├── LICENSE ├── README.md ├── pom.xml └── src └── main ├── java └── com │ └── lucidworks │ └── solr │ └── query │ └── CategoryExtractionComponent.java └── test └── resources └── inputdata.xml /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # simple-category-extraction-component 2 | Simple Lucene FieldCache based query introspection Solr Search Component - solves the 'red sofa' problem 3 | described in http://lucidworks.com/blog/well-tempered-search-application-fugue/ 4 | 5 | ============================== 6 | Solr Search Component that filters incoming query looking for category terms identified by an index field that we would also use to facet on. Changes the query from q=foo bar to q=bar fq=category:foo if the keyword 'foo' is a field value of 'category'. The implementation uses a way cool suggestion by Erik Hatcher to use the FieldCache field values to determine what are valid values for a field. 7 | 8 | To use this code, you will need to have Solr downloaded and installed. The latest released version is 4.10.3 (Solr 5.0 should be out soon, this code has not been tested with 5.0 yet). 9 | 10 | Compile the code by running Maven (if you don't have this, you will need to download it from Apache) from the directory that you downloaded this plugin code to: 11 | 12 | >mvn package 13 | 14 | This will generate a jar file in the ./target directory called category-extraction-component-1.0-SNAPSHOT.jar 15 | 16 | Copy this to the solr/lib folder in your solr directory (actually <where you downloaded solr>/example/solr/lib. If this 'lib' folder doesn't exist (and it won't for a new install), create it first then copy the jar file into it. 17 | 18 | 19 | ============================= 20 | Configuration: 21 | 22 | For example, to create a category extractor for 'color' this would configure the search component in solrconfig.xml. You will need to modify the solrconfig.xml to do this, open this file in a text editor - or XML editor if you have one. The file is located in <solr install dir>/example/solr/collection1/conf). 23 | 24 | Add these elements: 25 | 26 | 
 27 | <searchComponent name="colorExtractor" class="com.lucidworks.solr.query.CategoryExtractionComponent" >
 28 |       <str name="field">color</str>
 29 |     </searchComponent>
 30 |
31 | 32 | And to create a request handler using this component, insert the component as a 'first-components' so that it executes before the QueryHandler: 33 | 34 | 
 35 |   <requestHandler name="/infer" class="solr.SearchHandler">
 36 |     <lst name="defaults">
 37 |       <str name="echoParams">explicit</str>
 38 |       <int name="rows">10</int>
 39 |       <str name="df">description</str>
 40 |     </lst>
 41 |      
 42 |     <arr name="first-components">
 43 |       <str>colorExtractor</str>
 44 |     </arr>
 45 |   </requestHandler>
 46 |
47 | 48 | restart solr (java -jar start.jar will do fine for this demo) If you don't know how to do this, consult the Solr documentation. 49 | 50 | Loading the test data into a Solr collection: 51 | 52 | 
 53 | <add>
 54 |   <doc>
 55 |     <field name="id">1</field>
 56 |     <field name="color">red</field>
 57 |     <field name="description">This is the red sofa example. Please find with 'red sofa' query.</field>
 58 |   </doc>
 59 |   <doc>
 60 |     <field name="id">2</field>
 61 |     <field name="color">blue</field>
 62 |     <field name="description">This is a blue sofa, it should only hit on sofas that are blue in color.</field>
 63 |   </doc>
 64 |   <doc>
 65 |     <field name="id">3</field>
 66 |     <field name="color">red</field>
 67 |     <field name="description">This is a red beach ball. It is red in color but is not something that you should not sit on because you would tend to roll off.</field>
 68 |   </doc>
 69 | </add>
 70 |
71 | 72 | You can do this using curl (on Linux) If you are on Windows ... 73 | 74 | cd to src/main/test/resources 75 | 76 | curl -X POST -H 'Content-Type: text/xml; charset=utf-8' -d @inputdata.xml http://localhost:8983/solr/collection1/update 77 | 78 | and force a commit using: 79 | 80 | curl http://localhost:8983/solr/collection1/update --data '<commit/>' -H 'Content-type:text/xml; charset=utf-8' 81 | 82 | 83 | Now bring up the Solr Admin at http://localhost:8983/solr to make sure that you have a collection. Select collection1 from the Core Selector Dropdown button. Click on the Query tab and click on the "Execute Query" button. You should see the three documents that you just indexed. 84 | 85 | The color field will now have the values: 'red' and 'blue'. The component now knows what the valid values for 'color' are - the ones that have been indexed into the collection! 86 | 87 | Now searching for 'red sofa' using the /infer handler will only bring back the first record, whereas searching for 'red sofa' with the select handler will bring back all three. (In my solrconfig.xml, I made the df to be 'description' in both the /select and /infer handlers so that we don't have to worry about searching the default 'text' field - OR I could have added a copyField from description to text - OR I could have used 'text' for the 'description' field in the input SolrXML file - always more than way to do cat skinnin'). Note that searching for 'green sofa' in either handler would bring back two records (the ones with sofa) because the index doesn't recognize 'green' as a sofa color because we haven't given it one to index yet. This means that all colors that are associated with a record by having a color facet value will work, no other colors will. And we can do this with ANY field that we can facet on! 88 | 89 | Out-Of-The-Box Solr /request handler 90 | 91 | http://localhost:8983/solr/collection1/select?q=red+sofa&wt=json&indent=true 92 | 93 | 
 94 | {
 95 |   "responseHeader":{
 96 |     "status":0,
 97 |     "QTime":1,
 98 |     "params":{
 99 |       "indent":"true",
100 |       "q":"red sofa",
101 |       "wt":"json"}},
102 |   "response":{"numFound":3,"start":0,"docs":[
103 |       {
104 |         "id":"1",
105 |         "color":"red",
106 |         "description":"This is the red sofa example. Please find with 'red sofa' query.",
107 |         "_version_":1492376486934478848},
108 |       {
109 |         "id":"3",
110 |         "color":"red",
111 |         "description":"This is a red beach ball. It is red in color but is not something that you should not sit on because you would tend to roll off.",
112 |         "_version_":1492376486956498944},
113 |       {
114 |         "id":"2",
115 |         "color":"blue",
116 |         "description":"This is a blue sofa, it should only hit on sofas that are blue in color.",
117 |         "_version_":1492376486955450368}]
118 |   }}
119 |
120 | 121 | And with our handy-dandy new /infer request handler: 122 | 123 | http://localhost:8983/solr/collection1/infer?q=red+sofa&wt=json&indent=true 124 | 125 | 
126 | 
127 | {
128 |   "responseHeader":{
129 |     "status":0,
130 |     "QTime":7,
131 |     "params":{
132 |       "indent":"true",
133 |       "q":"red sofa",
134 |       "wt":"json"}},
135 |   "response":{"numFound":1,"start":0,"docs":[
136 |       {
137 |         "id":"1",
138 |         "color":"red",
139 |         "description":"This is the red sofa example. Please find with 'red sofa' query.",
140 |         "_version_":1492376486934478848}]
141 |   }}
142 |
143 | 144 | And now for my next magic trick ... 145 | 146 | (I call this technique 'autofaceting' - very powerful way to surface the intelligence that we built into our Lucene search index at index time.) 147 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 3 | 4.0.0 4 | com.lucidworks 5 | category-extraction-component 6 | jar 7 | 1.0-SNAPSHOT 8 | category-extraction-component 9 | http://maven.apache.org 10 | 11 | Solr Search Component for query introspection of category white lists 12 | 13 | 14 | 4.10.2 15 | 4.10.2 16 | 1.7.5 17 | 18 | 19 | 20 | 21 | org.slf4j 22 | slf4j-api 23 | ${slf4j.version} 24 | 25 | 26 | org.apache.solr 27 | solr-core 28 | ${solr.version} 29 | 30 | 31 | org.apache.lucene 32 | lucene-core 33 | ${lucene.version} 34 | 35 | 36 | 37 | -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/solr/query/CategoryExtractionComponent.java: -------------------------------------------------------------------------------- 1 | package com.lucidworks.solr.query; 2 | 3 | import org.apache.solr.common.params.SolrParams; 4 | import org.apache.solr.common.params.ModifiableSolrParams; 5 | import org.apache.solr.common.params.CommonParams; 6 | import org.apache.solr.common.util.NamedList; 7 | import org.apache.solr.request.SolrQueryRequest; 8 | import org.apache.solr.handler.component.QueryComponent; 9 | import org.apache.solr.handler.component.ResponseBuilder; 10 | 11 | import org.apache.lucene.util.BytesRef; 12 | import org.apache.lucene.index.AtomicReader; 13 | import org.apache.lucene.index.SortedDocValues; 14 | import org.apache.lucene.search.FieldCache; 15 | import org.apache.solr.search.SolrIndexSearcher; 16 | 17 | import java.util.HashSet; 18 | import java.util.List; 19 | import java.util.StringTokenizer; 20 | 21 | import org.slf4j.Logger; 22 | import org.slf4j.LoggerFactory; 23 | 24 | import java.io.IOException; 25 | 26 | 27 | public class CategoryExtractionComponent extends QueryComponent { 28 | 29 | private static final Logger Log = LoggerFactory.getLogger( CategoryExtractionComponent.class ); 30 | 31 | private String categoryField; 32 | 33 | @Override 34 | public void init( NamedList initArgs ) { 35 | Log.info( "init ..." ); 36 | 37 | // the Solr-Lucene field that will be used to create the filter query 38 | String catField = (String)initArgs.get( "field" ); 39 | if ( catField != null ) { 40 | Log.info( "setting category field: " + catField ); 41 | this.categoryField = catField; 42 | } 43 | } 44 | 45 | @Override 46 | public void prepare( ResponseBuilder rb ) throws IOException 47 | { 48 | SolrQueryRequest req = rb.req; 49 | 50 | SolrIndexSearcher searcher = req.getSearcher(); 51 | SortedDocValues fieldValues = FieldCache.DEFAULT.getTermsIndex( searcher.getAtomicReader( ), categoryField ); 52 | 53 | SolrParams params = req.getParams( ); 54 | 55 | ModifiableSolrParams modParams = new ModifiableSolrParams( params ); 56 | 57 | String qStr = params.get( CommonParams.Q ); 58 | // tokenize the query string, if any part of it matches, remove the token from the list and 59 | // add a filter query with :value 60 | StringTokenizer strtok = new StringTokenizer(qStr, " .,:;\"'" ); 61 | StringBuilder strbldr= new StringBuilder( ); 62 | 63 | while (strtok.hasMoreTokens( ) ) { 64 | String tok = strtok.nextToken( ).toLowerCase( ); 65 | Log.info( "got token: " + tok ); 66 | BytesRef key = new BytesRef( tok.getBytes() ); 67 | if (fieldValues.lookupTerm( key ) >= 0) { 68 | String fq = new String( categoryField + ":" + tok ); 69 | Log.info( "adding fq " + fq ); 70 | modParams.add( "fq", fq ); 71 | } 72 | else 73 | { 74 | strbldr.append( tok ); 75 | if (strbldr.length() > 0) { 76 | strbldr.append( " " ); 77 | } 78 | } 79 | } 80 | 81 | String modQ = strbldr.toString( ); 82 | // should we add the category fields here: need to test this first... 83 | 84 | // if the query is now empty, make sure it hits on everything 85 | if (modQ.trim().length() == 0) { 86 | modQ = "*:*"; 87 | } 88 | 89 | Log.info( "final q string is: '" + modQ + "'" ); 90 | modParams.set( "q", modQ ); 91 | 92 | req.setParams( modParams ); 93 | } 94 | 95 | @Override 96 | public void process(ResponseBuilder rb) throws IOException 97 | { 98 | // do nothing - needed so we don't execute the query here. 99 | } 100 | 101 | } 102 | -------------------------------------------------------------------------------- /src/main/test/resources/inputdata.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 1 4 | red 5 | This is the red sofa example. Please find with 'red sofa' query. 6 | 7 | 8 | 2 9 | blue 10 | This is a blue sofa, it should only hit on sofas that are blue in color. 11 | 12 | 13 | 3 14 | red 15 | This is a red beach ball. It is red in color but is not something that you should not sit on because you would tend to roll off. 16 | 17 | --------------------------------------------------------------------------------