Feature/1416 S3 input/output for Enceladus on EMR (S2.4, H2.8.5) #1483
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -52,8 +52,8 @@ trait ConformanceExecution extends CommonJobExecution { | |
| cmd: ConformanceConfigParser[T], | ||
| fsUtils: FileSystemVersionUtils, | ||
| spark: SparkSession): Unit = { | ||
| //val stdDirSize = fsUtils.getDirectorySize(preparationResult.pathCfg.standardizationPath) | ||
| //preparationResult.performance.startMeasurement(stdDirSize) // TODO fix for s3 [ref issue #1416] | ||
|
|
||
| log.info(s"standardization path: ${preparationResult.pathCfg.standardizationPath}") | ||
| log.info(s"publish path: ${preparationResult.pathCfg.publishPath}") | ||
|
|
@@ -67,11 +67,13 @@ trait ConformanceExecution extends CommonJobExecution { | |
| } | ||
|
|
||
| // InputPath is standardizationPath in the combined job | ||
| // TODO fix for s3 [ref issue #1416] | ||
| // spark.enableControlMeasuresTracking(s"${preparationResult.pathCfg.standardizationPath}/_INFO") | ||
| // .setControlMeasuresWorkflow(sourceId.toString) | ||
|
|
||
| // Enable control framework performance optimization for pipeline-like jobs | ||
| // TODO fix for s3 [ref issue #1416] | ||
| //Atum.setAllowUnpersistOldDatasets(true) | ||
|
|
||
| // Enable Menas plugin for Control Framework | ||
| MenasPlugin.enableMenas( | ||
|
|
@@ -105,16 +107,16 @@ trait ConformanceExecution extends CommonJobExecution { | |
| implicit val featureSwitcher: FeatureSwitches = conformanceReader.readFeatureSwitches() | ||
|
|
||
| Try { | ||
| // handleControlInfoValidation() // TODO fix for s3 [ref issue #1416] | ||
| DynamicInterpreter.interpret(preparationResult.dataset, inputData) | ||
| } match { | ||
| case Failure(e: ValidationException) => | ||
| // AtumImplicits.SparkSessionWrapper(spark).setControlMeasurementError(sourceId.toString, e.getMessage, e.techDetails) // TODO fix for s3 [ref issue #1416] | ||
| throw e | ||
| case Failure(NonFatal(e)) => | ||
| val sw = new StringWriter | ||
| e.printStackTrace(new PrintWriter(sw)) | ||
| // AtumImplicits.SparkSessionWrapper(spark).setControlMeasurementError(sourceId.toString, e.getMessage, sw.toString) // TODO fix for s3 [ref issue #1416] | ||
| throw e | ||
| case Success(conformedDF) => | ||
| if (SchemaUtils.fieldExists(Constants.EnceladusRecordId, conformedDF.schema)) { | ||
|
|
@@ -134,43 +136,48 @@ trait ConformanceExecution extends CommonJobExecution { | |
| fsUtils: FileSystemVersionUtils): Unit = { | ||
| val cmdLineArgs: String = args.mkString(" ") | ||
|
|
||
| // TODO fix for s3 [ref issue #1416] | ||
| // PerformanceMetricTools.addJobInfoToAtumMetadata( | ||
| // "conform", | ||
| // preparationResult.pathCfg.standardizationPath, | ||
| // preparationResult.pathCfg.publishPath, | ||
| // menasCredentials.username, cmdLineArgs | ||
| // ) | ||
|
|
||
| val withPartCols = result | ||
| .withColumnIfDoesNotExist(InfoDateColumn, to_date(lit(cmd.reportDate), ReportDateFormat)) | ||
| .withColumnIfDoesNotExist(InfoDateColumnString, lit(cmd.reportDate)) | ||
| .withColumnIfDoesNotExist(InfoVersionColumn, lit(preparationResult.reportVersion)) | ||
|
|
||
| // TODO fix for s3 [ref issue #1416] | ||
| val recordCount = 100 | ||
|
There was a problem hiding this comment. -1 would be better if there is no check for it to be > 0. Because 100 seems like a valid value. There was a problem hiding this comment. Thanks, took your advice (=> -1; #1416 (comment)) |
||
| // val recordCount = result.lastCheckpointRowCount match { | ||
| // case None => withPartCols.count | ||
| // case Some(p) => p | ||
| // } | ||
| if (recordCount == 0) { | ||
| handleEmptyOutput(SourcePhase.Conformance) | ||
| } | ||
|
|
||
| // ensure the whole path but version exists | ||
| //fsUtils.createAllButLastSubDir(preparationResult.pathCfg.publishPath) // TODO fix for s3 [ref issue #1416] | ||
|
|
||
| withPartCols.write.parquet(preparationResult.pathCfg.publishPath) | ||
|
|
||
| // TODO fix for s3 [ref issue #1416] | ||
| //val publishDirSize = fsUtils.getDirectorySize(preparationResult.pathCfg.publishPath) | ||
| // preparationResult.performance.finishMeasurement(publishDirSize, recordCount) | ||
| // PerformanceMetricTools.addPerformanceMetricsToAtumMetadata( | ||
| // spark, | ||
| // "conform", | ||
| // preparationResult.pathCfg.standardizationPath, | ||
| // preparationResult.pathCfg.publishPath, | ||
| // menasCredentials.username, cmdLineArgs | ||
| // ) | ||
|
|
||
| // TODO fix for s3 [ref issue #1416] | ||
| //withPartCols.writeInfoFile(preparationResult.pathCfg.publishPath) | ||
| //writePerformanceMetrics(preparationResult.performance, cmd) | ||
|
|
||
| if (conformanceReader.isAutocleanStdFolderEnabled()) { | ||
|
There was a problem hiding this comment. I think this should also be commented out |
||
| fsUtils.deleteDirectoryRecursively(preparationResult.pathCfg.standardizationPath) | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Note that the SDK is not being used, yet as of now, but the support is now added because the usage is expected based on the S3 PoC.