全文检索技术(二)：Lucene的索引库维护

1、索引库的添加 

    /**
     * 索引库添加
     * @throws Exception
     */
    @Test
    public void addDocument() throws Exception {
        //创建一个IndexWriter对象，需要使用IKAnalyzer作为分析器
        indexWriter =
                new IndexWriter(FSDirectory.open(new File("E:\\Resources\\temp\\index").toPath()),
                        new IndexWriterConfig(new IKAnalyzer()));
        //创建一个Document对象
        Document document = new Document();
        //向document对象中添加域
        document.add(new TextField("name", "新添加的文件", Field.Store.YES));
        document.add(new TextField("content", "新添加的文件内容", Field.Store.NO));
        document.add(new StoredField("path", "e:/Resources/temp/hello"));
        // 把文档写入索引库
        indexWriter.addDocument(document);
        //关闭索引库
        indexWriter.close();
    }

2、索引库的修改 

    /**
     * 索引库文档更新
     * @throws Exception
     */
    @Test
    public void updateDocument() throws Exception {
        //创建一个IndexWriter对象，需要使用IKAnalyzer作为分析器
        indexWriter =
                new IndexWriter(FSDirectory.open(new File("E:\\Resources\\temp\\index").toPath()),
                        new IndexWriterConfig(new IKAnalyzer()));
        //创建一个新的文档对象
        Document document = new Document();
        //向文档对象中添加域
        document.add(new TextField("name", "更新之后的文档", Field.Store.YES));
        document.add(new TextField("name1", "更新之后的文档2", Field.Store.YES));
        document.add(new TextField("name2", "更新之后的文档3", Field.Store.YES));
        //更新操作
        indexWriter.updateDocument(new Term("name", "spring"), document);
        //关闭索引库
        indexWriter.close();
    }

3、索引库的删除 

    /**
     * 索引库删除全部文档
     * @throws Exception
     */
    @Test
    public void deleteAllDocument() throws Exception {
        //创建一个IndexWriter对象，需要使用IKAnalyzer作为分析器
        indexWriter =
                new IndexWriter(FSDirectory.open(new File("E:\\Resources\\temp\\index").toPath()),
                        new IndexWriterConfig(new IKAnalyzer()));
        //删除全部文档
        indexWriter.deleteAll();
        //关闭索引库
        indexWriter.close();
    }

    /**
     * 删除指定内容的文档
     * @throws Exception
     */
    @Test
    public void deleteDocumentByQuery() throws Exception {
        //创建一个IndexWriter对象，需要使用IKAnalyzer作为分析器
        indexWriter =
                new IndexWriter(FSDirectory.open(new File("E:\\Resources\\temp\\index").toPath()),
                        new IndexWriterConfig(new IKAnalyzer()));
        indexWriter.deleteDocuments(new Term("name", "apache"));
        indexWriter.close();
    }

4、索引库的查询 

package com.wedu.lucene;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.LongPoint;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;

import java.io.File;

/**
 * 索引库的查询
 */
public class SearchIndex {
    private IndexReader indexReader;
    private IndexSearcher indexSearcher;
    @Before
    public void init() throws Exception {
        indexReader = DirectoryReader.open(FSDirectory.open(new File("E:\\Resources\\temp\\index").toPath()));
        indexSearcher = new IndexSearcher(indexReader);
    }

    /**
     * 范围查询
     * @throws Exception
     */
    @Test
    public void testRangeQuery() throws Exception {
        //创建一个Query对象
        Query query = LongPoint.newRangeQuery("size", 0l, 100l);
        printResult(query);
    }

    private void printResult(Query query) throws Exception {
        //执行查询
        TopDocs topDocs = indexSearcher.search(query, 10);
        System.out.println("总记录数：" + topDocs.totalHits);
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (ScoreDoc doc:scoreDocs){
            //取文档id
            int docId = doc.doc;
            //根据id取文档对象
            Document document = indexSearcher.doc(docId);
            System.out.println(document.get("name"));
            System.out.println(document.get("path"));
            System.out.println(document.get("size"));
            //System.out.println(document.get("content"));
            System.out.println("-----------------寂寞的分割线");
        }
        indexReader.close();
    }

    /**
     * 使用QueryPaser查询
     * @throws Exception
     */
    @Test
    public void testQueryParser() throws Exception {
        //创建一个QueryPaser对象，两个参数
        QueryParser queryParser = new QueryParser("name", new IKAnalyzer());
        //参数1：默认搜索域，参数2：分析器对象
        //使用QueryPaser对象创建一个Query对象
        Query query = queryParser.parse("lucene是一个Java开发的全文检索工具包");
        //执行查询
        printResult(query);
    }
}