Practice Every Day_12(精确搜索和模糊搜索)

最新推荐文章于 2021-12-18 14:48:30 发布

SherryWang0622

最新推荐文章于 2021-12-18 14:48:30 发布

阅读量1.2k

点赞数

分类专栏： Lucene 文章标签： string query lucene file float class

本文链接：https://blog.csdn.net/supersnow0622/article/details/7524962

版权

Lucene 专栏收录该内容

11 篇文章 0 订阅

订阅专栏

今天看了搜索的相关知识，了解了几种搜索方法。下面来总结一下：

主要有两类方法：一类是创建Term，然后以Term为参数构建****Term

1、词条搜索：TermQue

方法示例：Term t=new Term(String field,String keyword);

TermQuery q=new TermQuery(t);

2、组合搜索：BooleanQuery

方法实例：Term t1=new Term(String field,String keyword);

TermQuery q1=new TermQuery(t1);

Term t2=new Term(String field,String keyword);

TermQuery q2=new TermQuery(t2);

BooleanQuery q=new BooleanQuery();

q.add(q1,BooleanClause.Occur.MUST)MUST代表必须含有;

q.add(q2,BooleanClause.Occur.Not_MUST);Not_MUST代表一定不含有；SHOULD表可以有

3、范围搜索：RangeQuery

方法实例：Query query=new TermRangeQuery(String field,String start,String end,Boolean inclusive,Boolean inclusive);

4、前缀搜索：PrefixQuery

方法实例：Term t=new Term(String field,String keyword);

Query q=new PrefixQuery(t);

5、短语搜索：PhraseQuery（可以设置匹配度）

方法示例：Term t1=new Term(String field,String keyword);

Term t2=new Term(String field,String keyword);

PhraseQuery q=new PhraseQuery();

q.setslop(int num);//设置t1中的keyword和t2中的keyword之间的单词数

q.add(t1)；

q.add(t2);

6、多短语搜索:MultiPhraseQuery

方法示例:Term t=new Term(String field,String keyword);

Term t1=new Term(String field,String keyword);

Term t2=new Term(String field,String keyword);

MultiPhraseQuery q=new MultiPhraseQuery();

q.add(t);//统一前缀

q.add(new Term[]{t1,t2});//后缀

7、模糊搜索：FuzzyQuery

方法实例： Term t=new Term(String field,String keyword);

FuzzyQuery q=new FuzzyQuery(t,float f);

8、通配符搜索：WildcardQuery

方法实例：Term t=new Term(String field,String keyword*);

WildcardQuery q=new WildcardQuery（t）；

常用*表示任意多个字符，用？表示任意一个字符

恩，今天有点晚了，另一类方法明天写。

我用TermQuery和FuzzyQuery写了一个程序，可是运行不出结果来，郁闷啊！

以下是代码，帮忙找找错哈！

package MySearcher;

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class FuzzySearcher
{
        private final static Analyzer analyzer=new IKAnalyzer();
        private static String ids[]={"01","02","03","04","05","06","07","08","09","10"};
        private static String names[]={"Lucy","Lily","Jerry","Mike","Tom","王琪琪","李木子","王聪聪","张小花","猪猪"};
        private static String address[]={"王大街","Green Street","White Streen","主大街","金晶大道","王府井","House Avenue","洪沟小区","张家界","Living Avenue"};
  public static void main(String[] args) throws IOException ,CorruptIndexException
  {
   String f="address";
   String s="王大街";
   int num=10;
      index();
   System.out.println("精确搜索的结果为");
         searcher1(f,s, num);
      System.out.println("模糊搜索的结果为");
         searcher2(f,s,num);
     }
       public static void index() throws CorruptIndexException, LockObtainFailedException, IOException
       {
        Directory directory=FSDirectory.open(new File("f:Lucene/Index_04"));
        IndexWriterConfig iwc=new IndexWriterConfig(Version.LUCENE_35,analyzer);
        IndexWriter writer=new IndexWriter(directory,iwc);
        for(int i=0;i<ids.length;i++)
        {
         Document doc=new Document();
         doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
         doc.add(new Field("name",names[i],Field.Store.YES,Field.Index.ANALYZED));
         doc.add(new Field("address",address[i],Field.Store.YES,Field.Index.ANALYZED));
           writer.addDocument(doc) ;
        }
        writer.close();
       }
   public static void searcher1(String f,String s,int num) throws IOException,CorruptIndexException
   {
  Directory directory=FSDirectory.open(new File("f:Lucene/Index_04"));
  IndexReader reader= IndexReader.open(directory);
  IndexSearcher searcher=new IndexSearcher(reader);
  Term t=new Term(f,s);
  TermQuery query=new TermQuery(t);
  TopDocs tds=searcher.search(query,num);
  int total=tds.totalHits;
     System.out.println("共搜索到"+total+"条结果");
  ScoreDoc[] sds=tds.scoreDocs;
    for(ScoreDoc sd:sds)
    {
     Document doc=searcher.doc(sd.doc);
     System.out.println(doc.get("id")+doc.get("name")+doc.get("address"));
    }
    searcher.close();
   }
      public static void searcher2(String f,String s,int num) throws CorruptIndexException, IOException
{
    Directory directory=FSDirectory.open(new File("e:Lucene实例/Index_01"));
  IndexReader reader= IndexReader.open(directory);
  IndexSearcher searcher=new IndexSearcher(reader);
  Term t=new Term(f,s);
  FuzzyQuery query=new FuzzyQuery(t,0.3f);
  TopDocs tds=searcher.search(query,num);
  int total=tds.totalHits;
     System.out.println("共搜索到"+total+"条结果");
  ScoreDoc[] sds=tds.scoreDocs;
    for(ScoreDoc sd:sds)
    {
     Document doc=searcher.doc(sd.doc);
     System.out.println(doc.get("id")+doc.get("name")+doc.get("address"));
    }
    reader.close();
    searcher.close();
   }
}