[SPARK-10934] [SQL] handle hashCode of unsafe array correctly

`Murmur3_x86_32.hashUnsafeWords` only accepts word-aligned bytes, but unsafe array is not.

Author: Wenchen Fan <cloud0fan@163.com>

Closes #8987 from cloud-fan/hash.

2 files changed, 12 insertions, 1 deletions

diff --git a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java
index da9538b3f1..6a16d34083 100644
--- a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java
+++ b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java
@@ -285,7 +285,11 @@ public class UnsafeArrayData extends ArrayData {
 
   @Override
   public int hashCode() {
-    return Murmur3_x86_32.hashUnsafeWords(baseObject, baseOffset, sizeInBytes, 42);
+    int result = 37;
+    for (int i = 0; i < sizeInBytes; i++) {
+      result = 37 * result + Platform.getByte(baseObject, baseOffset + i);
+    }
+    return result;
   }
 
   @Override
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/UnsafeRowSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/UnsafeRowSuite.scala
index 2476b10e3c..944d4e1134 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/UnsafeRowSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/UnsafeRowSuite.scala
@@ -131,4 +131,11 @@ class UnsafeRowSuite extends SparkFunSuite {
     assert(emptyRow.getInt(0) === unsafeRow.getInt(0))
     assert(emptyRow.getUTF8String(1) === unsafeRow.getUTF8String(1))
   }
+
+  test("calling hashCode on unsafe array returned by getArray(ordinal)") {
+    val row = InternalRow.apply(new GenericArrayData(Array(1L)))
+    val unsafeRow = UnsafeProjection.create(Array[DataType](ArrayType(LongType))).apply(row)
+    // Makes sure hashCode on unsafe array won't crash
+    unsafeRow.getArray(0).hashCode()
+  }
 }