nastra commented on code in PR #17433:
URL: https://github.com/apache/iceberg/pull/17433#discussion_r3688450996
##########
core/src/main/java/org/apache/iceberg/V4ManifestReader.java:
##########
@@ -263,17 +297,62 @@ private Schema readSchema(boolean hasPartitionFilter) {
if (columns != null) {
Schema selected =
caseSensitive ? fullSchema.select(columns) :
fullSchema.caseInsensitiveSelect(columns);
- return addRequiredColumns(selected, hasPartitionFilter);
+ return addRequiredColumns(fullSchema, selected, hasPartitionFilter);
}
if (requestedProjection != null) {
- return addRequiredColumns(requestedProjection, hasPartitionFilter);
+ return addRequiredColumns(fullSchema, requestedProjection,
hasPartitionFilter);
}
return fullSchema;
}
- private Schema addRequiredColumns(Schema projection, boolean
hasPartitionFilter) {
+ /** Returns the schema of everything this reader may read, including
content stats. */
+ private Schema fullSchema() {
+ Types.StructType contentStatsType = contentStatsType();
+ Schema base = TrackedFile.schema(unionPartitionType, contentStatsType);
+ if (contentStatsType.fields().isEmpty()) {
+ // schema uses the unknown type for empty stats, which cannot be
paired with the stats
+ // struct in the manifest, so drop the field instead of reading it as
unknown
+ base = TypeUtil.selectNot(base,
ImmutableSet.of(TrackedFile.CONTENT_STATS_ID));
+ }
+
+ // the read schema carries row_position (via BASE_TYPE) so the reader
can fill manifestPos
+ return TypeUtil.replaceFieldTypes(
+ base, ImmutableMap.of(TrackedFile.TRACKING.fieldId(),
TrackingStruct.BASE_TYPE));
+ }
+
+ /** Returns the stats type to read, which is empty when no stats are
needed. */
+ private Types.StructType contentStatsType() {
+ Set<Integer> fieldIds = requiredStatsFieldIds();
Review Comment:
yep makes sense, updated
--
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]
