[SPARK-20910][SQL] Add build-in SQL function - UUID

## What changes were proposed in this pull request? Add build-int SQL function - UUID. ## How was this patch tested? unit tests Author: Yuming Wang <[email protected]> Closes apache#18136 from wangyum/SPARK-20910.
DoufuX · Jun 1, 2017 · 6d05c1c · 6d05c1c
1 parent c8045f8
commit 6d05c1c
Show file tree

Hide file tree

Showing 5 changed files with 46 additions and 1 deletion.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
@@ -380,6 +380,7 @@ object FunctionRegistry {
     expression[AssertTrue]("assert_true"),
     expression[Crc32]("crc32"),
     expression[Md5]("md5"),
+    expression[Uuid]("uuid"),
     expression[Murmur3Hash]("hash"),
     expression[Sha1]("sha"),
     expression[Sha1]("sha1"),

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
@@ -17,9 +17,12 @@
 
 package org.apache.spark.sql.catalyst.expressions
 
+import java.util.UUID
+
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.types._
+import org.apache.spark.unsafe.types.UTF8String
 
 /**
  * Print the result of an expression to stderr (used for debugging codegen).
@@ -104,3 +107,28 @@ case class CurrentDatabase() extends LeafExpression with Unevaluable {
   override def nullable: Boolean = false
   override def prettyName: String = "current_database"
 }
+
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+  usage = "_FUNC_() - Returns an universally unique identifier (UUID) string. The value is returned as a canonical UUID 36-character string.",
+  extended = """
+    Examples:
+      > SELECT _FUNC_();
+       46707d92-02f4-4817-8116-a4c3b23e6266
+  """)
+// scalastyle:on line.size.limit
+case class Uuid() extends LeafExpression {
+
+  override def deterministic: Boolean = false
+
+  override def nullable: Boolean = false
+
+  override def dataType: DataType = StringType
+
+  override def eval(input: InternalRow): Any = UTF8String.fromString(UUID.randomUUID().toString)
+
+  override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+    ev.copy(code = s"final UTF8String ${ev.value} = " +
+      s"UTF8String.fromString(java.util.UUID.randomUUID().toString());", isNull = "false")
+  }
+}
diff --git a/...alyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/MiscExpressionsSuite.scala b/...alyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/MiscExpressionsSuite.scala
@@ -39,4 +39,9 @@ class MiscExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     checkEvaluation(AssertTrue(Cast(Literal(1), BooleanType)), null)
   }
 
+  test("uuid") {
+    checkEvaluation(Length(Uuid()), 36)
+    assert(evaluate(Uuid()) !== evaluate(Uuid()))
+  }
+
 }
diff --git a/sql/core/src/test/resources/sql-tests/inputs/string-functions.sql b/sql/core/src/test/resources/sql-tests/inputs/string-functions.sql
@@ -12,3 +12,6 @@ FROM (SELECT id col1, id col2, id col3, id col4 FROM range(10)) t;
 -- replace function
 select replace('abc', 'b', '123');
 select replace('abc', 'b');
+
+-- uuid
+select length(uuid()), (uuid() <> uuid());
diff --git a/sql/core/src/test/resources/sql-tests/results/string-functions.sql.out b/sql/core/src/test/resources/sql-tests/results/string-functions.sql.out
@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 6
+-- Number of queries: 7
 
 
 -- !query 0
@@ -70,3 +70,11 @@ select replace('abc', 'b')
 struct<replace(abc, b, ):string>
 -- !query 5 output
 ac
+
+
+-- !query 6
+select length(uuid()), (uuid() <> uuid())
+-- !query 6 schema
+struct<length(uuid()):int,(NOT (uuid() = uuid())):boolean>
+-- !query 6 output
+36	true