source_cache.py

import hashlib
import json
from pathlib import Path


def file_sha256(path: Path) -> str:
    digest = hashlib.sha256()
    with open(path, "rb") as file:
        for chunk in iter(lambda: file.read(1024 * 1024), b""):
            digest.update(chunk)
    return digest.hexdigest()


def file_signature(path: str) -> dict:
    source = Path(path)
    stat = source.stat()
    return {
        "path": str(source.resolve()),
        "size": stat.st_size,
        "mtime_ns": stat.st_mtime_ns,
        "sha256": file_sha256(source),
    }


def read_json(path: Path):
    path = Path(path)
    if not path.exists():
        return None
    try:
        with open(path, "r", encoding="utf-8") as file:
            return json.load(file)
    except (OSError, json.JSONDecodeError):
        return None


def write_json(path: Path, payload: dict) -> None:
    path = Path(path)
    path.parent.mkdir(parents=True, exist_ok=True)
    with open(path, "w", encoding="utf-8") as file:
        json.dump(payload, file, ensure_ascii=False, indent=2)