ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-4513][SQL] Support relational operator '<=>' in Spark SQL

Browse source 
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
This commit is contained in:
ravipesala 2014-11-20 15:34:03 -08:00 committed by Michael Armbrust
parent 1c53a5db99
commit 98e9419784
3 changed files with 14 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SparkSQLParser.scala
View file

@ -61,7 +61,7 @@ class SqlLexical(val keywords: Seq[String]) extends StdLexical {
delimiters += (
"@", "*", "+", "-", "<", "=", "<>", "!=", "<=", ">=", ">", "/", "(", ")",
",", ";", "%", "{", "}", ":", "[", "]", ".", "&", "|", "^", "~"
",", ";", "%", "{", "}", ":", "[", "]", ".", "&", "|", "^", "~", "<=>"
)
override lazy val token: Parser[Token] =

1
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala
View file

@ -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))

12
sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
View file

@ -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)))
}
}