zoukankan html css js c++ java

lucene 简单实用

  1 package com.kite.luncene.helloworld;
  2 
  3 import java.io.File;
  4 import java.util.ArrayList;
  5 import java.util.List;
  6 
  7 import org.apache.lucene.analysis.Analyzer;
  8 import org.apache.lucene.analysis.standard.StandardAnalyzer;
  9 import org.apache.lucene.document.Document;
 10 import org.apache.lucene.document.Field;
 11 import org.apache.lucene.document.Field.Index;
 12 import org.apache.lucene.document.Field.Store;
 13 import org.apache.lucene.index.IndexWriter;
 14 import org.apache.lucene.index.IndexWriter.MaxFieldLength;
 15 import org.apache.lucene.queryParser.QueryParser;
 16 import org.apache.lucene.search.IndexSearcher;
 17 import org.apache.lucene.search.Query;
 18 import org.apache.lucene.search.ScoreDoc;
 19 import org.apache.lucene.search.TopDocs;
 20 import org.apache.lucene.store.Directory;
 21 import org.apache.lucene.store.FSDirectory;
 22 import org.apache.lucene.util.Version;
 23 import org.junit.Test;
 24 
 25 import com.kite.bean.Article;
 26 
 27 public class HelloWorld
 28 {
 29     @Test
 30     public void testCreate() throws Exception
 31     {
 32         /**
 33          * 1、创建一个article对象，并且把信息存放进去
 34          * 2、调用indexWriter的API把数据存放在索引库中
 35          * 3、关闭indexWriter
 36          */
 37         //创建一个article对象，并且把信息存放进去
 38         Article article = new Article();
 39         article.setId(1L);
 40         article.setTitle("java goodnice");
 41         article .setContent("多年来就是这么吊");
 42         
 43         //2、调用indexWriter的API把数据存放在索引库中
 44          /**
 45             * 创建一个IndexWriter
 46             *    参数三个
 47             *       1、索引库   指向索引库的位置
 48             *       2、分词器
 49             */
 50             //创建索引库
 51             Directory directory = FSDirectory.open(new File("./indexDir"));
 52             //创建分词器
 53             Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
 54         IndexWriter indexWriter = new IndexWriter(directory, analyzer, MaxFieldLength.LIMITED);
 55         
 56         //把一个对象转换成document
 57         Document document = new Document();
 58         Field idField = new Field("id", article.getId().toString(), Store.YES, Index.NOT_ANALYZED);
 59         Field titleField = new Field("title", article.getTitle(), Store.YES, Index.ANALYZED);
 60         Field contentField = new Field("content", article.getContent(), Store.YES, Index.ANALYZED);
 61         document.add(idField);
 62         document.add(titleField);
 63         document.add(contentField);
 64         indexWriter.addDocument(document);
 65         
 66         //3、关闭indexWriter
 67         indexWriter.close();
 68     }
 69     
 70     @Test
 71     public  void testSearchIndex() throws Exception
 72     {
 73         /**
 74          * 1.创建一个 indexSerach对象
 75          * 2.调用search方法进行检索
 76          * 3.输出内容
 77          */
 78         
 79         // 1.创建一个 indexSerach对象
 80         //--索引库
 81         Directory directory = FSDirectory.open(new File("./indexDir"));
 82         IndexSearcher searcher = new IndexSearcher(directory);
 83         //2..调用search方法进行检索
 84         //--
 85         Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
 86         QueryParser queryParser = new QueryParser(Version.LUCENE_30, "id", analyzer);
 87         //设置搜索的关键字
 88         Query query = queryParser.parse("1");
 89         TopDocs topDocs = searcher.search(query, 10);
 90         //获得根据关键字查询出来的总的记录数
 91         int count = topDocs.totalHits;
 92         List<Article> articles = new ArrayList<Article>();
 93         //获得数组
 94         ScoreDoc[] scoreDocs = topDocs.scoreDocs;
 95         for(ScoreDoc scoreDoc : scoreDocs)
 96         {
 97             //关键字得分
 98             float score = scoreDoc.score;
 99             //索引的下标
100             int index = scoreDoc.doc;
101             //根据索引获得document对象
102             Document document = searcher.doc(index);
103             //把document转化成article
104             Article article = new Article();
105             article.setId(Long.parseLong(document.get("id")));
106             article.setTitle(document.get("title"));
107             article.setContent(document.get("content"));
108             articles.add(article);
109         }
110         for(Article article : articles)
111         {
112             System.out.println(article.getId());
113             System.out.println(article.getTitle());
114             System.out.println(article.getContent());
115         }
116     }
117 }


两个工具类

package com.kite.luncene.utils;

import java.io.File;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class LunceneUtils
{
    //索引库
    public static Directory directory;
    //分词器
    public static Analyzer analyzer;
    static
    {
        try
        {
            directory = FSDirectory.open(new File("./indexDor"));
            analyzer = new StandardAnalyzer(Version.LUCENE_30);
        } catch (Exception e)
        {
            e.printStackTrace();
        }
        
    }
}

package com.kite.luncene.utils;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;

import com.kite.bean.Article;

public class DocumentUtils
{
    /**
     * 通过 article获得document
     * @param article
     * @return
     */
    public static Document articleToDocument(Article article)
    {
        Document document = new Document();
        Field idField = new Field("id", article.getId().toString(), Store.YES, Index.NOT_ANALYZED);
        Field titleField = new Field("title", article.getTitle(), Store.YES, Index.ANALYZED);
        Field  contentField = new Field("content", article.getContent(), Store.YES, Index.ANALYZED);
        document.add(idField);
        document.add(titleField);
        document.add(contentField);
        return document;
    }
    /**
     * 通过document 获得article对象
     * @param document
     * @return
     */
    public static Article documentToArticle(Document document) 
    {
        Article article = new Article();
        article.setId(Long.parseLong(document.get("id")));
        article.setTitle((document.get("title")));
        article.setContent(document.get("content"));
        return article;
    }
}


实用工具类实现简单的增删改查功能

package com.kite.luncene.index;

import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.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.util.Version;
import org.junit.Test;

import com.kite.bean.Article;
import com.kite.luncene.utils.DocumentUtils;
import com.kite.luncene.utils.LunceneUtils;

public class ArticleIndex
{
    @Test
    public void testCreateIndex() throws Exception
    {
        IndexWriter indexWriter = new IndexWriter(LunceneUtils.directory, LunceneUtils.analyzer, MaxFieldLength.LIMITED);
        Article article = new Article();
        article.setId(1L);
        article.setTitle("luncenes是一个好难写的东西");
        article.setContent("百度，谷歌是很好的搜索引擎");
        //通过工具类转换成document
        Document document = DocumentUtils.articleToDocument(article);
        indexWriter.addDocument(document);
        
        indexWriter.close();
    }
    @Test
    public void testSearchIndex() throws Exception
    {
        IndexSearcher indexSearcher = new IndexSearcher(LunceneUtils.directory);
        /**
         * Version.LUCENE_30 版本
         * "title"   根据那个字段
         * LunceneUtils.analyzer  分词器
         */
        QueryParser queryParser = new QueryParser(Version.LUCENE_30, "title", LunceneUtils.analyzer);
        //luncene  关键字
        Query query = queryParser.parse("luncene");
        TopDocs topDocs = indexSearcher.search(query, 2);
        //获得根据关键字查询到的所有的记录数
        int count = topDocs.totalHits;
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        List<Article> articles = new ArrayList<Article>();
        for(ScoreDoc scoreDoc : scoreDocs)
        {
            //scoreDoc.score 获得关键字得分
            float score = scoreDoc.score;
            //scoreDoc.doc 获得索引的下标
            int index = scoreDoc.doc;
            //通过索引的下标进行查询
            Document document = indexSearcher.doc(index);
            Article article = DocumentUtils.documentToArticle(document);
            articles.add(article);
        }
        //遍历输出
        for(Article article : articles)
        {
            System.out.println(article.getId().toString());
            System.err.println(article.getTitle());
            System.out.println(article.getContent());
        }
    }
    /**
     * 修改是先删除 然后进行添加
     * @throws Exception
     */
    @Test
    public void testDeleteIndex() throws Exception
    {
        IndexWriter indexWriter = new IndexWriter(LunceneUtils.directory, LunceneUtils.analyzer, MaxFieldLength.LIMITED);
        
        //indexWriter.deleteAll();--删除所有
        /*
         * term  关键字对象     
         *             title  字段名
         *             luncenes    关键字的内容
         */
        Term term = new Term("title", "luncenes");
        //根据关键字进行删除   会在文件夹中增加一个.del结尾的文件
        indexWriter.deleteDocuments(term);
        indexWriter.close();
    }
    @Test
    public void testUpdateIndex() throws Exception
    {
        IndexWriter indexWriter = new IndexWriter(LunceneUtils.directory, LunceneUtils.analyzer, MaxFieldLength.LIMITED);
        
        
        Term term = new Term("title","luncenes");
        Article article = new Article();
        article.setId(1L);
        article.setTitle("luncene是一个好难写的东西,少个s不解释");
        article.setContent("百度，谷歌是很好的搜索引擎");
        /*
         * term 根据关键字进行修改 
         * doc   修改后的内容
         */
        indexWriter.updateDocument(term, DocumentUtils.articleToDocument(article));
        indexWriter.close();
        
    }
}

查看全文

相关阅读:
supervisor 配置
 单链表
 二叉排序树
 python 排序
 64 位 Ubuntu 下 android adb 不可用解决方法
 python 获取文件夹大小
 Ubuntu mongodb 安装和配置
 关于c3p0配置详细说明
 dwr消息推送
 关于如果修改 ie 浏览器文本模式

原文地址：https://www.cnblogs.com/kite/p/3645571.html