From 9182dab96f359aecc225923e5f010fae3c36e916 Mon Sep 17 00:00:00 2001 From: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com> Date: Wed, 18 Sep 2024 15:00:16 +0200 Subject: [PATCH] Update croissant_crumbs.py --- .../worker/src/worker/job_runners/dataset/croissant_crumbs.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/services/worker/src/worker/job_runners/dataset/croissant_crumbs.py b/services/worker/src/worker/job_runners/dataset/croissant_crumbs.py index 78b38e780..06c0c6751 100644 --- a/services/worker/src/worker/job_runners/dataset/croissant_crumbs.py +++ b/services/worker/src/worker/job_runners/dataset/croissant_crumbs.py @@ -131,7 +131,7 @@ def get_croissant_crumbs_from_dataset_infos( "fileSet": {"@id": distribution_name}, "extract": {"fileProperty": "fullpath"}, "transform": { - "regex": f"{re.escape(config)}/{'partial-' if partial else ''}({piped_splits})/.+parquet$" + "regex": f"{re.escape(config)}/(?:partial-)?({piped_splits})/.+parquet$" }, }, "references": {"field": {"@id": f"{split_record_set_name}/split_name"}},