diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala index e6f7619519e6aff6448813f56eedb56a55f7b9a5..9de75f4c4d08414bd9641028a4525ed050dafaa1 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala @@ -312,7 +312,7 @@ private[spark] object SQLConf { doc = "When true, enable filter pushdown for ORC files.") val HIVE_VERIFY_PARTITION_PATH = booleanConf("spark.sql.hive.verifyPartitionPath", - defaultValue = Some(true), + defaultValue = Some(false), doc = "<TODO>") val HIVE_METASTORE_PARTITION_PRUNING = booleanConf("spark.sql.hive.metastorePartitionPruning", diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala index 017bc2adc103b40b3910f21cb01b9b5ac2650de3..1cc8a93e834119eaf3f889a9aa2f4340059213ef 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala @@ -18,50 +18,54 @@ package org.apache.spark.sql.hive import com.google.common.io.Files +import org.apache.spark.sql.test.SQLTestUtils import org.apache.spark.sql.{QueryTest, _} import org.apache.spark.util.Utils -class QueryPartitionSuite extends QueryTest { +class QueryPartitionSuite extends QueryTest with SQLTestUtils { private lazy val ctx = org.apache.spark.sql.hive.test.TestHive import ctx.implicits._ - import ctx.sql + + protected def _sqlContext = ctx test("SPARK-5068: query data when path doesn't exist"){ - val testData = ctx.sparkContext.parallelize( - (1 to 10).map(i => TestData(i, i.toString))).toDF() - testData.registerTempTable("testData") + withSQLConf((SQLConf.HIVE_VERIFY_PARTITION_PATH.key, "true")) { + val testData = ctx.sparkContext.parallelize( + (1 to 10).map(i => TestData(i, i.toString))).toDF() + testData.registerTempTable("testData") - val tmpDir = Files.createTempDir() - // create the table for test - sql(s"CREATE TABLE table_with_partition(key int,value string) " + - s"PARTITIONED by (ds string) location '${tmpDir.toURI.toString}' ") - sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='1') " + - "SELECT key,value FROM testData") - sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='2') " + - "SELECT key,value FROM testData") - sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='3') " + - "SELECT key,value FROM testData") - sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='4') " + - "SELECT key,value FROM testData") + val tmpDir = Files.createTempDir() + // create the table for test + sql(s"CREATE TABLE table_with_partition(key int,value string) " + + s"PARTITIONED by (ds string) location '${tmpDir.toURI.toString}' ") + sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='1') " + + "SELECT key,value FROM testData") + sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='2') " + + "SELECT key,value FROM testData") + sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='3') " + + "SELECT key,value FROM testData") + sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='4') " + + "SELECT key,value FROM testData") - // test for the exist path - checkAnswer(sql("select key,value from table_with_partition"), - testData.toDF.collect ++ testData.toDF.collect - ++ testData.toDF.collect ++ testData.toDF.collect) + // test for the exist path + checkAnswer(sql("select key,value from table_with_partition"), + testData.toDF.collect ++ testData.toDF.collect + ++ testData.toDF.collect ++ testData.toDF.collect) - // delete the path of one partition - tmpDir.listFiles - .find { f => f.isDirectory && f.getName().startsWith("ds=") } - .foreach { f => Utils.deleteRecursively(f) } + // delete the path of one partition + tmpDir.listFiles + .find { f => f.isDirectory && f.getName().startsWith("ds=") } + .foreach { f => Utils.deleteRecursively(f) } - // test for after delete the path - checkAnswer(sql("select key,value from table_with_partition"), - testData.toDF.collect ++ testData.toDF.collect ++ testData.toDF.collect) + // test for after delete the path + checkAnswer(sql("select key,value from table_with_partition"), + testData.toDF.collect ++ testData.toDF.collect ++ testData.toDF.collect) - sql("DROP TABLE table_with_partition") - sql("DROP TABLE createAndInsertTest") + sql("DROP TABLE table_with_partition") + sql("DROP TABLE createAndInsertTest") + } } }