refactor: unify data preparations and research input snapshots
Deploy production / deploy (push) Successful in 53s

This commit is contained in:
yuxuanhui
2026-09-12 01:24:02 +08:00
parent 849f86fef7
commit 394438e753
82 changed files with 4146 additions and 2076 deletions
+31 -9
View File
@@ -340,7 +340,9 @@ class CatalogScope(Base):
class CatalogBatch(Base):
__tablename__ = "catalog_batches"
id: Mapped[str] = mapped_column(ForeignKey("sync_jobs.id"), primary_key=True)
id: Mapped[str] = mapped_column(String(36), primary_key=True)
job_id: Mapped[str] = mapped_column(ForeignKey("sync_jobs.id"), index=True)
offset: Mapped[int] = mapped_column(Integer, default=0)
scope_key: Mapped[str] = mapped_column(ForeignKey("catalog_scopes.key"), index=True)
dataset_id: Mapped[str | None] = mapped_column(String(200))
complete: Mapped[bool] = mapped_column(Boolean, default=False)
@@ -386,16 +388,36 @@ class CatalogNote(Base):
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=now)
class TemplateInput(Base):
__tablename__ = "template_inputs"
class DataPreparation(Base):
"""Editable collection; scope never changes after creation."""
__tablename__ = "data_preparations"
id: Mapped[str] = mapped_column(String(36), primary_key=True)
scope_key: Mapped[str] = mapped_column(ForeignKey("catalog_scopes.key"), index=True)
dataset_id: Mapped[str] = mapped_column(String(200))
collection_version: Mapped[str] = mapped_column(ForeignKey("catalog_batches.id"))
selection: Mapped[str] = mapped_column(String(20))
field_ids: Mapped[list] = mapped_column(JSON)
field_types: Mapped[dict] = mapped_column(JSON)
name: Mapped[str] = mapped_column(String(200))
note: Mapped[str] = mapped_column(Text, default="")
scope_key: Mapped[str] = mapped_column(String(200), index=True)
scope: Mapped[dict] = mapped_column(JSON)
version: Mapped[int] = mapped_column(Integer, default=1)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=now)
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=now)
class PreparationField(Base):
__tablename__ = "preparation_fields"
preparation_id: Mapped[str] = mapped_column(ForeignKey("data_preparations.id", ondelete="CASCADE"), primary_key=True)
field_id: Mapped[str] = mapped_column(String(200), primary_key=True)
dataset_id: Mapped[str] = mapped_column(String(200), index=True)
content: Mapped[dict] = mapped_column(JSON)
class ResearchInputSnapshot(Base):
"""Self-contained research input: deletion of its preparation cannot invalidate it."""
__tablename__ = "research_input_snapshots"
id: Mapped[str] = mapped_column(String(36), primary_key=True)
preparation_id: Mapped[str] = mapped_column(String(36), index=True)
preparation_version: Mapped[int] = mapped_column(Integer)
content: Mapped[dict] = mapped_column(JSON)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=now)
__table_args__ = (UniqueConstraint("preparation_id", "preparation_version"),)
class CatalogResource(Base):