#!/usr/bin/env python3
"""Compare L118 owner4 hashes to L115 at W1/W8/W12 under Clang and GCC."""
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/l118/hashes"
DATA = ROOT / "Standalone/data/owner_world.json"
BASELINE = ROOT / "Saved/Linux/l115/hashes/summary.json"
BINARIES = {
    "clang": ROOT / "Saved/Linux/l118/bin/VoxelForgeCoreHeadless-l118-clang",
    "gcc": ROOT / "Saved/Linux/l118/bin/VoxelForgeCoreHeadless-l118-gcc",
}
HASH = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)
STAMP = re.compile(r"^\[VoxelForgeSourceStamp\] sha256=(\S+)$", re.M)


def run(workers: int, compiler: str) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    label = f"owner4-w{workers}-{compiler}"
    log = OUT / f"{label}.log"
    layout = OUT / f"{label}.layout.json"
    command = [
        "taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "timeout", "1740s", str(BINARIES[compiler]), str(DATA),
        "--workers=" + str(workers), "--world-assembler-prototype", "--stream-benchmark",
        "--stream-pipeline", "--force-generate", "--clip-radius=3",
        "--max-clip-level=8", "--max-level=8", "--stream-hash",
        f"--resolved-layout-output={layout}",
    ]
    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)
    content = log.read_text(encoding="utf-8", errors="replace")
    hashes = HASH.findall(content)
    if result.returncode or len(hashes) != 12:
        raise SystemExit(f"hash run failed or incomplete: {label}; exit={result.returncode} "
                         f"hashes={len(hashes)} log={log}")
    row = {"workers": workers, "compiler": compiler, "exit_code": result.returncode,
           "hashes": hashes,
           "source_stamp": (STAMP.search(content).group(1) if STAMP.search(content) else None),
           "elapsed_s": round(time.monotonic() - started, 3),
           "log": str(log.relative_to(ROOT))}
    print("[L118HashRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def main() -> int:
    if not DATA.is_file() or not BASELINE.is_file() or any(not path.is_file()
                                                           for path in BINARIES.values()):
        raise SystemExit("missing L118 hash input or L115 reference")
    reference = json.loads(BASELINE.read_text(encoding="utf-8"))["runs"]
    reference = [row for row in reference if row["dataset"] == "owner4"
                 and row["recipe"] == "surface-world"]
    rows = [run(workers, compiler) for workers in (1, 8, 12)
            for compiler in ("clang", "gcc")]
    comparisons = []
    for row in rows:
        matches = [old for old in reference if old["workers"] == row["workers"]
                   and old["compiler"] == row["compiler"]]
        if len(matches) != 1:
            raise SystemExit(f"expected one L115 reference for W{row['workers']}/{row['compiler']}")
        match = row["hashes"] == matches[0]["hashes"]
        comparisons.append({"workers": row["workers"], "compiler": row["compiler"],
                            "matches_l115": match, "l115_log": matches[0]["log"],
                            "l118_log": row["log"]})
        if not match:
            raise SystemExit(f"L118 hash mismatch versus L115 at W{row['workers']}/{row['compiler']}")
    summary = {"runs": rows, "comparisons": comparisons,
               "l115_hashes_identical": len({tuple(r["hashes"]) for r in reference}) == 1,
               "candidate_matches_l115_all_workers_and_compilers": True}
    (OUT / "summary.json").write_text(json.dumps(summary, indent=2) + "\n",
                                      encoding="utf-8")
    return 0


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