From 5d9951e01a3462bc081c4b6816c5a8c1e89c6d0f Mon Sep 17 00:00:00 2001 From: jeanlyn Date: Mon, 5 Jan 2015 00:26:14 +0800 Subject: [PATCH 1/3] SPARK-5068: fix bug query data when path doesn't exists --- .../apache/spark/sql/hive/TableReader.scala | 6 ++- .../spark/sql/hive/QueryPartitionSuite.scala | 49 +++++++++++++++++++ 2 files changed, 54 insertions(+), 1 deletion(-) create mode 100644 sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala index c368715f7c6f5..bce835d5ff17b 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala @@ -141,7 +141,11 @@ class HadoopTableReader( partitionToDeserializer: Map[HivePartition, Class[_ <: Deserializer]], filterOpt: Option[PathFilter]): RDD[Row] = { - val hivePartitionRDDs = partitionToDeserializer.map { case (partition, partDeserializer) => + val hivePartitionRDDs = partitionToDeserializer.filter{ case (partition, partDeserializer) => + val partPath = HiveShim.getDataLocationPath(partition) + val fs = partPath.getFileSystem(sc.hiveconf) + fs.exists(partPath) + }.map { case (partition, partDeserializer) => val partDesc = Utilities.getPartitionDesc(partition) val partPath = HiveShim.getDataLocationPath(partition) val inputPathStr = applyFilterIfNeeded(partPath, filterOpt) 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 new file mode 100644 index 0000000000000..576a9bfd61b6b --- /dev/null +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala @@ -0,0 +1,49 @@ +package org.apache.spark.sql.hive + +import java.io.File + +import com.google.common.io.Files +import org.apache.spark.sql.{QueryTest, _} +import org.apache.spark.sql.hive.test.TestHive +/* Implicits */ +import org.apache.spark.sql.hive.test.TestHive._ + + +class QueryPartitionSuite extends QueryTest { + + test("SPARK-5068: query data when path doesn't exists"){ + val testData = TestHive.sparkContext.parallelize( + (1 to 10).map(i => TestData(i, i.toString))) + testData.registerTempTable("testData") + + val tmpDir = Files.createTempDir() + //create the table for test + sql(s"CREATE TABLE table_with_partition(key int,value string) 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.collect.toSeq ++ testData.collect.toSeq ++ testData.collect.toSeq ++ testData.collect.toSeq) + + //delect the path of one partition + val folders = tmpDir.listFiles.filter(_.isDirectory).toList + def deleteAll(file:File){ + if(file.isDirectory()){ + for(f:File <-file.listFiles()){ + deleteAll(f); + } + } + file.delete(); + } + deleteAll(folders(0)) + + //test for the affter delete the path + checkAnswer(sql("select key,value from table_with_partition"), + testData.collect.toSeq ++ testData.collect.toSeq ++ testData.collect.toSeq) + + sql("DROP TABLE table_with_partition") + sql("DROP TABLE createAndInsertTest") + } +} From 72783003d9986ac2ddc927115b86ec00c371cdb7 Mon Sep 17 00:00:00 2001 From: jeanlyn Date: Wed, 28 Jan 2015 11:29:21 +0800 Subject: [PATCH 2/3] add the Licensed --- .../spark/sql/hive/QueryPartitionSuite.scala | 23 +++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) 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 576a9bfd61b6b..0562127109ff9 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 @@ -1,3 +1,20 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + package org.apache.spark.sql.hive import java.io.File @@ -25,7 +42,8 @@ class QueryPartitionSuite extends QueryTest { 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.collect.toSeq ++ testData.collect.toSeq ++ testData.collect.toSeq ++ testData.collect.toSeq) + testData.toSchemaRDD.collect ++ testData.toSchemaRDD.collect + ++ testData.toSchemaRDD.collect ++ testData.toSchemaRDD.collect) //delect the path of one partition val folders = tmpDir.listFiles.filter(_.isDirectory).toList @@ -41,7 +59,8 @@ class QueryPartitionSuite extends QueryTest { //test for the affter delete the path checkAnswer(sql("select key,value from table_with_partition"), - testData.collect.toSeq ++ testData.collect.toSeq ++ testData.collect.toSeq) + testData.toSchemaRDD.collect ++ testData.toSchemaRDD.collect + ++ testData.toSchemaRDD.collect) sql("DROP TABLE table_with_partition") sql("DROP TABLE createAndInsertTest") From 40d1c941fcb0bd9ea64877c1d7046cd9509aa159 Mon Sep 17 00:00:00 2001 From: jeanlyn Date: Mon, 2 Feb 2015 19:49:46 +0800 Subject: [PATCH 3/3] fix code style --- .../src/main/scala/org/apache/spark/sql/hive/TableReader.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala index bce835d5ff17b..37fca9c153141 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala @@ -141,7 +141,7 @@ class HadoopTableReader( partitionToDeserializer: Map[HivePartition, Class[_ <: Deserializer]], filterOpt: Option[PathFilter]): RDD[Row] = { - val hivePartitionRDDs = partitionToDeserializer.filter{ case (partition, partDeserializer) => + val hivePartitionRDDs = partitionToDeserializer.filter { case (partition, partDeserializer) => val partPath = HiveShim.getDataLocationPath(partition) val fs = partPath.getFileSystem(sc.hiveconf) fs.exists(partPath)