├── .gitignore ├── LICENSE ├── README.md ├── pom.xml └── src └── main └── java └── com └── canelmas └── kafka └── connect └── FieldAndTimeBasedPartitioner.java /.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 | 11 | # Avoid ignoring Maven wrapper jar file (.jar files are usually ignored) 12 | !/.mvn/wrapper/maven-wrapper.jar 13 | 14 | *.iml 15 | *.idea -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ### Kafka Connect Field and Time Based Partitioner 2 | 3 | #### Summary 4 | - Partition initially by custom fields and then by time. 5 | - It extends **[TimeBasedPartitioner](https://github.com/confluentinc/kafka-connect-storage-common/blob/master/partitioner/src/main/java/io/confluent/connect/storage/partitioner/TimeBasedPartitioner.java)**, so any existing time based partition config should be fine i.e. `path.format` will be respected. 6 | - In order to make it work, set `"partitioner.class"="com.canelmas.kafka.connect.FieldAndTimeBasedPartitioner"` and `"partition.field.name"=""` in your connector config. 7 | - Set `partition.field.format.path=false` if you don't want to use field labels for partitions names. 8 | 9 | ```bash 10 | { 11 | ... 12 | "s3.bucket.name" : "data", 13 | "partition.field.name" : "appId,eventName,country", 14 | "partition.field.format.path" : true, 15 | "path.format": "'year'=YYYY/'month'=MM/'day'=dd", 16 | ... 17 | } 18 | ``` 19 | will produce an output in the following format : 20 | 21 | ```bash 22 | /data/appId=XXXXX/eventName=YYYYYY/country=ZZ/year=2020/month=11/day=30 23 | ``` 24 | 25 | #### Example 26 | 27 | ```bash 28 | KCONNECT_NODES=("localhost:18083" "localhost:28083" "localhost:38083") 29 | 30 | for i in "${!KCONNECT_NODES[@]}"; do 31 | curl ${KCONNECT_NODES[$i]}/connectors -XPOST -H 'Content-type: application/json' -H 'Accept: application/json' -d '{ 32 | "name": "connect-s3-sink-'$i'", 33 | "config": { 34 | "topics": "events", 35 | "connector.class": "io.confluent.connect.s3.S3SinkConnector", 36 | "tasks.max" : 10, 37 | "flush.size": 50, 38 | "rotate.schedule.interval.ms": 600, 39 | "rotate.interval.ms": -1, 40 | "s3.part.size" : 5242880, 41 | "s3.region" : "us-east-1", 42 | "s3.bucket.name" : "playground-parquet-ingestion", 43 | "topics.dir": "data", 44 | "storage.class" : "io.confluent.connect.s3.storage.S3Storage", 45 | "partitioner.class": "com.canelmas.kafka.connect.FieldAndTimeBasedPartitioner", 46 | "partition.field.name" : "appId,eventName", 47 | "partition.duration.ms" : 86400000, 48 | "path.format": "'year'=YYYY/'month'=MM/'day'=dd", 49 | "locale" : "US", 50 | "timezone" : "UTC", 51 | "format.class": "io.confluent.connect.s3.format.parquet.ParquetFormat", 52 | "key.converter": "org.apache.kafka.connect.storage.StringConverter", 53 | "value.converter": "io.confluent.connect.avro.AvroConverter", 54 | "value.converter.schema.registry.url": "http://schema-registry:8081", 55 | "schema.compatibility": "NONE", 56 | "timestamp.extractor": "RecordField", 57 | "timestamp.field" : "clientCreationDate", 58 | "parquet.codec": "snappy" 59 | } 60 | }' 61 | done 62 | ``` 63 | 64 | #### Installation Guide 65 | 66 | 1. Before building make sure maven and java development kit is install. 67 | 2. Firstly build the package using the following command `mvn package`. 68 | 3. After building the package a new jar will created in `target/connect-fieldandtime-partitioner-1.1.0-SNAPSHOT.jar` copy the jar file into the s3 plugin directory. 69 | 4. Restart the connector if the user use helm redeploy the helm so that it can detect the plugin. 70 | 71 | __Tips__ 72 | 73 | *Where is the plugin?* 74 | 75 | If the plugin was installed via confluent-hub the jar file should be copy to `/usr/share/confluent-hub-components/confluentinc-kafka-connect-s3/lib/` however if kafka-connect-s3-sink was installed somewhere else place the jar file in the __same directory as the connector plugin jars__. 76 | 77 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 2 | 17 | 18 | 21 | 4.0.0 22 | 23 | com.canelmas.kafka 24 | connect-fieldandtime-partitioner 25 | 1.1.0-SNAPSHOT 26 | 27 | 28 | 29 | org.apache.maven.plugins 30 | maven-compiler-plugin 31 | 32 | 8 33 | 8 34 | 35 | 36 | 37 | 38 | jar 39 | 40 | 41 | 5.5.2 42 | 43 | 44 | 45 | 46 | confluent 47 | https://packages.confluent.io/maven/ 48 | 49 | 50 | 51 | 52 | 53 | io.confluent 54 | kafka-connect-storage-partitioner 55 | ${confluent.version} 56 | 57 | 58 | joda-time 59 | joda-time 60 | 2.10.2 61 | 62 | 63 | org.apache.kafka 64 | connect-api 65 | 2.3.0 66 | 67 | 68 | 69 | -------------------------------------------------------------------------------- /src/main/java/com/canelmas/kafka/connect/FieldAndTimeBasedPartitioner.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright (C) 2020 Can Elmas 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 com.canelmas.kafka.connect; 18 | 19 | import io.confluent.connect.storage.common.StorageCommonConfig; 20 | import io.confluent.connect.storage.errors.PartitionException; 21 | import io.confluent.connect.storage.partitioner.PartitionerConfig; 22 | import io.confluent.connect.storage.partitioner.TimeBasedPartitioner; 23 | import io.confluent.connect.storage.util.DataUtils; 24 | import org.apache.kafka.connect.connector.ConnectRecord; 25 | import org.apache.kafka.connect.data.Struct; 26 | import org.apache.kafka.connect.sink.SinkRecord; 27 | import org.joda.time.DateTimeZone; 28 | import org.slf4j.Logger; 29 | import org.slf4j.LoggerFactory; 30 | 31 | import java.util.List; 32 | import java.util.Locale; 33 | import java.util.Map; 34 | 35 | public final class FieldAndTimeBasedPartitioner extends TimeBasedPartitioner { 36 | 37 | public static final String PARTITION_FIELD_FORMAT_PATH_CONFIG = "partition.field.format.path"; 38 | public static final String PARTITION_FIELD_FORMAT_PATH_DOC = "Whether directory labels should be included when partitioning for custom fields e.g. " + 39 | "whether this 'orgId=XXXX/appId=ZZZZ/customField=YYYY' or this 'XXXX/ZZZZ/YYYY'."; 40 | public static final String PARTITION_FIELD_FORMAT_PATH_DISPLAY = "Partition Field Format Path"; 41 | public static final boolean PARTITION_FIELD_FORMAT_PATH_DEFAULT = true; 42 | private static final Logger log = LoggerFactory.getLogger(FieldAndTimeBasedPartitioner.class); 43 | private PartitionFieldExtractor partitionFieldExtractor; 44 | 45 | protected void init(long partitionDurationMs, String pathFormat, Locale locale, DateTimeZone timeZone, Map config) { 46 | super.init(partitionDurationMs, pathFormat, locale, timeZone, config); 47 | 48 | final List fieldNames = (List) config.get(PartitionerConfig.PARTITION_FIELD_NAME_CONFIG); 49 | // option value is parse as string all other type is cast as string by kafka connect need to parse by ourselves 50 | final boolean formatPath = Boolean.parseBoolean((String) config.getOrDefault(PARTITION_FIELD_FORMAT_PATH_CONFIG, PARTITION_FIELD_FORMAT_PATH_DEFAULT)); 51 | 52 | this.partitionFieldExtractor = new PartitionFieldExtractor(fieldNames, formatPath); 53 | } 54 | 55 | public String encodePartition(final SinkRecord sinkRecord, final long nowInMillis) { 56 | final String partitionsForTimestamp = super.encodePartition(sinkRecord, nowInMillis); 57 | final String partitionsForFields = this.partitionFieldExtractor.extract(sinkRecord); 58 | final String partition = String.join(this.delim, partitionsForFields, partitionsForTimestamp); 59 | 60 | log.info("Encoded partition : {}", partition); 61 | 62 | return partition; 63 | } 64 | 65 | public String encodePartition(final SinkRecord sinkRecord) { 66 | final String partitionsForTimestamp = super.encodePartition(sinkRecord); 67 | final String partitionsForFields = this.partitionFieldExtractor.extract(sinkRecord); 68 | final String partition = String.join(this.delim, partitionsForFields, partitionsForTimestamp); 69 | 70 | log.info("Encoded partition : {}", partition); 71 | 72 | return partition; 73 | } 74 | 75 | public static class PartitionFieldExtractor { 76 | 77 | private static final String DELIMITER_EQ = "="; 78 | 79 | private final boolean formatPath; 80 | private final List fieldNames; 81 | 82 | PartitionFieldExtractor(final List fieldNames, final boolean formatPath) { 83 | this.fieldNames = fieldNames; 84 | this.formatPath = formatPath; 85 | } 86 | 87 | public String extract(final ConnectRecord record) { 88 | 89 | final Object value = record.value(); 90 | 91 | final StringBuilder builder = new StringBuilder(); 92 | 93 | for (final String fieldName : this.fieldNames) { 94 | 95 | if (builder.length() != 0) { 96 | builder.append(StorageCommonConfig.DIRECTORY_DELIM_DEFAULT); 97 | } 98 | 99 | if (value instanceof Struct || value instanceof Map) { 100 | 101 | final String partitionField = (String) DataUtils.getNestedFieldValue(value, fieldName); 102 | 103 | if (formatPath) { 104 | builder.append(String.join(DELIMITER_EQ, fieldName, partitionField)); 105 | } else { 106 | builder.append(partitionField); 107 | } 108 | 109 | } else { 110 | log.error("Value is not of Struct or Map type."); 111 | throw new PartitionException("Error encoding partition."); 112 | } 113 | 114 | } 115 | 116 | return builder.toString(); 117 | 118 | } 119 | } 120 | 121 | } 122 | --------------------------------------------------------------------------------