Gradually introduce type checking (#50)

* set up type checking pre-commit

* set up type checks for pgscatalog.core

* add mypy action

* don't use poetry for mypy

* fix is_complex check

* delete redundant functions

Author: nebfield

.github/workflows/pytest.yaml

@@ -1,4 +1,4 @@
-name: Run pytest
+name: Run pytest and mypy
 
 on:
   workflow_call:
@@ -62,3 +62,20 @@ jobs:
             fail_ci_if_error: true
             slug: PGScatalog/pygscatalog
             flags: ${{ inputs.package-directory }}
+            
+  mypy:
+      runs-on: ubuntu-latest
+
+      steps:
+        - uses: actions/checkout@v4
+
+        - name: Install Python
+          uses: actions/setup-python@v5
+          with:
+            python-version: ${{ inputs.python-version }}
+            cache: 'pip'
+
+        - run: pip install mypy
+
+        - run: mypy # import to run in top level directory
+

.pre-commit-config.yaml

@@ -5,3 +5,8 @@ repos:
     - id: ruff
       args: [ --fix ]
     - id: ruff-format
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: 'v1.11.2'  # Use the sha / tag you want to point at
+  hooks:
+    - id: mypy
+      args: [--config-file, mypy.ini]

mypy.ini

@@ -0,0 +1,10 @@
+[mypy]
+files = pgscatalog.core/**/*.py
+exclude = [pgscatalog.calc, pgscatalog.match]
+
+warn_unused_configs = True
+ignore_missing_imports = true
+follow_imports = silent
+disallow_untyped_calls = false
+disallow_incomplete_defs = true
+

pgscatalog.core/mypy.ini

@@ -0,0 +1 @@
+../mypy.ini

pgscatalog.core/poetry.lock

@@ -28,6 +28,7 @@ pydantic = "^2.9.0"
 pytest = "^7.4.4"
 sphinx-autoapi = "^3.0.0"
 pytest-cov = "^4.1.0"
+mypy = "^1.11.2"
 
 [build-system]
 requires = ["poetry-core"]
@@ -39,4 +40,4 @@ addopts = "-ra -q --doctest-modules"
 filterwarnings = ["error"]
 
 [tool.coverage.run]
-source = ['src/pgscatalog/core']
+source = ['src/pgscatalog/core']

pgscatalog.core/pyproject.toml

@@ -1,4 +1,5 @@
-""" Public interface to the Polygenic Score Catalog core package """
+"""Public interface to the Polygenic Score Catalog core package"""
+
 import logging
 import importlib.metadata
 

pgscatalog.core/src/pgscatalog/core/__init__.py

@@ -2,6 +2,7 @@
 These functions aren't really meant to be imported outside corelib"""
 
 import logging
+from typing import Generator, Iterator
 
 from xopen import xopen
 
@@ -11,8 +12,13 @@
 
 
 def read_rows_lazy(
-    *, csv_reader, fields: list[str], name: str, wide: bool, row_nr: int
-):
+    *,
+    csv_reader: Iterator[list[str]],
+    fields: list[str],
+    name: str,
+    wide: bool,
+    row_nr: int,
+) -> Generator[ScoreVariant, None, None]:
     """Read rows from an open scoring file and instantiate them as ScoreVariants"""
     for row in csv_reader:
         variant = dict(zip(fields, row))

pgscatalog.core/src/pgscatalog/core/lib/_read.py

@@ -1,7 +1,8 @@
-""" This module assumes you're working with paths that follow the format:
+"""This module assumes you're working with paths that follow the format:
 
 {sampleset}_{chrom}_{effect_type}_{n}
 """
+
 from natsort import natsort_keygen, ns