aokolnychyi commented on a change in pull request #3400:
URL: https://github.com/apache/iceberg/pull/3400#discussion_r740534412
##########
File path:
spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/source/SparkBatchQueryScan.java
##########
@@ -104,30 +144,100 @@
}
}
- if (splitSize != null) {
- scan = scan.option(TableProperties.SPLIT_SIZE, splitSize.toString());
+ for (Expression filter : filterExpressions()) {
+ scan = scan.filter(filter);
}
- if (splitLookback != null) {
- scan = scan.option(TableProperties.SPLIT_LOOKBACK,
splitLookback.toString());
+ try (CloseableIterable<FileScanTask> filesIterable = scan.planFiles()) {
+ this.files = Lists.newArrayList(filesIterable);
+ } catch (IOException e) {
+ throw new UncheckedIOException("Failed to close table scan: " + scan,
e);
}
+ }
- if (splitOpenFileCost != null) {
- scan = scan.option(TableProperties.SPLIT_OPEN_FILE_COST,
splitOpenFileCost.toString());
- }
+ return files;
+ }
- for (Expression filter : filterExpressions()) {
- scan = scan.filter(filter);
+ @Override
+ protected List<CombinedScanTask> tasks() {
+ if (tasks == null) {
+ CloseableIterable<FileScanTask> splitFiles = TableScanUtil.splitFiles(
+ CloseableIterable.withNoopClose(files()),
+ splitSize);
+ CloseableIterable<CombinedScanTask> scanTasks = TableScanUtil.planTasks(
+ splitFiles, splitSize,
+ splitLookback, splitOpenFileCost);
+ tasks = Lists.newArrayList(scanTasks);
+ }
+
+ return tasks;
+ }
+
+ @Override
+ public NamedReference[] filterAttributes() {
+ Set<Integer> partitionFieldSourceIds = Sets.newHashSet();
+
+ for (Integer specId : specIds()) {
+ PartitionSpec spec = table().specs().get(specId);
+ for (PartitionField field : spec.fields()) {
+ partitionFieldSourceIds.add(field.sourceId());
}
+ }
- try (CloseableIterable<CombinedScanTask> tasksIterable =
scan.planTasks()) {
- this.tasks = Lists.newArrayList(tasksIterable);
- } catch (IOException e) {
- throw new RuntimeIOException(e, "Failed to close table scan: %s",
scan);
+ Map<Integer, String> nameById =
TypeUtil.indexQuotedNameById(table().schema().asStruct());
Review comment:
Yeah, @rdblue is right. I'll add a test for the rename to be safe.
--
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]