├── .gitignore ├── LICENSE.txt ├── NOTICE.txt ├── README.textile ├── build.gradle ├── demo.sh ├── gradle └── wrapper │ ├── gradle-wrapper.jar │ └── gradle-wrapper.properties ├── gradlew ├── gradlew.bat ├── licenses ├── english-1.4-SNAPSHOT.jar.sha1 ├── english-LICENSE ├── english-NOTICE ├── morph-1.4-SNAPSHOT.jar.sha1 ├── morph-LICENSE ├── morph-NOTICE ├── russian-1.4-SNAPSHOT.jar.sha1 ├── russian-LICENSE └── russian-NOTICE └── src ├── main └── java │ └── org │ └── elasticsearch │ └── plugin │ └── analysis │ └── morphology │ ├── AnalysisMorphologyPlugin.java │ ├── MorphologyAnalyzerProvider.java │ └── MorphologyTokenFilterFactory.java └── test ├── java └── org │ └── elasticsearch │ ├── index │ └── analysis │ │ └── morphology │ │ └── SimpleMorphologyAnalysisTests.java │ └── plugin │ └── analysis │ └── morphology │ └── AnalysisMorphologyRestIT.java └── resources └── rest-api-spec └── test └── analysis-morphology ├── 10_analyze.yml └── 5_plugin_version.yml /.gitignore: -------------------------------------------------------------------------------- 1 | 2 | # intellij files 3 | .idea/ 4 | *.iml 5 | *.ipr 6 | *.iws 7 | build-idea/ 8 | 9 | # eclipse files 10 | .project 11 | .classpath 12 | .settings 13 | build-eclipse/ 14 | 15 | # netbeans files 16 | nb-configuration.xml 17 | nbactions.xml 18 | 19 | # gradle stuff 20 | .gradle/ 21 | build/ 22 | target/ 23 | 24 | # testing stuff 25 | **/.local* 26 | .vagrant/ 27 | 28 | # osx stuff 29 | .DS_Store 30 | 31 | # needed in case docs build is run...maybe we can configure doc build to generate files under build? 32 | html_docs 33 | 34 | # random old stuff that we should look at the necessity of... 35 | /tmp/ 36 | backwards/ 37 | eclipse-build 38 | 39 | 40 | *~ 41 | -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /NOTICE.txt: -------------------------------------------------------------------------------- 1 | This product includes software developed by The Apache Software 2 | Foundation (http://www.apache.org/). 3 | 4 | morph-*.jar, russian-*.jar, and english-*.jar are under the ASL license, the 5 | original source code for these can be found at 6 | https://github.com/AKuznetsov/russianmorphology. The dictionaries in these 7 | libaries are based on open source dictionary developed by working group Aot.ru 8 | and licensed under LGPL license. The original source code for these 9 | dictionaries can be found at http://aot.ru/. 10 | 11 | The LICENSE and NOTICE files for all dependencies may be found in the licenses/ 12 | directory. -------------------------------------------------------------------------------- /README.textile: -------------------------------------------------------------------------------- 1 | h1. This project is no longer supported 2 | 3 | Elasticsearch 5.6.x is not maintained since March of 2019. This project is no longer supported and due to sunsetting of Bintray the binary builds are no longer available. The best strategy at this point would be to migrate to a supported version of Elasticsearch and another plugin such as Hunspell. 4 | 5 | h1. Morphological Analysis Plugin for Elasticsearch 6 | 7 | The Morphological Analysis plugin integrates Russian and English morphology for java and lucene framework into elasticsearch. This plugin adds two new analyzers: "russian_morphology" and "english_morphology" and two token filters with the same names. 8 | 9 | The demo.sh file shows a few examples of the analyzers behavior. 10 | 11 | h2. Switching to Hunspell 12 | 13 | *NOTE:* Please note that this plugin is available only for Elasticsearch v5.6.x and below. For Elasticsearch version 6.0 and above consider switching to the officially supported hunspell token filter with russian dictionaries. 14 | 15 | h2. Building from the source 16 | 17 | In order to build the project from the source, you need *git*, *maven* and *java JDK* 8 and follow a few simple steps: 18 | 19 | First you need to build the last commit of russianmorphology that supported Lucene 6.x: 20 | 21 | bc. $ git clone https://github.com/AKuznetsov/russianmorphology.git 22 | $ cd russianmorphology 23 | $ git checkout 6fc7e109cb23c88cfb44313275df44117b8b97f7 24 | $ mvn install 25 | 26 | If it resulted in the following output, we can move on. 27 | 28 | bc. [INFO] ------------------------------------------------------------------------ 29 | [INFO] BUILD SUCCESS 30 | [INFO] ------------------------------------------------------------------------ 31 | 32 | 33 | Now we can check out *5.6* branch of this project and build it using the russianmorphology library that we built in previous step. 34 | 35 | bc. $ cd .. 36 | $ git clone https://github.com/imotov/elasticsearch-analysis-morphology.git 37 | $ cd elasticsearch-analysis-morphology 38 | $ git checkout 5.6 39 | $ ./gradlew assemble -Drepos.mavenlocal=true 40 | 41 | If you see the following message, the build was successful: 42 | 43 | bc. BUILD SUCCESSFUL in 26s 44 | 11 actionable tasks: 11 executed 45 | 46 | The plugin can be found file is @build/distributions/analysis-morphology-5.6.16.zip@ 47 | 48 | 49 | 50 | 51 | -------------------------------------------------------------------------------- /build.gradle: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | 16 | buildscript { 17 | repositories { 18 | mavenCentral() 19 | maven { 20 | name 'sonatype-snapshots' 21 | url "https://oss.sonatype.org/content/repositories/snapshots/" 22 | } 23 | jcenter() 24 | } 25 | dependencies { 26 | classpath "org.elasticsearch.gradle:build-tools:6.0.0" 27 | classpath "com.jfrog.bintray.gradle:gradle-bintray-plugin:1.7" 28 | } 29 | } 30 | 31 | apply plugin: 'idea' 32 | apply plugin: 'eclipse' 33 | apply plugin: 'elasticsearch.esplugin' 34 | apply plugin: 'com.jfrog.bintray' 35 | apply plugin: 'maven-publish' 36 | 37 | //repositories { 38 | // maven { 39 | // name 'bintray-akuznetsov-russianmorphology' 40 | // url "http://dl.bintray.com/akuznetsov/russianmorphology" 41 | // } 42 | //} 43 | 44 | version = '6.0.0-SNAPSHOT' 45 | 46 | esplugin { 47 | description 'English and Russian Morphology for ElasticSearch.' 48 | classname 'org.elasticsearch.plugin.analysis.morphology.AnalysisMorphologyPlugin' 49 | name 'analysis-morphology' 50 | } 51 | esplugin.version = version 52 | 53 | dependencies { 54 | compile "org.apache.lucene.morphology:russian:1.4-SNAPSHOT" 55 | compile "org.apache.lucene.morphology:english:1.4-SNAPSHOT" 56 | compile "org.apache.lucene.morphology:morph:1.4-SNAPSHOT" 57 | } 58 | 59 | publishing { 60 | publications { 61 | DefaultPublication(MavenPublication) { 62 | groupId 'org.elasticsearch' 63 | artifactId 'elasticsearch-analysis-morphology' 64 | from components.java 65 | artifact javadocJar 66 | artifact sourcesJar 67 | artifact bundlePlugin 68 | } 69 | } 70 | } 71 | 72 | 73 | // Only needed if we publish to bintray 74 | if (project.hasProperty('bintrayUser')) { 75 | 76 | bintray { 77 | user = project.property('bintrayUser') 78 | key = project.property('bintrayApiKey') 79 | pkg { 80 | repo = 'elasticsearch-plugins' 81 | name = 'elasticsearch-analysis-morphology' 82 | } 83 | publications = ['DefaultPublication'] 84 | } 85 | } 86 | 87 | // TODO: temporary workaround until it's fixed in elasticsearch 88 | thirdPartyAudit.enabled = false 89 | dependencyLicenses.enabled = false 90 | 91 | project.licenseFile = project.rootProject.file('LICENSE.txt') 92 | project.noticeFile = project.rootProject.file('NOTICE.txt') 93 | 94 | -------------------------------------------------------------------------------- /demo.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | curl --header "Content-Type:application/json" -XDELETE 'http://localhost:9200/rustest' && echo 3 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest' -d '{ 4 | "settings": { 5 | "analysis": { 6 | "analyzer": { 7 | "my_analyzer": { 8 | "type": "custom", 9 | "tokenizer": "standard", 10 | "filter": ["lowercase", "russian_morphology", "english_morphology", "my_stopwords"] 11 | } 12 | }, 13 | "filter": { 14 | "my_stopwords": { 15 | "type": "stop", 16 | "stopwords": "а,без,более,бы,был,была,были,было,быть,в,вам,вас,весь,во,вот,все,всего,всех,вы,где,да,даже,для,до,его,ее,если,есть,еще,же,за,здесь,и,из,или,им,их,к,как,ко,когда,кто,ли,либо,мне,может,мы,на,надо,наш,не,него,нее,нет,ни,них,но,ну,о,об,однако,он,она,они,оно,от,очень,по,под,при,с,со,так,также,такой,там,те,тем,то,того,тоже,той,только,том,ты,у,уже,хотя,чего,чей,чем,что,чтобы,чье,чья,эта,эти,это,я,a,an,and,are,as,at,be,but,by,for,if,in,into,is,it,no,not,of,on,or,such,that,the,their,then,there,these,they,this,to,was,will,with" 17 | } 18 | } 19 | } 20 | } 21 | }' && echo 22 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/_mapping' -d '{ 23 | "doc": { 24 | "properties" : { 25 | "body" : { "type" : "text", "analyzer" : "russian_morphology" }, 26 | "text" : { "type" : "text", "analyzer" : "my_analyzer" } 27 | } 28 | } 29 | }' && echo 30 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/1' -d '{"body": "У московского бизнесмена из автомобиля украли шесть миллионов рублей "}' && echo 31 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/1' -d '{"body": "У московского бизнесмена из автомобиля украли шесть миллионов рублей "}' && echo 32 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/2' -d '{"body": "Креативное агентство Jvision, запустило сервис, способствующий развитию автомобильного туризма в России."}' && echo 33 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/3' -d '{"body": "Просто авто"}' && echo 34 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/4' -d '{"body": "Японские автомобили вновь заняли в США первые места в рейтингах"}' && echo 35 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/5' -d '{"body": "Январский дефицит платежного баланса Японии превысил $5 млрд"}' && echo 36 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/6' -d '{"body": "Японская корпорация Sony представила новый смартфон под названием Xperia Sola."}' && echo 37 | curl --header "Content-Type:application/json" -XPOST 'http://localhost:9200/rustest/_refresh' && echo 38 | echo "Should return 5" 39 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:Япония"}}}' | grep "_id" 40 | echo "Should return 4, 6" 41 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:Японский"}}}' | grep "_id" 42 | echo "Should return 4" 43 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:первый"}}}' | grep "_id" 44 | echo "Should return 1, 4" 45 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:автомобиль"}}}' | grep "_id" 46 | echo "Should return 2" 47 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:автомобильный"}}}' | grep "_id" 48 | echo "Should return 3" 49 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:авто"}}}' | grep "_id" 50 | echo "Should return 1,2,3,4" 51 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "body:авто*", "analyze_wildcard": true}}}' | grep "_id" 52 | 53 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/1' -d '{"text": "Curiously enough, the only thing that went through the mind of the bowl of petunias as it fell was Oh no, not again."}' && echo 54 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/2' -d '{"text": "Many people have speculated that if we knew exactly why the bowl of petunias had thought that we would know a lot more about the nature of the Universe than we do now."}' && echo 55 | curl --header "Content-Type:application/json" -XPUT 'http://localhost:9200/rustest/doc/3' -d '{"text": "Не повезло только кашалоту, который внезапно возник из небытия в нескольких милях над поверхностью планеты."}' && echo 56 | curl --header "Content-Type:application/json" -XPOST 'http://localhost:9200/rustest/_refresh' && echo 57 | echo "Should return 3" 58 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "text:\"миль по поверхности\"", "analyze_wildcard": true}}}' | grep "_id" 59 | echo "Should return 1" 60 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "text:go", "analyze_wildcard": true}}}' | grep "_id" 61 | echo "Should return 2" 62 | curl --header "Content-Type:application/json" -s 'http://localhost:9200/rustest/doc/_search?pretty=true' -d '{"query": {"query_string": {"query": "text:thinking", "analyze_wildcard": true}}}' | grep "_id" 63 | echo "Searching _all field" 64 | curl --header "Content-Type:application/json" -XPOST 'localhost:9200/rustest/_search?pretty' -d '{ 65 | "query": { 66 | "query_string": { 67 | "query": "Япония", 68 | "analyze_wildcard": true 69 | } 70 | } 71 | }' -------------------------------------------------------------------------------- /gradle/wrapper/gradle-wrapper.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/imotov/elasticsearch-analysis-morphology/7dd6af9bfe0775ebc92513a95e0bfe8921406c3e/gradle/wrapper/gradle-wrapper.jar -------------------------------------------------------------------------------- /gradle/wrapper/gradle-wrapper.properties: -------------------------------------------------------------------------------- 1 | #Thu May 04 14:24:29 EDT 2017 2 | distributionBase=GRADLE_USER_HOME 3 | distributionPath=wrapper/dists 4 | zipStoreBase=GRADLE_USER_HOME 5 | zipStorePath=wrapper/dists 6 | distributionUrl=https\://services.gradle.org/distributions/gradle-3.3-bin.zip 7 | -------------------------------------------------------------------------------- /gradlew: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | ############################################################################## 4 | ## 5 | ## Gradle start up script for UN*X 6 | ## 7 | ############################################################################## 8 | 9 | # Attempt to set APP_HOME 10 | # Resolve links: $0 may be a link 11 | PRG="$0" 12 | # Need this for relative symlinks. 13 | while [ -h "$PRG" ] ; do 14 | ls=`ls -ld "$PRG"` 15 | link=`expr "$ls" : '.*-> \(.*\)$'` 16 | if expr "$link" : '/.*' > /dev/null; then 17 | PRG="$link" 18 | else 19 | PRG=`dirname "$PRG"`"/$link" 20 | fi 21 | done 22 | SAVED="`pwd`" 23 | cd "`dirname \"$PRG\"`/" >/dev/null 24 | APP_HOME="`pwd -P`" 25 | cd "$SAVED" >/dev/null 26 | 27 | APP_NAME="Gradle" 28 | APP_BASE_NAME=`basename "$0"` 29 | 30 | # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. 31 | DEFAULT_JVM_OPTS="" 32 | 33 | # Use the maximum available, or set MAX_FD != -1 to use that value. 34 | MAX_FD="maximum" 35 | 36 | warn ( ) { 37 | echo "$*" 38 | } 39 | 40 | die ( ) { 41 | echo 42 | echo "$*" 43 | echo 44 | exit 1 45 | } 46 | 47 | # OS specific support (must be 'true' or 'false'). 48 | cygwin=false 49 | msys=false 50 | darwin=false 51 | nonstop=false 52 | case "`uname`" in 53 | CYGWIN* ) 54 | cygwin=true 55 | ;; 56 | Darwin* ) 57 | darwin=true 58 | ;; 59 | MINGW* ) 60 | msys=true 61 | ;; 62 | NONSTOP* ) 63 | nonstop=true 64 | ;; 65 | esac 66 | 67 | CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar 68 | 69 | # Determine the Java command to use to start the JVM. 70 | if [ -n "$JAVA_HOME" ] ; then 71 | if [ -x "$JAVA_HOME/jre/sh/java" ] ; then 72 | # IBM's JDK on AIX uses strange locations for the executables 73 | JAVACMD="$JAVA_HOME/jre/sh/java" 74 | else 75 | JAVACMD="$JAVA_HOME/bin/java" 76 | fi 77 | if [ ! -x "$JAVACMD" ] ; then 78 | die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME 79 | 80 | Please set the JAVA_HOME variable in your environment to match the 81 | location of your Java installation." 82 | fi 83 | else 84 | JAVACMD="java" 85 | which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. 86 | 87 | Please set the JAVA_HOME variable in your environment to match the 88 | location of your Java installation." 89 | fi 90 | 91 | # Increase the maximum file descriptors if we can. 92 | if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then 93 | MAX_FD_LIMIT=`ulimit -H -n` 94 | if [ $? -eq 0 ] ; then 95 | if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then 96 | MAX_FD="$MAX_FD_LIMIT" 97 | fi 98 | ulimit -n $MAX_FD 99 | if [ $? -ne 0 ] ; then 100 | warn "Could not set maximum file descriptor limit: $MAX_FD" 101 | fi 102 | else 103 | warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT" 104 | fi 105 | fi 106 | 107 | # For Darwin, add options to specify how the application appears in the dock 108 | if $darwin; then 109 | GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\"" 110 | fi 111 | 112 | # For Cygwin, switch paths to Windows format before running java 113 | if $cygwin ; then 114 | APP_HOME=`cygpath --path --mixed "$APP_HOME"` 115 | CLASSPATH=`cygpath --path --mixed "$CLASSPATH"` 116 | JAVACMD=`cygpath --unix "$JAVACMD"` 117 | 118 | # We build the pattern for arguments to be converted via cygpath 119 | ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null` 120 | SEP="" 121 | for dir in $ROOTDIRSRAW ; do 122 | ROOTDIRS="$ROOTDIRS$SEP$dir" 123 | SEP="|" 124 | done 125 | OURCYGPATTERN="(^($ROOTDIRS))" 126 | # Add a user-defined pattern to the cygpath arguments 127 | if [ "$GRADLE_CYGPATTERN" != "" ] ; then 128 | OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)" 129 | fi 130 | # Now convert the arguments - kludge to limit ourselves to /bin/sh 131 | i=0 132 | for arg in "$@" ; do 133 | CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -` 134 | CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option 135 | 136 | if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition 137 | eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"` 138 | else 139 | eval `echo args$i`="\"$arg\"" 140 | fi 141 | i=$((i+1)) 142 | done 143 | case $i in 144 | (0) set -- ;; 145 | (1) set -- "$args0" ;; 146 | (2) set -- "$args0" "$args1" ;; 147 | (3) set -- "$args0" "$args1" "$args2" ;; 148 | (4) set -- "$args0" "$args1" "$args2" "$args3" ;; 149 | (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;; 150 | (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;; 151 | (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;; 152 | (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;; 153 | (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;; 154 | esac 155 | fi 156 | 157 | # Escape application args 158 | save ( ) { 159 | for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done 160 | echo " " 161 | } 162 | APP_ARGS=$(save "$@") 163 | 164 | # Collect all arguments for the java command, following the shell quoting and substitution rules 165 | eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS" 166 | 167 | # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong 168 | if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then 169 | cd "$(dirname "$0")" 170 | fi 171 | 172 | exec "$JAVACMD" "$@" 173 | -------------------------------------------------------------------------------- /gradlew.bat: -------------------------------------------------------------------------------- 1 | @if "%DEBUG%" == "" @echo off 2 | @rem ########################################################################## 3 | @rem 4 | @rem Gradle startup script for Windows 5 | @rem 6 | @rem ########################################################################## 7 | 8 | @rem Set local scope for the variables with windows NT shell 9 | if "%OS%"=="Windows_NT" setlocal 10 | 11 | set DIRNAME=%~dp0 12 | if "%DIRNAME%" == "" set DIRNAME=. 13 | set APP_BASE_NAME=%~n0 14 | set APP_HOME=%DIRNAME% 15 | 16 | @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. 17 | set DEFAULT_JVM_OPTS= 18 | 19 | @rem Find java.exe 20 | if defined JAVA_HOME goto findJavaFromJavaHome 21 | 22 | set JAVA_EXE=java.exe 23 | %JAVA_EXE% -version >NUL 2>&1 24 | if "%ERRORLEVEL%" == "0" goto init 25 | 26 | echo. 27 | echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. 28 | echo. 29 | echo Please set the JAVA_HOME variable in your environment to match the 30 | echo location of your Java installation. 31 | 32 | goto fail 33 | 34 | :findJavaFromJavaHome 35 | set JAVA_HOME=%JAVA_HOME:"=% 36 | set JAVA_EXE=%JAVA_HOME%/bin/java.exe 37 | 38 | if exist "%JAVA_EXE%" goto init 39 | 40 | echo. 41 | echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME% 42 | echo. 43 | echo Please set the JAVA_HOME variable in your environment to match the 44 | echo location of your Java installation. 45 | 46 | goto fail 47 | 48 | :init 49 | @rem Get command-line arguments, handling Windows variants 50 | 51 | if not "%OS%" == "Windows_NT" goto win9xME_args 52 | 53 | :win9xME_args 54 | @rem Slurp the command line arguments. 55 | set CMD_LINE_ARGS= 56 | set _SKIP=2 57 | 58 | :win9xME_args_slurp 59 | if "x%~1" == "x" goto execute 60 | 61 | set CMD_LINE_ARGS=%* 62 | 63 | :execute 64 | @rem Setup the command line 65 | 66 | set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar 67 | 68 | @rem Execute Gradle 69 | "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS% 70 | 71 | :end 72 | @rem End local scope for the variables with windows NT shell 73 | if "%ERRORLEVEL%"=="0" goto mainEnd 74 | 75 | :fail 76 | rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of 77 | rem the _cmd.exe /c_ return code! 78 | if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1 79 | exit /b 1 80 | 81 | :mainEnd 82 | if "%OS%"=="Windows_NT" endlocal 83 | 84 | :omega 85 | -------------------------------------------------------------------------------- /licenses/english-1.4-SNAPSHOT.jar.sha1: -------------------------------------------------------------------------------- 1 | 3253659ade1c48e6d254ab1b6a1c0a22c0d9cdcb -------------------------------------------------------------------------------- /licenses/english-LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /licenses/english-NOTICE: -------------------------------------------------------------------------------- 1 | Copyright 2009 Alexander Kuznetsov 2 | 3 | Licensed under the Apache License, Version 2.0 (the "License"); 4 | you may not use this file except in compliance with the License. 5 | You may obtain a copy of the License at 6 | 7 | http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | Unless required by applicable law or agreed to in writing, software 10 | distributed under the License is distributed on an "AS IS" BASIS, 11 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | See the License for the specific language governing permissions and 13 | limitations under the License. -------------------------------------------------------------------------------- /licenses/morph-1.4-SNAPSHOT.jar.sha1: -------------------------------------------------------------------------------- 1 | 33f83204e8365173cd324c5251689cab9937b986 -------------------------------------------------------------------------------- /licenses/morph-LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /licenses/morph-NOTICE: -------------------------------------------------------------------------------- 1 | Copyright 2009 Alexander Kuznetsov 2 | 3 | Licensed under the Apache License, Version 2.0 (the "License"); 4 | you may not use this file except in compliance with the License. 5 | You may obtain a copy of the License at 6 | 7 | http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | Unless required by applicable law or agreed to in writing, software 10 | distributed under the License is distributed on an "AS IS" BASIS, 11 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | See the License for the specific language governing permissions and 13 | limitations under the License. -------------------------------------------------------------------------------- /licenses/russian-1.4-SNAPSHOT.jar.sha1: -------------------------------------------------------------------------------- 1 | 9f6c6c96b19bcb982c178f84ffb6f25d05e138d6 -------------------------------------------------------------------------------- /licenses/russian-LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /licenses/russian-NOTICE: -------------------------------------------------------------------------------- 1 | Copyright 2009 Alexander Kuznetsov 2 | 3 | Licensed under the Apache License, Version 2.0 (the "License"); 4 | you may not use this file except in compliance with the License. 5 | You may obtain a copy of the License at 6 | 7 | http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | Unless required by applicable law or agreed to in writing, software 10 | distributed under the License is distributed on an "AS IS" BASIS, 11 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | See the License for the specific language governing permissions and 13 | limitations under the License. -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/plugin/analysis/morphology/AnalysisMorphologyPlugin.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2012 Igor Motov 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package org.elasticsearch.plugin.analysis.morphology; 18 | 19 | import org.apache.lucene.analysis.Analyzer; 20 | import org.apache.lucene.morphology.english.EnglishLuceneMorphology; 21 | import org.apache.lucene.morphology.russian.RussianLuceneMorphology; 22 | import org.elasticsearch.index.analysis.AnalyzerProvider; 23 | import org.elasticsearch.index.analysis.TokenFilterFactory; 24 | import org.elasticsearch.indices.analysis.AnalysisModule; 25 | import org.elasticsearch.plugins.AnalysisPlugin; 26 | import org.elasticsearch.plugins.Plugin; 27 | 28 | import java.io.IOException; 29 | import java.util.HashMap; 30 | import java.util.Map; 31 | 32 | /** 33 | * Plugin for russian/english morphology analyzer 34 | */ 35 | public class AnalysisMorphologyPlugin extends Plugin implements AnalysisPlugin { 36 | 37 | private final RussianLuceneMorphology russianLuceneMorphology; 38 | private final EnglishLuceneMorphology englishLuceneMorphology; 39 | 40 | public AnalysisMorphologyPlugin() { 41 | super(); 42 | try { 43 | russianLuceneMorphology = new RussianLuceneMorphology(); 44 | } catch (IOException ex) { 45 | throw new IllegalStateException("unable to load russian morphology info", ex); 46 | } 47 | try { 48 | englishLuceneMorphology = new EnglishLuceneMorphology(); 49 | } catch (IOException ex) { 50 | throw new IllegalStateException("unable to load english morphology info", ex); 51 | } 52 | } 53 | 54 | @Override 55 | public Map> getTokenFilters() { 56 | Map> extra = new HashMap<>(); 57 | extra.put("russian_morphology", (indexSettings, environment, name, settings) -> 58 | new MorphologyTokenFilterFactory(indexSettings, environment, name, settings, russianLuceneMorphology)); 59 | extra.put("english_morphology", (indexSettings, environment, name, settings) -> 60 | new MorphologyTokenFilterFactory(indexSettings, environment, name, settings, englishLuceneMorphology)); 61 | return extra; 62 | } 63 | 64 | @Override 65 | public Map>> getAnalyzers() { 66 | Map>> extra = new HashMap<>(); 67 | extra.put("russian_morphology", (indexSettings, environment, name, settings) -> 68 | new MorphologyAnalyzerProvider(indexSettings, environment, name, settings, russianLuceneMorphology)); 69 | extra.put("english_morphology", (indexSettings, environment, name, settings) -> 70 | new MorphologyAnalyzerProvider(indexSettings, environment, name, settings, englishLuceneMorphology)); 71 | return extra; 72 | } 73 | 74 | } 75 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/plugin/analysis/morphology/MorphologyAnalyzerProvider.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2012 Igor Motov 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package org.elasticsearch.plugin.analysis.morphology; 18 | 19 | import org.apache.lucene.morphology.LuceneMorphology; 20 | import org.apache.lucene.morphology.analyzer.MorphologyAnalyzer; 21 | import org.elasticsearch.common.settings.Settings; 22 | import org.elasticsearch.env.Environment; 23 | import org.elasticsearch.index.IndexSettings; 24 | import org.elasticsearch.index.analysis.AbstractIndexAnalyzerProvider; 25 | 26 | /** 27 | * Provider for russian/english morphology analyzer 28 | */ 29 | public class MorphologyAnalyzerProvider extends AbstractIndexAnalyzerProvider { 30 | 31 | private final MorphologyAnalyzer analyzer; 32 | 33 | public MorphologyAnalyzerProvider(IndexSettings indexSettings, Environment environment, String name, 34 | Settings settings, LuceneMorphology luceneMorphology) { 35 | super(indexSettings, name, settings); 36 | analyzer = new MorphologyAnalyzer(luceneMorphology); 37 | } 38 | 39 | @Override 40 | public MorphologyAnalyzer get() { 41 | return this.analyzer; 42 | } 43 | } 44 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/plugin/analysis/morphology/MorphologyTokenFilterFactory.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2012 Igor Motov 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package org.elasticsearch.plugin.analysis.morphology; 18 | 19 | import org.apache.lucene.analysis.TokenStream; 20 | import org.apache.lucene.morphology.LuceneMorphology; 21 | import org.apache.lucene.morphology.analyzer.MorphologyFilter; 22 | import org.apache.lucene.morphology.english.EnglishLuceneMorphology; 23 | import org.elasticsearch.common.settings.Settings; 24 | import org.elasticsearch.env.Environment; 25 | import org.elasticsearch.index.IndexSettings; 26 | import org.elasticsearch.index.analysis.AbstractTokenFilterFactory; 27 | 28 | import java.io.IOException; 29 | 30 | /** 31 | * Russian/english morphology token filter factory 32 | */ 33 | public class MorphologyTokenFilterFactory extends AbstractTokenFilterFactory { 34 | 35 | private final LuceneMorphology luceneMorph; 36 | 37 | public MorphologyTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, 38 | Settings settings, LuceneMorphology englishLuceneMorphology) { 39 | super(indexSettings, name, settings); 40 | luceneMorph = englishLuceneMorphology; 41 | } 42 | 43 | @Override 44 | public TokenStream create(TokenStream tokenStream) { 45 | return new MorphologyFilter(tokenStream, luceneMorph); 46 | } 47 | } 48 | -------------------------------------------------------------------------------- /src/test/java/org/elasticsearch/index/analysis/morphology/SimpleMorphologyAnalysisTests.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2012 Igor Motov 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package org.elasticsearch.index.analysis.morphology; 18 | 19 | import org.apache.lucene.analysis.TokenStream; 20 | import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; 21 | import org.apache.lucene.morphology.LuceneMorphology; 22 | import org.apache.lucene.morphology.analyzer.MorphologyAnalyzer; 23 | import org.apache.lucene.morphology.analyzer.MorphologyFilter; 24 | import org.apache.lucene.morphology.english.EnglishLuceneMorphology; 25 | import org.apache.lucene.morphology.russian.RussianLuceneMorphology; 26 | import org.elasticsearch.common.io.FastStringReader; 27 | import org.elasticsearch.common.settings.Settings; 28 | import org.elasticsearch.index.Index; 29 | import org.elasticsearch.index.analysis.NamedAnalyzer; 30 | import org.elasticsearch.plugin.analysis.morphology.AnalysisMorphologyPlugin; 31 | import org.elasticsearch.test.ESTestCase; 32 | 33 | import java.io.IOException; 34 | import java.io.StringReader; 35 | 36 | import static org.hamcrest.Matchers.instanceOf; 37 | 38 | public class SimpleMorphologyAnalysisTests extends ESTestCase { 39 | 40 | private TestAnalysis getAnalysisService() throws IOException { 41 | Settings indexSettings = Settings.builder() 42 | .put("index.analysis.analyzer.test.type", "custom") 43 | .put("index.analysis.analyzer.test.tokenizer", "standard") 44 | .putArray("index.analysis.analyzer.test.filter", "lowercase", "russian_morphology") 45 | .build(); 46 | 47 | return createTestAnalysis(new Index("test", "_na_"), indexSettings, new AnalysisMorphologyPlugin()); 48 | } 49 | 50 | public static void assertSimpleTSOutput(TokenStream stream, String[] expected) throws IOException { 51 | stream.reset(); 52 | CharTermAttribute termAttr = stream.getAttribute(CharTermAttribute.class); 53 | assertNotNull(termAttr); 54 | int i = 0; 55 | while (stream.incrementToken()) { 56 | assertTrue("got extra term: " + termAttr.toString(), i < expected.length); 57 | assertEquals("expected different term at index " + i, expected[i], termAttr.toString()); 58 | i++; 59 | } 60 | assertEquals("not all tokens produced", expected.length, i); 61 | } 62 | 63 | public void testMorphologyAnalysis() throws Exception { 64 | TestAnalysis testAnalysis = getAnalysisService(); 65 | 66 | NamedAnalyzer russianAnalyzer = testAnalysis.indexAnalyzers.get("russian_morphology"); 67 | assertThat(russianAnalyzer.analyzer(), instanceOf(MorphologyAnalyzer.class)); 68 | assertSimpleTSOutput(russianAnalyzer.tokenStream("test", new StringReader("тест")), new String[] {"тест", "тесто"}); 69 | 70 | NamedAnalyzer englishAnalyzer = testAnalysis.indexAnalyzers.get("english_morphology"); 71 | assertThat(englishAnalyzer.analyzer(), instanceOf(MorphologyAnalyzer.class)); 72 | assertSimpleTSOutput(englishAnalyzer.tokenStream("test", new StringReader("gone")), new String[]{"gone", "go"}); 73 | } 74 | 75 | public void testPm() throws Exception { 76 | LuceneMorphology russianLuceneMorphology = new RussianLuceneMorphology(); 77 | LuceneMorphology englishLuceneMorphology = new EnglishLuceneMorphology(); 78 | 79 | MorphologyAnalyzer russianAnalyzer = new MorphologyAnalyzer(russianLuceneMorphology); 80 | TokenStream stream = russianAnalyzer.tokenStream("name", new FastStringReader("тест пм тест")); 81 | MorphologyFilter englishFilter = new MorphologyFilter(stream, englishLuceneMorphology); 82 | assertSimpleTSOutput(englishFilter, new String[] {"тест", "тесто", "пм", "тест", "тесто"}); 83 | } 84 | } 85 | -------------------------------------------------------------------------------- /src/test/java/org/elasticsearch/plugin/analysis/morphology/AnalysisMorphologyRestIT.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright 2012 Igor Motov 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package org.elasticsearch.plugin.analysis.morphology; 18 | 19 | import com.carrotsearch.randomizedtesting.annotations.Name; 20 | import com.carrotsearch.randomizedtesting.annotations.ParametersFactory; 21 | import org.elasticsearch.test.rest.yaml.ClientYamlTestCandidate; 22 | import org.elasticsearch.test.rest.yaml.ESClientYamlSuiteTestCase; 23 | 24 | import java.io.IOException; 25 | 26 | public class AnalysisMorphologyRestIT extends ESClientYamlSuiteTestCase { 27 | 28 | public AnalysisMorphologyRestIT(@Name("yaml") ClientYamlTestCandidate testCandidate) { 29 | super(testCandidate); 30 | } 31 | 32 | @ParametersFactory 33 | public static Iterable parameters() throws Exception { 34 | return ESClientYamlSuiteTestCase.createParameters(); 35 | } 36 | } 37 | 38 | 39 | -------------------------------------------------------------------------------- /src/test/resources/rest-api-spec/test/analysis-morphology/10_analyze.yml: -------------------------------------------------------------------------------- 1 | # Basic integration tests for the morphology analysis plugin 2 | # 3 | --- 4 | "Russian analyzer and filter": 5 | - do: 6 | indices.analyze: 7 | body: 8 | tokenizer: standard 9 | filter: ["lowercase", "russian_morphology"] 10 | text: Японские автомобили 11 | - length: { tokens: 2 } 12 | - match: { tokens.0.token: японский } 13 | - match: { tokens.1.token: автомобиль } 14 | 15 | -------------------------------------------------------------------------------- /src/test/resources/rest-api-spec/test/analysis-morphology/5_plugin_version.yml: -------------------------------------------------------------------------------- 1 | # Basic integration tests for the morphology analysis plugin 2 | # 3 | --- 4 | "Russian analyzer and filter": 5 | - do: 6 | cluster.state: {} 7 | 8 | # Get master node id 9 | - set: { master_node: master } 10 | 11 | - do: 12 | nodes.info: 13 | metric: [ plugins ] 14 | 15 | - match : { nodes.$master.plugins.0.name: "analysis-morphology" } 16 | - match : 17 | nodes.$master.plugins.0.version: | 18 | /^\d+\.\d+\.\d+(\.\d+)?$/ 19 | --------------------------------------------------------------------------------