Spaces:
Sleeping
Sleeping
File size: 1,389 Bytes
9459cd0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | """
Cache layer: avoids re-downloading the same URL twice.
Key = SHA256(url). Cache index kept as a flat JSON file so it survives restarts.
"""
import hashlib
import json
import os
import threading
CACHE_DIR = "cache"
INDEX_PATH = os.path.join(CACHE_DIR, "index.json")
_lock = threading.Lock()
def _url_hash(url: str) -> str:
return hashlib.sha256(url.encode("utf-8")).hexdigest()
def _load_index() -> dict:
if not os.path.exists(INDEX_PATH):
return {}
with open(INDEX_PATH, "r") as f:
return json.load(f)
def _save_index(index: dict):
os.makedirs(CACHE_DIR, exist_ok=True)
tmp = INDEX_PATH + ".tmp"
with open(tmp, "w") as f:
json.dump(index, f, indent=2)
os.replace(tmp, INDEX_PATH) # atomic write, avoids torn reads
def get_cached_path(url: str) -> str | None:
with _lock:
index = _load_index()
entry = index.get(_url_hash(url))
if entry and os.path.exists(entry["path"]):
return entry["path"]
return None
def register_cache(url: str, local_path: str):
with _lock:
index = _load_index()
index[_url_hash(url)] = {"url": url, "path": local_path}
_save_index(index)
def cache_path_for(url: str, ext: str) -> str:
os.makedirs(os.path.join(CACHE_DIR, "files"), exist_ok=True)
return os.path.join(CACHE_DIR, "files", f"{_url_hash(url)}{ext}")
|