Lucene 4.8 - Facet Demo
package com.fox.facet; /*
* 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.
*/ 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.DrillDownQuery;
import org.apache.lucene.facet.DrillSideways;
import org.apache.lucene.facet.DrillSideways.DrillSidewaysResult;
import org.apache.lucene.facet.FacetField;
import org.apache.lucene.facet.FacetResult;
import org.apache.lucene.facet.Facets;
import org.apache.lucene.facet.FacetsCollector;
import org.apache.lucene.facet.FacetsConfig;
import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts;
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; /** Shows simple usage of faceted indexing and search. */
public class SimpleFacetsExample48 { private final Directory indexDir = new RAMDirectory();
private final Directory taxoDir = new RAMDirectory();
private final FacetsConfig config = new FacetsConfig(); /** Empty constructor */
public SimpleFacetsExample48() {
config.setHierarchical("Publish Date", true);
} /** Build the example index. */
private void index() throws IOException {
IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(Version.LUCENE_48, new WhitespaceAnalyzer(
Version.LUCENE_48))); // 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<FacetResult>(); // 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(), null /* Filter */, fc); // Retrieve results
List<FacetResult> results = new ArrayList<FacetResult>(); // 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("-----------------------");
SimpleFacetsExample48 example1 = new SimpleFacetsExample48();
List<FacetResult> results1 = example1.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("-----------------------");
SimpleFacetsExample48 example = new SimpleFacetsExample48();
List<FacetResult> results = example.runSearch();
System.out.println("Author: " + results.get(0));
System.out.println("Publish Date: " + results.get(1)); System.out.println("\n");
System.out.println("Facet drill-down example (Publish Date/2010):");
System.out.println("---------------------------------------------");
System.out.println("Author: " + example.runDrillDown()); System.out.println("\n");
System.out.println("Facet drill-sideways example (Publish Date/2010):");
System.out.println("---------------------------------------------");
for (FacetResult result : example.runDrillSideways()) {
System.out.println(result);
}
} }
Result:
Facet counting example:
-----------------------
Author: dim=Author path=[] value=5 childCount=4
Lisa (2)
Bob (1)
Susan (1)
Frank (1) Publish Date: dim=Publish Date path=[] value=5 childCount=3
2010 (2)
2012 (2)
1999 (1) Facet counting example (combined facets and search):
-----------------------
Author: dim=Author path=[] value=5 childCount=4
Lisa (2)
Bob (1)
Susan (1)
Frank (1) Publish Date: dim=Publish Date path=[] value=5 childCount=3
2010 (2)
2012 (2)
1999 (1) Facet drill-down example (Publish Date/2010):
---------------------------------------------
Author: dim=Author path=[] value=4 childCount=2
Bob (2)
Lisa (2) Facet drill-sideways example (Publish Date/2010):
---------------------------------------------
dim=Publish Date path=[] value=15 childCount=3
2010 (6)
2012 (6)
1999 (3) dim=Author path=[] value=6 childCount=2
Bob (3)
Lisa (3)
Lucene 4.8 - Facet Demo的更多相关文章
- Lucene 4.3 - Facet demo
package com.fox.facet; import java.io.IOException; import java.util.ArrayList; import java.util.List ...
- 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
- SSH升级到7.7
#!/bin/bash#删除旧版ssh包 危险操作,不删除也可以安装,建议跳过此操作.#rpm -e `rpm -qa | grep openssh` #安装zlib依赖包wget -c http:/ ...
- [LeetCode&Python] Problem 830. Positions of Large Groups
In a string S of lowercase letters, these letters form consecutive groups of the same character. For ...
- hdoj-1022(栈的模拟)
#include <iostream> #include <cstring> #include <algorithm> #include <stack> ...
- 2018.4.23 git删除已经add的文件
使用 git rm 命令即可,有两种选择, 一种是 git rm --cached "文件路径",不删除物理文件,仅将该文件从缓存中删除: 一种是 git rm --f " ...
- hdu3746 Cyclic Nacklace KMP
CC always becomes very depressed at the end of this month, he has checked his credit card yesterday, ...
- LeetCode - Rectangle Overlap
A rectangle is represented as a list [x1, y1, x2, y2], where (x1, y1) are the coordinates of its bot ...
- 【BZOJ3527】【ZJOI2014】力
"FFT还不是随手写?"我终于能说这样的话了இwஇ 原题: 给出n个数qi,给出Fj的定义如下: 令Ei=Fi/qi,求Ei. FFT嘛,直接推公式 然后就变成俩卷积了,FFT ...
- 【liunx】时间处理函数
一.脚本示例 [mylinuxaccount@linux01 ~]$ date +%Y%m%d 20171224 [mylinuxaccount@linux01 ~]$ date +%F 2017-1 ...
- imrersize函数
imrersize函数: 用法:imresize(图像I,method,倍数) 'nearest'(默认值)最近邻插值'bilinear'双线性插值'bicubic'双三次插值 使用方法: clear ...
- MySQL--字符集参数
================================================== MySQL字符集相关参数 character_set_client: 表示客户端请求数据的字符集 ...