Code clean up

Author: gengliangwang

core/src/main/scala/org/apache/spark/internal/io/HadoopMapReduceCommitProtocol.scala

@@ -145,18 +145,7 @@ class HadoopMapReduceCommitProtocol(
   }
 
   override def setupJob(jobContext: JobContext): Unit = {
-    // Setup IDs
-    val jobId = SparkHadoopWriterUtils.createJobID(new Date, 0)
-    val taskId = new TaskID(jobId, TaskType.MAP, 0)
-    val taskAttemptId = new TaskAttemptID(taskId, 0)
-
-    // Set up the configuration object
-    jobContext.getConfiguration.set("mapreduce.job.id", jobId.toString)
-    jobContext.getConfiguration.set("mapreduce.task.id", taskAttemptId.getTaskID.toString)
-    jobContext.getConfiguration.set("mapreduce.task.attempt.id", taskAttemptId.toString)
-    jobContext.getConfiguration.setBoolean("mapreduce.task.ismap", true)
-    jobContext.getConfiguration.setInt("mapreduce.task.partition", 0)
-
+    val taskAttemptId = new TaskAttemptID(new TaskID(new JobID(), TaskType.MAP, 0), 0)
     val taskAttemptContext = new TaskAttemptContextImpl(jobContext.getConfiguration, taskAttemptId)
     committer = setupCommitter(taskAttemptContext)
     committer.setupJob(jobContext)

sql/core/src/main/java/org/apache/spark/sql/execution/datasources/orc/OrcColumnVector.java

@@ -47,11 +47,7 @@ public class OrcColumnVector extends org.apache.spark.sql.vectorized.ColumnVecto
   OrcColumnVector(DataType type, ColumnVector vector) {
     super(type);
 
-    if (type instanceof TimestampType) {
-      isTimestamp = true;
-    } else {
-      isTimestamp = false;
-    }
+    isTimestamp = type instanceof TimestampType;
 
     baseData = vector;
     if (vector instanceof LongColumnVector) {

sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java

@@ -571,7 +571,7 @@ private int readIntLittleEndian() throws IOException {
     int ch3 = in.read();
     int ch2 = in.read();
     int ch1 = in.read();
-    return ((ch1 << 24) + (ch2 << 16) + (ch3 << 8) + (ch4 << 0));
+    return ((ch1 << 24) + (ch2 << 16) + (ch3 << 8) + (ch4));
   }
 
   /**
@@ -592,7 +592,7 @@ private int readIntLittleEndianPaddedOnBitWidth() throws IOException {
         int ch3 = in.read();
         int ch2 = in.read();
         int ch1 = in.read();
-        return (ch1 << 16) + (ch2 << 8) + (ch3 << 0);
+        return (ch1 << 16) + (ch2 << 8) + (ch3);
       }
       case 4: {
         return readIntLittleEndian();

sql/core/src/main/scala/org/apache/spark/sql/api/r/SQLUtils.scala

@@ -188,7 +188,7 @@ private[sql] object SQLUtils extends Logging {
     dataType match {
       case 's' =>
         // Read StructType for DataFrame
-        val fields = SerDe.readList(dis, jvmObjectTracker = null).asInstanceOf[Array[Object]]
+        val fields = SerDe.readList(dis, jvmObjectTracker = null)
         Row.fromSeq(fields)
       case _ => null
     }

sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala

@@ -410,12 +410,10 @@ object ViewHelper {
     }
 
     // Detect cyclic references from subqueries.
-    plan.expressions.foreach { expr =>
-      expr match {
-        case s: SubqueryExpression =>
-          checkCyclicViewReference(s.plan, path, viewIdent)
-        case _ => // Do nothing.
-      }
+    plan.expressions.foreach {
+      case s: SubqueryExpression =>
+        checkCyclicViewReference(s.plan, path, viewIdent)
+      case _ => // Do nothing.
     }
   }
 }

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala

@@ -244,18 +244,17 @@ object FileFormatWriter extends Logging {
       iterator: Iterator[InternalRow]): WriteTaskResult = {
 
     val jobId = SparkHadoopWriterUtils.createJobID(new Date, sparkStageId)
-    val taskId = new TaskID(jobId, TaskType.MAP, sparkPartitionId)
-    val taskAttemptId = new TaskAttemptID(taskId, sparkAttemptNumber)
 
     // Set up the attempt context required to use in the output committer.
     val taskAttemptContext: TaskAttemptContext = {
+      val taskId = new TaskID(jobId, TaskType.MAP, sparkPartitionId)
+      val taskAttemptId = new TaskAttemptID(taskId, sparkAttemptNumber)
       // Set up the configuration object
       val hadoopConf = description.serializableHadoopConf.value
       hadoopConf.set("mapreduce.job.id", jobId.toString)
       hadoopConf.set("mapreduce.task.id", taskAttemptId.getTaskID.toString)
       hadoopConf.set("mapreduce.task.attempt.id", taskAttemptId.toString)
       hadoopConf.setBoolean("mapreduce.task.ismap", true)
-      hadoopConf.setInt("mapreduce.task.partition", 0)
 
       new TaskAttemptContextImpl(hadoopConf, taskAttemptId)
     }
@@ -378,7 +377,7 @@ object FileFormatWriter extends Logging {
         dataSchema = description.dataColumns.toStructType,
         context = taskAttemptContext)
 
-      statsTrackers.map(_.newFile(currentPath))
+      statsTrackers.foreach(_.newFile(currentPath))
     }
 
     override def execute(iter: Iterator[InternalRow]): ExecutedWriteSummary = {
@@ -429,10 +428,10 @@ object FileFormatWriter extends Logging {
       committer: FileCommitProtocol) extends ExecuteWriteTask {
 
     /** Flag saying whether or not the data to be written out is partitioned. */
-    val isPartitioned = desc.partitionColumns.nonEmpty
+    private val isPartitioned = desc.partitionColumns.nonEmpty
 
     /** Flag saying whether or not the data to be written out is bucketed. */
-    val isBucketed = desc.bucketIdExpression.isDefined
+    private val isBucketed = desc.bucketIdExpression.isDefined
 
     assert(isPartitioned || isBucketed,
       s"""DynamicPartitionWriteTask should be used for writing out data that's either

sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala

@@ -170,7 +170,7 @@ class SQLAppStatusListener(
       .filter { case (id, _) => metricIds.contains(id) }
       .groupBy(_._1)
       .map { case (id, values) =>
-        id -> SQLMetrics.stringValue(metricTypes(id), values.map(_._2).toSeq)
+        id -> SQLMetrics.stringValue(metricTypes(id), values.map(_._2))
       }
 
     // Check the execution again for whether the aggregated metrics data has been calculated.