From 7ab951885fd34aa8184b70a3a39b865a239e5052 Mon Sep 17 00:00:00 2001
From: Jen-Ming Chung <jenmingisme@gmail.com>
Date: Thu, 17 Aug 2017 15:59:45 -0700
Subject: [PATCH] [SPARK-21677][SQL] json_tuple throws NullPointException when
column is null as string type
## What changes were proposed in this pull request?
``` scala
scala> Seq(("""{"Hyukjin": 224, "John": 1225}""")).toDS.selectExpr("json_tuple(value, trim(null))").show()
...
java.lang.NullPointerException
at ...
```
Currently the `null` field name will throw NullPointException. As a given field name null can't be matched with any field names in json, we just output null as its column value. This PR achieves it by returning a very unlikely column name `__NullFieldName` in evaluation of the field names.
## How was this patch tested?
Added unit test.
Author: Jen-Ming Chung <jenmingisme@gmail.com>
Closes #18930 from jmchung/SPARK-21677.
---
.../expressions/jsonExpressions.scala | 8 ++---
.../expressions/JsonExpressionsSuite.scala | 10 ++++++
.../sql-tests/inputs/json-functions.sql | 6 ++++
.../sql-tests/results/json-functions.sql.out | 34 ++++++++++++++++++-
4 files changed, 53 insertions(+), 5 deletions(-)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
index 17b605438d..c3757373a3 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
@@ -362,9 +362,9 @@ case class JsonTuple(children: Seq[Expression])
@transient private lazy val fieldExpressions: Seq[Expression] = children.tail
// eagerly evaluate any foldable the field names
- @transient private lazy val foldableFieldNames: IndexedSeq[String] = {
+ @transient private lazy val foldableFieldNames: IndexedSeq[Option[String]] = {
fieldExpressions.map {
- case expr if expr.foldable => expr.eval().asInstanceOf[UTF8String].toString
+ case expr if expr.foldable => Option(expr.eval()).map(_.asInstanceOf[UTF8String].toString)
case _ => null
}.toIndexedSeq
}
@@ -417,7 +417,7 @@ case class JsonTuple(children: Seq[Expression])
val fieldNames = if (constantFields == fieldExpressions.length) {
// typically the user will provide the field names as foldable expressions
// so we can use the cached copy
- foldableFieldNames
+ foldableFieldNames.map(_.orNull)
} else if (constantFields == 0) {
// none are foldable so all field names need to be evaluated from the input row
fieldExpressions.map(_.eval(input).asInstanceOf[UTF8String].toString)
@@ -426,7 +426,7 @@ case class JsonTuple(children: Seq[Expression])
// prefer the cached copy when available
foldableFieldNames.zip(fieldExpressions).map {
case (null, expr) => expr.eval(input).asInstanceOf[UTF8String].toString
- case (fieldName, _) => fieldName
+ case (fieldName, _) => fieldName.orNull
}
}
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
index f892e80204..1cd2b4fc18 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
@@ -363,6 +363,16 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
InternalRow(UTF8String.fromString("b\nc")))
}
+ test("SPARK-21677: json_tuple throws NullPointException when column is null as string type") {
+ checkJsonTuple(
+ JsonTuple(Literal("""{"f1": 1, "f2": 2}""") ::
+ NonFoldableLiteral("f1") ::
+ NonFoldableLiteral("cast(NULL AS STRING)") ::
+ NonFoldableLiteral("f2") ::
+ Nil),
+ InternalRow(UTF8String.fromString("1"), null, UTF8String.fromString("2")))
+ }
+
val gmtId = Option(DateTimeUtils.TimeZoneGMT.getID)
test("from_json") {
diff --git a/sql/core/src/test/resources/sql-tests/inputs/json-functions.sql b/sql/core/src/test/resources/sql-tests/inputs/json-functions.sql
index b3cc2cea51..5a46fb4321 100644
--- a/sql/core/src/test/resources/sql-tests/inputs/json-functions.sql
+++ b/sql/core/src/test/resources/sql-tests/inputs/json-functions.sql
@@ -20,3 +20,9 @@ select from_json('{"a":1}', 'a InvalidType');
select from_json('{"a":1}', 'a INT', named_struct('mode', 'PERMISSIVE'));
select from_json('{"a":1}', 'a INT', map('mode', 1));
select from_json();
+-- json_tuple
+SELECT json_tuple('{"a" : 1, "b" : 2}', CAST(NULL AS STRING), 'b', CAST(NULL AS STRING), 'a');
+CREATE TEMPORARY VIEW jsonTable(jsonField, a) AS SELECT * FROM VALUES ('{"a": 1, "b": 2}', 'a');
+SELECT json_tuple(jsonField, 'b', CAST(NULL AS STRING), a) FROM jsonTable;
+-- Clean up
+DROP VIEW IF EXISTS jsonTable;
diff --git a/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out b/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out
index 22da20d9a9..ae21d00116 100644
--- a/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out
@@ -1,5 +1,5 @@
-- Automatically generated by SQLQueryTestSuite
--- Number of queries: 17
+-- Number of queries: 21
-- !query 0
@@ -178,3 +178,35 @@ struct<>
-- !query 16 output
org.apache.spark.sql.AnalysisException
Invalid number of arguments for function from_json; line 1 pos 7
+
+
+-- !query 17
+SELECT json_tuple('{"a" : 1, "b" : 2}', CAST(NULL AS STRING), 'b', CAST(NULL AS STRING), 'a')
+-- !query 17 schema
+struct<c0:string,c1:string,c2:string,c3:string>
+-- !query 17 output
+NULL 2 NULL 1
+
+
+-- !query 18
+CREATE TEMPORARY VIEW jsonTable(jsonField, a) AS SELECT * FROM VALUES ('{"a": 1, "b": 2}', 'a')
+-- !query 18 schema
+struct<>
+-- !query 18 output
+
+
+
+-- !query 19
+SELECT json_tuple(jsonField, 'b', CAST(NULL AS STRING), a) FROM jsonTable
+-- !query 19 schema
+struct<c0:string,c1:string,c2:string>
+-- !query 19 output
+2 NULL 1
+
+
+-- !query 20
+DROP VIEW IF EXISTS jsonTable
+-- !query 20 schema
+struct<>
+-- !query 20 output
+
--
GitLab