From ea465af12ddae424af9b4e742c3d5aed2a0bc8ec Mon Sep 17 00:00:00 2001 From: ravipesala Date: Fri, 31 Oct 2014 11:33:20 -0700 Subject: [SPARK-4154][SQL] Query does not work if it has "not between " in Spark SQL and HQL if the query contains "not between" does not work like. SELECT * FROM src where key not between 10 and 20' Author: ravipesala Closes #3017 from ravipesala/SPARK-4154 and squashes the following commits: 65fc89e [ravipesala] Handled admin comments 32e6d42 [ravipesala] 'not between' is not working --- .../scala/org/apache/spark/sql/catalyst/SqlParser.scala | 6 ++++-- .../src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 5 +++++ .../src/main/scala/org/apache/spark/sql/hive/HiveQl.scala | 13 +++++++++---- .../org/apache/spark/sql/hive/execution/SQLQuerySuite.scala | 5 +++++ 4 files changed, 23 insertions(+), 6 deletions(-) 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 942b843104..b1e7570f57 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 @@ -232,8 +232,10 @@ 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 ~ (BETWEEN ~> termExpression) ~ (AND ~> termExpression) ^^ { - case e ~ el ~ eu => And(GreaterThanOrEqual(e, el), LessThanOrEqual(e, eu)) + | termExpression ~ NOT.? ~ (BETWEEN ~> termExpression) ~ (AND ~> termExpression) ^^ { + case e ~ not ~ el ~ eu => + val betweenExpr: Expression = And(GreaterThanOrEqual(e, el), LessThanOrEqual(e, eu)) + not.fold(betweenExpr)(f=> Not(betweenExpr)) } | termExpression ~ (RLIKE ~> termExpression) ^^ { case e1 ~ e2 => RLike(e1, e2) } | termExpression ~ (REGEXP ~> termExpression) ^^ { case e1 ~ e2 => RLike(e1, e2) } 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 4c36ca0f41..4acd92d33d 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 @@ -909,4 +909,9 @@ class SQLQuerySuite extends QueryTest with BeforeAndAfterAll { """.stripMargin), (1 to 100).map(i => Seq(i, i, i))) } + + test("SPARK-4154 Query does not work if it has 'not between' in Spark SQL and HQL") { + checkAnswer(sql("SELECT key FROM testData WHERE key not between 0 and 10 order by key"), + (11 to 100).map(i => Seq(i))) + } } diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 9d9d68affa..a3573e6502 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -985,15 +985,20 @@ private[hive] object HiveQl { In(nodeToExpr(value), list.map(nodeToExpr)) case Token("TOK_FUNCTION", Token(BETWEEN(), Nil) :: - Token("KW_FALSE", Nil) :: + kw :: target :: minValue :: maxValue :: Nil) => val targetExpression = nodeToExpr(target) - And( - GreaterThanOrEqual(targetExpression, nodeToExpr(minValue)), - LessThanOrEqual(targetExpression, nodeToExpr(maxValue))) + val betweenExpr = + And( + GreaterThanOrEqual(targetExpression, nodeToExpr(minValue)), + LessThanOrEqual(targetExpression, nodeToExpr(maxValue))) + kw match { + case Token("KW_FALSE", Nil) => betweenExpr + case Token("KW_TRUE", Nil) => Not(betweenExpr) + } /* Boolean Logic */ case Token(AND(), left :: right:: Nil) => And(nodeToExpr(left), nodeToExpr(right)) diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala index 4f96a327ee..76a0ec01a6 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala @@ -158,4 +158,9 @@ class SQLQuerySuite extends QueryTest { sql("SELECT case when ~1=-2 then 1 else 0 end FROM src"), sql("SELECT 1 FROM src").collect().toSeq) } + + test("SPARK-4154 Query does not work if it has 'not between' in Spark SQL and HQL") { + checkAnswer(sql("SELECT key FROM src WHERE key not between 0 and 10 order by key"), + sql("SELECT key FROM src WHERE key between 11 and 500 order by key").collect().toSeq) + } } -- cgit v1.2.3