refactor: restructure project layout

app/shared/db/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

app/shared/db/alembic/env.py

@@ -0,0 +1,80 @@
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from app.shared.config import settings
+from app.shared.db.models import Base
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+config.set_main_option("sqlalchemy.url", settings.DATABASE_URI)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

app/shared/db/alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

app/shared/db/alembic/versions/c43a1ddae8b7_add_job_and_artifact_tables.py

@@ -0,0 +1,71 @@
+"""add_job_and_artifact_tables
+
+Revision ID: c43a1ddae8b7
+Revises: 
+Create Date: 2023-01-05 12:00:58.824773
+
+"""
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "c43a1ddae8b7"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "jobs",
+        sa.Column("url", sa.String(length=2048), nullable=True),
+        sa.Column(
+            "status",
+            sa.Enum("Create", "Error", "Success", name="jobstatus"),
+            nullable=False,
+        ),
+        sa.Column("type", sa.Enum("Transcript", name="jobtype"), nullable=False),
+        sa.Column(
+            "created_at",
+            sa.DateTime(),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("updated_at", sa.DateTime(), nullable=True),
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_jobs_id"), "jobs", ["id"], unique=False)
+    op.create_table(
+        "artifacts",
+        sa.Column("job_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("data", sa.JSON(none_as_null=True), nullable=True),
+        sa.Column(
+            "type",
+            sa.Enum("RawTranscript", name="artifacttype"),
+            nullable=False,
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("updated_at", sa.DateTime(), nullable=True),
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.ForeignKeyConstraint(["job_id"], ["jobs.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_artifacts_id"), "artifacts", ["id"], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f("ix_artifacts_id"), table_name="artifacts")
+    op.drop_table("artifacts")
+    op.drop_index(op.f("ix_jobs_id"), table_name="jobs")
+    op.drop_table("jobs")
+    # ### end Alembic commands ###

app/shared/db/base.py

@@ -0,0 +1,21 @@
+from typing import Generator
+
+from sqlalchemy import create_engine
+from sqlalchemy.orm import Session, sessionmaker
+
+from app.shared.config import settings
+
+engine = create_engine(settings.DATABASE_URI)
+
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+
+def get_session() -> Generator[Session, None, None]:
+    db: Session = SessionLocal()
+    try:
+        yield db
+        db.commit()
+    except Exception:
+        db.rollback()
+    finally:
+        db.close()

app/shared/db/dtos.py

@@ -0,0 +1,41 @@
+import enum
+from datetime import datetime
+from typing import Optional
+from uuid import UUID
+
+from pydantic import AnyHttpUrl, BaseModel, Json
+
+
+class ArtifactType(enum.Enum):
+    RawTranscript = "RawTranscript"
+
+
+class JobType(enum.Enum):
+    Transcript = "Transcript"
+
+
+class JobStatus(enum.Enum):
+    Create = "Create"
+    Error = "Error"
+    Success = "Success"
+
+
+class WithDbFields(BaseModel):
+    id: UUID
+    created_at: datetime
+    updated_at: Optional[datetime]
+
+    class Config:
+        orm_mode = True
+
+
+class Job(WithDbFields):
+    status: JobStatus
+    type: JobType
+    url: AnyHttpUrl
+
+
+class Artifact(WithDbFields):
+    data: Optional[Json]
+    job_id: UUID
+    type: ArtifactType

app/shared/db/models.py

@@ -0,0 +1,50 @@
+import uuid
+from typing import Optional
+
+from sqlalchemy import JSON, Column, DateTime, Enum, ForeignKey, String, func
+from sqlalchemy.dialects.postgresql import UUID
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import Mapped, declarative_mixin, declared_attr
+
+from .dtos import ArtifactType, JobStatus, JobType
+
+Base = declarative_base()
+
+
+@declarative_mixin
+class WithStandardFields:
+    """Mixin that adds standard fields (id, created_at, updated_at)."""
+
+    @declared_attr
+    def created_at(cls) -> Mapped[DateTime]:
+        return Column(DateTime, server_default=func.now(), nullable=False)
+
+    @declared_attr
+    def updated_at(cls) -> Mapped[Optional[DateTime]]:
+        return Column(DateTime, onupdate=func.now())
+
+    @declared_attr
+    def id(cls) -> Mapped[UUID]:
+        return Column(
+            UUID(as_uuid=True), primary_key=True, index=True, default=uuid.uuid4
+        )
+
+
+class Job(Base, WithStandardFields):
+    __tablename__ = "jobs"
+
+    # TODO: job config
+    url = Column(String(length=2048))
+    status = Column(Enum(JobStatus), nullable=False)
+    type = Column(Enum(JobType), nullable=False)
+
+
+class Artifact(Base, WithStandardFields):
+    __tablename__ = "artifacts"
+
+    job_id = Column(
+        UUID(as_uuid=True), ForeignKey("jobs.id", ondelete="CASCADE"), nullable=False
+    )
+
+    data = Column(JSON(none_as_null=True))
+    type = Column(Enum(ArtifactType), nullable=False)