CTTY commented on code in PR #16936:
URL: https://github.com/apache/iceberg/pull/16936#discussion_r3858132869
##########
core/src/main/java/org/apache/iceberg/TrackedFileAdapters.java:
##########
@@ -405,6 +458,508 @@ public DeleteFile copyWithStats(Set<Integer>
requestedColumnIds) {
}
}
+ /** Shared base for content-file (DATA / EQUALITY_DELETES) write-direction
wrappers. */
+ abstract static class ContentTrackedFile<F extends ContentFile<F>>
+ implements TrackedFile, StructLike {
+ private final int formatVersion;
+ private final Types.StructType partitionType;
+ private final MapBackedContentStats statsWrapper;
+
+ private Tracking tracking;
+ private F file;
+ private StructProjection partition;
+ private ContentStats stats;
+
+ ContentTrackedFile(
+ int formatVersion,
+ Schema tableSchema,
+ MetricsConfig metricsConfig,
+ Types.StructType partitionType) {
+ Preconditions.checkArgument(
+ formatVersion >=
TableMetadata.MIN_FORMAT_VERSION_ADAPTIVE_MANIFEST_TREE,
+ "Invalid format version for adaptive manifest tree: %s (must be >=
%s)",
+ formatVersion,
+ TableMetadata.MIN_FORMAT_VERSION_ADAPTIVE_MANIFEST_TREE);
+ Preconditions.checkArgument(tableSchema != null, "Invalid table schema:
null");
+ Preconditions.checkArgument(metricsConfig != null, "Invalid metrics
config: null");
+ Preconditions.checkArgument(partitionType != null, "Invalid partition
type: null");
+ this.formatVersion = formatVersion;
+ this.partitionType = partitionType;
+ this.statsWrapper = new MapBackedContentStats(tableSchema,
metricsConfig);
+ }
+
+ void wrapWithTracking(F newFile, Tracking newTracking) {
+ Preconditions.checkArgument(newFile != null, "Invalid file: null");
+ Preconditions.checkArgument(newTracking != null, "Invalid tracking:
null");
+ validateContent(newFile);
+
+ this.file = newFile;
+ this.partition = projectPartition(newFile, partitionType);
+ this.stats = statsWrapper.wrap(newFile);
+ this.tracking = newTracking;
+ }
+
+ /** 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 formatVersion;
+ }
+
+ @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");
Review Comment:
Trying to understand better here: does this mean the writer needs to
materialize the adapter before writing the current tracked file, so the adapter
can be reused by the next writer? This means the writer will need to use the
adapter synchronously, correct?
--
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]
