lucene-查询query->WildcardQuery使用通配符搜索

Posted 2020-06-17

Lucene也提供了通配符的查询，这就是WildcardQuery。

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.Hits;

import org.apache.lucene.search.IndexSearcher;

import org.apache.lucene.search.WildcardQuery;

 

public class WildcardQueryTest {

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

         //生成Document对象，下同

         Document doc1 = new Document();

         //添加“content”字段的内容，下同

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

         //添加“title”字段的内容，下同

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

        

         Document doc2 = new Document();

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

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

        

         Document doc3 = new Document();

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

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

        

         Document doc4 = new Document();

         doc4.add(Field.Text("content", "everest"));

         doc4.add(Field.Keyword("title", "doc4"));

        

         //生成索引书写器

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

                 new StandardAnalyzer(), true);

         //将文档对象添加到索引中

         writer.addDocument(doc1);

         writer.addDocument(doc2);

         writer.addDocument(doc3);

         writer.addDocument(doc4);

         //关闭索引书写器

         writer.close();

 

         //生成索引书写器

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

         //构造词条

         Term word1 = new Term("content", "*ever");

         Term word2 = new Term("content", "wh?ever");

         Term word3 = new Term("content", "h??ever");

         Term word4 = new Term("content", "ever*");

         //生成WildcardQuery对象，初始化为null

         WildcardQuery query = null;

         //用于保存检索结果

         Hits hits = null;

        

         query = new WildcardQuery(word1);

         //开始第一次检索，并返回检索结果

         hits = searcher.search(query);

         //输出检索结果的相关信息

         printResult(hits, "*ever");

        

         query = new WildcardQuery(word2);

         //开始第二次检索，并返回检索结果

         hits = searcher.search(query);

         //输出检索结果的相关信息

         printResult(hits, "wh?ever");

        

         query = new WildcardQuery(word3);

         //开始第三次检索，并返回检索结果

         hits = searcher.search(query);

         //输出检索结果的相关信息

         printResult(hits, "h??ever");

        

         query = new WildcardQuery(word4);

         //开始第四次检索，并返回检索结果

         hits = searcher.search(query);

         //输出检索结果的相关信息

         printResult(hits, "ever*");

     }

   

     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();

             }

         }

     }

}

由上述代码可以看出，通配符“?”代表1个字符，而“*”则代表0至多个字符。不过通配符检索和上面的FuzzyQuery由于需要对字段关键字进行字符串匹配，所以，在搜索的性能上面会受到一些影响。