1.lucene入門-准備Lucene的開發環境

1.1        准備lucene的開發環境
 

搭建lucene的開發環境，要准備lucene的jar包，要加入的jar包至少有：
 
1)    lucene-core-3.1.0.jar    (核心包)
 
2)    lucene-analyzers-3.1.0.jar    (分詞器)
 
3)    lucene-highlighter-3.1.0.jar    (高亮器)
 
4)    lucene-memory-3.1.0.jar      (高亮器)
 

 

1.

package com.home.utils;

public class Article {
    private Long id;
    private String title;
    private String content;

    public Long getId() {
        return id;
    }

    public void setId(Long id) {
        this.id = id;
    }

    public String getTitle() {
        return title;
    }

    public void setTitle(String title) {
        this.title = title;
    }

    public String getContent() {
        return content;
    }

    public void setContent(String content) {
        this.content = content;

    }
}

 

2.

package com.home.utils;

import java.io.File;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
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 org.apache.lucene.index.IndexWriter;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;

public class HelloWorld {

    @Test
    public void testCreateIndex() throws Exception {
        /**
         * 1、創建一個article對象，並且把信息存放進去 2、調用indexWriter的API把數據存放在索引庫中
         * 3、關閉indexWriter
         */

        // 創建一個article對象，並且把信息存放進去
        Article article = new Article();
        article.setId(1L);
        article.setTitle("lucene可以做搜索引擎");
        article.setContent("baidu,google都是很好的搜索引擎");
        // 調用indexWriter的API把數據存放在索引庫中
        /**
         * 創建一個IndexWriter 參數三個 1、索引庫 指向索引庫的位置 2、分詞器
         */

        // 創建索引庫
        Directory directory = FSDirectory.open(new File("E:\\s"));
        // 創建分詞器
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
        IndexWriter indexWriter = new IndexWriter(directory, analyzer,
                MaxFieldLength.LIMITED);
        // 把一個article對象轉化成document
        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);

        indexWriter.addDocument(document);
        // 關閉indexWriter
        indexWriter.close();
    }

    @Test
    public void testSearchIndex() throws Exception {

        /**
         * 1、創建一個 IndexSearch對象 2、調用search方法進行檢索 3、輸出內容
         */
        // 創建索引庫
        Directory directory = FSDirectory.open(new File("E:\\s"));

        IndexSearcher indexSearcher = new IndexSearcher(directory);
        // 調用search方法進行檢索

        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
        // 為查詢分析器QueryParser 指定查詢字段和分詞器
        QueryParser queryParser = new QueryParser(Version.LUCENE_30, "content",
                analyzer);
        // 查詢
        Query query = queryParser.parse("baidu");// 關鍵詞
        // 指向相匹配的搜索條件的前N個搜索結果
        TopDocs topDocs = indexSearcher.search(query, 2);
        // 根據關鍵詞查詢出來的總的記錄數
        int count = topDocs.totalHits;
        // 。ScoreDoc是代表一個結果的相關度得分與文檔編號等信息的對象。
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        List<Article> articleList = new ArrayList<Article>();

        for (ScoreDoc scoreDoc : scoreDocs) {
            float score = scoreDoc.score;// 關鍵詞得分
            int index = scoreDoc.doc;// 索引的下標
            // 查詢文檔
            Document document = indexSearcher.doc(index);
            // 把document轉化成article
            Article article = new Article();
            article.setId(Long.parseLong(document.get("id")));// document.getField("id").stringValue()
            article.setTitle(document.get("title"));
            article.setContent(document.get("content"));
            articleList.add(article);

        }

        for (Article article : articleList) {
            System.out.println(article.getId());
            System.out.println(article.getTitle());
            System.out.println(article.getContent());
        }
    }
}

 

如何把一個信息寫到索引庫中

讀取信息的過程