✨ Add cavatica related gf fields

🗃️ add tests and flask migration

🎨 fix formating to old version

dataservice/api/genomic_file/models.py

@@ -54,6 +54,11 @@ class GenomicFile(db.Model, Base, IndexdFile):
     source files, this field should be NULL
     :param file_version_descriptor: Indicates the release status
     :param data_category: Type of data
+    :param cavatica_file_id: Indicates the file ID in CAVATICA
+    :param cavatica_volume: Indicates the CAVATICA volume ID, mediating cloud
+    storage access
+    :param workflow_endpoint: The endpoint name of the task outputs from
+    CAVATICA task or the CAVATICA app output name
     """
     __tablename__ = 'genomic_file'
     __prefix__ = 'GF'
@@ -95,6 +100,19 @@ class GenomicFile(db.Model, Base, IndexdFile):
         db.Text(),
         doc='Inidicates type of data file'
     )
+    cavatica_file_id = db.Column(
+        db.Text(),
+        doc='Indicates the file ID in CAVATICA'
+    )
+    cavatica_volume = db.Column(
+        db.Text(),
+        doc='Indicates the CAVATICA volume ID, mediating cloud storage access'
+    )
+    workflow_endpoint = db.Column(
+        db.Text(),
+        doc='The endpoint name of the task outputs from CAVATICA task or the'
+        ' CAVATICA app output name'
+    )
 
     task_genomic_files = db.relationship(TaskGenomicFile,
                                          backref='genomic_file',

migrations/versions/869f891d97ad_add_cavatica_gf_fields.py

@@ -0,0 +1,32 @@
+"""add cavatica gf fields
+
+Revision ID: 869f891d97ad
+Revises: 0454317cd224
+Create Date: 2024-09-04 14:48:36.499552
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '869f891d97ad'
+down_revision = '0454317cd224'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('genomic_file', sa.Column('cavatica_file_id', sa.Text(), nullable=True))
+    op.add_column('genomic_file', sa.Column('cavatica_volume', sa.Text(), nullable=True))
+    op.add_column('genomic_file', sa.Column('workflow_endpoint', sa.Text(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('genomic_file', 'workflow_endpoint')
+    op.drop_column('genomic_file', 'cavatica_volume')
+    op.drop_column('genomic_file', 'cavatica_file_id')
+    # ### end Alembic commands ###

tests/data.json

@@ -125,6 +125,9 @@
       "workflow_version": "v1",
       "file_version_descriptor": "latest",
       "data_category": "foo",
+      "cavatica_file_id": "668e2b079b1e4f4bec36a685",
+      "cavatica_volume": "d3b-bixu/sd_p6a1apwc",
+      "workflow_endpoint": "ctrlfreec_pngs"
       "visible": true
     },
     "/biospecimen-genomic-files": {},

tests/genomic_file/test_genomic_file_models.py

@@ -54,6 +54,9 @@ def test_create_and_find(self):
                 'workflow_version': 'v1',
                 'file_version_descriptor': 'released',
                 'data_category': 'foo',
+                'cavatica_file_id': '668e2b079b1e4f4bec36a685',
+                'cavatica_volume': 'd3b-bixu/sd_p6a1apwc',
+                'workflow_endpoint': 'ctrlfreec_pngs'
             }
             # Add genomic file to db session
             gf = GenomicFile(**kwargs)

tests/genomic_file/test_genomic_file_resources.py

@@ -520,7 +520,10 @@ def _new_genomic_file(client):
         'urls': ['s3://bucket/key'],
         'hashes': {'md5': 'd418219b883fce3a085b1b7f38b01e37'},
         'availability': 'Immediate Download',
-        'controlled_access': False
+        'controlled_access': False,
+        'cavatica_file_id': '668e2b079b1e4f4bec36a685',
+        'cavatica_volume': 'd3b-bixu/sd_p6a1apwc',
+        'workflow_endpoint': 'ctrlfreec_pngs'
     }
 
     response = client.post(url_for(GENOMICFILE_LIST_URL),