Skip to content

chore: cleanup unused vars #232

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

Merged
merged 3 commits into from
Jan 17, 2025
Merged

chore: cleanup unused vars #232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
721ec30
chore: cleanup unused vars
tchow-zlai Jan 16, 2025
9ddaaf8
update UT
tchow-zlai Jan 16, 2025
1e3e537
refactor
tchow-zlai Jan 17, 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
2 changes: 1 addition & 1 deletion cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GCSFormat.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
import org.apache.spark.sql.execution.FileSourceScanExec
import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex

case class GCS(project: String, sourceUri: String, fileFormat: String) extends Format {
case class GCS(sourceUri: String, fileFormat: String) extends Format {

override def name: String = fileFormat

Expand Down
13 changes: 8 additions & 5 deletions cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GcpFormatProvider.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ import com.google.cloud.bigquery.connector.common.BigQueryUtil
import com.google.cloud.spark.bigquery.repackaged.com.google.cloud.bigquery.TableId
import org.apache.spark.sql.SparkSession

import scala.jdk.CollectionConverters._

case class GcpFormatProvider(sparkSession: SparkSession) extends FormatProvider {

/**
Expand All @@ -30,8 +32,8 @@ case class GcpFormatProvider(sparkSession: SparkSession) extends FormatProvider

override def resolveTableName(tableName: String): String =
format(tableName) match {
case GCS(_, uri, _) => uri
case _ => tableName
case GCS(uri, _) => uri
case _ => tableName
}

override def readFormat(tableName: String): Format = format(tableName)
Expand Down Expand Up @@ -66,11 +68,12 @@ case class GcpFormatProvider(sparkSession: SparkSession) extends FormatProvider
val uri = Option(externalTable.getHivePartitioningOptions)
.map(_.getSourceUriPrefix)
.getOrElse {
val uris = externalTable.getSourceUris
val uris = externalTable.getSourceUris.asScala
require(uris.size == 1, s"External table ${table} can be backed by only one URI.")
uris.get(0).replaceAll("/\\*\\.parquet$", "")
uris.head.replaceAll("/\\*\\.parquet$", "")
}
GCS(table.getTableId.getProject, uri, formatOptions.getType)

GCS(uri, formatOptions.getType)

case _: StandardTableDefinition =>
BigQueryFormat(table.getTableId.getProject, Map.empty)
Expand Down
6 changes: 3 additions & 3 deletions cloud_gcp/src/test/scala/ai/chronon/integrations/cloud_gcp/GCSFormatTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ class GCSFormatTest extends AnyFlatSpec {

val df = spark.createDataFrame(testData).toDF("ds", "first", "second")
df.write.partitionBy("ds").format("parquet").mode(SaveMode.Overwrite).save(dir.getAbsolutePath)
val gcsFormat = GCS(project = "test-project", sourceUri = dir.getAbsolutePath, fileFormat = "parquet")
val gcsFormat = GCS(sourceUri = dir.getAbsolutePath, fileFormat = "parquet")
val partitions = gcsFormat.partitions("unused_table")(spark)

assertEquals(Set(Map("ds" -> "20241223"), Map("ds" -> "20241224"), Map("ds" -> "20241225")), partitions.toSet)
Expand All @@ -53,7 +53,7 @@ class GCSFormatTest extends AnyFlatSpec {

val df = spark.createDataFrame(testData).toDF("ds", "first", "second")
df.write.format("parquet").mode(SaveMode.Overwrite).save(dir.getAbsolutePath)
val gcsFormat = GCS(project = "test-project", sourceUri = dir.getAbsolutePath, fileFormat = "parquet")
val gcsFormat = GCS(sourceUri = dir.getAbsolutePath, fileFormat = "parquet")
val partitions = gcsFormat.partitions("unused_table")(spark)

assertEquals(Set.empty, partitions.toSet)
Expand Down Expand Up @@ -83,7 +83,7 @@ class GCSFormatTest extends AnyFlatSpec {
.toDF("ds", "first", "second")
.select(to_date(col("ds"), "yyyy-MM-dd").as("ds"), col("first"), col("second"))
df.write.format("parquet").partitionBy("ds").mode(SaveMode.Overwrite).save(dir.getAbsolutePath)
val gcsFormat = GCS(project = "test-project", sourceUri = dir.getAbsolutePath, fileFormat = "parquet")
val gcsFormat = GCS(sourceUri = dir.getAbsolutePath, fileFormat = "parquet")
val partitions = gcsFormat.partitions("unused_table")(spark)

assertEquals(Set(Map("ds" -> "2024-12-23"), Map("ds" -> "2024-12-24"), Map("ds" -> "2024-12-25")), partitions.toSet)
Expand Down
1 change: 0 additions & 1 deletion cloud_gcp/src/test/scala/ai/chronon/integrations/cloud_gcp/GcpFormatProviderTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,6 @@ class GcpFormatProviderTest extends AnyFlatSpec with MockitoSugar {

val gcsFormat = gcpFormatProvider.getFormat(mockTable).asInstanceOf[GCS]
assert(gcsFormat.sourceUri == tableName)
assert(gcsFormat.project == "project")
assert(gcsFormat.fileFormat == "PARQUET")
}
}
Loading