Lucene 5.5 入門實戰（一）：索引創建與查詢基礎

環境準備

• JDK 1.7（Lucene 5.5.3 兼容）
• Maven 項目，packaging: jar

Maven 依賴

<dependencies>
  <!-- 核心包 -->
  <dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-core</artifactId>
    <version>5.5.3</version>
  </dependency>
  <!-- 查詢解析器 -->
  <dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-queryparser</artifactId>
    <version>5.5.3</version>
  </dependency>
  <!-- 標準分詞器 -->
  <dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-analyzers-common</artifactId>
    <version>5.5.3</version>
  </dependency>
</dependencies>

<build>
  <plugins>
    <plugin>
      <groupId>org.apache.maven.plugins</groupId>
      <artifactId>maven-compiler-plugin</artifactId>
      <version>3.3</version>
      <configuration>
        <source>1.7</source>
        <target>1.7</target>
      </configuration>
    </plugin>
  </plugins>
</build>

核心類一：Indexer（索引構建）

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;
    
    public Indexer(String indexDir) throws Exception {
        Directory dir = FSDirectory.open(Paths.get(indexDir));
        Analyzer analyzer = new StandardAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
        writer = new IndexWriter(dir, iwc);
    }
    
    public void close() throws Exception { writer.close(); }
    
    public int index(String dataDir) throws Exception {
        File[] files = new File(dataDir).listFiles();
        for (File f : files) indexFile(f);
        return writer.numDocs();
    }
    
    private void indexFile(File f) throws Exception {
        System.out.println("索引文件：" + f.getCanonicalPath());
        Document doc = getDocument(f);
        writer.addDocument(doc);
    }
    
    private Document getDocument(File f) throws Exception {
        Document doc = new Document();
        // 內容：不存儲，只分詞索引
        doc.add(new TextField("contents", new FileReader(f)));
        // 文件名：存儲
        doc.add(new TextField("fileName", f.getName(), Field.Store.YES));
        // 完整路徑：存儲
        doc.add(new TextField("fullPath", f.getCanonicalPath(), Field.Store.YES));
        return doc;
    }
    
    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 + " 個文件，耗時 " + (end - start) + " 毫秒");
    }
}

運行前準備： 在任意盤符創建 lucene/data 目錄，放入若干 .txt 文件測試。

索引目錄下生成文件：

核心類二：Searcher（查詢檢索）

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();
        QueryParser parser = new QueryParser("contents", analyzer);
        Query query = parser.parse(q);
        
        long start = System.currentTimeMillis();
        TopDocs hits = is.search(query, 10); // 取前 10
        long end = System.currentTimeMillis();
        
        System.out.println("查詢 \"" + q + "\"，耗時 " + (end - start) + "ms，命中 " + hits.totalHits + " 條");
        for (ScoreDoc sd : hits.scoreDocs) {
            Document doc = is.doc(sd.doc);
            System.out.println(doc.get("fullPath"));
        }
        reader.close();
    }
    
    public static void main(String[] args) {
        String indexDir = "E:\\lucene";
        String q = "Zygmunt Saloni"; // 測試關鍵詞
        try { search(indexDir, q); } catch (Exception e) { e.printStackTrace(); }
    }
}

關鍵概念解析

• Directory：索引存儲抽象（FSDirectory 文件系統、RAMDirectory 內存）
• Analyzer：分詞器（StandardAnalyzer 標準、IKAnalyzer 中文）
• Document：索引單元，包含多個 Field
• Field：字段，TextField 分詞索引，StringField 不分詞精確匹配，StoredField 僅存儲
• IndexWriter：寫索引，addDocument/deleteDocuments/updateDocument
• IndexSearcher：讀索引，search(Query, n) 返回 TopDocs
• QueryParser：解析查詢語法（支持 +、-、*、?、""、~ 等）

注意事項

• 索引文件不可刪除，否則查詢報錯（IndexNotFoundException）
• 分詞器索引與查詢必須一致，否則無法命中
• TextField 內容不存儲（Store.NO），需顯示內容請另加 StoredField
• 生產環境建議使用 NearRealTime (NRT) 搜尋，避免頻繁 commit

轉載請注明出處。博客園：https://www.cnblogs.com/tenglongwentian/