diff options
| -rw-r--r-- | gn3/csvcmp.py | 17 | ||||
| -rw-r--r-- | tests/unit/db/test_sample_data.py | 18 | ||||
| -rw-r--r-- | tests/unit/test_csvcmp.py | 54 |
3 files changed, 63 insertions, 26 deletions
diff --git a/gn3/csvcmp.py b/gn3/csvcmp.py index 8db89ca..4e8cc0f 100644 --- a/gn3/csvcmp.py +++ b/gn3/csvcmp.py @@ -52,8 +52,7 @@ def clean_csv_text(csv_text: str) -> str: """Remove extra white space elements in all elements of the CSV file""" _csv_text = [] for line in csv_text.strip().split("\n"): - _csv_text.append( - ",".join([el.strip() for el in line.split(",")])) + _csv_text.append(",".join([el.strip() for el in line.split(",")])) return "\n".join(_csv_text) @@ -73,8 +72,9 @@ def csv_diff(base_csv, delta_csv, tmp_dir="/tmp") -> dict: if base_csv_header != delta_csv_header: if longest_header != base_csv_header: - base_csv = base_csv.replace("Strain Name,Value,SE,Count", - longest_header, 1) + base_csv = base_csv.replace( + "Strain Name,Value,SE,Count", longest_header, 1 + ) else: delta_csv = delta_csv.replace( "Strain Name,Value,SE,Count", longest_header, 1 @@ -89,9 +89,9 @@ def csv_diff(base_csv, delta_csv, tmp_dir="/tmp") -> dict: _f.write(fill_csv(delta_csv, width=_l)) # Now we can run the diff! - _r = run_cmd(cmd=('"csvdiff ' - f"{file_name1} {file_name2} " - '--format json"')) + _r = run_cmd( + cmd=('"csvdiff ' f"{file_name1} {file_name2} " '--format json"') + ) if _r.get("code") == 0: _r = json.loads(_r.get("output", "")) if any(_r.values()): @@ -127,8 +127,7 @@ def get_allowable_sampledata_headers(conn: Any) -> List: attributes = ["Strain Name", "Value", "SE", "Count"] with conn.cursor() as cursor: cursor.execute("SELECT Name from CaseAttribute") - attributes += [attributes[0] for attributes in - cursor.fetchall()] + attributes += [attributes[0] for attributes in cursor.fetchall()] return attributes diff --git a/tests/unit/db/test_sample_data.py b/tests/unit/db/test_sample_data.py index 2524e07..607b278 100644 --- a/tests/unit/db/test_sample_data.py +++ b/tests/unit/db/test_sample_data.py @@ -34,11 +34,13 @@ def test_insert_sample_data(mocker): ) calls = [ mocker.call( - "SELECT Id FROM PublishData where Id = %s " "AND StrainId = %s", + "SELECT Id FROM PublishData where Id = %s " + "AND StrainId = %s", (data_id, strain_id), ), mocker.call( - "INSERT INTO PublishData " "(StrainId, Id, value) VALUES (%s, %s, %s)", + "INSERT INTO PublishData " + "(StrainId, Id, value) VALUES (%s, %s, %s)", (strain_id, data_id, "18"), ), mocker.call( @@ -47,10 +49,13 @@ def test_insert_sample_data(mocker): (strain_id, data_id, "3"), ), mocker.call( - "INSERT INTO NStrain " "(StrainId, DataId, count) VALUES (%s, %s, %s)", + "INSERT INTO NStrain " + "(StrainId, DataId, count) VALUES (%s, %s, %s)", (strain_id, data_id, "0"), ), - mocker.call("SELECT Id FROM CaseAttribute WHERE Name = %s", ("Sex",)), + mocker.call( + "SELECT Id FROM CaseAttribute WHERE Name = %s", ("Sex",) + ), mocker.call( "SELECT StrainId FROM CaseAttributeXRefNew " "WHERE StrainId = %s AND " @@ -135,7 +140,10 @@ def test_extract_actions(): ) == { "delete": None, "insert": {"data": "BXD1,2,F", "csv_header": "Strain Name,SE,Sex"}, - "update": {"data": "BXD1,19,1", "csv_header": "Strain Name,Value,Count"}, + "update": { + "data": "BXD1,19,1", + "csv_header": "Strain Name,Value,Count", + }, } diff --git a/tests/unit/test_csvcmp.py b/tests/unit/test_csvcmp.py index c2fda6b..0843bef 100644 --- a/tests/unit/test_csvcmp.py +++ b/tests/unit/test_csvcmp.py @@ -82,7 +82,9 @@ BXD15,14,x,x""" "Additions": [], "Columns": "Strain Name,Value,SE,Count,Sex", "Deletions": [], - "Modifications": [{"Current": "BXD12,16,x,x,1", "Original": "BXD12,16,x,x,x"}], + "Modifications": [ + {"Current": "BXD12,16,x,x,1", "Original": "BXD12,16,x,x,x"} + ], } @@ -113,7 +115,9 @@ BXD15,14,x,x def test_extract_strain_name(): """Test that the strain's name is extracted given a csv header""" assert ( - extract_strain_name(csv_header="Strain Name,Value,SE,Count", data="BXD1,18,x,0") + extract_strain_name( + csv_header="Strain Name,Value,SE,Count", data="BXD1,18,x,0" + ) == "BXD1" ) @@ -123,27 +127,53 @@ def test_get_allowable_csv_headers(mocker): """Test that all the csv headers are fetched properly""" mock_conn = mocker.MagicMock() expected_values = [ - "Strain Name", "Value", "SE", "Count", - "Condition", "Tissue", "Sex", "Age", - "Ethn.", "PMI (hrs)", "pH", "Color", + "Strain Name", + "Value", + "SE", + "Count", + "Condition", + "Tissue", + "Sex", + "Age", + "Ethn.", + "PMI (hrs)", + "pH", + "Color", ] with mock_conn.cursor() as cursor: cursor.fetchall.return_value = ( - ('Condition',), ('Tissue',), ('Sex',), - ('Age',), ('Ethn.',), ('PMI (hrs)',), ('pH',), ('Color',)) + ("Condition",), + ("Tissue",), + ("Sex",), + ("Age",), + ("Ethn.",), + ("PMI (hrs)",), + ("pH",), + ("Color",), + ) assert get_allowable_sampledata_headers(mock_conn) == expected_values cursor.execute.assert_called_once_with( - "SELECT Name from CaseAttribute") + "SELECT Name from CaseAttribute" + ) @pytest.mark.unit_test def test_extract_invalid_csv_headers_with_some_wrong_headers(): """Test that invalid column headers are extracted correctly from a csv -string""" + string""" allowed_headers = [ - "Strain Name", "Value", "SE", "Count", - "Condition", "Tissue", "Sex", "Age", - "Ethn.", "PMI (hrs)", "pH", "Color", + "Strain Name", + "Value", + "SE", + "Count", + "Condition", + "Tissue", + "Sex", + "Age", + "Ethn.", + "PMI (hrs)", + "pH", + "Color", ] csv_text = "Strain Name, Value, SE, Colour" |