FuzzyQuery是一种模糊查询,它可以简单地识别两个相近的词语。下面以11.10为例进行详细介绍。

package ch11;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.index.IndexWriter;

import org.apache.lucene.index.Term;

import org.apache.lucene.search.FuzzyQuery;

import org.apache.lucene.search.Hits;

import org.apache.lucene.search.IndexSearcher;

public class FuzzyQueryTest {

     public static void main(String[] args) throws Exception {

         //生成Document对象

         Document doc1 = new Document();

         //添加“content”字段的内容

         doc1.add(Field.Text("content", "david"));

         //添加“title”字段的内容

         doc1.add(Field.Keyword("title", "doc1"));

         Document doc2 = new Document();

         doc2.add(Field.Text("content", "sdavid"));

         doc2.add(Field.Keyword("title", "doc2"));

         Document doc3 = new Document();

         doc3.add(Field.Text("content", "davie"));

         doc3.add(Field.Keyword("title", "doc3"));

         //生成索引书写器

         IndexWriter writer = new IndexWriter("c://index",

                 new StandardAnalyzer(), true);

         //将文档添加到索引中

         writer.addDocument(doc1);

         writer.addDocument(doc2);

         writer.addDocument(doc3);

         //关闭索引写器

         writer.close();

         //生成索引搜索器

         IndexSearcher searcher = new IndexSearcher("c://index");

         Term word1 = new Term("content", "david");

         //用于保存检索结果

         Hits hits = null;

         //生成FuzzyQuery对象,初始化为null

         FuzzyQuery query = null;

         query = new FuzzyQuery(word1);

         //开始检索,并返回检索结果

         hits = searcher.search(query);

         //输出检索结果的相关信息

         printResult(hits,"与'david'相似的词");

     }

     public static void printResult(Hits hits, String key) throws Exception

         {System.out.println("查找 /"" + key + "/" :");

         if (hits != null) {

             if (hits.length() == 0) {

                 System.out.println("没有找到任何结果");

                 System.out.println();

             } else {

                 System.out.print("找到");

                 for (int i = 0; i < hits.length(); i++) {

                     //取得文档对象

                     Document d = hits.doc(i);

                     //取得“title”字段的内容

                     String dname = d.get("title");

                     System.out.print(dname + "   ");

                 }

                 System.out.println();

                 System.out.println();

             }

         }

     }

}

在上述代码中,首先构建了3个Document,这3个Document的“content”字段中都有一个与“david”较为相似的关键字(其中第一个就是david)。然后使用FuzzyQuery来对其进行检索。

04-13 09:51