < ids.length; i++) {
                document = new Document();
                document.add(new Field("id", ids[i], Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
                document.add(new Field("email", emails[i], Field.Store.YES, Field.Index.NOT_ANALYZED));
                document.add(new Field("content", contents[i], Field.Store.NO, Field.Index.ANALYZED));
                document.add(new Field("name", names[i], Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
                String emailType = emails[i].substring(emails[i].lastIndexOf("@")+1);
                if(scores.containsKey(emailType)){
                    document.setBoost(scores.get(emailType));
                } else {
                    document.setBoost(0.1f);
                }
                indexWriter.addDocument(document);
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (indexWriter != null) {
                try {
                    indexWriter.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    public void search() {
        try {
            IndexReader indexReader = IndexReader.open(directory);
            IndexSearcher indexSearcher = new IndexSearcher(indexReader);
            // 搜索content域包含“content”的
            TermQuery termQuery = new TermQuery(new Term("content", "content"));
            TopDocs topDocs = indexSearcher.search(termQuery, 10);
            for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
                Document document = indexSearcher.doc(scoreDoc.doc);
                System.out.println(document.get("name") + " " + document.getBoost() + " " + scoreDoc.score);
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (indexReader != null) {
                try {
                    indexReader.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

先将setBoost()语句注释掉，调用一遍index()和search()，记住输出，再将setBoost()还原再去index()和search()，就会发现和刚刚的顺序是不一样的，这时setBoost()就起作用了。可是比较奇怪的是，在加上setBoost()之后，为什么searcher()方法中的输出显示的boost还是1.0呢？是因为index()中的document和search()中的document不是同一个，不行你可以试一下，把document.hashCode()打印出来看一看就知道了。

二、Luke的使用

Luke的版本要和Lucene的版本对应，否则索引是打不开的。

下载之后，放到一个文件夹中，在文件夹中创建一个startup.bat文件，文件内容如下，将luke-3.5.0.jar放到当前文件夹下的target中，以后启动Luke的时候，直接运行这个bat文件就可以了。

start javaw -jar .\target\luke-3.5.0.jar

 先看个图，以后慢慢接触到了就会用了。