Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/6970#discussion_r33365450
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
---
@@ -47,4 +48,73 @@ case class Md5(child: Expression)
"org.apache.spark.unsafe.types.UTF8String.fromString" +
s"(org.apache.commons.codec.digest.DigestUtils.md5Hex($c))")
}
+
+}
+
+/**
+ * A function that calculates an SHA-1 digest and returns it as a hex
string
+ * For input of type [[BinaryType]]
+ */
+case class Sha1(child: Expression)
+ extends UnaryExpression with ExpectsInputTypes {
+
+ override def dataType: DataType = StringType
+
+ override def expectedChildTypes: Seq[DataType] = Seq(BinaryType)
+
+ override def eval(input: InternalRow): Any = {
+ val value = child.eval(input)
+ if (value == null) {
+ null
+ } else {
+
UTF8String.fromString(DigestUtils.shaHex(value.asInstanceOf[Array[Byte]]))
+ }
+ }
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ defineCodeGen(ctx, ev, c =>
+ "org.apache.spark.unsafe.types.UTF8String.fromString(" +
+ s"org.apache.commons.codec.digest.DigestUtils.shaHex($c))"
+ )
+ }
+
+}
+
+/**
+ * A function that computes a cyclic redundancy check value and returns it
as a bigint
+ * For input of type [[BinaryType]]
+ */
+case class Crc32(child: Expression)
+ extends UnaryExpression with ExpectsInputTypes {
+
+ override def dataType: DataType = LongType
+
+ override def expectedChildTypes: Seq[DataType] = Seq(BinaryType)
+
+ override def eval(input: InternalRow): Any = {
+ val value = child.eval(input)
+ if (value == null) {
+ null
+ } else {
+ val checksum = new CRC32
+ checksum.update(value.asInstanceOf[Array[Byte]], 0,
value.asInstanceOf[Array[Byte]].length)
+ checksum.getValue
+ }
+ }
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ val value = child.gen(ctx)
+ val CRC32 = "java.util.zip.CRC32"
+ s"""
+ ${value.code}
+ boolean ${ev.isNull} = ${value.isNull};
+ ${ctx.javaType(dataType)} ${ev.primitive} =
${ctx.defaultValue(dataType)};
--- End diff --
nit: We could use `long` here, since `dataType` is LongType, this could
make the Java template easy to understand.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
