Fix issues in code style

ravipesala · Jul 28, 2014 · 888968f · 888968f
1 parent 27540ba
commit 888968f
Show file tree

Hide file tree

Showing 4 changed files with 21 additions and 14 deletions.
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
@@ -51,8 +51,10 @@ private[hive] sealed trait TableReader {
  * data warehouse directory.
  */
 private[hive]
-class HadoopTableReader(@transient attributes: Seq[Attribute], 
-    @transient relation: MetastoreRelation, @transient sc: HiveContext)
+class HadoopTableReader(
+    @transient attributes: Seq[Attribute],
+    @transient relation: MetastoreRelation,
+    @transient sc: HiveContext)
   extends TableReader {
 
   // Choose the minimum number of splits. If mapred.map.tasks is set, then use that unless
@@ -135,7 +137,8 @@ class HadoopTableReader(@transient attributes: Seq[Attribute],
    *     subdirectory of each partition being read. If None, then all files are accepted.
    */
   def makeRDDForPartitionedTable(
-      partitionToDeserializer: Map[HivePartition, Class[_ <: Deserializer]],
+      partitionToDeserializer: Map[HivePartition,
+      Class[_ <: Deserializer]],
       filterOpt: Option[PathFilter]): RDD[Row] = {
     val hivePartitionRDDs = partitionToDeserializer.map { case (partition, partDeserializer) =>
       val partDesc = Utilities.getPartitionDesc(partition)
@@ -261,8 +264,11 @@ private[hive] object HadoopTableReader extends HiveInspectors {
    * 
    * @return Iterable Row object that transformed from the given iterable input.
    */
-  def fillObject(iter: Iterator[Writable], deserializer: Deserializer, 
-      attrs: Seq[(Attribute, Int)], row: GenericMutableRow): Iterator[Row] = {
+  def fillObject(
+      iter: Iterator[Writable],
+      deserializer: Deserializer,
+      attrs: Seq[(Attribute, Int)],
+      row: GenericMutableRow): Iterator[Row] = {
     val soi = deserializer.getObjectInspector().asInstanceOf[StructObjectInspector]
     // get the field references according to the attributes(output of the reader) required
     val fieldRefs = attrs.map { case (attr, idx) => (soi.getStructFieldRef(attr.name), idx) }

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala
@@ -77,7 +77,7 @@ case class HiveTableScan(
     val columnInternalNames = neededColumnIDs.map(HiveConf.getColumnInternalName(_)).mkString(",")
 
     if (attributes.size == relation.output.size) {
-      // TODO what if duplicated attributes queried?
+      // SQLContext#pruneFilterProject guarantees no duplicated value in `attributes`
       ColumnProjectionUtils.setFullyReadColumns(hiveConf)
     } else {
       ColumnProjectionUtils.appendReadColumnIDs(hiveConf, neededColumnIDs)

diff --git a/..._serde-0-8d612014b2c7d3775f637020e568768d → ..._serde-0-8caed2a6e80250a6d38a59388679c298 b/..._serde-0-8d612014b2c7d3775f637020e568768d → ..._serde-0-8caed2a6e80250a6d38a59388679c298
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala
@@ -17,9 +17,10 @@
 
 package org.apache.spark.sql.hive.execution
 
+import org.scalatest.{BeforeAndAfterAll, FunSuite}
+
 import org.apache.spark.{SparkConf, SparkContext}
 import org.apache.spark.sql.hive.test.TestHive
-import org.scalatest.{BeforeAndAfterAll, FunSuite}
 
 class HiveTableScanSuite extends HiveComparisonTest {
   // MINOR HACK: You must run a query before calling reset the first time.
@@ -31,17 +32,17 @@ class HiveTableScanSuite extends HiveComparisonTest {
                  | 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe' 
                  | STORED AS RCFILE
                """.stripMargin)
-  TestHive.hql("""from src 
-                 | insert into table part_scan_test PARTITION (ds='2010-01-01') 
-                 | select 100,100 limit 1
+  TestHive.hql("""FROM src
+                 | INSERT INTO TABLE part_scan_test PARTITION (ds='2010-01-01')
+                 | SELECT 100,100 LIMIT 1
                """.stripMargin)
-  TestHive.hql("""ALTER TABLE part_scan_test set SERDE 
+  TestHive.hql("""ALTER TABLE part_scan_test SET SERDE
                  | 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
                """.stripMargin)
-  TestHive.hql("""from src insert into table part_scan_test PARTITION (ds='2010-01-02') 
-                 | select 200,200 limit 1
+  TestHive.hql("""FROM src INSERT INTO TABLE part_scan_test PARTITION (ds='2010-01-02')
+                 | SELECT 200,200 LIMIT 1
                """.stripMargin)
 
   createQueryTest("partition_based_table_scan_with_different_serde", 
-    "select * from part_scan_test", false)
+    "SELECT * from part_scan_test", false)
 }