style: Fix linting issues (#4)

* style: Fix linting issues

* compat: Remove dict union operator

genomeinfo/__init__.py

@@ -1,9 +1,20 @@
-from .interface import GenomeInfo
+from __future__ import annotations
+
 from . import core
+from .interface import GenomeInfo
 
 for module in [core]:
     for name, func in module.__dict__.items():
         if callable(func) and not name.startswith("_"):
             setattr(GenomeInfo, name, func)
 
 __all__ = ["GenomeInfo"]
+
+
+_db: GenomeInfo | None = None
+
+def connect() -> GenomeInfo:
+    global _db
+    if _db is None:
+        _db = GenomeInfo()
+    return _db

genomeinfo/build/schema.py

@@ -60,11 +60,9 @@
     "WBcel235": "ce11",
     "WS190": "ce6",
     "WS195": np.NaN,
-    "WS195": np.NaN,
     "ASM2820141v1": np.NaN,
 }
 DROSOPHILA_ASSEMBLY_MAP = {
-    "Release_5": "dm3",
     "Release_5": "dm3",
     "Release_6": "dm6",
     "Release_6_plus_ISO1_MT": "dm6",

genomeinfo/core/chrom.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from __future__ import annotations
 
 import pandas as pd
 
@@ -14,9 +14,9 @@
 def filter_chromosome_data(
     cls,
     assembly: str,
-    roles: Optional[List[str]] = None,
-    units: Optional[List[str]] = None,
-    length: Optional[str] = None,
+    roles: list[str] | None = None,
+    units: list[str] | None = None,
+    length: str | None = None,
 ) -> pd.DataFrame:
     """
     Filters the chromosome data based on the provided parameters.
@@ -25,9 +25,9 @@ def filter_chromosome_data(
     ----------
     assembly : str
         The assembly name to filter by.
-    roles : Optional[List[str]]
+    roles : list[str], optional
         The roles to filter by.
-    units : Optional[List[str]]
+    units : list[str], optional
         The units to filter by.
     length : Optional[str]
         The length condition to filter by (e.g., '> 1000').
@@ -88,11 +88,11 @@ def filter_chromosome_data(
 def get_chromnames(
     cls,
     assembly: str,
-    provider: Optional[str] = None,
-    roles: Optional[List[str]] = None,
-    units: Optional[List[str]] = None,
-    length: Optional[str] = None,
-) -> List[str]:
+    provider: str | None = None,
+    roles: list[str] | None = None,
+    units: list[str] | None = None,
+    length: str | None = None,
+) -> list[str]:
     """
     Returns the chromosome names for the specified assembly.
 
@@ -140,10 +140,10 @@ def get_chromnames(
 def get_chromsizes(
     cls,
     assembly: str,
-    provider: Optional[str] = None,
-    roles: Optional[List[str]] = None,
-    units: Optional[List[str]] = None,
-    length: Optional[str] = None,
+    provider: str | None = None,
+    roles: list[str] | None = None,
+    units: list[str] | None = None,
+    length: str | None = None,
 ) -> pd.Series:
     """
     Returns the chromosome sizes for the specified assembly.
@@ -193,10 +193,10 @@ def get_chromsizes(
 def get_chrom_eq(
     cls,
     assembly: str,
-    providers: Optional[List[str]] = None,
-    roles: Optional[List[str]] = None,
-    units: Optional[List[str]] = None,
-    length: Optional[str] = None,
+    providers: list[str] | None = None,
+    roles: list[str] | None = None,
+    units: list[str] | None = None,
+    length: str | None = None,
 ) -> pd.DataFrame:
     """
     Returns the chromosome equivalence for the specified assembly.

genomeinfo/core/info.py

@@ -161,10 +161,6 @@ def get_species_info(cls, species: Optional[str] = None) -> str:
     species : Optional[str]
         The species name to filter by.
 
-    Returns
-    ----------
-    NoReturn
-
     Examples
     --------
     >>> GenomeInfo.get_species_info("species", "homo_sapiens")
@@ -203,10 +199,6 @@ def get_organism_info(cls, organism: Optional[str] = None) -> str:
     organism : Optional[str]
         The common name of the organism to filter by.
 
-    Returns
-    ----------
-    NoReturn
-
     Examples
     --------
     >>> GenomeInfo.get_species_info("species", "homo_sapiens")
@@ -334,14 +326,14 @@ def build_assembly_info(cls, local_db: pd.DataFrame, assembly: str) -> Dict[str,
             f"patch=='{local_db.assembly.unique()[0]}'"
         ).metadata.tolist()[0]
 
-    return core | {
+    return dict(core, **{
         "species": local_db.species.unique()[0],
         "common_name": local_db.common_name.unique()[0],
         "synonyms": [local_db.assembly.unique()[0], local_db.assembly_ucsc.unique()[0]],
         "patches": local_db.patch.tolist(),
         "genbank": local_db.genbank_accession.tolist(),
         "refseq": local_db.refseq_accession.tolist(),
-    }
+    })
 
 
 def available_assemblies(cls, provider: Optional[str] = None) -> List[str]:

genomeinfo/interface.py

@@ -1,10 +1,8 @@
-import pandas as pd
-import pyarrow.parquet as pq
-import pyarrow as pa
-import numpy as np
-from typing import Self, NoReturn
+from __future__ import annotations
+
 from pathlib import Path
-import os
+
+import pyarrow.parquet as pq
 
 __all__ = ["GenomeInfo"]
 
@@ -13,17 +11,17 @@ class GenomeInfo:
     _instance = None
     _db_path = Path(__file__).parent / "data" / "db.parquet"
 
-    def __new__(cls, *args, **kwargs) -> Self:
+    def __new__(cls, *args, **kwargs):
         if cls._instance is None:
-            cls._instance = super(GenomeInfo, cls).__new__(cls)
+            cls._instance = super().__new__(cls)
             cls._instance._load_db()
         return cls._instance
 
-    def _load_db(self) -> NoReturn:
+    def _load_db(self) -> None:
         """Private method to connect to the database."""
         self._data = pq.read_table(self._db_path).to_pandas()
 
     @classmethod
-    def connect(cls) -> Self:
+    def connect(cls):
         """Returns the singleton instance of GenomeInfo."""
         return cls()