A lot of spelling (#512)

src/aki_prj23_transparenzregister/ai/ner_pipeline.py

@@ -48,21 +48,21 @@ class EntityPipeline:
         # spaCy
         if ner_method == "spacy":
             ner_service_instance = ner_service.NerAnalysisService(
-                use_spacy=True, use_transformer=False, use_companylist=False
+                use_spacy=True, use_transformer=False, use_company_list=False
             )
             ner_service_func = ner_service_instance.ner_spacy
 
         # company list
         elif ner_method == "company_list":
             ner_service_instance = ner_service.NerAnalysisService(
-                use_spacy=False, use_transformer=False, use_companylist=True
+                use_spacy=False, use_transformer=False, use_company_list=True
             )
             ner_service_func = ner_service_instance.ner_company_list
 
         # transformer
         elif ner_method == "transformer":
             ner_service_instance = ner_service.NerAnalysisService(
-                use_spacy=False, use_transformer=True, use_companylist=False
+                use_spacy=False, use_transformer=True, use_company_list=False
             )
             ner_service_func = ner_service_instance.ner_transformer
         else:

src/aki_prj23_transparenzregister/ai/ner_service.py

@@ -15,14 +15,14 @@ class NerAnalysisService:
         self,
         use_spacy: bool = False,
         use_transformer: bool = False,
-        use_companylist: bool = False,
+        use_company_list: bool = False,
     ) -> None:
         """Method to check which sentiment model is chosen."""
         if use_spacy:
             self.init_spacy()
         if use_transformer:
             self.init_transformer()
-        if use_companylist:
+        if use_company_list:
             self.init_companylist()
 
     def init_spacy(self) -> None:

src/aki_prj23_transparenzregister/ai/sentiment_service.py

@@ -78,15 +78,14 @@ class SentimentAnalysisService:
         """Sentiment Analytics with Spacy.
 
         Args:
-                doc: a document which is processed with spacy
+            doc: a document which is processed with spacy
-                docAttrib: which attribute of the document has to be processed: text or title
 
         Returns:
-                label: positive, negative, neutral.
+            label: positive, negative, neutral.
         """
         # set limits for sentiments
-        _upperlimit = 0.1
+        _upper_limit = 0.1
-        _lowerlimit = -0.1
+        _lower_limit = -0.1
 
         _doc = self.nlp(doc)
         _score = None
@@ -108,9 +107,9 @@ class SentimentAnalysisService:
         # Normalize the score to the range 0..1
         _normalized_score = (_pos - abs(_neg)) / _max_score if _max_score > 0 else 0
 
-        if _normalized_score > _upperlimit:
+        if _normalized_score > _upper_limit:
             _sent = "positive"
-        elif _normalized_score < _lowerlimit:
+        elif _normalized_score < _lower_limit:
             _sent = "negative"
         else:
             _sent = "neutral"

src/aki_prj23_transparenzregister/apps/enrich_company_financials.py

@@ -26,7 +26,7 @@ from aki_prj23_transparenzregister.utils.mongo.connector import MongoConnector
 def cli() -> None:  # pragma: no cover
     """CLI entry point."""
     parser = argparse.ArgumentParser(
-        prog="Transparenzregister enriching companies with mising financial data",
+        prog="Transparenzregister enriching companies with missing financial data",
         description="Filters all raw companies with missing financial info from the MongoDB and enriches them with yearly result data from the Bundesanzeiger.",
         epilog="Example: enrich-company-financials --log-level ERROR --log-path print.log",
     )

src/aki_prj23_transparenzregister/apps/fetch_news.py

@@ -77,15 +77,15 @@ def main(config_provider: ConfigProvider) -> int:
         logger.error("Error while fetching news from Handelsblatt")
         news_handelsblatt = []
 
-    news_tageschau = tagesschau.get_news_for_category()
+    news_tagesschau = tagesschau.get_news_for_category()
-    if news_tageschau is None:
+    if news_tagesschau is None:
         logger.error("Error while fetching news from Tagesschau")
-        news_tageschau = []
+        news_tagesschau = []
 
     logger.info(f"Found {len(news_handelsblatt)} news articles from Handelsblatt")
-    logger.info(f"Found {len(news_tageschau)} news articles from Tagesschau")
+    logger.info(f"Found {len(news_tagesschau)} news articles from Tagesschau")
 
-    news_joined = news_handelsblatt + news_tageschau
+    news_joined = news_handelsblatt + news_tagesschau
 
     count_new_documents = 0
     count_duplicate_documents = 0

src/aki_prj23_transparenzregister/apps/ingest.py

@@ -25,7 +25,7 @@ from aki_prj23_transparenzregister.utils.logger_config import (
 
 
 def load_schedule(schedule_file: str) -> dict:
-    """Load scheudle data from file.
+    """Load schedule data from file.
 
     Returns:
         dict: Schedule data
@@ -52,7 +52,7 @@ def cli() -> None:  # pragma: no cover
     """CLI entry point."""
     parser = argparse.ArgumentParser(
         prog="Transparenzregister Company ingestion",
-        description="Ingests all missing companies and enriches them with finandcial data - runs on scheulde.",
+        description="Ingests all missing companies and enriches them with financial data - runs on schedule.",
         epilog="Example: ingest --log-level ERROR --log-path print.log",
     )
     parser.add_argument(
@@ -73,7 +73,7 @@ def cli() -> None:  # pragma: no cover
 
     # Schedule tasks or resume scheduling based on last execution times
     every(6).hours.do(fetch_news.main, config_provider).tag("fetch_news")
-    every(3).hours.do(main, config_provider).tag("missing_compnies_and_financials")
+    every(3).hours.do(main, config_provider).tag("missing_companies_and_financials")
 
     # Run the scheduler in a persistent loops
     while True:

src/aki_prj23_transparenzregister/config/config_providers.py

@@ -20,7 +20,7 @@ from aki_prj23_transparenzregister.config.config_template import (
 HELP_TEXT_CONFIG: Final[str] = (
     "Database configuration. "
     "Either give the paths to a *.json containing the secrets. "
-    "Alternativly specify the use of enviromental vairables by entering the ENV or the einviromental prefix ending with a '_'."
+    "Alternatively specify the use of environmental vairables by entering the ENV or the environmental prefix ending with a '_'."
 )
 
 

src/aki_prj23_transparenzregister/ui/protection.py

@@ -20,5 +20,5 @@ def add_auth(app: Dash) -> None:
         return
     logger.info("The password protection is not or only partially configured!")
     logger.debug(
-        "The enviromental variables PYTHON_DASH_LOGIN_USERNAME and PYTHON_DASH_LOGIN_PW should be used to activate this feature."
+        "The environmental variables PYTHON_DASH_LOGIN_USERNAME and PYTHON_DASH_LOGIN_PW should be used to activate this feature."
     )

src/aki_prj23_transparenzregister/utils/data_extraction/news/base.py

@@ -25,7 +25,7 @@ class BaseNewsExtractor(metaclass=abc.ABCMeta):
             category (str): News category to retrieve.
 
         Returns:
-            list[News] | None: List of news or None if an error occured.
+            list[News] | None: List of news or None if an error occurred.
         """
 
     @abc.abstractmethod

src/aki_prj23_transparenzregister/utils/data_extraction/news/tagesschau.py

@@ -1,4 +1,4 @@
-"""Tageschau API news extractor."""
+"""Tagesschau API news extractor."""
 import requests
 from bs4 import BeautifulSoup
 from loguru import logger
@@ -10,7 +10,7 @@ from aki_prj23_transparenzregister.utils.data_extraction.news.base import (
 
 
 class TagesschauAPI(BaseNewsExtractor):
-    """Tageschau API news extractor."""
+    """Tagesschau API news extractor."""
 
     def __init__(self) -> None:
         """Constructor."""
@@ -18,7 +18,7 @@ class TagesschauAPI(BaseNewsExtractor):
 
     @logger.catch(reraise=True)
     def get_news_for_category(self, category: str = "wirtschaft") -> list[News] | None:
-        """Retrieve news for the given category from the Tageschau API.
+        """Retrieve news for the given category from the Tagesschau API.
 
         Args:
             category (str, optional): Category to search for. Defaults to "wirtschaft".

src/aki_prj23_transparenzregister/utils/data_extraction/unternehmensregister/transform/common.py

@@ -134,7 +134,7 @@ class BaseTransformer(metaclass=abc.ABCMeta):
 
     @abc.abstractmethod
     def parse_date_of_birth(self, data: dict) -> str | None:
-        """Retreives the date of birth from a stakeholder entry if possible.
+        """Retrieves the date of birth from a stakeholder entry if possible.
 
         Args:
             data (dict): Stakeholder data

src/aki_prj23_transparenzregister/utils/data_extraction/unternehmensregister/transform/v1/v1.py

@@ -24,7 +24,7 @@ from aki_prj23_transparenzregister.utils.data_extraction.unternehmensregister.tr
     normalize_street,
 )
 from aki_prj23_transparenzregister.utils.string_tools import (
-    remove_traling_and_leading_quotes,
+    remove_trailing_and_leading_quotes,
     transform_date_to_iso,
 )
 
@@ -33,7 +33,7 @@ class V1_Transformer(BaseTransformer):  # noqa: N801
     """Transformer for data exports from Unternehmensregister (v1)."""
 
     def parse_date_of_birth(self, data: dict) -> str | None:
-        """Retreives the date of birth from a stakeholder entry if possible.
+        """Retrieves the date of birth from a stakeholder entry if possible.
 
         Args:
             data (dict): Stakeholder data
@@ -64,7 +64,7 @@ class V1_Transformer(BaseTransformer):  # noqa: N801
             ):
                 return CompanyToCompanyRelationship(
                     **{  # type: ignore
-                        "name": remove_traling_and_leading_quotes(
+                        "name": remove_trailing_and_leading_quotes(
                             data["Beteiligter"]["Natuerliche_Person"]["Voller_Name"][
                                 "Nachname"
                             ]
@@ -130,7 +130,7 @@ class V1_Transformer(BaseTransformer):  # noqa: N801
                     "role": RelationshipRoleEnum(
                         data["Rolle"]["Rollenbezeichnung"]["content"]
                     ),
-                    "name": remove_traling_and_leading_quotes(
+                    "name": remove_trailing_and_leading_quotes(
                         data["Beteiligter"]["Organisation"]["Bezeichnung"][
                             "Bezeichnung_Aktuell"
                         ]
@@ -213,7 +213,7 @@ class V1_Transformer(BaseTransformer):  # noqa: N801
         name = data["XJustiz_Daten"]["Grunddaten"]["Verfahrensdaten"]["Beteiligung"][0][
             "Beteiligter"
         ]["Organisation"]["Bezeichnung"]["Bezeichnung_Aktuell"]
-        return remove_traling_and_leading_quotes(name)
+        return remove_trailing_and_leading_quotes(name)
 
     def map_rechtsform(self, company_name: str, data: dict) -> CompanyTypeEnum | None:
         """Extracts the company type from a given Unternehmensregister export.

src/aki_prj23_transparenzregister/utils/data_extraction/unternehmensregister/transform/v3/v3.py

@@ -28,7 +28,7 @@ from aki_prj23_transparenzregister.utils.data_extraction.unternehmensregister.tr
     RoleMapper,
 )
 from aki_prj23_transparenzregister.utils.string_tools import (
-    remove_traling_and_leading_quotes,
+    remove_trailing_and_leading_quotes,
     transform_date_to_iso,
 )
 
@@ -37,7 +37,7 @@ class V3_Transformer(BaseTransformer):  # noqa: N801
     """Transformer for data exports from Unternehmensregister (v3)."""
 
     def parse_date_of_birth(self, data: dict) -> str | None:
-        """Retreives the date of birth from a stakeholder entry if possible.
+        """Retrieves the date of birth from a stakeholder entry if possible.
 
         Args:
             data (dict): Stakeholder data
@@ -89,7 +89,7 @@ class V3_Transformer(BaseTransformer):  # noqa: N801
             ):
                 return CompanyToCompanyRelationship(
                     **{  # type: ignore
-                        "name": remove_traling_and_leading_quotes(
+                        "name": remove_trailing_and_leading_quotes(
                             data["tns:beteiligter"]["tns:auswahl_beteiligter"][
                                 "tns:natuerlichePerson"
                             ]["tns:vollerName"]["tns:nachname"]
@@ -160,7 +160,6 @@ class V3_Transformer(BaseTransformer):  # noqa: N801
                 "tns:organisation"
             ]
 
-            location = None
             if "tns:anschrift" in base:
                 location = Location(
                     **{
@@ -197,7 +196,7 @@ class V3_Transformer(BaseTransformer):  # noqa: N801
                     "role": self.map_role_id_to_enum(
                         data["tns:rolle"]["tns:rollenbezeichnung"]["code"]
                     ),
-                    "name": remove_traling_and_leading_quotes(
+                    "name": remove_trailing_and_leading_quotes(
                         base["tns:bezeichnung"]["tns:bezeichnung.aktuell"]
                     ),
                     "location": location,
@@ -273,7 +272,7 @@ class V3_Transformer(BaseTransformer):  # noqa: N801
             "tns:bezeichnung.aktuell",
         ]
         name = traversal(data, path)
-        return remove_traling_and_leading_quotes(name)
+        return remove_trailing_and_leading_quotes(name)
 
     def map_rechtsform(self, company_name: str, data: dict) -> CompanyTypeEnum | None:
         """Extracts the company type from a given Unternehmensregister export.

src/aki_prj23_transparenzregister/utils/data_processing.py

@@ -35,7 +35,7 @@ def cli() -> None:  # pragma: no cover
     """A cli interface for the data transfer."""
     parser = argparse.ArgumentParser(
         prog="Process and transform data",
-        description="Process the raw data from the MongoDB with AI models and match and transform the data from the MongoDB when transfering into the SQL DB.",
+        description="Process the raw data from the MongoDB with AI models and match and transform the data from the MongoDB when transferring into the SQL DB.",
         epilog="Example: 'data-processing secrets.json' or 'data-processing ENV'",
     )
     parser.add_argument(

src/aki_prj23_transparenzregister/utils/mongo/company_mongo_service.py

@@ -99,7 +99,7 @@ class CompanyMongoService:
         return any(not re.match("^[0-9]{4}$", key) for key in data["yearly_results"])
 
     def is_self_referencing_auditors(self, data: dict) -> bool:
-        """Does the entry contain yearly_resutls which are self-referencing?
+        """Does the entry contain yearly_results which are self-referencing?
 
         Args:
             data (dict): Entry from MongoDB

src/aki_prj23_transparenzregister/utils/networkx/network_2d.py

@@ -15,7 +15,7 @@ def create_2d_graph(  # noqa PLR0913
     edge_annotation: bool,
     edge_thickness: int,
 ) -> go.Figure:
-    """This Method creates a 2d Network in Plotly with a Scatter Graph and retuns it.
+    """This Method creates a 2d Network in Plotly with a Scatter Graph and returns it.
 
     Args:
         graph: NetworkX Graph.

src/aki_prj23_transparenzregister/utils/networkx/network_3d.py

@@ -15,7 +15,7 @@ def create_3d_graph(  # noqa : PLR0913
     edge_annotation: bool,
     edge_thickness: int,
 ) -> go.Figure:
-    """This Method creates a 3D Network in Plotly with a Scatter Graph and retuns it.
+    """This Method creates a 3D Network in Plotly with a Scatter Graph and returns it.
 
     Args:
         graph: NetworkX Graph.

src/aki_prj23_transparenzregister/utils/networkx/network_base.py

@@ -4,7 +4,7 @@ import pandas as pd
 
 
 def initialize_network(edges: list, nodes: dict) -> tuple[nx.Graph, pd.DataFrame]:
-    """This Method creates a Network from the Framework NetworkX with the help of a Node and Edge List. Furthemore it creates a DataFrame with the most important Metrics.
+    """This Method creates a Network from the Framework NetworkX with the help of a Node and Edge List. Furthermore it creates a DataFrame with the most important Metrics.
 
     Args:
         edges (list): List with the connections between Nodes.
@@ -50,7 +50,7 @@ def initialize_network(edges: list, nodes: dict) -> tuple[nx.Graph, pd.DataFrame
 def initialize_network_with_reduced_metrics(
     edges: list, nodes: dict
 ) -> tuple[nx.Graph, pd.DataFrame]:
-    """This Method creates a Network from the Framework NetworkX with the help of a Node and Edge List. Furthemore it creates a DataFrame with the most important Metrics.
+    """This Method creates a Network from the Framework NetworkX with the help of a Node and Edge List. Furthermore it creates a DataFrame with the most important Metrics.
 
     Args:
         edges: List with the connections between Nodes.
@@ -58,7 +58,7 @@ def initialize_network_with_reduced_metrics(
 
     Returns:
         Graph: Plotly Figure
-        Metrices: DataFrame with Metrics
+        Metrics: DataFrame with Metrics
     """
     # create edge dataframe
     df_edges = pd.DataFrame(edges, columns=["from", "to", "type"])

src/aki_prj23_transparenzregister/utils/string_tools.py

@@ -36,15 +36,8 @@ def transform_date_to_iso(date: str) -> str:
     return date_temp.strftime("%Y-%m-%d")
 
 
-def remove_traling_and_leading_quotes(value: str) -> str:
+def remove_trailing_and_leading_quotes(value: str) -> str:
-    """Removes trailing and leading double-quotes from given string if present.
+    """Removes trailing and leading double-quotes from given string if present."""
-
-    Args:
-        value (str): _description_
-
-    Returns:
-        str: _description_
-    """
     if value is not None:
         count_quotes = value.count('"')
         if count_quotes > 0:

tests/ai/ner_pipeline_test.py

@@ -12,9 +12,6 @@ from aki_prj23_transparenzregister.config.config_template import MongoConnection
 def mock_mongo_connection() -> MongoConnection:
     """Mock MongoConnector class.
 
-    Args:
-        mocker (any): Library mocker
-
     Returns:
         Mock: Mocked MongoConnector
     """

tests/ai/ner_service_test.py

@@ -7,7 +7,7 @@ def test_ner_spacy() -> None:
     """Mock TestNerService."""
     # Create instance of NerAnalysisService with use_spacy=True
     ner_service = NerAnalysisService(
-        use_spacy=True, use_transformer=False, use_companylist=False
+        use_spacy=True, use_transformer=False, use_company_list=False
     )
     # 1st testing
     doc = {"title": "Siemens ist ein Unternehmen."}
@@ -24,7 +24,7 @@ def test_ner_company_list() -> None:
     """Mock test_ner_company."""
     # Create instance of NerAnalysisService with use_companylist=True
     ner_service = NerAnalysisService(
-        use_spacy=False, use_transformer=False, use_companylist=True
+        use_spacy=False, use_transformer=False, use_company_list=True
     )
 
     doc = {"title": "Siemens ist ein Unternehmen."}
@@ -41,7 +41,7 @@ def test_ner_transformer() -> None:
     """Mock test_ner_company."""
     # Create instance of NerAnalysisService with use_use_companylist=True
     ner_service = NerAnalysisService(
-        use_spacy=False, use_transformer=True, use_companylist=False
+        use_spacy=False, use_transformer=True, use_company_list=False
     )
 
     doc = {"title": "Siemens ist ein Unternehmen."}

tests/ai/sentiment_pipeline_test.py

@@ -14,9 +14,6 @@ from aki_prj23_transparenzregister.config.config_template import MongoConnection
 def mock_mongo_connection() -> MongoConnection:
     """Mock MongoConnector class.
 
-    Args:
-        mocker (any): Library mocker
-
     Returns:
         Mock: Mocked MongoConnector
     """

tests/apps/find_missing_companies_test.py

@@ -20,6 +20,10 @@ def test_work(
     company_mongo_service_mock: Mock,
     mongo_connector_mock: Mock,
 ) -> None:
+    _ = connector_mock
+    _ = mongo_connector_mock
+    _ = company_mongo_service_mock
+
     config_provider_mock = Mock()
     config_provider_mock.session.return_value = Mock()
 

tests/utils/mongo/company_mongo_service_test.py

@@ -91,7 +91,7 @@ def test_by_id_result(mock_mongo_connector: Mock, mock_collection: Mock) -> None
     """
     mock_mongo_connector.database = {"companies": mock_collection}
     service = CompanyMongoService(mock_mongo_connector)
-    mock_entry = {"id": "Does exist", "vaue": 42}
+    mock_entry = {"id": "Does exist", "value": 42}
     mock_collection.find.return_value = [mock_entry]
     id = CompanyID(DistrictCourt("a", "b"), "c").to_dict()
     assert service.get_by_id(id) == mock_entry
@@ -154,7 +154,7 @@ def test_get_where_financial_results(
     assert service.get_where_yearly_results() == mock_result
 
 
-def test_add_yearly_reslults(mock_mongo_connector: Mock, mock_collection: Mock) -> None:
+def test_add_yearly_results(mock_mongo_connector: Mock, mock_collection: Mock) -> None:
     mock_mongo_connector.database = {"companies": mock_collection}
     service = CompanyMongoService(mock_mongo_connector)
     mock_result: list = [{"_id": "abc", "brille?": "Fielmann", "Hotel?": "Trivago"}]

tests/utils/networkx/network_base_test.py

@@ -81,5 +81,5 @@ def test_initialize_network() -> None:
         "id",
     ]
 
-    graph = initialize_network_without_metrics(edges=edges, nodes=nodes)
+    initialize_network_without_metrics(edges=edges, nodes=nodes)
     assert isinstance(graph_reduced, nx.Graph)

tests/utils/string_tools_test.py

@@ -57,5 +57,5 @@ def test_transform_date_to_iso(value: str, expected: str) -> None:
     ],
 )
 def test_remove_trailing_and_leading_quotes(value: str, expected_result: str) -> None:
-    result = string_tools.remove_traling_and_leading_quotes(value)
+    result = string_tools.remove_trailing_and_leading_quotes(value)
     assert result == expected_result