cloud-fan commented on a change in pull request #23714:
[SPARK-26744][SQL]Support schema validation in FileDataSourceV2 framework
URL: https://github.com/apache/spark/pull/23714#discussion_r256791683
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileWriteBuilder.scala
##########
@@ -104,12 +104,24 @@ abstract class FileWriteBuilder(options:
DataSourceOptions)
options: Map[String, String],
dataSchema: StructType): OutputWriterFactory
+ /**
+ * Returns whether this format supports the given [[DataType]] in write path.
+ * By default all data types are supported.
+ */
+ def supportDataType(dataType: DataType): Boolean = true
+
private def validateInputs(): Unit = {
assert(schema != null, "Missing input data schema")
assert(queryId != null, "Missing query ID")
assert(mode != null, "Missing save mode")
assert(options.paths().length == 1)
DataSource.validateSchema(schema)
+ schema.foreach { field =>
+ if (!supportDataType(field.dataType)) {
+ throw new AnalysisException(
+ s"$this data source does not support ${field.dataType.catalogString}
data type.")
Review comment:
+1
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
