lucene源码分析(3)facet实例
简单的facet实例
public class SimpleFacetsExample {
private final Directory indexDir = new RAMDirectory();
private final Directory taxoDir = new RAMDirectory();
private final FacetsConfig config = new FacetsConfig();
/** Empty constructor */
public SimpleFacetsExample() {
config.setHierarchical("Publish Date", true);
}
/** Build the example index. */
private void index() throws IOException {
IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(
new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));
// Writes facet ords to a separate directory from the main index
DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
Document doc = new Document();
doc.add(new FacetField("Author", "Bob"));
doc.add(new FacetField("Publish Date", "2010", "10", "15"));
indexWriter.addDocument(config.build(taxoWriter, doc));
doc = new Document();
doc.add(new FacetField("Author", "Lisa"));
doc.add(new FacetField("Publish Date", "2010", "10", "20"));
indexWriter.addDocument(config.build(taxoWriter, doc));
doc = new Document();
doc.add(new FacetField("Author", "Lisa"));
doc.add(new FacetField("Publish Date", "2012", "1", "1"));
indexWriter.addDocument(config.build(taxoWriter, doc));
doc = new Document();
doc.add(new FacetField("Author", "Susan"));
doc.add(new FacetField("Publish Date", "2012", "1", "7"));
indexWriter.addDocument(config.build(taxoWriter, doc));
doc = new Document();
doc.add(new FacetField("Author", "Frank"));
doc.add(new FacetField("Publish Date", "1999", "5", "5"));
indexWriter.addDocument(config.build(taxoWriter, doc));
indexWriter.close();
taxoWriter.close();
}
/** User runs a query and counts facets. */
private List<FacetResult> facetsWithSearch() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
FacetsCollector fc = new FacetsCollector();
// MatchAllDocsQuery is for "browsing" (counts facets
// for all non-deleted docs in the index); normally
// you'd use a "normal" query:
FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
// Retrieve results
List<FacetResult> results = new ArrayList<>();
// Count both "Publish Date" and "Author" dimensions
Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
results.add(facets.getTopChildren(10, "Author"));
results.add(facets.getTopChildren(10, "Publish Date"));
indexReader.close();
taxoReader.close();
return results;
}
/** User runs a query and counts facets only without collecting the matching documents.*/
private List<FacetResult> facetsOnly() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
FacetsCollector fc = new FacetsCollector();
// MatchAllDocsQuery is for "browsing" (counts facets
// for all non-deleted docs in the index); normally
// you'd use a "normal" query:
searcher.search(new MatchAllDocsQuery(), fc);
// Retrieve results
List<FacetResult> results = new ArrayList<>();
// Count both "Publish Date" and "Author" dimensions
Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
results.add(facets.getTopChildren(10, "Author"));
results.add(facets.getTopChildren(10, "Publish Date"));
indexReader.close();
taxoReader.close();
return results;
}
/** User drills down on 'Publish Date/2010', and we
* return facets for 'Author' */
private FacetResult drillDown() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
// Passing no baseQuery means we drill down on all
// documents ("browse only"):
DrillDownQuery q = new DrillDownQuery(config);
// Now user drills down on Publish Date/2010:
q.add("Publish Date", "2010");
FacetsCollector fc = new FacetsCollector();
FacetsCollector.search(searcher, q, 10, fc);
// Retrieve results
Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
FacetResult result = facets.getTopChildren(10, "Author");
indexReader.close();
taxoReader.close();
return result;
}
/** User drills down on 'Publish Date/2010', and we
* return facets for both 'Publish Date' and 'Author',
* using DrillSideways. */
private List<FacetResult> drillSideways() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
// Passing no baseQuery means we drill down on all
// documents ("browse only"):
DrillDownQuery q = new DrillDownQuery(config);
// Now user drills down on Publish Date/2010:
q.add("Publish Date", "2010");
DrillSideways ds = new DrillSideways(searcher, config, taxoReader);
DrillSidewaysResult result = ds.search(q, 10);
// Retrieve results
List<FacetResult> facets = result.facets.getAllDims(10);
indexReader.close();
taxoReader.close();
return facets;
}
/** Runs the search example. */
public List<FacetResult> runFacetOnly() throws IOException {
index();
return facetsOnly();
}
/** Runs the search example. */
public List<FacetResult> runSearch() throws IOException {
index();
return facetsWithSearch();
}
/** Runs the drill-down example. */
public FacetResult runDrillDown() throws IOException {
index();
return drillDown();
}
/** Runs the drill-sideways example. */
public List<FacetResult> runDrillSideways() throws IOException {
index();
return drillSideways();
}
/** Runs the search and drill-down examples and prints the results. */
public static void main(String[] args) throws Exception {
System.out.println("Facet counting example:");
System.out.println("-----------------------");
SimpleFacetsExample example = new SimpleFacetsExample();
List<FacetResult> results1 = example.runFacetOnly();
System.out.println("Author: " + results1.get(0));
System.out.println("Publish Date: " + results1.get(1));
System.out.println("Facet counting example (combined facets and search):");
System.out.println("-----------------------");
List<FacetResult> results = example.runSearch();
System.out.println("Author: " + results.get(0));
System.out.println("Publish Date: " + results.get(1));
System.out.println("Facet drill-down example (Publish Date/2010):");
System.out.println("---------------------------------------------");
System.out.println("Author: " + example.runDrillDown());
System.out.println("Facet drill-sideways example (Publish Date/2010):");
System.out.println("---------------------------------------------");
for(FacetResult result : example.runDrillSideways()) {
System.out.println(result);
}
}
}
查询及其关系
查询
/** Lower-level search API.
*
* <p>{@link LeafCollector#collect(int)} is called for every matching document.
*
* @throws BooleanQuery.TooManyClauses If a query would exceed
* {@link BooleanQuery#getMaxClauseCount()} clauses.
*/
public void search(Query query, Collector results)
throws IOException {
query = rewrite(query);
search(leafContexts, createWeight(query, results.needsScores(), 1), results);
}
关系

lucene源码分析(3)facet实例的更多相关文章
- Lucene 源码分析之倒排索引(三)
上文找到了 collect(-) 方法,其形参就是匹配的文档 Id,根据代码上下文,其中 doc 是由 iterator.nextDoc() 获得的,那 DefaultBulkScorer.itera ...
- 一个lucene源码分析的博客
ITpub上的一个lucene源码分析的博客,写的比较全面:http://blog.itpub.net/28624388/cid-93356-list-1/
- Vue源码分析(二) : Vue实例挂载
Vue源码分析(二) : Vue实例挂载 author: @TiffanysBear 实例挂载主要是 $mount 方法的实现,在 src/platforms/web/entry-runtime-wi ...
- JVM源码分析-类加载场景实例分析
A类调用B类的静态方法,除了加载B类,但是B类的一个未被调用的方法间接使用到的C类却也被加载了,这个有意思的场景来自一个提问:方法中使用的类型为何在未调用时尝试加载?. 场景如下: public cl ...
- HashMap源码分析和应用实例的介绍
1.HashMap介绍 HashMap 是一个散列表,它存储的内容是键值对(key-value)映射.HashMap 继承于AbstractMap,实现了Map.Cloneable.java.io.S ...
- Stack的源码分析和应用实例
1.Stack介绍 Stack是栈.它的特性是:先进后出(FILO:First In Last Out). java工具包中的Stack是继承于Vector(矢量队列)的,由于Vector是通过数组实 ...
- lucene源码分析的一些资料
针对lucene6.1较新的分析:http://46aae4d1e2371e4aa769798941cef698.devproxy.yunshipei.com/conansonic/article/d ...
- lucene源码分析(1)基本要素
1.源码包 core: Lucene core library analyzers-common: Analyzers for indexing content in different langua ...
- mybatis源码分析(1)——SqlSessionFactory实例的产生过程
在使用mybatis框架时,第一步就需要产生SqlSessionFactory类的实例(相当于是产生连接池),通过调用SqlSessionFactoryBuilder类的实例的build方法来完成.下 ...
随机推荐
- Python学习-34.Python中os模块的一些方法(二)
stat方法: 用于获取文件信息,例如创建时间.文件大小等. import os filestate=os.stat("e:/temp/test.txt") print(files ...
- Git安全配置
今天收到了阿里云异地登录的短信报警,登录阿里云后台发现,有人从深圳登录了我的服务器(本人在北京),查看详细信息一共登录了5次,前两次是使用的git用户进行登录,后两次已经变成了root用户,怀疑是 ...
- LeetCode151:Reverse Words in a String
题目: Given an input string, reverse the string word by word. For example, Given s = "the sk ...
- 3D空间中射线与三角形的交叉检测算法【转】
引言 射线Ray,在3D图形学中有很多重要的应用.比如,pick操作就是使用射线Ray来实现的,还有诸如子弹射线的碰撞检测等等都可以使用射线Ray来完成.所以,在本次博客中,将会简单的像大家介绍下,如 ...
- HLSL-高级着色语言简介【转】
HLSL-High Level Shader Language 优点 用来书写Vertex Shader和Pixel Shader程序的代码,语法类似于C/C++,在DirectX 8.x的时代,Sh ...
- C# 读取Excel,一波华丽的操作
C# 读取Excel,其实有很多方法.但是今天要来一波华丽的操作. 先看效果: 以上这波操作使用了 ExcelDataReader 和 ExcelDataReader.DataSet 完成的. Exc ...
- C#穿透session隔离———Windows服务启动UI交互程序
在Windows服务里面启动其他具有界面的应用程序,需要穿透session隔离,尝试了很多种方法,都可行,现在一一列举下来,并写下几个需要注意的地方. 需要注意的地方 首先要将服务的Account属性 ...
- SSM集成Easyui框架及多模块开发的认识
首先我们需要建立好一个emaven项目,并且在pom.xml中导入响应的jar包, <?xml version="1.0" encoding="UTF-8" ...
- Java基础学习篇---------static
一.static的使用 1.使用static定义的属性往往通过类名直接调用,它的属性(方法)不属于某一个的对象的.所以对象没有创建之前就可以对static的属性的调用,方法亦如此. 2.static ...
- django 自定义中间件 middleware
Django 中间件 Django中的中间件是一个轻量级.底层的插件系统,可以介入Django的请求和响应处理过程,修改Django的输入或输出.中间件的设计为开发者提供了一种无侵入式的开发方式,增强 ...