lucene创建索引

上篇博客写了信息检索的基本知识和lucene架构,这篇博客记录一下如何在eclipse中创建索引.

1.lucene下载.

下载地址:http://archive.apache.org/dist/lucene/java/.
lucene不同版本之间有不小的差别，这里下载的是lucene 4.3.

2.导入jar包

打开eclipse，新建dynamic web project.解压下载的lucene压缩包，依次找到下面几个jar包,加到/WebContent/WEB-INF/lib目录下，然后Add to Build Path：

3.创建索引

package ac.ucas.lucene;

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

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class IndexCreate {

    public static void main(String[] args) {
        // TODO Auto-generated method stub
        // 创建标准分词器
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_43);
        // 创建indexwriter配置信息
        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_43, analyzer);
        // 设置索引的打开方式
        indexWriterConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
        // 索引的存储路径
        Directory directory = null;
        // 索引的增删改由indexWriter创建
        IndexWriter indexWriter = null;

        try {
            directory = FSDirectory.open(new File("/Users/yaopan/Documents/eclipseworkspace/test"));
            if (indexWriter.isLocked(directory)) {//若indexWriter锁定则解锁
                indexWriter.unlock(directory);
            }

            //实例化indexWriter
            indexWriter = new IndexWriter(directory, indexWriterConfig);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

        Document doc1 = new Document();
        //添加三个域
        doc1.add(new StringField("id", "abcde", Store.YES));
        doc1.add(new TextField("content", "极客学院", Store.YES));
        doc1.add(new IntField("num", 1, Store.YES));

        // 写入索引
        try {
            indexWriter.addDocument(doc1);
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

        Document doc2 = new Document();
        doc2.add(new StringField("id", "addff", Store.YES));
        doc2.add(new TextField("content", "LUCENE案例", Store.YES));
        doc2.add(new IntField("num", 2, Store.YES));

        // 写入索引
        try {
            indexWriter.addDocument(doc2);
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();

        }

        try {
            indexWriter.commit();

            indexWriter.close();
            directory.close();
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

        System.out.println("index ceate complete!");
    }
}

4.lucene分词器

{%codeblock lang:java lucene分词器 %}
package ac.ucas.lucene;

import java.io.IOException;
import java.io.StringReader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.Version;

import sun.dc.pr.PRError;

public class AnalyerStudy {

private static String str = "lucene, 全文检索框架";
public static void print(Analyzer analyzer){
    StringReader stringReader=new StringReader(str);
    try {
        TokenStream tokenStream=analyzer.tokenStream(str, stringReader);
        tokenStream.reset();
        CharTermAttribute term=tokenStream.getAttribute(CharTermAttribute.class);
        System.out.println("分词技术："+analyzer.getClass());
        while(tokenStream.incrementToken()){
            System.out.print(term.toString()+" | ");
        }
        System.out.println("\n");
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}
public static void main(String[] args) {
    Analyzer analyzer=null;
    //标准分词
    analyzer=new StandardAnalyzer(Version.LUCENE_43);
    print(analyzer);


    //空格分词
    analyzer =new WhitespaceAnalyzer(Version.LUCENE_43);
    print(analyzer);

    //简单分词
    analyzer=new SimpleAnalyzer(Version.LUCENE_43);
    print(analyzer);

    //二分法
    analyzer=new CJKAnalyzer(Version.LUCENE_43);
    print(analyzer);

    //关键字
    analyzer=new KeywordAnalyzer();
    print(analyzer);

    //
    analyzer=new StopAnalyzer(Version.LUCENE_43);
    print(analyzer);
}

}

{% endcodeblock %}

分词结果：
分词技术：class org.apache.lucene.analysis.standard.StandardAnalyzer
lucene | 全 | 文 | 检 | 索 | 框 | 架 |
分词技术：class org.apache.lucene.analysis.core.WhitespaceAnalyzer

lucene, | 全文检索框架 |
分词技术：class org.apache.lucene.analysis.core.SimpleAnalyzer
lucene | 全文检索框架 |
分词技术：class org.apache.lucene.analysis.cjk.CJKAnalyzer
lucene | 全文 | 文检 | 检索 | 索框 | 框架 |
分词技术：class org.apache.lucene.analysis.core.KeywordAnalyzer
lucene, 全文检索框架 |
分词技术：class org.apache.lucene.analysis.core.StopAnalyzer
lucene | 全文检索框架 |

5. 使用luke打开索引

Luke是一个用于Lucene搜索引擎的，方便开发和诊断的第三方工具，它可以访问现有Lucene的索引.
luke下载地址:https://github.com/DmitryKey/luke/releases