Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/6135#discussion_r30300318
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcTableOperations.scala
---
@@ -0,0 +1,116 @@
+/*
+ * 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.orc
+
+import java.util._
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.fs.Path
+import org.apache.hadoop.hive.ql.io.orc._
+import org.apache.hadoop.io.NullWritable
+import org.apache.hadoop.io.Writable
+import org.apache.hadoop.mapred.JobConf
+import org.apache.hadoop.mapreduce.Job
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.hive.HiveShim
+import org.apache.spark.sql.sources.Filter
+import org.apache.spark.{Logging, SerializableWritable}
+import scala.collection.JavaConversions._
+
+case class OrcTableScan(attributes: Seq[Attribute],
+ @transient relation: OrcRelation,
+ filters: Array[Filter],
+ inputPaths: Array[String]) extends Logging {
+ @transient val sqlContext = relation.sqlContext
+ val path = relation.paths(0)
+
+ def addColumnIds(output: Seq[Attribute],
+ relation: OrcRelation, conf: Configuration) {
+ val ids =
+ output.map(a =>
+ relation.dataSchema.toAttributes.indexWhere(_.name == a.name):
Integer)
+ .filter(_ >= 0)
+ val names = attributes.map(_.name)
+ val sorted = ids.zip(names).sorted
+ HiveShim.appendReadColumns(conf, sorted.map(_._1), sorted.map(_._2))
+ }
+
+ def buildFilter(job: Job, filters: Array[Filter]): Unit = {
+ if (ORC_FILTER_PUSHDOWN_ENABLED) {
+ val conf: Configuration = job.getConfiguration
+ val recordFilter = OrcFilters.createFilter(filters)
+ if (recordFilter.isDefined) {
+ conf.set(SARG_PUSHDOWN, toKryo(recordFilter.get))
+ conf.setBoolean(INDEX_FILTER, true)
+ }
--- End diff --
The following style is more preferrable:
```scala
OrcFilters.createFilter(filters).foreach { f =>
conf.set(SARG_PUSHDOWN, toKryo(f))
conf.setBoolean(ConfVars.HIVEOPTINDEXFILTER.name(), true)
}
```
`INDEX_FILTER` duplicates `ConfVars.HIVEOPTINDEXFILTER.name()`, so I
removed it.
Where does the `SARG_PUSHDOWN` property get checked? Couldn't find it
elsewhere in this PR. Is is checked in Hive ORC code path?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
