#!/usr/bin/env bash
# generate-monitoring-sites.sh — run taler-monitoring, build console HTML for
# /monitoring and /monitoring_err (static files for host Caddy later).
#
# Usage:
#   ./generate-monitoring-sites.sh              # all SITES (or ONLY_HOSTS)
#   ONLY_HOSTS="bank.hacktivism.ch taler.hacktivism.ch" ./generate-monitoring-sites.sh
#   ./generate-monitoring-sites.sh --dry-run    # HTML from empty/missing logs only
#   ./generate-monitoring-sites.sh --skip-run   # only convert existing logs
#
# Settings: settings.conf (from settings.conf.example). No secrets in settings.
# Secrets for e2e: ../secrets.env (optional; default phases are urls versions).
#
set -uo pipefail

export PYTHONUNBUFFERED=1
# Global reporting defaults (same as host-agent run-host-report.sh)
: "${RUN_TIMEOUT:=600}"
export RUN_TIMEOUT

HERE=$(cd "$(dirname "$0")" && pwd)
SUITE_ROOT=$(cd "$HERE/../.." && pwd)
SITE_GEN="${SITE_GEN_DIR:-$SUITE_ROOT/site-gen}"
ROOT="$HERE"
SETTINGS="${SITE_GEN_SETTINGS:-$SITE_GEN/settings.conf}"
EXAMPLE="${SITE_GEN}/settings.conf.example"
[ -f "$EXAMPLE" ] || EXAMPLE="$HERE/settings.conf.example"

if [ ! -f "$SETTINGS" ]; then
  if [ -f "$EXAMPLE" ]; then
    echo "note: no $SETTINGS — using example defaults (copy to settings.conf to customize)"
    SETTINGS="$EXAMPLE"
  else
    echo "missing settings: $EXAMPLE" >&2
    exit 2
  fi
fi

# Load KEY=value lines; allow SITES already set in environment to win.
# Multiline SITES in the conf file: use SITES_FILE= or env SITES= instead.
while IFS= read -r _line || [ -n "$_line" ]; do
  _line=${_line%%#*}
  _line=$(echo "$_line" | sed 's/^[[:space:]]*//;s/[[:space:]]*$//')
  [ -z "$_line" ] && continue
  case "$_line" in
    SITES=*|SITES_FILE=*) continue ;; # handled below / env
    *=*)
      _k=${_line%%=*}
      _v=${_line#*=}
      # do not override pre-set env
      if [ -z "${!_k+x}" ] 2>/dev/null || [ -z "${!_k}" ]; then
        export "$_k=$_v"
      fi
      ;;
  esac
done < "$SETTINGS"

# SITES from dedicated file or keep env; else parse heredoc-style from example list
if [ -n "${SITES_FILE:-}" ] && [ -f "$SITES_FILE" ]; then
  SITES=$(grep -v '^\s*#' "$SITES_FILE" | grep -v '^\s*$')
  export SITES
elif [ -z "${SITES:-}" ]; then
  # default 9 fronts
  SITES="bank.hacktivism.ch|hacktivism.ch
exchange.hacktivism.ch|hacktivism.ch
taler.hacktivism.ch|hacktivism.ch
stage.bank.lefrancpaysan.ch|stage.lefrancpaysan.ch
stage.exchange.lefrancpaysan.ch|stage.lefrancpaysan.ch
stage.monnaie.lefrancpaysan.ch|stage.lefrancpaysan.ch
bank.lefrancpaysan.ch|lefrancpaysan.ch
exchange.lefrancpaysan.ch|lefrancpaysan.ch
monnaie.lefrancpaysan.ch|lefrancpaysan.ch"
  export SITES
fi

SKIP_RUN=0
DRY=0
while [ $# -gt 0 ]; do
  case "$1" in
    --skip-run) SKIP_RUN=1; shift ;;
    --dry-run) DRY=1; SKIP_RUN=1; shift ;;
    -h|--help) sed -n '1,20p' "$0"; exit 0 ;;
    *) echo "unknown arg: $1" >&2; exit 2 ;;
  esac
done

MONITORING_ROOT=$(cd "${MONITORING_ROOT:-$SUITE_ROOT}" && pwd)
WORK_ROOT="${WORK_ROOT:-/tmp/taler-monitoring-sites-work}"
LOG_DIR="$WORK_ROOT/logs"
HTML_DIR="$WORK_ROOT/html"
mkdir -p "$LOG_DIR" "$HTML_DIR"

# commit of monitoring suite used for this run
if git -C "$MONITORING_ROOT/../.." rev-parse HEAD >/dev/null 2>&1; then
  REPO_ROOT=$(cd "$MONITORING_ROOT/../.." && pwd)
elif git -C "$MONITORING_ROOT" rev-parse HEAD >/dev/null 2>&1; then
  REPO_ROOT=$(cd "$MONITORING_ROOT" && pwd)
else
  REPO_ROOT=$(cd "$ROOT/../../.." && pwd)
fi
COMMIT=$(git -C "$REPO_ROOT" rev-parse HEAD 2>/dev/null || echo unknown)
COMMIT_SHORT=$(git -C "$REPO_ROOT" rev-parse --short=12 HEAD 2>/dev/null || echo unknown)
SOURCE_REPO_WEB="${SOURCE_REPO_WEB:-https://git.hacktivism.ch/hernani/taler-monitoring}"
TMPL="${SOURCE_COMMIT_URL_TMPL:-\{repo\}/src/commit/\{commit\}}"
COMMIT_URL=$(printf '%s' "$TMPL" | sed "s|{repo}|$SOURCE_REPO_WEB|g; s|{commit}|$COMMIT|g")
SUITE_PATH="${SOURCE_SUITE_PATH:-.}"

# Outside-only public checks (no SSH into koopa/stage containers)
PHASES_ERR="${PHASES_ERR:-urls versions}"
PHASES_OK="${PHASES_OK:-urls versions}"
CONTINUE_ON_ERROR="${CONTINUE_ON_ERROR:-1}"
SKIP_SSH="${SKIP_SSH:-1}"
# Drop SSH phases if someone passes "all" / inside / server / e2e by mistake
filter_phases_outside() {
  local out=() p
  for p in "$@"; do
    case "$p" in
      inside|server|e2e|ladder|goa-ladder|auth401) continue ;;
      all) out+=(urls versions);;
      *) out+=("$p") ;;
    esac
  done
  printf '%s\n' "${out[@]}"
}

run_mon() {
  local domain="$1" phases="$2" logfile="$3" cont="$4"
  # shellcheck disable=SC2206
  local ph=( $phases )
  mapfile -t ph < <(filter_phases_outside "${ph[@]}")
  [ "${#ph[@]}" -gt 0 ] || ph=(urls versions)

  : >"$logfile"
  echo "+ -d $domain · phases=${ph[*]} · CONTINUE=$cont · SKIP_SSH=$SKIP_SSH · RUN_TIMEOUT=$RUN_TIMEOUT"

  if [ -n "${RUNNER_SSH:-}" ]; then
    echo "+ via ssh $RUNNER_SSH"
    rsync -az --delete \
      --exclude secrets.env \
      --exclude 'android-test/artifacts' \
      --exclude '.git' \
      "$MONITORING_ROOT/" \
      "${RUNNER_SSH}:${RUNNER_REMOTE_WORKDIR}/" \
      || return 1
    # shellcheck disable=SC2029
    if command -v stdbuf >/dev/null 2>&1; then
      ssh -o BatchMode=yes -o ConnectTimeout=30 "$RUNNER_SSH" \
        "cd '${RUNNER_REMOTE_WORKDIR}' && chmod +x taler-monitoring.sh check_*.sh 2>/dev/null; \
         export CONTINUE_ON_ERROR='$cont' AUTH401_CONTINUE='$cont' SKIP_SSH='$SKIP_SSH' RUN_TIMEOUT='$RUN_TIMEOUT'; \
         stdbuf -oL -eL ./taler-monitoring.sh -d '$domain' ${ph[*]}" \
        2>&1 | stdbuf -oL -eL tee -a "$logfile"
    else
      ssh -o BatchMode=yes -o ConnectTimeout=30 "$RUNNER_SSH" \
        "cd '${RUNNER_REMOTE_WORKDIR}' && chmod +x taler-monitoring.sh check_*.sh 2>/dev/null; \
         export CONTINUE_ON_ERROR='$cont' AUTH401_CONTINUE='$cont' SKIP_SSH='$SKIP_SSH' RUN_TIMEOUT='$RUN_TIMEOUT'; \
         ./taler-monitoring.sh -d '$domain' ${ph[*]}" \
        2>&1 | tee -a "$logfile"
    fi
    return "${PIPESTATUS[0]}"
  fi

  if command -v stdbuf >/dev/null 2>&1; then
    ( cd "$MONITORING_ROOT" && \
        CONTINUE_ON_ERROR="$cont" AUTH401_CONTINUE="$cont" SKIP_SSH="$SKIP_SSH" \
        RUN_TIMEOUT="$RUN_TIMEOUT" \
        stdbuf -oL -eL ./taler-monitoring.sh -d "$domain" "${ph[@]}" ) \
      2>&1 | stdbuf -oL -eL tee -a "$logfile"
  else
    ( cd "$MONITORING_ROOT" && \
        CONTINUE_ON_ERROR="$cont" AUTH401_CONTINUE="$cont" SKIP_SSH="$SKIP_SSH" \
        RUN_TIMEOUT="$RUN_TIMEOUT" \
        ./taler-monitoring.sh -d "$domain" "${ph[@]}" ) \
      2>&1 | tee -a "$logfile"
  fi
  return "${PIPESTATUS[0]}"
}

htmlify() {
  local host="$1" mode="$2" log="$3" out="$4" other="$5"
  mkdir -p "$(dirname "$out")"
  if [ ! -f "$SITE_GEN/console_to_html.py" ]; then
    echo "WARN: console_to_html.py missing — bootstrap $out"
    {
      echo "<!DOCTYPE html><html><head><meta charset=utf-8><title>$host $mode</title></head>"
      echo "<body><h1>$host · $mode</h1><p>commit <a href=\"$COMMIT_URL\">$COMMIT_SHORT</a></p>"
      echo "<pre>"
      tail -n 100 "$log" 2>/dev/null | sed 's/&/\&amp;/g;s/</\&lt;/g' || true
      echo "</pre></body></html>"
    } >"$out"
    return 0
  fi
  python3 "$SITE_GEN/console_to_html.py" \
    --log "$log" \
    --out "$out" \
    --hostname "$host" \
    --mode "$mode" \
    --commit "$COMMIT" \
    --commit-url "$COMMIT_URL" \
    --suite-path "$SUITE_PATH" \
    --link-other "$other"
}

# Parse SITES
mapfile -t SITE_LINES < <(printf '%s\n' "$SITES" | sed '/^\s*$/d' | sed 's/#.*//')
ONLY="${ONLY_HOSTS:-}"

for line in "${SITE_LINES[@]}"; do
  line=$(echo "$line" | tr -d ' \t')
  [ -z "$line" ] && continue
  host=${line%%|*}
  domain=${line#*|}
  if [ -n "$ONLY" ]; then
    echo " $ONLY " | grep -q " $host " || continue
  fi

  echo "======== $host  (domain=$domain)  commit=$COMMIT_SHORT ========"
  base_html="$HTML_DIR/$host"
  mkdir -p "$base_html/monitoring" "$base_html/monitoring_err"
  log_err="$LOG_DIR/${host}.err.log"
  log_ok="$LOG_DIR/${host}.ok.log"
  ec_err=1
  ec_ok=1

  if [ "$SKIP_RUN" != "1" ]; then
    run_mon "$domain" "$PHASES_ERR" "$log_err" "$CONTINUE_ON_ERROR"
    ec_err=$?
    # ok-run without continue (strict)
    run_mon "$domain" "$PHASES_OK" "$log_ok" "0"
    ec_ok=$?
  else
    [ -f "$log_err" ] || : >"$log_err"
    [ -f "$log_ok" ] || : >"$log_ok"
    # infer exit from log if present
    if grep -q '\[ ERROR \]' "$log_err" 2>/dev/null || grep -q 'ERROR' "$log_err" 2>/dev/null; then
      ec_err=1
    else
      ec_err=0
    fi
    ec_ok=$ec_err
  fi

  # Always write pages (first run / empty logs too)
  [ -f "$log_err" ] || : >"$log_err"
  [ -f "$log_ok" ] || : >"$log_ok"

  htmlify "$host" "err" "$log_err" \
    "$base_html/monitoring_err/index.html" "/monitoring/"

  if [ "$ec_ok" -eq 0 ] && [ "$ec_err" -eq 0 ]; then
    htmlify "$host" "ok" "$log_ok" \
      "$base_html/monitoring/index.html" "/monitoring_err/"
    echo "  → /monitoring (clean) + /monitoring_err"
  else
    htmlify "$host" "redirect" "$log_err" \
      "$base_html/monitoring/index.html" "/monitoring_err/"
    echo "  → /monitoring (redirect stub) + /monitoring_err (errors)  ec_err=$ec_err ec_ok=$ec_ok"
  fi

  # first-run safety
  if [ ! -f "$base_html/monitoring/index.html" ]; then
    htmlify "$host" "err" "$log_err" \
      "$base_html/monitoring/index.html" "/monitoring_err/"
  fi

  printf '%s\n' "$COMMIT" >"$base_html/COMMIT"
  printf '%s\n' "$COMMIT_URL" >"$base_html/COMMIT_URL"
  printf 'host=%s domain=%s ec_err=%s ec_ok=%s commit=%s run_timeout=%s\n' \
    "$host" "$domain" "$ec_err" "$ec_ok" "$COMMIT" "$RUN_TIMEOUT" | tee "$base_html/STATUS.txt"
done

echo
echo "HTML under $HTML_DIR"
echo "commit $COMMIT_SHORT  $COMMIT_URL"
echo "RUN_TIMEOUT=${RUN_TIMEOUT}s (global; 0=unlimited)"
echo "Deploy (as hernani, may need sudo for /var/www):"
echo "  $HERE/deploy-monitoring-sites.sh"
echo "Root on koopa: see ROOT-ON-KOOPA.md"