lucene上千万的数据翻页怎么这么慢啊,基本上要5s-6s。前面的页数还比较快,越到后面的页数翻页越慢。
贴上代码:
方式一:
public static void searchPage(int pageIndex,int pageSize) throws IOException, ParseException{
Date start=new Date();
Directory dir=FSDirectory.open(Paths.get("D:\\FCJS\\FCJS_bigdata_lucene5.3.0"));
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher=new IndexSearcher(reader);
Analyzer analyzer=new IKAnalyzer(false);//false细粒度分词,true智能分词
QueryParser parser=new QueryParser("all", analyzer);
Query query=parser.parse("all");
TopDocs tds = searcher.search(query,Integer.MAX_VALUE);
ScoreDoc[] sds = tds.scoreDocs;
int page_start = (pageIndex-1)*pageSize;
int page_end = pageIndex*pageSize;
for(int i=page_start;i<page_end;i++) {
Document doc = searcher.doc(sds[i].doc);
System.out.println(sds[i].doc+":"+doc.get("ArticleID"));
}
Date end=new Date();
System.out.println("耗时:"+(end.getTime()-start.getTime())+"ms");
}
方式二:
private static void searchPageByAfter(int pageIndex,int pageSize) throws IOException, ParseException{
Date start=new Date();
Directory dir=FSDirectory.open(Paths.get("D:\\FCJS\\FCJS_bigdata"));
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher=new IndexSearcher(reader);
Analyzer analyzer=new IKAnalyzer(false);//false细粒度分词,true智能分词
QueryParser parser=new QueryParser("all", analyzer);
Query query=parser.parse("all");
//获取上一页的最后一个元素
ScoreDoc lastSd = getLastScoreDoc(pageIndex, pageSize, query, searcher);
//通过最后一个元素去搜索下一页的元素
TopDocs tds = searcher.searchAfter(lastSd,query, pageSize);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(sd.doc+":"+doc.get("ArticleID"));
}
Date end=new Date();
System.out.println("耗时:"+(end.getTime()-start.getTime())+"ms");
}