搜索学习入门--Lucene初体验（Lucene索引的增删改查）

Lucene是一个开放源代码的全文检索引擎工具包，它提供了完整的查询引擎和索引引擎，开发人员可以方便的在目标系统中实现全文检索。Lucene的核心使用的是基于倒排索引的，并且实现了实现了分块索引。下面，先来体验一下Lucene对索引的增删改查功能。Lucene存储对象是以document为存储单元，对象中相关的属性值则存放到Field中。

第一步：引入依赖

    org.apache.lucene
    lucene-core
    4.7.2




    org.apache.lucene
    lucene-queryparser
    4.7.2




    org.apache.lucene
    lucene-analyzers-common
    4.7.2

第二步：建立索引

这里使用标准分词器建立5个Document的索引

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.index.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;

/**
 * created by yuyufeng on 2017/11/13.
 */
public class LuceneIndexDemo {
    public static void main(String[] args) {
        // Lucene Document的域名
        String fieldName = "blog";
        String text = "";
        // 建立5条索引
        text = "10月11日杭州云栖大会上，马云表达了对新建成的阿里巴巴全球研究院—阿里巴巴达摩院的愿景，希望达摩院二十年内成为世界第一大经济体，服务世界二十亿人，创造一亿个工作岗位。";
        doIndex(fieldName, text);
        text = "中国互联网界，阿里巴巴被认为是技术实力最弱的公司。我确实不懂技术，承认不懂技术不丢人，不懂装懂才丢人。";
        doIndex(fieldName, text);
        text = "阿里巴巴未来二十年的目标是打造世界第五大经济体，不是我们狂妄，而是世界需要这么一个经济体，也一定会有这么一个经济体。";
        doIndex(fieldName, text);
        text = "达摩院一定也必须要超越英特尔，必须超越微软，必须超越IBM，因为我们生于二十一世纪，我们是有机会后发优势的。";
        doIndex(fieldName, text);
        text = "阿里巴巴有很多争议，似乎无处不在，我还真想不出有什么东西是我们不做的。互联网是一种思想，是一种技术革命，不应该有界限。跨界乐趣无穷。我觉得阿里巴巴的跨界还不错";
        doIndex(fieldName, text);


    }

    private static void doIndex(String fieldName, String text) {
        // 实例化IKAnalyzer分词器
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);

        Directory directory = null;
        IndexWriter iwriter;
        try {
            // 索引目录
            directory = new SimpleFSDirectory(new File("D://test/lucene_index"));

            // 配置IndexWriterConfig
            IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_47, analyzer);
            iwConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
            iwriter = new IndexWriter(directory, iwConfig);
            // 写入索引
            Document doc = new Document();
            Long id = System.currentTimeMillis();
            doc.add(new StringField("ID", id+"", Field.Store.YES));
            doc.add(new TextField(fieldName, text, Field.Store.YES));
            iwriter.addDocument(doc);
            iwriter.close();
            System.out.println("建立索引成功:" + id);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (directory != null) {
                try {
                    directory.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

运行结果：
建立索引成功:1510579712099
建立索引成功:1510579712355
建立索引成功:1510579712512
建立索引成功:1510579712743
建立索引成功:1510579712912

查看索引文件：运行之后，打开我们存放索引的文件夹，你会看到如下文件列表结构：

这里写图片描述

第三步:搜索查询

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
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.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;

/**
 * created by yuyufeng on 2017/11/13.
 */
public class LuceneSearchDemo {
    public static void main(String[] args) {

        // Lucene Document的域名
        String fieldName = "blog";
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
        Directory directory = null;
        IndexReader ireader = null;
        IndexSearcher isearcher;

        try {
            //索引目录
            directory = new SimpleFSDirectory(new File("D://test/lucene_index"));
            // 配置IndexWriterConfig
            IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_47, analyzer);
            iwConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);

            // 搜索过程**********************************
            // 实例化搜索器
            ireader = DirectoryReader.open(directory);
            isearcher = new IndexSearcher(ireader);

            String keyword = "达摩院";
            // 使用QueryParser查询分析器构造Query对象
            QueryParser qp = new QueryParser(Version.LUCENE_47, fieldName, analyzer);
            qp.setDefaultOperator(QueryParser.OR_OPERATOR);  // and or 跟数据库查询语法类似
            Query query = qp.parse(keyword);
            System.out.println("Query = " + query);

            // 搜索相似度最高的5条记录
            TopDocs topDocs = isearcher.search(query, 5);
            System.out.println("命中：" + topDocs.totalHits);
            // 遍历输出结果
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (int i = 0; i < topDocs.totalHits; i++) {
                Document targetDoc = isearcher.doc(scoreDocs[i].doc);
                System.out.println("内容：" + targetDoc.toString());
            }
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (ireader != null) {
                try {
                    ireader.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (directory != null) {
                try {
                    directory.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }

    }
}

**keyword= ："达摩院"
运行结果：

Query = blog:达 blog:摩 blog:院
命中：2
内容：Document< stored,indexed,tokenized>
内容：Document stored,indexed,tokenized>    

---

**keyword= :"阿里巴巴达摩院"
运行结果：

Query = blog:阿 blog:里 blog:巴 blog:巴 blog:达 blog:摩 blog:院
命中：5
内容：Document stored,indexed,tokenized>
内容：Document stored,indexed,tokenized>
内容：Document stored,indexed,tokenized>
内容：Document stored,indexed,tokenized>
内容：Document stored,indexed,tokenized>

第四步：更新索引文档

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.index.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

public class LuceneUpdateDemo {
    public static void main(String[] args) {
        // 实例化IKAnalyzer分词器
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);

        Directory directory = null;
        IndexWriter iwriter;
        try {
            // 索引目录
            directory = new SimpleFSDirectory(new File("D://test/lucene_index"));

            // 配置IndexWriterConfig
            IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_47, analyzer);
            iwConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
            iwriter = new IndexWriter(directory, iwConfig);
            // 写入索引
            Document doc = new Document();
            String id = "1510579934220";
            doc.add(new StringField("ID", id, Field.Store.YES));
            doc.add(new TextField("blog", "更新文档后->达摩院一定也必须要超越英特尔，必须超越微软，必须超越IBM，因为我们生于二十一世纪，我们是有机会后发优势的。", Field.Store.YES));
            //先根据Term ID 删除，在建立新的索引
            iwriter.updateDocument(new Term("ID", id), doc);
            iwriter.close();
            System.out.println("更新索引成功:" + 1511233039462L);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (directory != null) {
                try {
                    directory.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

在执行第三步查询，即可查看更新结果

第五步：索引删除

package top.yuyufeng.learn.lucene.demo1;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.*;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;

/**
 * @author yuyufeng
 * @date 2017/11/21
 */
public class LuceneDeleteDemo {
    public static void main(String[] args) {
        // Lucene Document的域名
        String fieldName = "blog";
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
        Directory directory = null;
        IndexReader ireader = null;
        IndexSearcher isearcher;
        IndexWriter iwriter = null;
        try {
            //索引目录
            directory = new SimpleFSDirectory(new File("D://test/lucene_index"));
            // 配置IndexWriterConfig
            IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_47, analyzer);
            iwConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
            ireader = DirectoryReader.open(directory);
            iwriter = new IndexWriter(directory, iwConfig);
            iwriter.deleteDocuments(new Term("ID","1511235710648"));
            //使用IndexWriter进行Document删除操作时，文档并不会立即被删除，而是把这个删除动作缓存起来，当IndexWriter.Commit()或IndexWriter.Close()时，删除操作才会被真正执行。
            iwriter.commit();
            iwriter.close();
            ireader.close();
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (directory != null) {
                try {
                    directory.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

方法	说明
DeleteDocuments(Query query)	根据Query条件来删除单个或多个Document
DeleteDocuments(Query[] queries)	根据Query条件来删除单个或多个Document
DeleteDocuments(Term term)	根据Term来删除单个或多个Document
DeleteDocuments(Term[] terms)	根据Term来删除单个或多个Document
DeleteAll()	删除所有的Document