This is an automated email from the ASF dual-hosted git repository.
yamamuro pushed a commit to branch branch-3.0
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.0 by this push:
new 782ab8e [SPARK-33091][SQL] Avoid using map instead of foreach to
avoid potential side effect at callers of OrcUtils.readCatalystSchema
782ab8e is described below
commit 782ab8e244252696c50b4b432d07a56c374b8680
Author: HyukjinKwon <[email protected]>
AuthorDate: Thu Oct 8 16:29:15 2020 +0900
[SPARK-33091][SQL] Avoid using map instead of foreach to avoid potential
side effect at callers of OrcUtils.readCatalystSchema
### What changes were proposed in this pull request?
This is a kind of a followup of SPARK-32646. New JIRA was filed to control
the fixed versions properly.
When you use `map`, it might be lazily evaluated and not executed. To avoid
this, we should better use `foreach`. See also SPARK-16694. Current codes look
not causing any bug for now but it should be best to fix to avoid potential
issues.
### Why are the changes needed?
To avoid potential issues from `map` being lazy and not executed.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Ran related tests. CI in this PR should verify.
Closes #29974 from HyukjinKwon/SPARK-32646.
Authored-by: HyukjinKwon <[email protected]>
Signed-off-by: Takeshi Yamamuro <[email protected]>
(cherry picked from commit 5effa8ea261ba59214afedc2853d1b248b330ca6)
Signed-off-by: Takeshi Yamamuro <[email protected]>
---
.../org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala | 2 +-
.../sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
index 69badb4..c540007 100644
---
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
+++
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
@@ -185,7 +185,7 @@ class OrcFileFormat
} else {
// ORC predicate pushdown
if (orcFilterPushDown) {
- OrcUtils.readCatalystSchema(filePath, conf, ignoreCorruptFiles).map
{ fileSchema =>
+ OrcUtils.readCatalystSchema(filePath, conf,
ignoreCorruptFiles).foreach { fileSchema =>
OrcFilters.createFilter(fileSchema, filters).foreach { f =>
OrcInputFormat.setSearchArgument(conf, f, fileSchema.fieldNames)
}
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala
index 1f38128..b0ddee0 100644
---
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala
+++
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala
@@ -69,7 +69,7 @@ case class OrcPartitionReaderFactory(
private def pushDownPredicates(filePath: Path, conf: Configuration): Unit = {
if (orcFilterPushDown) {
- OrcUtils.readCatalystSchema(filePath, conf, ignoreCorruptFiles).map {
fileSchema =>
+ OrcUtils.readCatalystSchema(filePath, conf, ignoreCorruptFiles).foreach
{ fileSchema =>
OrcFilters.createFilter(fileSchema, filters).foreach { f =>
OrcInputFormat.setSearchArgument(conf, f, fileSchema.fieldNames)
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
