build: separate dependency groups by use case (#202)

.github/workflows/github-actions.yml

@@ -1,11 +1,31 @@
 name: github-actions
 on: [push, pull_request]
 jobs:
+  lint:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10']
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: python3 -m pip install ".[dev]"
+
+      - name: Check style
+        run: python3 -m flake8 gene/ tests/ setup.py
+
   test:
     runs-on: ubuntu-latest
     strategy:
       matrix:
         db_url: ["http://localhost:8000", "postgres://postgres:postgres@localhost:5432/gene_normalizer_test"]
+        python-version: ['3.8', '3.9', '3.10']
     services:
       postgres:
         image: postgres:14
@@ -25,24 +45,27 @@ jobs:
     steps:
       - uses: actions/checkout@v3
 
-      - name: Setup Python
+      - name: Set up Python
         uses: actions/setup-python@v4
         with:
-            python-version: 3.8
+          python-version: ${{ matrix.python-version }}
 
-      - name: Install dependencies
-        run: |
-          python3 -m pip install pipenv
-          pipenv install --dev
+      - name: Install DynamoDB dependencies
+        if: ${{ env.GENE_NORM_DB_URL == 'http://localhost:8000' }}
+        run: python3 -m pip install ".[etl,test]"
+
+      - name: Install PG dependencies
+        if: ${{ env.GENE_NORM_DB_URL != 'http://localhost:8000' }}
+        run: python3 -m pip install ".[pg,etl,test]"
 
       - name: Build local DynamoDB
         if: ${{ env.GENE_NORM_DB_URL == 'http://localhost:8000' }}
         run: |
           chmod +x ./tests/unit/dynamodb_build.bash
           ./tests/unit/dynamodb_build.bash
 
-      - run: pipenv run flake8
-      - run: pipenv run pytest tests/
+      - name: Run tests
+        run: python3 -m pytest tests/
   docs:
     runs-on: ubuntu-latest
     steps:
@@ -52,4 +75,3 @@ jobs:
         with:
           pre-build-command: "python3 -m pip install .; python3 -m pip install sphinx_autodoc_typehints"
           docs-folder: "docs/"
-

README.md

@@ -8,10 +8,10 @@ Services and guidelines for normalizing gene terms
 The Normalizer is available via PyPI:
 
 ```commandline
-pip install gene-normalizer[dev]
+pip install gene-normalizer[etl,pg]
 ```
 
-The `[dev]` argument tells pip to install packages to fulfill the dependencies of the `gene.etl` package.
+The `[etl,pg]` argument tells pip to install packages to fulfill the dependencies of the `gene.etl` package and the PostgreSQL data storage implementation.
 
 ### External requirements
 
@@ -121,6 +121,16 @@ pipenv update
 pipenv install --dev
 ```
 
+Alternatively, install the `pg`, `etl`, `dev`, and `test` dependency groups in a virtual environment:
+
+```commandline
+git clone https://github.com/cancervariants/gene-normalization
+cd gene-normalization
+python3 -m virtualenv venv
+source venv/bin/activate
+pip install -e ".[pg,etl,dev,test]"
+```
+
 ### Init coding style tests
 
 Code style is managed by [flake8](https://github.com/PyCQA/flake8) and checked prior to commit.

docs/source/full_install.rst

@@ -16,10 +16,24 @@ Package installation
 
 First, install the Gene Normalizer from PyPI: ::
 
-    pip install gene-normalizer[dev]
+    pip install "gene-normalizer[etl]"
 
-The ``[dev]`` option installs dependencies necessary for using the ``gene.etl`` package, which performs data loading operations.
+The ``[etl]`` option installs dependencies necessary for using the ``gene.etl`` package, which performs data loading operations.
 
+Users intending to utilize PostgreSQL to store source data should also include the `pg` dependency group: ::
+
+    pip install "gene-normalizer[etl,pg]"
+
+.. _Dependency groups:
+
+.. note::
+
+    The Gene Normalizer defines four optional dependency groups in total:
+
+    * `etl` provides dependencies for regenerating data from sources. It's necessary for users who don't intend to rely on existing database dumps.
+    * `pg` provides dependencies for connecting to a PostgreSQL database. It's not necessary for users who are using a DynamoDB backend.
+    * `dev` provides development dependencies, such as static code analysis and docs generation tools. It's required for contributing to the Gene Normalizer, but otherwise unnecessary.
+    * `test` provides dependencies for running tests. As with `dev`, it's mostly relevant for contributors.
 
 SeqRepo
 -------

docs/source/quick_install.rst

@@ -13,9 +13,9 @@ Requirements
 Installation Steps
 ------------------
 
-Install the Gene Normalizer via PyPI: ::
+Install the Gene Normalizer via PyPI (see the :ref:`note on dependency groups <Dependency groups>` for more info): ::
 
-    pip install gene-normalizer
+    pip install "gene-normalizer[pg]"
 
 Create a new PostgreSQL database. For example, using the `psql createdb <https://www.postgresql.org/docs/current/app-createdb.html>`_ utility, and assuming that ``postgres`` is a valid user: ::
 

docs/source/search_capabilities.rst

@@ -38,8 +38,6 @@ Each search mode can be accessed directly within Python using the :ref:`query AP
     >>> normalized_response.gene_descriptor.label
     'ERBB2'
 
-
-
 Match types
 -----------
 

gene/cli.py

@@ -1,10 +1,9 @@
 """This module provides a CLI util to make updates to normalizer database."""
-from collections.abc import Collection
 import logging
 import os
 from pathlib import Path
 from timeit import default_timer as timer
-from typing import List, Optional, Set
+from typing import Collection, List, Optional, Set
 
 import click
 

setup.cfg

@@ -49,19 +49,25 @@ console_scripts =
     gene_norm_check_db = gene.cli:check_db
 
 [options.extras_require]
-dev =
+pg =
     psycopg[binary]
+
+etl =
     gffutils
     biocommons.seqrepo
+
+test =
     pytest
+    pytest-cov
+    mock
+
+dev =
     pre-commit
     flake8
     flake8-docstrings
-    pytest-cov
-    mock
     ipykernel
     sphinx == 6.1.3
     sphinx-autodoc-typehints == 1.22.0
 
 [tool:pytest]
-addopts = --ignore setup.py --ignore codebuild/ --ignore dynamodb_local_latest/ --doctest-modules --cov-report term-missing --cov .
+addopts = --ignore setup.py --ignore dynamodb_local_latest/ --ignore docs/ --doctest-modules --cov-report term-missing --cov=.