from django.conf import settings from django.db import models class Feed(models.Model): """A single polled RSS/Atom source, shared across every subscriber. One row per feed_url regardless of how many users subscribe to it — the fetch pipeline polls each feed exactly once and every Subscription below just points at the same Feed/Article data. Never add per-user fetching. """ STATUS_PENDING = "pending" STATUS_OK = "ok" STATUS_NOT_MODIFIED = "not_modified" STATUS_ERROR = "error" STATUS_CHOICES = [ (STATUS_PENDING, "Pending"), (STATUS_OK, "OK"), (STATUS_NOT_MODIFIED, "Not modified"), (STATUS_ERROR, "Error"), ] feed_url = models.URLField(max_length=1000, unique=True) site_url = models.URLField(max_length=1000, blank=True) title = models.CharField(max_length=500, blank=True) favicon_url = models.URLField(max_length=1000, blank=True) etag = models.CharField(max_length=255, blank=True) last_modified = models.CharField(max_length=255, blank=True) last_fetched_at = models.DateTimeField(null=True, blank=True) last_fetch_status = models.CharField( max_length=20, choices=STATUS_CHOICES, default=STATUS_PENDING ) last_error_message = models.TextField(blank=True) # The poll interval itself is site-wide now (apps.core.models. # SiteSettings), not per-feed — only the error-driven backoff on top # of it still varies per feed (see apps.feeds.services.fetcher. # effective_interval_minutes). fetch_error_count = models.PositiveIntegerField(default=0) is_active = models.BooleanField(default=True) # Set by fetch_feed right after every fetch attempt (success or error) # to last_fetched_at + effective_interval_minutes — precomputed once, # at write time, instead of poll_due_feeds re-deriving due-ness (which # depends on fetch_error_count's exponential backoff) for every active # feed on every tick (C1). NULL means "due now", same as a feed that's # never been fetched. Indexed with is_active below so the scheduler's # query is a direct index range scan, not a full table scan. next_fetch_at = models.DateTimeField(null=True, blank=True) # Set by poll_due_feeds' atomic claim (an UPDATE ... WHERE clause, not # select_for_update — Celery Beat and fetch_feed run in separate # transactions) and cleared once fetch_feed finishes, so overlapping # beat ticks or a fetch that runs long can't both dispatch the same # feed. A claim older than CLAIM_STALE_MINUTES (tasks.py) is treated as # abandoned and can be reclaimed, so a worker dying mid-fetch doesn't # wedge the feed forever. claimed_at = models.DateTimeField(null=True, blank=True) created_at = models.DateTimeField(auto_now_add=True) class Meta: indexes = [models.Index(fields=["is_active", "next_fetch_at"])] def __str__(self): return self.title or self.feed_url class Subscription(models.Model): """Per-user join between a User and a shared Feed.""" user = models.ForeignKey( settings.AUTH_USER_MODEL, on_delete=models.CASCADE, related_name="subscriptions" ) feed = models.ForeignKey(Feed, on_delete=models.CASCADE, related_name="subscriptions") custom_title = models.CharField(max_length=500, blank=True) order = models.PositiveIntegerField(default=0) created_at = models.DateTimeField(auto_now_add=True) class Meta: unique_together = [("user", "feed")] ordering = ["order", "id"] def __str__(self): return self.custom_title or self.feed.title or self.feed.feed_url @property def display_title(self): return self.custom_title or self.feed.title or self.feed.feed_url