#!/usr/bin/env bash
# Copy the analysed demo cases and the HPO reference data into a remote database.
#
# The deployed demo has no Nextflow and no Docker daemon, so it cannot run VEP. Instead the cases
# are annotated here, where the pipeline works, and the results are copied up. Visitors get real
# analysed cases -- funnel, ranking, evidence, decisions, report -- against a database that is
# never asked to produce them.
#
# Everything copied is derived from public, openly licensed sources (docs/data.md). There is no
# patient data in this dump, and there must never be.
#
#   scripts/seed-remote.sh "$(railway variables -s Postgres --kv | grep DATABASE_PUBLIC_URL | cut -d= -f2-)"
set -euo pipefail

TARGET=${1:-${TARGET_DATABASE_URL:-}}
SOURCE=${SOURCE_DATABASE_URL:-postgresql://rarelens:rarelens@localhost:5432/rarelens}
IMAGE=${PG_IMAGE:-postgres:16-alpine}

# Reference data first, then a case's own rows: variants reference jobs, jobs reference cases.
TABLES=(hpo_terms gene_phenotypes cases case_phenotypes jobs variants predictions variant_decisions)

if [ -z "$TARGET" ]; then
  echo "usage: $0 <target postgres URL>   (or set TARGET_DATABASE_URL)" >&2
  echo "the target must already have the schema: run 'alembic upgrade head' against it first" >&2
  exit 2
fi

case "$TARGET" in
  postgres://*|postgresql://*) ;;
  *) echo "target must be a postgres:// URL, got ${TARGET%%:*}:..." >&2; exit 2 ;;
esac

echo "==> source: ${SOURCE%%\?*}" >&2
echo "==> target: ${TARGET%%:*}://…${TARGET##*@}" >&2   # host only: the password stays out of the log
echo "==> tables: ${TABLES[*]}" >&2

# --data-only: the target's schema comes from Alembic, so the two can never disagree about it.
# Truncating first makes the script repeatable; cascade because variants hang off jobs.
docker run --rm -i --add-host=host.docker.internal:host-gateway \
  -e PGPASSWORD_UNUSED=1 "$IMAGE" \
  pg_dump --data-only --no-owner --no-privileges \
          $(printf -- '--table=%s ' "${TABLES[@]}") \
          "${SOURCE/localhost/host.docker.internal}" \
  > /tmp/rarelens-seed.sql

lines=$(wc -l < /tmp/rarelens-seed.sql)
echo "==> dumped $lines lines" >&2

docker run --rm -i "$IMAGE" psql "$TARGET" -v ON_ERROR_STOP=1 \
  -c "TRUNCATE $(IFS=,; echo "${TABLES[*]}") RESTART IDENTITY CASCADE" >&2

docker run --rm -i "$IMAGE" psql "$TARGET" -v ON_ERROR_STOP=1 -q < /tmp/rarelens-seed.sql
rm -f /tmp/rarelens-seed.sql

echo "==> loaded. counts on the target:" >&2
docker run --rm -i "$IMAGE" psql "$TARGET" -At -c "
  select 'cases: '||count(*) from cases
  union all select 'variants: '||count(*) from variants
  union all select 'gene_phenotypes: '||count(*) from gene_phenotypes
  union all select 'hpo_terms: '||count(*) from hpo_terms"