szehon-ho commented on a change in pull request #3400:
URL: https://github.com/apache/iceberg/pull/3400#discussion_r739424911
##########
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:
Curious, does Iceberg support rename of partition fields?
##########
File path: api/src/main/java/org/apache/iceberg/types/IndexByName.java
##########
@@ -177,10 +189,15 @@ private void addField(String name, int fieldId) {
// also track the short name, if this is a nested field
if (!shortFieldNames.isEmpty()) {
- String shortName =
DOT.join(DOT.join(shortFieldNames.descendingIterator()), name);
+ Iterator<String> quotedShortFieldNames =
Iterators.transform(shortFieldNames.descendingIterator(), this::quote);
+ String shortName = DOT.join(DOT.join(quotedShortFieldNames),
quote(name));
Review comment:
Same as above
##########
File path: api/src/main/java/org/apache/iceberg/types/IndexByName.java
##########
@@ -166,9 +177,10 @@ public void afterMapValue(Types.NestedField valueField) {
}
private void addField(String name, int fieldId) {
- String fullName = name;
+ String fullName = quote(name);
if (!fieldNames.isEmpty()) {
- fullName = DOT.join(DOT.join(fieldNames.descendingIterator()), name);
+ Iterator<String> quotedFieldNames =
Iterators.transform(fieldNames.descendingIterator(), this::quote);
+ fullName = DOT.join(DOT.join(quotedFieldNames), quote(name));
Review comment:
Can we replace quote(name) with 'fullName' variable already computed
above?
--
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]
