nubiv/my-nome/content-hash-cache-pattern

import hashlib
from pathlib import Path
_HASH_CHUNK_SIZE = 65536  # 64KB chunks for large files
def compute_file_hash(path: Path) -> str:
    """SHA-256 of file contents (chunked for large files)."""
    if not path.is_file():
        raise FileNotFoundError(f"File not found: {path}")
    sha256 = hashlib.sha256()
    with open(path, "rb") as f:
        while True:
            chunk = f.read(_HASH_CHUNK_SIZE)
            if not chunk:
                break
            sha256.update(chunk)
    return sha256.hexdigest()

from dataclasses import dataclass
@dataclass(frozen=True, slots=True)
class CacheEntry:
    file_hash: str
    source_path: str
    document: ExtractedDocument  # The cached result

import json
from typing import Any
def write_cache(cache_dir: Path, entry: CacheEntry) -> None:
    cache_dir.mkdir(parents=True, exist_ok=True)
    cache_file = cache_dir / f"{entry.file_hash}.json"
    data = serialize_entry(entry)
    cache_file.write_text(json.dumps(data, ensure_ascii=False), encoding="utf-8")
def read_cache(cache_dir: Path, file_hash: str) -> CacheEntry | None:
    cache_file = cache_dir / f"{file_hash}.json"
    if not cache_file.is_file():
        return None
    try:
        raw = cache_file.read_text(encoding="utf-8")
        data = json.loads(raw)
        return deserialize_entry(data)
    except (json.JSONDecodeError, ValueError, KeyError):
        return None  # Treat corruption as cache miss

def extract_with_cache(
    file_path: Path,
    *,
    cache_enabled: bool = True,
    cache_dir: Path = Path(".cache"),
) -> ExtractedDocument:
    """Service layer: cache check -> extraction -> cache write."""
    if not cache_enabled:
        return extract_text(file_path)  # Pure function, no cache knowledge
    file_hash = compute_file_hash(file_path)
    # Check cache
    cached = read_cache(cache_dir, file_hash)
    if cached is not None:
        logger.info("Cache hit: %s (hash=%s)", file_path.name, file_hash[:12])
        return cached.document
    # Cache miss -> extract -> store
    logger.info("Cache miss: %s (hash=%s)", file_path.name, file_hash[:12])
    doc = extract_text(file_path)
    entry = CacheEntry(file_hash=file_hash, source_path=str(file_path), document=doc)
    write_cache(cache_dir, entry)
    return doc

# BAD: Path-based caching (breaks on file move/rename)
cache = {"/path/to/file.pdf": result}
# BAD: Adding cache logic inside the processing function (SRP violation)
def extract_text(path, *, cache_enabled=False, cache_dir=None):
    if cache_enabled:  # Now this function has two responsibilities
        ...
# BAD: Using dataclasses.asdict() with nested frozen dataclasses
# (can cause issues with complex nested types)
data = dataclasses.asdict(entry)  # Use manual serialization instead