#!/usr/bin/env python3
"""Check Clang/GCC hash identity at W1/W8/W12 and repin v217 owner hashes."""
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/l109/hashes"
DATASETS = {
    "owner4": ROOT / "Standalone/data/owner_world.json",
    "owner2": ROOT / "Standalone/data/regression/owner_world_2strate_l61.json",
}
BINARIES = {
    "clang": ROOT / "Saved/Linux/l109/bin-final/VoxelForgeCoreHeadless-l109-clang",
    "gcc": ROOT / "Saved/Linux/l109/bin-final/VoxelForgeCoreHeadless-l109-gcc",
}
HASH = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)
STAMP = re.compile(r"^\[VoxelForgeSourceStamp\] sha256=(\S+)$", re.M)


def run(dataset: str, recipe: str, workers: int, compiler: str) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    label = f"{dataset}-{recipe}-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(DATASETS[dataset]),
        f"--workers={workers}", "--world-assembler-prototype", "--stream-benchmark",
        "--stream-pipeline", "--force-generate", "--clip-radius=3",
        "--max-clip-level=8", "--max-level=8", f"--recipe={recipe}",
        "--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)
    output = log.read_text(encoding="utf-8", errors="replace")
    hashes = HASH.findall(output)
    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 = {"dataset": dataset, "recipe": recipe, "workers": workers,
           "compiler": compiler, "exit_code": result.returncode,
           "hashes": hashes, "source_stamp": (STAMP.search(output).group(1)
                                                if STAMP.search(output) else None),
           "elapsed_s": round(time.monotonic() - started, 3),
           "log": str(log.relative_to(ROOT))}
    print("[L109HashRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def main() -> int:
    if any(not path.is_file() for path in (*DATASETS.values(), *BINARIES.values())):
        raise SystemExit("missing L109 hash input")
    rows = []
    recipes = {"owner4": ("surface-world",),
               "owner2": ("surface-world", "floating-islands")}
    for dataset, dataset_recipes in recipes.items():
        for recipe in dataset_recipes:
            for workers in (1, 8, 12):
                for compiler in ("clang", "gcc"):
                    rows.append(run(dataset, recipe, workers, compiler))
                    (OUT / "runs-partial.json").write_text(
                        json.dumps(rows, indent=2) + "\n", encoding="utf-8")
    groups = {}
    for dataset, dataset_recipes in recipes.items():
        for recipe in dataset_recipes:
            key = f"{dataset}/{recipe}"
            group = [row for row in rows if row["dataset"] == dataset
                     and row["recipe"] == recipe]
            reference = group[0]["hashes"]
            groups[key] = {"all_worker_compiler_hashes_match": all(
                row["hashes"] == reference for row in group),
                "source_stamps": sorted({row["source_stamp"] for row in group}),
                "runs": [{"workers": row["workers"], "compiler": row["compiler"],
                          "log": row["log"]} for row in group]}
            if not groups[key]["all_worker_compiler_hashes_match"]:
                raise SystemExit(f"determinism mismatch: {key}")
            if dataset == "owner2":
                canonical = next(row for row in group if row["workers"] == 12
                                 and row["compiler"] == "clang")
                recipe_name = "floating-islands" if recipe == "floating-islands" else "surface-world"
                style = 1 if recipe_name == "surface-world" else 2
                baseline = (ROOT / "Standalone/Tools/verify/baselines/owner-hash/canonical"
                            / f"owner-hash-{recipe_name}-style{style}-v217.baseline")
                baseline.write_text("\n".join(canonical["hashes"]) + "\n",
                                    encoding="utf-8")
    summary = {"runs": rows, "groups": groups,
               "owner4_all_four_strata": "owner4/surface-world",
               "owner2_canonical_pins": ["owner2/surface-world",
                                          "owner2/floating-islands"]}
    (OUT / "summary.json").write_text(json.dumps(summary, indent=2) + "\n",
                                      encoding="utf-8")
    return 0


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