rdblue commented on code in PR #18225:
URL: https://github.com/apache/iceberg/pull/18225#discussion_r4087789427
##########
core/src/test/java/org/apache/iceberg/TestV4ManifestReader.java:
##########
@@ -447,6 +485,86 @@ public void inheritanceAddedFileSequenceNumber(FileFormat
format) throws IOExcep
.containsExactly(MANIFEST_SEQ, 500L);
}
+ @ParameterizedTest
+ @FieldSource("MANIFEST_FORMATS")
+ public void inheritanceFirstRowId(FileFormat format) throws IOException {
+ Tracking trackingWithoutFirstRowId =
+ new TrackingStruct(EntryStatus.ADDED, SNAPSHOT_ID, null, null, null,
null, null, null);
+ TrackedFile withoutFirstRowId =
+ unpartitionedDataFile(trackingWithoutFirstRowId,
"s3://bucket/table/file-a.parquet");
+ Tracking trackingWithFirstRowId =
+ new TrackingStruct(EntryStatus.EXISTING, SNAPSHOT_ID, null, null,
null, 5_000L, null, null);
+ TrackedFile withFirstRowId =
+ unpartitionedDataFile(trackingWithFirstRowId,
"s3://bucket/table/file-c.parquet");
+
+ ManifestFile manifest =
+ writeManifest(
+ format, UNPARTITIONED_TYPE, ImmutableList.of(withoutFirstRowId,
withFirstRowId));
+ when(manifest.firstRowId()).thenReturn(10_000L);
+
+ V4ManifestReader.Builder builder =
+ V4ManifestReader.builder(manifest, IO, TABLE_SCHEMA,
ID_PARTITIONING_SPECS)
+ .metricsConfig(METRICS_CONFIG);
+ List<TrackedFile> actual = read(builder);
+
+ assertThat(actual)
+ .extracting(file -> file.tracking().firstRowId())
+ .containsExactly(10_000L, 5_000L);
+ }
+
+ @ParameterizedTest
+ @FieldSource("MANIFEST_FORMATS")
+ public void inheritanceUncommittedSkipsFirstRowId(FileFormat format) throws
IOException {
+ Tracking trackingWithoutFirstRowId =
+ new TrackingStruct(EntryStatus.ADDED, SNAPSHOT_ID, null, null, null,
null, null, null);
+ TrackedFile withoutFirstRowId =
+ unpartitionedDataFile(trackingWithoutFirstRowId,
"s3://bucket/table/file-a.parquet");
+ Tracking trackingWithFirstRowId =
+ new TrackingStruct(EntryStatus.EXISTING, SNAPSHOT_ID, null, null,
null, 5_000L, null, null);
+ TrackedFile withFirstRowId =
+ unpartitionedDataFile(trackingWithFirstRowId,
"s3://bucket/table/file-c.parquet");
+
+ ManifestFile manifest =
+ writeManifest(
+ format, UNPARTITIONED_TYPE, ImmutableList.of(withoutFirstRowId,
withFirstRowId));
+ when(manifest.firstRowId()).thenReturn(10_000L);
+
+ V4ManifestReader.Builder builder =
+ V4ManifestReader.uncommitted(manifest, IO, TABLE_SCHEMA,
ID_PARTITIONING_SPECS)
+ .metricsConfig(METRICS_CONFIG);
+ List<TrackedFile> actual = read(builder);
+
+ assertThat(actual)
+ .extracting(file -> file.tracking().firstRowId())
+ .containsExactly(null, 5_000L);
+ }
+
+ @ParameterizedTest
+ @FieldSource("MANIFEST_FORMATS")
+ public void inheritanceFirstRowIdNullFromUpgradedTable(FileFormat format)
throws IOException {
+ Tracking trackingWithoutFirstRowId =
+ new TrackingStruct(EntryStatus.ADDED, SNAPSHOT_ID, null, null, null,
null, null, null);
+ TrackedFile withoutFirstRowId =
+ unpartitionedDataFile(trackingWithoutFirstRowId,
"s3://bucket/table/file-a.parquet");
+ Tracking trackingWithFirstRowId =
+ new TrackingStruct(EntryStatus.EXISTING, SNAPSHOT_ID, null, null,
null, 5_000L, null, null);
+ TrackedFile withFirstRowId =
+ unpartitionedDataFile(trackingWithFirstRowId,
"s3://bucket/table/file-c.parquet");
+
+ ManifestFile manifest =
+ writeManifest(
+ format, UNPARTITIONED_TYPE, ImmutableList.of(withoutFirstRowId,
withFirstRowId));
+ // first row ID is null in upgraded tables, which is propagated to all
files
Review Comment:
You're right that we don't expect this to happen with v4 files because
having one means that we should have written `first_row_id` for every record.
While we don't expect this to ever happen, do we want to remove what happens if
it does? That would be a behavior difference between v4 and earlier versions.
Seems reasonable to me to keep the behavior to propagate null when the
manifest's value is null.
I could go either way, but I have a slight preference for preserving the
behavior, even if we don't expect it to be used.
--
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]
