who_need_help/scripts/quality.sh

458 lines
18 KiB
Bash
Executable File

#!/bin/sh
set -eu
ROOT=$(CDPATH='' cd -- "$(dirname -- "$0")/.." && pwd)
cd "$ROOT"
SHELLCHECK_IMAGE="koalaman/shellcheck-alpine:v0.11.0@sha256:9955be09ea7f0dbf7ae942ac1f2094355bb30d96fffba0ec09f5432207544002"
HADOLINT_IMAGE="hadolint/hadolint:v2.14.0-debian@sha256:158cd0184dcaa18bd8ec20b61f4c1cabdf8b32a592d062f57bdcb8e4c1d312e2"
ACTIONLINT_IMAGE="rhysd/actionlint:1.7.12@sha256:b1934ee5f1c509618f2508e6eb47ee0d3520686341fec936f3b79331f9315667"
TRIVY_IMAGE="aquasec/trivy:0.72.0@sha256:cffe3f5161a47a6823fbd23d985795b3ed72a4c806da4c4df16266c02accdd6f"
PROMETHEUS_IMAGE="quay.io/prometheus/prometheus:v3.13.1@sha256:3c42b892cf723fa54d2f262c37a0e1f80aa8c8ddb1da7b9b0df9455a35a7f893"
ALERTMANAGER_IMAGE="quay.io/prometheus/alertmanager:v0.33.1@sha256:9e082985f56f4c8c9f724e18f2288c6708f472e56a5286b8863d080434ea065d"
PYTHON_IMAGE="python:3.14.6-alpine3.23@sha256:b165067c5afc37fa5608a3c05609cc3d51aafd808a30fbfd822ee594fef55ad4"
run_id="$(date -u +%Y%m%d%H%M%S)-$$"
project="wnh_quality_$(printf '%s' "$run_id" | tr -d '-')"
quality_image="who-need-help:quality-$run_id"
assets_image="who-need-help:assets-audit-$run_id"
e2e_image="who-need-help:e2e-audit-$run_id"
release_image="who-need-help:security-$run_id"
backup_image="who-need-help:backup-audit-$run_id"
minio_image="who-need-help:minio-audit-$run_id"
mc_image="who-need-help:mc-audit-$run_id"
boundary_mock_image="who-need-help:boundary-mock-audit-$run_id"
socket_proxy_image="who-need-help:socket-proxy-audit-$run_id"
postgis_image="who-need-help:postgis-audit-$run_id"
socket_proxy_container="wnh-socket-proxy-audit-$run_id"
scan_dir=$(mktemp -d "${TMPDIR:-/tmp}/wnh-quality-scan.XXXXXX")
scan_list="${scan_dir}.files"
scan_tar="${scan_dir}.tar"
umask 077
QUALITY_POSTGRES_USER="wnh_quality_$(openssl rand -hex 6)"
QUALITY_POSTGRES_PASSWORD=$(openssl rand -base64 48 | tr -d '\n')
export QUALITY_POSTGRES_USER QUALITY_POSTGRES_PASSWORD
QUALITY_POSTGIS_IMAGE=$postgis_image
export QUALITY_POSTGIS_IMAGE
compose="docker compose -p $project -f $ROOT/compose.quality.yaml"
cleanup() {
$compose down --volumes --remove-orphans >/dev/null 2>&1 || true
docker rm --force "$socket_proxy_container" >/dev/null 2>&1 || true
docker image rm "$quality_image" "$assets_image" "$e2e_image" "$release_image" \
"$backup_image" "$minio_image" "$mc_image" \
"$boundary_mock_image" "$socket_proxy_image" "$postgis_image" \
>/dev/null 2>&1 || true
rm -rf "$scan_dir" "$scan_list" "$scan_tar"
}
trap cleanup EXIT HUP INT TERM
echo "Checking shell scripts with ShellCheck 0.11.0"
# Word splitting is intentional: find emits repository-controlled paths and
# ShellCheck expects each file as a separate argument.
# shellcheck disable=SC2046
docker run --rm \
--volume "$ROOT:/mnt:ro" \
--workdir /mnt \
--entrypoint shellcheck \
"$SHELLCHECK_IMAGE" \
$(find scripts -type f -name '*.sh' -print | sort)
echo "Checking Dockerfiles with Hadolint 2.14.0"
for dockerfile in Dockerfile Dockerfile.backup Dockerfile.minio \
Dockerfile.postgis Dockerfile.socket-proxy \
android/Dockerfile e2e/Dockerfile ops/external-boundaries/Dockerfile; do
docker run --rm --interactive "$HADOLINT_IMAGE" \
hadolint --failure-threshold warning - <"$dockerfile"
done
echo "Checking the GitHub Actions workflow with actionlint 1.7.12"
docker run --rm \
--volume "$ROOT:/repo:ro" \
--workdir /repo \
"$ACTIONLINT_IMAGE"
echo "Checking crash dumps are excluded from the Docker build context"
grep -Fx 'core' .dockerignore >/dev/null
grep -Fx 'core.*' .dockerignore >/dev/null
echo "Rendering every Docker Compose profile"
docker compose --env-file .env.example -f compose.yaml config --quiet
docker compose --env-file .env.example -f compose.yaml config --format json |
jq --exit-status '
. as $root
| [$root.services.migrate, $root.services.web, $root.services.worker]
| all(
.environment.ERL_ZFLAGS == "+Q 65536" and
.environment.CLUSTER_INTERFACE == "eth0" and
.read_only == true and
.cap_drop == ["ALL"] and
.security_opt == ["no-new-privileges:true"] and
(.tmpfs | index("/tmp") != null)
)
and $root.services.web.environment.POOL_SIZE == "4"
and $root.services.worker.environment.POOL_SIZE == "2"
and $root.services.migrate.environment.POOL_SIZE == "2"
and $root.services.worker.environment.OBAN_MAINTENANCE_CONCURRENCY == "2"
and $root.services.worker.environment.OBAN_PUSH_CONCURRENCY == "1"
and $root.services.web.deploy.replicas == 2
and $root.services.worker.deploy.replicas == 2
and ($root.services.proxy.networks | keys | sort) == ["docker-api", "edge", "ingress"]
and ($root.services.web.networks | keys | sort) == ["egress", "ingress", "internal"]
and ($root.services.worker.networks | keys | sort) == ["egress", "internal"]
and $root.services.web.networks.internal.interface_name == "eth0"
and $root.services.web.networks.internal.aliases == ["cluster-web"]
and $root.services.web.networks.ingress.interface_name == "eth1"
and $root.services.web.networks.egress.interface_name == "eth2"
and $root.services.web.networks.egress.gw_priority == 1
and $root.services.worker.networks.internal.interface_name == "eth0"
and $root.services.worker.networks.egress.interface_name == "eth1"
and $root.services.worker.networks.egress.gw_priority == 1
and ($root.services.db.networks | keys) == ["internal"]
and $root.networks.ingress.internal == true
and $root.networks.internal.internal == true
and ($root.networks.egress.internal // false) == false
and $root.services.db.security_opt == ["no-new-privileges:true"]
and $root.services.mailpit.ports[0].host_ip == "127.0.0.1"
' >/dev/null
WEB_REPLICAS=1 WORKER_REPLICAS=1 \
docker compose --env-file .env.example -f compose.yaml config --format json |
jq --exit-status '
.services.web.deploy.replicas == 1 and
.services.worker.deploy.replicas == 1
' >/dev/null
CPU_REPLAY_WEB_CPUS=1 \
CPU_REPLAY_WORKER_CPUS=1 \
CPU_REPLAY_WEB_SCHEDULERS=1 \
CPU_REPLAY_WORKER_SCHEDULERS=1 \
docker compose --env-file .env.example \
-f compose.yaml -f compose.cpu-replay.yaml config --quiet
PORTABILITY_IMAGE=who-need-help:portability-render \
docker compose --env-file .env.example \
-f compose.yaml -f compose.portability.yaml config --quiet
mkdir -p "$scan_dir/e2e-output"
E2E_OUTPUT_DIR="$scan_dir/e2e-output" docker compose --env-file .env.e2e.example \
-f compose.yaml -f compose.e2e.yaml config --quiet
REHEARSAL_IMAGE=who-need-help:rehearsal-render \
docker compose --env-file .env.e2e.example \
-f compose.yaml -f compose.upgrade-rehearsal.yaml config --quiet
docker compose --env-file .env.load.example \
-f compose.yaml -f compose.load.yaml config --quiet
test "$(
docker compose --env-file .env.load.example \
-f compose.yaml -f compose.load.yaml config --format json |
jq -r '.services.db.command | join(" ")'
)" = "postgres -c shared_preload_libraries=pg_stat_statements -c compute_query_id=on"
mkdir -p "$scan_dir/observability-runtime/prometheus" \
"$scan_dir/observability-runtime/grafana"
OBSERVABILITY_RUNTIME_DIR="$scan_dir/observability-runtime" \
docker compose --env-file .env.load.example \
-f compose.yaml -f compose.load.yaml -f compose.observability.yaml \
--profile observability config --quiet
mkdir -p "$scan_dir/backup-runtime"
BACKUP_RUNTIME_DIR="$scan_dir/backup-runtime" \
BACKUP_HOST_UID="$(id -u)" \
BACKUP_HOST_GID="$(id -g)" \
docker compose --env-file .env.load.example \
-f compose.yaml -f compose.load.yaml -f compose.backup.yaml \
--profile backup config --quiet
docker compose -p "$project" -f compose.quality.yaml config --quiet
mkdir -p "$scan_dir/external-boundary-output"
EXTERNAL_BOUNDARY_APP_IMAGE=who-need-help:boundary-render \
EXTERNAL_BOUNDARY_MOCK_IMAGE=who-need-help:boundary-mock-render \
EXTERNAL_BOUNDARY_OUTPUT_DIR="$scan_dir/external-boundary-output" \
EXTERNAL_BOUNDARY_HOST_UID="$(id -u)" \
EXTERNAL_BOUNDARY_HOST_GID="$(id -g)" \
EXTERNAL_OAUTH_CLIENT_ID=render-client \
EXTERNAL_OAUTH_CLIENT_SECRET=render-secret \
EXTERNAL_PUSH_BEARER_TOKEN=render-push-token \
EXTERNAL_POSTGRES_PASSWORD=render-database-secret \
EXTERNAL_DATABASE_URL=ecto://boundary:render-database-secret@boundary-db/boundary \
EXTERNAL_SECRET_KEY_BASE=render-secret-key-base \
EXTERNAL_HANDOVER_SECRET=render-handover-secret \
docker compose -f compose.external-boundaries.yaml config --quiet
echo "Validating local observability configuration"
sed \
-e 's/__SCRAPE_INTERVAL__/1s/g' \
-e 's/__EVALUATION_INTERVAL__/1s/g' \
ops/observability/prometheus.template.yml \
>"$scan_dir/observability-runtime/prometheus/prometheus.yml"
printf '%s' 'isolated-quality-metrics-token' \
>"$scan_dir/observability-runtime/prometheus/metrics-token"
printf '%s\n' '[]' \
>"$scan_dir/observability-runtime/prometheus/web-targets.json"
printf '%s\n' '[]' \
>"$scan_dir/observability-runtime/prometheus/worker-targets.json"
docker run --rm \
--user 0:0 \
--volume "$scan_dir/observability-runtime/prometheus:/runtime:ro" \
--volume "$ROOT/ops/observability/rules.yml:/etc/prometheus/rules.yml:ro" \
--entrypoint /bin/promtool \
"$PROMETHEUS_IMAGE" check config /runtime/prometheus.yml
docker run --rm \
--user 0:0 \
--volume "$ROOT/ops/observability/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro" \
--entrypoint /bin/amtool \
"$ALERTMANAGER_IMAGE" check-config /etc/alertmanager/alertmanager.yml
docker run --rm \
--volume "$ROOT/scripts/alert-receiver.py:/src/alert-receiver.py:ro" \
"$PYTHON_IMAGE" python -c \
'import py_compile; py_compile.compile("/src/alert-receiver.py", cfile="/tmp/alert-receiver.pyc", doraise=True)'
docker run --rm \
--volume "$ROOT/ops/external-boundaries/mock_server.py:/src/mock_server.py:ro" \
"$PYTHON_IMAGE" python -c \
'import py_compile; py_compile.compile("/src/mock_server.py", cfile="/tmp/mock_server.pyc", doraise=True)'
jq --exit-status \
'type == "object" and .uid == "wnh-overview" and (.panels | length) == 10' \
ops/observability/grafana/dashboards/who-need-help-overview.json \
>/dev/null
echo "Linting the Helm chart"
"$ROOT/scripts/bootstrap-kubernetes-tools.sh" >/dev/null
"$ROOT/.tools/bin/helm" lint \
--values "$ROOT/deploy/helm/who-need-help/values-kind.yaml" \
"$ROOT/deploy/helm/who-need-help"
echo "Scanning only tracked and non-ignored source files"
# The single-quoted program must expand $path inside the child shell.
# shellcheck disable=SC2016
git ls-files --cached --others --exclude-standard -z |
xargs -0 -r sh -c '
for path do
if [ -f "$path" ]; then
printf "%s\0" "$path"
fi
done
' sh >"$scan_list"
tar --null --no-recursion --files-from="$scan_list" --create --file="$scan_tar"
tar --extract --file="$scan_tar" --directory "$scan_dir"
"$ROOT/.tools/bin/helm" template who-need-help \
--values "$ROOT/deploy/helm/who-need-help/values-kind.yaml" \
"$ROOT/deploy/helm/who-need-help" \
>"$scan_dir/rendered-helm.yaml"
test "$(
grep -c 'name: ERL_ZFLAGS' "$scan_dir/rendered-helm.yaml"
)" -eq 5
test "$(
grep -c 'value: "+Q 65536"' "$scan_dir/rendered-helm.yaml"
)" -eq 5
test "$(
grep -c '^kind: NetworkPolicy$' "$scan_dir/rendered-helm.yaml"
)" -eq 1
mkdir -p "$ROOT/.tools/trivy-cache"
docker run --rm \
--volume "$scan_dir:/scan:ro" \
--volume "$ROOT/.tools/trivy-cache:/root/.cache/trivy" \
"$TRIVY_IMAGE" fs \
--scanners misconfig,secret \
--severity HIGH,CRITICAL \
--exit-code 1 \
/scan
echo "Building, smoke-testing, and scanning pinned runtime infrastructure images"
docker build --tag "$socket_proxy_image" --file Dockerfile.socket-proxy .
docker build --tag "$postgis_image" --file Dockerfile.postgis .
test "$(docker image inspect --format '{{.Config.User}}' "$socket_proxy_image")" = "haproxy"
test "$(docker image inspect --format '{{.Config.User}}' "$postgis_image")" = "postgres"
docker run --rm --entrypoint sh "$postgis_image" -euc '
test ! -e /usr/local/bin/gosu
test "$(id -u)" = 70
'
docker run --detach \
--name "$socket_proxy_container" \
--read-only \
--tmpfs /run:uid=99,gid=99,mode=0755 \
--tmpfs /tmp \
--cap-drop ALL \
--group-add "$(stat -c '%g' /var/run/docker.sock)" \
--security-opt no-new-privileges \
--env CONTAINERS=1 \
--env EVENTS=1 \
--env INFO=1 \
--env NETWORKS=1 \
--env PING=1 \
--env POST=0 \
--env VERSION=1 \
--volume /var/run/docker.sock:/var/run/docker.sock:ro \
--publish 127.0.0.1::2375 \
"$socket_proxy_image" >/dev/null
socket_proxy_port=$(
docker port "$socket_proxy_container" 2375/tcp |
sed -n 's/.*://p' |
head -n 1
)
test -n "$socket_proxy_port"
socket_proxy_ready=false
for _attempt in $(seq 1 30); do
if curl --fail --silent --show-error \
"http://127.0.0.1:$socket_proxy_port/_ping" >/dev/null; then
socket_proxy_ready=true
break
fi
sleep 1
done
test "$socket_proxy_ready" = true
test "$(
curl --silent --output /dev/null --write-out '%{http_code}' \
"http://127.0.0.1:$socket_proxy_port/containers/json"
)" = "200"
test "$(
curl --silent --output /dev/null --write-out '%{http_code}' \
--request POST \
"http://127.0.0.1:$socket_proxy_port/containers/create"
)" = "403"
docker rm --force "$socket_proxy_container" >/dev/null
for image in \
"$socket_proxy_image" \
"$postgis_image" \
"traefik:v3.7.8@sha256:4299bbed850421258fc5448c2e0e6ad350981d4d335a68de11b92448aedbefe5" \
"axllent/mailpit:v1.30.4@sha256:5a49a77c5bdbe7c5474450b4f46348d09949df3695257729c93a30369382d4f6"; do
docker run --rm \
--volume /var/run/docker.sock:/var/run/docker.sock \
--volume "$ROOT/.tools/trivy-cache:/root/.cache/trivy" \
"$TRIVY_IMAGE" image \
--scanners vuln \
--severity HIGH,CRITICAL \
--ignore-unfixed \
--exit-code 1 \
"$image"
done
echo "Building the pinned quality image and cached Dialyzer PLTs"
docker build --target quality --tag "$quality_image" .
echo "Running Elixir format, compiler, xref, Credo, Sobelow, Dialyzer, and Hex audit"
docker run --rm "$quality_image" sh -euc '
mix format --check-formatted
mix compile --force --warnings-as-errors
mix xref graph --label compile-connected --fail-above 0
mix credo --strict --min-priority high
mix sobelow --exit --strict --private --skip
mix dialyzer
mix hex.audit
'
echo "Starting an isolated PostgreSQL/PostGIS volume for the Phoenix suite"
$compose up --detach --wait db
docker run --rm \
--network "${project}_internal" \
--env MIX_ENV=test \
--env DB_HOST=db \
--env "DB_USER=$QUALITY_POSTGRES_USER" \
--env "DB_PASSWORD=$QUALITY_POSTGRES_PASSWORD" \
--env TEST_POOL_SIZE=10 \
"$quality_image" \
mix test
echo "Auditing locked browser dependencies"
docker build --target node_deps --tag "$assets_image" .
docker run --rm "$assets_image" npm audit --audit-level=high
docker build --tag "$e2e_image" e2e
docker run --rm "$e2e_image" npm audit --audit-level=high
echo "Building and scanning the pinned non-root backup tool image"
docker build --tag "$backup_image" --file Dockerfile.backup .
test "$(docker image inspect --format '{{.Config.User}}' "$backup_image")" = \
"10001:10001"
backup_versions=$(docker run --rm \
--user 10001:10001 \
--read-only \
--tmpfs /tmp \
"$backup_image" \
sh -euc 'restic version; pg_dump --version; test "$(id -u)" = 10001')
printf '%s\n' "$backup_versions"
printf '%s\n' "$backup_versions" |
grep -F 'restic 0.19.1 compiled with go1.26.5' >/dev/null
printf '%s\n' "$backup_versions" |
grep -F 'pg_dump (PostgreSQL) 18.4' >/dev/null
docker run --rm \
--volume /var/run/docker.sock:/var/run/docker.sock \
--volume "$ROOT/.tools/trivy-cache:/root/.cache/trivy" \
"$TRIVY_IMAGE" image \
--scanners vuln \
--severity HIGH,CRITICAL \
--ignore-unfixed \
--exit-code 1 \
"$backup_image"
echo "Building and scanning the pinned non-root MinIO server and client images"
docker build --target server --tag "$minio_image" --file Dockerfile.minio .
docker build --target client --tag "$mc_image" --file Dockerfile.minio .
test "$(docker image inspect --format '{{.Config.User}}' "$minio_image")" = \
"10001:10001"
test "$(docker image inspect --format '{{.Config.User}}' "$mc_image")" = \
"10001:10001"
minio_version=$(docker run --rm \
--user 10001:10001 \
--read-only \
--tmpfs /tmp \
"$minio_image" \
--version)
mc_version=$(docker run --rm \
--user 10001:10001 \
--read-only \
--tmpfs /tmp \
"$mc_image" \
--version)
printf '%s\n' "$minio_version"
printf '%s\n' "$mc_version"
printf '%s\n' "$minio_version" |
grep -F 'RELEASE.2025-10-15T17-29-55Z' >/dev/null
printf '%s\n' "$minio_version" |
grep -F 'commit-id=9e49d5e7a648f00e26f2246f4dc28e6b07f8c84a' >/dev/null
printf '%s\n' "$minio_version" |
grep -F 'Runtime: go1.26.5 linux/' >/dev/null
printf '%s\n' "$mc_version" |
grep -F 'RELEASE.2025-08-13T08-35-41Z' >/dev/null
printf '%s\n' "$mc_version" |
grep -F 'commit-id=7394ce0dd2a80935aded936b09fa12cbb3cb8096' >/dev/null
printf '%s\n' "$mc_version" |
grep -F 'Runtime: go1.26.5 linux/' >/dev/null
for image in "$minio_image" "$mc_image"; do
docker run --rm \
--volume /var/run/docker.sock:/var/run/docker.sock \
--volume "$ROOT/.tools/trivy-cache:/root/.cache/trivy" \
"$TRIVY_IMAGE" image \
--scanners vuln \
--severity HIGH,CRITICAL \
--ignore-unfixed \
--exit-code 1 \
"$image"
done
echo "Building and scanning the pinned non-root external-boundary mock image"
docker build \
--tag "$boundary_mock_image" \
--file ops/external-boundaries/Dockerfile \
ops/external-boundaries
test "$(docker image inspect --format '{{.Config.User}}' "$boundary_mock_image")" = \
"10001:10001"
docker run --rm \
--volume /var/run/docker.sock:/var/run/docker.sock \
--volume "$ROOT/.tools/trivy-cache:/root/.cache/trivy" \
"$TRIVY_IMAGE" image \
--scanners vuln \
--severity HIGH,CRITICAL \
--ignore-unfixed \
--exit-code 1 \
"$boundary_mock_image"
echo "Building and scanning the production release image"
docker build --target release --tag "$release_image" .
docker run --rm \
--volume /var/run/docker.sock:/var/run/docker.sock \
--volume "$ROOT/.tools/trivy-cache:/root/.cache/trivy" \
"$TRIVY_IMAGE" image \
--scanners vuln \
--severity HIGH,CRITICAL \
--ignore-unfixed \
--exit-code 1 \
"$release_image"
echo "All isolated quality and security gates passed."