#!/usr/bin/env python3
"""Compare per-tile passage candidate-list sizes for L109 and L112."""
from __future__ import annotations

import json
import math
import re
import statistics
import subprocess
import time
from pathlib import Path

ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / "Saved/Linux/l112/candidate-lists"
DATA = ROOT / "Standalone/data/owner_world.json"
BINARIES = {
    "L109": ROOT / "Saved/Linux/l109/bin-final/VoxelForgeCoreHeadless-l109-clang",
    "L112": ROOT / "Saved/Linux/l112/bin-clang/VoxelForgeCoreHeadless-l112-clang",
}
CAMERAS = {
    0: (8.0, 16.0, -372.2626953125),
    1: (25.8369140625, 3.19921875, -737.0),
    2: (19.166015625, -14.2001953125, -753.3740234375),
    3: (-20.0625, -5.068359375, -900.353515625),
}
LIST = re.compile(r"^\[PassageComposerTile\].*?features=(\d+) route_candidates=(\d+)", re.M)


def percentile(values: list[int], fraction: float) -> int:
    ordered = sorted(values)
    if not ordered:
        return 0
    return ordered[min(len(ordered) - 1,
                       max(0, math.ceil(fraction * len(ordered)) - 1))]


def run(strate: int, version: str) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    log = OUT / f"{version}-s{strate}.log"
    camera = ",".join(f"{v:.12f}" for v in CAMERAS[strate]) + ",0,0"
    command = [
        "taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "timeout", "1740s", str(BINARIES[version]), str(DATA),
        "--world-assembler-prototype", "--stream-benchmark", "--stream-pipeline",
        "--workers=12", "--clip-radius=3", "--max-clip-level=8", "--max-level=8",
        f"--camera={camera}", "--profile-passage-composer", "--stream-scheduler-policy=3",
    ]
    started = time.monotonic()
    with log.open("w", encoding="utf-8") as stream:
        result = subprocess.run(command, cwd=ROOT, stdout=stream,
                                stderr=subprocess.STDOUT, check=False, timeout=1740)
    output = log.read_text(encoding="utf-8", errors="replace")
    features = [int(row[0]) for row in LIST.findall(output)]
    routes = [int(row[1]) for row in LIST.findall(output)]
    if result.returncode or not features:
        raise SystemExit(f"candidate-list profile missing: {log}; exit={result.returncode}")
    row = {
        "strate": strate, "version": version, "profiled_tiles": len(features),
        "feature_candidates": {"sum": sum(features), "min": min(features),
            "median": statistics.median(features), "p95": percentile(features, .95),
            "max": max(features)},
        "route_segment_candidates": {"sum": sum(routes), "min": min(routes),
            "median": statistics.median(routes), "p95": percentile(routes, .95),
            "max": max(routes)},
        "elapsed_s": round(time.monotonic() - started, 3),
        "log": str(log.relative_to(ROOT)),
    }
    print("[L112CandidateLists] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def main() -> int:
    if any(not path.is_file() for path in (*BINARIES.values(), DATA)):
        raise SystemExit("missing L109/L112 candidate-list input")
    rows = [run(strate, version) for strate in range(4)
            for version in ("L109", "L112")]
    (OUT / "summary.json").write_text(json.dumps(rows, indent=2) + "\n",
                                      encoding="utf-8")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())