fix: clear remaining ruff baseline errors on main

.github/badges/tests.json

@@ -1 +1,6 @@
-{"schemaVersion": 1, "label": "tests", "message": "397/400 passing", "color": "brightgreen"}
+{
+	"schemaVersion": 1,
+	"label": "tests",
+	"message": "397/400 passing",
+	"color": "brightgreen"
+}

.pre-commit-config.yaml

@@ -25,7 +25,7 @@ exclude: |
       gget/bins/
     | gget/constants/
     | tests/fixtures/
-    | tests/pytest_results_py.*\.txt
+    | tests/pytest_results.*\.txt
   )
 repos:
   - repo: https://github.com/biomejs/pre-commit

gget/gget_cbio.py

@@ -415,7 +415,9 @@ def _get_ensembl_gene_name_bulk(gene_ids: list[str]) -> dict[str, Any]:
         raise e
 
 
-def _get_valid_ensembl_gene_id(row: pd.Series, transcript_column: str = "seq_ID", gene_column: str = "gene_name") -> Any:
+def _get_valid_ensembl_gene_id(
+    row: pd.Series, transcript_column: str = "seq_ID", gene_column: str = "gene_name"
+) -> Any:
     ensembl_gene_id = _get_ensembl_gene_id(row[transcript_column])
     if ensembl_gene_id == "Unknown":
         return row[gene_column]

gget/gget_g2p.py

@@ -1,11 +1,12 @@
 from __future__ import annotations
 
 import io
+
 import pandas as pd
 import requests
 
 from .constants import G2P_API
-from .utils import set_up_logger, DEFAULT_REQUESTS_TIMEOUT
+from .utils import DEFAULT_REQUESTS_TIMEOUT, set_up_logger
 
 logger = set_up_logger()
 
@@ -18,9 +19,9 @@ def g2p(
     save: bool = False,
     verbose: bool = True,
 ) -> pd.DataFrame | None:
-    """
-    Query the Genomics 2 Proteins (G2P) portal (https://g2p.broadinstitute.org/) to link
-    genes/proteins to per-residue structural and functional annotations.
+    """Query the Genomics 2 Proteins (G2P) portal to link genes/proteins to per-residue structural and functional annotations.
+
+    Portal: https://g2p.broadinstitute.org/
 
     Args:
     - gene          Gene symbol, e.g. "BRCA1" (str).
@@ -43,9 +44,7 @@ def g2p(
     """
     resources = ["features", "map", "alignment"]
     if resource not in resources:
-        raise ValueError(
-            f"'resource' argument specified as {resource}. Expected one of: {', '.join(resources)}"
-        )
+        raise ValueError(f"'resource' argument specified as {resource}. Expected one of: {', '.join(resources)}")
 
     if not uniprot_id:
         raise ValueError(
@@ -69,9 +68,7 @@ def g2p(
         url = f"{base}/{isoform}/alignment"
 
     if verbose:
-        logger.info(
-            f"Querying the Genomics 2 Proteins portal ('{resource}') for {gene} / {uniprot_id}..."
-        )
+        logger.info(f"Querying the Genomics 2 Proteins portal ('{resource}') for {gene} / {uniprot_id}...")
 
     try:
         r = requests.get(
@@ -92,9 +89,7 @@ def g2p(
         return
 
     if not r.text.strip():
-        logger.warning(
-            "The Genomics 2 Proteins portal returned an empty result for this query."
-        )
+        logger.warning("The Genomics 2 Proteins portal returned an empty result for this query.")
         return pd.DataFrame()
 
     df = pd.read_csv(io.StringIO(r.text), sep="\t")

gget/gget_muscle.py

@@ -113,9 +113,7 @@ def muscle(fasta: str | list[str], super5: bool = False, out: str | None = None,
         diagnosis = diagnose_binary_load_error(stderr_2, "muscle")
         if diagnosis:
             raise RuntimeError(diagnosis)
-        raise RuntimeError(
-            f"MUSCLE failed with exit code {process_2.returncode}. See stderr above for details."
-        )
+        raise RuntimeError(f"MUSCLE failed with exit code {process_2.returncode}. See stderr above for details.")
     if verbose:
         logger.info(f"MUSCLE alignment complete. Alignment time: {round(time.time() - start_time, 2)} seconds")
 

gget/gget_pdb.py

@@ -1,8 +1,7 @@
 from __future__ import annotations
 
-from typing import Any
-
 import json
+from typing import Any
 from urllib.error import HTTPError
 from urllib.request import urlopen
 

gget/gget_search.py

@@ -310,8 +310,7 @@ def search(
     # inside the list to None so an empty-synonym row is [None] rather than
     # [nan]. (SQL LEFT JOIN on external_synonym surfaces missing rows as NaN.)
     df["synonym"] = [
-        [None if pd.isna(item) else item
-         for item in np.sort(syn if isinstance(syn, list) else [syn]).tolist()]
+        [None if pd.isna(item) else item for item in np.sort(syn if isinstance(syn, list) else [syn]).tolist()]
         for syn in df["synonym"].values
     ]
 

gget/gget_setup.py

@@ -115,9 +115,7 @@ def setup(module: str, verbose: bool = True, out: str | None = None) -> None:
         raise ValueError(f"'module' argument specified as {module}. Expected one of: {', '.join(supported_modules)}")
 
     if module == "gpt":
-        logger.warning(
-            "gget gpt is no longer actively maintained."
-        )
+        logger.warning("gget gpt is no longer actively maintained.")
         _install("openai<=0.28.1", "openai", verbose=verbose)
 
     elif module == "cellxgene":

gget/gget_virus.py

@@ -341,7 +341,10 @@ def _retry_with_exponential_backoff(
     initial_delay: float = API_INITIAL_RETRY_DELAY,
     backoff_multiplier: float = API_RETRY_BACKOFF_MULTIPLIER,
     max_delay: int = MAX_RETRY_DELAY,
-    retryable_exceptions: tuple[type[BaseException], ...] = (requests.exceptions.ConnectionError, requests.exceptions.HTTPError),
+    retryable_exceptions: tuple[type[BaseException], ...] = (
+        requests.exceptions.ConnectionError,
+        requests.exceptions.HTTPError,
+    ),
     failed_commands: dict[str, Any] | None = None,
 ) -> tuple[bool, Any, dict[str, Any] | None]:
     """Execute an operation with exponential backoff retry logic.
@@ -414,7 +417,9 @@ def _retry_with_exponential_backoff(
     return False, None, error_info
 
 
-def _track_failed_operation(failed_commands: dict[str, Any] | None, operation_type: str, batch_info: dict[str, Any], error_info: dict[str, Any]) -> None:
+def _track_failed_operation(
+    failed_commands: dict[str, Any] | None, operation_type: str, batch_info: dict[str, Any], error_info: dict[str, Any]
+) -> None:
     """Track a failed operation in the failed_commands dictionary.
 
     This ensures consistent error tracking across all operation types for
@@ -864,7 +869,9 @@ def _parse_baseline_file(baseline_path: str) -> set[str]:
     return baseline_accessions
 
 
-def _deduplicate_metadata_against_baseline(metadata_dict: dict[str, Any], baseline_accessions: set[str]) -> tuple[dict[str, Any], int]:
+def _deduplicate_metadata_against_baseline(
+    metadata_dict: dict[str, Any], baseline_accessions: set[str]
+) -> tuple[dict[str, Any], int]:
     """Remove metadata records whose accessions are already in the baseline set.
 
     Args:
@@ -889,7 +896,9 @@ def _deduplicate_metadata_against_baseline(metadata_dict: dict[str, Any], baseli
     return new_metadata, skipped_count
 
 
-def _save_partial_metadata(metadata_dict: dict[str, Any], outfolder: str, virus_clean: str, reason: str = "api_failure") -> str | None:
+def _save_partial_metadata(
+    metadata_dict: dict[str, Any], outfolder: str, virus_clean: str, reason: str = "api_failure"
+) -> str | None:
     """Save partial metadata to CSV for recovery via --baseline.
 
     Args:
@@ -2786,7 +2795,9 @@ def process_cached_download(zip_file: str, virus_type: str = "virus") -> tuple[s
     return cached_fasta_file, cached_metadata_jsonl_path, True
 
 
-def _monitor_subprocess_with_progress(process: subprocess.Popen[Any], cmd: list[str], timeout: int | None = None, progress_timeout: int | None = None) -> subprocess.CompletedProcess[Any]:
+def _monitor_subprocess_with_progress(
+    process: subprocess.Popen[Any], cmd: list[str], timeout: int | None = None, progress_timeout: int | None = None
+) -> subprocess.CompletedProcess[Any]:
     """Monitor a subprocess with progress tracking and timeout handling.
 
     This helper function monitors a running subprocess. When stdout/stderr are piped, it checks for progress indicators. When they're not piped (output goes to console), it simply polls for completion.
@@ -3463,7 +3474,13 @@ def download_alphainfluenza_optimized(
     )
 
 
-def download_sequences_by_accessions(accessions: list[str], outdir: str | None = None, batch_size: int = 200, failed_commands: dict[str, Any] | None = None, api_key: str | None = None) -> str:
+def download_sequences_by_accessions(
+    accessions: list[str],
+    outdir: str | None = None,
+    batch_size: int = 200,
+    failed_commands: dict[str, Any] | None = None,
+    api_key: str | None = None,
+) -> str:
     """Download virus genome sequences for a specific list of accession numbers.
 
     This function downloads sequences for a pre-filtered list of accessions,
@@ -3590,7 +3607,9 @@ def download_sequences_by_accessions(accessions: list[str], outdir: str | None =
     )
 
 
-def _download_sequences_epost_efetch(accessions: list[str], fasta_path: str, failed_commands: dict[str, Any] | None = None, api_key: str | None = None) -> str:
+def _download_sequences_epost_efetch(
+    accessions: list[str], fasta_path: str, failed_commands: dict[str, Any] | None = None, api_key: str | None = None
+) -> str:
     """Download FASTA sequences using NCBI EPost + EFetch History Server pipeline.
 
     This is NCBI's recommended approach for large datasets. It uploads accession
@@ -3756,7 +3775,11 @@ def _fetch_fasta_batch(rs=retstart):
 
 
 def _download_sequences_single_batch(
-    accessions: list[str], NCBI_EUTILS_BASE_EFETCH: str, fasta_path: str, failed_commands: dict[str, Any] | None = None, api_key: str | None = None
+    accessions: list[str],
+    NCBI_EUTILS_BASE_EFETCH: str,
+    fasta_path: str,
+    failed_commands: dict[str, Any] | None = None,
+    api_key: str | None = None,
 ) -> str:
     """Download sequences in a single E-utilities request with exponential backoff retries.
 
@@ -3882,7 +3905,12 @@ def execute_request():
 
 
 def _download_sequences_batched(
-    accessions: list[str], NCBI_EUTILS_BASE_EFETCH: str, fasta_path: str, batch_size: int, failed_commands: dict[str, Any] | None = None, api_key: str | None = None
+    accessions: list[str],
+    NCBI_EUTILS_BASE_EFETCH: str,
+    fasta_path: str,
+    batch_size: int,
+    failed_commands: dict[str, Any] | None = None,
+    api_key: str | None = None,
 ) -> str:
     """Download sequences using multiple batched E-utilities requests with incremental file writing.
 
@@ -4154,7 +4182,9 @@ def _parse_date(date_str: str, filtername: str = "") -> datetime:
         #     return None
 
 
-def _parse_partial_date_for_range_check(date_str: str, for_min_comparison: bool = True, filtername: str = "") -> datetime:
+def _parse_partial_date_for_range_check(
+    date_str: str, for_min_comparison: bool = True, filtername: str = ""
+) -> datetime:
     """Parse partial dates with range-aware handling for comparison.
 
     When comparing partial dates (year-only or year-month) against specific dates,
@@ -4749,7 +4779,9 @@ def load_metadata_from_api_reports(api_reports: list[dict[str, Any]]) -> dict[st
     return metadata_dict
 
 
-def _check_protein_requirements(record: Any, metadata: dict[str, Any], has_proteins: Any, proteins_complete: bool) -> bool:
+def _check_protein_requirements(
+    record: Any, metadata: dict[str, Any], has_proteins: Any, proteins_complete: bool
+) -> bool:
     """Check if a sequence meets protein/gene requirements based on FASTA header.
 
     This function validates whether a virus sequence contains required proteins
@@ -5491,7 +5523,9 @@ def merge_metadata_csvs(genbank_csv_path: str, standard_csv_path: str) -> bool:
         return False
 
 
-def save_metadata_to_csv(filtered_metadata: list[dict[str, Any]], protein_headers: list[Any], output_metadata_file: str) -> None:
+def save_metadata_to_csv(
+    filtered_metadata: list[dict[str, Any]], protein_headers: list[Any], output_metadata_file: str
+) -> None:
     """Save filtered metadata to a CSV file with a specific column order.
 
     This function creates a comprehensive CSV file containing all relevant metadata
@@ -5968,7 +6002,14 @@ def _epost_accessions(accessions: list[str], api_key: str | None = None) -> tupl
         return None, None
 
 
-def _efetch_with_history(web_env: str, query_key: str, retstart: int, retmax: int, api_key: str | None = None, failed_log_path: str | None = None) -> tuple[dict[str, Any], str]:
+def _efetch_with_history(
+    web_env: str,
+    query_key: str,
+    retstart: int,
+    retmax: int,
+    api_key: str | None = None,
+    failed_log_path: str | None = None,
+) -> tuple[dict[str, Any], str]:
     """Fetch GenBank records using History Server reference (WebEnv/query_key).
 
     This is the NCBI-recommended method for large datasets. After uploading UIDs
@@ -6609,7 +6650,9 @@ def fetch_genbank_metadata(
     return all_metadata, failed_log_path if os.path.exists(failed_log_path) else None
 
 
-def _fetch_genbank_batch(accessions: list[str], failed_log_path: str | None = None) -> tuple[dict[str, Any], str | None]:
+def _fetch_genbank_batch(
+    accessions: list[str], failed_log_path: str | None = None
+) -> tuple[dict[str, Any], str | None]:
     """Fetch GenBank metadata for a single batch of accessions.
 
     Includes retry logic with exponential backoff and automatic batch splitting
@@ -7188,7 +7231,9 @@ def _parse_genbank_xml(xml_content: str) -> dict[str, Any]:
     return metadata_dict
 
 
-def save_genbank_metadata_to_csv(genbank_metadata: dict[str, Any], output_file: str, virus_metadata: list[dict[str, Any]] | None = None) -> None:
+def save_genbank_metadata_to_csv(
+    genbank_metadata: dict[str, Any], output_file: str, virus_metadata: list[dict[str, Any]] | None = None
+) -> None:
     """Save GenBank metadata to a CSV file with the same column headers as the standard metadata CSV.
 
     Args:

gget/main.py

@@ -1,10 +1,9 @@
 from __future__ import annotations
 
-from typing import Any
-
 import argparse
 import sys
 from datetime import datetime
+from typing import Any
 
 import pandas as pd
 
@@ -31,38 +30,18 @@
 from .gget_diamond import diamond  # noqa: E402
 from .gget_elm import elm  # noqa: E402
 from .gget_enrichr import enrichr  # noqa: E402
+from .gget_g2p import g2p  # noqa: E402
 from .gget_gpt import gpt  # noqa: E402
 from .gget_info import info  # noqa: E402
 from .gget_muscle import muscle  # noqa: E402
 from .gget_mutate import mutate  # noqa: E402
 from .gget_opentargets import OPENTARGETS_RESOURCES, opentargets  # noqa: E402
 from .gget_pdb import pdb  # noqa: E402
-
-# Module functions
-from .gget_ref import ref
-from .gget_search import search
-from .gget_info import info
-from .gget_seq import seq
-from .gget_muscle import muscle
-from .gget_blast import blast
-from .gget_blat import blat
-from .gget_enrichr import enrichr
-from .gget_archs4 import archs4
-from .gget_alphafold import alphafold
-from .gget_setup import setup
-from .gget_pdb import pdb
-from .gget_gpt import gpt
-from .gget_cellxgene import cellxgene
-from .gget_elm import elm
-from .gget_diamond import diamond
-from .gget_cosmic import cosmic
-from .gget_mutate import mutate
-from .gget_opentargets import opentargets, OPENTARGETS_RESOURCES
-from .gget_cbio import cbio_plot, cbio_search
-from .gget_bgee import bgee
-from .gget_g2p import g2p
-from .gget_8cube import specificity, psi_block, gene_expression
-from .gget_virus import virus
+from .gget_ref import ref  # noqa: E402
+from .gget_search import search  # noqa: E402
+from .gget_seq import seq  # noqa: E402
+from .gget_setup import setup  # noqa: E402
+from .gget_virus import virus  # noqa: E402
 
 
 # Custom formatter for help messages that preserved the text formatting and adds the default value to the end of the help message
@@ -3835,16 +3814,12 @@ def main() -> None:
                 if args.csv:
                     g2p_results.to_csv(f, index=False)
                 else:
-                    g2p_results.to_json(
-                        f, orient="records", force_ascii=False, indent=4
-                    )
+                    g2p_results.to_json(f, orient="records", force_ascii=False, indent=4)
         else:
             if args.csv:
                 g2p_results.to_csv(sys.stdout, index=False)
             else:
-                print(
-                    g2p_results.to_json(orient="records", force_ascii=False, indent=4)
-                )
+                print(g2p_results.to_json(orient="records", force_ascii=False, indent=4))
 
     ## 8cube return
     if args.command == "8cube":