# Applies Pillar 1 v1.1 and v1.2 (and ablations) to real Zeek conn.log files; tuple label from IoT-23 labeled file.
import sys, os, collections, importlib.util
here = os.path.dirname(os.path.abspath(__file__))
spec = importlib.util.spec_from_file_location('sim', os.path.join(here, 'p1v12sim_lib.py')); sim = importlib.util.module_from_spec(spec); spec.loader.exec_module(sim)
def read(path):
    fields = None
    for line in open(path, errors='replace'):
        line = line.rstrip('\n')
        if line.startswith('#fields'): fields = line.split('\t')[1:]; continue
        if line.startswith('#') or not line: continue
        yield dict(zip(fields, line.split('\t')))
def labels(path):
    lab = {}
    if not path or not os.path.exists(path): return lab
    for r in read(path):
        last = ' '.join(v for k, v in r.items() if k in ('tunnel_parents', 'label', 'detailed-label', 'det_label'))
        mal = 'Malicious' in last or 'Malicious' in str(list(r.values())[-3:])
        k = (r['id.orig_h'], r['id.resp_h'], r['id.resp_p'])
        lab[k] = lab.get(k, False) or mal
    return lab
import ipaddress
EXCL = {('udp','5355'),('udp','546'),('udp','547'),('udp', '123'), ('udp', '53'), ('tcp', '53'), ('udp', '5353'), ('udp', '137'), ('udp', '138'), ('udp', '67'), ('udp', '68'), ('udp', '1900')}
conn, labf = sys.argv[1], (sys.argv[2] if len(sys.argv) > 2 else None)
lab = labels(labf)
tup = collections.defaultdict(list); protos = {}
for r in read(conn):
    k = (r['id.orig_h'], r['id.resp_h'], r['id.resp_p']); tup[k].append(float(r['ts'])); protos.setdefault(k, set()).add(r['proto'])
rows = []
for k, ts in sorted(tup.items()):
    if len(ts) < 20: continue
    a = sim.v11(ts)[0]; b = sim.v12(ts)
    span_only = sim.v12(ts, gate=1e-12)[0]; gate_only = sim.v12(ts, cycles=1e-12)[0]
    try:
        a_ = ipaddress.ip_address(k[1]); mc = a_.is_multicast or k[1] == '255.255.255.255'
    except ValueError:
        mc = False
    excl = mc or any(p not in ('tcp', 'udp') for p in protos[k]) or any((p, k[2]) in EXCL for p in protos[k])
    rows.append((k, len(ts), a, span_only, gate_only, b[0], b[1], b[2], excl, lab.get(k)))
print(f"== {conn}: tuples with n>=20: {len(rows)}")
print("tuple n v1.1 span_only gate_only v1.2 status period excluded label")
for r in rows:
    if max(r[2], r[5]) >= .40:
        print(f"  {r[0]} n={r[1]} v11={r[2]:.3f} span={r[3]:.3f} gate={r[4]:.3f} v12={r[5]:.3f} {r[6]} per={r[7] and round(r[7])} excl={r[8]} mal={r[9]}")
c = lambda i, ex: sum(1 for r in rows if r[i] >= .4 and (not ex or not r[8]))
print(f"  alerts>=0.40: v1.1={c(2,False)} span_only={c(3,False)} gate_only={c(4,False)} v1.2={c(5,False)} v1.2+exclusion={c(5,True)}")