Repository: spark Updated Branches: refs/heads/master d3cdf9128 -> 73da9c26b
[SPARK-3771][SQL] AppendingParquetOutputFormat should use reflection to prevent from breaking binary-compatibility. Original problem is [SPARK-3764](https://issues.apache.org/jira/browse/SPARK-3764). `AppendingParquetOutputFormat` uses a binary-incompatible method `context.getTaskAttemptID`. This causes binary-incompatible of Spark itself, i.e. if Spark itself is built against hadoop-1, the artifact is for only hadoop-1, and vice versa. Author: Takuya UESHIN <[email protected]> Closes #2638 from ueshin/issues/SPARK-3771 and squashes the following commits: efd3784 [Takuya UESHIN] Add a comment to explain the reason to use reflection. ec213c1 [Takuya UESHIN] Use reflection to prevent breaking binary-compatibility. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/73da9c26 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/73da9c26 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/73da9c26 Branch: refs/heads/master Commit: 73da9c26b0e2e8bf0ab055906211727a7097c963 Parents: d3cdf91 Author: Takuya UESHIN <[email protected]> Authored: Mon Oct 13 13:43:41 2014 -0700 Committer: Michael Armbrust <[email protected]> Committed: Mon Oct 13 13:43:41 2014 -0700 ---------------------------------------------------------------------- .../apache/spark/sql/parquet/ParquetTableOperations.scala | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/73da9c26/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala index ffb7323..1f4237d 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala @@ -331,13 +331,21 @@ private[parquet] class AppendingParquetOutputFormat(offset: Int) // override to choose output filename so not overwrite existing ones override def getDefaultWorkFile(context: TaskAttemptContext, extension: String): Path = { - val taskId: TaskID = context.getTaskAttemptID.getTaskID + val taskId: TaskID = getTaskAttemptID(context).getTaskID val partition: Int = taskId.getId val filename = s"part-r-${partition + offset}.parquet" val committer: FileOutputCommitter = getOutputCommitter(context).asInstanceOf[FileOutputCommitter] new Path(committer.getWorkPath, filename) } + + // The TaskAttemptContext is a class in hadoop-1 but is an interface in hadoop-2. + // The signatures of the method TaskAttemptContext.getTaskAttemptID for the both versions + // are the same, so the method calls are source-compatible but NOT binary-compatible because + // the opcode of method call for class is INVOKEVIRTUAL and for interface is INVOKEINTERFACE. + private def getTaskAttemptID(context: TaskAttemptContext): TaskAttemptID = { + context.getClass.getMethod("getTaskAttemptID").invoke(context).asInstanceOf[TaskAttemptID] + } } /** --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
