bkietz commented on a change in pull request #7704:
URL: https://github.com/apache/arrow/pull/7704#discussion_r453715480
##########
File path: cpp/src/parquet/arrow/reader.cc
##########
@@ -780,11 +741,29 @@ Status GetReader(const SchemaField& field, const
std::shared_ptr<ReaderContext>&
Status FileReaderImpl::GetRecordBatchReader(const std::vector<int>&
row_group_indices,
const std::vector<int>&
column_indices,
std::unique_ptr<RecordBatchReader>* out) {
- // column indices check
- for (auto row_group_index : row_group_indices) {
+ // row group indices check
+ for (int row_group_index : row_group_indices) {
RETURN_NOT_OK(BoundsCheckRowGroup(row_group_index));
}
+ // column indices check
+ ARROW_ASSIGN_OR_RAISE(std::vector<int> field_indices,
+ manifest_.GetFieldIndices(column_indices));
+
+ std::shared_ptr<::arrow::Schema> batch_schema;
+ RETURN_NOT_OK(GetSchema(&batch_schema));
+
+ // filter to only arrow::Fields which contain the selected physical columns
+ {
+ ::arrow::FieldVector selected_fields;
+
+ for (int field_idx : field_indices) {
+ selected_fields.push_back(batch_schema->field(field_idx));
+ }
+
+ batch_schema = ::arrow::schema(std::move(selected_fields));
Review comment:
It should. I'll fix this in #7534
----------------------------------------------------------------
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:
us...@infra.apache.org
