stevenzwu commented on code in PR #13310:
URL: https://github.com/apache/iceberg/pull/13310#discussion_r2193559119
##########
spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/SparkTable.java:
##########
@@ -260,18 +260,52 @@ public MetadataColumn[] metadataColumns() {
DataType sparkPartitionType =
SparkSchemaUtil.convert(Partitioning.partitionType(table()));
ImmutableList.Builder<SparkMetadataColumn> metadataColumns =
ImmutableList.builder();
metadataColumns.add(
- new SparkMetadataColumn(MetadataColumns.SPEC_ID.name(),
DataTypes.IntegerType, true),
- new SparkMetadataColumn(MetadataColumns.PARTITION_COLUMN_NAME,
sparkPartitionType, true),
- new SparkMetadataColumn(MetadataColumns.FILE_PATH.name(),
DataTypes.StringType, false),
- new SparkMetadataColumn(MetadataColumns.ROW_POSITION.name(),
DataTypes.LongType, false),
- new SparkMetadataColumn(MetadataColumns.IS_DELETED.name(),
DataTypes.BooleanType, false));
-
- if (TableUtil.formatVersion(table()) >= 3) {
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.SPEC_ID.name())
+ .dataType(DataTypes.IntegerType)
+ .withNullability(true)
+ .build(),
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.PARTITION_COLUMN_NAME)
+ .dataType(sparkPartitionType)
+ .withNullability(true)
+ .build(),
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.FILE_PATH.name())
+ .dataType(DataTypes.StringType)
+ .withNullability(false)
+ .build(),
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.ROW_POSITION.name())
+ .dataType(DataTypes.LongType)
+ .withNullability(false)
+ .build(),
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.IS_DELETED.name())
+ .dataType(DataTypes.BooleanType)
+ .withNullability(false)
+ .build());
+
+ if (TableUtil.supportsRowLineage(icebergTable)) {
metadataColumns.add(
- new SparkMetadataColumn(MetadataColumns.ROW_ID.name(),
DataTypes.LongType, true));
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.ROW_ID.name())
+ .dataType(DataTypes.LongType)
+ .withNullability(true)
+ .preserveOnReinsert(true)
+ .preserveOnUpdate(true)
+ .preserveOnDelete(false)
+ .build());
+
metadataColumns.add(
- new SparkMetadataColumn(
- MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER.name(),
DataTypes.LongType, true));
+ SparkMetadataColumn.builder()
+ .name(MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER.name())
+ .dataType(DataTypes.LongType)
+ .withNullability(true)
+ .preserveOnReinsert(false)
Review Comment:
for compaction, shouldn't `last updated seq num` be preserved?
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
