Initial implementation of NCHG cartesian-product #231

Workflow file for this run

.github/workflows/ubuntu-ci.yml at 4597bd9

	# Copyright (C) 2024 Roberto Rossini <[email protected]>
	#
	# SPDX-License-Identifier: GPL-3.0
	#
	# This library is free software: you can redistribute it and/or
	# modify it under the terms of the GNU Public License as published
	# by the Free Software Foundation; either version 3 of the License,
	# or (at your option) any later version.
	#
	# This library is distributed in the hope that it will be useful,
	# but WITHOUT ANY WARRANTY; without even the implied warranty of
	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
	# Library General Public License for more details.
	#
	# You should have received a copy of the GNU Public License along
	# with this library. If not, see
	# <https://www.gnu.org/licenses/>.

	name: Ubuntu CI

	on:
	push:
	branches: [main]
	paths:
	- ".github/workflows/build-conan-deps.yml"
	- ".github/workflows/cache-test-dataset.yml"
	- ".github/workflows/ubuntu-ci.yml"
	- "cmake/**"
	- "src/**"
	- "test/**"
	- "CMakeLists.txt"
	- "conanfile.py"

	pull_request:
	paths:
	- ".github/workflows/build-conan-deps.yml"
	- ".github/workflows/cache-test-dataset.yml"
	- ".github/workflows/ubuntu-ci.yml"
	- "cmake/**"
	- "src/**"
	- "test/**"
	- "CMakeLists.txt"
	- "conanfile.py"

	# https://stackoverflow.com/a/72408109
	concurrency:
	group: ${{ github.workflow }}-${{ github.event.pull_request.number \|\| github.ref }}
	cancel-in-progress: true

	defaults:
	run:
	shell: bash

	jobs:
	matrix-factory:
	name: Generate job matrix
	runs-on: ubuntu-latest
	outputs:
	matrix: ${{ steps.set-result.outputs.result }}
	ci-type: ${{ steps.ci-type.outputs.type }}
	steps:
	- name: Checkout repo
	uses: actions/checkout@v4
	with:
	fetch-depth: 0
	ref: ${{ github.event.after }}

	- name: Detect CI type
	id: ci-type
	run: \|
	if git log --format=%B -n 1 ${{ github.event.after }} \| grep -qF '[ci full]'; then
	echo "type=full" \| tee -a "$GITHUB_OUTPUT"
	else
	echo "type=short" \| tee -a "$GITHUB_OUTPUT"
	fi

	- name: Generate matrix
	uses: actions/github-script@v7
	id: set-result
	with:
	script: \|
	// Documentation
	// https://docs.github.com/en/actions/learn-github-actions/contexts#fromjson
	// https://github.com/actions/runner/issues/982#issuecomment-809360765

	var ci_short = "${{ steps.ci-type.outputs.type }}" === "short"

	var includes = []

	// Debug builds (short CI)
	includes.push({ compiler: 'gcc-13', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Debug', developer_mode: 'OFF' })
	includes.push({ compiler: 'gcc-14', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Debug', developer_mode: 'ON' })
	includes.push({ compiler: 'clang-17', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Debug', developer_mode: 'OFF' })
	includes.push({ compiler: 'clang-19', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Debug', developer_mode: 'ON' })

	// Release builds (short CI)
	includes.push({ compiler: 'gcc-14', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Release', developer_mode: 'ON' })
	includes.push({ compiler: 'clang-19', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Release', developer_mode: 'ON' })

	if (ci_short) {
	return { include: includes }
	}

	// Debug builds (long CI)
	includes.push({ compiler: 'clang-18', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Debug', developer_mode: 'OFF' })

	// Release builds (long CI)
	includes.push({ compiler: 'gcc-13', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Release', developer_mode: 'OFF' })
	includes.push({ compiler: 'clang-17', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Release', developer_mode: 'OFF' })
	includes.push({ compiler: 'clang-18', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.30.*', build_type: 'Release', developer_mode: 'OFF' })

	// Make sure project builds with CMake 3.25
	includes.push({ compiler: 'clang-19', os: 'ubuntu-24.04', generator: 'Ninja', cmake: '3.25.2', build_type: 'Release', developer_mode: 'OFF' })
	// Make sure project builds with make
	includes.push({ compiler: 'clang-19', os: 'ubuntu-24.04', generator: 'Unix Makefiles', cmake: '3.30.*', build_type: 'Release', developer_mode: 'OFF' })

	return { include: includes }

	cache-test-dataset:
	name: Cache test dataset
	uses: paulsengroup/nchg/.github/workflows/cache-test-dataset.yml@main

	build-conan-deps:
	name: Build Conan deps
	uses: paulsengroup/nchg/.github/workflows/build-conan-deps.yml@main
	with:
	os: ubuntu-24.04

	build-project:
	name: Build project
	needs:
	- matrix-factory
	- build-conan-deps
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix: ${{ fromJSON(needs.matrix-factory.outputs.matrix) }}

	container:
	image: ghcr.io/paulsengroup/ci-docker-images/${{ matrix.os }}-cxx-${{ matrix.compiler }}:latest
	options: "--user=root"

	env:
	CCACHE_DIR: "/opt/ccache-cache"
	CCACHE_COMPILERCHECK: "content"
	CCACHE_COMPRESSLEVEL: "1"
	CCACHE_MAXSIZE: "500M"
	CONAN_HOME: "/opt/conan/"

	steps:
	- uses: actions/checkout@v4

	- name: Fix permissions
	run: \|
	chown -R $(id -u):$(id -g) $PWD

	- name: Check build deps are up-to-date
	id: build-deps-outdated
	run: \|
	pattern='[[:digit:]]\+\.[[:digit:]]\+\.[[:digit:]]\+$'
	flag=false

	if [[ $(cmake --version \| grep -o "$pattern") != ${{ matrix.cmake }} ]]; then
	flag=true
	fi

	echo "outdated=$flag" \| tee -a "$GITHUB_OUTPUT"

	- name: Update build deps
	if: ${{ steps.build-deps-outdated.outputs.outdated }}
	run: \|
	apt-get update
	apt-get install -y --no-install-recommends python3-pip

	python3 -m pip install "cmake==${{ matrix.cmake }}"

	- name: Generate cache keys
	id: cache-key
	run: \|
	set -u

	os="${{ matrix.os }}"
	compiler="${{ matrix.compiler }}"
	generator="${{ matrix.generator }}"
	build_type="${{ matrix.build_type }}"
	dev_mode="${{ matrix.developer_mode }}"

	conanfile_hash="${{ hashFiles('conanfile.py') }}"

	# This can be used by to always update a cache entry (useful e.g. for ccache)
	current_date="$(date '+%s')"

	ccache_key_prefix="ccache-$os-$compiler-$conanfile_hash-$build_type-$generator-$dev_mode"

	echo "ccache-key=${ccache_key_prefix}-$GITHUB_REF-${current_date}" \| tee -a $GITHUB_OUTPUT
	echo "ccache-restore-key-1=$ccache_key_prefix-$GITHUB_REF" \| tee -a $GITHUB_OUTPUT
	echo "ccache-restore-key-2=$ccache_key_prefix" \| tee -a $GITHUB_OUTPUT

	- name: Restore Conan cache
	uses: actions/cache/restore@v4
	with:
	key: ${{ needs.build-conan-deps.outputs.conan-key }}
	path: ${{ env.CONAN_HOME }}/p
	fail-on-cache-miss: true

	- name: Restore CMake configs (Debug)
	if: matrix.build_type == 'Debug'
	uses: actions/cache/restore@v4
	with:
	key: ${{ needs.build-conan-deps.outputs.cmake-prefix-debug-key }}
	path: /tmp/cmake-prefix-dbg.tar
	fail-on-cache-miss: true

	- name: Restore CMake configs (Release)
	if: matrix.build_type == 'Release'
	uses: actions/cache/restore@v4
	with:
	key: ${{ needs.build-conan-deps.outputs.cmake-prefix-release-key }}
	path: /tmp/cmake-prefix-rel.tar
	fail-on-cache-miss: true

	- name: Extract CMake configs
	run: \|
	mkdir conan-env
	tar -xf /tmp/cmake-prefix-*.tar -C conan-env/ --strip-components=1

	- name: Restore Ccache folder
	id: cache-ccache
	uses: actions/cache/restore@v4
	with:
	key: ${{ steps.cache-key.outputs.ccache-restore-key-1 }}
	restore-keys: ${{ steps.cache-key.outputs.ccache-restore-key-2 }}
	path: ${{ env.CCACHE_DIR }}

	- name: Reset Ccache stats
	run: ccache --zero-stats

	- name: Configure project
	run: \|
	cmake -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
	-DCMAKE_PREFIX_PATH="$PWD/conan-env" \
	-DENABLE_DEVELOPER_MODE=${{ matrix.developer_mode }} \
	-DOPT_ENABLE_CLANG_TIDY=OFF \
	-DOPT_ENABLE_CPPCHECK=OFF \
	-DNCHG_ENABLE_TESTING=ON \
	-DNCHG_DOWNLOAD_TEST_DATASET=OFF \
	-DCMAKE_INSTALL_PREFIX=dest \
	-S . \
	-B build

	- name: Build project
	run: cmake --build build -j $(nproc)

	- name: Package binaries
	run: \|
	cmake --install build

	tar -cf - -C dest/ bin \| zstd -T0 -13 -o binaries.tar.zst

	- name: Package unit tests
	run: \|
	rm -r build/src
	tar --exclude='*.o' -cf - build/ \| zstd -T0 -13 -o unit-tests.tar.zst

	- name: Upload unit tests
	uses: actions/upload-artifact@v4
	with:
	name: "unit-tests-${{ matrix.os }}-\
	${{ matrix.compiler }}-\
	${{ matrix.generator }}-\
	${{ matrix.build_type }}-\
	${{ matrix.developer_mode }}"
	path: unit-tests.tar.zst
	if-no-files-found: error
	retention-days: 1

	- name: Upload binaries
	uses: actions/upload-artifact@v4
	with:
	name: "binaries-${{ matrix.os }}-\
	${{ matrix.compiler }}-\
	${{ matrix.generator }}-\
	${{ matrix.build_type }}-\
	${{ matrix.developer_mode }}"
	path: binaries.tar.zst
	if-no-files-found: error
	retention-days: 1

	- name: Print Ccache statistics (pre-cleanup)
	run: \|
	ccache --show-stats \
	--show-compression \
	--verbose

	- name: Cleanup Ccache folder
	if: needs.matrix-factory.outputs.ci-type == 'short'
	run: \|
	ccache --evict-older-than=14400s # 4h
	ccache --recompress=19 --recompress-threads="$(nproc)"
	ccache --cleanup

	- name: Print Ccache statistics (post-cleanup)
	if: needs.matrix-factory.outputs.ci-type == 'short'
	run: \|
	ccache --show-stats \
	--show-compression \
	--verbose

	- name: Save Ccache folder
	uses: actions/cache/save@v4
	with:
	key: ${{ steps.cache-key.outputs.ccache-key }}
	path: ${{ env.CCACHE_DIR }}
	env:
	ZSTD_CLEVEL: 1

	- name: Generate list of stale cache entries
	id: stale-cache
	if: steps.cache-ccache.outputs.cache-matched-key != ''
	run: \|
	fname='stale-cache-${{ matrix.os }}-${{ matrix.compiler }}-${{ matrix.generator }}-${{ matrix.build_type }}-${{ matrix.developer_mode }}.txt'
	echo '${{ steps.cache-ccache.outputs.cache-matched-key }}' > "$fname"

	echo "name=$fname" \| tee -a "$GITHUB_OUTPUT"

	- name: Upload stale cache entries
	if: steps.cache-ccache.outputs.cache-matched-key != ''
	uses: actions/upload-artifact@v4
	with:
	name: ${{ steps.stale-cache.outputs.name }}
	path: "${{ steps.stale-cache.outputs.name }}"
	if-no-files-found: error
	retention-days: 1

	clean-stale-cache:
	needs: [build-project]
	name: Evict stale cache entries
	runs-on: ubuntu-latest
	permissions:
	actions: write

	steps:
	- name: Download artifacts
	uses: actions/download-artifact@v4
	continue-on-error: true
	with:
	pattern: stale-cache-*
	merge-multiple: true

	- name: Evict cache entries
	continue-on-error: true
	run: \|
	set -x
	while read entry; do
	if ! grep -q '/heads/main' <(echo "$entry"); then
	gh cache delete --repo '${{ github.repository }}' "$entry"
	fi
	done < <(cat stale-cache*.txt \| grep -v '^$')
	env:
	GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

	run-unit-tests:
	name: Run unit tests
	needs: [matrix-factory, cache-test-dataset, build-project]
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix: ${{ fromJSON(needs.matrix-factory.outputs.matrix) }}

	container:
	image: ghcr.io/paulsengroup/ci-docker-images/${{ matrix.os }}-cxx-${{ matrix.compiler }}:latest
	options: "--user=root"

	steps:
	- name: Checkout repo
	uses: actions/checkout@v4

	- name: Restore test dataset
	uses: actions/cache/restore@v4
	with:
	key: ${{ needs.cache-test-dataset.outputs.cache-key }}
	path: test/data/nchg_test_data.tar.zst
	fail-on-cache-miss: true

	- name: Download unit tests artifact
	uses: actions/download-artifact@v4
	with:
	name: "unit-tests-${{ matrix.os }}-\
	${{ matrix.compiler }}-\
	${{ matrix.generator }}-\
	${{ matrix.build_type }}-\
	${{ matrix.developer_mode }}"

	- name: Extract binaries and test dataset
	run: \|
	tar -xf unit-tests.tar.zst
	tar -xf test/data/nchg_test_data.tar.zst

	- name: Add test user
	run: useradd devel

	- name: Fix permissions
	run: \|
	chown -R devel:devel build/

	- name: Setup dependencies
	run: \|
	apt-get update
	apt-get install -q -y --no-install-recommends \
	python3-pip \
	sudo

	python3 -m pip install "cmake==${{ matrix.cmake }}"

	- name: Run unit tests
	run: \|
	sudo -u devel -E env "PATH=$PATH" \
	ctest --test-dir build/ \
	--schedule-random \
	--output-on-failure \
	--no-tests=error \
	--timeout 240 \
	-j $(nproc) \|&
	head -n 1000

	run-integration-tests:
	name: Run integration tests
	needs: [matrix-factory, cache-test-dataset, build-project]
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix: ${{ fromJSON(needs.matrix-factory.outputs.matrix) }}

	container:
	image: ubuntu:24.04
	options: "--user=root"

	env:
	DEBIAN_FRONTEND: "noninteractive"
	TZ: "Etc/UTC"

	steps:
	- name: Install dependencies
	run: \|
	apt-get update
	apt-get install -q -y --no-install-recommends \
	curl \
	git \
	python3.12 \
	python3.12-venv \
	python3-pip \
	sudo \
	tar \
	zip \
	zstd

	if [ "${{ matrix.developer_mode }}" = ON ]; then
	apt-get install -q -y --no-install-recommends \
	libasan8 \
	libubsan1
	fi

	- name: Checkout repo
	uses: actions/checkout@v4

	- name: Restore test dataset
	uses: actions/cache/restore@v4
	with:
	key: ${{ needs.cache-test-dataset.outputs.cache-key }}
	path: test/data/nchg_test_data.tar.zst
	fail-on-cache-miss: true

	- name: Download binaries artifact
	uses: actions/download-artifact@v4
	with:
	name: "binaries-${{ matrix.os }}-\
	${{ matrix.compiler }}-\
	${{ matrix.generator }}-\
	${{ matrix.build_type }}-\
	${{ matrix.developer_mode }}"

	- name: Extract binaries and test dataset
	run: \|
	tar -xf binaries.tar.zst
	tar -xf test/data/nchg_test_data.tar.zst

	- name: Add test user
	run: useradd devel

	- name: Setup test dependencies
	run: \|
	python3.12 -m venv venv --upgrade
	echo "PATH=$PWD/venv/bin:$PATH" \| tee -a "$GITHUB_ENV"

	venv/bin/pip install -r test/requirements.txt

	- name: Setup test environment
	run: \|
	echo "DATA_DIR=$PWD/test/data/integration_tests" \| tee -a "$GITHUB_ENV"
	echo "OUT_PREFIX=ENCFF447ERX.1000000" \| tee -a "$GITHUB_ENV"

	- name: Test NCHG cartesian-product (gw)
	run: \|
	sudo -u devel \
	bin/NCHG cartesian-product \
	test/data/ENCFF447ERX.1000000.compartments.bed \
	> "$OUT_PREFIX.bedpe"

	test/scripts/validate_nchg_output.py cartesian-product \
	"$OUT_PREFIX.bedpe" \
	"$DATA_DIR/cartesian_product/$OUT_PREFIX.gw-domains.bedpe"

	rm "$OUT_PREFIX"*

	- name: Test NCHG cartesian-product (cis)
	run: \|
	sudo -u devel \
	bin/NCHG cartesian-product \
	--cis-only \
	test/data/ENCFF447ERX.1000000.compartments.bed \
	> domains.bedpe

	test/scripts/validate_nchg_output.py cartesian-product \
	domains.bedpe \
	"$DATA_DIR/cartesian_product/$OUT_PREFIX.cis-domains.bedpe"

	rm *.bedpe

	- name: Test NCHG cartesian-product (trans)
	run: \|
	sudo -u devel \
	bin/NCHG cartesian-product \
	--trans-only \
	test/data/ENCFF447ERX.1000000.compartments.bed \
	> domains.bedpe

	test/scripts/validate_nchg_output.py cartesian-product \
	domains.bedpe \
	"$DATA_DIR/cartesian_product/$OUT_PREFIX.trans-domains.bedpe"

	rm *.bedpe

	- name: Test NCHG cartesian-product (chr1:chr3)
	run: \|
	sudo -u devel \
	bin/NCHG cartesian-product \
	--chrom1 chr1 \
	--chrom2 chr3 \
	test/data/ENCFF447ERX.1000000.compartments.bed \
	> domains.bedpe

	grep -E '\bchr1\b.*\bchr3\b' \
	"$DATA_DIR/cartesian_product/$OUT_PREFIX.trans-domains.bedpe" \
	> expected.bedpe

	test/scripts/validate_nchg_output.py cartesian-product \
	domains.bedpe \
	expected.bedpe

	rm *.bedpe

	- name: Test NCHG compute (mt)
	run: \|
	sudo -u devel \
	bin/NCHG compute \
	test/data/ENCFF447ERX.1000000.cool \
	"$OUT_PREFIX" \
	--threads "$(nproc)"

	test/scripts/validate_nchg_output.py compute \
	"$OUT_PREFIX" \
	"$DATA_DIR/compute/$OUT_PREFIX"

	rm "$OUT_PREFIX"*

	- name: Test NCHG compute (st)
	run: \|
	sudo -u devel \
	bin/NCHG compute \
	test/data/ENCFF447ERX.1000000.cool \
	"$OUT_PREFIX" \
	--cis-only \
	--threads 1

	rm "$OUT_PREFIX"*

	- name: Test NCHG compute (mt; w/ domain list)
	run: \|
	sudo -u devel \
	bin/NCHG compute \
	test/data/ENCFF447ERX.1000000.cool \
	"$OUT_PREFIX" \
	--threads "$(nproc)" \
	--domains test/data/ENCFF447ERX.1000000.compartments.bed

	test/scripts/validate_nchg_output.py compute \
	"$OUT_PREFIX" \
	"$DATA_DIR/compute_with_domains/$OUT_PREFIX"

	rm "$OUT_PREFIX"*

	- name: Test NCHG merge
	run: \|
	sudo -u devel \
	bin/NCHG merge \
	"$DATA_DIR/compute/$OUT_PREFIX" \
	"$OUT_PREFIX.parquet" \
	--threads "$(nproc)"

	test/scripts/validate_nchg_output.py merge \
	"$OUT_PREFIX.parquet" \
	"$DATA_DIR/merge/$OUT_PREFIX.parquet"

	rm "$OUT_PREFIX"*

	- name: Test NCHG filter
	run: \|
	sudo -u devel \
	bin/NCHG filter \
	"$DATA_DIR/merge/$OUT_PREFIX.parquet" \
	"$OUT_PREFIX.filtered.parquet" \
	--threads "$(nproc)"

	test/scripts/validate_nchg_output.py filter \
	"$OUT_PREFIX.filtered.parquet" \
	"$DATA_DIR/filter/$OUT_PREFIX.parquet"

	rm "$OUT_PREFIX"*

	- name: Test NCHG view (compute)
	run: \|
	sudo -u devel \
	bin/NCHG view \
	"$DATA_DIR/merge/$OUT_PREFIX.parquet" > /dev/null

	- name: Test NCHG view (filter)
	run: \|
	sudo -u devel \
	bin/NCHG view \
	"$DATA_DIR/filter/$OUT_PREFIX.parquet" \
	> "$OUT_PREFIX.tsv"

	test/scripts/validate_nchg_output.py view \
	"$OUT_PREFIX.tsv" \
	"$DATA_DIR/view/$OUT_PREFIX.tsv"

	rm "$OUT_PREFIX"*

	- name: Test NCHG expected (w/ mask)
	run: \|
	printf 'chr1\t0\t248956422' > mask.bed

	sudo -u devel \
	bin/NCHG expected \
	test/data/ENCFF447ERX.1000000.cool \
	--output "$OUT_PREFIX.h5" \
	--bin-mask mask.bed

	rm "$OUT_PREFIX"* mask.bed

	- name: Test NCHG expected (wo/ mask)
	run: \|
	sudo -u devel \
	bin/NCHG expected \
	test/data/ENCFF447ERX.1000000.cool \
	--output "$OUT_PREFIX.h5"

	test/scripts/validate_nchg_output.py expected \
	"$OUT_PREFIX.h5" \
	"$DATA_DIR/expected/$OUT_PREFIX.h5"

	rm "$OUT_PREFIX"*

	ubuntu-ci-status-check:
	name: Status Check (Ubuntu CI)
	if: ${{ always() }}
	runs-on: ubuntu-latest
	needs:
	- build-project
	- run-unit-tests
	- run-integration-tests

	steps:
	- name: Collect job results
	if: \|
	needs.build-project.result != 'success' \|\|
	needs.run-unit-tests.result != 'success' \|\|
	needs.run-integration-tests.result != 'success'
	run: exit 1

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Initial implementation of NCHG cartesian-product #231

Workflow file

Initial implementation of NCHG cartesian-product #231

Jobs

Run details

Workflow file for this run