#!/usr/bin/env bash
# Phase 3: parse the stored raw Compass pages for one child into SQLite.
#
# This runs the `school parse` subcommand in a one-off container that mounts the
# service's own data volume (read/write) and the stored raw pages (read-only).
# It does not restart or touch the running service.
#
# Usage:
#   scripts/parse-compass.sh [--child Harry] [--run latest] [--classify auto]
#
# Environment overrides:
#   IMAGE                image tag                  (default 0.5.0-phase7)
#   VOLUME               SQLite volume              (default compass-teams-nhs_compass-teams-nhs-data)
#   RAW_ROOT             host path to var/raw       (default <repo>/var/raw)
#   SCHOOL_TIMEZONE      family timezone            (default Australia/Melbourne)
#   OMNIROUTE_BASE_URL   OmniRoute endpoint         (default http://127.0.0.1:20129/v1)
#   TIMEOUT              docker command timeout     (default 300)
#
# Importance classification (FR-4) uses OmniRoute when OMNIROUTE_API_KEY is set;
# pass --classify none for the offline deterministic rule.
set -euo pipefail

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

IMAGE="${IMAGE:-compass-teams-nhs/school:0.5.0-phase7}"
VOLUME="${VOLUME:-compass-teams-nhs_compass-teams-nhs-data}"
RAW_ROOT="${RAW_ROOT:-$REPO_ROOT/var/raw}"
SCHOOL_TIMEZONE="${SCHOOL_TIMEZONE:-Australia/Melbourne}"
OMNIROUTE_BASE_URL="${OMNIROUTE_BASE_URL:-http://127.0.0.1:20129/v1}"
TIMEOUT="${TIMEOUT:-300}"

CHILD="Harry"
RUN="latest"
CLASSIFY="auto"
while [[ $# -gt 0 ]]; do
  case "$1" in
    --child) CHILD="$2"; shift 2 ;;
    --run) RUN="$2"; shift 2 ;;
    --classify) CLASSIFY="$2"; shift 2 ;;
    *) echo "unknown argument: $1" >&2; exit 2 ;;
  esac
done

if [[ ! -d "$RAW_ROOT" ]]; then
  echo "raw pages not found at $RAW_ROOT" >&2
  exit 1
fi

exec timeout "$TIMEOUT" docker run --rm --network host \
  -v "$VOLUME:/data" \
  -v "$RAW_ROOT:/raw:ro" \
  -e SCHOOL_DB_PATH=/data/school.db \
  -e SCHOOL_TIMEZONE="$SCHOOL_TIMEZONE" \
  -e OMNIROUTE_API_KEY \
  -e OMNIROUTE_BASE_URL="$OMNIROUTE_BASE_URL" \
  "$IMAGE" parse --child "$CHILD" --run "$RUN" --raw-root /raw --classify "$CLASSIFY"