Initial extraction from monorepo

alembic/env.py

@@ -0,0 +1,59 @@
+import asyncio
+import os
+from logging.config import fileConfig
+
+from sqlalchemy.engine import Connection
+from sqlalchemy.ext.asyncio import async_engine_from_config
+
+from alembic import context
+from hmrc_sync.db import SCHEMA_NAME, Base
+
+config = context.config
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+db_url = os.environ.get("DB_CONNECTION_STRING")
+if db_url:
+    config.set_main_option("sqlalchemy.url", db_url)
+
+target_metadata = Base.metadata
+
+
+def do_run_migrations(connection: Connection) -> None:
+    connection.exec_driver_sql(f'CREATE SCHEMA IF NOT EXISTS "{SCHEMA_NAME}"')
+    context.configure(
+        connection=connection,
+        target_metadata=target_metadata,
+        version_table_schema=SCHEMA_NAME,
+        include_schemas=True,
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_migrations_online() -> None:
+    configuration = config.get_section(config.config_ini_section, {})
+    connectable = async_engine_from_config(configuration, prefix="sqlalchemy.")
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+        await connection.commit()
+    await connectable.dispose()
+
+
+def run_migrations_offline() -> None:
+    context.configure(
+        url=config.get_main_option("sqlalchemy.url"),
+        target_metadata=target_metadata,
+        literal_binds=True,
+        version_table_schema=SCHEMA_NAME,
+        include_schemas=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    asyncio.run(run_migrations_online())

alembic/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+"""
+from collections.abc import Sequence
+from typing import Union
+
+import sqlalchemy as sa
+
+from alembic import op
+${imports if imports else ""}
+
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

alembic/versions/0001_initial.py

@@ -0,0 +1,85 @@
+"""Create hmrc_sync.tax_year_snapshot + hmrc_sync.fetch_log.
+
+These two tables hold everything hmrc-sync persists. The snapshot table
+keeps HMRC's `hmrc-held` PAYE/NI view per (tax_year, employer, day);
+fetch_log is the audit trail of every outbound API call (for
+fraud-header compliance reviews HMRC may trigger).
+"""
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from alembic import op
+
+revision = "0001"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+SCHEMA = "hmrc_sync"
+
+
+def upgrade() -> None:
+    op.create_table(
+        "tax_year_snapshot",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("tax_year", sa.String(), nullable=False),
+        sa.Column("employer_paye_ref", sa.String(), nullable=False),
+        sa.Column("snapshot_date", sa.TIMESTAMP(timezone=True), nullable=False),
+        sa.Column("gross_pay", sa.Numeric(12, 2), nullable=False),
+        sa.Column("income_tax", sa.Numeric(12, 2), nullable=False),
+        sa.Column("ni_contributions", sa.Numeric(12, 2), nullable=False),
+        sa.Column("source", sa.String(), nullable=False, server_default="hmrc-held"),
+        sa.Column(
+            "raw_response",
+            postgresql.JSONB().with_variant(sa.JSON(), "sqlite"),
+            nullable=False,
+        ),
+        sa.Column(
+            "fetched_at",
+            sa.TIMESTAMP(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.UniqueConstraint(
+            "tax_year",
+            "employer_paye_ref",
+            "snapshot_date",
+            name="uq_tax_year_snapshot",
+        ),
+        schema=SCHEMA,
+    )
+    op.create_index(
+        "ix_tax_year_snapshot_tax_year",
+        "tax_year_snapshot",
+        ["tax_year"],
+        schema=SCHEMA,
+    )
+
+    op.create_table(
+        "fetch_log",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("endpoint", sa.String(), nullable=False),
+        sa.Column("status_code", sa.Integer(), nullable=False),
+        sa.Column("request_id", sa.String(), nullable=True),
+        sa.Column("correlation_id", sa.String(), nullable=True),
+        sa.Column(
+            "fraud_headers_sent",
+            postgresql.JSONB().with_variant(sa.JSON(), "sqlite"),
+            nullable=False,
+        ),
+        sa.Column("response_snippet", sa.String(), nullable=True),
+        sa.Column("duration_ms", sa.Integer(), nullable=False),
+        sa.Column(
+            "fetched_at",
+            sa.TIMESTAMP(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        schema=SCHEMA,
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("fetch_log", schema=SCHEMA)
+    op.drop_index("ix_tax_year_snapshot_tax_year", table_name="tax_year_snapshot", schema=SCHEMA)
+    op.drop_table("tax_year_snapshot", schema=SCHEMA)