lucene中创建索引库

package com.hope.lucene;

import org.apache.commons.io.FileUtils;
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.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;

import java.io.File;


/**
 * @author newcityman
 * @date 2020/1/15 - 0:01
 */
public class LuceneFirst {

    /**
     * 创建索引
     * @throws Exception
     */
    @Test
    public void createIndex() throws  Exception{
        //1、创建一个Director对象，指定索引库保存的位置
        //把索引库保存到磁盘
        Directory directory = FSDirectory.open(new File("G:\workspace_idea3\lucene\temp\index").toPath());
        //2、基于Directory对象，创建一个IndexWriter对象
        IndexWriter indexWriter = new IndexWriter(directory,new IndexWriterConfig());
        //3、读取磁盘上的文件，对应每个文件创建一个文档对象
        File file = new File("G:\workspace_idea3\lucene\temp\searchsource");
        File[] files = file.listFiles();
        for (File f : files) {
            //取文件名
            String fileName = f.getName();
            //取文件路径
            String filePath = f.getPath();
            //取文件内容
            String fileContent = FileUtils.readFileToString(f, "utf-8");
            //文件大小
            long fileSize = FileUtils.sizeOf(f);

            //创建Field
            TextField fieldName = new TextField("name", fileName, Field.Store.YES);
            TextField fieldPath = new TextField("path", filePath, Field.Store.YES);
            TextField fieldContent = new TextField("content", fileContent, Field.Store.YES);
            TextField fieldSize = new TextField("size", fileSize+"", Field.Store.YES);

            //4、向文档对象中添加Field
            //创建文档
            Document document = new Document();
            document.add(fieldName);
            document.add(fieldPath);
            document.add(fieldContent);
            document.add(fieldSize);
            //5、把文档对象写入到索引库中
            indexWriter.addDocument(document);
        }
        //6、关闭indexWriter对象
            indexWriter.close();
    }

    /**
     * 查询索引
     * @throws Exception
     */
    @Test
    public void  searchIndex() throws  Exception{
        //1、创建一个Directory对象，指定索引库位置
        Directory directory = FSDirectory.open(new File("G:\workspace_idea3\lucene\temp\index").toPath());
        //2、创建IndexReader对象
        IndexReader indexReader = DirectoryReader.open(directory);
        //3、创建IndexSearch对象
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);
        //4、创建Query对象，TermQuery对象
        TermQuery termQuery = new TermQuery(new Term("content", "spring"));
        //5、执行查询TopDocs
        //参数1：查询对象   参数2：查询结果返回的最大记录数
        TopDocs topDocs = indexSearcher.search(termQuery, 10);
        //6、取查询结果的总记录数
        System.out.println("查询总记录数："+topDocs.totalHits);
        //7、取文档列表
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        //8、打印文档内容
        for (ScoreDoc scoreDoc : scoreDocs) {
            //取文档id
            int docId = scoreDoc.doc;
            //根据id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("size"));
           // System.out.println(document.get("content"));
            System.out.println("++++++++++++++++++++++++++++++");
        }
        //9、关闭IndexReader对象
       indexReader.close();
    }

/**
 * 查询标准分词器的分词效果
 *
 * @throws Exception
 */
@Test
public void testTokenStream() throws Exception {
    // 1、创建一个Analyzer对象，StrandAnalyzer对象
    Analyzer analyzer = new StandardAnalyzer();
    // 2、使用分词器对象的tokenStream方法获取一个TokenStream对象
    TokenStream tokenStream = analyzer.tokenStream("", "Learn how to create a web page with Spring MVC.");
    // 3、向TokenStream对象中设置一个引用，相当于一个指针
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
    // 4、调用TokenStream对象的reset方法，如果不调用会抛异常
    tokenStream.reset();
    // 5、使用while循环遍历TokenStream对象
    while (tokenStream.incrementToken()) {
        System.out.println(charTermAttribute.toString());
    }
    // 6、关闭TokenStream对象
    tokenStream.close();
}

}