#!/usr/bin/env bash
# Seeds the acceptance stand with datasets for the load test (Приложение 3,
# п. 3.3), so the read endpoints work on a realistic catalogue.
#
#   test/acceptance/seed.sh          create (idempotent) category "acc-load":
#                                    SEED_VECTOR (25) vector GeoJSON,
#                                    SEED_KATO (25) vector_with_kato GeoJSON with
#                                    KATO mapping (14 districts x 3 years each),
#                                    SEED_RASTER (50) GeoTIFF rasters; the
#                                    vector_with_kato datasets form the group
#                                    "acc-load-population"
#   test/acceptance/seed.sh clean    delete everything seed.sh created
#
# Writes the ids load.sh needs to test/acceptance/results/seed.env.
# WRITES to the stand: never point it at production.
set -euo pipefail

HERE="$(cd "$(dirname "$0")" && pwd)"
BASE_URL="${BASE_URL:-http://localhost:18080}"
BASE_URL="${BASE_URL%/}"
PYTHON="${PYTHON:-python3}"
SEED_VECTOR="${SEED_VECTOR:-25}"
SEED_KATO="${SEED_KATO:-25}"
SEED_RASTER="${SEED_RASTER:-50}"
CAT_CODE=acc-load
GRP_CODE=acc-load-population
ENV_OUT="$HERE/results/seed.env"
mkdir -p "$HERE/results"
case "$BASE_URL" in
  *dssgis.dwh.kz*) echo "refusing to write to $BASE_URL (production)" >&2; exit 2;;
esac
J=(-H 'Content-Type: application/json')

cat_id() { curl -fsS "$BASE_URL/categories" | jq -r --arg c "$CAT_CODE" '.[]|select(.code==$c)|.id' | head -n1; }
grp_id() { curl -fsS "$BASE_URL/dataset-groups?code=$GRP_CODE" | jq -r '.data[0].id // empty'; }
ids_in_category() { # all dataset ids of a category (paginated)
  local cat="$1" page=1 out
  while :; do
    out="$(curl -fsS "$BASE_URL/datasets?category_id=$cat&page_size=100&page=$page")"
    jq -r '.data[].id' <<< "$out"
    [ "$page" -lt "$(jq -r .total_pages <<< "$out")" ] || break
    page=$((page + 1))
  done
}

if [ "${1:-}" = clean ]; then
  CAT="$(cat_id || true)"; GRP="$(grp_id || true)"
  if [ -n "$CAT" ]; then
    n=0; for id in $(ids_in_category "$CAT"); do curl -sS -o /dev/null -X DELETE "$BASE_URL/datasets/$id"; n=$((n + 1)); done
    echo "deleted $n datasets"
  fi
  [ -n "$GRP" ] && curl -sS -o /dev/null -w "group delete %{http_code}\n" -X DELETE "$BASE_URL/dataset-groups/$GRP"
  [ -n "$CAT" ] && curl -sS -o /dev/null -w "category delete %{http_code}\n" -X DELETE "$BASE_URL/categories/$CAT"
  rm -f "$ENV_OUT"
  exit 0
fi

CAT="$(cat_id || true)"
if [ -z "$CAT" ]; then
  CAT="$(curl -fsS -X POST "$BASE_URL/categories" "${J[@]}" -d "{\"code\":\"$CAT_CODE\",\"name\":\"Нагрузочное тестирование\",\"description\":\"Данные для test/acceptance/load.sh\"}" | jq -r .id)"
fi
GRP="$(grp_id || true)"
if [ -z "$GRP" ]; then
  GRP="$(curl -fsS -X POST "$BASE_URL/dataset-groups" "${J[@]}" -d "{\"code\":\"$GRP_CODE\",\"name\":\"Население СКО (нагрузочный тест)\"}" | jq -r .id)"
fi

want=$((SEED_VECTOR + SEED_KATO + SEED_RASTER))
have="$(curl -fsS "$BASE_URL/datasets?category_id=$CAT&status=ready&page_size=1" | jq -r .total)"
if [ "$have" -lt "$want" ]; then
  echo "seeding $BASE_URL: $SEED_VECTOR vector, $SEED_KATO vector_with_kato, $SEED_RASTER raster (category $CAT_CODE)"
  TMP="$(mktemp -d "${TMPDIR:-/tmp}/gis-seed.XXXXXX")"; trap 'rm -rf "$TMP"' EXIT
  "$PYTHON" "$HERE/lib/helpers.py" ndvi "$TMP/ndvi_seed.tif"
  upload() { curl -fsS -X POST "$BASE_URL/datasets" "$@" | jq -r .id; }
  for i in $(seq 1 "$SEED_VECTOR"); do
    upload -F "file=@$HERE/data/plots_nko.geojson" -F file_type=vector -F "category_id=$CAT" -F "name=Участки $i" >/dev/null
  done
  kato_ids=""
  for i in $(seq 1 "$SEED_KATO"); do
    y=$((2000 + i))
    kato_ids="$kato_ids $(upload -F "file=@$HERE/data/population_kato.geojson" -F file_type=vector_with_kato -F "category_id=$CAT" \
      -F "name=Население $i" -F "dg_id=$GRP" -F "start_date=$y-01-01" -F "end_date=$y-12-31")"
  done
  for i in $(seq 1 "$SEED_RASTER"); do
    upload -F "file=@$TMP/ndvi_seed.tif" -F file_type=raster -F "category_id=$CAT" -F "name=NDVI $i" >/dev/null
  done
  MAP='{"kato_column":"kato","year_columns":[{"column":"Y2022","start_date":"2022-01-01","end_date":"2022-12-31"},{"column":"Y2023","start_date":"2023-01-01","end_date":"2023-12-31"},{"column":"Y2024","start_date":"2024-01-01","end_date":"2024-12-31"}]}'
  for id in $kato_ids; do
    for _ in $(seq 1 120); do
      [ "$(curl -fsS "$BASE_URL/datasets/$id" | jq -r .status)" = awaiting_mapping ] && break; sleep 1
    done
    curl -fsS -o /dev/null -X POST "$BASE_URL/datasets/$id/mapping" "${J[@]}" -d "$MAP"
  done
  for _ in $(seq 1 300); do
    have="$(curl -fsS "$BASE_URL/datasets?category_id=$CAT&status=ready&page_size=1" | jq -r .total)"
    [ "$have" -ge "$want" ] && break; sleep 1
  done
fi
VWK="$(curl -fsS "$BASE_URL/datasets?category_id=$CAT&file_type=vector_with_kato&status=ready&page_size=1" | jq -r '.data[0].id')"
printf 'CAT_ID=%s\nGROUP_ID=%s\nVWK_ID=%s\n' "$CAT" "$GRP" "$VWK" > "$ENV_OUT"
echo "seed: category $CAT_CODE has $have ready datasets (wanted $want); ids in $ENV_OUT"
cat "$ENV_OUT"