rdblue commented on code in PR #16936:
URL: https://github.com/apache/iceberg/pull/16936#discussion_r4170120477
##########
core/src/main/java/org/apache/iceberg/TrackedFileAdapters.java:
##########
@@ -552,6 +609,511 @@ public ManifestFile copy() {
}
}
+ /** Shared base for content-file (DATA / EQUALITY_DELETES) write-direction
wrappers. */
+ abstract static class ContentTrackedFile<F extends ContentFile<F>>
+ implements TrackedFile, StructLike {
+ private final Types.StructType partitionType;
+ private final MapBackedContentStats statsWrapper;
+
+ private Tracking tracking;
+ private F file;
+ private StructProjection partition;
+ private ContentStats stats;
+
+ ContentTrackedFile(Schema writeSchema) {
+ Preconditions.checkArgument(writeSchema != null, "Invalid write schema:
null");
+ Types.StructType statsType = nestedStruct(writeSchema,
TrackedFile.CONTENT_STATS_ID);
+ this.partitionType = nestedStruct(writeSchema, TrackedFile.PARTITION_ID);
+ this.statsWrapper = statsType != null ? new
MapBackedContentStats(statsType) : null;
+ }
+
+ TrackedFile wrapWithTracking(F newFile, Tracking newTracking) {
+ Preconditions.checkArgument(newFile != null, "Invalid file: null");
+ Preconditions.checkArgument(newTracking != null, "Invalid tracking:
null");
+ validateContent(newFile);
+
+ if (newFile instanceof TrackedContentFile) {
+ return ((TrackedContentFile<?>) newFile).file();
+ }
+
+ this.file = newFile;
+ this.partition = partitionType != null ? projectPartition(newFile,
partitionType) : null;
+ this.stats = statsWrapper != null ? statsWrapper.wrap(newFile) : null;
+ this.tracking = newTracking;
+ return this;
+ }
+
+ /** Content-type-specific validation of the wrapped file. */
+ abstract void validateContent(F newFile);
+
+ protected F file() {
+ return file;
+ }
+
+ @Override
+ public Tracking tracking() {
+ return tracking;
+ }
+
+ @Override
+ public int formatVersion() {
+ return TableMetadata.MIN_FORMAT_VERSION_PARQUET_MANIFESTS;
+ }
+
+ @Override
+ public String location() {
+ return file.location();
+ }
+
+ @Override
+ public FileFormat fileFormat() {
+ return file.format();
+ }
+
+ @Override
+ public long recordCount() {
+ return file.recordCount();
+ }
+
+ @Override
+ public long fileSizeInBytes() {
+ return file.fileSizeInBytes();
+ }
+
+ @Override
+ public Integer specId() {
+ return file.specId();
+ }
+
+ @Override
+ public StructLike partition() {
+ return partition;
+ }
+
+ @Override
+ public ContentStats contentStats() {
+ return stats;
+ }
+
+ @Override
+ public Integer sortOrderId() {
+ return null;
+ }
+
+ @Override
+ public DeletionVector deletionVector() {
+ return null;
+ }
+
+ @Override
+ public ManifestInfo manifestInfo() {
+ return null;
+ }
+
+ @Override
+ public ByteBuffer keyMetadata() {
+ return file.keyMetadata();
+ }
+
+ @Override
+ public List<Long> splitOffsets() {
+ return file.splitOffsets();
+ }
+
+ @Override
+ public List<Integer> equalityIds() {
+ return null;
+ }
+
+ @Override
+ public TrackedFile copy() {
+ throw new UnsupportedOperationException(
+ "Reusable content-file wrapper does not support copy(); materialize
via a writer instead");
+ }
+
+ @Override
+ public TrackedFile copyWithStats(Set<Integer> requestedColumnIds) {
+ throw new UnsupportedOperationException(
+ "Reusable content-file wrapper does not support copyWithStats()");
+ }
+
+ @Override
+ public int size() {
+ return TRACKED_FILE_FIELD_COUNT;
+ }
+
+ @Override
+ public <T> T get(int pos, Class<T> javaClass) {
+ return javaClass.cast(TrackedFileStruct.getByPos(this, pos));
+ }
+
+ @Override
+ public <T> void set(int pos, T value) {
+ throw new UnsupportedOperationException(
+ "Reusable content-file wrapper does not support set()");
+ }
+ }
+
+ /** Wraps a {@link DataFile} as a {@link TrackedFile} row. */
+ static class DataTrackedFile extends ContentTrackedFile<DataFile> {
Review Comment:
Good point about "to" in the name. I think I would still prefer
`DataFileAsTrackedFile` and `TrackedFileAsDataFile` to be more clear, but we
can discuss that later.
--
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]
