hatch formatting (ie ruff) on whole repo

conftest.py

@@ -3,7 +3,8 @@
 # Register tests/test_utils.py module as a pytest plugin so that tests can use fixtures from that
 # module without importing them (pytest recommends against importing them, and linters will flag the
 # import as unused and the fixture usage in test method args as redefining the var; https://github.com/astral-sh/ruff/issues/4046)
-pytest_plugins="tests.test_utils"
+pytest_plugins = "tests.test_utils"
+
 
 def pytest_addoption(parser):
     """Used to pass database URL for DB docker container in integration test."""
@@ -18,4 +19,3 @@ def pytest_addoption(parser):
 @pytest.fixture
 def database_url_command_line_arg(request):
     return request.config.getoption("--database-url")
-

src/tiktok_api_helper/api_client.py

@@ -23,9 +23,7 @@
 
 ALL_VIDEO_DATA_URL = "https://open.tiktokapis.com/v2/research/video/query/?fields=id,video_description,create_time,region_code,share_count,view_count,like_count,comment_count,music_id,hashtag_names,username,effect_ids,voice_to_text,playlist_id"
 
-SEARCH_ID_INVALID_ERROR_MESSAGE_REGEX = re.compile(
-    r"Search Id \d+ is invalid or expired"
-)
+SEARCH_ID_INVALID_ERROR_MESSAGE_REGEX = re.compile(r"Search Id \d+ is invalid or expired")
 
 INVALID_SEARCH_ID_ERROR_RETRY_WAIT = 5
 INVALID_SEARCH_ID_ERROR_MAX_NUM_RETRIES = 5
@@ -136,9 +134,11 @@ def as_json(self, indent=None):
             request_obj["cursor"] = self.cursor
         return json.dumps(request_obj, cls=QueryJSONEncoder, indent=indent)
 
+
 def is_json_decode_error(exception):
     return isinstance(exception, rq.exceptions.JSONDecodeError | json.JSONDecodeError)
 
+
 def retry_json_decoding_error_once(
     retry_state,
 ):
@@ -451,7 +451,8 @@ def _post(self, request: TiktokRequest) -> rq.Response | None:
         else:
             logging.warning(
                 f"Request failed, status code {response.status_code} - text {response.text} - data "
-                "{data}",)
+                "{data}",
+            )
         response.raise_for_status()
         # In case raise_for_status does not raise an exception we return None
         return None
@@ -476,9 +477,7 @@ def _parse_response(response: rq.Response | None) -> TikTokResponse:
 
         videos = response_data_section.get("videos", [])
 
-        return TikTokResponse(
-            data=response_data_section, videos=videos, error=error_data
-        )
+        return TikTokResponse(data=response_data_section, videos=videos, error=error_data)
 
 
 def update_crawl_from_api_response(
@@ -487,10 +486,7 @@ def update_crawl_from_api_response(
     crawl.cursor = api_response.data["cursor"]
     crawl.has_more = api_response.data["has_more"]
 
-    if (
-        "search_id" in api_response.data
-        and api_response.data["search_id"] != crawl.search_id
-    ):
+    if "search_id" in api_response.data and api_response.data["search_id"] != crawl.search_id:
         if crawl.search_id is not None:
             logging.log(
                 logging.ERROR,
@@ -591,7 +587,8 @@ def api_results_iter(self) -> TikTokApiClientFetchResult:
                 logging.log(
                     logging.ERROR,
                     "No videos in response but there's still data to Crawl - Query: "
-                    f"{self._config.query} \n api_response.data: {api_response.data}",)
+                    f"{self._config.query} \n api_response.data: {api_response.data}",
+                )
             if self._config.stop_after_one_request:
                 logging.info("Stopping after one request")
                 break

src/tiktok_api_helper/cli_data_acquisition.py

@@ -57,7 +57,7 @@ def run_long_query(config: ApiClientConfig):
     """Runs a "long" query, defined as one that may need multiple requests to get all the data.
 
     Unless you have a good reason to believe otherwise, queries should default to be considered
-    "long".  """
+    "long"."""
     api_client = TikTokApiClient.from_config(config)
     api_client.fetch_and_store_all()
 
@@ -288,7 +288,8 @@ def run(
     query_file_json: JsonQueryFileType | None = None,
     api_credentials_file: ApiCredentialsFileType = _DEFAULT_CREDENTIALS_FILE_PATH,
     rate_limit_wait_strategy: ApiRateLimitWaitStrategyType = (
-            ApiRateLimitWaitStrategy.WAIT_FOUR_HOURS),
+        ApiRateLimitWaitStrategy.WAIT_FOUR_HOURS
+    ),
     region: RegionCodeListType | None = None,
     include_any_hashtags: IncludeAnyHashtagListType | None = None,
     exclude_any_hashtags: ExcludeAnyHashtagListType | None = None,

src/tiktok_api_helper/custom_types.py

@@ -13,8 +13,10 @@
 TikTokEndDateFormat = Annotated[
     str,
     typer.Argument(
-        help=("End date in the format %Y%m%d (e.g. 20210101) NOT INCLUSIVE (ie start date 20210101 "
-              "and end date 20210102 will only include API results from 20210101.)")
+        help=(
+            "End date in the format %Y%m%d (e.g. 20210101) NOT INCLUSIVE (ie start date 20210101 "
+            "and end date 20210102 will only include API results from 20210101.)"
+        )
     ),
 ]
 
@@ -72,7 +74,8 @@
             "(ie close lid on laptop) the wait time is also paused. So if you use "
             f"{ApiRateLimitWaitStrategy.WAIT_NEXT_UTC_MIDNIGHT.value} and the machine goes to "
             "sleep retry will likely wait past upcoming midnight by however long the machine was "
-            "asleep"),
+            "asleep"
+        ),
     ),
 ]
 

src/tiktok_api_helper/sql.py

@@ -402,9 +402,7 @@ def from_query(
             has_more=has_more,
             query=json.dumps(query, cls=QueryJSONEncoder),
             search_id=search_id,
-            crawl_tags=(
-                {CrawlTag(name=name) for name in crawl_tags} if crawl_tags else set()
-            ),
+            crawl_tags=({CrawlTag(name=name) for name in crawl_tags} if crawl_tags else set()),
         )
 
     def upload_self_to_db(self, engine: Engine) -> None:

tests/test_api_client.py

@@ -139,15 +139,11 @@ def test_tiktok_api_request_client_retry_once_on_json_decoder_error(
         access_token_fetcher_session=mock_access_token_fetcher_session,
     )
     with pytest.raises(json.JSONDecodeError):
-        request.fetch(
-            api_client.TiktokRequest(query={}, start_date=None, end_date=None)
-        )
+        request.fetch(api_client.TiktokRequest(query={}, start_date=None, end_date=None))
     # Confirm that code retried the post request and json extraction twice (ie retried once after
     # the decode error before the exception is re-raised)
     assert mock_request_session_json_decoder_error.post.call_count == 2
-    assert (
-        mock_request_session_json_decoder_error.post.return_value.json.call_count == 2
-    )
+    assert mock_request_session_json_decoder_error.post.return_value.json.call_count == 2
     mock_sleep.assert_called_once_with(0)
 
 
@@ -170,10 +166,7 @@ def test_tiktok_api_request_client_wait_one_hour_on_rate_limit_wait_strategy(
     # Confirm that code retried the post request and json extraction twice (ie retried once after
     # the decode error before the exception is re-raised)
     assert mock_request_session_rate_limit_error.post.call_count == num_retries
-    assert (
-        mock_request_session_rate_limit_error.post.return_value.json.call_count
-        == num_retries
-    )
+    assert mock_request_session_rate_limit_error.post.return_value.json.call_count == num_retries
     # Sleep will be called once less than num_retries because it is not called after last retry
     assert mock_sleep.call_count == num_retries - 1
     assert mock_sleep.mock_calls == [
@@ -207,8 +200,7 @@ def test_tiktok_api_request_client_wait_til_next_utc_midnight_on_rate_limit_wait
         # after the decode error before the exception is re-raised)
         assert mock_request_session_rate_limit_error.post.call_count == num_retries
         assert (
-            mock_request_session_rate_limit_error.post.return_value.json.call_count
-            == num_retries
+            mock_request_session_rate_limit_error.post.return_value.json.call_count == num_retries
         )
         # Sleep will be called once less than num_retries because it is not called after last retry
         assert mock_sleep.call_count == num_retries - 1
@@ -395,9 +387,7 @@ def assert_has_expected_crawl_and_videos_in_database(
         crawl = crawls[0]
         assert crawl.id == fetch_result.crawl.id
         assert crawl.cursor == len(tiktok_responses) * acquisition_config.max_count
-        assert crawl.query == json.dumps(
-            acquisition_config.query, cls=query.QueryJSONEncoder
-        )
+        assert crawl.query == json.dumps(acquisition_config.query, cls=query.QueryJSONEncoder)
         videos = all_videos(session)
         assert len(videos) == len(tiktok_responses) * len(tiktok_responses[0].videos)
         assert len(videos) == len(fetch_result.videos)

tests/test_sql.py

@@ -362,9 +362,9 @@ def test_upsert_videos_to_crawls_association(test_database_engine, mock_crawl, a
         engine=test_database_engine,
     )
     with Session(test_database_engine) as session:
-        assert {
-            v.id: {crawl.id for crawl in v.crawls} for v in all_videos(session)
-        } == {v["id"]: {expected_crawl_id} for v in api_response_videos}
+        assert {v.id: {crawl.id for crawl in v.crawls} for v in all_videos(session)} == {
+            v["id"]: {expected_crawl_id} for v in api_response_videos
+        }
 
 
 def test_upsert_existing_hashtags_names_gets_same_id(
@@ -396,9 +396,7 @@ def test_upsert_existing_hashtags_names_gets_same_id(
             engine=test_database_engine,
         )
 
-        original_hashtags = {
-            hashtag.id: hashtag.name for hashtag in all_hashtags(session)
-        }
+        original_hashtags = {hashtag.id: hashtag.name for hashtag in all_hashtags(session)}
         assert set(original_hashtags.values()) == {"hashtag1", "hashtag2"}
 
         upsert_videos(

tests/test_utils.py

@@ -2,6 +2,7 @@
 pytest plugins in conftest.py. If this module is moved conftest.py pytest_plugins will also need to
 be updated.
 """
+
 import json
 
 import pytest