Ekklesia/scripts/test-migrations-integration.sh

#!/usr/bin/env bash

set -Eeuo pipefail

repository_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$repository_root"

# shellcheck source=scripts/lib/compose-job-network.sh
source "$repository_root/scripts/lib/compose-job-network.sh"
# shellcheck source=scripts/lib/compose-diagnostics.sh
source "$repository_root/scripts/lib/compose-diagnostics.sh"
# shellcheck source=scripts/lib/ci-project.sh
source "$repository_root/scripts/lib/ci-project.sh"

command -v docker >/dev/null || {
  echo "Docker is required for the PostgreSQL migration integration suite." >&2
  exit 1
}
command -v pnpm >/dev/null || {
  echo "pnpm is required for the PostgreSQL migration integration suite." >&2
  exit 1
}
if ! docker compose version >/dev/null 2>&1; then
  echo "Docker Compose is required for the PostgreSQL migration integration suite." >&2
  exit 1
fi
if ! compose_job_network_initialize; then
  echo "The current Docker job container could not be identified." >&2
  exit 1
fi

# Unique per invocation, and findable by run and job if this script is killed before its trap runs
# (scripts/lib/ci-project.sh, scripts/ci-sweep.sh).
project="$(ci_project_name migration)"

export POSTGRES_DB="ekklesia_migration_test"
export POSTGRES_USER="ekklesia_migration_test"
export POSTGRES_PASSWORD="temporary-$project-${RANDOM}-${RANDOM}"
# Both host ports are ephemeral: concurrent runs on one Docker daemon must never contend for a
# fixed one. `.env.example` pins the storage port for local development, so it is overridden here
# exactly like the database's. The bound ports are discovered below.
export POSTGRES_PORT="0"
export S3_PORT="0"

compose=(
  docker compose
  --project-name "$project"
  --env-file .env.example
  --file infrastructure/compose.yaml
)

cleanup() {
  local exit_status=$?
  trap - EXIT INT TERM

  if ! compose_job_network_disconnect; then
    echo "PostgreSQL migration test network cleanup failed." >&2
    if ((exit_status == 0)); then
      exit_status=1
    fi
  fi
  if ! "${compose[@]}" down --volumes --remove-orphans --timeout 10 >/dev/null 2>&1; then
    echo "PostgreSQL migration test infrastructure cleanup failed." >&2
    if ((exit_status == 0)); then
      exit_status=1
    fi
  fi
  exit "$exit_status"
}
trap cleanup EXIT
trap 'exit 130' INT
trap 'exit 143' TERM

if ! "${compose[@]}" config --quiet >/dev/null 2>&1; then
  echo "PostgreSQL migration test infrastructure configuration is invalid." >&2
  exit 1
fi
# PostgreSQL and the S3-compatible object-storage service are both brought up from the repository's
# own pinned Compose file, so the live suites exercise exactly the services a developer runs locally
# and CI already knows how to provision. SeaweedFS is the intended deployment target (ADR 0004), and
# proving the storage contract against a mock instead would have hidden the provider quirks this
# suite exists to catch.
# Masked in any diagnostics below, along with anything else that looks like a credential.
COMPOSE_DIAGNOSTICS_SECRETS=(
  "$POSTGRES_PASSWORD"
  "$(grep -E '^S3_ACCESS_KEY=' .env.example | cut -d= -f2-)"
  "$(grep -E '^S3_SECRET_KEY=' .env.example | cut -d= -f2-)"
)
if ! up_output="$(
  "${compose[@]}" up --detach --wait --wait-timeout 180 postgres object-storage 2>&1
)"; then
  echo "Disposable PostgreSQL and object storage did not become ready." >&2
  compose_report_not_ready "$up_output" "${compose[@]}"
  exit 1
fi

if [[ "$COMPOSE_JOB_NETWORK_RUNNING_IN_CONTAINER" == "true" ]]; then
  if ! compose_job_network_connect postgres "${compose[@]}"; then
    echo "The migration test job could not join the isolated PostgreSQL network." >&2
    exit 1
  fi
  if ! compose_job_network_connect object-storage "${compose[@]}"; then
    echo "The migration test job could not join the isolated object-storage network." >&2
    exit 1
  fi
  database_host="postgres"
  database_port="5432"
  storage_endpoint="http://object-storage:8333"
else
  if ! postgres_binding="$("${compose[@]}" port postgres 5432 2>/dev/null)"; then
    echo "The disposable PostgreSQL loopback port could not be determined." >&2
    exit 1
  fi
  if [[ ! "$postgres_binding" =~ ^127\.0\.0\.1:([0-9]+)$ ]]; then
    echo "The disposable PostgreSQL port is not bound safely to loopback." >&2
    exit 1
  fi
  database_host="127.0.0.1"
  database_port="${BASH_REMATCH[1]}"
  if ((database_port < 1 || database_port > 65535)); then
    echo "The disposable PostgreSQL loopback port is invalid." >&2
    exit 1
  fi

  if ! storage_binding="$("${compose[@]}" port object-storage 8333 2>/dev/null)"; then
    echo "The disposable object-storage loopback port could not be determined." >&2
    exit 1
  fi
  if [[ ! "$storage_binding" =~ ^127\.0\.0\.1:([0-9]+)$ ]]; then
    echo "The disposable object-storage port is not bound safely to loopback." >&2
    exit 1
  fi
  storage_port="${BASH_REMATCH[1]}"
  if ((storage_port < 1 || storage_port > 65535)); then
    echo "The disposable object-storage loopback port is invalid." >&2
    exit 1
  fi
  storage_endpoint="http://127.0.0.1:$storage_port"
fi

# The TLS suite provisions its own disposable PostgreSQL rather than a Compose service, so it
# cannot call `compose_job_network_connect`. It receives the same topology decision this script
# already made, instead of detecting the topology a second time.
# The storage credentials come from `.env.example`, the same file `--env-file` already hands the
# Compose services, so the suite signs requests with exactly what the service was started with.
EKKLESIA_TEST_JOB_CONTAINER="$(compose_job_network_job_container)" \
EKKLESIA_MIGRATION_TEST_DATABASE_URL="postgresql://$POSTGRES_USER:$POSTGRES_PASSWORD@$database_host:$database_port/$POSTGRES_DB" \
EKKLESIA_TEST_STORAGE_ENDPOINT="$storage_endpoint" \
EKKLESIA_TEST_STORAGE_ACCESS_KEY="$(grep -E '^S3_ACCESS_KEY=' .env.example | cut -d= -f2-)" \
EKKLESIA_TEST_STORAGE_SECRET_KEY="$(grep -E '^S3_SECRET_KEY=' .env.example | cut -d= -f2-)" \
  pnpm exec vitest run --config vitest.migrations.integration.config.ts