feat: Add ChEMBL and Mondo (#1)

.github/workflows/checks.yml

@@ -0,0 +1,33 @@
+name: Checks
+on: [push, pull_request]
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: black
+        uses: psf/black@stable
+
+      - name: ruff
+        uses: chartboost/ruff-action@v1
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11']
+    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 ".[test]"
+
+      - name: Run tests
+        env:
+          WAGSTAILS_TEST_ENV: true
+        run: python3 -m pytest tests/

.gitignore

@@ -158,3 +158,6 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Test temp directory
+tests/tmp/

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v1.4.0
+  hooks:
+  - id: check-added-large-files
+    args: ['--maxkb=1500']
+  - id: detect-private-key
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+- repo: https://github.com/psf/black
+  rev: 23.10.0
+  hooks:
+    - id: black
+      language_version: python3.11
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.1.0
+  hooks:
+    - id: ruff
+      args: [ --fix, --exit-non-zero-on-fix ]

README.md

@@ -1,2 +1,72 @@
-# WagsTools
-Data acquisition tools for Wagnerds
+# WagsTAILS
+
+*Technology-Assisted Information Loading and Structure (TAILS) for Wagnerds.*
+
+This tool provides data acquisition and access utilities for several projects developed by the Wagner Lab.
+
+## Installation
+
+Install from PyPI:
+
+```shell
+python3 -m pip install wags_tails
+```
+
+## Usage
+
+Data source classes provide a `get_latest()` method that acquires the most recent available data file and returns a pathlib.Path object with its location:
+
+```pycon
+>>> from wags_tails.mondo import MondoData
+>>> m = MondoData()
+>>> m.get_latest(force_refresh=True)
+Downloading mondo.owl: 100%|█████████████████| 171M/171M [00:28<00:00, 6.23MB/s]
+PosixPath('/Users/genomicmedlab/.local/share/wags_tails/mondo/mondo_v2023-09-12.owl'), 'v2023-09-12'
+```
+
+Initialize the source class with the `silent` parameter set to True to suppress console output:
+
+```pycon
+>>> from wags_tails.mondo import MondoData
+>>> m = MondoData(silent=True)
+>>> latest_file, version = m.get_latest(force_refresh=True)
+```
+
+## Configuration
+
+All data is stored within source-specific subdirectories of a designated WagsTails data directory. By default, this location is `~/.local/share/wags_tails/`, but it can be configured by passing a Path directly to a data class on initialization, via the `$WAGS_TAILS_DIR` environment variable, or via [XDG data environment variables](https://specifications.freedesktop.org/basedir-spec/basedir-spec-0.6.html).
+
+## Development
+
+Check out the repository:
+
+```shell
+git clone https://github.com/GenomicMedLab/wags-tails
+cd wags-tails
+```
+
+Create a developer environment, e.g. with `virtualenv`:
+
+```shell
+python3 -m virtualenv venv
+source venv/bin/activate
+```
+
+Install dev and test dependencies, including `pre-commit`:
+
+```shell
+python3 -m pip install -e '.[dev,test]'
+pre-commit install
+```
+
+Check style:
+
+```shell
+black . && ruff check --fix .
+```
+
+Run tests:
+
+```shell
+pytest
+```

pyproject.toml

@@ -0,0 +1,99 @@
+[project]
+name = "wags_tails"
+version = "0.1.0"
+authors = [
+    {name = "Kori Kuzma"},
+    {name = "James S Stevenson"},
+    {name = "Alex H Wagner"}
+]
+readme = "README.md"
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Framework :: Pydantic",
+    "Framework :: Pydantic :: 2",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+]
+requires-python = ">=3.8"
+description = "Data acquisition tools for Wagnerds"
+license = {file = "LICENSE"}
+dependencies = [
+    "requests",
+    "tqdm",
+]
+
+[project.optional-dependencies]
+test = ["pytest>=6.0", "pytest-cov", "requests-mock"]
+
+dev = ["pre-commit", "black", "ruff"]
+
+[project.urls]
+Homepage = "https://github.com/GenomicMedLab/wags-tails/"
+Changelog = "https://github.com/GenomicMedLab/wags-tails/releases"
+Source = "https://github.com/GenomicMedLab/wags-tails/"
+"Bug Tracker" = "https://github.com/GenomicMedLab/wags-tails/issues"
+
+[build-system]
+requires = ["setuptools", "setuptools-scm"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+addopts = "--cov=src --cov-report term-missing"
+testpaths = ["tests"]
+
+[tool.coverage.run]
+branch = true
+
+[tool.black]
+line-length = 88
+extend-exclude = "^/docs/source/conf.py"
+
+[tool.ruff]
+src = ["src"]
+# pycodestyle (E, W)
+# Pyflakes (F)
+# flake8-annotations (ANN)
+# flake8-quotes (Q)
+# pydocstyle (D)
+# pep8-naming (N)
+# isort (I)
+select = ["E", "W", "F", "ANN", "Q", "D", "N", "I"]
+
+fixable = ["I", "F401"]
+
+# D203 - one-blank-line-before-class
+# D205 - blank-line-after-summary
+# D213 - multi-line-summary-second-line
+# D400 - ends-in-period
+# D415 - ends-in-punctuation
+# ANN101 - missing-type-self
+# ANN003 - missing-type-kwargs
+# E501 - line-too-long
+ignore = ["D203", "D205", "D213", "D400", "D415", "ANN101", "ANN003", "E501"]
+
+[tool.ruff.flake8-quotes]
+docstring-quotes = "double"
+
+[tool.ruff.per-file-ignores]
+# ANN001 - missing-type-function-argument
+# ANN2 - missing-return-type
+# ANN201 - Missing type annotation
+# ANN102 - missing-type-cls
+# D103 - Missing docstring in public function
+# F821 - undefined-name
+# F401 - unused-import
+# I001 - Import block unsorted or unformatted
+# N805 - invalid-first-argument-name-for-method
+"tests/*" = ["ANN001", "ANN102", "ANN2"]
+"*__init__.py" = ["F401"]
+"docs/source/conf.py" = ["D100", "I001", "D103", "ANN201", "ANN001"]

src/wags_tails/__init__.py

@@ -0,0 +1,5 @@
+"""Data acquisition tools for Wagnerds."""
+from .chembl import ChemblData
+from .mondo import MondoData
+
+__all__ = ["MondoData", "ChemblData"]