Github user jose-torres commented on a diff in the pull request:
https://github.com/apache/spark/pull/22009#discussion_r208982830
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/sources/v2/BatchReadSupportProvider.java
---
@@ -18,19 +18,22 @@
package org.apache.spark.sql.sources.v2;
import org.apache.spark.annotation.InterfaceStability;
-import org.apache.spark.sql.sources.DataSourceRegister;
-import org.apache.spark.sql.sources.v2.reader.DataSourceReader;
+import org.apache.spark.sql.execution.datasources.v2.DataSourceV2Utils;
+import org.apache.spark.sql.sources.v2.reader.BatchReadSupport;
import org.apache.spark.sql.types.StructType;
/**
* A mix-in interface for {@link DataSourceV2}. Data sources can implement
this interface to
- * provide data reading ability and scan the data from the data source.
+ * provide data reading ability for batch processing.
+ *
+ * This interface is used when end users want to use a data source
implementation directly, e.g.
+ * {@code SparkSession.read.format(...).option(...).load()}.
*/
@InterfaceStability.Evolving
-public interface ReadSupport extends DataSourceV2 {
+public interface BatchReadSupportProvider extends DataSourceV2 {
/**
- * Creates a {@link DataSourceReader} to scan the data from this data
source.
+ * Creates a {@link BatchReadSupport} to scan the data from this data
source.
--- End diff --
nit: ... from this data source with a user specified schema.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
