#!/usr/bin/env bash
# Is SearXNG actually searching?
#
#   scripts/searxng-health.sh          check the fleet instance
#   scripts/searxng-health.sh --url http://host:9996
#
# ⚠ THIS EXISTS BECAUSE /healthz CANNOT ANSWER THE QUESTION. On 2026-09-03 the
# old ana-docker instance was found returning ZERO results for every query, for
# an unknown number of weeks, while its container reported `healthy` for 7 days
# straight and its dashboard card was green. /healthz proves the web app
# answers; it says nothing about whether a single engine works.
#
# SearXNG rots quietly: engine scrapers break as upstream sites change markup,
# and the project ships near-daily releases to keep up. An instance pinned to
# `:latest` that nobody re-pulls is frozen at whatever `latest` meant on the day
# it was created — that one was 4.5 months behind.
#
# So this asserts the property, not the mechanism: RESULTS > 0.
set -euo pipefail

URL="http://10.100.50.40:9996"
[[ "${1:-}" == "--url" ]] && { URL="${2:?--url needs a value}"; shift 2; }

fail=0
say() { printf '%s\n' "$*"; }

say "── ${URL}"

# 1. reachable at all? An unreachable instance is an OUTAGE, not "no results".
if ! ver=$(curl -s -m 15 "$URL/config" | python3 -c 'import sys,json;print(json.load(sys.stdin)["version"])' 2>/dev/null); then
    say "  ✗ unreachable — this is an outage, not an empty index"
    exit 1
fi
say "  version: $ver"

# 2. is that version current? `:latest` is only latest at pull time.
if latest=$(curl -s -m 20 "https://hub.docker.com/v2/repositories/searxng/searxng/tags/?page_size=1&ordering=last_updated" \
            | python3 -c 'import sys,json;print(json.load(sys.stdin)["results"][0]["last_updated"][:10])' 2>/dev/null); then
    say "  registry :latest last pushed: $latest   (running build predates any later push)"
fi

# 3. THE CHECK THAT MATTERS. Three unrelated queries, because one query
#    returning nothing can legitimately mean nothing matched; three cannot.
for q in "proxmox backup" "python asyncio" "linux kernel"; do
    out=$(curl -s -m 45 --get --data-urlencode "q=$q" --data "format=json" "$URL/search" 2>/dev/null) || out=""
    n=$(printf '%s' "$out" | python3 -c 'import sys,json;print(len(json.load(sys.stdin).get("results") or []))' 2>/dev/null || echo 0)
    errs=$(printf '%s' "$out" | python3 -c 'import sys,json;print(",".join(e[0] for e in (json.load(sys.stdin).get("unresponsive_engines") or [])) or "-")' 2>/dev/null || echo "?")
    if [[ "$n" -gt 0 ]]; then
        say "  ✓ '$q' -> $n results   (failed engines: $errs)"
    else
        say "  ✗ '$q' -> ZERO results  (failed engines: $errs)"
        fail=1
    fi
done

if (( fail )); then
    say ""
    say "  ✗ SearXNG answers HTTP but finds nothing. Almost always staleness:"
    say "      ssh infra-ops@nh3-docker 'cd /opt/docker/compose/searxng && \\"
    say "        sudo docker compose pull && sudo docker compose up -d'"
    exit 1
fi
say "  ✓ searching"