sadhen commented on a change in pull request #32026:
URL: https://github.com/apache/spark/pull/32026#discussion_r606088240
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowEvalPythonExec.scala
##########
@@ -89,9 +89,57 @@ case class ArrowEvalPythonExec(udfs: Seq[PythonUDF],
resultAttrs: Seq[Attribute]
columnarBatchIter.flatMap { batch =>
val actualDataTypes = (0 until batch.numCols()).map(i =>
batch.column(i).dataType())
- assert(outputTypes == actualDataTypes, "Invalid schema from pandas_udf:
" +
- s"expected ${outputTypes.mkString(", ")}, got
${actualDataTypes.mkString(", ")}")
+ assert(plainSchemaSeq(outputTypes) == actualDataTypes,
+ "Incompatible schema from pandas_udf: " +
+ s"expected ${outputTypes.mkString(", ")}, got
${actualDataTypes.mkString(", ")}")
batch.rowIterator.asScala
}
}
+
+ private def plainSchemaSeq(schema: Seq[DataType]): Seq[DataType] = {
+ schema.map(v => ArrowEvalPythonExec.plainSchema(v)).toList
+ }
+
+}
+
+private[sql] object ArrowEvalPythonExec {
+ /**
+ * Erase User-Defined Types and returns the plain Spark StructType instead.
+ *
+ * UserDefinedType:
+ * - will be erased as dt.sqlType
+ * - recursively rewrite internal ArrayType with `containsNull=true`
+ * ArrayType: containsNull will always be true when returned by PyArrow
Review comment:
link to python code added.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
