[
https://issues.apache.org/jira/browse/SPARK-35252?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
lynn updated SPARK-35252:
-------------------------
Description:
The codes of "MyPartitionReaderFactory" of
{code:java}
// Implemention Class
package com.lynn.spark.sql.v2
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.connector.read.{InputPartition, PartitionReader,
PartitionReaderFactory}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.vectorized.ColumnarBatch
case class MyPartitionReaderFactory(sqlConf: SQLConf,
dataSchema: StructType,
readSchema: StructType)
extends PartitionReaderFactory with Logging {
def batchSize = sqlConf.getConf("spark.sql.my.vectorized.batch.size")
override def createReader(partition: InputPartition):
PartitionReader[InternalRow] = {
MyRowReader(batchSize, dataSchema, readSchema)
}
override def createColumnarReader(partition: InputPartition):
PartitionReader[ColumnarBatch] = {
if(!supportColumnarReads(partition))
throw new UnsupportedOperationException("Cannot create columnar reader.")
//TODO: delete this line
println(sqlConf.getAllConfs)
MyColumnReader(batchSize, dataSchema, readSchema)
}
override def supportColumnarReads(partition: InputPartition) = true
}
{code}
was:
The codes of
{code:java}
// Implemention Class
package com.lynn.spark.sql.v2
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.connector.read.{InputPartition, PartitionReader,
PartitionReaderFactory}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.vectorized.ColumnarBatch
case class MyPartitionReaderFactory(sqlConf: SQLConf,
dataSchema: StructType,
readSchema: StructType)
extends PartitionReaderFactory with Logging {
def batchSize = sqlConf.getConf("spark.sql.my.vectorized.batch.size")
override def createReader(partition: InputPartition):
PartitionReader[InternalRow] = {
MyRowReader(batchSize, dataSchema, readSchema)
}
override def createColumnarReader(partition: InputPartition):
PartitionReader[ColumnarBatch] = {
if(!supportColumnarReads(partition))
throw new UnsupportedOperationException("Cannot create columnar reader.")
//TODO: delete this line
println(sqlConf.getAllConfs)
MyColumnReader(batchSize, dataSchema, readSchema)
}
override def supportColumnarReads(partition: InputPartition) = true
}
{code}
> PartitionReaderFactory's Implemention Class of DataSourceV2 sqlConf parameter
> is null
> -------------------------------------------------------------------------------------
>
> Key: SPARK-35252
> URL: https://issues.apache.org/jira/browse/SPARK-35252
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.0.2
> Reporter: lynn
> Priority: Major
>
> The codes of "MyPartitionReaderFactory" of
> {code:java}
> // Implemention Class
> package com.lynn.spark.sql.v2
> import org.apache.spark.internal.Logging
> import org.apache.spark.sql.catalyst.InternalRow
> import org.apache.spark.sql.connector.read.{InputPartition, PartitionReader,
> PartitionReaderFactory}
> import org.apache.spark.sql.internal.SQLConf
> import org.apache.spark.sql.types.StructType
> import org.apache.spark.sql.vectorized.ColumnarBatch
> case class MyPartitionReaderFactory(sqlConf: SQLConf,
> dataSchema: StructType,
> readSchema: StructType)
> extends PartitionReaderFactory with Logging {
> def batchSize = sqlConf.getConf("spark.sql.my.vectorized.batch.size")
> override def createReader(partition: InputPartition):
> PartitionReader[InternalRow] = {
> MyRowReader(batchSize, dataSchema, readSchema)
> }
> override def createColumnarReader(partition: InputPartition):
> PartitionReader[ColumnarBatch] = {
> if(!supportColumnarReads(partition))
> throw new UnsupportedOperationException("Cannot create columnar
> reader.")
> //TODO: delete this line
> println(sqlConf.getAllConfs)
> MyColumnReader(batchSize, dataSchema, readSchema)
> }
> override def supportColumnarReads(partition: InputPartition) = true
> }
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
