Lucene 快速入门

Lucene使得全文索引这项技术活变得非常简单，我将用5分钟做个快速展示。

1.建立索引  这个例子展示的是在内存中为几个String建立索引

StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);
Directory index = new RAMDirectory();

IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_44, analyzer);

IndexWriter w = new IndexWriter(index, config);
addDoc(w, "Lucene in Action", "193398817");
addDoc(w, "Lucene for Dummies", "55320055Z");
addDoc(w, "Managing Gigabytes", "55063554A");
addDoc(w, "The Art of Computer Science", "9900333X");
w.close();

来看addDoc()方法：

private static void addDoc(IndexWriter w, String title, String isbn) throws IOException {
  Document doc = new Document();
  doc.add(new TextField("title", title, Field.Store.YES));
  doc.add(new StringField("isbn", isbn, Field.Store.YES));
  w.addDocument(doc);
}

2.查询 从标准输入读取查询信息，建立Lucene的Query对象

String querystr = args.length > 0 ? args[0] : "lucene";
Query q = new QueryParser(Version.LUCENE_44, "title", analyzer).parse(querystr);

3.查找 利用2产生的Query对象建立Searcher对象在索引中查找

int hitsPerPage = 10;
IndexReader reader = IndexReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
searcher.search(q, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;

4.显示 显示查找结果

System.out.println("找到 " + hits.length + " hits.");
for(int i=0;i<hits.length;++i) {
    int docId = hits[i].doc;
    Document d = searcher.doc(docId);
    System.out.println((i + 1) + ". " + d.get("isbn") + "\t" + d.get("title"));
}

完整的Java代码：

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
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.TopScoreDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

import java.io.IOException;

public class HelloLucene {
  public static void main(String[] args) throws IOException, ParseException {
    // 0. analyzer 
    //    
    StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);

    // 1. index
    Directory index = new RAMDirectory();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_44, analyzer);

    IndexWriter w = new IndexWriter(index, config);
    addDoc(w, "Lucene in Action", "193398817");
    addDoc(w, "Lucene for Dummies", "55320055Z");
    addDoc(w, "Managing Gigabytes", "55063554A");
    addDoc(w, "The Art of Computer Science", "9900333X");
    w.close();

    // 2. query
    String querystr = args.length > 0 ? args[0] : "lucene";

  
    Query q = new QueryParser(Version.LUCENE_44, "title", analyzer).parse(querystr);

    // 3. search
    int hitsPerPage = 10;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
    searcher.search(q, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;
   
    // 4. display 
    System.out.println("找到 " + hits.length + " hits.");
    for(int i=0;i<hits.length;++i) {
      int docId = hits[i].doc;
      Document d = searcher.doc(docId);
      System.out.println((i + 1) + ". " + d.get("isbn") + "\t" + d.get("title"));
    }

    reader.close();
  }

  private static void addDoc(IndexWriter w, String title, String isbn) throws IOException {
    Document doc = new Document();
    doc.add(new TextField("title", title, Field.Store.YES));
    doc.add(new StringField("isbn", isbn, Field.Store.YES));
    w.addDocument(doc);
  }
}