SPARK-4297 [BUILD] Build warning fixes omnibus

There are a number of warnings generated in a normal, successful build right now. They're mostly Java unchecked cast warnings, which can be suppressed. But there's a grab bag of other Scala language warnings and so on that can all be easily fixed. The forthcoming PR fixes about 90% of the build warnings I see now. Author: Sean Owen <[email protected]> Closes apache#3157 from srowen/SPARK-4297 and squashes the following commits: 8c9e469 [Sean Owen] Suppress unchecked cast warnings, and several other build warning fixes
ankurdave · Dec 24, 2014 · 29fabb1 · 29fabb1
1 parent 199e59a
commit 29fabb1
Show file tree

Hide file tree

Showing 14 changed files with 45 additions and 32 deletions.
diff --git a/core/pom.xml b/core/pom.xml
@@ -352,9 +352,9 @@
           </execution>
         </executions>
         <configuration>
-          <tasks>
+          <target>
             <unzip src="../python/lib/py4j-0.8.2.1-src.zip" dest="../python/build" />
-          </tasks>
+          </target>
         </configuration>
       </plugin>
       <plugin>

diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala
@@ -19,6 +19,7 @@ package org.apache.spark.scheduler
 
 import java.nio.ByteBuffer
 
+import scala.language.existentials
 import scala.util.control.NonFatal
 
 import org.apache.spark._

diff --git a/core/src/test/java/org/apache/spark/JavaAPISuite.java b/core/src/test/java/org/apache/spark/JavaAPISuite.java
@@ -184,6 +184,7 @@ public void sortByKey() {
     Assert.assertEquals(new Tuple2<Integer, Integer>(3, 2), sortedPairs.get(2));
   }
 
+  @SuppressWarnings("unchecked")
   @Test
   public void repartitionAndSortWithinPartitions() {
     List<Tuple2<Integer, Integer>> pairs = new ArrayList<Tuple2<Integer, Integer>>();
@@ -491,6 +492,7 @@ public Integer call(Integer a, Integer b) {
     Assert.assertEquals(33, sum);
   }
 
+  @SuppressWarnings("unchecked")
   @Test
   public void aggregateByKey() {
     JavaPairRDD<Integer, Integer> pairs = sc.parallelizePairs(
@@ -1556,7 +1558,7 @@ static class Class2 {}
   @Test
   public void testRegisterKryoClasses() {
     SparkConf conf = new SparkConf();
-    conf.registerKryoClasses(new Class[]{ Class1.class, Class2.class });
+    conf.registerKryoClasses(new Class<?>[]{ Class1.class, Class2.class });
     Assert.assertEquals(
         Class1.class.getName() + "," + Class2.class.getName(),
         conf.get("spark.kryo.classesToRegister"));

diff --git a/core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala b/core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala
@@ -24,14 +24,14 @@ import org.apache.spark.deploy.SparkHadoopUtil
 import org.apache.spark.scheduler.{SparkListenerTaskEnd, SparkListener}
 
 import org.scalatest.FunSuite
-import org.scalatest.matchers.ShouldMatchers
+import org.scalatest.Matchers
 
 import org.apache.hadoop.conf.Configuration
 import org.apache.hadoop.fs.{Path, FileSystem}
 
 import scala.collection.mutable.ArrayBuffer
 
-class InputOutputMetricsSuite extends FunSuite with SharedSparkContext with ShouldMatchers {
+class InputOutputMetricsSuite extends FunSuite with SharedSparkContext with Matchers {
   test("input metrics when reading text file with single split") {
     val file = new File(getClass.getSimpleName + ".txt")
     val pw = new PrintWriter(new FileWriter(file))

diff --git a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
@@ -739,7 +739,7 @@ class DAGSchedulerSuite extends TestKit(ActorSystem("DAGSchedulerSuite")) with F
 
   test("accumulator not calculated for resubmitted result stage") {
     //just for register
-    val accum = new Accumulator[Int](0, SparkContext.IntAccumulatorParam)
+    val accum = new Accumulator[Int](0, AccumulatorParam.IntAccumulatorParam)
     val finalRdd = new MyRDD(sc, 1, Nil)
     submit(finalRdd, Array(0))
     completeWithAccumulator(accum.id, taskSets(0), Seq((Success, 42)))

diff --git a/mllib/src/test/java/org/apache/spark/mllib/feature/JavaTfIdfSuite.java b/mllib/src/test/java/org/apache/spark/mllib/feature/JavaTfIdfSuite.java
@@ -49,6 +49,7 @@ public void tearDown() {
   public void tfIdf() {
     // The tests are to check Java compatibility.
     HashingTF tf = new HashingTF();
+    @SuppressWarnings("unchecked")
     JavaRDD<ArrayList<String>> documents = sc.parallelize(Lists.newArrayList(
       Lists.newArrayList("this is a sentence".split(" ")),
       Lists.newArrayList("this is another sentence".split(" ")),
@@ -68,6 +69,7 @@ public void tfIdf() {
   public void tfIdfMinimumDocumentFrequency() {
     // The tests are to check Java compatibility.
     HashingTF tf = new HashingTF();
+    @SuppressWarnings("unchecked")
     JavaRDD<ArrayList<String>> documents = sc.parallelize(Lists.newArrayList(
       Lists.newArrayList("this is a sentence".split(" ")),
       Lists.newArrayList("this is another sentence".split(" ")),

diff --git a/sql/core/src/main/java/org/apache/spark/sql/api/java/UserDefinedType.java b/sql/core/src/main/java/org/apache/spark/sql/api/java/UserDefinedType.java
@@ -35,6 +35,7 @@ protected UserDefinedType() { }
   public boolean equals(Object o) {
     if (this == o) return true;
     if (o == null || getClass() != o.getClass()) return false;
+    @SuppressWarnings("unchecked")
     UserDefinedType<UserType> that = (UserDefinedType<UserType>) o;
     return this.sqlType().equals(that.sqlType());
   }

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala
@@ -24,8 +24,8 @@ import scala.util.Try
 import org.apache.hadoop.conf.Configuration
 import org.apache.hadoop.fs.{FileSystem, Path}
 import org.apache.hadoop.mapreduce.Job
-import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
 
+import parquet.format.converter.ParquetMetadataConverter
 import parquet.hadoop.{ParquetFileReader, Footer, ParquetFileWriter}
 import parquet.hadoop.metadata.{ParquetMetadata, FileMetaData}
 import parquet.hadoop.util.ContextUtil
@@ -458,7 +458,7 @@ private[parquet] object ParquetTypesConverter extends Logging {
       // ... and fallback to "_metadata" if no such file exists (which implies the Parquet file is
       // empty, thus normally the "_metadata" file is expected to be fairly small).
       .orElse(children.find(_.getPath.getName == ParquetFileWriter.PARQUET_METADATA_FILE))
-      .map(ParquetFileReader.readFooter(conf, _))
+      .map(ParquetFileReader.readFooter(conf, _, ParquetMetadataConverter.NO_FILTER))
       .getOrElse(
         throw new IllegalArgumentException(s"Could not find Parquet metadata at path $path"))
   }

diff --git a/sql/core/src/test/java/org/apache/spark/sql/api/java/JavaRowSuite.java b/sql/core/src/test/java/org/apache/spark/sql/api/java/JavaRowSuite.java
@@ -141,6 +141,7 @@ public void constructComplexRow() {
       doubleValue, stringValue, timestampValue, null);
 
     // Complex array
+    @SuppressWarnings("unchecked")
     List<Map<String, Long>> arrayOfMaps = Arrays.asList(simpleMap);
     List<Row> arrayOfRows = Arrays.asList(simpleStruct);
 

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala
@@ -24,6 +24,8 @@ import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.dsl._
 import org.apache.spark.sql.test.TestSQLContext._
 
+import scala.language.postfixOps
+
 class DslQuerySuite extends QueryTest {
   import org.apache.spark.sql.TestData._
 

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala
@@ -17,6 +17,8 @@
 
 package org.apache.spark.sql.parquet
 
+import scala.reflect.ClassTag
+
 import org.apache.hadoop.fs.{FileSystem, Path}
 import org.apache.hadoop.mapreduce.Job
 import org.scalatest.{BeforeAndAfterAll, FunSuiteLike}
@@ -459,11 +461,17 @@ class ParquetQuerySuite extends QueryTest with FunSuiteLike with BeforeAndAfterA
   }
 
   test("make RecordFilter for simple predicates") {
-    def checkFilter[T <: FilterPredicate](predicate: Expression, defined: Boolean = true): Unit = {
+    def checkFilter[T <: FilterPredicate : ClassTag](
+        predicate: Expression,
+        defined: Boolean = true): Unit = {
       val filter = ParquetFilters.createFilter(predicate)
       if (defined) {
         assert(filter.isDefined)
-        assert(filter.get.isInstanceOf[T])
+        val tClass = implicitly[ClassTag[T]].runtimeClass
+        val filterGet = filter.get
+        assert(
+          tClass.isInstance(filterGet),
+          s"$filterGet of type ${filterGet.getClass} is not an instance of $tClass")
       } else {
         assert(filter.isEmpty)
       }
@@ -484,7 +492,7 @@ class ParquetQuerySuite extends QueryTest with FunSuiteLike with BeforeAndAfterA
 
     checkFilter[Operators.And]('a.int === 1 && 'a.int < 4)
     checkFilter[Operators.Or]('a.int === 1 || 'a.int < 4)
-    checkFilter[Operators.Not](!('a.int === 1))
+    checkFilter[Operators.NotEq[Integer]](!('a.int === 1))
 
     checkFilter('a.int > 'b.int, defined = false)
     checkFilter(('a.int > 'b.int) && ('a.int > 'b.int), defined = false)

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/parquet/FakeParquetSerDe.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/parquet/FakeParquetSerDe.scala
@@ -32,7 +32,7 @@ import org.apache.hadoop.io.Writable
  * 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")
+            "placeholder in the Hive MetaStore", "1.2.0")
 class FakeParquetSerDe extends SerDe {
   override def getObjectInspector: ObjectInspector = new ObjectInspector {
     override def getCategory: Category = Category.PRIMITIVE

diff --git a/sql/hive/src/test/java/org/apache/spark/sql/hive/execution/UDFListListInt.java b/sql/hive/src/test/java/org/apache/spark/sql/hive/execution/UDFListListInt.java
@@ -23,25 +23,21 @@
 
 public class UDFListListInt extends UDF {
   /**
-   *
    * @param obj
-   *   SQL schema: array<struct<x: int, y: int, z: int>>
-   *   Java Type: List<List<Integer>>
-   * @return
+   *   SQL schema: array&lt;struct&lt;x: int, y: int, z: int&gt;&gt;
+   *   Java Type: List&lt;List&lt;Integer&gt;&gt;
    */
+  @SuppressWarnings("unchecked")
   public long evaluate(Object obj) {
     if (obj == null) {
-      return 0l;
+      return 0L;
     }
-    List<List> listList = (List<List>) obj;
+    List<List<?>> listList = (List<List<?>>) obj;
     long retVal = 0;
-    for (List aList : listList) {
-      @SuppressWarnings("unchecked")
-      List<Object> list = (List<Object>) aList;
-      @SuppressWarnings("unchecked")
-      Integer someInt = (Integer) list.get(1);
+    for (List<?> aList : listList) {
+      Number someInt = (Number) aList.get(1);
       try {
-        retVal += (long) (someInt.intValue());
+        retVal += someInt.longValue();
       } catch (NullPointerException e) {
         System.out.println(e);
       }

diff --git a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java
@@ -57,7 +57,7 @@ public void equalIterable(Iterable<?> a, Iterable<?> b) {
 
   @Test
   public void testInitialization() {
-    Assert.assertNotNull(ssc.sc());
+    Assert.assertNotNull(ssc.sparkContext());
   }
 
   @SuppressWarnings("unchecked")
@@ -662,7 +662,7 @@ public void testStreamingContextTransform(){
       listOfDStreams1,
       new Function2<List<JavaRDD<?>>, Time, JavaRDD<Long>>() {
         public JavaRDD<Long> call(List<JavaRDD<?>> listOfRDDs, Time time) {
-          assert(listOfRDDs.size() == 2);
+          Assert.assertEquals(2, listOfRDDs.size());
           return null;
         }
       }
@@ -675,7 +675,7 @@ public JavaRDD<Long> call(List<JavaRDD<?>> listOfRDDs, Time time) {
       listOfDStreams2,
       new Function2<List<JavaRDD<?>>, Time, JavaPairRDD<Integer, Tuple2<Integer, String>>>() {
         public JavaPairRDD<Integer, Tuple2<Integer, String>> call(List<JavaRDD<?>> listOfRDDs, Time time) {
-          assert(listOfRDDs.size() == 3);
+          Assert.assertEquals(3, listOfRDDs.size());
           JavaRDD<Integer> rdd1 = (JavaRDD<Integer>)listOfRDDs.get(0);
           JavaRDD<Integer> rdd2 = (JavaRDD<Integer>)listOfRDDs.get(1);
           JavaRDD<Tuple2<Integer, String>> rdd3 = (JavaRDD<Tuple2<Integer, String>>)listOfRDDs.get(2);
@@ -969,7 +969,7 @@ public Integer call(Tuple2<String, Integer> in) throws Exception {
             });
 
     JavaTestUtils.attachTestOutputStream(reversed);
-    List<List<Tuple2<Integer, String>>> result = JavaTestUtils.runStreams(ssc, 2, 2);
+    List<List<Integer>> result = JavaTestUtils.runStreams(ssc, 2, 2);
 
     Assert.assertEquals(expected, result);
   }
@@ -1012,7 +1012,7 @@ public Iterable<Tuple2<Integer, String>> call(Tuple2<String, Integer> in) throws
           }
         });
     JavaTestUtils.attachTestOutputStream(flatMapped);
-    List<List<Tuple2<String, Integer>>> result = JavaTestUtils.runStreams(ssc, 2, 2);
+    List<List<Tuple2<Integer, String>>> result = JavaTestUtils.runStreams(ssc, 2, 2);
 
     Assert.assertEquals(expected, result);
   }
@@ -1163,9 +1163,9 @@ public void testGroupByKeyAndWindow() {
     JavaTestUtils.attachTestOutputStream(groupWindowed);
     List<List<Tuple2<String, List<Integer>>>> result = JavaTestUtils.runStreams(ssc, 3, 3);
 
-    assert(result.size() == expected.size());
+    Assert.assertEquals(expected.size(), result.size());
     for (int i = 0; i < result.size(); i++) {
-      assert(convert(result.get(i)).equals(convert(expected.get(i))));
+      Assert.assertEquals(convert(expected.get(i)), convert(result.get(i)));
     }
   }
 
@@ -1383,7 +1383,7 @@ public JavaPairRDD<Integer, Integer> call(JavaPairRDD<Integer, Integer> in) thro
         });
 
     JavaTestUtils.attachTestOutputStream(sorted);
-    List<List<Tuple2<String, String>>> result = JavaTestUtils.runStreams(ssc, 2, 2);
+    List<List<Tuple2<Integer, Integer>>> result = JavaTestUtils.runStreams(ssc, 2, 2);
 
     Assert.assertEquals(expected, result);
   }