├── lang-detect ├── src │ ├── main │ │ ├── resources │ │ │ └── .exists │ │ └── java │ │ │ └── net │ │ │ └── alexott │ │ │ └── ksql │ │ │ └── langdetect │ │ │ ├── LanguageDetector.java │ │ │ └── LanguageModelHolder.java │ └── test │ │ └── java │ │ └── net │ │ └── alexott │ │ └── ksql │ │ └── langdetect │ │ └── LanguageDetectorTest.java ├── README.md └── pom.xml ├── README.md ├── .gitignore └── LICENSE /lang-detect/src/main/resources/.exists: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Experiments with KSQL 2 | 3 | This repository contains code for different experiments with KSQL... 4 | 5 | -------------------------------------------------------------------------------- /lang-detect/README.md: -------------------------------------------------------------------------------- 1 | 2 | 3 | ## Build ## 4 | 5 | Right now, the code requires patched version of JFastText library that could be found at 6 | https://github.com/alexott/JFastText/tree/issue-19-fix - execute `mvn install` on it to 7 | install patched Jars into local Maven repo. 8 | 9 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | target/ 2 | pom.xml.tag 3 | pom.xml.releaseBackup 4 | pom.xml.versionsBackup 5 | pom.xml.next 6 | release.properties 7 | dependency-reduced-pom.xml 8 | buildNumber.properties 9 | .mvn/timing.properties 10 | .idea/ 11 | *~ 12 | /lang-detect/src/main/resources/lid.176.ftz 13 | /lang-detect/src/main/resources/lid.176.bin 14 | 15 | # Avoid ignoring Maven wrapper jar file (.jar files are usually ignored) 16 | !/.mvn/wrapper/maven-wrapper.jar 17 | -------------------------------------------------------------------------------- /lang-detect/src/test/java/net/alexott/ksql/langdetect/LanguageDetectorTest.java: -------------------------------------------------------------------------------- 1 | package net.alexott.ksql.langdetect; 2 | 3 | import junit.framework.TestCase; 4 | 5 | public class LanguageDetectorTest extends TestCase { 6 | LanguageDetector languageDetector = new LanguageDetector(); 7 | 8 | public void testLangRussian() { 9 | String lang = languageDetector.langdetect("Это русский текст"); 10 | assertNotNull(lang); 11 | assertEquals("ru", lang); 12 | } 13 | 14 | public void testLangVietnamese() { 15 | String lang = languageDetector.langdetect("Xin chào"); 16 | assertNotNull(lang); 17 | assertEquals("vi", lang); 18 | } 19 | 20 | public void testLangGerman() { 21 | String lang = languageDetector.langdetect("Das ist Deutsch"); 22 | assertNotNull(lang); 23 | assertEquals("de", lang); 24 | } 25 | 26 | public void testLangEnglish() { 27 | String lang = languageDetector.langdetect("This is English"); 28 | assertNotNull(lang); 29 | assertEquals("en", lang); 30 | } 31 | } -------------------------------------------------------------------------------- /lang-detect/src/main/java/net/alexott/ksql/langdetect/LanguageDetector.java: -------------------------------------------------------------------------------- 1 | package net.alexott.ksql.langdetect; 2 | 3 | import com.github.jfasttext.JFastText; 4 | import io.confluent.ksql.function.udf.Udf; 5 | import io.confluent.ksql.function.udf.UdfDescription; 6 | import org.slf4j.Logger; 7 | import org.slf4j.LoggerFactory; 8 | 9 | import java.io.InputStream; 10 | 11 | @UdfDescription(name = "langdetect", description = "Language detection using FastText") 12 | public class LanguageDetector { 13 | private static Logger LOGGER = LoggerFactory.getLogger(LanguageDetector.class); 14 | private final static String UNKNOWN_LANGUAGE="unk"; 15 | private final static String LABEL_PREFIX="__label__"; 16 | 17 | @Udf(description = "perform language detection") 18 | public String langdetect(final String text) { 19 | JFastText langModel = LanguageModelHolder.getLangModel(); 20 | if (langModel == null || text == null) { 21 | return null; 22 | } 23 | try { 24 | String label = langModel.predict(text); 25 | if (label != null && label.startsWith(LABEL_PREFIX)) { 26 | return label.substring(LABEL_PREFIX.length()); 27 | } else { 28 | return UNKNOWN_LANGUAGE; 29 | } 30 | } catch (Exception ex) { 31 | LOGGER.error("Exception during language detection. " + ex); 32 | return null; 33 | } 34 | } 35 | } 36 | -------------------------------------------------------------------------------- /lang-detect/src/main/java/net/alexott/ksql/langdetect/LanguageModelHolder.java: -------------------------------------------------------------------------------- 1 | package net.alexott.ksql.langdetect; 2 | 3 | import com.github.jfasttext.JFastText; 4 | import io.confluent.ksql.function.udf.Udf; 5 | import io.confluent.ksql.function.udf.UdfDescription; 6 | import org.slf4j.Logger; 7 | import org.slf4j.LoggerFactory; 8 | 9 | import java.io.InputStream; 10 | 11 | class LanguageModelHolder { 12 | private static Logger LOGGER = LoggerFactory.getLogger(LanguageModelHolder.class); 13 | static JFastText langModel = null; 14 | 15 | private static final String COMPRESSED_MODEL = "/lid.176.ftz"; 16 | private static final String FULL_MODEL = "/lid.176.bin"; 17 | private static final boolean USE_FULL_MODEL = true; 18 | 19 | static { 20 | try { 21 | // TODO: use system property to load compressed or full language model... 22 | String model = (USE_FULL_MODEL ? FULL_MODEL : COMPRESSED_MODEL); 23 | InputStream is = LanguageModelHolder.class.getResourceAsStream(model); 24 | if (is != null) { 25 | langModel = new JFastText(is); 26 | } else { 27 | LOGGER.error("Can't load resource from classpath..."); 28 | } 29 | } catch (Exception ex) { 30 | LOGGER.error("Error loading language model: " + ex.getMessage(), ex); 31 | } 32 | } 33 | 34 | static JFastText getLangModel() { 35 | return langModel; 36 | } 37 | } 38 | -------------------------------------------------------------------------------- /lang-detect/pom.xml: -------------------------------------------------------------------------------- 1 | 3 | 4.0.0 4 | 5 | net.alexott.ksql 6 | ksql-lang-detect 7 | 0.0.1 8 | jar 9 | 10 | jdtest1 11 | http://maven.apache.org 12 | 13 | 14 | UTF-8 15 | 1.8 16 | 5.2.1 17 | 18 | 19 | 20 | 21 | com.github.vinhkhuc 22 | jfasttext 23 | 0.4 24 | 25 | 26 | io.confluent.ksql 27 | ksql-udf 28 | ${confluent.version} 29 | provided 30 | 31 | 32 | junit 33 | junit 34 | 3.8.1 35 | test 36 | 37 | 38 | 39 | 40 | 41 | 42 | confluent 43 | http://packages.confluent.io/maven/ 44 | 45 | 46 | 47 | 48 | 49 | 50 | src/main/resources 51 | 52 | 53 | 54 | 55 | maven-compiler-plugin 56 | 3.6.1 57 | 58 | ${java.version} 59 | ${java.version} 60 | true 61 | 62 | 63 | 64 | org.apache.maven.plugins 65 | maven-assembly-plugin 66 | 3.1.0 67 | 68 | 69 | jar-with-dependencies 70 | 71 | 72 | 73 | 74 | package 75 | 76 | single 77 | 78 | 79 | 80 | 81 | 82 | com.googlecode.maven-download-plugin 83 | download-maven-plugin 84 | 1.4.1 85 | 86 | 87 | get-compressed-model 88 | generate-resources 89 | 90 | wget 91 | 92 | 93 | https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.ftz 94 | src/main/resources/ 95 | 86d1b630ba55a5040231eda9fe24a7befdc411f2 96 | 97 | 98 | 99 | get-full-model 100 | generate-resources 101 | 102 | wget 103 | 104 | 105 | https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin 106 | src/main/resources/ 107 | e613bda316ecb4f5e1924140eedf81b81c087d9a 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | 116 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------