Skip to content

[SPARK-19809][SQL][TEST][FOLLOWUP] Move the test case to HiveOrcQuerySuite #19960

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
dongjoon-hyun wants to merge 2 commits into from
Closed

[SPARK-19809][SQL][TEST][FOLLOWUP] Move the test case to HiveOrcQuerySuite #19960

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1d5dd76
[SPARK-19809][SQL][TEST][FOLLOWUP] Move the test case to HiveOrcQuery…
dongjoon-hyun Dec 13, 2017
a32da5f
Move the test case of SPARK-22267, too.
dongjoon-hyun Dec 13, 2017
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
36 changes: 0 additions & 36 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2153,40 +2153,4 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
}
}
}

test("SPARK-22267 Spark SQL incorrectly reads ORC files when column order is different") {
Seq("native", "hive").foreach { orcImpl =>
withSQLConf(SQLConf.ORC_IMPLEMENTATION.key -> orcImpl) {
withTempPath { f =>
val path = f.getCanonicalPath
Seq(1 -> 2).toDF("c1", "c2").write.orc(path)
checkAnswer(spark.read.orc(path), Row(1, 2))

withSQLConf(HiveUtils.CONVERT_METASTORE_ORC.key -> "true") { // default since 2.3.0
withTable("t") {
sql(s"CREATE EXTERNAL TABLE t(c2 INT, c1 INT) STORED AS ORC LOCATION '$path'")
checkAnswer(spark.table("t"), Row(2, 1))
}
}
}
}
}
}

test("SPARK-19809 NullPointerException on zero-size ORC file") {
Seq("native", "hive").foreach { orcImpl =>
withSQLConf(SQLConf.ORC_IMPLEMENTATION.key -> orcImpl) {
withTempPath { dir =>
withTable("spark_19809") {
sql(s"CREATE TABLE spark_19809(a int) STORED AS ORC LOCATION '$dir'")
Files.touch(new File(s"${dir.getCanonicalPath}", "zero.orc"))

withSQLConf(HiveUtils.CONVERT_METASTORE_ORC.key -> "true") { // default since 2.3.0
checkAnswer(sql("SELECT * FROM spark_19809"), Seq.empty)
}
}
}
}
}
}
}
48 changes: 47 additions & 1 deletion sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/HiveOrcQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,11 @@

package org.apache.spark.sql.hive.orc

import org.apache.spark.sql.AnalysisException
import java.io.File

import com.google.common.io.Files

import org.apache.spark.sql.{AnalysisException, Row}
import org.apache.spark.sql.catalyst.catalog.HiveTableRelation
import org.apache.spark.sql.execution.datasources.{HadoopFsRelation, LogicalRelation}
import org.apache.spark.sql.execution.datasources.orc.OrcQueryTest
Expand Down Expand Up @@ -162,4 +166,46 @@ class HiveOrcQuerySuite extends OrcQueryTest with TestHiveSingleton {
}
}
}

// Since Hive 1.2.1 library code path still has this problem, users may hit this
// when spark.sql.hive.convertMetastoreOrc=false. However, after SPARK-22279,
// Apache Spark with the default configuration doesn't hit this bug.
test("SPARK-22267 Spark SQL incorrectly reads ORC files when column order is different") {
Seq("native", "hive").foreach { orcImpl =>
withSQLConf(SQLConf.ORC_IMPLEMENTATION.key -> orcImpl) {
withTempPath { f =>
val path = f.getCanonicalPath
Seq(1 -> 2).toDF("c1", "c2").write.orc(path)
checkAnswer(spark.read.orc(path), Row(1, 2))

withSQLConf(HiveUtils.CONVERT_METASTORE_ORC.key -> "true") { // default since 2.3.0
withTable("t") {
sql(s"CREATE EXTERNAL TABLE t(c2 INT, c1 INT) STORED AS ORC LOCATION '$path'")
checkAnswer(spark.table("t"), Row(2, 1))
}
}
}
}
}
}

// Since Hive 1.2.1 library code path still has this problem, users may hit this
// when spark.sql.hive.convertMetastoreOrc=false. However, after SPARK-22279,
// Apache Spark with the default configuration doesn't hit this bug.
test("SPARK-19809 NullPointerException on zero-size ORC file") {
Seq("native", "hive").foreach { orcImpl =>
withSQLConf(SQLConf.ORC_IMPLEMENTATION.key -> orcImpl) {
withTempPath { dir =>
withTable("spark_19809") {
sql(s"CREATE TABLE spark_19809(a int) STORED AS ORC LOCATION '$dir'")
Files.touch(new File(s"${dir.getCanonicalPath}", "zero.orc"))

withSQLConf(HiveUtils.CONVERT_METASTORE_ORC.key -> "true") { // default since 2.3.0
checkAnswer(spark.table("spark_19809"), Seq.empty)
}
}
}
}
}
}
}