educoder Lucene - 全文检索入门

第1关：使用lucene创建索引

package step1;

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

import org.apache.commons.io.FileUtils;
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.Store;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class WriterIndex {
	
	
	
	//创建索引库
	public static void createIndex() throws IOException{
		/********** Begin **********/
		//创建索引库
        Directory dir = FSDirectory.open(new File("/temp/doc/1101/index"));
        //创建标准分析器
        Analyzer analyzer = new StandardAnalyzer();
        //创建indexwriterConfig对象
        //第一个参数：lucene的版本信息，可以选择对应的lucene版本也可以使用LATEST
        //第二个参数：分析器对象
        IndexWriterConfig config = new IndexWriterConfig(Version.LATEST, analyzer);
        //创建indexwriter对象
        IndexWriter index = new IndexWriter(dir,config);
        //原始文档的路径
        File resource = new File("source/searchsource");
        for (File f : resource.listFiles()) {
            //文件名
            String fileName = f.getName();
            //文件内容
            String fileContent = FileUtils.readFileToString(f);
            //文件路径
            String filePath = f.getPath();
            //文件大小
            long fileSize = FileUtils.sizeOf(f);
            //创建文件名域
            //第一个参数：域的名称
            //第二个参数：域的内容
            //第三个参数：是否存储
            Field fileNameField = new TextField("filename", fileName, Store.YES);
            //文件内容域
            Field fileContentField = new TextField("content", fileContent, Store.YES);
            //文件路径域（不分析、不索引、只存储）
            Field filePathField = new StoredField("path", filePath);
            //文件大小域
            Field fileSizeField = new LongField("size", fileSize, Store.YES);
            //创建document对象
            Document document = new Document();
            //添加field
            document.add(fileNameField);
            document.add(fileContentField);
            document.add(filePathField);
            document.add(fileSizeField);
            index.addDocument(document);
        }
        //关闭indexwriter
        index.close();












		/********** End **********/
	}
	
}

第2关：查询索引

package step2;

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

import javax.sql.rowset.serial.SerialArray;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
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.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
public class SearchIndex {

	
	public static void searchIndex() throws IOException{
		/********** Begin **********/
Directory directory = FSDirectory.open(new File("/temp/doc/1101/index"));
IndexReader reader = DirectoryReader.open(directory);
//创建indexsearcher对象
IndexSearcher searcher = new IndexSearcher(reader);
//创建查询
Query query = new TermQuery(new Term("content","mybatis"));
//执行查询
//第一个参数是查询对象,第二个参数是查询结果返回的最大值
TopDocs topDocs = searcher.search(query, 10);
//查询结束的总条数
System.out.println("查询结果的总条数：" + topDocs.totalHits);
//遍历查询结果
//topDocs.scoreDocs 存储了document对象的id
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (ScoreDoc scoreDoc : scoreDocs) {
//sourceDoc.doc属性就是document对象的Id
//根据document的id找到document对象的id
//根据id获取document对象
Document document = searcher.doc(scoreDoc.doc);
//System.out.println(document.get("filename"));
System.out.println(document.get("path"));
System.out.println(document.get("content"));
}
reader.close();

		/********** End **********/
	}
	
}

第3关：分词器的使用

package step3;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;

public class AnalyzerTest {
	public static void main(String[] args) throws IOException {
		/********** Begin **********/
		    //创建一个标准分析器对象
    Analyzer analyzer = new CJKAnalyzer();
    //获得tokenStream对象
    //第一个参数：域名，可以随便给一个
    //第二个参数：要分析的文本内容
    TokenStream tokenStream = analyzer.tokenStream("test", "我喜欢在Educoder上学习");
    //添加一个引用，可以获得每个关键词
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
    //添加一个偏移量的引用，记录了关键词的开始位置以及结束位置
    OffsetAttribute offsetAttribute = tokenStream.addAttribute(OffsetAttribute.class);
    //将指针调整到列表的头部
    tokenStream.reset();
    //遍历关键词列表，通过incrementToken方法判断列表是否结束
    while(tokenStream.incrementToken()) {
    //关键词的起始位置
    System.out.println("start->" + offsetAttribute.startOffset());
    //取关键词
    System.out.println(charTermAttribute);
    //结束位置
    System.out.println("end->" + offsetAttribute.endOffset());
    }
    tokenStream.close();
    
		
		
		
		
		
		/********** End **********/
	}
}