# Pillar 2 candidate metrics on real Zeek conn.log: chained session duration per tuple, persistence score,
# per-host robust z of ln(duration), PCR, failed attempts.
import sys, math, collections, statistics
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')))
num = lambda x: float(x) if x not in ('-', '', '(empty)') else 0.0
GAP = 3600.0
def sessions(rows):
    by4 = collections.defaultdict(list)
    for r in rows:
        if r['proto'] != 'tcp': continue
        by4[(r['id.orig_h'], r['id.orig_p'], r['id.resp_h'], r['id.resp_p'])].append(r)
    out = []
    for k, rs in by4.items():
        rs.sort(key=lambda r: float(r['ts']))
        cur = None
        for r in rs:
            s = float(r['ts']); e = s + num(r['duration'])
            cont = cur is not None and 'S' not in r['history'] and s - cur['end'] <= GAP
            if cont:
                cur['end'] = max(cur['end'], e); cur['ob'] += num(r['orig_bytes']); cur['rb'] += num(r['resp_bytes']); cur['parts'] += 1
            else:
                if cur: out.append(cur)
                cur = dict(key=k, start=s, end=e, ob=num(r['orig_bytes']), rb=num(r['resp_bytes']), parts=1)
        out.append(cur)
    return out
for path in sys.argv[1:]:
    rows = list(read(path))
    ss = sessions(rows)
    fails = collections.Counter((r['id.orig_h'], r['id.resp_h'], r['id.resp_p']) for r in rows if r['proto'] == 'tcp' and r['conn_state'] in ('S0', 'REJ', 'RSTOS0', 'SH'))
    host_ld = collections.defaultdict(list)
    for s in ss:
        d = s['end'] - s['start']
        if d > 0: host_ld[s['key'][0]].append(math.log(d))
    best = {}
    for s in ss:
        t = (s['key'][0], s['key'][2], s['key'][3]); d = s['end'] - s['start']
        if t not in best or d > best[t]['end'] - best[t]['start']: best[t] = s
    ranked = sorted(best.items(), key=lambda kv: -(kv[1]['end'] - kv[1]['start']))
    print(f"== {path}: tcp sessions={len(ss)} tuples={len(best)}")
    for t, s in ranked[:5]:
        d = s['end'] - s['start']; xs = host_ld[t[0]]
        xs = xs or [0.0]; med = statistics.median(xs); mad = statistics.median(abs(x - med) for x in xs) or 1e-9
        z = (math.log(d) - med) / (1.4826 * mad) if d > 0 else 0
        pers = min(1, max(0, math.log(d / 3600) / math.log(24))) if d > 0 else 0
        tot = s['ob'] + s['rb']; pcr = (s['ob'] - s['rb']) / tot if tot else 0
        print(f"  {t} L={d:.0f}s ({d/3600:.2f}h) parts={s['parts']} persistence={pers:.3f} host_robust_z={z:.1f} ob={s['ob']:.0f} rb={s['rb']:.0f} PCR={pcr:+.2f} B/h={(tot/(d/3600)) if d>0 else 0:.0f} failed_attempts={fails[t]}")