"""Check historical source manifests against their own recorded commit, not today's checkout."""

import io
from pathlib import Path
import subprocess
import tarfile

ROOT = Path(__file__).resolve().parents[2]


def _require(commit):
    """Missing recorded history is an explicit failure, never a skip or a repin."""
    found = subprocess.run(
        ["git", "-C", str(ROOT), "cat-file", "-e", commit + "^{commit}"],
        capture_output=True,
    )
    if found.returncode:
        raise AssertionError(
            f"Required history missing: commit {commit} is not in this clone; "
            "fetch it instead of repinning or substituting"
        )


def tracked(commit, prefix="src"):
    """Tracked paths under prefix at the recorded commit."""
    _require(commit)
    return set(
        subprocess.check_output(
            ["git", "-C", str(ROOT), "ls-tree", "-r", "--name-only", commit, prefix],
            text=True,
        ).splitlines()
    )


def historical_tree(commit, dest):
    """Extract the tracked tree of the recorded commit into dest."""
    _require(commit)
    archive = subprocess.check_output(
        ["git", "-C", str(ROOT), "archive", "--format=tar", commit]
    )
    dest = Path(dest)
    dest.mkdir(parents=True, exist_ok=True)
    extra = {"filter": "data"} if hasattr(tarfile, "data_filter") else {}
    with tarfile.open(fileobj=io.BytesIO(archive)) as tar:
        tar.extractall(dest, **extra)
    return dest