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

  1. Lucene 4.8 - Facet Demo

    package com.fox.facet; /* * Licensed to the Apache Software Foundation (ASF) under one or more * con ...

  2. lucene 4.0 - Facet demo

    package com.fox.facet; import java.io.File; import java.io.IOException; import java.util.ArrayList; ...

  3. 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 ...

  4. (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 ...

  5. Facet with Lucene

    Facets with Lucene Posted on August 1, 2014 by Pascal Dimassimo in Latest Articles During the develo ...

  6. lucene 索引 demo

    核心util /** * Alipay.com Inc. * Copyright (c) 2004-2015 All Rights Reserved/ */ package com.lucene.de ...

  7. 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 ...

  8. 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 ...

  9. lucene 4.4 demo

    ackage com.zxf.demo; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStr ...

随机推荐

  1. 【HDOJ1043】【康拓展开+BFS】

    http://acm.hdu.edu.cn/showproblem.php?pid=1043 Eight Time Limit: 10000/5000 MS (Java/Others)    Memo ...

  2. Go Example--工作池

    package main import ( "fmt" "time" ) func main() { jobs :=make(chan int,100) res ...

  3. MySQL Execution Plan--数据排序操作

    MySQL数据排序 MySQL中对数据进行排序有三种方式:1.常规排序(双路排序)2.优化排序(单路排序)3.优先队列排序 优先队列排序使用对排序算法,利用堆数据结构在所有数据中取出前N条记录. 常规 ...

  4. phpdocumentor安装和使用总结

    为了解决一校友在安装和使用phpDocumentor过程中遇到的问题,自己闲时也折腾了一下这个东西,总结见下: 一.定义: 自己刚听到这个词时还不知道这个是什么东西,干啥用的,就去百度了一下,说道: ...

  5. 目前支持WebGL的浏览器有哪些?

    Google Chrome 9+ Mozilla Firefox 4+ Safari 5.1+(仅限于Mac OS X操作系统,不包括Windows) Opera 12 alpha及以上版本 IE9+ ...

  6. python 简明教程 【转】

    转自:https://learnxinyminutes.com/docs/python/ # Single line comments start with a number symbol. &quo ...

  7. Percona XtraDB Cluster 的一些使用限制(PXC 5.7)

    Percona XtraDB Cluster有众多的优秀特性,使得mysql集群得以轻松实现.但是不要忽略了它的一些限制.如果你无法接受,或者你的应用程序或数据库(比如使用了memory引擎)对限制无 ...

  8. kafka 学习资料

    kafka 学习资料 kafka 学习资料 网址 kafka 中文教程 http://orchome.com/kafka/index

  9. TypeScript 之 函数

    https://m.runoob.com/manual/gitbook/TypeScript/_book/doc/handbook/Functions.html 为函数定义类型 为函数添加类型: fu ...

  10. 比较字典推导式/dict()/通过键来构造的字典的速率 笔记

    # 下面结果执行一次不容易出差距,所以都执行100000次 import time dict1 = {'a':1, 'b':2, 'c':3, 'd':4} # 第一种:字典推导式 start_tim ...