(data_source, record_batch, file_format, col_id)
| 4636 | # partitioning column contains duplicate records. |
| 4637 | # Returns: (number_of_files_generated, number_of_partitions) |
| 4638 | def _get_compare_pair(data_source, record_batch, file_format, col_id): |
| 4639 | num_of_files_generated = _get_num_of_files_generated( |
| 4640 | base_directory=data_source, file_format=file_format) |
| 4641 | number_of_partitions = len(pa.compute.unique(record_batch[col_id])) |
| 4642 | return num_of_files_generated, number_of_partitions |
| 4643 | |
| 4644 | # CASE 1: when max_open_files=default & max_open_files >= num_of_partitions |
| 4645 | # In case of a writing to disk via partitioning based on a |
no test coverage detected