lucene学习之近实时搜索

清疚 2022-08-21 06:57 217阅读 0赞

下面是近实时搜索的一个例子

public class IndexFenci \{  
  
private static String\[\] ids = \{"1","2","3"\};  
private static String\[\] citys = \{"北京","南京","上海"\};  
private static String\[\] descs = \{"北京是一个美丽的城市。",  
"南京是一个有文化的城市。",  
"上海是一个繁华的城市。"\};  
private static IndexWriter writer = null;  
private static SearcherManager sm =null;  
private static IndexSearcher is =null;  
public static void main(String\[\] args)\{  
try \{  
  
Directory d = FSDirectory.open(Paths.get("D:/lucene/index"));  
SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();  
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);  
writer = new IndexWriter(d, iwc);  
TrackingIndexWriter track = new TrackingIndexWriter(writer);  
track.deleteAll();  
for(int i=0;i<ids.length;i++)\{  
Document  doc = new Document();  
doc.add(new StringField("city", citys\[i\], Field.Store.YES));  
doc.add(new StringField("id", ids\[i\], Field.Store.YES));  
doc.add(new TextField("desc",descs\[i\],Field.Store.YES));  
track.addDocument(doc);\}  
System.out.println("索引："+writer.numDocs()+"文件");  
//近实时搜索  
sm = new SearcherManager(writer, true, new SearcherFactory());  
ControlledRealTimeReopenThread<IndexSearcher> crt = new ControlledRealTimeReopenThread<IndexSearcher>(track, sm, 3.0, 0.05);  
crt.setDaemon(true);  
crt.setName("后台搜索服务");  
crt.start();

QueryParser parser = new QueryParser("desc",new SmartChineseAnalyzer());  
Query query = parser.parse("南京城市");  
  
Document  doc = new Document();  
doc.add(new StringField("city", "杭州", Field.Store.YES));  
doc.add(new StringField("id", "4", Field.Store.YES));  
doc.add(new TextField("desc","杭州是一个美丽的城市",Field.Store.YES));  
track.addDocument(doc);  
  
sm.maybeRefresh();  
is = sm.acquire();  
  
TopDocs top = is.search(query, 10);  
for (ScoreDoc scoreDoc:top.scoreDocs) \{  
Document document= is.doc(scoreDoc.doc);  
System.out.print("编号："+scoreDoc.doc);  
System.out.print(" 分数: "+scoreDoc.score);  
System.out.print(" id: "+document.get("id"));  
System.out.print(" city: "+document.get("city"));  
System.out.print(" desc: "+document.get("desc"));  
System.out.println();  
\}  
  
\} catch (Exception e) \{  
e.printStackTrace();  
\} finally\{  
try \{  
sm.release(is);  
//if(writer !=null)\{  
//writer.close();  
//\}  
\} catch (IOException e) \{  
e.printStackTrace();  
\}  
\}  
  
\}  
\}

这样输出的是：

索引：3文件  
编号：1 分数: 0.27066463 id: 2 city: 南京 desc: 南京是一个有文化的城市。  
编号：0 分数: 0.06074384 id: 1 city: 北京 desc: 北京是一个美丽的城市。  
编号：2 分数: 0.06074384 id: 3 city: 上海 desc: 上海是一个繁华的城市。  
编号：3 分数: 0.06074384 id: 4 city: 杭州 desc: 杭州是一个美丽的城市

但是杭州这条索引信息还没有存到本地。用下面的程序去搜索：

public class SearcherFenci \{  
public static IndexSearcher is =null;  
public static IndexReader indexReader = null;  
public static void main(String\[\] args) throws IOException \{  
  
SearcherFenci searcherFenci = new SearcherFenci();  
searcherFenci.displayAllTokenInfo("南京城市");  
  
\}  
  
  
/\*\*  
\* 得到分词的结果  
\*/  
public  void displayAllTokenInfo(String str)\{  
try \{  
Directory d = FSDirectory.open(Paths.get("D:/lucene/index"));  
indexReader = DirectoryReader.open(d);  
System.out.println("maxdoc: "+indexReader.maxDoc());  
System.out.println("numdoc: "+indexReader.numDocs());  
System.out.println("numdeletedoc: "+indexReader.numDeletedDocs());  
SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();  
IndexSearcher is = new IndexSearcher(indexReader);  
QueryParser queryParser = new QueryParser("desc", analyzer);  
Query query = queryParser.parse(str);  
TopDocs top = is.search(query, 10);  
  
for(ScoreDoc scoreDoc : top.scoreDocs)\{  
Document doc = is.doc(scoreDoc.doc);  
System.out.print("编号："+scoreDoc.doc);  
System.out.print(" 分数: "+scoreDoc.score);  
System.out.print(" id: "+doc.get("id"));  
System.out.print(" city: "+doc.get("city"));  
System.out.print(" desc: "+doc.get("desc"));  
System.out.println();  
\}  
indexReader.close();  
\} catch (Exception e) \{  
e.printStackTrace();  
\}  
\}  
\}

输出的结果是：

maxdoc: 3  
numdoc: 3  
numdeletedoc: 0  
编号：1 分数: 0.5908754 id: 2 city: 南京 desc: 南京是一个有文化的城市。  
编号：0 分数: 0.06037879 id: 1 city: 北京 desc: 北京是一个美丽的城市。  
编号：2 分数: 0.06037879 id: 3 city: 上海 desc: 上海是一个繁华的城市。

杭州没在本地索引中，因为还没提交。这样就是近实时索引的内容了。可以搜索到还没提交的修改信息。