Override hashCode() for public Row.

apache · Aug 28, 2015 · 51ffea1 · 51ffea1
1 parent 4eeda8d
commit 51ffea1
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 0 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
@@ -18,6 +18,7 @@
 package org.apache.spark.sql
 
 import scala.collection.JavaConverters._
+import scala.util.hashing.MurmurHash3
 
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.expressions.GenericRow
@@ -410,6 +411,18 @@ trait Row extends Serializable {
     true
   }
 
+  override def hashCode: Int = {
+    // Using Scala's Seq hash code implementation.
+    var n = 0
+    var h = MurmurHash3.seqSeed
+    val len = length
+    while (n < len) {
+      h = MurmurHash3.mix(h, apply(n).##)
+      n += 1
+    }
+    MurmurHash3.finalizeHash(h, n)
+  }
+
   /* ---------------------- utility methods for Scala ---------------------- */
 
   /**

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/RowSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/RowSuite.scala
@@ -85,4 +85,13 @@ class RowSuite extends SparkFunSuite with SharedSQLContext {
     val r2 = Row(Double.NaN)
     assert(r1 === r2)
   }
+
+  test("equals and hashCode") {
+    val r1 = Row("Hello")
+    val r2 = Row("Hello")
+    assert(r1 === r2)
+    assert(r1.hashCode() === r2.hashCode())
+    val r3 = Row("World")
+    assert(r3.hashCode() != r1.hashCode())
+  }
 }