apache · srowen · Oct 13, 2014 · Oct 16, 2014 · Nov 1, 2014
diff --git a/core/src/main/scala/org/apache/spark/SparkHadoopWriter.scala b/core/src/main/scala/org/apache/spark/SparkHadoopWriter.scala
@@ -26,6 +26,7 @@ import org.apache.hadoop.mapred._
 import org.apache.hadoop.fs.FileSystem
 import org.apache.hadoop.fs.Path
 
+import org.apache.spark.mapred.SparkHadoopMapRedUtil
 import org.apache.spark.rdd.HadoopRDD
 
 /**

diff --git a/...hadoop/mapred/SparkHadoopMapRedUtil.scala → .../spark/mapred/SparkHadoopMapRedUtil.scala b/...hadoop/mapred/SparkHadoopMapRedUtil.scala → .../spark/mapred/SparkHadoopMapRedUtil.scala
@@ -15,22 +15,35 @@
  * limitations under the License.
  */
 
-package org.apache.hadoop.mapred
+package org.apache.spark.mapred
 
-private[apache]
+import java.lang.reflect.Modifier
+
+import org.apache.hadoop.mapred.{TaskAttemptID, JobID, JobConf, JobContext, TaskAttemptContext}
+
+private[spark]
 trait SparkHadoopMapRedUtil {
   def newJobContext(conf: JobConf, jobId: JobID): JobContext = {
     val klass = firstAvailableClass("org.apache.hadoop.mapred.JobContextImpl",
       "org.apache.hadoop.mapred.JobContext")
     val ctor = klass.getDeclaredConstructor(classOf[JobConf],
       classOf[org.apache.hadoop.mapreduce.JobID])
+    // In Hadoop 1.0.x, JobContext is an interface, and JobContextImpl is package private.
+    // Make it accessible if it's not in order to access it.
+    if (!Modifier.isPublic(ctor.getModifiers)) {
+      ctor.setAccessible(true)
+    }
     ctor.newInstance(conf, jobId).asInstanceOf[JobContext]
   }
 
   def newTaskAttemptContext(conf: JobConf, attemptId: TaskAttemptID): TaskAttemptContext = {
     val klass = firstAvailableClass("org.apache.hadoop.mapred.TaskAttemptContextImpl",
       "org.apache.hadoop.mapred.TaskAttemptContext")
     val ctor = klass.getDeclaredConstructor(classOf[JobConf], classOf[TaskAttemptID])
+    // See above
+    if (!Modifier.isPublic(ctor.getModifiers)) {
+      ctor.setAccessible(true)
+    }
     ctor.newInstance(conf, attemptId).asInstanceOf[TaskAttemptContext]
   }
 

diff --git a/.../mapreduce/SparkHadoopMapReduceUtil.scala → .../mapreduce/SparkHadoopMapReduceUtil.scala b/.../mapreduce/SparkHadoopMapReduceUtil.scala → .../mapreduce/SparkHadoopMapReduceUtil.scala
@@ -15,13 +15,14 @@
  * limitations under the License.
  */
 
-package org.apache.hadoop.mapreduce
+package org.apache.spark.mapreduce
 
 import java.lang.{Boolean => JBoolean, Integer => JInteger}
 
 import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.mapreduce.{JobContext, JobID, TaskAttemptContext, TaskAttemptID}
 
-private[apache]
+private[spark]
 trait SparkHadoopMapReduceUtil {
   def newJobContext(conf: Configuration, jobId: JobID): JobContext = {
     val klass = firstAvailableClass(

diff --git a/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala b/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala
@@ -35,6 +35,7 @@ import org.apache.spark.Partition
 import org.apache.spark.SerializableWritable
 import org.apache.spark.{SparkContext, TaskContext}
 import org.apache.spark.executor.{DataReadMethod, InputMetrics}
+import org.apache.spark.mapreduce.SparkHadoopMapReduceUtil
 import org.apache.spark.rdd.NewHadoopRDD.NewHadoopMapPartitionsWithSplitRDD
 import org.apache.spark.util.Utils
 import org.apache.spark.deploy.SparkHadoopUtil

diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
@@ -33,13 +33,14 @@ import org.apache.hadoop.io.SequenceFile.CompressionType
 import org.apache.hadoop.io.compress.CompressionCodec
 import org.apache.hadoop.mapred.{FileOutputCommitter, FileOutputFormat, JobConf, OutputFormat}
 import org.apache.hadoop.mapreduce.{Job => NewAPIHadoopJob, OutputFormat => NewOutputFormat,
-RecordWriter => NewRecordWriter, SparkHadoopMapReduceUtil}
+RecordWriter => NewRecordWriter}
 
 import org.apache.spark._
 import org.apache.spark.Partitioner.defaultPartitioner
 import org.apache.spark.SparkContext._
 import org.apache.spark.annotation.Experimental
 import org.apache.spark.deploy.SparkHadoopUtil
+import org.apache.spark.mapreduce.SparkHadoopMapReduceUtil
 import org.apache.spark.partial.{BoundedDouble, PartialResult}
 import org.apache.spark.serializer.Serializer
 import org.apache.spark.util.Utils

diff --git a/project/MimaExcludes.scala b/project/MimaExcludes.scala
@@ -77,6 +77,14 @@ object MimaExcludes {
             // SPARK-3822
             ProblemFilters.exclude[IncompatibleResultTypeProblem](
               "org.apache.spark.SparkContext.org$apache$spark$SparkContext$$createTaskScheduler")
+          ) ++ Seq(
+            // SPARK-1209
+            ProblemFilters.exclude[MissingClassProblem](
+              "org.apache.hadoop.mapreduce.SparkHadoopMapReduceUtil"),
+            ProblemFilters.exclude[MissingClassProblem](
+              "org.apache.hadoop.mapred.SparkHadoopMapRedUtil"),
+            ProblemFilters.exclude[MissingTypesProblem](
+              "org.apache.spark.rdd.PairRDDFunctions")
           )
 
         case v if v.startsWith("1.1") =>

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala
@@ -43,6 +43,7 @@ import parquet.hadoop.util.ContextUtil
 import parquet.io.ParquetDecodingException
 import parquet.schema.MessageType
 
+import org.apache.spark.mapreduce.SparkHadoopMapReduceUtil
 import org.apache.spark.rdd.RDD
 import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.SQLConf

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveWriterContainers.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveWriterContainers.scala
@@ -31,6 +31,7 @@ import org.apache.hadoop.hive.ql.plan.{PlanUtils, TableDesc}
 import org.apache.hadoop.io.Writable
 import org.apache.hadoop.mapred._
 
+import org.apache.spark.mapred.SparkHadoopMapRedUtil
 import org.apache.spark.sql.Row
 import org.apache.spark.{Logging, SerializableWritable, SparkHadoopWriter}
 import org.apache.spark.sql.hive.{ShimFileSinkDesc => FileSinkDesc}