feat: support hail independently

.github/workflows/tests.yaml

@@ -0,0 +1,56 @@
+name: Kit tests
+
+on:
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  get-changed-kits:
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Get changed files in root directories
+        uses: tj-actions/changed-files@v47.0.5
+        id: changed-files
+        with:
+          dir_names: "true"
+          dir_names_max_depth: 1
+          files: |
+            */**
+          files_ignore: |
+            .github/**
+          base_sha: ${{ github.event.pull_request.base.ref }}
+
+      - name: Set matrix
+        id: set-matrix
+        run: |
+          kits="${{ steps.changed-files.outputs.all_changed_files }}"
+          # Convert space-separated string to JSON array (single line)
+          MATRIX=$(echo $kits | jq -cR 'split(" ") | map(select(length > 0))')
+          echo "matrix=$MATRIX" >> $GITHUB_OUTPUT
+
+  test-kit:
+    name: Test ${{ matrix.module }}
+    needs: [get-changed-kits]
+    if: ${{ needs.get-changed-kits.outputs.matrix != '[]' }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        module: ${{ fromJson(needs.get-changed-kits.outputs.matrix) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Run kit test
+        run: |
+          cd ${{ matrix.module }} && make test

Readme.md

@@ -6,3 +6,4 @@ Genomics Kit integrates the utilities for bioinformatics analysis
 2. [spark-on-slurm](./spark-on-slurm/): Spark on SLURM cluster configuration, supported
 3. [GLnexus](https://github.com/dnanexus-rnd/GLnexus): The joint variant calling for cohort vcf for deepvariant gvcf
 4. [DPGT](https://github.com/BGI-flexlab/DPGT): DPGT is a distributed population genetics analysis tool which enabled joint calling on millions of WGS(whole genome sequencing) samples.
+5. [Hail](https://hail.is/): Powering genomic analysis, at every scale

common.mk

@@ -1,3 +1,4 @@
 .PHONY: test
+HOMEDIR:=$(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 ${HOME}/.pixi/bin/pixi:
 	curl -sSL https://pixi.sh/install.sh | sh

hail/.gitattributes

@@ -0,0 +1,2 @@
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true -diff

hail/.gitignore

@@ -0,0 +1,3 @@
+# pixi environments
+.pixi/*
+!.pixi/config.toml

hail/Makefile

@@ -0,0 +1,47 @@
+include ../common.mk
+SLURM_IMAGE:= nttg8100/river-slurm:1.1.0
+.PHONY: setup example clean install
+
+setup: ${HOME}/.pixi/bin/pixi
+	${HOME}/.pixi/bin/pixi install
+
+start-slurm:
+	docker run \
+		-v ${HOMEDIR}:/tmp/gkit \
+		-v ${HOME}/.pixi:/root/.pixi \
+		--name slurm-dev \
+		-p 8081:22 \
+		--rm \
+		--privileged \
+		-d ${SLURM_IMAGE} || echo "Docker Slurm is already configured"
+
+get-slurm:
+	@count=0; \
+	max=5; \
+	until [ $$count -ge $$max ]; do \
+		echo "Checking SLURM (attempt $$((count+1))/$$max)..." ; \
+		docker exec -w /home/river slurm-dev squeue && break; \
+		count=$$((count+1)); \
+		echo "SLURM not ready, retrying in 5 seconds..." ; \
+		sleep 5; \
+	done; \
+	if [ $$count -eq $$max ]; then \
+		echo "SLURM still not available after $$max attempts"; \
+		exit 1; \
+	fi
+
+install:
+	${HOME}/.pixi/bin/pixi run install-sparkhpc
+
+# inside user river is the standard user with 1001 mapping id, Github Actions does not have this user
+test: ${HOME}/.pixi/bin/pixi start-slurm get-slurm
+	docker exec \
+		-w /tmp/gkit/hail \
+		slurm-dev /root/.pixi/bin/pixi run sparkhpc-hail
+
+test-slurm-local:
+	${HOME}/.pixi/bin/pixi run sparkhpc-example
+
+clean:
+	rm -f sparkhpc/sparkcluster-*.log sparkhpc/job
+	rm -f ${HOME}/.sparkhpc*