Skip to content

Commit

Permalink
remove hive parquet bundle
Browse files Browse the repository at this point in the history
  • Loading branch information
marmbrus committed Aug 16, 2014
1 parent a43e0da commit 41ebc5f
Show file tree
Hide file tree
Showing 3 changed files with 58 additions and 9 deletions.
1 change: 0 additions & 1 deletion project/SparkBuild.scala
Original file line number Diff line number Diff line change
Expand Up @@ -228,7 +228,6 @@ object SQL {
object Hive {

lazy val settings = Seq(
libraryDependencies += "com.twitter" % "parquet-hive-bundle" % "1.5.0",
javaOptions += "-XX:MaxPermSize=1g",
// Multiple queries rely on the TestHive singleton. See comments there for more details.
parallelExecution in Test := false,
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
/*
* 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.parquet

import java.util.Properties

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector.Category
import org.apache.hadoop.hive.serde2.{SerDeStats, SerDe}
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector
import org.apache.hadoop.io.Writable

/**
* A placeholder that allows SparkSQL users to create metastore tables that are stored as
* parquet files. It is only intended to pass the checks that the serde is valid and exists
* when a CREATE TABLE is run. The actual work of decoding will be done by ParquetTableScan
* when "spark.sql.hive.convertMetastoreParquet" is set to true.
*/
@deprecated("No code should depend on FakeParquetHiveSerDe as it is only intended as a " +
"placeholder in the Hive MetaStore")
class FakeParquetSerDe extends SerDe {
override def getObjectInspector: ObjectInspector = new ObjectInspector {
override def getCategory: Category = Category.PRIMITIVE

override def getTypeName: String = "string"
}

override def deserialize(p1: Writable): AnyRef = throwError

override def initialize(p1: Configuration, p2: Properties): Unit = {}

override def getSerializedClass: Class[_ <: Writable] = throwError

override def getSerDeStats: SerDeStats = throwError

override def serialize(p1: scala.Any, p2: ObjectInspector): Writable = throwError

private def throwError =
sys.error(
"spark.sql.hive.convertMetastoreParquet must be set to true to use FakeParquetSerDe")
}
Original file line number Diff line number Diff line change
Expand Up @@ -63,10 +63,7 @@ class ParquetMetastoreSuite extends QueryTest with BeforeAndAfterAll {
stringField STRING
)
PARTITIONED BY (p int)
ROW FORMAT SERDE 'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
STORED AS
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
ROW FORMAT SERDE 'org.apache.spark.sql.hive.parquet.FakeParquetSerDe'
location '${partitionedTableDir.getCanonicalPath}'
""")

Expand All @@ -76,10 +73,7 @@ class ParquetMetastoreSuite extends QueryTest with BeforeAndAfterAll {
intField INT,
stringField STRING
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
STORED AS
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
ROW FORMAT SERDE 'org.apache.spark.sql.hive.parquet.FakeParquetSerDe'
location '${new File(partitionedTableDir, "p=1").getCanonicalPath}'
""")

Expand Down

0 comments on commit 41ebc5f

Please sign in to comment.