kamcheungting-db commented on code in PR #16582:
URL: https://github.com/apache/iceberg/pull/16582#discussion_r3312443944
##########
core/src/main/java/org/apache/iceberg/BasePartitionStatisticsScan.java:
##########
@@ -71,16 +91,46 @@ public CloseableIterable<PartitionStatistics> scan() {
return CloseableIterable.empty();
}
+ // Always read with the latest schema
Types.StructType partitionType = Partitioning.partitionType(table);
- Schema schema = PartitionStatistics.schema(partitionType,
TableUtil.formatVersion(table));
+ Schema schema = PartitionStatistics.latestSchema(partitionType);
+ Schema readSchema = readSchema(schema);
FileFormat fileFormat = FileFormat.fromFileName(statsFile.get().path());
Preconditions.checkNotNull(
fileFormat != null, "Unable to determine format of file: %s",
statsFile.get().path());
- return InternalData.read(fileFormat,
table.io().newInputFile(statsFile.get().path()))
- .project(schema)
- .setRootType(BasePartitionStatistics.class)
- .build();
+ CloseableIterable<PartitionStatistics> result =
+ InternalData.read(fileFormat,
table.io().newInputFile(statsFile.get().path()))
+ .project(readSchema)
+ .setRootType(BasePartitionStatistics.class)
+ .build();
+
+ if (filter != Expressions.alwaysTrue()) {
+ Evaluator evaluator = new Evaluator(readSchema.asStruct(), filter,
caseSensitive);
+ result = CloseableIterable.filter(result, evaluator::eval);
+ }
+
+ return result;
+ }
+
+ /**
+ * Resolves the schema to read. When a projection is set, all columns
referenced by the filter are
+ * added to the result not just the projected fields.
+ */
+ private Schema readSchema(Schema schema) {
+ if (projection == null) {
+ return schema;
+ }
Review Comment:
same comment above, if we support filter on the read builder, we can reduce
the unnecessary cost of projecting the columns inside filters.
--
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]
