.PHONY: up down clean migrate test lint data hpo demo-case published-case benchmark training-set train loader pipeline annotate images kind serverless-deploy serverless-destroy gcp-configure gcp-secrets

VCF ?= data/example.vcf.gz
MLFLOW_URI ?= http://localhost:5001
DB_CONTAINER ?= rarelens-db-1
BENCH_DIR ?= data
TAG ?= latest
# The loader container reaches docker-compose's Postgres through the host.
HOST_DB_URL ?= postgresql://rarelens:rarelens@host.docker.internal:5432/rarelens

up:
	docker compose up -d --build

down:
	docker compose down

clean:  ## also deletes the Postgres and MLflow volumes
	docker compose down -v

migrate:
	docker compose exec api alembic upgrade head

test:
	cd api && uv run --extra dev pytest -q
	cd ml && uv run --extra dev pytest -q
	cd pipeline && uv run --no-project --with-requirements requirements.txt --with pytest --with pgserver pytest -q tests
	cd web && npm test

lint:
	cd api && uv run --extra dev ruff check . && uv run --extra dev mypy app
	cd web && npm run check

data:  ## download the public demo slice: GIAB HG002 + ClinVar, chr22 (see docs/data.md)
	scripts/fetch-demo-data.sh

hpo:  ## load HPO annotations, propagated up the ontology and weighted by information content
	cd ml && uv run --extra db python ../scripts/load-hpo.py

demo-case:  ## build the simulated proband: GIAB background + one ClinVar pathogenic variant
	scripts/make-demo-case.sh

published-case:  ## build a case from a published patient: a GA4GH phenopacket + GIAB background
	scripts/make-published-case.py

training-set:  ## build a ClinVar training table, shaped like VEP --tab output
	scripts/make-training-set.sh

benchmark:  ## measure the phenotype ranking against every published case (see docs/data.md)
	docker exec $(DB_CONTAINER) psql -U rarelens -d rarelens -At -F',' \
	  -c "select gene_symbol, hpo_id from gene_phenotypes" \
	  | tr ',' '\t' > $(BENCH_DIR)/gene_phenotypes.tsv
	test -f $(BENCH_DIR)/all_phenopackets.zip || curl -sL -o $(BENCH_DIR)/all_phenopackets.zip \
	  "$$(curl -s https://api.github.com/repos/monarch-initiative/phenopacket-store/releases/latest \
	     | sed -n 's/.*"browser_download_url": "\(.*all_phenopackets.zip\)".*/\1/p')"
	cd ml && uv run --extra dev python -m rarelens_ml.benchmark \
	  --phenopackets ../$(BENCH_DIR)/all_phenopackets.zip \
	  --annotations ../$(BENCH_DIR)/gene_phenotypes.tsv

train: ## train the pathogenicity model and point the production alias at it (needs `make up`)
	cd ml && MLFLOW_TRACKING_URI=$(MLFLOW_URI) uv run --extra dev \
		python -m rarelens_ml.train --tsv ../data/clinvar-training.vep.tsv --register

loader:
	docker build -t rarelens/loader:dev -f pipeline/loader.Dockerfile pipeline

pipeline: loader  ## dry run: annotate $(VCF) without touching the database
	cd pipeline && nextflow run main.nf -profile docker --vcf ../$(VCF)

annotate: loader  ## make annotate JOB=<job id> [VCF=data/x.vcf.gz]
	@test -n "$(JOB)" || (echo "usage: make annotate JOB=<job id> [VCF=...]"; exit 1)
	cd pipeline && DATABASE_URL=$(HOST_DB_URL) nextflow run main.nf -profile docker \
		--vcf ../$(VCF) --job_id $(JOB)

images:
	docker build -t rarelens-api:dev api
	docker build -t rarelens-web:dev web

kind: images
	kind create cluster --name rarelens 2>/dev/null || true
	kind load docker-image rarelens-api:dev rarelens-web:dev --name rarelens
	kubectl apply -k infra/k8s/overlays/local
	kubectl -n rarelens rollout status deploy/postgres deploy/api deploy/web
	@echo "kubectl -n rarelens port-forward svc/web 8080:80  (UI)"
	@echo "kubectl -n rarelens port-forward svc/api 8000:80  (API, used by the UI)"

serverless-deploy:  ## deploy the Cloud Run track: make serverless-deploy PROJECT=<id> [TAG=<sha>]
	@test -n "$(PROJECT)" || (echo "usage: make serverless-deploy PROJECT=<gcp project id> [TAG=<image tag>]"; exit 1)
	@test -n "$$TF_VAR_database_url" || echo "note: TF_VAR_database_url is unset; add -var deploy_cloud_sql=true or export a Postgres URL"
	cd infra/terraform && terraform apply -var project=$(PROJECT) -var image_tag=$(TAG)

serverless-destroy:  ## tear it all down
	cd infra/terraform && terraform destroy -var project=$(PROJECT) -var deletion_protection=false

gcp-configure:  ## one-time: write your GCP project id into the gcp overlay and Argo manifests
	@test -n "$(PROJECT)" || (echo "usage: make gcp-configure PROJECT=<gcp project id>"; exit 1)
	grep -rl __GCP_PROJECT__ infra/k8s/overlays/gcp infra/argo-workflows \
		| xargs sed -i.bak "s/__GCP_PROJECT__/$(PROJECT)/g"
	find infra -name '*.bak' -delete

gcp-secrets:  ## after terraform apply: copy DB URLs from Secret Manager into k8s secrets
	@test -n "$(PROJECT)" || (echo "usage: make gcp-secrets PROJECT=<gcp project id>"; exit 1)
	kubectl -n rarelens create secret generic api-secrets --dry-run=client -o yaml \
		--from-literal=DATABASE_URL="$$(gcloud secrets versions access latest --project $(PROJECT) --secret rarelens-api-database-url)" \
		| kubectl apply -f -
	kubectl -n rarelens create secret generic pipeline-secrets --dry-run=client -o yaml \
		--from-literal=DATABASE_URL="$$(gcloud secrets versions access latest --project $(PROJECT) --secret DATABASE_URL)" \
		| kubectl apply -f -