#!/usr/bin/env python3
"""Run Clang/GCC owner hashes at W1/W8/W12 and compare with b96dd73."""
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/l130/hashes"
BASELINE = json.loads((ROOT / "Saved/Linux/l125/hashes/summary.json").read_text())
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 = {
    "clang": ROOT / "Saved/Linux/l130/bin/VoxelForgeCoreHeadless-l130-clang",
    "gcc": ROOT / "Saved/Linux/l130/bin/VoxelForgeCoreHeadless-l130-gcc",
}
HASH_RE = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)
STAMP_RE = 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_RE.findall(output)
    if result.returncode or len(hashes) != 12:
        raise SystemExit(f"hash run failed: {label}; exit={result.returncode} "
                         f"hashes={len(hashes)} log={log}")
    stamp = STAMP_RE.search(output)
    row = {"dataset": dataset, "recipe": recipe, "workers": workers,
        "compiler": compiler, "exit_code": result.returncode, "hashes": hashes,
        "source_stamp": stamp.group(1) if stamp else None,
        "elapsed_s": round(time.monotonic() - started, 3),
        "log": str(log.relative_to(ROOT))}
    print("[L130HashRun] " + 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 L130 hash input")
    old = {(row["dataset"], row["recipe"], row["workers"], row["compiler"]): row
           for row in BASELINE["runs"]}
    rows = []
    for dataset, recipes in RECIPES.items():
        for recipe in 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, recipes in RECIPES.items():
        for recipe in recipes:
            group = [row for row in rows if row["dataset"] == dataset
                     and row["recipe"] == recipe]
            key = f"{dataset}/{recipe}"
            stable = all(row["hashes"] == group[0]["hashes"] for row in group)
            baseline = old[(dataset, recipe, 12, "clang")]["hashes"]
            changed = [i for i, (before, after) in enumerate(zip(baseline,
                group[0]["hashes"])) if before != after]
            groups[key] = {"all_workers_and_compilers_match": stable,
                "matches_b96dd73_v225": not changed,
                "changed_hash_rows_from_v225": changed,
                "source_stamps": sorted({row["source_stamp"] for row in group})}
            if not stable:
                raise SystemExit(f"worker/compiler hash mismatch: {key}")
    (OUT / "summary.json").write_text(
        json.dumps({"baseline_source": "b96dd73", "runs": rows,
                    "groups": groups}, indent=2) + "\n", encoding="utf-8")
    print("[L130HashSummary] " + json.dumps(groups, sort_keys=True), flush=True)
    return 0


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