Lucene 4.3 - Facet demo
package com.fox.facet; import java.io.IOException;
import java.util.ArrayList;
import java.util.List; import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.facet.index.FacetFields;
import org.apache.lucene.facet.params.FacetSearchParams;
import org.apache.lucene.facet.search.CountFacetRequest;
import org.apache.lucene.facet.search.DrillDownQuery;
import org.apache.lucene.facet.search.FacetResult;
import org.apache.lucene.facet.search.FacetsCollector;
import org.apache.lucene.facet.taxonomy.CategoryPath;
import org.apache.lucene.facet.taxonomy.TaxonomyReader;
import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version; /*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/ /** Shows simple usage of faceted indexing and search. */
public class SimpleFacetsExample { private final Directory indexDir = new RAMDirectory();
private final Directory taxoDir = new RAMDirectory(); /** Empty constructor */
public SimpleFacetsExample() {
} private void add(IndexWriter indexWriter, FacetFields facetFields, String... categoryPaths) throws IOException {
Document doc = new Document(); List<CategoryPath> paths = new ArrayList<CategoryPath>();
for (String categoryPath : categoryPaths) {
paths.add(new CategoryPath(categoryPath, '/'));
}
facetFields.addFields(doc, paths);
indexWriter.addDocument(doc);
} /** Build the example index. */
private void index() throws IOException {
IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(Version.LUCENE_43, new WhitespaceAnalyzer(
Version.LUCENE_43))); // Writes facet ords to a separate directory from the main index
DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir); // Reused across documents, to add the necessary facet fields
FacetFields facetFields = new FacetFields(taxoWriter); add(indexWriter, facetFields, "Author/Bob", "Publish Date/2010/10/15");
add(indexWriter, facetFields, "Author/Lisa", "Publish Date/2010/10/20");
add(indexWriter, facetFields, "Author/Lisa", "Publish Date/2012/1/1");
add(indexWriter, facetFields, "Author/Susan", "Publish Date/2012/1/7");
add(indexWriter, facetFields, "Author/Frank", "Publish Date/1999/5/5"); indexWriter.close();
taxoWriter.close();
} /** User runs a query and counts facets. */
private List<FacetResult> search() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); // Count both "Publish Date" and "Author" dimensions
FacetSearchParams fsp = new FacetSearchParams(new CountFacetRequest(new CategoryPath("Publish Date"), 10),
new CountFacetRequest(new CategoryPath("Author"), 10)); // Aggregatses the facet counts
FacetsCollector fc = FacetsCollector.create(fsp, searcher.getIndexReader(), taxoReader); // MatchAllDocsQuery is for "browsing" (counts facets
// for all non-deleted docs in the index); normally
// you'd use a "normal" query, and use MultiCollector to
// wrap collecting the "normal" hits and also facets:
searcher.search(new MatchAllDocsQuery(), fc); // Retrieve results
List<FacetResult> facetResults = fc.getFacetResults(); indexReader.close();
taxoReader.close(); return facetResults;
} /** User drills down on 'Publish Date/2010'. */
private List<FacetResult> drillDown() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); // Now user drills down on Publish Date/2010:
FacetSearchParams fsp = new FacetSearchParams(new CountFacetRequest(new CategoryPath("Author"), 10));
DrillDownQuery q = new DrillDownQuery(fsp.indexingParams, new MatchAllDocsQuery());
q.add(new CategoryPath("Publish Date/2010", '/'));
FacetsCollector fc = FacetsCollector.create(fsp, searcher.getIndexReader(), taxoReader);
searcher.search(q, fc); // Retrieve results
List<FacetResult> facetResults = fc.getFacetResults(); indexReader.close();
taxoReader.close(); return facetResults;
} /** Runs the search example. */
public List<FacetResult> runSearch() throws IOException {
index();
return search();
} /** Runs the drill-down example. */
public List<FacetResult> runDrillDown() throws IOException {
index();
return drillDown();
} /** 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("-----------------------");
List<FacetResult> results = new SimpleFacetsExample().runSearch();
for (FacetResult res : results) {
System.out.println(res);
} System.out.println("\n");
System.out.println("Facet drill-down example (Publish Date/2010):");
System.out.println("---------------------------------------------");
results = new SimpleFacetsExample().runDrillDown();
for (FacetResult res : results) {
System.out.println(res);
}
} }
Result:
Facet counting example:
-----------------------
Request: Publish Date nRes=10 nLbl=10
Num valid Descendants (up to specified depth): 3
Publish Date (0.0)
Publish Date/2012 (2.0)
Publish Date/2010 (2.0)
Publish Date/1999 (1.0)
Request: Author nRes=10 nLbl=10
Num valid Descendants (up to specified depth): 4
Author (0.0)
Author/Lisa (2.0)
Author/Frank (1.0)
Author/Susan (1.0)
Author/Bob (1.0) Facet drill-down example (Publish Date/2010):
---------------------------------------------
Request: Author nRes=10 nLbl=10
Num valid Descendants (up to specified depth): 2
Author (0.0)
Author/Lisa (1.0)
Author/Bob (1.0)
Lucene 4.3 - Facet demo的更多相关文章
- Lucene 4.8 - Facet Demo
package com.fox.facet; /* * Licensed to the Apache Software Foundation (ASF) under one or more * con ...
- lucene 4.0 - Facet demo
package com.fox.facet; import java.io.File; import java.io.IOException; import java.util.ArrayList; ...
- lucene搜索之facet查询原理和facet查询实例——TODO
转自:http://www.lai18.com/content/7084969.html Facet说明 我们在浏览网站的时候,经常会遇到按某一类条件查询的情况,这种情况尤以电商网站最多,以天猫商城为 ...
- (一)Lucene简介以及索引demo
一.百度百科 Lucene是apache软件基金会4 jakarta项目组的一个子项目,是一个开放源代码的全文检索引擎工具包,但它不是一个完整的全文检索引擎,而是一个全文检索引擎的架构,提供了完整的查 ...
- Facet with Lucene
Facets with Lucene Posted on August 1, 2014 by Pascal Dimassimo in Latest Articles During the develo ...
- lucene 索引 demo
核心util /** * Alipay.com Inc. * Copyright (c) 2004-2015 All Rights Reserved/ */ package com.lucene.de ...
- MVC+MQ+WinServices+Lucene.Net Demo
前言: 我之前没有接触过Lucene.Net相关的知识,最近在园子里看到很多大神在分享这块的内容,深受启发.秉着“实践出真知”的精神,再结合公司项目的实际情况,有了写一个Demo的想法,算是对自己能力 ...
- Lucene系列-facet
1.facet的直观认识 facet:面.切面.方面.个人理解就是维度,在满足query的前提下,观察结果在各维度上的分布(一个维度下各子类的数目). 如jd上搜“手机”,得到4009个商品.其中品牌 ...
- lucene 4.4 demo
ackage com.zxf.demo; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStr ...
随机推荐
- jquery中on绑定click事件在苹果手机失效的问题
因为是动态添加的内容,所以想要使用click事件,需要给他用on绑定一下: $(document).on("click",".next_button",func ...
- HPU第四次积分赛-L:A Winged Steed(完全背包)
A Winged Steed 描述 有n种千里马,每一种都有若干匹,第i种马的颜值ai,价格di.现有m个牧马人要去挑选千里马,每一位牧马人对马的颜值都有要求:{所选马的颜值总和} ⩾Ai.现在 ...
- scripy
性能相关 在编写爬虫时,性能的消耗主要在IO请求中,当单进程单线程模式下请求URL时必然会引起等待,从而使得请求整体变慢. import requests def fetch_async(url): ...
- Windows 10瘦身
Windows操作系统功能越来越强大,同时体型也越来越臃肿.安装盘没有60Gb都不敢安装.Windows10 安装最低磁盘要求20G ====瘦身基础篇,适合任何用户:(可见目录,简单迁移)1. 安装 ...
- C# 后台获取API接口数据
using System; using System.Collections.Generic; using System.IO; using System.Linq; using System.Net ...
- (18)模型层 -ORM之msql 多表操作(字段的属性)
数据库表的对应关系 1.一对一 #关联字段写在那张表都可以 PS:只要写OneToOneField就会自动加一个id 2.一对多 #关系确立,关联字段写在多的一方 3.多对多 #多对多的关系 ...
- (10)MySQL触发器(同时操作两张表)
什么是触发器 触发器是与表有关的数据库对象,在满足定义条件时触发,并执行触发器中定义的语句集合.触发器的这种特性可以协助应用在数据库端确保数据的完整性. 举个例子,比如你现在有两个表[用户表]和[日志 ...
- time,datetime模块
time & datetime 模块 在平常的代码中,我们常常需要与时间打交道.在Python中,与时间处理有关的模块就包括:time,datetime,calendar(很少用,不讲),下面 ...
- struts2拦截器执行模拟 参考马士兵老师
public class ActionProxy { public static void main(String[] args) { //模拟ActionProxy调用invoke()方法 Acti ...
- Redis(一)入门
最近,学习了一下,Redis 这个Nosql数据库,从安装到基本语法,作为入门.下面,整理一下基本知识. 参考的地址如下: http://www.runoob.com/redis/redis-java ...