bkietz commented on a change in pull request #8301:
URL: https://github.com/apache/arrow/pull/8301#discussion_r502461050
##########
File path: cpp/src/arrow/dataset/file_parquet.cc
##########
@@ -631,6 +631,39 @@ Result<FragmentVector>
ParquetFileFragment::SplitByRowGroup(
return fragments;
}
+Result<std::shared_ptr<Fragment>> ParquetFileFragment::Subset(
+ const std::shared_ptr<Expression>& predicate) {
+ RETURN_NOT_OK(EnsureCompleteMetadata());
+ ARROW_ASSIGN_OR_RAISE(auto row_groups, FilterRowGroups(*predicate));
+
+ ARROW_ASSIGN_OR_RAISE(auto new_fragment,
+ parquet_format_.MakeFragment(source_,
partition_expression(),
+ row_groups,
physical_schema_));
+ return new_fragment;
Review comment:
```suggestion
return checked_pointer_cast<ParquetFileFragment>(std::move(new_fragment));
```
##########
File path: cpp/src/arrow/dataset/file_parquet.h
##########
@@ -232,6 +232,10 @@ class ARROW_DS_EXPORT ParquetFileFragment : public
FileFragment {
/// \brief Ensure attached statistics are complete and the physical schema
is cached.
Status EnsureCompleteMetadata(parquet::arrow::FileReader* reader = NULLPTR);
+ /// \brief Return a filtered subset of the ParquetFileFragment.
+ Result<std::shared_ptr<Fragment>> Subset(const std::shared_ptr<Expression>&
predicate);
+ Result<std::shared_ptr<Fragment>> Subset(const std::vector<int>
row_group_ids);
Review comment:
```suggestion
Result<std::shared_ptr<ParquetFileFragment>> Subset(const
std::shared_ptr<Expression>& predicate);
Result<std::shared_ptr<ParquetFileFragment>> Subset(const std::vector<int>
row_group_ids);
```
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
