lucene简单使用

lucene7以上最低要求jdk1.8

lucene下载地址：

http://archive.apache.org/dist/lucene/java/

<dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>6.0.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-highlighter</artifactId>
            <version>6.0.0</version>
        </dependency>

        <!-- http://mvnrepository.com/artifact/org.apache.lucene/lucene-analyzers-common -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-common</artifactId>
            <version>6.0.0</version>
        </dependency>

        <!-- http://mvnrepository.com/artifact/org.apache.lucene/lucene-memory -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-memory</artifactId>
            <version>6.0.0</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.9</version>
        </dependency>

        <!-- http://mvnrepository.com/artifact/org.apache.lucene/lucene-queryparser -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-queryparser</artifactId>
            <version>6.0.0</version>
        </dependency>
        <dependency>
            <groupId>commons-io</groupId>
            <artifactId>commons-io</artifactId>
            <version>2.6</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>6.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-smartcn</artifactId>
            <version>7.3.0</version>
        </dependency>
        <dependency>
            <groupId>com.janeluo</groupId>
            <artifactId>ikanalyzer</artifactId>
            <version>2012_u6</version>
            <!--排除掉里面旧的lucene包，因为我们要重写里面的分析器和分词器  -->
            <exclusions>
                <exclusion>
                    <groupId>org.apache.lucene</groupId>
                    <artifactId>lucene-core</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>org.apache.lucene</groupId>
                    <artifactId>lucene-queryparser</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>org.apache.lucene</groupId>
                    <artifactId>lucene-analyzers-common</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>com.janeluo</groupId>
            <artifactId>ikanalyzer</artifactId>
            <version>2012_u6</version>
        </dependency>

 

package com.ytkj.lucene;

import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.*;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;

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

/**
 * lucene入门程序
 */
public class LuceneFrist {
    /**
     * 创建索引库
     * @throws Exception
     */
    public static void createIndex()throws Exception{
        //1.创建一个Director对象，指定索引库保存的位置，保存在磁盘中
        Directory directory=FSDirectory.open(new File("E:\\lucene\\lucenetemp").toPath());
        //2.创建IndexWriter对象
            //创建使用的分词器
        StandardAnalyzer analyzer = new StandardAnalyzer();
        IndexWriter indexWriter=new IndexWriter(directory,new IndexWriterConfig(analyzer));
        //3.读取磁盘上的文件，对应每个文件创建一个文档对象
        File dir=new File("E:\\lucene\\luceneresource");
        File[] files = dir.listFiles();
        for (File file : files) {
            //文件名称
            String name = file.getName();
            //文件路径
            String path = file.getPath();
            //文件内容
            String content = FileUtils.readFileToString(file, "utf-8");
            //文件大小
            long size = FileUtils.sizeOf(file);
            //创建域 参数：域的名称 文件名称 是否存储
            Field fieldName=new TextField("name",name,Field.Store.YES);
            Field fieldPath=new TextField("path",path,Field.Store.YES);
            Field fieldContent=new TextField("content",content,Field.Store.YES);
            Field fieldSize=new TextField("size",size+"",Field.Store.YES);
            //4.创建文档对象
            Document document=new Document();
            //5.向文档对象中添加域
            document.add(fieldName);
            document.add(fieldPath);
            document.add(fieldContent);
            document.add(fieldSize);
            //6.把文档对象写入索引库
            indexWriter.addDocument(document);
        }
        //7.关闭indexwriter对象
        indexWriter.close();
    }

    /**
     * 查询索引库
     * @throws Exception
     */
    public static void searchIndex() throws Exception {
        //1.创建一个Director对象，指定索引库保存的位置
        Directory directory=FSDirectory.open(new File("E:\\lucene\\lucenetemp").toPath());
        //2.创建indexReader对象
        IndexReader indexReader= DirectoryReader.open(directory);
        //3.创建indexsearcher对象，构造方法中的参数indexReader对象
        IndexSearcher indexSearcher=new IndexSearcher(indexReader);
        //4.创建一个query对象
        Query query=new TermQuery(new Term("content","spring"));
        //5.执行查询，得到一个TopDocs对象 参数：查询对象 查询结果返回的最大记录数
        TopDocs topDocs = indexSearcher.search(query, 10);
        //6.取查询结果的总记录数
        int totalHits = topDocs.totalHits;
        System.out.println("查询结果的总记录数："+totalHits);
        //7.获取文档列表
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : scoreDocs) {
            //取文档id
            int docId = scoreDoc.doc;
            //8.根据id获取文档对象
            Document document = indexSearcher.doc(docId);
            System.out.println(document.get("name"));
            System.out.println(document.get("path"));
            System.out.println(document.get("content"));
            System.out.println(document.get("size"));
        }
        //关闭创建indexReader对象
        indexReader.close();

    }

    /**
     * 查看分词器的分词效果
     * @throws Exception
     */
    public static  void testTikenStream() throws Exception {
        //创建使用的标准分词器
        StandardAnalyzer analyzer = new StandardAnalyzer();
        //使用分词器对象的tokenStream方法获取tokenStream对象
        TokenStream tokenStream=analyzer.tokenStream("","org.springframework.jdbc.datasource.DataSourceTransactionManager");
        //向tokenstream对象中设置一个引用，相当于一个指针
        CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
        //调用tokenstream的rest方法
        tokenStream.reset();
        //循环遍历tokenStream对象
        while (tokenStream.incrementToken()){
            System.out.println(charTermAttribute.toString());
        }
        //关闭
        tokenStream.close();

    }

    /**
     * 中文分词器测试
     */
    public static  void testIKAnalyzer() throws Exception {
        String etext = "Analysis is one of the main causes of slow indexing. Simply put, the more you analyze the slower analyze the indexing (in most cases).";
        String chineseText = "张三说的确实在理。";
        /**
         * ikanalyzer 中文分词器 因为Analyzer的createComponents方法API改变了 需要我们自己实现
         * 分析器IKAnalyzer4Lucene7和分词器IKTokenizer4Lucene7
         */
        // IKAnalyzer 细粒度切分
        try (Analyzer ik = new IKAnalyzer();) {
            TokenStream ts = ik.tokenStream("content", etext);
            System.out.println("IKAnalyzer中文分词器 细粒度切分，英文分词效果：");
            doToken(ts);
            ts = ik.tokenStream("content", chineseText);
            System.out.println("IKAnalyzer中文分词器 细粒度切分，中文分词效果：");
            doToken(ts);
        }

        // IKAnalyzer 智能切分
        try (Analyzer ik = new IKAnalyzer(true);) {
            TokenStream ts = ik.tokenStream("content", etext);
            System.out.println("IKAnalyzer中文分词器 智能切分，英文分词效果：");
            doToken(ts);
            ts = ik.tokenStream("content", chineseText);
            System.out.println("IKAnalyzer中文分词器 智能切分，中文分词效果：");
            doToken(ts);
        }
    }
    private static void doToken(TokenStream ts) throws IOException {
        ts.reset();
        CharTermAttribute cta = ts.getAttribute(CharTermAttribute.class);
        while (ts.incrementToken()) {
            System.out.print(cta.toString() + "|");
        }
        System.out.println();
        ts.end();
        ts.close();
    }


    public static void main(String[] args) throws Exception {
        //createIndex();
        //searchIndex();
        //testTikenStream();
        testIKAnalyzer();
    }
}