Skip to content

[SPARK-32380][SQL] Fixing access of HBase table via Hive from Spark #38516

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
wants to merge 1 commit into from
Closed

[SPARK-32380][SQL] Fixing access of HBase table via Hive from Spark #38516

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
14 changes: 12 additions & 2 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,16 @@ class HadoopTableReader(
}
}

/**
* True if the new org.apache.hadoop.mapreduce.InputFormat is implemented (except
* HiveHBaseTableInputFormat where although the new interface is implemented by base HBase class
* the table inicialization in the Hive layer only happens via the old interface methods -
* for more details see SPARK-32380).
*/
private def compatibleWithNewHadoopRDD(inputClass: Class[_ <: oldInputClass[_, _]]): Boolean =
classOf[newInputClass[_, _]].isAssignableFrom(inputClass) &&
!inputClass.getName.equalsIgnoreCase("org.apache.hadoop.hive.hbase.HiveHBaseTableInputFormat")

/**
* The entry of creating a RDD.
* [SPARK-26630] Using which HadoopRDD will be decided by the input format of tables.
Expand All @@ -307,7 +317,7 @@ class HadoopTableReader(
*/
private def createHadoopRDD(localTableDesc: TableDesc, inputPathStr: String): RDD[Writable] = {
val inputFormatClazz = localTableDesc.getInputFileFormatClass
if (classOf[newInputClass[_, _]].isAssignableFrom(inputFormatClazz)) {
if (compatibleWithNewHadoopRDD(inputFormatClazz)) {
createNewHadoopRDD(localTableDesc, inputPathStr)
} else {
createOldHadoopRDD(localTableDesc, inputPathStr)
Expand All @@ -316,7 +326,7 @@ class HadoopTableReader(

private def createHadoopRDD(partitionDesc: PartitionDesc, inputPathStr: String): RDD[Writable] = {
val inputFormatClazz = partitionDesc.getInputFileFormatClass
if (classOf[newInputClass[_, _]].isAssignableFrom(inputFormatClazz)) {
if (compatibleWithNewHadoopRDD(inputFormatClazz)) {
createNewHadoopRDD(partitionDesc, inputPathStr)
} else {
createOldHadoopRDD(partitionDesc, inputPathStr)
Expand Down