amogh-jahagirdar commented on code in PR #12736:
URL: https://github.com/apache/iceberg/pull/12736#discussion_r2060870333
##########
spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkTable.java:
##########
@@ -258,23 +256,16 @@ public Set<TableCapability> capabilities() {
@Override
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, false),
- 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) {
- metadataColumns.add(
- new SparkMetadataColumn(MetadataColumns.ROW_ID.name(),
DataTypes.LongType, true));
- metadataColumns.add(
- new SparkMetadataColumn(
- MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER.name(),
DataTypes.LongType, true));
- }
-
- return metadataColumns.build().toArray(SparkMetadataColumn[]::new);
+ return new MetadataColumn[] {
+ new SparkMetadataColumn(MetadataColumns.SPEC_ID.name(),
DataTypes.IntegerType, false),
+ 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),
+ new SparkMetadataColumn(MetadataColumns.ROW_ID.name(),
DataTypes.LongType, true),
+ new SparkMetadataColumn(
+ MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER.name(),
DataTypes.LongType, true)
+ };
Review Comment:
Changed this to always allow projecting row lineage columns regardless of
format version. For the unsupported format versions, it'll return null
##########
spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkTable.java:
##########
@@ -258,23 +256,16 @@ public Set<TableCapability> capabilities() {
@Override
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, false),
- 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) {
- metadataColumns.add(
- new SparkMetadataColumn(MetadataColumns.ROW_ID.name(),
DataTypes.LongType, true));
- metadataColumns.add(
- new SparkMetadataColumn(
- MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER.name(),
DataTypes.LongType, true));
- }
-
- return metadataColumns.build().toArray(SparkMetadataColumn[]::new);
+ return new MetadataColumn[] {
+ new SparkMetadataColumn(MetadataColumns.SPEC_ID.name(),
DataTypes.IntegerType, false),
+ 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),
+ new SparkMetadataColumn(MetadataColumns.ROW_ID.name(),
DataTypes.LongType, true),
+ new SparkMetadataColumn(
+ MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER.name(),
DataTypes.LongType, true)
+ };
Review Comment:
Changed this to always allow projecting row lineage columns regardless of
format version. For the unsupported format versions, it'll return null for the
row IDs
--
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]
