Add ruff flake8-comprehensions rules

docs/conf.py

@@ -114,7 +114,7 @@
 try:
     html_context  # noqa: B018
 except NameError:
-    html_context = dict()
+    html_context = {}
 
 html_context["display_versions_lower_left"] = True
 

parsons/action_kit/action_kit.py

@@ -1432,7 +1432,7 @@ def bulk_upload_table(
         results = []
         for tbl in upload_tables:
             user_fields_only = int(
-                not any([h for h in tbl.columns if h != "email" and not h.startswith("user_")])
+                not any(h for h in tbl.columns if h != "email" and not h.startswith("user_"))
             )
             results.append(
                 self.bulk_upload_csv(
@@ -1442,7 +1442,7 @@ def bulk_upload_table(
                     user_fields_only=user_fields_only,
                 )
             )
-        return {"success": all([r["success"] for r in results]), "results": results}
+        return {"success": all(r["success"] for r in results), "results": results}
 
     def _split_tables_no_empties(self, table, no_overwrite_on_empty, set_only_columns):
         table_groups = {}
@@ -1463,7 +1463,7 @@ def _split_tables_no_empties(self, table, no_overwrite_on_empty, set_only_column
                 subset_table.table = subset_table.table.cutout(*blanks)
             logger.debug(f"Column Upload Blanks: {blanks}")
             logger.debug(f"Column Upload Columns: {subset_table.columns}")
-            if not set(["user_id", "email"]).intersection(subset_table.columns):
+            if not {"user_id", "email"}.intersection(subset_table.columns):
                 logger.warning(
                     f"Upload will fail without user_id or email. "
                     f"Rows: {subset_table.num_rows}, Columns: {subset_table.columns}"

parsons/airtable/airtable.py

@@ -303,7 +303,7 @@ def delete_records(self, table):
         # is provided then map the ids into the expected list of id strings.
 
         if any(isinstance(row, dict) for row in table):
-            table = list(map(lambda row: row["id"], table))
+            table = [row["id"] for row in table]
 
         resp = self.client.batch_delete(table)
         logger.info(f"{len(table)} records deleted.")

parsons/aws/s3.py

@@ -155,7 +155,7 @@ def list_keys(
                 'Size', and 'Owner'.
         """
 
-        keys_dict = dict()
+        keys_dict = {}
         logger.debug(f"Fetching keys in {bucket} bucket")
 
         continuation_token = None

parsons/azure/azure_blob_storage.py

@@ -157,7 +157,7 @@ def list_blobs(self, container_name, name_starts_with=None):
         """
 
         container_client = self.get_container(container_name)
-        blobs = [blob for blob in container_client.list_blobs(name_starts_with=name_starts_with)]
+        blobs = list(container_client.list_blobs(name_starts_with=name_starts_with))
         logger.info(f"Found {len(blobs)} blobs in {container_name} container.")
         return blobs
 

parsons/braintree/braintree.py

@@ -235,7 +235,7 @@ def get_disputes(self, start_date=None, end_date=None, query_list=None, query_di
             query_list=query_list,
             query_dict=query_dict,
             default_query=(
-                {"effective_date": dict(between=[start_date, end_date])}
+                {"effective_date": {"between": [start_date, end_date]}}
                 if start_date and end_date
                 else None
             ),
@@ -310,7 +310,7 @@ def get_subscriptions(
             query_list=query_list,
             query_dict=query_dict,
             default_query=(
-                {"created_at": dict(between=[start_date, end_date])}
+                {"created_at": {"between": [start_date, end_date]}}
                 if start_date and end_date
                 else None
             ),
@@ -389,11 +389,7 @@ def get_transactions(
             query_list=query_list,
             query_dict=query_dict,
             default_query=(
-                {
-                    "disbursement_date": dict(
-                        between=[disbursement_start_date, disbursement_end_date]
-                    )
-                }
+                {"disbursement_date": {"between": [disbursement_start_date, disbursement_end_date]}}
                 if disbursement_start_date and disbursement_end_date
                 else None
             ),

parsons/capitol_canary/capitol_canary.py

@@ -294,7 +294,7 @@ def create_advocate(
 
         # Turn into a list of items so we can append multiple campaigns
         campaign_keys = [("campaigns[]", val) for val in campaigns]
-        data = [(key, value) for key, value in payload.items()] + campaign_keys
+        data = list(payload.items()) + campaign_keys
 
         # Call into the CapitolCanary API
         response = self.client.post_request("advocates", data=data)
@@ -387,7 +387,7 @@ def update_advocate(
         # Turn into a list of items so we can append multiple campaigns
         campaigns = campaigns or []
         campaign_keys = [("campaigns[]", val) for val in campaigns]
-        data = [(key, value) for key, value in payload.items()] + campaign_keys
+        data = list(payload.items()) + campaign_keys
 
         # Call into the CapitolCanary API
         self.client.post_request("advocates", data=data)

parsons/etl/table.py

@@ -103,7 +103,7 @@ def __getitem__(self, index):
 
         elif isinstance(index, slice):
             tblslice = petl.rowslice(self.table, index.start, index.stop, index.step)
-            return [row for row in tblslice]
+            return list(tblslice)
 
         else:
             raise TypeError("You must pass a string or an index as a value.")

parsons/facebook_ads/facebook_ads.py

@@ -200,7 +200,7 @@ def get_match_table_for_users_table(users_table):
     @staticmethod
     def _get_match_schema_and_data(table):
         # Grab the raw data as a list of tuples
-        data_list = [row for row in table.data]
+        data_list = list(table.data)
         return (table.columns, data_list)
 
     @staticmethod

parsons/google/google_cloud_storage.py

@@ -202,7 +202,7 @@ def list_blobs(
         )
 
         if include_file_details:
-            lst = [b for b in blobs]
+            lst = list(blobs)
         else:
             lst = [b.name for b in blobs]
 

parsons/ngpvan/email.py

@@ -127,7 +127,7 @@ def get_email_stats(self, aggregate_ab: bool = True) -> Table:
         if aggregate_ab:
             for email in email_list:  # One row per foreignMessageId
                 outer = {field: email[field] for field in outer_fields}
-                inner = {field: 0 for field in inner_fields}
+                inner = dict.fromkeys(inner_fields, 0)
                 for i in email["emailMessageContent"]:
                     # Pending emails don't have emailMessageContentDistributions, just have defaults
                     if not i["emailMessageContentDistributions"]:
@@ -149,7 +149,7 @@ def get_email_stats(self, aggregate_ab: bool = True) -> Table:
                 for i in email["emailMessageContent"]:
                     # One row per foreignMessageId / emailMessageContent entry
                     outer = {field: email[field] for field in outer_fields}
-                    inner = {field: 0 for field in inner_fields}
+                    inner = dict.fromkeys(inner_fields, 0)
                     if not i["emailMessageContentDistributions"]:
                         logger.info(
                             f"No emailMessageContentDistributions for email {i['name']}, defaulting values to 0"

parsons/scytl/scytl.py

@@ -91,7 +91,7 @@ def __init__(self, state: str, election_id: str, county=""):
         self.previous_details_version_num = None
         self.previous_county_details_version_num = None
         self.previous_county_details_list = None
-        self.previously_fetched_counties = set([])
+        self.previously_fetched_counties = set()
 
     def _parse_date_to_utc(self, input_dt: str) -> datetime:
         """

parsons/sftp/utilities.py

@@ -4,7 +4,7 @@
 
 
 def connection_exists(args, kwargs):
-    if any([isinstance(arg, paramiko.sftp_client.SFTPClient) for arg in args]):
+    if any(isinstance(arg, paramiko.sftp_client.SFTPClient) for arg in args):
         return True
     if "connection" in kwargs and kwargs["connection"]:
         return True

parsons/targetsmart/targetsmart_api.py

@@ -200,7 +200,7 @@ def radius_search(
         }
 
         r = self.connection.request(url, args=args, raw=True)
-        return Table([itm for itm in r["output"]]).unpack_dict("data_fields", prepend=False)
+        return Table(list(r["output"])).unpack_dict("data_fields", prepend=False)
 
     def phone(self, table):
         """

parsons/utilities/dbt/logging.py

@@ -120,7 +120,7 @@ def format_command_result(
 
         # Skips
         if manifest.skips:
-            skips = set([i.node.name for i in manifest.skips])
+            skips = {i.node.name for i in manifest.skips}
             log_message += "\nSkipped:\n```{}```".format(", ".join(skips))
 
         return log_message
@@ -130,7 +130,7 @@ def format_result(self) -> str:
         full_log_message = ""
 
         # Header
-        if any([command.errors for command in self.commands]):
+        if any(command.errors for command in self.commands):
             status = "failed"
             full_log_message += "\U0001f534"
         else:

parsons/utilities/dbt/models.py

@@ -28,7 +28,7 @@ def filter_results(self, **kwargs) -> list[NodeResult]:
         filtered_results = [
             result
             for result in self.dbt_manifest
-            if all([str(getattr(result, key)) == value for key, value in kwargs.items()])
+            if all(str(getattr(result, key)) == value for key, value in kwargs.items())
         ]
         return filtered_results
 

pyproject.toml

@@ -48,6 +48,7 @@ select = [
     "B", # flake8-bugbear (B)
     "E", # pycodestyle errors (E)
     "W", # pycodestyle warnings (W)
+    "C4", # flake8-comprehensions (C4)
     "F", # Pyflakes (F)
     "I", # isort (I)
     "TID", # flake8-tidy-imports (TID)

test/test_action_kit.py

@@ -485,12 +485,12 @@ def test_paginated_get(self):
         first_mock.status_code = 201
         first_mock.json = lambda: {
             "meta": {"next": "/rest/v1/user/abc"},
-            "objects": list(map(lambda x: {"value": x}, [*range(100)])),
+            "objects": [{"value": x} for x in [*range(100)]],
         }
         second_mock.status_code = 201
         second_mock.json = lambda: {
             "meta": {"next": "/rest/v1/user/def"},
-            "objects": list(map(lambda x: {"value": x}, [*range(100, 200)])),
+            "objects": [{"value": x} for x in [*range(100, 200)]],
         }
         resp_mock.get.side_effect = [first_mock, second_mock]
         self.actionkit.conn = resp_mock
@@ -513,12 +513,12 @@ def test_paginated_get_custom_limit(self):
         first_mock.status_code = 201
         first_mock.json = lambda: {
             "meta": {"next": "/rest/v1/user/abc"},
-            "objects": list(map(lambda x: {"value": x}, [*range(100)])),
+            "objects": [{"value": x} for x in [*range(100)]],
         }
         second_mock.status_code = 201
         second_mock.json = lambda: {
             "meta": {"next": "/rest/v1/user/def"},
-            "objects": list(map(lambda x: {"value": x}, [*range(100, 200)])),
+            "objects": [{"value": x} for x in [*range(100, 200)]],
         }
         resp_mock.get.side_effect = [first_mock, second_mock]
         self.actionkit.conn = resp_mock

test/test_airtable/test_airtable.py

@@ -220,4 +220,4 @@ def test_delete_records(self, m):
         resp = self.at.delete_records(tbl)
 
         self.assertEqual(len(delete_responses["records"]), len(resp))
-        self.assertTrue(all([r["deleted"] for r in resp]))
+        self.assertTrue(all(r["deleted"] for r in resp))

test/test_catalist/test_catalist.py

@@ -94,7 +94,7 @@ def test_upload(self, mock_requests) -> None:
         requested_base_url = mock_requests._adapter.request_history[1]._url_parts.netloc
 
         assert requested_base_url == "api.catalist.us"
-        assert set(requested_queries.keys()) == set(["token"])
+        assert set(requested_queries.keys()) == {"token"}
         assert requested_queries["token"] == ["tokenexample"]
         assert requested_endpoint.startswith("/mapi/upload/template/48827/action/publish/url/")
 
@@ -112,7 +112,7 @@ def test_upload_with_options(self, mock_requests) -> None:
 
         requested_queries = mock_requests._adapter.request_history[1].qs
 
-        assert set(requested_queries.keys()) == set(["token", "copytosandbox", "phone"])
+        assert set(requested_queries.keys()) == {"token", "copytosandbox", "phone"}
         assert requested_queries["copytosandbox"] == ["true"]
         assert requested_queries["phone"] == ["123456789"]
 
@@ -128,7 +128,7 @@ def test_status(self, mock_requests) -> None:
         requested_base_url = mock_requests._adapter.request_history[1]._url_parts.netloc
 
         assert requested_base_url == "api.catalist.us"
-        assert set(requested_queries.keys()) == set(["token"])
+        assert set(requested_queries.keys()) == {"token"}
         assert requested_queries["token"] == ["tokenexample"]
         assert requested_endpoint == "/mapi/status/id/12345"
 
@@ -147,7 +147,7 @@ def test_load_matches(self) -> None:
         first_called_method = str(first_mocked_call).split("(")[0].split(".")[1]
 
         assert first_called_method == "list_directory"
-        assert set(first_mocked_call.args) == set(["/myDownloads/"])
+        assert set(first_mocked_call.args) == {"/myDownloads/"}
 
         second_mocked_call = match.sftp.mock_calls[1]
         second_called_method = str(second_mocked_call).split("(")[0].split(".")[1]

test/test_databases/fakes.py

@@ -77,7 +77,7 @@ def distinct_primary_key(self, primary_key):
         if primary_key not in self.data.columns:
             return True
 
-        pk_values = [val for val in self.data[primary_key]]
+        pk_values = list(self.data[primary_key])
         pk_set = set(pk_values)
         return len(pk_set) == len(pk_values)
 

test/test_databases/test_bigquery.py

@@ -82,7 +82,7 @@ def test_query__no_results(self):
         # Because Table() == Table() fails for some reason
         assert isinstance(result, Table)
         assert not len(result)
-        assert tuple(result.columns) == tuple([])
+        assert tuple(result.columns) == ()
 
     @mock.patch("parsons.utilities.files.create_temp_file")
     def test_query__no_return(self, create_temp_file_mock):
@@ -119,7 +119,7 @@ def test_query_with_transaction(self, create_temp_file_mock):
 
         # Check that queries and transaction keywords are included in sql
         self.assertTrue(
-            all([text in keyword_args["sql"] for text in queries + ["BEGIN TRANSACTION", "COMMIT"]])
+            all(text in keyword_args["sql"] for text in queries + ["BEGIN TRANSACTION", "COMMIT"])
         )
         self.assertEqual(keyword_args["parameters"], parameters)
         self.assertFalse(keyword_args["return_values"])

test/test_sftp.py

@@ -210,15 +210,15 @@ def test_table_to_sftp_csv(live_sftp, simple_table, compression):  # noqa F811
 def assert_results_match_expected(expected, results):
     assert len(results) == len(expected)
     for e in expected:
-        assert any([e in r for r in results])
+        assert any(e in r for r in results)
 
 
 def assert_has_call(mock, args):
     return call(*args) in mock.mock_calls
 
 
 def assert_has_calls(mock, calls):
-    return all([assert_has_call(mock, c) for c in calls])
+    return all(assert_has_call(mock, c) for c in calls)
 
 
 @mark_live_test

useful_resources/sample_code/apply_activist_code.py

@@ -44,7 +44,7 @@
 myv_keys = {k: VAN(api_key=v, db=os.environ["VAN_DB_NAME"]) for k, v in myv_states.items()}
 
 # Create simple set of states for insertion into SQL
-states = "','".join([s for s in myv_keys])
+states = "','".join(list(myv_keys))
 
 # SQL to pull those needing Activist Code
 sql = f"""