invalid-parameter-default fix

pyproject.toml

@@ -122,19 +122,6 @@ omit = ["*/tests/*", "*/__init__.py"]
 [tool.ty.src]
 include = ["src"]
 
-[tool.ty.rules]
-unresolved-import = "warn"
-invalid-parameter-default = "warn"
-invalid-return-type = "warn"
-invalid-argument-type = "warn"
-invalid-assignment = "warn"
-unsupported-operator = "warn"
-unresolved-attribute = "warn"
-missing-argument = "warn"
-unknown-argument = "warn"
-not-subscriptable = "warn"
-possibly-missing-submodule = "warn"
-
 [tool.numpydoc_validation]
 checks = [
     "all",  # report on all checks, except the below

src/scribe_data/check/check_missing_forms/check_missing_forms.py

@@ -53,8 +53,8 @@ def execute_sparql_query(query: str, max_retries: int = 3) -> Optional[list]:
     query : str
         The SPARQL query to execute.
 
-    max_retries : int, optional
-        Maximum number of retry attempts (default: 3).
+    max_retries : int, optional, default=3
+        Maximum number of retry attempts.
 
     Returns
     -------
@@ -183,8 +183,8 @@ def get_forms_from_sparql_service(
         Minimum frequency threshold for including form combinations.
         Default is 0 (include all combinations).
 
-    max_results : int, optional
-        Maximum number of results to return (default: 1000).
+    max_results : int, optional, default=1000
+        Maximum number of results to return.
         Helps prevent timeout for very large datasets.
 
     language_name : str, optional
@@ -288,8 +288,8 @@ def get_forms_from_sparql_service_all_languages(
         Minimum frequency threshold for including form combinations.
         Default is 0 (include all combinations).
 
-    max_results : int, optional
-        Maximum results per query to prevent timeouts (default: 1000).
+    max_results : int, optional, default=1000
+        Maximum results per query to prevent timeouts.
 
     Returns
     -------
@@ -384,8 +384,8 @@ def get_features_from_sparql_service(
         Minimum frequency threshold for including form combinations.
         Default is 0 (include all combinations).
 
-    max_results : int, optional
-        Maximum results per query to prevent timeouts (default: 1000).
+    max_results : int, optional, default=1000
+        Maximum results per query to prevent timeouts .
 
     Returns
     -------

src/scribe_data/check/check_missing_forms/normalize_forms.py

@@ -3,11 +3,13 @@
 Order QID from a missing_unique_forms based on lexeme_form_metadata.yaml.
 """
 
+from typing import List
+
 from scribe_data.utils import lexeme_form_metadata
 
 
 # Precompute QID positions mapping only once when the module is imported.
-def sort_qids_in_list(qids_lists: list[list[str]]) -> list[list[str]]:
+def sort_qids_in_list(qids_lists: List[List[str]]) -> List[List[str]]:
     """
     Sort QIDs within each sublist based on their predefined positions.
 
@@ -16,7 +18,7 @@ def sort_qids_in_list(qids_lists: list[list[str]]) -> list[list[str]]:
 
     Parameters
     ----------
-    qids_lists : list[list[str]]
+    qids_lists : List[List[str]]
         A list of lists, where each sublist contains QIDs.
 
     Returns
@@ -37,17 +39,17 @@ def sort_qids_in_list(qids_lists: list[list[str]]) -> list[list[str]]:
     ]
 
 
-def sort_qids_by_position(nested_qids: list[list[str]]) -> list[list[str]]:
+def sort_qids_by_position(nested_qids: List[List[str]]) -> List[List[str]]:
     """
     Sort lists of QIDs based on their predefined positions and sublist length.
 
-    This function sorts the sublists within `nested_qids` based on two criteria:
+    This function sorts the sub-lists within `nested_qids` based on two criteria:
     1. The length of the sublist (shorter lists come first).
     2. The positions of the QIDs within each sublist, as defined in `lexeme_form_metadata`.
 
     Parameters
     ----------
-    nested_qids : list[list[str]]
+    nested_qids : List[List[str]]
         A list of lists, where each sublist contains QIDs.
 
     Returns

src/scribe_data/check/check_project_metadata.py

@@ -9,6 +9,7 @@
 
 import difflib
 import sys
+from typing import List
 
 from scribe_data.utils import (
     WIKIDATA_QUERIES_ALL_DATA_DIR,
@@ -19,13 +20,13 @@
 all_data_types = tuple(data_type_metadata.keys())
 
 
-def get_available_languages() -> dict[str, list[str]]:
+def get_available_languages() -> dict[str, List[str]]:
     """
     Get available languages from the data extraction folder.
 
     Returns
     -------
-    dict[str, list[str]]
+    dict[str, List[str]]
         A dictionary with the language name as the key and a list of its sub-languages (if available).
     """
     available_languages = {}
@@ -64,7 +65,7 @@ def get_available_languages() -> dict[str, list[str]]:
 
 def get_missing_languages(
     reference_languages: dict, target_languages: dict
-) -> list[str]:
+) -> List[str]:
     """
     Compare two language dictionaries and return a list of languages and sub-languages that exist.
 
@@ -78,7 +79,7 @@ def get_missing_languages(
 
     Returns
     -------
-    list[str]
+    List[str]
         A list of languages and sub-languages that are in target_languages but not in reference_languages.
     """
     missing_languages = []

src/scribe_data/check/check_pyicu.py

@@ -13,7 +13,7 @@
 import subprocess
 import sys
 from pathlib import Path
-from typing import Optional
+from typing import List, Optional
 
 import questionary
 import requests
@@ -55,7 +55,7 @@ def get_python_version_and_architecture() -> tuple[str, str]:
     return python_version, architecture
 
 
-def fetch_wheel_releases() -> tuple[list[tuple[str, str]], float]:
+def fetch_wheel_releases() -> tuple[List[tuple[str, str]], float]:
     """
     Fetch the release data for PyICU from GitHub with error handling for rate limits.
 
@@ -114,7 +114,7 @@ def download_wheel_file(wheel_url: str, output_dir: Path) -> str:
 
 
 def find_matching_wheel(
-    wheels: list[tuple[str, str]], python_version: str, architecture: str
+    wheels: List[tuple[str, str]], python_version: str, architecture: str
 ) -> Optional[str]:
     """
     Find the matching wheel file based on Python version and architecture.

src/scribe_data/check/check_query_forms.py

@@ -135,7 +135,7 @@ def decompose_label_features(label: str) -> list:
 # MARK: Extract QIDs
 
 
-def extract_form_qids(form_text: str) -> Optional[list[str]]:
+def extract_form_qids(form_text: str) -> Optional[List[str]]:
     """
     Extract all QIDs from an optional query form.
 
@@ -146,7 +146,7 @@ def extract_form_qids(form_text: str) -> Optional[list[str]]:
 
     Returns
     -------
-    list[str]
+    Optional[List[str]]
         All QIDS that make up the form.
     """
     qids_pattern = r"wikibase:grammaticalFeature .+ \."
@@ -224,13 +224,13 @@ def check_query_formatting(form_text: str) -> bool:
 # MARK: Correct Label
 
 
-def return_correct_form_label(qids: list[str]) -> str:
+def return_correct_form_label(qids: List[str]) -> str:
     """
     Return the correct label for a lexeme form representation given the QIDs that compose it.
 
     Parameters
     ----------
-    qids : list[str]
+    qids : List[str]
         All QIDS that make up the form.
 
     Returns
@@ -447,12 +447,12 @@ def compare_key(components: List[str]) -> List[str | int | float]:
 
         Parameters
         ----------
-        components : list[str]
+        components : List[str]
             The components that can make up the form identifier.
 
         Returns
         -------
-        list[str]
+        List[str | int | float]
             The list of component parts to compare against.
         """
         return [order_map.get(c, float("inf")) for c in components]

src/scribe_data/cli/convert.py

@@ -397,13 +397,13 @@ def convert_wrapper(
     output_type : str
         The desired output format. Can be 'json', 'csv', 'tsv', or 'sqlite'.
 
-    overwrite : bool, optional (default=False)
+    overwrite : bool, optional, default=False
         Whether to overwrite existing output files.
 
-    identifier_case : str, optional (default='camel')
+    identifier_case : str, optional, default='camel'
         The case format for identifiers.
 
-    all : bool, optional (default=False)
+    all : bool, optional, default=False
         Convert all languages and data types.
 
     Returns

src/scribe_data/cli/download.py

@@ -9,7 +9,7 @@
 from collections.abc import Callable
 from datetime import date, datetime
 from pathlib import Path
-from typing import Optional
+from typing import List, Optional
 
 import questionary
 import requests
@@ -298,7 +298,7 @@ def wd_lexeme_dump_download_wrapper(
 
 def download_wiktionary_dumps(
     output_dir: Path = DEFAULT_WIKTIONARY_DUMP_EXPORT_DIR,
-    language_isos: list[str] = ["en"],
+    language_isos: List[str] = ["en"],
     dump_snapshot: Optional[str] = "latest",
 ) -> Optional[Path]:
     """
@@ -309,7 +309,7 @@ def download_wiktionary_dumps(
     output_dir : Path, optional, default=DEFAULT_WIKTIONARY_DUMP_EXPORT_DIR
         Directory to save the dump. Defaults to DEFAULT_WIKTIONARY_DUMP_EXPORT_DIR.
 
-    language_isos : list[str], optional, default=['en']
+    language_isos : List[str], optional, default=['en']
         A list of ISO-2 codes for desired Wiktionary dumps.
 
     dump_snapshot : str, optional, default='latest'

src/scribe_data/cli/get.py

@@ -48,10 +48,10 @@ def get_data(
 
     Parameters
     ----------
-    languages : list[str]
+    languages : List[str]
         The language(s) to get.
 
-    data_types : list[str]
+    data_types : List[str]
         The data type(s) to get.
 
     output_type : str
@@ -60,7 +60,7 @@ def get_data(
     output_dir : Path
         The output directory path for results.
 
-    overwrite : bool (default: False)
+    overwrite : bool, default=False
         Whether to overwrite existing files.
 
     outputs_per_entry : str
@@ -69,7 +69,7 @@ def get_data(
     all_bool : bool
         Get all languages and data types.
 
-    interactive : bool (default: False)
+    interactive : bool, default: False
         Whether it's running in interactive mode.
 
     identifier_case : str

src/scribe_data/cli/interactive.py

@@ -103,7 +103,7 @@ def create_word_completer(
 
     Parameters
     ----------
-    options : list[str]
+    options : List[str]
         The options that could complete the current input.
 
     include_all : bool

src/scribe_data/cli/total.py

@@ -58,7 +58,7 @@ def get_datatype_list(language: str) -> list | dict:
 
     Returns
     -------
-    list[str]
+    list | dict
         A list of the corresponding data types.
     """
     language_key = language.strip().lower()  # normalize input

src/scribe_data/load/data_to_sqlite.py

@@ -25,7 +25,7 @@
 
 
 def create_table(
-    cursor: sqlite3.Cursor, identifier_case: str, data_type: str, cols: list[str]
+    cursor: sqlite3.Cursor, identifier_case: str, data_type: str, cols: List[str]
 ) -> None:
     """
     Create a table in the language database.
@@ -102,10 +102,10 @@ def translations_to_sqlite(
         A list of current languages.
     identifier_case : str, optional
         The identifier case. Default is "snake".
-    input_file : str, optional
-        The input JSON export directory (default=DEFAULT_JSON_EXPORT_DIR).
-    output_file : str, optional
-        The output SQLite export directory (default=DEFAULT_SQLITE_EXPORT_DIR).
+    input_file : str, optional, default=DEFAULT_JSON_EXPORT_DIR
+        The input JSON export directory.
+    output_file : str, optional, default=DEFAULT_SQLITE_EXPORT_DIR
+        The output SQLite export directory.
     overwrite : bool, optional
         If True, existing SQLite files will be overwritten without prompting.
     """
@@ -195,11 +195,11 @@ def wiktionary_translations_to_sqlite(
     identifier_case : str, optional
         Either "camel" or "snake" to determine column naming. Default is "snake".
 
-    input_file : str, optional
-        The input JSON export directory (default=DEFAULT_JSON_EXPORT_DIR).
+    input_file : str, optional, default=DEFAULT_JSON_EXPORT_DIR
+        The input JSON export directory.
 
-    output_file : str, optional
-        The output SQLite export directory (default=DEFAULT_SQLITE_EXPORT_DIR).
+    output_file : str, optional, default=DEFAULT_SQLITE_EXPORT_DIR
+        The output SQLite export directory.
 
     overwrite : bool, optional
         If True, existing SQLite files will be overwritten without prompting.
@@ -296,14 +296,14 @@ def data_to_sqlite(
     specific_tables : Optional[Union[str, List[str]]]
         The specific tables to process. If None, process all tables.
 
-    identifier_case : str, optional (default='camel')
+    identifier_case : str, optional, default='camel'
         Format of the identifiers ("camel" or "snake"). Defaults to "camel".
 
-    input_file : str, optional
-        The input JSON export directory (default=DEFAULT_JSON_EXPORT_DIR).
+    input_file : str, optional, default=DEFAULT_JSON_EXPORT_DIR
+        The input JSON export directory.
 
-    output_file : str, optional
-        The output SQLite export directory (default=DEFAULT_SQLITE_EXPORT_DIR).
+    output_file : str, optional, default=DEFAULT_SQLITE_EXPORT_DIR
+        The output SQLite export directory.
 
     overwrite : bool, optional
         If set to True, existing SQLite files will be overwritten without prompting.

src/scribe_data/unicode/process_unicode.py

@@ -34,10 +34,10 @@ def gen_emoji_lexicon(
 
     Parameters
     ----------
-    language : str (default=None)
+    language : str
         The language keywords are being generated for.
 
-    emojis_per_keyword : int (default=None)
+    emojis_per_keyword : int
         The limit for number of emoji keywords that should be generated per keyword.
 
     Returns