enforce wheel size limits, README formatting in CI (#643)

Contributes to rapidsai/build-planning#110

Proposes adding 2 types of validation on wheels in CI, to ensure we continue to produce wheels that are suitable for PyPI.

* checks on wheel size (compressed),
  - *to be sure they're under PyPI limits*
  - *and to prompt discussion on PRs that significantly increase wheel sizes*
* checks on README formatting
  - *to ensure they'll render properly as the PyPI project homepages*
  - *e.g. like how https://github.com/scikit-learn/scikit-learn/blob/main/README.rst becomes https://pypi.org/project/scikit-learn/*

Authors:
  - James Lamb (https://github.com/jameslamb)

Approvers:
  - Bradley Dice (https://github.com/bdice)
  - Ajay Thorve (https://github.com/AjayThorve)

URL: #643

ci/build_wheel.sh

@@ -16,4 +16,6 @@ cd "${package_dir}"
 
 python -m pip wheel . -w dist -v --no-deps --disable-pip-version-check
 
+../ci/validate_wheel.sh dist
+
 RAPIDS_PY_WHEEL_NAME="${package_name}_${RAPIDS_PY_CUDA_SUFFIX}" RAPIDS_PY_WHEEL_PURE="1" rapids-upload-wheels-to-s3 dist

ci/validate_wheel.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+set -euo pipefail
+
+wheel_dir_relative_path=$1
+
+rapids-logger "validate packages with 'pydistcheck'"
+
+pydistcheck \
+    --inspect \
+    "$(echo ${wheel_dir_relative_path}/*.whl)"
+
+rapids-logger "validate packages with 'twine'"
+
+twine check \
+    --strict \
+    "$(echo ${wheel_dir_relative_path}/*.whl)"

python/pyproject.toml

@@ -69,6 +69,14 @@ license-files = ["LICENSE"]
 [tool.setuptools.dynamic]
 version = {file = "cuxfilter/VERSION"}
 
+[tool.pydistcheck]
+select = [
+    "distro-too-large-compressed",
+]
+
+# PyPI limit is 100 MiB, fail CI before we get too close to that
+max_allowed_size_compressed = '75M'
+
 [tool.pytest.ini_options]
 filterwarnings = [
     "error::FutureWarning",