Merge branch 'main' into merge

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ repos:
   - id: trailing-whitespace
   - id: end-of-file-fixer
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.1.2
+  rev: v0.1.9
   hooks:
     - id: ruff
     - id: ruff-format

README.md

@@ -5,9 +5,9 @@ Gene Normalizer
 ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/gene-normalizer?color=gr) [![tests](https://github.com/cancervariants/gene-normalization/actions/workflows/github-actions.yml/badge.svg)](https://github.com/cancervariants/gene-normalization/actions/workflows/github-actions.yml) [![DOI](https://zenodo.org/badge/309797998.svg)](https://zenodo.org/badge/latestdoi/309797998)
 
 ## Overview
-
+<!-- description -->
 The Gene Normalizer provides tools for resolving ambiguous human gene references to consistently-structured, normalized terms. For gene concepts extracted from [NCBI Gene](https://www.ncbi.nlm.nih.gov/gene/), [Ensembl](https://useast.ensembl.org/index.html), and [HGNC](https://www.genenames.org/), it designates a [CURIE](https://en.wikipedia.org/wiki/CURIE), and provides additional metadata like current and previously-used symbols, aliases, database cross-references and associations, and coordinates.
-
+<!-- /description -->
 ---
 
 **[Live service](https://normalize.cancervariants.org/gene)**

pyproject.toml

@@ -38,7 +38,7 @@ dynamic = ["version"]
 pg = ["psycopg[binary]"]
 etl = ["gffutils", "biocommons.seqrepo", "wags-tails>=0.1.1"]
 test = ["pytest>=6.0", "pytest-cov", "mock", "httpx"]
-dev = ["pre-commit", "ruff>=0.1.2"]
+dev = ["pre-commit", "ruff>=0.1.9"]
 docs = [
     "sphinx==6.1.3",
     "sphinx-autodoc-typehints==1.22.0",

src/gene/etl/base.py

@@ -6,6 +6,7 @@
 from pathlib import Path
 from typing import Dict, List, Optional, Union
 
+import click
 import pydantic
 from biocommons.seqrepo import SeqRepo
 from gffutils.feature import Feature
@@ -34,6 +35,13 @@ class GeneNormalizerEtlError(Exception):
 }
 
 
+DATA_DISPATCH = {
+    SourceName.HGNC: HgncData,
+    SourceName.ENSEMBL: EnsemblData,
+    SourceName.NCBI: NcbiGeneData,
+}
+
+
 class Base(ABC):
     """The ETL base class."""
 
@@ -79,6 +87,8 @@ def perform_etl(self, use_existing: bool = False) -> List[str]:
         """
         self._extract_data(use_existing)
         _logger.info(f"Transforming and loading {self._src_name} data to DB...")
+        if not self._silent:
+            click.echo("Transforming and loading data to DB...")
         self._add_meta()
         self._transform_data()
         self._database.complete_write_transaction()
@@ -93,11 +103,9 @@ def _extract_data(self, use_existing: bool) -> None:
 
         :param bool use_existing: if True, don't try to fetch latest source data
         """
-        _logger.info(f"Gathering {self._src_name} data...")
         self._data_file, self._version = self._data_source.get_latest(
             from_local=use_existing
         )
-        _logger.info(f"Acquired data for {self._src_name}: {self._data_file}")
 
     @abstractmethod
     def _transform_data(self) -> None: