feat(subscribestar): seen/failed ledger models + migration 0054 (#889)
CI / lint (push) Successful in 3s
CI / frontend-build (push) Successful in 21s
CI / backend-lint-and-test (push) Successful in 28s
CI / integration (push) Successful in 3m21s

Phase 1, step 1 of moving SubscribeStar off gallery-dl onto the native core
ingester (milestone: SubscribeStar native). Mirror of the Patreon ledger:
SubscribeStarSeenMedia (skip already-ingested media on routine walks; recovery
bypasses) and SubscribeStarFailedMedia (dead-letter so persistently-failing
media stops re-burning backfill chunks). Per operator decision, dedicated
per-platform tables (not a generalized shared ledger).

filehash is String(128): a CDN content hash when the URL carries one, else a
synthesized <post_id>:<filename> key. UNIQUE (source_id, filehash) upsert key.
Registered in models/__init__; migration 0054 creates both tables (down 0053).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-06-17 10:04:52 -04:00
parent ee1b45f8cc
commit f678819093
4 changed files with 170 additions and 0 deletions
@@ -0,0 +1,82 @@
"""subscribestar_seen_media + subscribestar_failed_media: per-source ledgers
Revision ID: 0054
Revises: 0053
Create Date: 2026-06-17
SubscribeStar native ingester (phase 1 of the gallery-dl → native-core
migration). Mirrors the Patreon ledger tables (0037/0038): a seen-ledger so
routine walks skip already-ingested media (recovery bypasses it) and a
dead-letter ledger so persistently-failing media stops re-burning backfill
chunks. `filehash` is a CDN content hash when present, else a synthesized
``<post_id>:<filename>`` key — hence String(128). UNIQUE (source_id, filehash)
is the upsert key on each.
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
revision: str = "0054"
down_revision: Union[str, None] = "0053"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
op.create_table(
"subscribestar_seen_media",
sa.Column("id", sa.Integer, primary_key=True),
sa.Column(
"source_id",
sa.Integer,
sa.ForeignKey("source.id", ondelete="CASCADE"),
nullable=False,
index=True,
),
sa.Column("filehash", sa.String(128), nullable=False),
sa.Column("post_id", sa.String(64), nullable=True),
sa.Column(
"seen_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.text("NOW()"),
),
sa.UniqueConstraint(
"source_id", "filehash", name="uq_subscribestar_seen_media_source_id"
),
)
op.create_table(
"subscribestar_failed_media",
sa.Column("id", sa.Integer, primary_key=True),
sa.Column(
"source_id",
sa.Integer,
sa.ForeignKey("source.id", ondelete="CASCADE"),
nullable=False,
index=True,
),
sa.Column("filehash", sa.String(128), nullable=False),
sa.Column("attempts", sa.Integer, nullable=False, server_default="1"),
sa.Column("last_error", sa.Text, nullable=True),
sa.Column(
"first_failed_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.text("NOW()"),
),
sa.Column(
"last_failed_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.text("NOW()"),
),
sa.UniqueConstraint(
"source_id", "filehash", name="uq_subscribestar_failed_media_source_id"
),
)
def downgrade() -> None:
op.drop_table("subscribestar_failed_media")
op.drop_table("subscribestar_seen_media")
+4
View File
@@ -24,6 +24,8 @@ from .series_chapter import SeriesChapter
from .series_page import SeriesPage
from .series_suggestion import SeriesSuggestion
from .source import Source
from .subscribestar_failed_media import SubscribeStarFailedMedia
from .subscribestar_seen_media import SubscribeStarSeenMedia
from .tag import Tag, TagKind, image_tag
from .tag_alias import TagAlias
from .tag_allowlist import TagAllowlist
@@ -41,6 +43,8 @@ __all__ = [
"Credential",
"PatreonFailedMedia",
"PatreonSeenMedia",
"SubscribeStarFailedMedia",
"SubscribeStarSeenMedia",
"Post",
"PostAttachment",
"SeriesChapter",
@@ -0,0 +1,44 @@
"""SubscribeStarFailedMedia — per-source dead-letter ledger of SubscribeStar
media that keeps failing to download/validate.
Mirror of PatreonFailedMedia. Media that fails every walk (404'd CDN URL,
deleted post, persistently-corrupt bytes) would otherwise re-error forever and
re-burn backfill chunks. After ``attempts`` reaches the dead-letter threshold
the ingester skips it on routine tick/backfill walks (recovery still
re-attempts). A later clean download clears the row.
`filehash` is the same per-media key the seen-ledger uses (CDN content hash or a
synthesized ``<post_id>:<filename>`` key) — hence String(128). UNIQUE
(source_id, filehash) is the upsert key.
"""
from datetime import datetime
from sqlalchemy import ForeignKey, Integer, String, Text, UniqueConstraint, func
from sqlalchemy.orm import Mapped, mapped_column
from sqlalchemy.types import DateTime
from .base import Base
class SubscribeStarFailedMedia(Base):
__tablename__ = "subscribestar_failed_media"
__table_args__ = (
UniqueConstraint(
"source_id", "filehash", name="uq_subscribestar_failed_media_source_id"
),
)
id: Mapped[int] = mapped_column(Integer, primary_key=True)
source_id: Mapped[int] = mapped_column(
ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
)
filehash: Mapped[str] = mapped_column(String(128), nullable=False)
attempts: Mapped[int] = mapped_column(Integer, nullable=False, default=1)
last_error: Mapped[str | None] = mapped_column(Text, nullable=True)
first_failed_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, server_default=func.now()
)
last_failed_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, server_default=func.now()
)
@@ -0,0 +1,40 @@
"""SubscribeStarSeenMedia — per-source ledger of SubscribeStar media already
downloaded+processed.
Mirror of PatreonSeenMedia for the SubscribeStar native ingester (replacing
gallery-dl). One queryable row per (source, media) so routine walks skip media
we've already ingested; recovery mode bypasses the ledger to re-walk.
`filehash` is a CDN content hash when the media URL carries one, else a
synthesized ``<post_id>:<filename>`` key (SubscribeStar URLs aren't always
content-addressed) — hence String(128) rather than 32.
"""
from datetime import datetime
from sqlalchemy import ForeignKey, Integer, String, UniqueConstraint, func
from sqlalchemy.orm import Mapped, mapped_column
from sqlalchemy.types import DateTime
from .base import Base
class SubscribeStarSeenMedia(Base):
__tablename__ = "subscribestar_seen_media"
__table_args__ = (
# Dedup key the downloader upserts against: one ledger row per
# (source, media). A second sighting of the same media is a no-op.
UniqueConstraint(
"source_id", "filehash", name="uq_subscribestar_seen_media_source_id"
),
)
id: Mapped[int] = mapped_column(Integer, primary_key=True)
source_id: Mapped[int] = mapped_column(
ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
)
filehash: Mapped[str] = mapped_column(String(128), nullable=False)
post_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
seen_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, server_default=func.now()
)