From d3f87dc39480f075170817bbd00142967a938078 Mon Sep 17 00:00:00 2001
From: Josh Rosen <joshrosen@databricks.com>
Date: Fri, 28 Aug 2015 11:51:42 -0700
Subject: [SPARK-10325] Override hashCode() for public Row

This commit fixes an issue where the public SQL `Row` class did not override `hashCode`, causing it to violate the hashCode() + equals() contract. To fix this, I simply ported the `hashCode` implementation from the 1.4.x version of `Row`.

Author: Josh Rosen <joshrosen@databricks.com>

Closes #8500 from JoshRosen/SPARK-10325 and squashes the following commits:

51ffea1 [Josh Rosen] Override hashCode() for public Row.
---
 sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala  | 13 +++++++++++++
 sql/core/src/test/scala/org/apache/spark/sql/RowSuite.scala |  9 +++++++++
 2 files changed, 22 insertions(+)

(limited to 'sql')

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
index cfd9cb0e62..ed2fdf9f2f 100644
--- 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
index 795d4e983f..77ccd6f775 100644
--- 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())
+  }
 }
-- 
cgit v1.2.3