Skip to content

Adding CLI to idmapping script #75

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ialarmedalien merged 1 commit into from
Jan 29, 2026
Merged

Adding CLI to idmapping script #75

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,9 @@ dependencies = [
"ruff>=0.14.13",
]

[project.scripts]
idmapping = "cdm_data_loader_utils.parsers.idmapping:main"

[dependency-groups]
dev = [
"hypothesis>=6.148.9",
Expand Down
14 changes: 10 additions & 4 deletions src/cdm_data_loader_utils/parsers/uniprot/idmapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ def read_and_write(spark: SparkSession, pipeline_run: PipelineRun, id_mapping_ts
@click.option(
"--source",
required=True,
help="Full path to the source directory containing ID mapping file(s). Does not need to specify the Bucket (i.e. cdm-lake) but should specify everything else.",
help="Full path to the source directory containing ID mapping file(s). S3 buckets should include the full path with s3a:// prefix; otherwise, the path will be assumed to be local.",
)
@click.option(
"--namespace",
Expand All @@ -130,7 +130,7 @@ def read_and_write(spark: SparkSession, pipeline_run: PipelineRun, id_mapping_ts
default=None,
help="Tenant warehouse to save processed data to; defaults to saving data to the user warehouse if a tenant is not specified",
)
def main(source: str, namespace: str, tenant_name: str | None) -> None:
def cli(source: str, namespace: str, tenant_name: str | None) -> None:
"""Run the UniProt ID Mapping importer.

:param source: full path to the source directory containing ID mapping file(s)
Expand All @@ -141,12 +141,18 @@ def main(source: str, namespace: str, tenant_name: str | None) -> None:
:type tenant_name: str | None
"""
(spark, delta_ns) = set_up_workspace(APP_NAME, namespace, tenant_name)
for file in list_remote_dir_contents(source):
bucket_list = []
if "://" in source and source.startswith("s3a://"):
# we're golden
bucket_list = list_remote_dir_contents(source)
# TODO: other locations

for file in bucket_list:
# file names are in the 'Key' value
# 'tenant-general-warehouse/kbase/datasets/uniprot/id_mapping/id_mapping_part_001.tsv.gz'
pipeline_run = PipelineRun(str(uuid4()), APP_NAME, file["Key"], delta_ns)
read_and_write(spark, pipeline_run, file["Key"])


if __name__ == "__main__":
main()
cli()
Loading