#!/usr/bin/env python3
"""rmm-search engine. Reads the GuruRMM agents JSON array on stdin; reads
QUERY/CLIENT/ONLINE/JSON/LISTC/LIMIT from the environment. Flexible, forgiving
multi-field search — see rmm-search.sh for usage. Kept as a sidecar (not a
heredoc) because the agents payload is too large to pass as a CLI argument."""
import sys, os, json, re
from datetime import datetime, timezone

raw = sys.stdin.read()
agents = json.loads(raw) if raw.strip() else []
query = os.environ.get("QUERY", "").strip()
client = os.environ.get("CLIENT", "").strip()
online_only = os.environ.get("ONLINE") == "1"
as_json = os.environ.get("JSON") == "1"
list_clients = os.environ.get("LISTC") == "1"
try:
    limit = int(os.environ.get("LIMIT", "0") or 0)
except ValueError:
    limit = 0


def norm(s):
    return re.sub(r'[^a-z0-9]', '', (s or '').lower())


def is_subseq(t, v):
    it = iter(v)
    return all(c in it for c in t)


def field_score(val, term, allow_subseq):
    """How well a single query word matches one normalized field value."""
    if not val or not term:
        return 0
    if val == term:
        return 100
    if val.startswith(term):
        return 80
    if term in val:
        return 60
    if allow_subseq and len(term) >= 3 and is_subseq(term, val):
        return 25
    return 0


# field -> (key, weight, allow_subsequence)
FIELDS = [
    ('hostname', 1.00, True),
    ('client_name', 0.75, False),
    ('site_name', 0.60, False),
    ('os_type', 0.55, False),
    ('id', 0.40, False),
]


def fresh(last_seen):
    if not last_seen:
        return False
    try:
        dt = datetime.fromisoformat(last_seen.replace('Z', '+00:00'))
        return (datetime.now(timezone.utc) - dt).total_seconds() < 300
    except Exception:
        return False


if list_clients:
    for n in sorted({(a.get('client_name') or 'Unassigned') for a in agents}):
        print(n)
    sys.exit(0)

# --- explicit hard client scope (normalized; "valleywide" -> "Valley Wide Plastering") ---
if client:
    cn = norm(client)
    matched = sorted({(a.get('client_name') or '') for a in agents
                      if cn and cn in norm(a.get('client_name'))} - {''})
    if not matched:
        print(f"[ERROR] no client matches '{client}'. Try: rmm-search.sh --list-clients", file=sys.stderr)
        sys.exit(2)
    if len(matched) > 1:
        exact = [m for m in matched if norm(m) == cn]
        if len(exact) == 1:
            matched = exact
        else:
            print(f"[AMBIGUOUS] '{client}' matches {len(matched)} clients - narrow --client:", file=sys.stderr)
            for m in matched:
                print("  - " + m, file=sys.stderr)
            sys.exit(3)
    agents = [a for a in agents if (a.get('client_name') or '') == matched[0]]

if online_only:
    agents = [a for a in agents if fresh(a.get('last_seen'))]

terms = [t for t in (norm(x) for x in query.split()) if t]
joined = norm(query)


def score_agent(a):
    if not terms:
        return 1  # no query (e.g. "all machines for client X")
    nf = [(norm(a.get(k)), w, sub) for k, w, sub in FIELDS]
    total = 0.0
    for term in terms:
        best = max(field_score(val, term, sub) * w for val, w, sub in nf)
        if best == 0:
            return 0  # AND: every word must hit some field
        total += best
    if joined and joined in norm(a.get('hostname')):
        total += 60  # whole query lands in hostname -> clearly THE machine
    return total


results = sorted(((score_agent(a), a) for a in agents),
                 key=lambda t: (-t[0], (t[1].get('hostname') or '').lower()))
results = [(s, a) for s, a in results if s > 0]
if limit > 0:
    results = results[:limit]

if as_json:
    print(json.dumps([{
        'hostname': a.get('hostname'), 'id': a.get('id'), 'client': a.get('client_name'),
        'site': a.get('site_name'), 'os': a.get('os_type'),
        'online': fresh(a.get('last_seen')), 'last_seen': a.get('last_seen'), 'score': round(s, 1),
    } for s, a in results], indent=2))
    sys.exit(0)

scope = f" in '{(agents[0].get('client_name') if (client and agents) else client)}'" if client else ""
if not results:
    print(f"No machines match '{query}'{scope}. (try fewer/looser words, or --list-clients)")
    sys.exit(0)

hdr = f"{'HOSTNAME':<22} {'CLIENT':<26} {'SITE':<16} {'OS':<8} {'STAT':<7} ID"
print(f"{len(results)} match(es) for '{query}'{scope} (best first):")
print(hdr)
print("-" * len(hdr))
for s, a in results:
    st = 'online' if fresh(a.get('last_seen')) else 'offline'
    print(f"{(a.get('hostname') or '')[:21]:<22} {(a.get('client_name') or '?')[:25]:<26} "
          f"{(a.get('site_name') or '')[:15]:<16} {(a.get('os_type') or '')[:7]:<8} {st:<7} {a.get('id')}")