From 94f7a12b3c8e4a6ecd969893e562feb7ffba4c24 Mon Sep 17 00:00:00 2001
From: hyukjinkwon <gurwls223@gmail.com>
Date: Sat, 2 Jan 2016 00:04:48 -0800
Subject: [PATCH] [SPARK-10180][SQL] JDBC datasource are not processing
EqualNullSafe filter
This PR is followed by https://github.com/apache/spark/pull/8391.
Previous PR fixes JDBCRDD to support null-safe equality comparison for JDBC datasource. This PR fixes the problem that it can actually return null as a result of the comparison resulting error as using the value of that comparison.
Author: hyukjinkwon <gurwls223@gmail.com>
Author: HyukjinKwon <gurwls223@gmail.com>
Closes #8743 from HyukjinKwon/SPARK-10180.
---
.../spark/sql/execution/datasources/jdbc/JDBCRDD.scala | 4 +++-
.../src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala | 5 ++++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala
index c74574d280..87d43addd3 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala
@@ -193,6 +193,9 @@ private[sql] object JDBCRDD extends Logging {
private def compileFilter(f: Filter): Option[String] = {
Option(f match {
case EqualTo(attr, value) => s"$attr = ${compileValue(value)}"
+ case EqualNullSafe(attr, value) =>
+ s"(NOT ($attr != ${compileValue(value)} OR $attr IS NULL OR " +
+ s"${compileValue(value)} IS NULL) OR ($attr IS NULL AND ${compileValue(value)} IS NULL))"
case LessThan(attr, value) => s"$attr < ${compileValue(value)}"
case GreaterThan(attr, value) => s"$attr > ${compileValue(value)}"
case LessThanOrEqual(attr, value) => s"$attr <= ${compileValue(value)}"
@@ -320,7 +323,6 @@ private[sql] class JDBCRDD(
if (sb.length == 0) "1" else sb.substring(1)
}
-
/**
* `filters`, but as a WHERE clause suitable for injection into a SQL query.
*/
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
index 633ae215fc..dae72e8acb 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
@@ -185,6 +185,7 @@ class JDBCSuite extends SparkFunSuite
assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE THEID != 2")).collect().size == 2)
assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE THEID = 1")).collect().size == 1)
assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE NAME = 'fred'")).collect().size == 1)
+ assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE NAME <=> 'fred'")).collect().size == 1)
assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE NAME > 'fred'")).collect().size == 2)
assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE NAME != 'fred'")).collect().size == 2)
assert(stripSparkFilter(sql("SELECT * FROM foobar WHERE NAME IN ('mary', 'fred')"))
@@ -473,7 +474,9 @@ class JDBCSuite extends SparkFunSuite
=== "(NOT (col1 IN ('mno', 'pqr')))")
assert(doCompileFilter(IsNull("col1")) === "col1 IS NULL")
assert(doCompileFilter(IsNotNull("col1")) === "col1 IS NOT NULL")
- assert(doCompileFilter(And(EqualNullSafe("col0", "abc"), EqualTo("col1", "def"))) === "")
+ assert(doCompileFilter(And(EqualNullSafe("col0", "abc"), EqualTo("col1", "def")))
+ === "((NOT (col0 != 'abc' OR col0 IS NULL OR 'abc' IS NULL) "
+ + "OR (col0 IS NULL AND 'abc' IS NULL))) AND (col1 = 'def')")
}
test("Dialect unregister") {
--
GitLab