null is a valid partition value

Author: cloud-fan

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala

@@ -115,7 +115,12 @@ case class CatalogTablePartition(
     val caseInsensitiveProperties = CaseInsensitiveMap(storage.properties)
     val timeZoneId = caseInsensitiveProperties.getOrElse("timeZone", defaultTimeZondId)
     InternalRow.fromSeq(partitionSchema.map { field =>
-      Cast(Literal(spec(field.name)), field.dataType, Option(timeZoneId)).eval()
+      val partValue = if (spec(field.name) == ExternalCatalogUtils.DEFAULT_PARTITION_NAME) {
+        null
+      } else {
+        spec(field.name)
+      }
+      Cast(Literal(partValue), field.dataType, Option(timeZoneId)).eval()
     })
   }
 }
@@ -163,7 +168,7 @@ case class BucketSpec(
  * @param tracksPartitionsInCatalog whether this table's partition metadata is stored in the
  *                                  catalog. If false, it is inferred automatically based on file
  *                                  structure.
- * @param schemaPresevesCase Whether or not the schema resolved for this table is case-sensitive.
+ * @param schemaPreservesCase Whether or not the schema resolved for this table is case-sensitive.
  *                           When using a Hive Metastore, this flag is set to false if a case-
  *                           sensitive schema was unable to be read from the table properties.
  *                           Used to trigger case-sensitive schema inference at query time, when

sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala

@@ -319,7 +319,7 @@ case class FileSourceScanExec(
     val input = ctx.freshName("input")
     ctx.addMutableState("scala.collection.Iterator", input, s"$input = inputs[0];")
     val exprRows = output.zipWithIndex.map{ case (a, i) =>
-      new BoundReference(i, a.dataType, a.nullable)
+      BoundReference(i, a.dataType, a.nullable)
     }
     val row = ctx.freshName("row")
     ctx.INPUT_ROW = row

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

@@ -33,7 +33,6 @@ import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
 import org.apache.spark.sql.catalyst.expressions.{Cast, Literal}
 import org.apache.spark.sql.catalyst.util.DateTimeUtils
 import org.apache.spark.sql.types._
-import org.apache.spark.unsafe.types.UTF8String
 
 // TODO: We should tighten up visibility of the classes here once we clean up Hive coupling.
 
@@ -129,7 +128,7 @@ object PartitioningUtils {
       //   "hdfs://host:9000/invalidPath"
       //   "hdfs://host:9000/path"
       // TODO: Selective case sensitivity.
-      val discoveredBasePaths = optDiscoveredBasePaths.flatMap(x => x).map(_.toString.toLowerCase())
+      val discoveredBasePaths = optDiscoveredBasePaths.flatten.map(_.toString.toLowerCase())
       assert(
         discoveredBasePaths.distinct.size == 1,
         "Conflicting directory structures detected. Suspicious paths:\b" +

sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala

@@ -1004,8 +1004,8 @@ private[spark] class HiveExternalCatalog(conf: SparkConf, hadoopConf: Configurat
     val partColNameMap = buildLowerCasePartColNameMap(catalogTable).mapValues(escapePathName)
     val clientPartitionNames =
       client.getPartitionNames(catalogTable, partialSpec.map(lowerCasePartitionSpec))
-    clientPartitionNames.map { partName =>
-      val partSpec = PartitioningUtils.parsePathFragmentAsSeq(partName)
+    clientPartitionNames.map { partitionPath =>
+      val partSpec = PartitioningUtils.parsePathFragmentAsSeq(partitionPath)
       partSpec.map { case (partName, partValue) =>
         partColNameMap(partName.toLowerCase) + "=" + escapePathName(partValue)
       }.mkString("/")

sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionProviderCompatibilitySuite.scala

@@ -22,7 +22,7 @@ import java.io.File
 import org.apache.hadoop.fs.Path
 
 import org.apache.spark.metrics.source.HiveCatalogMetrics
-import org.apache.spark.sql.{AnalysisException, QueryTest}
+import org.apache.spark.sql.{AnalysisException, QueryTest, Row}
 import org.apache.spark.sql.catalyst.TableIdentifier
 import org.apache.spark.sql.hive.test.TestHiveSingleton
 import org.apache.spark.sql.internal.SQLConf
@@ -316,6 +316,20 @@ class PartitionProviderCompatibilitySuite
         }
       }
     }
+
+    test(s"SPARK-19887 partition value is null - partition management $enabled") {
+      withTable("test") {
+        Seq((1, "p", 1), (2, null, 2)).toDF("a", "b", "c")
+          .write.partitionBy("b", "c").saveAsTable("test")
+        checkAnswer(spark.table("test"),
+          Row(1, "p", 1) :: Row(2, null, 2) :: Nil)
+
+        Seq((3, null: String, 3)).toDF("a", "b", "c")
+          .write.mode("append").partitionBy("b", "c").saveAsTable("test")
+        checkAnswer(spark.table("test"),
+          Row(1, "p", 1) :: Row(2, null, 2) :: Row(3, null, 3) :: Nil)
+      }
+    }
   }
 
   /**