Lucene全文检索引擎

Posted 2020-10-14 Jansens

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
  <groupId>demo.lucene</groupId>
  <artifactId>Lucene01</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <build/>

  <dependencies>
    <!-- lucene核心包 -->
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-core</artifactId>
        <version>5.3.1</version>
    </dependency>
    <!-- lucene查询解析包 -->
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-queryparser</artifactId>
        <version>5.3.1</version>
    </dependency>
    <!-- lucene解析器包 -->
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-analyzers-common</artifactId>
        <version>5.3.1</version>
    </dependency>
  </dependencies>
</project>

　　

import java.io.File;
import java.io.FileReader;
import java.nio.file.Paths;

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.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;

/**
 * 建立索引的类
 * @author Ni Shengwu
 *
 */
public class Indexer {

    private IndexWriter writer; //写索引实例

    //构造方法，实例化IndexWriter
    public Indexer(String indexDir) throws Exception {
        Directory dir = FSDirectory.open(Paths.get(indexDir));
        Analyzer analyzer = new StandardAnalyzer(); //标准分词器，会自动去掉空格啊，is a the等单词
        IndexWriterConfig config = new IndexWriterConfig(analyzer); //将标准分词器配到写索引的配置中
        writer = new IndexWriter(dir, config); //实例化写索引对象
    }
    //关闭写索引
    public void close() throws Exception {
        writer.close();
    }
    //索引指定目录下的所有文件
    public int indexAll(String dataDir) throws Exception {
        File[] files = new File(dataDir).listFiles(); //获取该路径下的所有文件
        for(File file : files) {
            indexFile(file); //调用下面的indexFile方法，对每个文件进行索引
        }
        return writer.numDocs(); //返回索引的文件数
    }
    //索引指定的文件
    private void indexFile(File file) throws Exception {
        System.out.println("索引文件的路径：" + file.getCanonicalPath());
        Document doc = getDocument(file); //获取该文件的document
        writer.addDocument(doc); //调用下面的getDocument方法，将doc添加到索引中
    }
    //获取文档，文档里再设置每个字段，就类似于数据库中的一行记录
    private Document getDocument(File file) throws Exception{
        Document doc = new Document();
        //添加字段
        doc.add(new TextField("contents", new FileReader(file))); //添加内容
        doc.add(new TextField("fileName", file.getName(), Field.Store.YES)); //添加文件名，并把这个字段存到索引文件里
        doc.add(new TextField("fullPath", file.getCanonicalPath(), Field.Store.YES)); //添加文件路径
        return doc;
    }
    public static void main(String[] args) {
        String indexDir = "D:\\lucene"; //将索引保存到的路径
        String dataDir = "D:\\lucene\\data"; //需要索引的文件数据存放的目录
        Indexer indexer = null;
        int indexedNum = 0;
        long startTime = System.currentTimeMillis(); //记录索引开始时间
        try {
            indexer = new Indexer(indexDir);
            indexedNum = indexer.indexAll(dataDir);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                indexer.close();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        long endTime = System.currentTimeMillis(); //记录索引结束时间
        System.out.println("索引耗时" + (endTime-startTime) + "毫秒");
        System.out.println("共索引了" + indexedNum + "个文件");
    }
}

　　

import java.nio.file.Paths;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
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.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class Searcher {
	
	public static void search(String indexDir, String q) throws Exception {

        Directory dir = FSDirectory.open(Paths.get(indexDir)); //获取要查询的路径，也就是索引所在的位置
        IndexReader reader = DirectoryReader.open(dir);
        IndexSearcher searcher = new IndexSearcher(reader);
        Analyzer analyzer = new StandardAnalyzer(); //标准分词器，会自动去掉空格啊，is a the等单词
        QueryParser parser = new QueryParser("contents", analyzer); //查询解析器
        Query query = parser.parse(q); //通过解析要查询的String，获取查询对象

        long startTime = System.currentTimeMillis(); //记录索引开始时间
        TopDocs docs = searcher.search(query, 10);//开始查询，查询前10条数据，将记录保存在docs中
        long endTime = System.currentTimeMillis(); //记录索引结束时间
        System.out.println("匹配" + q + "共耗时" + (endTime-startTime) + "毫秒");
        System.out.println("查询到" + docs.totalHits + "条记录");

        for(ScoreDoc scoreDoc : docs.scoreDocs) { //取出每条查询结果
            Document doc = searcher.doc(scoreDoc.doc); //scoreDoc.doc相当于docID,根据这个docID来获取文档
            System.out.println(doc.get("fullPath")); //fullPath是刚刚建立索引的时候我们定义的一个字段
        }
        reader.close();
    }
    public static void main(String[] args) {
        String indexDir = "D:\\lucene";
        String q = "generate-maven-artifacts"; //查询这个字符串
        try {
            search(indexDir, q);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

　　

pom.xml