Skip to content

[SPARK-30558][SQL] Avoid rebuilding AvroOptions per each partition #27272

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

Closed
MaxGekk wants to merge 1 commit into from
Closed

[SPARK-30558][SQL] Avoid rebuilding AvroOptions per each partition #27272

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 2 additions & 3 deletions external/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,19 +46,18 @@ import org.apache.spark.util.SerializableConfiguration
* @param dataSchema Schema of AVRO files.
* @param readDataSchema Required data schema of AVRO files.
* @param partitionSchema Schema of partitions.
* @param options Options for parsing AVRO files.
* @param parsedOptions Options for parsing AVRO files.
*/
case class AvroPartitionReaderFactory(
sqlConf: SQLConf,
broadcastedConf: Broadcast[SerializableConfiguration],
dataSchema: StructType,
readDataSchema: StructType,
partitionSchema: StructType,
options: Map[String, String]) extends FilePartitionReaderFactory with Logging {
parsedOptions: AvroOptions) extends FilePartitionReaderFactory with Logging {

override def buildReader(partitionedFile: PartitionedFile): PartitionReader[InternalRow] = {
val conf = broadcastedConf.value.value
val parsedOptions = new AvroOptions(options, conf)
val userProvidedSchema = parsedOptions.schema.map(new Schema.Parser().parse)

if (parsedOptions.ignoreExtension || partitionedFile.filePath.endsWith(".avro")) {
Expand Down
4 changes: 3 additions & 1 deletion external/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ import scala.collection.JavaConverters._
import org.apache.hadoop.fs.Path

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.avro.AvroOptions
import org.apache.spark.sql.catalyst.expressions.Expression
import org.apache.spark.sql.connector.read.PartitionReaderFactory
import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex
Expand All @@ -45,10 +46,11 @@ case class AvroScan(
val hadoopConf = sparkSession.sessionState.newHadoopConfWithOptions(caseSensitiveMap)
val broadcastedConf = sparkSession.sparkContext.broadcast(
new SerializableConfiguration(hadoopConf))
val parsedOptions = new AvroOptions(caseSensitiveMap, hadoopConf)
// The partition values are already truncated in `FileScan.partitions`.
// We should use `readPartitionSchema` as the partition schema here.
AvroPartitionReaderFactory(sparkSession.sessionState.conf, broadcastedConf,
dataSchema, readDataSchema, readPartitionSchema, caseSensitiveMap)
dataSchema, readDataSchema, readPartitionSchema, parsedOptions)
}

override def withPartitionFilters(partitionFilters: Seq[Expression]): FileScan =
Expand Down