Project split #17
There are no files selected for viewing
This file contains hidden or 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 hidden or 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 |
|---|---|---|
| @@ -0,0 +1,71 @@ | ||
| /** Copyright 2020 ABSA Group Limited | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on | ||
| * an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the | ||
| * specific language governing permissions and limitations under the License. | ||
| */ | ||
|
|
||
| package za.co.absa | ||
|
|
||
| import za.co.absa.hash.HashUtils.HASH_COLUMN_NAME | ||
| import hash.HashUtils | ||
| import org.apache.spark.sql.{DataFrame, SparkSession} | ||
| import org.slf4j.{Logger, LoggerFactory} | ||
|
|
||
| /** Comparator object that compares two parquet files and creates metrics | ||
| */ | ||
| object Comparator { | ||
| private val logger: Logger = LoggerFactory.getLogger(Comparator.getClass) | ||
|
|
||
| /** Compare two DataFrames and return diff rows | ||
| * | ||
| * @param dataA | ||
| * A DataFrame whole data | ||
| * @param dataB | ||
| * B DataFrame whole data | ||
| * @param excludedColumns | ||
| * columns to exclude from comparison | ||
| * @param spark | ||
| * SparkSession | ||
| * @return | ||
| * Tuple of (diffA, diffB) DataFrames containing rows unique to each dataset | ||
| */ | ||
| def compare( | ||
| dataA: DataFrame, | ||
| dataB: DataFrame, | ||
| excludedColumns: Seq[String] = Seq.empty | ||
| )(implicit spark: SparkSession): (DataFrame, DataFrame) = { | ||
| // Apply column exclusion | ||
| val filteredDataA = DatasetComparisonHelper.exclude(dataA, excludedColumns, "A") | ||
| val filteredDataB = DatasetComparisonHelper.exclude(dataB, excludedColumns, "B") | ||
|
|
||
| val dfWithHashA: DataFrame = HashUtils.createHashColumn(filteredDataA) | ||
| logger.info("Hash for A created") | ||
|
|
||
| val dfWithHashB: DataFrame = HashUtils.createHashColumn(filteredDataB) | ||
| logger.info("Hash for B created") | ||
|
|
||
| // select non matching hashs | ||
| logger.info("Getting diff hashes, A except B") | ||
| val diffHashA: DataFrame = dfWithHashA.select(HASH_COLUMN_NAME).exceptAll(dfWithHashB.select(HASH_COLUMN_NAME)) | ||
| logger.info("Getting diff hashes, B except A") | ||
| val diffHashB: DataFrame = dfWithHashB.select(HASH_COLUMN_NAME).exceptAll(dfWithHashA.select(HASH_COLUMN_NAME)) | ||
|
|
||
| // join on hash column (get back whole rows) | ||
| logger.info("Getting diff rows for A") | ||
| val distinctDiffA: DataFrame = diffHashA.join(dfWithHashA, Seq(HASH_COLUMN_NAME)).distinct() | ||
| val diffA: DataFrame = diffHashA.join(distinctDiffA, Seq(HASH_COLUMN_NAME)) | ||
|
|
||
| logger.info("Getting diff rows for B") | ||
| val distinctDiffB: DataFrame = diffHashB.join(dfWithHashB, Seq(HASH_COLUMN_NAME)).distinct() | ||
| val diffB: DataFrame = diffHashB.join(distinctDiffB, Seq(HASH_COLUMN_NAME)) | ||
|
|
||
| (diffA, diffB) | ||
| } | ||
|
|
||
| } | ||
This file contains hidden or 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
File renamed without changes.
This file contains hidden or 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 |
|---|---|---|
| @@ -0,0 +1,53 @@ | ||
| /** Copyright 2020 ABSA Group Limited | ||
|
There was a problem hiding this comment. I'm gonna write it here so that we can have a chat based on this: I like the split and the overall structure, making things pretty obvious that one is CLI tool and the other is supposed to be an importable Scala library. However, naming (one of the difficulties of SW engineering, especially in prior-AI era) should be improved in my opinion. The module What about this? Rename:
There was a problem hiding this comment. So:
|
||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on | ||
| * an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the | ||
| * specific language governing permissions and limitations under the License. | ||
| */ | ||
|
|
||
| package za.co.absa.analysis | ||
|
|
||
| /** Result of row-by-row analysis with explicit outcome types. | ||
| */ | ||
| sealed trait AnalysisResult | ||
|
|
||
| object AnalysisResult { | ||
|
|
||
| /** Analysis completed successfully with row-by-row differences. | ||
| * | ||
| * @param diffAToB | ||
| * Differences from dataset A to B | ||
| * @param diffBToA | ||
| * Differences from dataset B to A | ||
| */ | ||
| case class Success(diffAToB: Seq[RowsDiff], diffBToA: Seq[RowsDiff]) extends AnalysisResult | ||
|
|
||
| /** Datasets are identical - no differences to analyze. | ||
| */ | ||
| case object DatasetsIdentical extends AnalysisResult | ||
|
|
||
| /** One dataset has differences but the other doesn't - cannot perform row-by-row matching. | ||
| * | ||
| * @param diffCountA | ||
| * Number of differences in dataset A | ||
| * @param diffCountB | ||
| * Number of differences in dataset B | ||
| */ | ||
| case class OneSidedDifference(diffCountA: Long, diffCountB: Long) extends AnalysisResult | ||
|
|
||
| /** Number of differences exceeds the threshold. | ||
| * | ||
| * @param diffCountA | ||
| * Number of differences in dataset A | ||
| * @param diffCountB | ||
| * Number of differences in dataset B | ||
| * @param threshold | ||
| * The threshold that was exceeded | ||
| */ | ||
| case class ThresholdExceeded(diffCountA: Long, diffCountB: Long, threshold: Int) extends AnalysisResult | ||
| } | ||
File renamed without changes.
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.
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.
These packages must be changed. If we release this into the maven central, there won't be a single nice package containing the dataset comparison library, it will be scattered and living among other absa OSS stuff. I propose this, on high level for all of the files pretty much (I am not a big fan of
analysiseither - too broad of a word):package za.co.absa.datasetcomparisonorpackage za.co.absa.dataset.comparisonDo this for the lib and for the CLI part. Then, under the lib part, it could be:
package za.co.absa.datasetcomparison.coreand under CLI:
package za.co.absa.datasetcomparison.cliThen, further, but this is really optional, it would make sense to split the interfaces and the overall structure into sub-packages:
modelorapianddiffandmetrics- so splitting interfaces, metrics, and diff logic.The cli part is pretty ok in terms of its sub-packages.
Uh oh!
There was an error while loading. Please reload this page.
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.
So in the end of the day, something like this: