#!/usr/bin/env python3
"""Extract ours tid=1 timeline, focused on the final wedge region.

Ours wedges by ~1.7s, so we want the FINAL kernel-call sequence ours emits
on tid=1 before the wait that wedges. Compare against canary tid=6 at a
matching matched-prefix point.
"""
import json
import os
from collections import Counter

INPUT = "/home/fabi/RE - Project Sylpheed/xenia-rs/audit-runs/phase-w-wedge-reattack/ours-postfix.jsonl"
OUTDIR = os.path.dirname(os.path.abspath(__file__))
TARGET_TID = 1

kernel_calls = []
kernel_returns = []
handle_creates = []
thread_events = []
import_calls = []
wait_events = []
other = []

last_idx = -1
last_host_ns = 0
with open(INPUT, "r") as f:
    for line in f:
        try:
            ev = json.loads(line)
        except json.JSONDecodeError:
            continue
        if ev.get("tid") != TARGET_TID:
            continue
        kind = ev.get("kind", "")
        last_idx = ev.get("tid_event_idx", last_idx)
        last_host_ns = ev.get("host_ns", last_host_ns)
        if kind == "kernel.call":
            kernel_calls.append(ev)
        elif kind == "kernel.return":
            kernel_returns.append(ev)
        elif kind == "handle.create":
            handle_creates.append(ev)
        elif kind in ("thread.create", "thread.exit"):
            thread_events.append(ev)
        elif kind == "import.call":
            import_calls.append(ev)
        elif kind in ("wait.begin", "wait.end", "wait.wake"):
            wait_events.append(ev)
        else:
            other.append(ev)

print(f"Ours tid={TARGET_TID} total kernel.call: {len(kernel_calls)}")
print(f"Ours tid={TARGET_TID} last tid_event_idx: {last_idx}")
print(f"Ours tid={TARGET_TID} last host_ns: {last_host_ns} ({last_host_ns/1e9:.3f} s)")

call_counts = Counter()
for ev in kernel_calls:
    call_counts[ev["payload"].get("name", "?")] += 1

# Show LAST 100 events on tid=1 to identify the wedge approach.
last_evts = []
for ev in kernel_calls + kernel_returns + wait_events + handle_creates + thread_events:
    last_evts.append((ev["host_ns"], ev["tid_event_idx"], ev["kind"], ev["payload"]))
last_evts.sort()
last_evts = last_evts[-150:]

with open(os.path.join(OUTDIR, "ours-tid1-final-150.csv"), "w") as f:
    f.write("host_ns,tid_event_idx,kind,name,detail\n")
    for host_ns, idx, kind, payload in last_evts:
        name = payload.get("name", "")
        detail = json.dumps(payload)[:300].replace('"', '""')
        f.write(f'{host_ns},{idx},{kind},{name},"{detail}"\n')

with open(os.path.join(OUTDIR, "ours-tid1-summary"), "w") as f:
    f.write(f"Ours tid={TARGET_TID} summary\n")
    f.write(f"\nTotal kernel.call: {len(kernel_calls)}\n")
    f.write(f"Last tid_event_idx: {last_idx}\n")
    f.write(f"Last host_ns: {last_host_ns} ({last_host_ns/1e9:.3f} s)\n")
    f.write(f"\n=== Top kernel.call by frequency ===\n")
    for name, c in call_counts.most_common(80):
        f.write(f"  {c:6d}  {name}\n")
    f.write(f"\n=== Unique kernel.call names ===\n")
    f.write(f"  {len(call_counts)}\n")

print(f"Wrote ours-tid1-final-150.csv")
print(f"Wrote ours-tid1-summary")