#!/usr/bin/env bash
# capture-dsh-token.sh — refresh the dsh-web login token WITHOUT restarting dsh-web.
#
# Context (CT 112 / tankodhs.sysloggh.net)
# ----------------------------------------
# The dsh-web UI (systemd unit `dsh-web.service`, 127.0.0.1:3080) prints a random
# launch token to the journal on every start:
#
#     dsh web: http://127.0.0.1:3080/?token=<TOKEN>
#
# That token is the only way to bootstrap the authority-bound 30-day browser
# cookie. It rotates on every dsh-web start, so the Authentik-gated
# `location = /dsh-web-login` in /etc/nginx/sites-available/dsh must always
# reference the token of the RUNNING process.
#
# This script:
#   1. selects the launch token the RUNNING service actually accepts from the
#      current systemd invocation — it NEVER stops or starts dsh-web,
#   2. records it in /etc/dsh-web/launch-token,
#   3. regenerates the nginx include /etc/dsh-web/nginx-login.conf (the
#      `proxy_pass ...?token=` line consumed by /dsh-web-login),
#   4. reloads nginx ONLY when the on-disk include differs from the generated
#      one or the applied-state stamp does not match the token (the stamp is
#      written only after a successful reload), rolling the include back on
#      failure so the next run retries,
#   5. removes the legacy unauthenticated :8081 endpoint if it ever reappears.
#
# Idempotent and safe to run at any time (systemd ExecStartPost or timer).
set -euo pipefail
umask 077
PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"

JOURNAL_UNIT="dsh-web.service"
TOKEN_FILE="/etc/dsh-web/launch-token"
INCLUDE_FILE="/etc/dsh-web/nginx-login.conf"
STAMP_FILE="/etc/dsh-web/nginx-login.conf.applied"
PENDING_FILE="/etc/dsh-web/nginx-reload.pending"
SITE_ENABLED="/etc/nginx/sites-enabled/dsh"
LEGACY_8081="/etc/nginx/sites-enabled/dsh.token"
STASH_DIR="/etc/nginx/sites-available"
LOCK_FILE="/run/capture-dsh-token.lock"
LOGIN_HOST="tankodhs.sysloggh.net"
LOGIN_UPSTREAM="http://127.0.0.1:3080"
TOKEN_WAIT=120

log()  { printf 'capture-dsh-token: %s\n' "$*" >&2; }
die()  { printf 'capture-dsh-token: ERROR: %s\n' "$*" >&2; exit 1; }

[ "$(id -u)" -eq 0 ] || die "must run as root"

# ── 0. Serialize runs so timer/ExecStartPost/manual runs cannot interleave ──
exec 9>"$LOCK_FILE"
flock -n 9 || { log "another capture-dsh-token run holds $LOCK_FILE; exiting"; exit 0; }
mkdir -p "$(dirname "$PENDING_FILE")"

# ── 0b. Guarantee the generated include exists before any `nginx -t` ──────
# The :80 site includes /etc/dsh-web/nginx-login.conf by literal path, so a
# missing include makes every `nginx -t` fail and can wedge recovery. Seed it
# from the last known token (or a placeholder); step 4 replaces it.
if [ ! -f "$INCLUDE_FILE" ]; then
  SEED="placeholder"
  if [ -f "$TOKEN_FILE" ]; then
    SEED="$(cat "$TOKEN_FILE" 2>/dev/null || true)"
    [ -n "$SEED" ] || SEED="placeholder"
  fi
  printf '%s' "$SEED" | grep -qE '^[A-Za-z0-9._~+/=:@-]+$' || SEED="placeholder"
  printf 'proxy_pass %s/?token=%s;\n' "$LOGIN_UPSTREAM" "$SEED" > "$INCLUDE_FILE"
  chmod 600 "$INCLUDE_FILE"
  log "created missing $INCLUDE_FILE"
fi

# ── 1. Remove the legacy unauthenticated :8081 endpoint, if present ─────────
# It bypassed Authentik entirely (listened on 0.0.0.0:8081 with no auth_request)
# and must never come back. Stash it rather than delete so it is auditable.
if [ -e "$LEGACY_8081" ] || [ -L "$LEGACY_8081" ]; then
  TS="$(date -u +%Y%m%dT%H%M%SZ)"
  STASHED="$STASH_DIR/dsh.token.disabled-$TS"
  mv "$LEGACY_8081" "$STASHED"
  chmod 600 "$STASHED" 2>/dev/null || true
  touch "$PENDING_FILE"
  if ! NGINX_TEST_OUT="$(nginx -t 2>&1)"; then
    die "nginx config test failed after disabling $LEGACY_8081 (kept disabled at $STASHED): $NGINX_TEST_OUT; a pending reload is recorded so running nginx is reloaded once the config is fixed. The legacy :8081 endpoint will NOT be restored."
  fi
  if ! nginx -s reload; then
    die "nginx reload failed after disabling $LEGACY_8081 (kept disabled at $STASHED); a pending reload is recorded so running nginx is reloaded on the next run. The legacy :8081 endpoint will NOT be restored."
  fi
  rm -f "$PENDING_FILE"
  log "removed legacy :8081 endpoint -> $STASHED"
fi

# ── 1b. Honor a recorded pending reload regardless of token selection ───────
# A failed reload leaves PENDING_FILE set so a stashed legacy :8081 file can
# never remain loaded in the running nginx while dsh-web is down or not yet
# answering. Reconcile it before the token wait.
if [ -e "$PENDING_FILE" ]; then
  if ! NGINX_TEST_OUT="$(nginx -t 2>&1)"; then
    log "WARNING: pending nginx reload recorded but 'nginx -t' fails: $NGINX_TEST_OUT; continuing so the include can be regenerated; will retry next run"
  elif ! nginx -s reload; then
    log "WARNING: pending nginx reload recorded but 'nginx -s reload' failed; will retry next run"
  else
    rm -f "$PENDING_FILE"
    log "completed pending nginx reload"
  fi
fi

# ── 2. Select the token the RUNNING service actually accepts ────────────────
# Re-sample the service's CURRENT systemd invocation on every pass and read
# candidates only from it, so a restart that lands during the wait immediately
# switches to the new invocation; there is no whole-journal or cross-invocation
# fallback, and an empty/unknown invocation just waits. Each candidate is then
# functionally verified against the local dsh-web using the public authority,
# exactly as the /dsh-web-login proxy does, and the first that answers 303 is
# the live token. Candidates are re-probed newest-first on each pass (connection
# failures stay eligible) until one is accepted or the wait elapses.
journal_tokens() {
  journalctl -u "$JOURNAL_UNIT" "_SYSTEMD_INVOCATION_ID=$1" --no-pager -o cat 2>/dev/null \
    | grep -oE 'dsh web: https?://[^[:space:]]+[?&]token=[^[:space:]]+' \
    | sed -E 's/.*[?&]token=//' \
    | grep -E '^[A-Za-z0-9._~+/=:@-]+$' \
    | tac | awk '!seen[$0]++' || true
}

TOKEN=""
DEADLINE=$((SECONDS + TOKEN_WAIT))
NO_INVOCATION_WARNED=0
while [ -z "$TOKEN" ] && [ "$SECONDS" -lt "$DEADLINE" ]; do
  INVOCATION="$(systemctl show -p InvocationID --value "$JOURNAL_UNIT" 2>/dev/null || true)"
  if [ -z "$INVOCATION" ] || [ "$INVOCATION" = "n/a" ]; then
    if [ "$NO_INVOCATION_WARNED" -eq 0 ]; then
      log "WARNING: no invocation id for $JOURNAL_UNIT; waiting for a live invocation"
      NO_INVOCATION_WARNED=1
    fi
    sleep 2
    continue
  fi
  for cand in $(journal_tokens "$INVOCATION"); do
    code="$(curl -s -o /dev/null --max-time 5 -w '%{http_code}' \
      -H "Host: $LOGIN_HOST" "$LOGIN_UPSTREAM/?token=$cand" || true)"
    if [ "$code" = "303" ]; then
      TOKEN="$cand"
      break
    fi
  done
  [ -n "$TOKEN" ] && break
  sleep 2
done

if [ -z "$TOKEN" ]; then
  log "no accepted launch token in the current invocation within ${TOKEN_WAIT}s; leaving the include untouched for the next run"
  [ -e "$PENDING_FILE" ] && die "pending nginx reload could not be completed; will retry next run"
  exit 0
fi

# ── 3. Record the token (atomic, private) ──────────────────────────────────
mkdir -p "$(dirname "$TOKEN_FILE")"
if ! printf '%s\n' "$TOKEN" | cmp -s - "$TOKEN_FILE" 2>/dev/null; then
  printf '%s\n' "$TOKEN" > "$TOKEN_FILE.tmp"
  chmod 600 "$TOKEN_FILE.tmp"
  mv "$TOKEN_FILE.tmp" "$TOKEN_FILE"
  log "recorded live launch token in $TOKEN_FILE"
fi
chmod 600 "$TOKEN_FILE"

# ── 4. Regenerate the nginx login include (reload only when it changes) ────
NEW_INCLUDE="$(mktemp "$INCLUDE_FILE.XXXXXX")"
printf 'proxy_pass %s/?token=%s;\n' "$LOGIN_UPSTREAM" "$TOKEN" > "$NEW_INCLUDE"
chmod 600 "$NEW_INCLUDE"

# The stamp records the token nginx actually loaded. It is written only after a
# successful reload, so the early exit is safe only when both the stamp and the
# on-disk include agree with the live token; anything else falls through to the
# reload path so the include can never silently diverge from what nginx serves.
APPLIED=""
[ -f "$STAMP_FILE" ] && APPLIED="$(cat "$STAMP_FILE" 2>/dev/null || true)"
[ -f "$INCLUDE_FILE" ] && chmod 600 "$INCLUDE_FILE"
[ -f "$STAMP_FILE" ] && chmod 600 "$STAMP_FILE"

if [ "$APPLIED" = "$TOKEN" ] && [ -f "$INCLUDE_FILE" ] && cmp -s "$NEW_INCLUDE" "$INCLUDE_FILE" \
  && [ ! -e "$PENDING_FILE" ]; then
  rm -f "$NEW_INCLUDE"
  log "token unchanged; nginx not reloaded"
  exit 0
fi

[ -e "$SITE_ENABLED" ] || { rm -f "$NEW_INCLUDE"; die "$SITE_ENABLED missing; refusing to reload"; }

RESTORE=""
if [ -f "$INCLUDE_FILE" ]; then
  RESTORE="$(mktemp "$INCLUDE_FILE.bak.XXXXXX")"
  cp -p "$INCLUDE_FILE" "$RESTORE"
  chmod 600 "$RESTORE"
fi

mv "$NEW_INCLUDE" "$INCLUDE_FILE"
chmod 600 "$INCLUDE_FILE"

if ! NGINX_TEST_OUT="$(nginx -t 2>&1)"; then
  if [ -n "$RESTORE" ]; then
    mv "$RESTORE" "$INCLUDE_FILE"
  else
    rm -f "$INCLUDE_FILE"
  fi
  die "nginx config test failed: $NGINX_TEST_OUT; previous include restored"
fi

if ! nginx -s reload; then
  if [ -n "$RESTORE" ]; then
    mv "$RESTORE" "$INCLUDE_FILE"
  else
    rm -f "$INCLUDE_FILE"
  fi
  touch "$PENDING_FILE"
  die "nginx reload failed; previous include restored; a pending reload is recorded so the next run retries"
fi

if [ -n "$RESTORE" ]; then
  rm -f "$RESTORE"
fi

rm -f "$PENDING_FILE"

printf '%s\n' "$TOKEN" > "$STAMP_FILE.tmp"
chmod 600 "$STAMP_FILE.tmp"
mv "$STAMP_FILE.tmp" "$STAMP_FILE"

log "token changed; nginx reloaded"
log "login endpoint: https://$LOGIN_HOST/dsh-web-login (Authentik-gated)"