Initial commit: event-driven UK payslip ingest service

Extracted from /home/wizard/code monorepo into its own repo so Woodpecker CI
can watch it. Identical content to /home/wizard/code commit e426028.

See README.md for overview, env vars, and Paperless workflow config.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

alembic/env.py

@@ -0,0 +1,57 @@
+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 payslip_ingest.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:
+    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 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 +1,25 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${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 +1,72 @@
+"""initial schema
+
+Revision ID: 0001
+Revises:
+Create Date: 2026-04-18 00:00:00.000000
+
+"""
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from alembic import op
+
+revision: str = "0001"
+down_revision: str | None = None
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+SCHEMA = "payslip_ingest"
+
+
+def upgrade() -> None:
+    op.execute(f"CREATE SCHEMA IF NOT EXISTS {SCHEMA}")
+
+    op.create_table(
+        "payslip",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("paperless_doc_id", sa.Integer(), nullable=False, unique=True),
+        sa.Column("pay_date", sa.Date(), nullable=False),
+        sa.Column("pay_period_start", sa.Date(), nullable=True),
+        sa.Column("pay_period_end", sa.Date(), nullable=True),
+        sa.Column("employer", sa.Text(), nullable=True),
+        sa.Column("currency", sa.CHAR(3), nullable=False, server_default="GBP"),
+        sa.Column("gross_pay", sa.Numeric(12, 2), nullable=False),
+        sa.Column("income_tax", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")),
+        sa.Column(
+            "national_insurance", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")
+        ),
+        sa.Column(
+            "pension_employee", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")
+        ),
+        sa.Column(
+            "pension_employer", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")
+        ),
+        sa.Column("student_loan", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")),
+        sa.Column("other_deductions", postgresql.JSONB(), nullable=True),
+        sa.Column("net_pay", sa.Numeric(12, 2), nullable=False),
+        sa.Column("tax_year", sa.Text(), nullable=False),
+        sa.Column("raw_extraction", postgresql.JSONB(), nullable=False),
+        sa.Column("validated", sa.Boolean(), nullable=False, server_default=sa.text("true")),
+        sa.Column(
+            "created_at",
+            sa.TIMESTAMP(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        schema=SCHEMA,
+    )
+    op.create_index(
+        "idx_payslip_pay_date", "payslip", ["pay_date"], schema=SCHEMA
+    )
+    op.create_index(
+        "idx_payslip_tax_year", "payslip", ["tax_year"], schema=SCHEMA
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("idx_payslip_tax_year", table_name="payslip", schema=SCHEMA)
+    op.drop_index("idx_payslip_pay_date", table_name="payslip", schema=SCHEMA)
+    op.drop_table("payslip", schema=SCHEMA)
+    op.execute(f"DROP SCHEMA IF EXISTS {SCHEMA}")