(tempdir)
| 5781 | |
| 5782 | |
| 5783 | def test_write_dataset_write_page_index(tempdir): |
| 5784 | for write_statistics in [True, False]: |
| 5785 | for write_page_index in [True, False]: |
| 5786 | schema = pa.schema([ |
| 5787 | pa.field("x", pa.int64()), |
| 5788 | pa.field("y", pa.int64())]) |
| 5789 | |
| 5790 | arrays = [[1, 2, 3], [None, 5, None]] |
| 5791 | table = pa.Table.from_arrays(arrays, schema=schema) |
| 5792 | |
| 5793 | file_format = ds.ParquetFileFormat() |
| 5794 | base_dir = tempdir / f"write_page_index_{write_page_index}" |
| 5795 | ds.write_dataset( |
| 5796 | table, |
| 5797 | base_dir, |
| 5798 | format="parquet", |
| 5799 | file_options=file_format.make_write_options( |
| 5800 | write_statistics=write_statistics, |
| 5801 | write_page_index=write_page_index, |
| 5802 | ), |
| 5803 | existing_data_behavior='overwrite_or_ignore', |
| 5804 | ) |
| 5805 | ds1 = ds.dataset(base_dir, format="parquet") |
| 5806 | |
| 5807 | for file in ds1.files: |
| 5808 | # Can retrieve sorting columns from metadata |
| 5809 | metadata = pq.read_metadata(file) |
| 5810 | cc = metadata.row_group(0).column(0) |
| 5811 | assert cc.has_offset_index is write_page_index |
| 5812 | assert cc.has_column_index is write_page_index & write_statistics |
| 5813 | |
| 5814 | |
| 5815 | @pytest.mark.parametrize('dstype', [ |
nothing calls this directly
no test coverage detected