使用Lucene

Question

package avajava; 
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. Specify the analyzer for tokenizing text. 
     // The same analyzer should be used for indexing and searching 
     StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_44); 

     // 1. create the 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 office use", "55320055Z"); 
     addDoc(w, "Managing Gigabytes", "55063554A"); 
     addDoc(w, "The Art of Computer Science", "9900333X"); 
     w.close(); 

     // 2. query 
     String querystr = "title:of"; 

     // the "title" arg specifies the default field to use 
     // when no field is explicitly specified in the query. 
     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 results 
     System.out.println("Found " + 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 can only be closed when there 
     // is no need to access the documents any more. 
     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)); 

    // use a string field for isbn because we don't want it tokenized 
    doc.add(new StringField("isbn", isbn, Field.Store.YES)); 
    w.addDocument(doc); 
    } 

}

問題，我得到了上面的代碼從一些examples.But我沒有得到的查詢字符串的基礎上，預期的結果（「標題：」）。

預期產出：

找到2個匹配數。 1. 55320055Z Lucene辦公室使用 2. 9900333X計算機科學藝術

請幫助。

Answer 1

您需要用一組空的停用詞構造StandardAnalyzer。 '的'是一個詞。

Lucene StandardAnalyzer