ahmedabu98 commented on code in PR #40229:
URL: https://github.com/apache/beam/pull/40229#discussion_r4086516944
##########
sdks/java/io/iceberg/src/main/java/org/apache/beam/sdk/io/iceberg/IcebergWriteSchemaTransformProvider.java:
##########
@@ -35,28 +44,37 @@
import org.apache.beam.sdk.schemas.transforms.SchemaTransform;
import org.apache.beam.sdk.schemas.transforms.SchemaTransformProvider;
import org.apache.beam.sdk.schemas.transforms.TypedSchemaTransformProvider;
+import org.apache.beam.sdk.schemas.transforms.providers.ErrorHandling;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.transforms.SimpleFunction;
import org.apache.beam.sdk.values.KV;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.sdk.values.PCollectionRowTuple;
import org.apache.beam.sdk.values.Row;
import
org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.annotations.VisibleForTesting;
+import
org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.ImmutableMap;
import org.apache.iceberg.DistributionMode;
import org.apache.iceberg.FileFormat;
import org.checkerframework.checker.nullness.qual.Nullable;
import org.joda.time.Duration;
/**
- * SchemaTransform implementation for {@link IcebergIO#writeRows}. Writes Beam
Rows to Iceberg and
- * outputs a {@code PCollection<Row>} representing snapshots created in the
process.
+ * SchemaTransform implementation for {@link IcebergIO#writeRows} and, when
the {@code cdc} block is
+ * set, {@link IcebergIO#writeCdcRows}. Outputs a {@code PCollection<Row>}
representing the
+ * snapshots created in the process; CDC writes add a {@code dead_letter}
output of late records.
*/
@AutoService(SchemaTransformProvider.class)
public class IcebergWriteSchemaTransformProvider
extends TypedSchemaTransformProvider<Configuration> {
static final String INPUT_TAG = "input";
static final String SNAPSHOTS_TAG = "snapshots";
+ static final String DEAD_LETTER_TAG = "dead_letter";
+ static final String ERRORS_TAG = "errors";
+
+ /** The default sequence-number column: what the CDC read source emits. */
+ private static final String DEFAULT_SEQUENCE_NUMBER_COLUMN =
Review Comment:
I'll remove both and just make everything reference
`IcebergCdcMetadataColumns.COMMIT_SNAPSHOT_SEQUENCE_NUMBER` directly
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]