chenjunjiedada commented on a change in pull request #2364:
URL: https://github.com/apache/iceberg/pull/2364#discussion_r679859836
##########
File path: data/src/main/java/org/apache/iceberg/data/DeleteFilter.java
##########
@@ -139,43 +173,122 @@ protected long pos(T record) {
CloseableIterable.transform(CloseableIterable.concat(deleteRecords),
Record::copy),
deleteSchema.asStruct());
- Predicate<T> isInDeleteSet = record ->
deleteSet.contains(projectRow.wrap(asStructLike(record)));
- isInDeleteSets.add(isInDeleteSet);
+ isDeleted = isDeleted == null ? record ->
deleteSet.contains(projectRow.wrap(asStructLike(record))) :
+ isDeleted.or(record ->
deleteSet.contains(projectRow.wrap(asStructLike(record))));
}
- return isInDeleteSets;
+ return isDeleted;
}
- public CloseableIterable<T> findEqualityDeleteRows(CloseableIterable<T>
records) {
+ private Predicate<T> buildPosDeletePredicate() {
+ if (posDeletes.isEmpty()) {
+ return null;
+ }
+
+ List<CloseableIterable<Record>> deletes = Lists.transform(posDeletes,
this::openPosDeletes);
+ Set<Long> deleteSet = Deletes.toPositionSet(dataFile.path(),
CloseableIterable.concat(deletes));
+ if (deleteSet.isEmpty()) {
+ return null;
+ }
+
+ return record -> deleteSet.contains(pos(record));
+ }
+
+ public CloseableIterable<T> keepRowsFromDeletes(CloseableIterable<T>
records) {
+ Predicate<T> isDeletedFromPosDeletes = buildPosDeletePredicate();
+ if (isDeletedFromPosDeletes == null) {
+ return keepRowsFromEqualityDeletes(records);
+ }
+
+ Predicate<T> isDeletedFromEqDeletes = buildEqDeletePredicate();
+ if (isDeletedFromEqDeletes == null) {
+ return keepRowsFromPosDeletes(records);
+ }
+
+ CloseableIterable<T> markedRecords;
+
+ if (posDeletes.stream().mapToLong(DeleteFile::recordCount).sum() <
setFilterThreshold) {
+ markedRecords = CloseableIterable.transform(records, record -> {
+ if (isDeletedFromPosDeletes.test(record) ||
isDeletedFromEqDeletes.test(record)) {
+ deleteMarker().accept(record);
+ }
+ return record;
+ });
+
+ } else {
+ List<CloseableIterable<Record>> deletes = Lists.transform(posDeletes,
this::openPosDeletes);
+ markedRecords =
CloseableIterable.transform(Deletes.streamingDeletedRowMarker(records,
this::pos,
Review comment:
Updated to open one by one.
--
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]
