#!/bin/bash

# ============================================================================
# Make the running bot pick up a change, and prove that it did.
#
# Two kinds of change, two mechanisms:
#
#   scripts/reload.sh [cmd]          data changed (aliases, an album, a
#                                    command switched off): POST /_reload,
#                                    the table is rebuilt in place, nothing
#                                    restarts and no frame is lost.
#   scripts/reload.sh --code [cmd]   code changed: restart the unit, wait for
#                                    /healthz to go green again. Lossless too
#                                    (signal-cli replays what arrived), but
#                                    a deploy step -- so it is the flag, not
#                                    the default.
#
# With [cmd], the bot then types that command at itself in the test group,
# so "reloaded" means "answered", not "returned 200". E.g.
#
#   scripts/reload.sh '!nowaosoba'
#   scripts/reload.sh --code '!pomoc'
# ============================================================================

set -euo pipefail

SCRIPT_NAME="$(basename "$0")"
readonly SCRIPT_NAME
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
readonly SCRIPT_DIR
readonly BOT="http://127.0.0.1:${BIND_PORT:-8137}"
readonly UNIT="signal-bot"
readonly TEST_GROUP="${RELOAD_GROUP:-testbot}"

RESTART=0
PROBE=""

usage() {
    echo "Usage: $SCRIPT_NAME [--code] [command-to-selftest]"
    echo "  --code   restart the unit (code changed) instead of rebuilding the table"
    exit 0
}

validate_requirements() {
    if ! command -v jq >/dev/null; then
        echo "Error: jq is required" >&2
        exit 1
    fi
}

wait_healthy() {
    local attempt=0
    # 150 x 0.4 s: a restart is ~1 s, but signal-cli can take a while to
    # accept the websocket again after its own reconnect.
    until [[ "$(curl -s "${BOT}/healthz" | jq -r '.status // "down"')" == "ok" ]]; do
        attempt=$((attempt + 1))
        if [[ $attempt -ge 150 ]]; then
            echo "Error: ${BOT}/healthz never reported ok" >&2
            curl -s "${BOT}/healthz" >&2 || true
            exit 1
        fi
        sleep 0.4
    done
}

reload_data() {
    local reply status
    reply="$(curl -s -X POST "${BOT}/_reload")"
    status="$(jq -r '.status // "?"' <<<"$reply")"
    case "$status" in
    reloaded)
        echo "reloaded: $(jq -r '.commands' <<<"$reply") commands live"
        ;;
    kept)
        # The old table is still answering; the new data is what is broken.
        echo "Error: reload refused, previous table kept: $(jq -r '.reason' <<<"$reply")" >&2
        exit 1
        ;;
    *)
        echo "Error: unexpected answer from ${BOT}/_reload: ${reply}" >&2
        exit 1
        ;;
    esac
}

restart_code() {
    systemctl --user restart "$UNIT"
    wait_healthy
    echo "restarted: $(curl -s "${BOT}/healthz" | jq -r '"\(.version) \(.pope)"')"
}

main() {
    validate_requirements
    if [[ $RESTART -eq 1 ]]; then
        restart_code
    else
        wait_healthy
        reload_data
    fi
    if [[ -n "$PROBE" ]]; then
        "${SCRIPT_DIR}/selftest.sh" "$TEST_GROUP" "$PROBE"
    fi
}

while [[ $# -gt 0 ]]; do
    case $1 in
    --code)
        RESTART=1
        shift
        ;;
    -h | --help)
        usage
        ;;
    *)
        PROBE="$1"
        shift
        ;;
    esac
done

main