test: update and add unit tests aligned with new score set update flow

Revise existing tests and introduce new ones to cover optional update model and multipart handling.
Ensures regression coverage for newly added endpoint behaviors.

Author: davereinhart

src/mavedb/view_models/score_set_dataset_columns.py

@@ -25,7 +25,8 @@ class DatasetColumnsBase(BaseModel):
     def validate_dataset_columns_metadata(cls, v: Optional[dict[str, DatasetColumnMetadata]]) -> Optional[dict[str, DatasetColumnMetadata]]:
         if not v:
             return None
-        DatasetColumnMetadata.model_validate(v)
+        for val in v.values():
+            DatasetColumnMetadata.model_validate(val)
         return v
 
     @model_validator(mode="after")

tests/helpers/constants.py

@@ -696,7 +696,7 @@
 SAVED_MINIMAL_DATASET_COLUMNS = {
     "recordType": "DatasetColumns",
     "countColumns": [],
-    "scoreColumns": ["score"],
+    "scoreColumns": ["score", "s_0", "s_1"],
 }
 
 TEST_SEQ_SCORESET = {
@@ -1082,6 +1082,19 @@
     "officialCollections": [],
 }
 
+TEST_SCORE_SET_DATASET_COLUMNS = {
+    "score_columns": ["score", "s_0", "s_1"],
+    "count_columns": ["c_0", "c_1"],
+    "score_columns_metadata": {
+        "s_0": {"description": "s_0 description", "details": "s_0 details"},
+        "s_1": {"description": "s_1 description", "details": "s_1 details"},
+    },
+    "count_columns_metadata": {
+        "c_0": {"description": "c_0 description", "details": "c_0 details"},
+        "c_1": {"description": "c_1 description", "details": "c_1 details"},
+    },
+}
+
 TEST_NT_CDOT_TRANSCRIPT = {
     "start_codon": 0,
     "stop_codon": 18,

tests/helpers/util/score_set.py

@@ -88,10 +88,18 @@ def create_multi_target_score_set(
 
 
 def create_seq_score_set_with_mapped_variants(
-    client, db, data_provider, experiment_urn, scores_csv_path, update=None, counts_csv_path=None
+    client,
+    db,
+    data_provider,
+    experiment_urn,
+    scores_csv_path,
+    update=None,
+    counts_csv_path=None,
+    score_columns_metadata_json_path=None,
+    count_columns_metadata_json_path=None
 ):
     score_set = create_seq_score_set_with_variants(
-        client, db, data_provider, experiment_urn, scores_csv_path, update, counts_csv_path
+        client, db, data_provider, experiment_urn, scores_csv_path, update, counts_csv_path, score_columns_metadata_json_path, count_columns_metadata_json_path
     )
     score_set = mock_worker_vrs_mapping(client, db, score_set)
 
@@ -100,10 +108,18 @@ def create_seq_score_set_with_mapped_variants(
 
 
 def create_acc_score_set_with_mapped_variants(
-    client, db, data_provider, experiment_urn, scores_csv_path, update=None, counts_csv_path=None
+    client,
+    db,
+    data_provider,
+    experiment_urn,
+    scores_csv_path,
+    update=None,
+    counts_csv_path=None,
+    score_columns_metadata_json_path=None,
+    count_columns_metadata_json_path=None
 ):
     score_set = create_acc_score_set_with_variants(
-        client, db, data_provider, experiment_urn, scores_csv_path, update, counts_csv_path
+        client, db, data_provider, experiment_urn, scores_csv_path, update, counts_csv_path, score_columns_metadata_json_path, count_columns_metadata_json_path
     )
     score_set = mock_worker_vrs_mapping(client, db, score_set)
 
@@ -112,10 +128,20 @@ def create_acc_score_set_with_mapped_variants(
 
 
 def create_seq_score_set_with_variants(
-    client, db, data_provider, experiment_urn, scores_csv_path, update=None, counts_csv_path=None
+    client,
+    db,
+    data_provider,
+    experiment_urn,
+    scores_csv_path,
+    update=None,
+    counts_csv_path=None,
+    score_columns_metadata_json_path=None,
+    count_columns_metadata_json_path=None
 ):
     score_set = create_seq_score_set(client, experiment_urn, update)
-    score_set = mock_worker_variant_insertion(client, db, data_provider, score_set, scores_csv_path, counts_csv_path)
+    score_set = mock_worker_variant_insertion(
+        client, db, data_provider, score_set, scores_csv_path, counts_csv_path, score_columns_metadata_json_path, count_columns_metadata_json_path
+    )
 
     assert (
         score_set["numVariants"] == 3
@@ -126,10 +152,20 @@ def create_seq_score_set_with_variants(
 
 
 def create_acc_score_set_with_variants(
-    client, db, data_provider, experiment_urn, scores_csv_path, update=None, counts_csv_path=None
+    client,
+    db,
+    data_provider,
+    experiment_urn,
+    scores_csv_path,
+    update=None,
+    counts_csv_path=None,
+    score_columns_metadata_json_path=None,
+    count_columns_metadata_json_path=None
 ):
     score_set = create_acc_score_set(client, experiment_urn, update)
-    score_set = mock_worker_variant_insertion(client, db, data_provider, score_set, scores_csv_path, counts_csv_path)
+    score_set = mock_worker_variant_insertion(
+        client, db, data_provider, score_set, scores_csv_path, counts_csv_path, score_columns_metadata_json_path, count_columns_metadata_json_path
+    )
 
     assert (
         score_set["numVariants"] == 3

tests/routers/data/count_columns_metadata.json

@@ -0,0 +1,10 @@
+{
+    "c_0": {
+        "description": "c_0 description",
+        "details": "c_0 details"
+    },
+    "c_1": {
+        "description": "c_1 description",
+        "details": "c_1 details"
+    }
+}

tests/routers/data/score_columns_metadata.json

@@ -0,0 +1,10 @@
+{
+    "s_0": {
+        "description": "s_0 description",
+        "details": "s_0 details"
+    },
+    "s_1": {
+        "description": "s_0 description",
+        "details": "s_0 details"
+    }
+}

tests/routers/data/scores.csv

@@ -1,4 +1,4 @@
-hgvs_nt,hgvs_pro,score
-c.1A>T,p.Thr1Ser,0.3
-c.2C>T,p.Thr1Met,1.0
-c.6T>A,p.Phe2Leu,-1.65
+hgvs_nt,hgvs_pro,score,s_0,s_1
+c.1A>T,p.Thr1Ser,0.3,val1,val1
+c.2C>T,p.Thr1Met,1.0,val2,val2
+c.6T>A,p.Phe2Leu,-1.65,val3,val3

tests/routers/test_score_set.py

@@ -1,5 +1,6 @@
 # ruff: noqa: E402
 
+import json
 import re
 from copy import deepcopy
 import csv
@@ -400,6 +401,98 @@ def test_can_update_score_set_data_before_publication(
 
     assert expected_response_data == response_data[camelize(attribute)]
 
+@pytest.mark.parametrize(
+    "attribute,updated_data,expected_response_data",
+    [
+        ("title", "Updated Title", "Updated Title"),
+        ("method_text", "Updated Method Text", "Updated Method Text"),
+        ("abstract_text", "Updated Abstract Text", "Updated Abstract Text"),
+        ("short_description", "Updated Abstract Text", "Updated Abstract Text"),
+        ("extra_metadata", {"updated": "metadata"}, {"updated": "metadata"}),
+        ("data_usage_policy", "data_usage_policy", "data_usage_policy"),
+        ("contributors", [{"orcid_id": EXTRA_USER["username"]}], [SAVED_EXTRA_CONTRIBUTOR]),
+        ("primary_publication_identifiers", [{"identifier": TEST_PUBMED_IDENTIFIER}], [SAVED_PUBMED_PUBLICATION]),
+        ("secondary_publication_identifiers", [{"identifier": TEST_PUBMED_IDENTIFIER}], [SAVED_PUBMED_PUBLICATION]),
+        ("doi_identifiers", [{"identifier": TEST_CROSSREF_IDENTIFIER}], [SAVED_DOI_IDENTIFIER]),
+        ("license_id", EXTRA_LICENSE["id"], SAVED_SHORT_EXTRA_LICENSE),
+        ("target_genes", TEST_MINIMAL_ACC_SCORESET["targetGenes"], TEST_MINIMAL_ACC_SCORESET_RESPONSE["targetGenes"]),
+        ("score_ranges", TEST_SCORE_SET_RANGES_ALL_SCHEMAS_PRESENT, TEST_SAVED_SCORE_SET_RANGES_ALL_SCHEMAS_PRESENT),
+    ],
+)
+@pytest.mark.parametrize(
+    "mock_publication_fetch",
+    [({"dbName": "PubMed", "identifier": f"{TEST_PUBMED_IDENTIFIER}"})],
+    indirect=["mock_publication_fetch"],
+)
+def test_can_patch_score_set_data_before_publication(
+    client, setup_router_db, attribute, updated_data, expected_response_data, mock_publication_fetch
+):
+    experiment = create_experiment(client)
+    score_set = create_seq_score_set(client, experiment["urn"])
+    expected_response = update_expected_response_for_created_resources(
+        deepcopy(TEST_MINIMAL_SEQ_SCORESET_RESPONSE), experiment, score_set
+    )
+    expected_response["experiment"].update({"numScoreSets": 1})
+
+    response = client.get(f"/api/v1/score-sets/{score_set['urn']}")
+    assert response.status_code == 200
+    response_data = response.json()
+
+    assert sorted(expected_response.keys()) == sorted(response_data.keys())
+    for key in expected_response:
+        assert (key, expected_response[key]) == (key, response_data[key])
+
+    data = {}
+    if isinstance(updated_data, (dict, list)):
+        form_value = json.dumps(updated_data)
+    else:
+        form_value = str(updated_data)
+    data[attribute] = form_value
+
+    response = client.patch(f"/api/v1/score-sets-with-variants/{score_set['urn']}", data=data)
+    assert response.status_code == 200
+
+    response = client.get(f"/api/v1/score-sets/{score_set['urn']}")
+    assert response.status_code == 200
+    response_data = response.json()
+
+    # Although the client provides the license id, the response includes the full license.
+    if attribute == "license_id":
+        attribute = "license"
+
+    assert expected_response_data == response_data[camelize(attribute)]
+
+@pytest.mark.parametrize(
+    "form_field,filename,mime_type",
+    [
+        ("scores_file", "scores.csv", "text/csv"),
+        ("counts_file", "counts.csv", "text/csv"),
+        ("score_columns_metadata_file", "score_columns_metadata.json", "application/json"),
+        ("count_columns_metadata_file", "count_columns_metadata.json", "application/json"),
+    ]
+)
+@pytest.mark.parametrize(
+    "mock_publication_fetch",
+    [({"dbName": "PubMed", "identifier": f"{TEST_PUBMED_IDENTIFIER}"})],
+    indirect=["mock_publication_fetch"],
+)
+def test_can_patch_score_set_data_with_files_before_publication(
+    client, setup_router_db, form_field, filename, mime_type,data_files, mock_publication_fetch
+):
+    experiment = create_experiment(client)
+    score_set = create_seq_score_set(client, experiment["urn"])
+    expected_response = update_expected_response_for_created_resources(
+        deepcopy(TEST_MINIMAL_SEQ_SCORESET_RESPONSE), experiment, score_set
+    )
+    expected_response["experiment"].update({"numScoreSets": 1})
+
+    data_file_path = data_files / filename
+    files = {form_field: (filename, open(data_file_path, "rb"), mime_type)}
+    with patch.object(arq.ArqRedis, "enqueue_job", return_value=None) as worker_queue:
+        response = client.patch(f"/api/v1/score-sets-with-variants/{score_set['urn']}", files=files)
+        worker_queue.assert_called_once()
+        assert response.status_code == 200
+
 
 @pytest.mark.parametrize(
     "attribute,updated_data,expected_response_data",
@@ -415,7 +508,7 @@ def test_can_update_score_set_data_before_publication(
         ("secondary_publication_identifiers", [{"identifier": TEST_PUBMED_IDENTIFIER}], [SAVED_PUBMED_PUBLICATION]),
         ("doi_identifiers", [{"identifier": TEST_CROSSREF_IDENTIFIER}], [SAVED_DOI_IDENTIFIER]),
         ("license_id", EXTRA_LICENSE["id"], SAVED_SHORT_EXTRA_LICENSE),
-        ("dataset_columns", {"countColumns": [], "scoreColumns": ["score"]}, SAVED_MINIMAL_DATASET_COLUMNS)
+        ("dataset_columns", None, SAVED_MINIMAL_DATASET_COLUMNS)
     ],
 )
 @pytest.mark.parametrize(

tests/view_models/test_score_set_dataset_columns.py

@@ -0,0 +1,17 @@
+from mavedb.view_models.score_set_dataset_columns import DatasetColumnMetadata, SavedDatasetColumns
+from tests.helpers.constants import TEST_SCORE_SET_DATASET_COLUMNS
+
+def test_score_set_dataset_columns():
+    score_set_dataset_columns = TEST_SCORE_SET_DATASET_COLUMNS.copy()
+
+    for k, v in score_set_dataset_columns['score_columns_metadata'].items():
+        score_set_dataset_columns['score_columns_metadata'][k] = DatasetColumnMetadata.model_validate(v)
+    for k, v in score_set_dataset_columns['count_columns_metadata'].items():
+        score_set_dataset_columns['count_columns_metadata'][k] = DatasetColumnMetadata.model_validate(v)
+
+    saved_score_set_dataset_columns = SavedDatasetColumns.model_validate(score_set_dataset_columns)
+
+    assert saved_score_set_dataset_columns.score_columns_metadata == score_set_dataset_columns['score_columns_metadata']
+    assert saved_score_set_dataset_columns.count_columns_metadata == score_set_dataset_columns['count_columns_metadata']
+    assert saved_score_set_dataset_columns.score_columns == score_set_dataset_columns['score_columns']
+    assert saved_score_set_dataset_columns.count_columns == score_set_dataset_columns['count_columns']