diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py index cebf31db87..b55d893087 100644 --- a/pyiceberg/table/__init__.py +++ b/pyiceberg/table/__init__.py @@ -2411,6 +2411,7 @@ def _rest_file_to_data_file(rest_file: RESTContentFile, default_referenced_data_ referenced_data_file=referenced_data_file, content_offset=rest_file.content_offset if isinstance(rest_file, RESTPositionDeleteFile) else None, content_size_in_bytes=rest_file.content_size_in_bytes if isinstance(rest_file, RESTPositionDeleteFile) else None, + first_row_id=rest_file.first_row_id if isinstance(rest_file, RESTDataFile) else None, ) data_file.spec_id = rest_file.spec_id return data_file diff --git a/tests/catalog/test_scan_planning_models.py b/tests/catalog/test_scan_planning_models.py index f88e24e92f..03df70deba 100644 --- a/tests/catalog/test_scan_planning_models.py +++ b/tests/catalog/test_scan_planning_models.py @@ -564,6 +564,14 @@ def test_plan_scan_with_shared_dv_file( } +@pytest.mark.parametrize("first_row_id", [1000, None]) +def test_rest_task_preserves_first_row_id(first_row_id: int | None) -> None: + rest_data_file = {**_rest_data_file(), **({"first-row-id": first_row_id} if first_row_id is not None else {})} + task = FileScanTask.from_rest_response(RESTFileScanTask.model_validate({"data-file": rest_data_file}), []) + + assert task.file.first_row_id == first_row_id + + @pytest.mark.parametrize("missing_field", ["content-offset", "content-size-in-bytes"]) @pytest.mark.parametrize("include_referenced_data_file", [True, False]) def test_rest_task_preserves_partial_dv_reference(missing_field: str, include_referenced_data_file: bool) -> None: