├── .gitignore ├── LICENSE ├── README.md ├── pom.xml ├── repo └── com │ └── amazonaws │ └── redshiftjdbc41 │ ├── 1.1.13.1013 │ ├── .keep │ └── redshiftjdbc41-1.1.13.1013.pom │ └── maven-metadata-local.xml └── src └── main ├── java └── io │ └── tenjin │ └── kafka │ └── connect │ └── redshift │ ├── CopySerializer.java │ ├── DefaultCopySerializer.java │ ├── RedshiftSinkConnector.java │ ├── RedshiftSinkConnectorConfig.java │ ├── RedshiftSinkTask.java │ ├── RedshiftSinkTaskConfig.java │ └── utils │ └── Version.java └── resources └── kafka-connect-redshift-version.properties /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | *.iml 3 | .DS_Store 4 | target 5 | -------------------------------------------------------------------------------- /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 Redshift 2 | ====================== 3 | 4 | Kafka Sink Connector for Amazon Redshift 5 | 6 | ## Build 7 | 8 | * Install the Redshift driver into the local maven repository. 9 | * Download the [Redshift JDBC 4.1 Driver](http://docs.aws.amazon.com/redshift/latest/mgmt/configure-jdbc-connection.html). 10 | * Copy the jar into `repo/com/amazonaws/redshiftjdbc41/${redshift.version}/` 11 | * `mvn package` 12 | * Copy `target/kafka-connect-redshift-VERSION-jar-with-dependencies.jar` into your classpath. 13 | 14 | 15 | ## Configure 16 | 17 | * `name` - Connector identifier. 18 | * `connector.class` - io.tenjin.kafka.connect.redshift.RedshiftSinkConnector 19 | * `tasks.max` - Max number of tasks 20 | * `topics` - Topics to read from Kafka. 21 | 22 | * `temp.output.dir` - Output directory to write to the local filesystem. 23 | * `s3.bucket` - S3 bucket to stage data for COPY. 24 | * `aws.access.key.id` - AWS access key ID. 25 | * `aws.secret.access.key` - AWS secret access key. 26 | * `connection.url` - Redshift JDBC connection URL. If you're using Amazon's Redshift JDBC Driver, you may want to set 27 | `OpenSourceSubProtocolOverride=true` in case the PostgreSQL driver is on your classpath. 28 | * `table` - Redshift destination table name. 29 | * `fields` - Field names to send to Redshift. Use * for all fields. 30 | 31 | ## Run 32 | 33 | On Confluent Platform: 34 | ```bash 35 | bin/connect-standalone etc/connect-standalone.properties ... 36 | ``` 37 | 38 | With Kafka only download: 39 | ```bash 40 | bin/connect-standalone.sh config/connect-standalone.properties ... 41 | ``` 42 | 43 | 44 | ## Known Limitations 45 | 46 | * Untested. => Use at your own risk! 47 | * Uses the local filesystem. => Make sure you have enough disk space! 48 | * No WAL, probably doesn't recover well. => Contribute! 49 | * Only 1 destination table supported. 50 | 51 | If you're running the Confluent Platform on Java 8, there is an [issue with Joda Time and hadoop-aws] 52 | (https://github.com/JodaOrg/joda-time/issues/288). The workaround is to exclude the `share/java/kafka-connect-hdfs/joda-time-1.6.2.jar` 53 | from the classpath when running the connectors. The newer Joda Time classes should be included in the built jar. 54 | 55 | ## License 56 | 57 | Apache v2.0 58 | 59 | ## Contribute 60 | 61 | Help me out, please. Thanks! 62 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 2 | 5 | 4.0.0 6 | 7 | io.tenjin 8 | kafka-connect-redshift 9 | 0.0.1-SNAPSHOT 10 | 11 | 12 | 13 | local_driver_repo 14 | Local Drivers 15 | file:///${project.basedir}/repo 16 | 17 | 18 | confluent 19 | Confluent 20 | http://packages.confluent.io/maven/ 21 | 22 | 23 | 24 | 25 | 0.9.0.1 26 | 1.9.2 27 | 1.1.13.1013 28 | 29 | 30 | 31 | 32 | org.apache.kafka 33 | connect-api 34 | ${kafka.version} 35 | 36 | 37 | com.amazonaws 38 | aws-java-sdk-core 39 | ${aws.java.sdk.version} 40 | 41 | 42 | com.amazonaws 43 | aws-java-sdk-s3 44 | ${aws.java.sdk.version} 45 | 46 | 47 | com.amazonaws 48 | redshiftjdbc41 49 | ${redshift.jdbc.version} 50 | runtime 51 | 52 | 53 | 54 | org.apache.kafka 55 | connect-runtime 56 | ${kafka.version} 57 | runtime 58 | 59 | 60 | 61 | 62 | 63 | 64 | src/main/resources 65 | true 66 | 67 | 68 | 69 | 70 | maven-compiler-plugin 71 | 3.5 72 | 73 | 1.7 74 | 1.7 75 | 76 | 77 | 78 | maven-assembly-plugin 79 | 2.6 80 | 81 | 82 | make-assembly 83 | package 84 | 85 | single 86 | 87 | 88 | 89 | 90 | 91 | jar-with-dependencies 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | -------------------------------------------------------------------------------- /repo/com/amazonaws/redshiftjdbc41/1.1.13.1013/.keep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lepfhty/kafka-connect-redshift/85007971ac2c8c0ef23d8a21391c0f9ba9fc9e9b/repo/com/amazonaws/redshiftjdbc41/1.1.13.1013/.keep -------------------------------------------------------------------------------- /repo/com/amazonaws/redshiftjdbc41/1.1.13.1013/redshiftjdbc41-1.1.13.1013.pom: -------------------------------------------------------------------------------- 1 | 2 | 4 | 4.0.0 5 | com.amazonaws 6 | redshiftjdbc41 7 | 1.1.13.1013 8 | POM was created from install:install-file 9 | 10 | -------------------------------------------------------------------------------- /repo/com/amazonaws/redshiftjdbc41/maven-metadata-local.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | com.amazonaws 4 | redshiftjdbc41 5 | 6 | 1.1.13.1013 7 | 8 | 1.1.13.1013 9 | 10 | 20160222181830 11 | 12 | 13 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/CopySerializer.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift; 2 | 3 | import org.apache.kafka.connect.sink.SinkRecord; 4 | 5 | public interface CopySerializer { 6 | String serializeRecord(SinkRecord record); 7 | String copyOptions(); 8 | } 9 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/DefaultCopySerializer.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift; 2 | 3 | import org.apache.kafka.connect.data.Field; 4 | import org.apache.kafka.connect.data.Schema; 5 | import org.apache.kafka.connect.data.Struct; 6 | import org.apache.kafka.connect.sink.SinkRecord; 7 | 8 | import java.text.DateFormat; 9 | import java.text.SimpleDateFormat; 10 | import java.util.ArrayList; 11 | import java.util.Date; 12 | import java.util.List; 13 | import java.util.TimeZone; 14 | 15 | public class DefaultCopySerializer implements CopySerializer { 16 | 17 | private static final DateFormat FORMAT; 18 | private List fields; 19 | 20 | static { 21 | FORMAT = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSSSSS"); 22 | FORMAT.setTimeZone(TimeZone.getTimeZone("UTC")); 23 | } 24 | 25 | public DefaultCopySerializer(List fields) { 26 | this.fields = new ArrayList<>(fields); 27 | } 28 | 29 | private static final String DELIMITER = "|"; 30 | private static final String NULL = "\\N"; 31 | private static final String ESCAPE = "\\"; 32 | private static final String NEWLINE = "\n"; 33 | 34 | private static final String ESCAPE_ESCAPE = ESCAPE + ESCAPE; 35 | private static final String ESCAPE_NEWLINE = ESCAPE + NEWLINE; 36 | private static final String ESCAPE_DELIMITER = ESCAPE + DELIMITER; 37 | 38 | private static final String COPY_OPTIONS = "ESCAPE DELIMITER '" + DELIMITER + "'"; 39 | 40 | public String serializeRecord(SinkRecord record) { 41 | Struct struct = (Struct) record.value(); 42 | StringBuilder b = new StringBuilder(); 43 | boolean first = true; 44 | List fieldsList = fields; 45 | if (fields.isEmpty()) { 46 | for (Field f : record.valueSchema().fields()) 47 | fields.add(f.name()); 48 | } 49 | for (String field : fieldsList) { 50 | if (!first) 51 | b.append(DELIMITER); 52 | Object value = struct.get(field); 53 | if (value == null) 54 | b.append(NULL); 55 | else if (value instanceof Date) { 56 | b.append(FORMAT.format(value)); 57 | } 58 | else if (value instanceof String) { 59 | String str = value.toString() 60 | .replace(ESCAPE, ESCAPE_ESCAPE) 61 | .replace(DELIMITER, ESCAPE_DELIMITER) 62 | .replace(NEWLINE, ESCAPE_NEWLINE); 63 | b.append(str); 64 | } 65 | else { 66 | b.append(value); 67 | } 68 | first = false; 69 | } 70 | return b.toString(); 71 | } 72 | 73 | public String copyOptions() { 74 | return COPY_OPTIONS; 75 | } 76 | } 77 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/RedshiftSinkConnector.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift; 2 | 3 | import io.tenjin.kafka.connect.redshift.utils.Version; 4 | import org.apache.kafka.connect.connector.Task; 5 | import org.apache.kafka.connect.sink.SinkConnector; 6 | 7 | import java.util.ArrayList; 8 | import java.util.HashMap; 9 | import java.util.List; 10 | import java.util.Map; 11 | 12 | public class RedshiftSinkConnector extends SinkConnector { 13 | 14 | private Map configProperties; 15 | private RedshiftSinkConnectorConfig config; 16 | 17 | @Override 18 | public void start(Map properties) { 19 | configProperties = properties; 20 | config = new RedshiftSinkConnectorConfig(configProperties); 21 | } 22 | 23 | @Override 24 | public List> taskConfigs(int maxTasks) { 25 | List> taskConfigs = new ArrayList<>(maxTasks); 26 | for(int i = 0; i < maxTasks; i++) { 27 | taskConfigs.add(new HashMap<>(configProperties)); 28 | } 29 | return taskConfigs; 30 | } 31 | 32 | @Override 33 | public void stop() { 34 | 35 | } 36 | 37 | @Override 38 | public String version() { 39 | return Version.getVersion(); 40 | } 41 | 42 | @Override 43 | public Class taskClass() { 44 | return RedshiftSinkTask.class; 45 | } 46 | } 47 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/RedshiftSinkConnectorConfig.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift; 2 | 3 | import com.amazonaws.auth.AWSCredentials; 4 | import com.amazonaws.auth.BasicAWSCredentials; 5 | import org.apache.kafka.common.config.AbstractConfig; 6 | import org.apache.kafka.common.config.ConfigDef; 7 | 8 | import java.util.List; 9 | import java.util.Map; 10 | 11 | import static org.apache.kafka.common.config.ConfigDef.Importance; 12 | import static org.apache.kafka.common.config.ConfigDef.Type; 13 | 14 | public class RedshiftSinkConnectorConfig extends AbstractConfig { 15 | 16 | // public static final String TOPIC_CONFIG = "topic"; 17 | // private static final String TOPIC_DOC = "Kafka topic to consume messages."; 18 | 19 | public static final String S3_BUCKET_CONFIG = "s3.bucket"; 20 | private static final String S3_BUCKET_DOC = "S3 bucket to stage data for COPY."; 21 | 22 | public static final String CONNECTION_URL_CONFIG = "connection.url"; 23 | private static final String CONNECTION_URL_DOC = "Redshift JDBC connection URL."; 24 | 25 | public static final String TABLE_CONFIG = "table"; 26 | private static final String TABLE_DOC = "Redshift destination table name."; 27 | 28 | public static final String FIELDS_CONFIG = "fields"; 29 | private static final String FIELDS_DOC = "Field names to send to Redshift. Use * for all fields."; 30 | public static final String FIELDS_DEFAULT = "*"; 31 | 32 | public static final String TEMP_OUTPUT_DIR_CONFIG = "temp.output.dir"; 33 | private static final String TEMP_OUTPUT_DIR_DOC = "Output directory to write to the local filesystem."; 34 | public static final String TEMP_OUTPUT_DIR_DEFAULT = "/tmp/kafka-connect-redshift"; 35 | 36 | public static final String AWS_ACCESS_KEY_ID_CONFIG = "aws.access.key.id"; 37 | public static final String AWS_ACCESS_KEY_ID_DOC = "AWS Access Key ID"; 38 | public static final String AWS_SECRET_ACCESS_KEY_CONFIG = "aws.secret.access.key"; 39 | public static final String AWS_SECRET_ACCESS_KEY_DOC = "AWS Secret Access Key"; 40 | 41 | public static ConfigDef baseConfigDef() { 42 | return new ConfigDef() 43 | .define(RedshiftSinkConnector.TOPICS_CONFIG, Type.LIST, Importance.HIGH, "Topic list") 44 | .define(S3_BUCKET_CONFIG, Type.STRING, Importance.HIGH, S3_BUCKET_DOC) 45 | .define(CONNECTION_URL_CONFIG, Type.STRING, Importance.HIGH, CONNECTION_URL_DOC) 46 | .define(FIELDS_CONFIG, Type.LIST, FIELDS_DEFAULT, Importance.HIGH, FIELDS_DOC) 47 | .define(TABLE_CONFIG, Type.STRING, Importance.HIGH, TABLE_DOC) 48 | .define(TEMP_OUTPUT_DIR_CONFIG, Type.STRING, TEMP_OUTPUT_DIR_DEFAULT, Importance.HIGH, TEMP_OUTPUT_DIR_DOC) 49 | .define(AWS_ACCESS_KEY_ID_CONFIG, Type.STRING, Importance.HIGH, AWS_ACCESS_KEY_ID_DOC) 50 | .define(AWS_SECRET_ACCESS_KEY_CONFIG, Type.PASSWORD, Importance.HIGH, AWS_SECRET_ACCESS_KEY_DOC); 51 | } 52 | 53 | static ConfigDef config = baseConfigDef(); 54 | 55 | public RedshiftSinkConnectorConfig(Map originals) { 56 | super(config, originals); 57 | } 58 | 59 | protected RedshiftSinkConnectorConfig(ConfigDef def, Map props) { 60 | super(def, props); 61 | } 62 | 63 | public String getTopic() { 64 | return getList(RedshiftSinkConnector.TOPICS_CONFIG).get(0); 65 | } 66 | 67 | public String getS3Bucket() { 68 | return getString(S3_BUCKET_CONFIG); 69 | } 70 | 71 | public String getConnectionUrl() { 72 | return getString(CONNECTION_URL_CONFIG); 73 | } 74 | 75 | public String getTable() { 76 | return getString(TABLE_CONFIG); 77 | } 78 | 79 | public List getFields() { 80 | return getList(FIELDS_CONFIG); 81 | } 82 | 83 | public String getTempOutputDir() { 84 | return getString(TEMP_OUTPUT_DIR_CONFIG); 85 | } 86 | 87 | public AWSCredentials getAwsCredentials() { 88 | return new BasicAWSCredentials(getString(AWS_ACCESS_KEY_ID_CONFIG), getPassword(AWS_SECRET_ACCESS_KEY_CONFIG).value()); 89 | } 90 | 91 | } 92 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/RedshiftSinkTask.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift; 2 | 3 | import com.amazonaws.AmazonClientException; 4 | import com.amazonaws.auth.AWSCredentials; 5 | import com.amazonaws.services.s3.AmazonS3; 6 | import com.amazonaws.services.s3.AmazonS3Client; 7 | import io.tenjin.kafka.connect.redshift.utils.Version; 8 | import org.apache.kafka.clients.consumer.OffsetAndMetadata; 9 | import org.apache.kafka.common.TopicPartition; 10 | import org.apache.kafka.connect.errors.ConnectException; 11 | import org.apache.kafka.connect.errors.RetriableException; 12 | import org.apache.kafka.connect.sink.SinkRecord; 13 | import org.apache.kafka.connect.sink.SinkTask; 14 | import org.slf4j.Logger; 15 | import org.slf4j.LoggerFactory; 16 | 17 | import java.io.BufferedWriter; 18 | import java.io.File; 19 | import java.io.FileWriter; 20 | import java.io.IOException; 21 | import java.sql.Connection; 22 | import java.sql.DriverManager; 23 | import java.sql.SQLException; 24 | import java.sql.Statement; 25 | import java.text.SimpleDateFormat; 26 | import java.util.*; 27 | 28 | public class RedshiftSinkTask extends SinkTask { 29 | 30 | private static final Logger LOGGER = LoggerFactory.getLogger(RedshiftSinkTask.class); 31 | 32 | private Map configProperties; 33 | private RedshiftSinkTaskConfig config; 34 | 35 | private File tempDir; 36 | private Map tempFiles; 37 | private Map writers; 38 | 39 | private CopySerializer serializer; 40 | private AmazonS3 s3; 41 | 42 | @Override 43 | public void start(Map properties) { 44 | configProperties = properties; 45 | config = new RedshiftSinkTaskConfig(configProperties); 46 | 47 | tempDir = new File(config.getTempOutputDir()); 48 | tempDir.mkdirs(); 49 | tempFiles = new HashMap<>(); 50 | writers = new HashMap<>(); 51 | 52 | List fields = config.getFields(); 53 | if (fields.size() == 1 && fields.get(0).equals("*")) { 54 | fields.clear(); 55 | } 56 | serializer = new DefaultCopySerializer(fields); 57 | s3 = new AmazonS3Client(config.getAwsCredentials()); 58 | } 59 | 60 | private BufferedWriter getWriter(SinkRecord record) { 61 | TopicPartition tp = new TopicPartition(record.topic(), record.kafkaPartition()); 62 | BufferedWriter writer = writers.get(tp); 63 | if (writer == null) { 64 | try { 65 | File f = new File(tempDir, tp + ".dsv"); 66 | tempFiles.put(tp, f); 67 | writer = new BufferedWriter(new FileWriter(f)); 68 | writers.put(tp, writer); 69 | } catch (IOException e) { 70 | LOGGER.error("Couldn't create file for topic-partition {}.", tp, e); 71 | throw new ConnectException(e); 72 | } 73 | } 74 | return writer; 75 | } 76 | 77 | @Override 78 | public void put(Collection collection) { 79 | try { 80 | for (SinkRecord record : collection) { 81 | appendRecord(record); 82 | } 83 | } catch (IOException e) { 84 | LOGGER.warn("Failed to append records. Retrying batch.", e); 85 | throw new RetriableException(e); 86 | } 87 | } 88 | 89 | private void appendRecord(SinkRecord record) throws IOException { 90 | BufferedWriter writer = getWriter(record); 91 | String row = serializer.serializeRecord(record); 92 | writer.append(row); 93 | writer.newLine(); 94 | } 95 | 96 | @Override 97 | public void flush(Map map) { 98 | List s3Urls = new ArrayList<>(); 99 | Set tps = map.isEmpty() ? tempFiles.keySet() : map.keySet(); 100 | for (TopicPartition tp : tps) { 101 | closeTempFiles(tp); 102 | if (shouldCopyToRedshift(tp)) { 103 | String url = putFileToS3(tp); 104 | if (url != null) 105 | s3Urls.add(url); 106 | } 107 | } 108 | 109 | if (!s3Urls.isEmpty()) { 110 | String manifestUrl = createManifest(s3Urls); 111 | if (manifestUrl != null) 112 | copyFromS3ToRedshift(manifestUrl); 113 | } 114 | } 115 | 116 | private void closeTempFiles(TopicPartition tp) { 117 | try { 118 | BufferedWriter w = writers.get(tp); 119 | if (w != null) { 120 | w.close(); 121 | writers.remove(tp); 122 | } 123 | } catch (IOException e) { 124 | LOGGER.warn("Couldn't close writer for topic-partition {}", tp, e); 125 | } 126 | } 127 | 128 | private boolean shouldCopyToRedshift(TopicPartition tp) { 129 | return true; 130 | } 131 | 132 | private String putFileToS3(TopicPartition tp) { 133 | File file = tempFiles.get(tp); 134 | if (file == null || !file.exists() || file.length() == 0) 135 | return null; 136 | 137 | SimpleDateFormat f = new SimpleDateFormat("yyyy/MM/dd"); 138 | String key = String.format("%s/%s/%s", config.getTopic(), f.format(new Date()), file.getName()); 139 | String url = "s3://" + config.getS3Bucket() + "/" + key; 140 | try { 141 | s3.putObject(config.getS3Bucket(), key, file); 142 | if (file.delete()) { 143 | tempFiles.remove(tp); 144 | writers.remove(tp); 145 | } 146 | } catch (AmazonClientException e) { 147 | LOGGER.warn("Couldn't put file {} to S3 {}.", file.getName(), url, e); 148 | LOGGER.warn("Attempting to reopen writer for appending."); 149 | try { 150 | writers.put(tp, new BufferedWriter(new FileWriter(file))); 151 | } catch (IOException e1) { 152 | LOGGER.error("Couldn't reopen writer for appending {}.", file.getName(), e1); 153 | throw new ConnectException(e1); 154 | } 155 | } 156 | return url; 157 | } 158 | 159 | private String createManifest(List s3Urls) { 160 | File dir = new File(config.getTempOutputDir()); 161 | File manifestFile = new File(dir, "manifest_" + System.currentTimeMillis() + ".json"); 162 | BufferedWriter manifestWriter; 163 | try { 164 | manifestWriter = new BufferedWriter(new FileWriter(manifestFile)); 165 | manifestWriter.append("{\"entries\":["); 166 | boolean first = true; 167 | for (String url : s3Urls) { 168 | if (!first) { 169 | manifestWriter.append(","); 170 | } 171 | manifestWriter.append("{\"url\":\"").append(url).append("\",\"mandatory\":true}"); 172 | first = false; 173 | } 174 | manifestWriter.append("]}"); 175 | manifestWriter.close(); 176 | } catch (IOException e) { 177 | throw new ConnectException(e); 178 | } 179 | 180 | String key = config.getTopic() + "/" + manifestFile; 181 | String url = "s3://" + config.getS3Bucket() + "/" + key; 182 | try { 183 | s3.putObject(config.getS3Bucket(), key, manifestFile); 184 | } catch (AmazonClientException e) { 185 | LOGGER.warn("Couldn't put manifest file {} to S3 {}.", manifestFile.getName(), url, e); 186 | manifestFile.delete(); 187 | return null; 188 | } 189 | 190 | return url; 191 | } 192 | 193 | private void copyFromS3ToRedshift(String manifestUrl) { 194 | try (Connection conn = DriverManager.getConnection(config.getConnectionUrl()); 195 | Statement stmt = conn.createStatement()) { 196 | stmt.execute(copyStatement(manifestUrl)); 197 | } catch (SQLException e) { 198 | LOGGER.warn("Failed to copy data into Redshift.", e); 199 | } 200 | } 201 | 202 | private String copyStatement(String manifestUrl) { 203 | AWSCredentials creds = config.getAwsCredentials(); 204 | String copy = String.format("COPY %s FROM '%s' " + 205 | "CREDENTIALS 'aws_access_key_id=%s;aws_secret_access_key=%s' " + 206 | "MANIFEST %s", 207 | config.getTable(), 208 | manifestUrl, 209 | creds.getAWSAccessKeyId(), 210 | creds.getAWSSecretKey(), 211 | serializer.copyOptions()); 212 | return copy; 213 | } 214 | 215 | @Override 216 | public void stop() { 217 | 218 | } 219 | 220 | @Override 221 | public String version() { 222 | return Version.getVersion(); 223 | } 224 | 225 | @Override 226 | public void onPartitionsAssigned(Collection partitions) { 227 | super.onPartitionsAssigned(partitions); 228 | } 229 | 230 | @Override 231 | public void onPartitionsRevoked(Collection partitions) { 232 | super.onPartitionsRevoked(partitions); 233 | } 234 | } 235 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/RedshiftSinkTaskConfig.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift; 2 | 3 | import org.apache.kafka.common.config.ConfigDef; 4 | 5 | import java.util.Map; 6 | 7 | public class RedshiftSinkTaskConfig extends RedshiftSinkConnectorConfig { 8 | 9 | static ConfigDef config = baseConfigDef(); 10 | 11 | public RedshiftSinkTaskConfig(Map props) { 12 | super(config, props); 13 | } 14 | 15 | } 16 | -------------------------------------------------------------------------------- /src/main/java/io/tenjin/kafka/connect/redshift/utils/Version.java: -------------------------------------------------------------------------------- 1 | package io.tenjin.kafka.connect.redshift.utils; 2 | 3 | import org.slf4j.Logger; 4 | import org.slf4j.LoggerFactory; 5 | 6 | import java.util.Properties; 7 | 8 | public class Version { 9 | private static final Logger log = LoggerFactory.getLogger(Version.class); 10 | private static String version = "unknown"; 11 | 12 | static { 13 | try { 14 | Properties props = new Properties(); 15 | props.load(Version.class.getResourceAsStream("/kafka-connect-redshift-version.properties")); 16 | version = props.getProperty("version", version).trim(); 17 | } catch (Exception e) { 18 | log.warn("Error while loading version:", e); 19 | } 20 | } 21 | 22 | public static String getVersion() { 23 | return version; 24 | } 25 | } 26 | -------------------------------------------------------------------------------- /src/main/resources/kafka-connect-redshift-version.properties: -------------------------------------------------------------------------------- 1 | version=${project.version} 2 | --------------------------------------------------------------------------------