Lucene(5.3.1) demo

阅读更多

 

Lucene包含两部分内容：创建索引、检索。

 

package demo.mytest.lucene;

import java.io.IOException;
import java.nio.file.FileSystems;

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.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Encoder;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLEncoder;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.BytesRef;
import org.junit.Test;

import demo.mytest.lucene.utils.LuceneUtils;

public class HelloWorld {
	
	public static final String dataDir = "F:\\workspace\\luceneDemo\\dataDir\\CHANGES.txt";//文档所在路径 CHANGES.txt
	public static final String dataDir2 = "F:\\workspace\\luceneDemo\\dataDir\\bye.txt";
	public static final String indexDir = "F:\\workspace\\luceneDemo\\indexDir";//索引文件存储位置
	public static final Analyzer analyzer = new StandardAnalyzer();

	/**
	 * 
	 * testCreateIndex 创建索引库
	 * 
	 * @Description 
	 * @throws Exception void
	 * @see
	 */
	@Test
	public void testCreateIndex() throws Exception {
		
		IndexWriterConfig config = new IndexWriterConfig(analyzer);
		config.setOpenMode(OpenMode.CREATE);//设置indexWriter的打开方式，是新建或覆盖（CREATE）？是追加(APPEND)？还是两者结合(CREATE_OR_APPEND)？
		Directory directory = this.getFsIndexDirectory();//将索引文件保存的指定路径
		IndexWriter indexWriter = new IndexWriter(directory, config);//创建indexWriter对象
//		indexWriter.deleteAll();//删除索引库的所有文件
		
		Document doc = LuceneUtils.file2Document(dataDir);//处理、转换。将文件转换成文档对象
		indexWriter.addDocument(doc);
		
		Document doc2 = LuceneUtils.file2Document(dataDir2);//处理、转换。将文件转换成文档对象
		indexWriter.addDocument(doc2);
		
		indexWriter.close();//用完一定要关闭！
		/*
		 * 新添加一个Document并不会马上将它的索引写入最终的索引大文件,它的索引会暂时存于缓存。
		 * 当关闭时，会将缓存中的索引归并到索引大文件。如果此处没有关闭操作，那么刚刚添加的Document的索引不会保存到最终的索引大文件。
		 */
		directory.close();
	}

	/**
	 * 
	 * testTermQuery 关键词查询
	 * @throws IOException 
	 * 
	 * @Description 
	 * @see
	 */
	@Test
	public void testTermQuery() throws IOException {
		String queryStr = "bye.txt";
		Term term = new Term("fileName", queryStr);
		Query query = new TermQuery(term) ;
		
		this.queryAndPrintResult(query);
	}

	/**
	 * 
	 * testTermRangeQuery 范围查询
	 * 
	 * @Description
	 * @throws IOException void
	 * @see
	 */
	@Test
	public void testTermRangeQuery() throws IOException {
		Query query = new TermRangeQuery("fileSize",new BytesRef(10),new BytesRef(2000), true, true);
		this.queryAndPrintResult(query);
	}
	
	/**
	 * 
	 * queryAndPrintResult 测试查询对象用到的方法
	 * 
	 * @Description 
	 * @throws IOException void
	 * @see
	 */
	private void queryAndPrintResult(Query query) throws IOException {
		Directory directory = this.getFsIndexDirectory();//获取索引文件的存储路径
		IndexReader indexReader = DirectoryReader.open(directory);
		IndexSearcher indexSearcher = new IndexSearcher(indexReader);//从指定的路径的索引库检索指定的文本
		
		
		
		TopDocs topDocs = indexSearcher.search(query, 100000);
		
		ScoreDoc[] scoreDocs = topDocs.scoreDocs;

		System.out.println("共有【"+ topDocs.totalHits+"】条查询结果。\n----------------");
		//打印文档对象信息
		for(int i=0;i","");
		
		Encoder encoder = new SimpleHTMLEncoder();
		
		Scorer fragmentScorer = new QueryScorer(query);
		Highlighter highlighter = new Highlighter(formatter, encoder, fragmentScorer);
		//设置高亮器
		final int FRAGMENT_SIZE = 50;
		Fragmenter fragmenter = new SimpleFragmenter(FRAGMENT_SIZE);//每一个fragment的字符长度
		highlighter.setTextFragmenter(fragmenter);
		//--------------------
		
		for(int i=0;i 
  
 
 
  
 
 
  
 使用到的工具类：
 
  
 
 
  
package demo.mytest.lucene.utils;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;

/**
 * 
 * LuceneUtils 工具类
 * 
 */
public class LuceneUtils {
	
	/**
	 * 
	 * file2Document 将文件转换成文档对象
	 * 
	 * @Description 
	 * @param path
	 * @return
	 * @throws Exception Document
	 * @see
	 */
	public static Document file2Document(String path) throws Exception {
		File file = new File(path);
		Document doc = new Document();
		doc.add(new Field("fileName", file.getName(), TextField.TYPE_STORED));
		doc.add(new Field("content", getFileContent(file),TextField.TYPE_STORED));
		doc.add(new Field("fileSize", String.valueOf(file.getTotalSpace()), TextField.TYPE_STORED));
		doc.add(new Field("path", file.getAbsolutePath(),TextField.TYPE_STORED));
		//doc.add(new Field("fileName",String.valueOf(file.getName()),Store.YES, Index.ANALYZED));
		System.out.println(file.getAbsolutePath()+"\t"+file.isDirectory()+"\n"+getFileContent(file));
		doc.add(new Field("isDirectory",String.valueOf(file.isDirectory()),TextField.TYPE_STORED));
		
		return doc;
	}
	
	/**
	 * 
	 * printDocumentInfo 打印文档对象信息
	 * 
	 * @Description 打印文档对象信息
	 * @param document 文档对象
	 * void
	 * @see
	 */
	public static void printDocumentInfo(Document document) {
//		IndexableField field = document.getField("fileName");	
//		System.out.println(field.name() + ":" +field.stringValue());//结果---fileName:CHANGES.txt。此处的document.getField("fileName").stringValue()相当于document.get("fileName")
		//打印文档对象信息
		System.out.println("文档（"+document.get("fileName")+"）的信息-"
		+"内容："+document.get("content")+"\t存储位置："+document.get("path")
		+"\t文件大小：" + document.get("fileSize") +"\t是否为文件夹："+ document.get("isDirectory"));
	}
	
	/**
	 * 
	 * getFileContent 取得文件内容
	 * 
	 * @Description 
	 * @param file
	 * @return
	 * @throws Exception String
	 * @see
	 */
	private static String getFileContent(File file) throws Exception {
		StringBuffer sbf = new StringBuffer();
		BufferedReader br = new BufferedReader(new FileReader(file));
		String line = null;
		while ((line = br.readLine()) != null) {
			sbf.append(line).append("\n");
		}
		br.close();
		return sbf.toString();
	}
}