jorisvandenbossche commented on a change in pull request #8301:
URL: https://github.com/apache/arrow/pull/8301#discussion_r496842872
##########
File path: cpp/src/arrow/dataset/file_parquet.cc
##########
@@ -575,6 +575,39 @@ 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;
+}
+
+Result<std::shared_ptr<Fragment>> ParquetFileFragment::Subset(
+ const std::vector<int> row_group_ids) {
+ std::vector<RowGroupInfo> row_groups;
+
Review comment:
Here I would still need to check that all row_group_ids exist in the
fragment
----------------------------------------------------------------
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]
