bvandeusen/FabledCurator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 33 Wiki Activity
Files
a3bc98a53c32f3b546f6017716d26dedc44d0e07
FabledCurator/alembic/versions/0001_initial_unified_schema.py
T
bvandeusen d6a156dcd2 feat: define unified schema (Artist, Source, Post, ImageRecord, etc.) and initial migration 
Implements the data model from spec §3 in one go so FC-2/FC-3 don't need
schema-adding migrations of their own. Artist is the unified entity for
both gallery 'artist:' tags and GallerySubscriber Subscriptions
(is_subscription flag). ImageProvenance is many-to-one, enabling the
enrich-on-duplicate rule for downloaded content that pHash-matches an
existing record.

The SigLIP embedding column uses pgvector(1152) for SigLIP-so400m;
swapping models in FC-2 will require a column-width migration.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 07:34:29 -04:00

278 lines
11 KiB
Python
Raw Blame History

"""initial unified schema
Revision ID: 0001
Revises:
Create Date: 2026-05-13
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
from pgvector.sqlalchemy import Vector
revision: str = "0001"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
op.execute("CREATE EXTENSION IF NOT EXISTS vector")
op.create_table(
"artist",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("name", sa.String(length=255), nullable=False),
sa.Column("slug", sa.String(length=255), nullable=False),
sa.Column("notes", sa.Text(), nullable=True),
sa.Column("is_subscription", sa.Boolean(), nullable=False, server_default=sa.false()),
sa.Column("auto_check", sa.Boolean(), nullable=False, server_default=sa.true()),
sa.Column("check_interval_seconds", sa.Integer(), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.PrimaryKeyConstraint("id", name="pk_artist"),
sa.UniqueConstraint("name", name="uq_artist_name"),
sa.UniqueConstraint("slug", name="uq_artist_slug"),
)
op.create_table(
"source",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("artist_id", sa.Integer(), nullable=False),
sa.Column("platform", sa.String(length=64), nullable=False),
sa.Column("url", sa.Text(), nullable=False),
sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
sa.Column("config_overrides", sa.JSON(), nullable=True),
sa.Column("last_checked_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("last_error", sa.Text(), nullable=True),
sa.Column("check_interval_override", sa.Integer(), nullable=True),
sa.ForeignKeyConstraint(
["artist_id"], ["artist.id"], name="fk_source_artist_id_artist", ondelete="CASCADE"
),
sa.PrimaryKeyConstraint("id", name="pk_source"),
)
op.create_index("ix_source_artist_id", "source", ["artist_id"])
op.create_table(
"credential",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("platform", sa.String(length=64), nullable=False),
sa.Column("kind", sa.String(length=32), nullable=False),
sa.Column("encrypted_blob", sa.LargeBinary(), nullable=False),
sa.Column("status", sa.String(length=32), nullable=False, server_default="active"),
sa.Column(
"captured_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("expires_at", sa.DateTime(timezone=True), nullable=True),
sa.PrimaryKeyConstraint("id", name="pk_credential"),
sa.UniqueConstraint("platform", name="uq_credential_platform"),
)
op.create_table(
"post",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("source_id", sa.Integer(), nullable=False),
sa.Column("external_post_id", sa.String(length=128), nullable=False),
sa.Column("post_url", sa.Text(), nullable=True),
sa.Column("post_title", sa.Text(), nullable=True),
sa.Column("post_date", sa.DateTime(timezone=True), nullable=True),
sa.Column("raw_metadata", sa.JSON(), nullable=True),
sa.Column(
"downloaded_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["source_id"], ["source.id"], name="fk_post_source_id_source", ondelete="CASCADE"
),
sa.PrimaryKeyConstraint("id", name="pk_post"),
sa.UniqueConstraint("source_id", "external_post_id", name="uq_post_source_external_id"),
)
op.create_index("ix_post_source_id", "post", ["source_id"])
op.create_table(
"image_record",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("path", sa.Text(), nullable=False),
sa.Column("sha256", sa.String(length=64), nullable=False),
sa.Column("phash", sa.String(length=32), nullable=True),
sa.Column("size_bytes", sa.BigInteger(), nullable=False),
sa.Column("mime", sa.String(length=64), nullable=False),
sa.Column("width", sa.Integer(), nullable=True),
sa.Column("height", sa.Integer(), nullable=True),
sa.Column("thumbnail_path", sa.Text(), nullable=True),
sa.Column(
"origin",
sa.Enum(
"downloaded",
"imported_filesystem",
"uploaded",
name="origin_enum",
),
nullable=False,
),
sa.Column("primary_post_id", sa.Integer(), nullable=True),
sa.Column("wd14_predictions", sa.JSON(), nullable=True),
sa.Column("wd14_model_version", sa.String(length=128), nullable=True),
sa.Column("siglip_embedding", Vector(1152), nullable=True),
sa.Column("siglip_model_version", sa.String(length=128), nullable=True),
sa.Column("centroid_scores", sa.JSON(), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["primary_post_id"],
["post.id"],
name="fk_image_record_primary_post_id_post",
ondelete="SET NULL",
),
sa.PrimaryKeyConstraint("id", name="pk_image_record"),
sa.UniqueConstraint("path", name="uq_image_record_path"),
sa.UniqueConstraint("sha256", name="uq_image_record_sha256"),
)
op.create_index("ix_image_record_sha256", "image_record", ["sha256"])
op.create_index("ix_image_record_phash", "image_record", ["phash"])
op.create_index("ix_image_record_primary_post_id", "image_record", ["primary_post_id"])
op.create_table(
"image_provenance",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("image_record_id", sa.Integer(), nullable=False),
sa.Column("post_id", sa.Integer(), nullable=False),
sa.Column("source_id", sa.Integer(), nullable=False),
sa.Column("captured_metadata", sa.JSON(), nullable=True),
sa.Column(
"captured_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["image_record_id"],
["image_record.id"],
name="fk_image_provenance_image_record_id_image_record",
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["post_id"],
["post.id"],
name="fk_image_provenance_post_id_post",
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["source_id"],
["source.id"],
name="fk_image_provenance_source_id_source",
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name="pk_image_provenance"),
)
op.create_index("ix_image_provenance_image_record_id", "image_provenance", ["image_record_id"])
op.create_index("ix_image_provenance_post_id", "image_provenance", ["post_id"])
op.create_index("ix_image_provenance_source_id", "image_provenance", ["source_id"])
op.create_table(
"tag",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("name", sa.String(length=255), nullable=False),
sa.Column("namespace", sa.String(length=64), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.PrimaryKeyConstraint("id", name="pk_tag"),
sa.UniqueConstraint("name", name="uq_tag_name"),
)
op.create_index("ix_tag_name", "tag", ["name"])
op.create_index("ix_tag_namespace", "tag", ["namespace"])
op.create_table(
"image_tag",
sa.Column("image_record_id", sa.Integer(), nullable=False),
sa.Column("tag_id", sa.Integer(), nullable=False),
sa.Column("source", sa.String(length=32), nullable=False, server_default="manual"),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["image_record_id"],
["image_record.id"],
name="fk_image_tag_image_record_id_image_record",
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["tag_id"], ["tag.id"], name="fk_image_tag_tag_id_tag", ondelete="CASCADE"
),
sa.PrimaryKeyConstraint("image_record_id", "tag_id", name="pk_image_tag"),
)
op.create_table(
"download_event",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("source_id", sa.Integer(), nullable=False),
sa.Column("post_id", sa.Integer(), nullable=True),
sa.Column("status", sa.String(length=32), nullable=False),
sa.Column(
"started_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("bytes_downloaded", sa.BigInteger(), nullable=False, server_default="0"),
sa.Column("files_count", sa.Integer(), nullable=False, server_default="0"),
sa.Column("error", sa.Text(), nullable=True),
sa.ForeignKeyConstraint(
["source_id"],
["source.id"],
name="fk_download_event_source_id_source",
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["post_id"],
["post.id"],
name="fk_download_event_post_id_post",
ondelete="SET NULL",
),
sa.PrimaryKeyConstraint("id", name="pk_download_event"),
)
op.create_index("ix_download_event_source_id", "download_event", ["source_id"])
op.create_index("ix_download_event_post_id", "download_event", ["post_id"])
def downgrade() -> None:
op.drop_table("download_event")
op.drop_table("image_tag")
op.drop_table("tag")
op.drop_table("image_provenance")
op.drop_table("image_record")
op.execute("DROP TYPE IF EXISTS origin_enum")
op.drop_table("post")
op.drop_table("credential")
op.drop_table("source")
op.drop_table("artist")
op.execute("DROP EXTENSION IF EXISTS vector")
Reference in New Issue View Git Blame Copy Permalink