[SPARK-48601][SQL] Give a more user friendly error message when setti…

…ng a null value for JDBC Option ### What changes were proposed in this pull request? In this PR, proposed changes add a check for validating that JDBC Option values are not null, and throw a user-friendly error in case that they are. ### Why are the changes needed? When setting a `null` value for JDBC Option, a spark internal exception is thrown due to java.lang.NullPointerException. A more user-friendly message should be thrown in such cases. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? A new test in this PR. ### Was this patch authored or co-authored using generative AI tooling? No Closes #46955 from stevomitric/stevomitric/fix-jdbcoptions. Authored-by: Stevo Mitric <[email protected]> Signed-off-by: Wenchen Fan <[email protected]>
apache · Jun 19, 2024 · 878dd6a · 878dd6a
1 parent 5e28e95
commit 878dd6a
Show file tree

Hide file tree

Showing 4 changed files with 36 additions and 2 deletions.
diff --git a/common/utils/src/main/resources/error/error-conditions.json b/common/utils/src/main/resources/error/error-conditions.json
@@ -3328,6 +3328,12 @@
     ],
     "sqlState" : "42000"
   },
+  "NULL_DATA_SOURCE_OPTION" : {
+    "message" : [
+      "Data source read/write option <option> cannot have null value."
+    ],
+    "sqlState" : "22024"
+  },
   "NULL_MAP_KEY" : {
     "message" : [
       "Cannot use null as map key."

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
@@ -175,6 +175,13 @@ private[sql] object QueryCompilationErrors extends QueryErrorsBase with Compilat
         "functionName" -> toSQLId(funcName)))
   }
 
+  def nullDataSourceOption(option: String): Throwable = {
+    new AnalysisException(
+      errorClass = "NULL_DATA_SOURCE_OPTION",
+      messageParameters = Map("option" -> option)
+    )
+  }
+
   def unorderablePivotColError(pivotCol: Expression): Throwable = {
     new AnalysisException(
       errorClass = "INCOMPARABLE_PIVOT_COLUMN",

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCOptions.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCOptions.scala
@@ -25,7 +25,7 @@ import org.apache.commons.io.FilenameUtils
 import org.apache.spark.SparkFiles
 import org.apache.spark.internal.Logging
 import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap
-import org.apache.spark.sql.errors.QueryExecutionErrors
+import org.apache.spark.sql.errors.{QueryCompilationErrors, QueryExecutionErrors}
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.types.TimestampNTZType
 import org.apache.spark.util.Utils
@@ -52,7 +52,14 @@ class JDBCOptions(
    */
   val asProperties: Properties = {
     val properties = new Properties()
-    parameters.originalMap.foreach { case (k, v) => properties.setProperty(k, v) }
+    parameters.originalMap.foreach { case (k, v) =>
+      // If an option value is `null`, throw a user-friendly error. Keys here cannot be null, as
+      // scala's implementation of Maps prohibits null keys.
+      if (v == null) {
+        throw QueryCompilationErrors.nullDataSourceOption(k)
+      }
+      properties.setProperty(k, v)
+    }
     properties
   }
 

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
@@ -369,6 +369,20 @@ class JDBCV2Suite extends QueryTest with SharedSparkSession with ExplainSuiteHel
     }
   }
 
+  test("null value for option exception") {
+    val df = spark.read
+      .option("pushDownOffset", null)
+      .table("h2.test.employee")
+    checkError(
+      exception = intercept[AnalysisException] {
+        df.collect()
+      },
+      errorClass = "NULL_DATA_SOURCE_OPTION",
+      parameters = Map(
+        "option" -> "pushDownOffset")
+    )
+  }
+
   test("simple scan with OFFSET") {
     val df1 = spark.read
       .table("h2.test.employee")