Egdm 3374 - Unable to update customer data with Data Pull.

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html)
 
+## [0.1.71] - 2023-09-12
+Fixed bug of Unable to update customer data with Data Pull.
+
+## [0.1.70] - 2023-09-04
+Fixed bug of Jobs fails on duplicate subnet id
+
 ## [0.1.69] - 2023-06-07
 we have added partitions for every batch we write to s3 to avoid file already existing errors. and added logging for run job flow request response.
 

api/src/main/java/com/homeaway/datapullclient/process/DataPullTask.java

@@ -397,7 +397,7 @@ private JobFlowInstancesConfig getJobFlowInstancesConfig(EMRProperties emrProper
  .withInstanceTypeConfigs(workerInstanceTypeConfig)
  .withTargetOnDemandCapacity(count);
 
- List<String> subnetIds= new ArrayList<>();
+ Set<String> subnetIds= new HashSet<>();
 
  subnetIds.addAll(toList(new String[]{dataPullProperties.getApplicationSubnet1(),
  dataPullProperties.getApplicationSubnet2()}));

core/src/main/scala/core/DataFrameFromTo.scala

@@ -1277,7 +1277,7 @@ class DataFrameFromTo(appConfig: AppConfig, pipeline: String) extends Serializab
  // create the statement, and run the command
  val statement = connection.createStatement()
 
- if (colType != null) {
+ if (colType.isDefined) {
  resultSet= statement.executeQuery(sql_command)
 
  }