Skip to content

Use MetadataLogFileIndex to get latest version in AddDateVersionTransformer #308

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 2 commits into
base: develop
Choose a base branch
from
Draft

Use MetadataLogFileIndex to get latest version in AddDateVersionTransformer #308

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ca0e362
Use MetadataLogFileIndex to get latest version in AddDateVersionTrans…
jozefbakus May 19, 2025
30b931a
Fix
jozefbakus May 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion ...lity-api/src/main/scala/za/co/absa/hyperdrive/compatibility/api/CompatibleSparkUtil.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,10 @@ package za.co.absa.hyperdrive.compatibility.api

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.streaming.MetadataLogFileIndex
import org.apache.spark.sql.types.StructType

trait CompatibleSparkUtil {
def createMetadataLogFileIndex(spark: SparkSession, destination: String): MetadataLogFileIndex
def createMetadataLogFileIndex(spark: SparkSession, destination: String, userSpecifiedSchema: Option[StructType]): MetadataLogFileIndex
def hasMetadata(spark: SparkSession, destination: String): Boolean
def jsonStringToObject(jsonString: String): Object
def objectToJsonString(obj: Object): Option[String]
Expand Down
5 changes: 3 additions & 2 deletions ...main/scala/za/co/absa/hyperdrive/compatibility/provider/CompatibleSparkUtilProvider.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,12 +17,13 @@ package za.co.absa.hyperdrive.compatibility.provider

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.streaming.MetadataLogFileIndex
import org.apache.spark.sql.types.StructType
import za.co.absa.hyperdrive.compatibility.api.CompatibleSparkUtil
import za.co.absa.hyperdrive.compatibility.impl.SparkUtil

object CompatibleSparkUtilProvider extends CompatibleSparkUtil {
def createMetadataLogFileIndex(spark: SparkSession, destination: String): MetadataLogFileIndex =
SparkUtil.createMetadataLogFileIndex(spark, destination)
def createMetadataLogFileIndex(spark: SparkSession, destination: String, userSpecifiedSchema: Option[StructType]): MetadataLogFileIndex =
SparkUtil.createMetadataLogFileIndex(spark, destination, userSpecifiedSchema)

def hasMetadata(spark: SparkSession, destination: String): Boolean =
SparkUtil.hasMetadata(spark, destination)
Expand Down
5 changes: 3 additions & 2 deletions ...atibility_spark-3/src/main/scala/za/co/absa/hyperdrive/compatibility/impl/SparkUtil.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,15 +20,16 @@ import org.apache.avro.util.internal.JacksonUtils
import org.apache.hadoop.fs.Path
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.streaming.{FileStreamSink, MetadataLogFileIndex}
import org.apache.spark.sql.types.StructType
import za.co.absa.hyperdrive.compatibility.api.CompatibleSparkUtil

import java.io.ByteArrayOutputStream

object SparkUtil extends CompatibleSparkUtil {
private lazy val objectMapper = new ObjectMapper()

override def createMetadataLogFileIndex(spark: SparkSession, destination: String): MetadataLogFileIndex =
new MetadataLogFileIndex(spark, new Path(destination), Map.empty, None)
override def createMetadataLogFileIndex(spark: SparkSession, destination: String, userSpecifiedSchema: Option[StructType]): MetadataLogFileIndex =
new MetadataLogFileIndex(spark, new Path(destination), Map.empty, userSpecifiedSchema)

override def hasMetadata(spark: SparkSession, destination: String): Boolean =
FileStreamSink.hasMetadata(Seq(destination), spark.sparkContext.hadoopConfiguration, spark.sessionState.conf)
Expand Down
28 changes: 19 additions & 9 deletions ...yperdrive/ingestor/implementation/transformer/dateversion/AddDateVersionTransformer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,16 +16,21 @@
package za.co.absa.hyperdrive.ingestor.implementation.transformer.dateversion

import org.apache.commons.configuration2.Configuration
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.execution.streaming.MetadataLogFileIndex
import org.slf4j.LoggerFactory
import org.apache.spark.sql.functions.{lit, to_date}
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.{DataFrame, SparkSession}
import za.co.absa.hyperdrive.compatibility.provider.CompatibleSparkUtilProvider
import za.co.absa.hyperdrive.ingestor.api.transformer.{StreamTransformer, StreamTransformerFactory}
import za.co.absa.hyperdrive.ingestor.api.utils.ConfigUtils.getOrThrow
import za.co.absa.hyperdrive.ingestor.implementation.writer.parquet.ParquetStreamWriter
import org.apache.spark.sql.types.{DateType, StructField}

import java.time.LocalDate
import java.time.format.DateTimeFormatter
import org.apache.spark.sql.types._

private[transformer] class AddDateVersionTransformer(val reportDate: String, val destination: String) extends StreamTransformer {

Expand All @@ -44,22 +49,27 @@ private[transformer] class AddDateVersionTransformer(val reportDate: String, val
if (noCommittedParquetFilesExist(spark)) {
initialVersion
} else {
import spark.implicits._
val df = spark.read.parquet(destination)
val versions = df.select(df(ColumnVersion))
.filter(df(ColumnDate) === lit(reportDate))
.distinct()
.as[Int]
.collect().toList

val versions = getVersions(spark, ColumnDate, ColumnVersion, reportDate)
if (versions.nonEmpty) versions.max + 1 else initialVersion
}
}

private def noCommittedParquetFilesExist(spark: SparkSession): Boolean = {
val fileCatalog = CompatibleSparkUtilProvider.createMetadataLogFileIndex(spark, destination)
val fileCatalog = CompatibleSparkUtilProvider.createMetadataLogFileIndex(spark, destination, None)
!CompatibleSparkUtilProvider.hasMetadata(spark, destination) || fileCatalog.allFiles().isEmpty
}

private def getVersions(spark: SparkSession, ColumnDate: String, ColumnVersion: String, reportDate: String): Seq[Int] = {
val fileCatalog: MetadataLogFileIndex = CompatibleSparkUtilProvider.createMetadataLogFileIndex(spark, destination, Some(StructType(Seq(
StructField(ColumnDate, StringType, nullable = true),
StructField(ColumnVersion, IntegerType, nullable = true)
))))

fileCatalog.partitionSpec().partitions.map { partition =>
val row: InternalRow = partition.values
(row.getString(0), row.getInt(1))
}.filter { case (date, _) => date == reportDate }.map { case (_, version) => version }.toList
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Formatting could be clearer (.map and .toList on a new line)

}
}

object AddDateVersionTransformer extends StreamTransformerFactory with AddDateVersionTransformerAttributes {
Expand Down
Loading