#!/usr/bin/env python3
"""Find the canary tid that runs the sub_821748F0 worker body and see
what it does in its 155ms lifetime (host_ns 1.935s to ~2.09s).

The spawn semantic-id is 3bd922fbb385c2c9.
"""
import json
import os
from collections import Counter

INPUT = "/home/fabi/RE - Project Sylpheed/xenia-canary/build-cross/bin/Windows/Debug/canary-jitter-1.jsonl"
OUTDIR = os.path.dirname(os.path.abspath(__file__))
TARGET_HSID = "3bd922fbb385c2c9"

# First pass: locate this thread's tid by matching the spawn handle.
target_tid = None
with open(INPUT, "r") as f:
    for line in f:
        if '"thread.create"' in line and TARGET_HSID in line:
            ev = json.loads(line)
            if ev.get("payload", {}).get("handle_semantic_id") == TARGET_HSID:
                child_handle = TARGET_HSID
                print(f"  spawn at host_ns={ev['host_ns']}, entry={ev['payload'].get('entry_pc')}")
                # The thread's own tid will be in events the thread itself emits.
                # Look for the FIRST event whose tid is NOT the parent and whose
                # subsequent guest_pc/handle matches this child handle.
                break

# We need to find tid by looking at next thread.create's tid_event_idx=0 emission.
# Simpler: scan events after this point for new tid that emits with this handle.
# Canary's convention: each new thread emits its first events under its own tid.

# Better approach: find thread.create events with handle_semantic_id=TARGET_HSID,
# then find the smallest tid > 6 that emits AFTER that timestamp.

T_LO = 1_900_000_000  # 1.9s
T_HI = 3_000_000_000  # 3.0s

events_by_tid = {}
with open(INPUT, "r") as f:
    for line in f:
        if '"host_ns":' not in line:
            continue
        try:
            i = line.index('"host_ns":') + len('"host_ns":')
            j = i
            while j < len(line) and (line[j].isdigit() or line[j] == '-'):
                j += 1
            host_ns = int(line[i:j])
        except (ValueError, IndexError):
            continue
        if host_ns < T_LO:
            continue
        if host_ns >= T_HI:
            break
        try:
            ev = json.loads(line)
        except json.JSONDecodeError:
            continue
        tid = ev.get("tid")
        if tid is None:
            continue
        events_by_tid.setdefault(tid, []).append(ev)

# tid=6 is parent. Look for new tids that emit between 1.935s and 2.1s.
print("\n=== tids active in window [1.9..3.0s] ===")
for tid, evts in sorted(events_by_tid.items()):
    if not evts:
        continue
    first_ns = evts[0]["host_ns"]
    last_ns = evts[-1]["host_ns"]
    print(f"  tid={tid}: {len(evts)} events from {first_ns/1e9:.4f}s to {last_ns/1e9:.4f}s")

# Find tid that spawns at ~1.935s and ends at ~2.09s.
candidate_tid = None
for tid, evts in events_by_tid.items():
    if tid == 6:
        continue
    first_ns = evts[0]["host_ns"]
    if first_ns < 1_930_000_000 or first_ns > 1_960_000_000:
        continue
    # Check exit time.
    last_ns = evts[-1]["host_ns"]
    print(f"  CANDIDATE tid={tid}: first={first_ns/1e9:.4f}s last={last_ns/1e9:.4f}s events={len(evts)}")
    candidate_tid = tid

if candidate_tid is None:
    print("\nNo single candidate found.")
else:
    print(f"\n=== Worker tid={candidate_tid} timeline (sub_821748F0 body) ===")
    evts = events_by_tid[candidate_tid]
    # All kernel.calls and thread.create.
    summary = Counter()
    for ev in evts:
        if ev["kind"] == "kernel.call":
            summary[ev["payload"].get("name", "?")] += 1
    print(f"Total events: {len(evts)}")
    print(f"Top kernel.call names:")
    for n, c in summary.most_common(40):
        print(f"  {c:5d}  {n}")
    # Save full timeline.
    with open(os.path.join(OUTDIR, f"canary-worker-tid{candidate_tid}-timeline.csv"), "w") as f:
        f.write("host_ns,tid_event_idx,kind,name,detail\n")
        for ev in evts:
            name = ev["payload"].get("name", "")
            detail = json.dumps(ev["payload"])[:400].replace('"', '""')
            f.write(f'{ev["host_ns"]},{ev["tid_event_idx"]},{ev["kind"]},{name},"{detail}"\n')
    print(f"Wrote canary-worker-tid{candidate_tid}-timeline.csv")