[SPARK-17160] Properly escape field names in code-generated error messages

This patch addresses a corner-case escaping bug where field names which contain special characters were unsafely interpolated into error message string literals in generated Java code, leading to compilation errors.

This patch addresses these issues by using `addReferenceObj` to store the error messages as string fields rather than inline string constants.

Author: Josh Rosen <joshrosen@databricks.com>

Closes #15156 from JoshRosen/SPARK-17160.

1 files changed, 12 insertions, 1 deletions

diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CodeGenerationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CodeGenerationSuite.scala
index 0532cf5113..45dcfcaf23 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CodeGenerationSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CodeGenerationSuite.scala
@@ -23,7 +23,7 @@ import org.apache.spark.sql.Row
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.expressions.codegen._
-import org.apache.spark.sql.catalyst.expressions.objects.CreateExternalRow
+import org.apache.spark.sql.catalyst.expressions.objects.{CreateExternalRow, GetExternalRowField, ValidateExternalType}
 import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, GenericArrayData}
 import org.apache.spark.sql.types._
 import org.apache.spark.unsafe.types.UTF8String
@@ -265,4 +265,15 @@ class CodeGenerationSuite extends SparkFunSuite with ExpressionEvalHelper {
       Literal.create("\\\\u001/Compilation error occurs", StringType) :: Nil)
 
   }
+
+  test("SPARK-17160: field names are properly escaped by GetExternalRowField") {
+    val inputObject = BoundReference(0, ObjectType(classOf[Row]), nullable = true)
+    GenerateUnsafeProjection.generate(
+      ValidateExternalType(
+        GetExternalRowField(inputObject, index = 0, fieldName = "\"quote"), IntegerType) :: Nil)
+  }
+
+  test("SPARK-17160: field names are properly escaped by AssertTrue") {
+    GenerateUnsafeProjection.generate(AssertTrue(Cast(Literal("\""), BooleanType)) :: Nil)
+  }
 }