From 98e9419784a9ad5096cfd563fa9a433786a90bd4 Mon Sep 17 00:00:00 2001
From: ravipesala <ravindra.pesala@huawei.com>
Date: Thu, 20 Nov 2014 15:34:03 -0800
Subject: [PATCH] [SPARK-4513][SQL] Support relational operator '<=>' in Spark
SQL
The relational operator '<=>' is not working in Spark SQL. Same works in Spark HiveQL
Author: ravipesala <ravindra.pesala@huawei.com>
Closes #3387 from ravipesala/<=> and squashes the following commits:
7198e90 [ravipesala] Supporting relational operator '<=>' in Spark SQL
---
.../apache/spark/sql/catalyst/SparkSQLParser.scala | 2 +-
.../org/apache/spark/sql/catalyst/SqlParser.scala | 1 +
.../scala/org/apache/spark/sql/SQLQuerySuite.scala | 12 ++++++++++++
3 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SparkSQLParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SparkSQLParser.scala
index f5c19ee69c..b198ed9936 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SparkSQLParser.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SparkSQLParser.scala
@@ -61,7 +61,7 @@ class SqlLexical(val keywords: Seq[String]) extends StdLexical {
delimiters += (
"@", "*", "+", "-", "<", "=", "<>", "!=", "<=", ">=", ">", "/", "(", ")",
- ",", ";", "%", "{", "}", ":", "[", "]", ".", "&", "|", "^", "~"
+ ",", ";", "%", "{", "}", ":", "[", "]", ".", "&", "|", "^", "~", "<=>"
)
override lazy val token: Parser[Token] =
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala
index affef276c2..dc1d349f10 100755
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala
@@ -234,6 +234,7 @@ class SqlParser extends AbstractSparkSQLParser {
| termExpression ~ (">=" ~> termExpression) ^^ { case e1 ~ e2 => GreaterThanOrEqual(e1, e2) }
| termExpression ~ ("!=" ~> termExpression) ^^ { case e1 ~ e2 => Not(EqualTo(e1, e2)) }
| termExpression ~ ("<>" ~> termExpression) ^^ { case e1 ~ e2 => Not(EqualTo(e1, e2)) }
+ | termExpression ~ ("<=>" ~> termExpression) ^^ { case e1 ~ e2 => EqualNullSafe(e1, e2) }
| termExpression ~ NOT.? ~ (BETWEEN ~> termExpression) ~ (AND ~> termExpression) ^^ {
case e ~ not ~ el ~ eu =>
val betweenExpr: Expression = And(GreaterThanOrEqual(e, el), LessThanOrEqual(e, eu))
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
index a63515464c..0a96831c76 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
@@ -973,4 +973,16 @@ class SQLQuerySuite extends QueryTest with BeforeAndAfterAll {
checkAnswer(sql("SELECT a.b + 1 FROM data GROUP BY a.b + 1"), 2)
dropTempTable("data")
}
+
+ test("Supporting relational operator '<=>' in Spark SQL") {
+ val nullCheckData1 = TestData(1,"1") :: TestData(2,null) :: Nil
+ val rdd1 = sparkContext.parallelize((0 to 1).map(i => nullCheckData1(i)))
+ rdd1.registerTempTable("nulldata1")
+ val nullCheckData2 = TestData(1,"1") :: TestData(2,null) :: Nil
+ val rdd2 = sparkContext.parallelize((0 to 1).map(i => nullCheckData2(i)))
+ rdd2.registerTempTable("nulldata2")
+ checkAnswer(sql("SELECT nulldata1.key FROM nulldata1 join " +
+ "nulldata2 on nulldata1.value <=> nulldata2.value"),
+ (1 to 2).map(i => Seq(i)))
+ }
}
--
GitLab