Like ``run_batch``, but collects per-file results into a list.
(
extractor: BatchExtractor,
gz_files: list[str],
*,
manifest: BatchManifestWriter,
batch_size: int = 50,
jobs: int = 1,
on_start: Callable[[str], None] | None = None,
)
| 711 | |
| 712 | |
| 713 | def run_batch_collected( |
| 714 | extractor: BatchExtractor, |
| 715 | gz_files: list[str], |
| 716 | *, |
| 717 | manifest: BatchManifestWriter, |
| 718 | batch_size: int = 50, |
| 719 | jobs: int = 1, |
| 720 | on_start: Callable[[str], None] | None = None, |
| 721 | ) -> tuple[BatchResult, list[ExtractionResult]]: |
| 722 | """Like ``run_batch``, but collects per-file results into a list.""" |
| 723 | files: list[ExtractionResult] = [] |
| 724 | batch = run_batch( |
| 725 | extractor, |
| 726 | gz_files, |
| 727 | batch_size=batch_size, |
| 728 | jobs=jobs, |
| 729 | on_start=on_start, |
| 730 | on_result=lambda _p, e: files.append(e), |
| 731 | manifest=manifest, |
| 732 | ) |
| 733 | return batch, files |