#!/usr/bin/env python3
"""Compare 18 canonical owner4/owner2 hashes with the pre-cleanup L130 binary."""
from __future__ import annotations

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

ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / "Saved/Linux/l131/canonical-matrix"
DATASETS = {
    "owner4": ROOT / "Standalone/data/owner_world.json",
    "owner2": ROOT / "Standalone/data/regression/owner_world_2strate_l61.json",
}
RECIPES = {"owner4": ("surface-world",), "owner2": ("surface-world", "floating-islands")}
BINARIES = {
    "base": ROOT / "Saved/Linux/l130/bin/VoxelForgeCoreHeadless-l130-{compiler}",
    "l131": ROOT / "Saved/Linux/l131/bin/VoxelForgeCoreHeadless-l131-{compiler}",
}
HASH_RE = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)


def run(dataset: str, recipe: str, compiler: str, workers: int, version: str) -> tuple[list[str], float]:
    binary = Path(str(BINARIES[version]).format(compiler=compiler))
    label = f"{dataset}-{recipe}-{compiler}-w{workers}-{version}"
    log = OUT / f"{label}.log"
    command = ["taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "timeout", "1740s", str(binary), str(DATASETS[dataset]),
        "--world-assembler-prototype", "--stream-benchmark", "--stream-pipeline",
        "--force-generate", f"--workers={workers}", "--clip-radius=3",
        "--max-clip-level=8", "--max-level=8", f"--recipe={recipe}", "--stream-hash"]
    started = time.monotonic()
    with log.open("w", encoding="utf-8") as stream:
        process = subprocess.run(command, cwd=ROOT, stdout=stream,
            stderr=subprocess.STDOUT, check=False, timeout=1740)
    hashes = HASH_RE.findall(log.read_text(encoding="utf-8", errors="replace"))
    if process.returncode or len(hashes) != 12:
        raise RuntimeError(f"hash run failed: {log}; exit={process.returncode}; rows={len(hashes)}")
    return hashes, time.monotonic() - started


def main() -> int:
    OUT.mkdir(parents=True, exist_ok=True)
    rows = []
    groups = {}
    for dataset, recipes in RECIPES.items():
        for recipe in recipes:
            signatures = []
            for workers in (1, 8, 12):
                for compiler in ("clang", "gcc"):
                    before, before_s = run(dataset, recipe, compiler, workers, "base")
                    after, after_s = run(dataset, recipe, compiler, workers, "l131")
                    row = {"dataset": dataset, "recipe": recipe, "compiler": compiler,
                        "workers": workers, "hash_mismatches": sum(a != b for a, b in zip(before, after)),
                        "rows": len(after), "base_s": round(before_s, 3), "l131_s": round(after_s, 3),
                        "base_log": f"Saved/Linux/l131/canonical-matrix/{dataset}-{recipe}-{compiler}-w{workers}-base.log",
                        "l131_log": f"Saved/Linux/l131/canonical-matrix/{dataset}-{recipe}-{compiler}-w{workers}-l131.log"}
                    rows.append(row)
                    signatures.append((compiler, workers, after))
                    print("[L131CanonicalHash] " + json.dumps(row, sort_keys=True), flush=True)
                    (OUT / "runs-partial.json").write_text(json.dumps(rows, indent=2) + "\n")
            first = signatures[0][2]
            stable = all(sig == first for _, _, sig in signatures)
            groups[f"{dataset}/{recipe}"] = {"base_equals_l131": all(row["hash_mismatches"] == 0 for row in rows if row["dataset"] == dataset and row["recipe"] == recipe),
                "all_clang_gcc_workers_agree": stable}
    failures = [row for row in rows if row["hash_mismatches"]]
    (OUT / "summary.json").write_text(json.dumps({"runs": rows, "groups": groups,
        "passed": len(rows)-len(failures), "failed": len(failures)}, indent=2) + "\n")
    return 1 if failures or not all(group["all_clang_gcc_workers_agree"] for group in groups.values()) else 0


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