From 1a49496b4a9df40c74739fc0fb8a21c88a477075 Mon Sep 17 00:00:00 2001 From: Cheng Lian <lian@databricks.com> Date: Mon, 2 Mar 2015 16:18:00 -0800 Subject: [PATCH] [SPARK-6082] [SQL] Provides better error message for malformed rows when caching tables Constructs like Hive `TRANSFORM` may generate malformed rows (via badly authored external scripts for example). I'm a bit hesitant to have this feature, since it introduces per-tuple cost when caching tables. However, considering caching tables is usually a one-time cost, this is probably worth having. <!-- Reviewable:start --> [<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/4842) <!-- Reviewable:end --> Author: Cheng Lian <lian@databricks.com> Closes #4842 from liancheng/spark-6082 and squashes the following commits: b05dbff [Cheng Lian] Provides better error message for malformed rows when caching tables --- .../sql/columnar/InMemoryColumnarTableScan.scala | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/columnar/InMemoryColumnarTableScan.scala b/sql/core/src/main/scala/org/apache/spark/sql/columnar/InMemoryColumnarTableScan.scala index 11d5943fb4..8944a32bc3 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/columnar/InMemoryColumnarTableScan.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/columnar/InMemoryColumnarTableScan.scala @@ -119,6 +119,17 @@ private[sql] case class InMemoryRelation( var rowCount = 0 while (rowIterator.hasNext && rowCount < batchSize) { val row = rowIterator.next() + + // Added for SPARK-6082. This assertion can be useful for scenarios when something + // like Hive TRANSFORM is used. The external data generation script used in TRANSFORM + // may result malformed rows, causing ArrayIndexOutOfBoundsException, which is somewhat + // hard to decipher. + assert( + row.size == columnBuilders.size, + s"""Row column number mismatch, expected ${output.size} columns, but got ${row.size}. + |Row content: $row + """.stripMargin) + var i = 0 while (i < row.length) { columnBuilders(i).appendFrom(row, i) -- GitLab