41 lines
1.2 KiB
Python
41 lines
1.2 KiB
Python
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import time
|
|
from collections import OrderedDict
|
|
|
|
|
|
class EmailDeduplicator:
|
|
def __init__(self, max_entries: int = 100_000, ttl_seconds: int = 259200):
|
|
self._seen: OrderedDict[str, float] = OrderedDict()
|
|
self._max_entries = max_entries
|
|
self._ttl = ttl_seconds
|
|
|
|
def is_duplicate(self, message_id: str, uid: str = "") -> bool:
|
|
key = self._make_key(message_id, uid)
|
|
self._expire()
|
|
return key in self._seen
|
|
|
|
def mark(self, message_id: str, uid: str = ""):
|
|
key = self._make_key(message_id, uid)
|
|
self._expire()
|
|
self._seen[key] = time.monotonic()
|
|
if len(self._seen) > self._max_entries:
|
|
self._seen.popitem(last=False)
|
|
|
|
def _make_key(self, message_id: str, uid: str) -> str:
|
|
raw = f"{message_id}|{uid}".strip().lower()
|
|
return hashlib.sha256(raw.encode()).hexdigest()[:32]
|
|
|
|
def _expire(self):
|
|
now = time.monotonic()
|
|
while self._seen:
|
|
key, ts = next(iter(self._seen.items()))
|
|
if now - ts > self._ttl:
|
|
self._seen.popitem(last=False)
|
|
else:
|
|
break
|
|
|
|
def handle_uidvalidity_change(self):
|
|
self._seen.clear()
|