[SPARK-8236] [SQL] misc functions: crc32

https://issues.apache.org/jira/browse/SPARK-8236

Author: Shilei <shilei.qian@intel.com>

Closes #7108 from qiansl127/Crc32 and squashes the following commits:

5477352 [Shilei] Change to AutoCastInputTypes
5f16e5d [Shilei] Add misc function crc32

2 files changed, 27 insertions, 0 deletions

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index 4d9a019058..6331fe6105 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -1466,6 +1466,22 @@ object functions {
    */
   def sha2(columnName: String, numBits: Int): Column = sha2(Column(columnName), numBits)
 
+  /**
+   * Calculates the cyclic redundancy check value and returns the value as a bigint.
+   *
+   * @group misc_funcs
+   * @since 1.5.0
+   */
+  def crc32(e: Column): Column = Crc32(e.expr)
+
+  /**
+   * Calculates the cyclic redundancy check value and returns the value as a bigint.
+   *
+   * @group misc_funcs
+   * @since 1.5.0
+   */
+  def crc32(columnName: String): Column = crc32(Column(columnName))
+
   //////////////////////////////////////////////////////////////////////////////////////////////
   // String functions
   //////////////////////////////////////////////////////////////////////////////////////////////
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
index abfd47c811..11a8767ead 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
@@ -173,6 +173,17 @@ class DataFrameFunctionsSuite extends QueryTest {
     }
   }
 
+  test("misc crc32 function") {
+    val df = Seq(("ABC", Array[Byte](1, 2, 3, 4, 5, 6))).toDF("a", "b")
+    checkAnswer(
+      df.select(crc32($"a"), crc32("b")),
+      Row(2743272264L, 2180413220L))
+
+    checkAnswer(
+      df.selectExpr("crc32(a)", "crc32(b)"),
+      Row(2743272264L, 2180413220L))
+  }
+
   test("string length function") {
     checkAnswer(
       nullStrings.select(strlen($"s"), strlen("s")),