Initialize governed Dataflow module

src/govoplan_dataflow/backend/db/models.py

@@ -0,0 +1,114 @@
+from __future__ import annotations
+
+import uuid
+from datetime import datetime
+from typing import Any
+
+from sqlalchemy import DateTime, ForeignKey, Index, Integer, JSON, String, Text, UniqueConstraint
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from govoplan_core.db.base import Base, TimestampMixin
+
+
+def new_uuid() -> str:
+    return str(uuid.uuid4())
+
+
+class DataflowPipeline(Base, TimestampMixin):
+    __tablename__ = "dataflow_pipelines"
+    __table_args__ = (
+        Index("ix_dataflow_pipelines_tenant_status", "tenant_id", "status"),
+        Index("ix_dataflow_pipelines_tenant_updated", "tenant_id", "updated_at"),
+    )
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
+    tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
+    name: Mapped[str] = mapped_column(String(300), nullable=False)
+    description: Mapped[str | None] = mapped_column(Text)
+    status: Mapped[str] = mapped_column(String(32), default="draft", nullable=False, index=True)
+    current_revision: Mapped[int] = mapped_column(Integer, default=1, nullable=False)
+    created_by: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
+    updated_by: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
+    deleted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True, index=True)
+    metadata_: Mapped[dict[str, Any]] = mapped_column("metadata", JSON, default=dict, nullable=False)
+
+    revisions: Mapped[list["DataflowPipelineRevision"]] = relationship(
+        back_populates="pipeline",
+        cascade="all, delete-orphan",
+        order_by="DataflowPipelineRevision.revision",
+    )
+    runs: Mapped[list["DataflowRun"]] = relationship(
+        back_populates="pipeline",
+        cascade="all, delete-orphan",
+        order_by="DataflowRun.created_at",
+    )
+
+
+class DataflowPipelineRevision(Base, TimestampMixin):
+    __tablename__ = "dataflow_pipeline_revisions"
+    __table_args__ = (
+        UniqueConstraint("pipeline_id", "revision", name="uq_dataflow_pipeline_revision"),
+        Index("ix_dataflow_revisions_tenant_pipeline", "tenant_id", "pipeline_id"),
+        Index("ix_dataflow_revisions_content_hash", "tenant_id", "content_hash"),
+    )
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
+    tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
+    pipeline_id: Mapped[str] = mapped_column(
+        ForeignKey("dataflow_pipelines.id", ondelete="CASCADE"),
+        nullable=False,
+        index=True,
+    )
+    revision: Mapped[int] = mapped_column(Integer, nullable=False)
+    schema_version: Mapped[int] = mapped_column(Integer, default=1, nullable=False)
+    graph: Mapped[dict[str, Any]] = mapped_column(JSON, nullable=False)
+    sql_text: Mapped[str | None] = mapped_column(Text)
+    editor_mode: Mapped[str] = mapped_column(String(20), default="graph", nullable=False)
+    content_hash: Mapped[str] = mapped_column(String(64), nullable=False)
+    created_by: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
+
+    pipeline: Mapped[DataflowPipeline] = relationship(back_populates="revisions")
+
+
+class DataflowRun(Base, TimestampMixin):
+    __tablename__ = "dataflow_runs"
+    __table_args__ = (
+        Index("ix_dataflow_runs_tenant_status", "tenant_id", "status"),
+        Index("ix_dataflow_runs_pipeline_created", "pipeline_id", "created_at"),
+    )
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
+    tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
+    pipeline_id: Mapped[str] = mapped_column(
+        ForeignKey("dataflow_pipelines.id", ondelete="CASCADE"),
+        nullable=False,
+        index=True,
+    )
+    pipeline_revision_id: Mapped[str] = mapped_column(
+        ForeignKey("dataflow_pipeline_revisions.id", ondelete="RESTRICT"),
+        nullable=False,
+        index=True,
+    )
+    run_type: Mapped[str] = mapped_column(String(30), default="preview", nullable=False, index=True)
+    status: Mapped[str] = mapped_column(String(30), nullable=False, index=True)
+    executor_version: Mapped[str] = mapped_column(String(40), nullable=False)
+    definition_hash: Mapped[str] = mapped_column(String(64), nullable=False)
+    source_fingerprints: Mapped[list[dict[str, Any]]] = mapped_column(JSON, default=list, nullable=False)
+    result_schema: Mapped[list[dict[str, Any]]] = mapped_column(JSON, default=list, nullable=False)
+    diagnostics: Mapped[list[dict[str, Any]]] = mapped_column(JSON, default=list, nullable=False)
+    input_row_count: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
+    output_row_count: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
+    started_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
+    finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
+    error: Mapped[str | None] = mapped_column(Text)
+    created_by: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
+
+    pipeline: Mapped[DataflowPipeline] = relationship(back_populates="runs")
+
+
+__all__ = [
+    "DataflowPipeline",
+    "DataflowPipelineRevision",
+    "DataflowRun",
+    "new_uuid",
+]