Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/23266#discussion_r240073831
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/sources/v2/SupportsBatchRead.java
---
@@ -20,14 +20,27 @@
import org.apache.spark.annotation.Evolving;
import org.apache.spark.sql.sources.v2.reader.Scan;
import org.apache.spark.sql.sources.v2.reader.ScanBuilder;
+import org.apache.spark.sql.types.StructType;
/**
- * An empty mix-in interface for {@link Table}, to indicate this table
supports batch scan.
- * <p>
- * If a {@link Table} implements this interface, its {@link
Table#newScanBuilder(DataSourceOptions)}
- * must return a {@link ScanBuilder} that builds {@link Scan} with {@link
Scan#toBatch()}
- * implemented.
- * </p>
+ * A mix-in interface for {@link Table} to provide data reading ability of
batch processing.
*/
@Evolving
-public interface SupportsBatchRead extends Table { }
+public interface SupportsBatchRead extends Table {
+
+ /**
+ * Returns the schema of this table.
+ */
+ StructType schema();
+
+ /**
+ * Returns a {@link ScanBuilder} which can be used to build a {@link
Scan} later. The built
+ * {@link Scan} must implement {@link Scan#toBatch()}. Spark will call
this method for each data
+ * scanning query.
+ * <p>
+ * The builder can take some query specific information to do operators
pushdown, and keep these
+ * information in the created {@link Scan}.
+ * </p>
+ */
+ ScanBuilder newScanBuilder(DataSourceOptions options);
--- End diff --
+1
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
