Lucene简介与实现

阅读更多

1. Lucene简介

Lucece官网： http://lucene.apache.org/

2. Lucene实现

New maven project ->
Create a simple project ->
    Group Id: com.andrew.lucene
    Artifact Id: Lucene01
    Version: 0.0.1-SNAPSHOT
    Packaging: jar

Indexer.java代码

package com.andrew.lucene;

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;

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
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
        writer = new IndexWriter(dir, iwc);
    }
    // 索引指定目录的所有文件
    public int index(String dataDir) throws Exception {
        File[] files = new File(dataDir).listFiles();
        for (File f : files) {
            indexFile(f);
        }
        return writer.numDocs();
    }
    // 索引指定文件
    private void indexFile(File f) throws Exception {
        System.out.println("索引文件：" + f.getCanonicalPath());
        Document doc = getDocument(f);
        writer.addDocument(doc);
    }
    // 获取文档，文档里再设置每个字段
    private Document getDocument(File f) throws Exception {
        Document doc = new Document();
        doc.add(new TextField("contents", new FileReader(f)));
        doc.add(new TextField("fileName", f.getName(), Field.Store.YES));
        doc.add(new TextField("fullPath", f.getCanonicalPath(), Field.Store.YES));
        return doc;
    }
    // 关闭写索引
    public void close() throws Exception {
        writer.close();
    }
    public static void main(String[] args) {
        String indexDir = "E:\\lucene";
        String dataDir = "E:\\lucene\\data";
        Indexer indexer = null;
        int numIndexed = 0;
        long start = System.currentTimeMillis();
        try {
            indexer = new Indexer(indexDir);
            numIndexed = indexer.index(dataDir);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                indexer.close();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        long end = System.currentTimeMillis();
        System.out.println("索引：" + numIndexed + " 个文件,花费了" + (end - start) + "毫秒");
    }
}

执行结果

索引文件：E:\lucene\data\CHANGES.txt
索引文件：E:\lucene\data\JRE_VERSION_MIGRATION.txt
索引文件：E:\lucene\data\LICENSE.txt
索引文件：E:\lucene\data\MIGRATE.txt
索引文件：E:\lucene\data\NOTICE.txt
索引文件：E:\lucene\data\README.txt
索引文件：E:\lucene\data\SYSTEM_REQUIREMENTS.txt
索引：7 个文件,花费了901毫秒

Searcher.java代码

package com.andrew.lucene;

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));
        IndexReader reader = DirectoryReader.open(dir);
        IndexSearcher is = new IndexSearcher(reader);
        Analyzer analyzer = new StandardAnalyzer(); // 标准分词器
        QueryParser parser = new QueryParser("contents", analyzer);
        Query query = parser.parse(q);
        long start = System.currentTimeMillis();
        TopDocs hits = is.search(query, 10);
        long end = System.currentTimeMillis();
        System.out.println("匹配 " + q + ",总共花费" + (end - start) + "毫秒" + "查询到" + hits.totalHits + "个记录");
        for (ScoreDoc scoreDoc : hits.scoreDocs) {
            Document doc = is.doc(scoreDoc.doc);
            System.out.println(doc.get("fullPath"));
        }
        reader.close();
    }
    public static void main(String[] args) {
        String indexDir = "E:\\lucene";
        String q = "Zygmunt Saloni";
        try {
            search(indexDir, q);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

执行结果

匹配 Zygmunt Saloni,总共花费24毫秒查询到1个记录
E:\lucene\data\LICENSE.txt