lucene QueryParser用法示例

最新推荐文章于 2021-02-24 21:19:49 发布

置顶 feixiangdexin123087

最新推荐文章于 2021-02-24 21:19:49 发布

阅读量9.4k

点赞数 1

CC 4.0 BY-SA版权

分类专栏： lucene java LuceneSearch 文章标签： lucene search 正则表达式 string path

本文链接：https://blog.youkuaiyun.com/feixiangdexin123087/article/details/8053121

java 同时被 3 个专栏收录

55 篇文章

订阅专栏

LuceneSearch

8 篇文章

订阅专栏

lucene

4 篇文章

订阅专栏

本文介绍了一个基于Lucene的搜索应用实例，演示了如何构建索引、执行不同类型的查询及优化搜索性能。通过具体代码示例，展示了如何使用QueryParser解析查询、如何执行搜索并返回结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Java代码

packagedemo.first;
importjava.io.IOException;
importjava.util.Date;
importorg.apache.lucene.analysis.standard.StandardAnalyzer;
importorg.apache.lucene.document.Document;
importorg.apache.lucene.document.Field;
importorg.apache.lucene.index.CorruptIndexException;
importorg.apache.lucene.index.IndexWriter;
importorg.apache.lucene.queryParser.QueryParser;
importorg.apache.lucene.search.Hits;
importorg.apache.lucene.search.IndexSearcher;
importorg.apache.lucene.search.Query;
importorg.apache.lucene.search.Searcher;
importorg.apache.lucene.store.LockObtainFailedException;
publicclassTestQueryParser{
publicstaticvoidmain(String[]args)throwsCorruptIndexException,IOException{
Stringpath="D://workspace//fwk//lucenedemo//firstLuceneIndex";
TestQueryParsertqp=newTestQueryParser();
tqp.createIndex(path);
Searchersearch=tqp.getSearcher(path);
System.out.println("#_2");
tqp.testTime(search,tqp.getQueryParser2());
System.out.println("#_1");
tqp.testTime(search,tqp.getQueryParser1());
System.out.println("#_3");
tqp.testTime(search,tqp.getQueryParser3());
System.out.println("#_4");
tqp.testTime(search,tqp.getQueryParser4());
System.out.println("#_5");
tqp.testTime(search,tqp.getQueryParser5());
System.out.println("#_6");
tqp.testTime(search,tqp.getQueryParser6());
System.out.println("#_7");
tqp.testTime(search,tqp.getQueryParser7());
}
publicvoidtestTime(Searchersearch,Queryquery)throwsIOException{
Datestart=newDate();
Hitshits=search.search(query);
for(inti=0;i<hits.length();i++){
System.out.println(hits.id(i));
System.out.println(hits.doc(i));
System.out.println(hits.score(i));
}
System.out.println("本次搜索用时："+((newDate()).getTime()-start.getTime())+"毫秒");
}
publicSearchergetSearcher(Stringpath)throwsCorruptIndexException,IOException{
returnnewIndexSearcher(path);
}
publicQuerygetQueryParser1(){
//默认搜索字段
QueryParserqueryParser=newQueryParser("content",newStandardAnalyzer());
try{
returnqueryParser.parse("搜索-擎");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicQuerygetQueryParser2(){
QueryParserqueryParser=newQueryParser("content",newStandardAnalyzer());
try{
returnqueryParser.parse("欢迎");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicQuerygetQueryParser3(){
QueryParserqueryParser=newQueryParser("content",newStandardAnalyzer());
try{
returnqueryParser.parse("搜索and擎");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicQuerygetQueryParser4(){
QueryParserqueryParser=newQueryParser("content",newStandardAnalyzer());
try{
//content字段搜索索引title字段搜寻你好
returnqueryParser.parse("索引title:你好");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicQuerygetQueryParser5(){
QueryParserqueryParser=newQueryParser("content",newStandardAnalyzer());
//允许使用正则表达式方式,则可模糊查询
queryParser.setAllowLeadingWildcard(true);
try{
returnqueryParser.parse("*索*");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicQuerygetQueryParser6(){
QueryParserqueryParser=newQueryParser("testCapital",newStandardAnalyzer());
try{
returnqueryParser.parse("hellOwangzi");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicQuerygetQueryParser7(){
QueryParserqueryParser=newQueryParser("testAndOr",newStandardAnalyzer());
try{
//returnqueryParser.parse("and");
returnqueryParser.parse("test");
}catch(Exceptione){
e.printStackTrace();
}
returnnull;
}
publicvoidcreateIndex(Stringpath){
try{
IndexWriterwriter=newIndexWriter(path,newStandardAnalyzer(),true);
DocumentdocA=newDocument();
//相当于数据库中列的概念，因此第一个参数是列名，第二个参数是列的值，最后两个参数是enum类型的(JDK1.5)，对创建的索引的设置
//Field.Store是否覆盖原来的索引文件，而不是重新建一个
FieldfieldA=newField("content","搜索引擎",Field.Store.YES,Field.Index.TOKENIZED);
//我们把列(fieldA)加到某一行(docA)中
docA.add(fieldA);
docA.add(newField("title","你好中国",Field.Store.YES,Field.Index.TOKENIZED));
docA.add(newField("content","欢迎你llying",Field.Store.YES,Field.Index.TOKENIZED));
docA.add(newField("lastModifyTime","2008-9-17",Field.Store.YES,Field.Index.TOKENIZED));
docA.add(newField("testCapital","HelloWangzi",Field.Store.YES,Field.Index.TOKENIZED));
docA.add(newField("testAndOr","testand",Field.Store.YES,Field.Index.TOKENIZED));
DocumentdocB=newDocument();
//相当于数据库中列的概念，因此第一个参数是列名，第二个参数是列的值，最后两个参数是enum类型的(JDK1.5)，对创建的索引的设置
FieldfieldB=newField("content","创建索引",Field.Store.YES,Field.Index.TOKENIZED);
//我们把列(fieldA)加到某一行(docA)中
docB.add(fieldB);
docB.add(newField("title","你好世界",Field.Store.YES,Field.Index.TOKENIZED));
docB.add(newField("content","欢迎加入jee高级开发群46176507",Field.Store.YES,Field.Index.TOKENIZED));
docB.add(newField("lastModifyTime","2008-9-6",Field.Store.YES,Field.Index.TOKENIZED));
docB.add(newField("testCapital","hellowangZi",Field.Store.YES,Field.Index.TOKENIZED));
docB.add(newField("testAndOr","testor",Field.Store.YES,Field.Index.TOKENIZED));
writer.addDocument(docA);
writer.addDocument(docB);
//如果对海量数据进行创建索引的时候，需要对索引进行优化，以便提高速度
writer.optimize();
//跟数据库类似，打开一个连接，使用完后，要关闭它
writer.close();
}catch(CorruptIndexExceptione){
e.printStackTrace();
}catch(LockObtainFailedExceptione){
e.printStackTrace();
}catch(IOExceptione){
e.printStackTrace();
}
}
}

示例2：

/**
* 通过搜索条件获取列表信息
* @param keyword 搜索关键字
* @return List
* */
public static String findGoodsByKeyword(String keyword)
{
  StringBuilder sb = new StringBuilder();
  IndexSearcher searcher = null;
  Directory dir = null;
  StandardAnalyzer analyzer = null;
  try
  {
   keyword = getKeyword(keyword);
   BooleanQuery booleanQuery = new BooleanQuery();
   dir = FSDirectory.open(new File(ParamInit.getInitParameter("lucene_path")));
   searcher = new IndexSearcher(dir, true);
   analyzer = new StandardAnalyzer(Version.LUCENE_30);
   MultiFieldQueryParser multiParser1=new MultiFieldQueryParser(Version.LUCENE_CURRENT, new String[]{"name1" , "nameeng1" , "country"},analyzer);
   // OR ：设置以空格分开的短语keword是'或'的关系;
   multiParser1.setDefaultOperator(QueryParser.Operator.OR );
   //允许使用正则表达式方式,"*" 可模糊查询
   multiParser1.setAllowLeadingWildcard(true);
   //keword 可以使用空格隔开,"*" 可模糊查询
   Query multi_parser1 = multiParser1.parse("*"+keyword+"*" );
   System.out.println("Query转化后的Term内容为："+multi_parser1.toString());

   //SHOULD:表示“或”关系，最终检索结果为所有检索子句的并集
   booleanQuery.add(multi_parser1 , BooleanClause.Occur.SHOULD);

   //SortField.SCORE : 关键字搜索按近似排序，Score--匹配分值
   Sort sort = new Sort(new SortField[]{new SortField("status" , SortField.STRING , true),new SortField("name1" , SortField.SCORE , false),new SortField("nameeng1" , SortField.SCORE, false),new SortField("country" , SortField.SCORE, false)});

   TopFieldCollector topCollector = TopFieldCollector.create(sort , 8 , true , true , true , false);
            searcher.search(booleanQuery , null , topCollector);
   ScoreDoc[] docs = topCollector.topDocs(0).scoreDocs;
   int i = 1;
   for(ScoreDoc scdoc : docs)
   {
    Document doc = searcher.doc(scdoc.doc);
            sb.append("<li id='").append(doc.get("id")).append("'>").append(doc.get("name")) .append("</li>");
            i++;
            if(i >8)
              break;
         }
  }
  catch (Exception e)
  {
   e.printStackTrace();
  }
  finally
  {
   try
   {
    if(null != analyzer)analyzer.close();
    if(null != searcher)searcher.close();
    if(null != dir)dir.close();
   }
   catch (IOException e)
   {
    e.printStackTrace();
   }
  }
  return sb.toString();
}