/** * Generated by API Builder - https://www.apibuilder.io * Service version: 2.0.0-dev * User agent: apibuilder app.apibuilder.io/hbc/svc-sundial/2.0.0-dev/java_models */ package com.hbc.svc.sundial.v2.models; public class EmrCommand implements TaskExecutable { /** * The EMR cluster on which to launch the job (aka step) */ private EmrCluster emrCluster; /** * NAme to be assigned to the Job */ private String jobName; /** * the AWS Region */ private String region = "us-east-1"; /** * The spark job's `Main.class` to run */ private String class_; /** * the s3 path to the jar of the job to be run */ private String s3JarPath; /** * options that will be sent to spark as --conf key=value, e.g. `--conf spark.driver.extraJavaOptions=-Denvironment=integration` */ private java.util.List sparkConf; /** * External maven dependencies to include with Spark job */ private java.util.List sparkPackages = new java.util.ArrayList(); /** * command line arguments to be passe to the job's main class */ private java.util.List args; /** * AWS EMR periodically (currently every 5 minutes) zips up all the logs and upload them into S3. This does not work well with sundial's _live logs_. Make use of S3 Logs to visualise in real time job's log on sundial's live logs panel */ private S3LogDetails s3LogDetails; /** * will trigger a s3 dist cp job for every entry in this array, can be used to load data from s3 into HDFS. **requires Hadoop** as application on the cluster */ private java.util.List loadData; /** * will trigger a s3 dist cp job for every entry in this array, can be used to save data from HDFS to s3. **requires Hadoop** as application on the cluster */ private java.util.List saveResults; public EmrCommand() {} }