bvandeusen
0563b2d750
pixiv_seen_media / pixiv_failed_media mirror the Patreon/SubscribeStar ledgers (keys are always synthesized <illust_id>:p<num> / <illust_id>:ugoira — pximg URLs carry no content hash). PixivIngester wires client/downloader/ ledgers into ingest_core with drift label 'Pixiv app API' and the new body_canary=False opt-out: caption-less pixiv artists are common, so the zero-bodies #862 alarm would false-positive here — the client's response-shape drift checks cover that failure class instead. auth_token joins the uniform adapter constructor (pixiv is the first token-auth native platform). verify_pixiv_credential = one OAuth refresh, no feed walk. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
83 lines
2.7 KiB
Python
83 lines
2.7 KiB
Python
"""pixiv_seen_media + pixiv_failed_media: per-source ledgers
|
|
|
|
Revision ID: 0076
|
|
Revises: 0075
|
|
Create Date: 2026-07-03
|
|
|
|
Pixiv native ingester (milestone #129, gallery-dl → native-core migration).
|
|
Mirrors the Patreon (0037/0038) and SubscribeStar (0054) ledger tables: 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. Pixiv URLs carry no content hash, so `filehash` is always the
|
|
synthesized ``<illust_id>:p<num>`` / ``<illust_id>:ugoira`` key — String(128)
|
|
matches the siblings. 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 = "0076"
|
|
down_revision: Union[str, None] = "0075"
|
|
branch_labels: Union[str, Sequence[str], None] = None
|
|
depends_on: Union[str, Sequence[str], None] = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
op.create_table(
|
|
"pixiv_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_pixiv_seen_media_source_id"
|
|
),
|
|
)
|
|
op.create_table(
|
|
"pixiv_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_pixiv_failed_media_source_id"
|
|
),
|
|
)
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.drop_table("pixiv_failed_media")
|
|
op.drop_table("pixiv_seen_media")
|