Lucene搜索功能

1. 对特定项搜索

2. 查询表达式：QueryParser

3. 分页实现

New maven project ->
Create a simple project ->
    Group Id: com.andrew.lucene
    Artifact Id: Lucene03
    Version: 0.0.1-SNAPSHOT
    Packaging: jar

pom.xml

<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>com.andrew.lucene</groupId>
  <artifactId>Lucene03</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <dependencies>
      <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-core</artifactId>
        <version>5.3.1</version>
    </dependency>
    <dependency>
    <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-queryparser</artifactId>
        <version>5.3.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-analyzers-common</artifactId>
        <version>5.3.1</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.12</version>
    </dependency>
  </dependencies>
</project>

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:\\lucene4";
        String dataDir = "E:\\lucene4\\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");
    }
}

运行结果：

索引文件：E:\lucene4\data\CHANGES.txt
索引文件：E:\lucene4\data\LICENSE.txt
索引文件：E:\lucene4\data\NOTICE.txt
索引文件：E:\lucene4\data\SYSTEM_REQUIREMENTS.txt
索引：4个文件花费了6003毫秒

SearchTest.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.index.Term;
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.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

public class SearchTest {

    private Directory dir;
    private IndexReader reader;
    private IndexSearcher is;

    @Before
    public void setUp() throws Exception {
        dir = FSDirectory.open(Paths.get("E:\\lucene4"));
        reader = DirectoryReader.open(dir);
        is = new IndexSearcher(reader);
    }
    @After
    public void tearDown() throws Exception {
        reader.close();
    }
    // 对特定项搜索
    @Test
    public void testTermQuery() throws Exception {
        String searchField = "contents";
        String q = "particular";
        Term t = new Term(searchField, q);
        Query query = new TermQuery(t);
        TopDocs hits = is.search(query, 10);
        System.out.println("匹配 '" + q + "'，总共查询到" + hits.totalHits + "个文档");
        for (ScoreDoc scoreDoc : hits.scoreDocs) {
            Document doc = is.doc(scoreDoc.doc);
            System.out.println(doc.get("fullPath"));
        }
    }

    // 解析查询表达式
    @Test
    public void testQueryParser() throws Exception {
        Analyzer analyzer = new StandardAnalyzer(); // 标准分词器
        String searchField = "contents";
        String q = "abc~";
        // String q = "particular AND benchmarks";
        QueryParser parser = new QueryParser(searchField, analyzer);
        Query query = parser.parse(q);
        TopDocs hits = is.search(query, 100);
        System.out.println("匹配 " + q + "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"));
        }
    }
}

运行结果：

匹配 'particular'，总共查询到4个文档
E:\lucene4\data\SYSTEM_REQUIREMENTS.txt
E:\lucene4\data\LICENSE.txt
E:\lucene4\data\NOTICE.txt
E:\lucene4\data\CHANGES.txt

// 匹配 particular AND benchmarks查询到1个记录
// E:\lucene4\data\SYSTEM_REQUIREMENTS.txt

匹配 abc~查询到4个记录
E:\lucene4\data\CHANGES.txt
E:\lucene4\data\NOTICE.txt
E:\lucene4\data\LICENSE.txt
E:\lucene4\data\SYSTEM_REQUIREMENTS.txt