Compare commits

...
6 Commits
Author SHA1 Message Date
mathias2784 afe2478cc7 comdirect stringification 2026-09-13 09:45:16 +02:00
mathias2784 46bdd5e68c ingestion models: less code repetition, more inheritance 2026-09-13 07:55:24 +02:00
mathias2784 58dc585e7e b4w faker: occasionally empty other_iban 2026-09-13 07:31:20 +02:00
mathias2784 7ab7276db5 AGENTS.md 2026-09-12 22:58:22 +02:00
mathias2784 500b76b8a8 fix b4w real-world import 2026-09-12 21:00:26 +02:00
mathias2784 e9dcb88da5 fix settings template 2026-09-12 21:00:00 +02:00
9 changed files with 287 additions and 34 deletions
+107
View File
@@ -0,0 +1,107 @@
# finanz-cockpit Agent Instructions
## Setup Commands
```bash
# Install dependencies
uv sync
# Run migrations
alembic upgrade head
# Run all tests
pytest
# Run a single test file
pytest tests/test_model_b4wexport.py -v
```
## Project Structure
- **`src/`**: Application code
- `main.py`: CLI entrypoint for CSV ingestion
- `db.py`: Database connection management (uses global `_engine` pattern)
- `models/`: Pydantic models + SQLAlchemy tables for b4w and comdirect imports
- `ingest/`: Data ingestion logic per source
- **`tests/`**: Tests with fixtures in `conftest.py`
- **`alembic/versions/`**: Database migrations
## Key Patterns & Gotchas
### Database Configuration
```python
from src.db import get_engine, get_session, set_engine
# Development: use sqlite://
os.environ["DATABASE_URL"] = "sqlite://"
# Production/default: sqlite:///finanz.db
engine = get_engine() # reads DATABASE_URL or uses default
with get_session() as session:
session.query(...).all()
```
**Critical**: Tests override engine via `conftest.py`. Never assume global state - always use `get_session()` context manager.
### CSV Format Expectations
- **b4w**: German bank export (CSV) from `/mnt/anbau/Software/Python/finanz-cockpit/scripts/dummy_data/b4w_export_dummy_01.csv`
- **comdirect**: German bank export (CSV) with fields like `Buchungstag`, `Umsatz in EUR`, `Vorgang`
### Testing Workflow
```bash
# Tests automatically run migrations via conftest fixture
pytest tests/ -v --tb=short
# To test without migrations (in-memory SQLite), use DATABASE_URL="sqlite://"
export DATABASE_URL="sqlite://" pytest tests/test_db.py
```
### Environment Variables
- `DATABASE_URL`: Database connection string (default: `sqlite:///finanz.db`)
## Data Models
Two sources with shared patterns:
- **b4w**: `B4wExport`, `Category`, transactional import to `import_b4w` table + `category` table
- **comdirect**: `ComdirectGiro`, `ComdirectCreditCard`, `ComdirectDepot`, import to `comdirect_giro` table
All models inherit from common base in `src/models/_common.py`:
- `_hash()`: SHA256-based deduplication key
- `_parse_date_german()`: Handles "07.09.2026" format and values like "offen", "--"
- `_parse_decimal_german()`: Converts "1,23" to Decimal
## Factory Pattern for Testing
Import from `tests/factories.py`:
```python
from tests.factories import B4wExportFactory, ComdirectGiroFactory
from src.constants import Currency
B4wExportFactory.__faker__ = Faker("de_DE")
ComdirectGiroFactory.__faker__ = Faker("de_DE")
# Use in tests:
item = B4wExportFactory.build( # build() for partial, create() for full
Amt="50.00",
RmtInf="Supermarket",
)
```
## Common Mistakes to Avoid
1. **Assuming global engine state**: Always use `get_session()` context manager
2. **Ignoring German date formats**: Use `_parse_date_german()` for CSV parsing
3. **Forgetting migration setup in tests**: Tests auto-migrate, but integration tests with real db need explicit upgrade
4. **Wrong Faker locale**: Use `Faker("de_DE")` for realistic names/IBANs
## Testing Tips
- Run single test: `pytest tests/test_model_b4wexport.py -v`
- View migrations: `ls alembic/versions/`
- Test data location: `/scripts/dummy_data/`
+6 -9
View File
@@ -3,13 +3,12 @@ from pathlib import Path
from faker import Faker
from src.constants import Currency
from src.ingest.b4w import ingest_b4w, reader_b4w
from src.ingest.comdirect import reader_comdirect
from src.models import (
ComdirectCreditCard,
ComdirectDepot,
ComdirectGiro,
)
from src.models.b4w import B4wExport
from src.models.settings import Account, Source
fake = Faker()
@@ -18,11 +17,10 @@ BANK_ACCOUNTS = {
"b4w": Source(
name="b4w",
source_path=Path(""),
reader_function=reader_b4w,
accounts=[
Account(
name="b4w",
ingestion_function=ingest_b4w,
model=B4wExport,
iban=fake.iban(),
currency=Currency.EUR,
)
@@ -31,29 +29,28 @@ BANK_ACCOUNTS = {
"comdirect": Source(
name="comdirect",
source_path=Path(""),
reader_function=reader_comdirect,
accounts=[
Account(
name="Girokonto",
ingestion_function=lambda x: ComdirectGiro.model_validate(x),
model=ComdirectGiro,
iban=fake.iban(),
currency=Currency.EUR,
),
Account(
name="Visa-Karte (Kreditkarte)",
ingestion_function=lambda x: ComdirectCreditCard.model_validate(x),
model=ComdirectCreditCard,
iban=fake.iban(),
currency=Currency.EUR,
),
Account(
name="Tagesgeld PLUS-Konto",
ingestion_function=lambda x: ComdirectGiro.model_validate(x),
model=ComdirectGiro,
iban=fake.iban(),
currency=Currency.EUR,
),
Account(
name="Depot",
ingestion_function=lambda x: ComdirectDepot.model_validate(x),
model=ComdirectDepot,
iban=fake.iban(),
currency=Currency.EUR,
),
+2 -2
View File
@@ -27,8 +27,8 @@ def main():
assert isinstance(giro_account, Account)
ingest_comdirect(
Path(args.input_comdirect),
account_iban=giro_account.iban,
account_currency=giro_account.currency,
account_iban=giro_account.iban or "",
account_currency=giro_account.currency or "",
)
+19 -1
View File
@@ -61,7 +61,25 @@ type CsV2DictMulti = dict[str, Csv2Dict]
class ExportBaseModel(BaseModel):
pass
@classmethod
def _my_name(cls):
return cls.__name__
def parameters_to_dict(self) -> dict[str, str]:
return {}
def parameters_to_str(self):
parameters = ", ".join(
f"{key}='{value}'" for key, value in self.parameters_to_dict().items()
)
return parameters
def __repr__(self):
return f"{self._my_name()}({self.parameters_to_str()})"
def __str__(self):
return f"{self._my_name()}({self.parameters_to_str()})"
class BaseModelDb(DeclarativeBase):
+9 -14
View File
@@ -27,7 +27,7 @@ class B4wExport(ExportBaseModel):
sign: Sign = Field(alias="CdtDbtInd")
reference: str = Field(alias="RmtInf")
other_name: str = Field(alias="RmtdNm")
other_iban: str = Field(alias="RmtdAcctIBAN", pattern=IBAN_PATTERN)
other_iban: str | None = Field(alias="RmtdAcctIBAN", pattern=IBAN_PATTERN)
category: Category | None = Field(
alias="Category",
examples=[
@@ -51,23 +51,11 @@ class B4wExport(ExportBaseModel):
"CdtDbtInd": f"{self.sign!s}",
"RmtInf": f"{self.reference}",
"RmtdNm": f"{self.other_name}",
"RmtdAcctIBAN": f"{self.other_iban}",
"RmtdAcctIBAN": f"{self.other_iban or ''}",
"Category": f"{self.category.to_str() if self.category else ''}",
"Notes": f"{self.notes}",
}
def parameters_to_str(self):
parameters = ", ".join(
f"{key}='{value}'" for key, value in self.parameters_to_dict().items()
)
return parameters
def __repr__(self):
return f"B4wExport({self.parameters_to_str()})"
def __str__(self):
return f"B4wExport({self.parameters_to_str()})"
@computed_field
@property
def hash_id(self) -> str:
@@ -77,6 +65,13 @@ class B4wExport(ExportBaseModel):
def amount_signed(self) -> Decimal:
return self.amount * self.sign.to_sign()
@field_validator("other_iban", mode="before")
@classmethod
def other_iban_blank_is_none(cls, iban_in: str | None) -> str | None:
if iban_in is None or (isinstance(iban_in, str) and not iban_in.strip()):
return None
return iban_in
@field_validator("category", mode="before")
@classmethod
def category_str_is_parsable(
+69 -2
View File
@@ -1,7 +1,7 @@
from datetime import date
from decimal import Decimal
from pydantic import Field, computed_field, field_validator
from pydantic import ConfigDict, Field, computed_field, field_validator
from sqlalchemy import Column, Date, String
from src.models._common import (
@@ -10,10 +10,13 @@ from src.models._common import (
_hash,
_parse_date_german,
_parse_decimal_german,
date2str,
decimal2str,
)
class ComdirectBase(ExportBaseModel):
model_config = ConfigDict(populate_by_name=True)
date_val: date | None = Field(
alias="Wertstellung (Valuta)", examples=["07.09.2026"]
)
@@ -21,7 +24,9 @@ class ComdirectBase(ExportBaseModel):
@field_validator("date_val", mode="before")
@classmethod
def parse_date_val(cls, date_str: str) -> date | None:
def parse_date_val(cls, date_str: str | None) -> date | None:
if date_str is None:
return
return _parse_date_german(date_str)
@field_validator("amount_eur", mode="before")
@@ -29,6 +34,29 @@ class ComdirectBase(ExportBaseModel):
def parse_amount(cls, decimal_str: str) -> Decimal:
return _parse_decimal_german(decimal_str)
@classmethod
def _date2str(cls, date_value: date | None) -> str:
return date2str(date_value, default="--", date_format="%d.%m.%Y")
def parameters_to_dict(self, by_name=True) -> dict[str, str]:
return {
"date_val" if by_name else "Wertstellung (Valuta)": self._date2str(
self.date_val
),
"amount_eur" if by_name else "Umsatz in EUR": decimal2str(self.amount_eur),
}
def get_orig_headers(self, sep: str = ";", bracket: str = '"'):
return sep.join(
f"{bracket}{txt}{bracket}" for txt in self.parameters_to_dict(by_name=False)
)
def get_orig_row(self, sep: str = ";", bracket: str = '"'):
return sep.join(
f"{bracket}{txt}{bracket}"
for txt in self.parameters_to_dict(by_name=False).values()
)
class ComdirectGiro(ComdirectBase):
# # Fields from parents:
@@ -50,6 +78,19 @@ class ComdirectGiro(ComdirectBase):
def parse_date_book(cls, date_str: str) -> date | None:
return _parse_date_german(date_str)
def parameters_to_dict(self, by_name=True) -> dict[str, str]:
parameters = dict(**super().parameters_to_dict(by_name=by_name))
parameters.update(
{
"date_book" if by_name else "Buchungstag": self._date2str(
self.date_book
),
"type" if by_name else "Vorgang": self.type,
"text" if by_name else "Buchungstext": self.text,
}
)
return parameters
class ComdirectCreditCard(ComdirectGiro):
# # Fields from parents:
@@ -71,6 +112,18 @@ class ComdirectCreditCard(ComdirectGiro):
alias="Umsatz in EUR", examples=["32,43"], default=None
)
def parameters_to_str(self, sep=", ", str_qualifier=False): ...
def parameters_to_dict(self) -> dict[str, str]:
parameters = dict(**super().parameters_to_dict())
parameters.update(
{
"Umsatztag": self._date2str(self.date_val),
"Referenz": self.reference,
}
)
return parameters
class ComdirectDepot(ComdirectBase):
# # Fields from parents:
@@ -88,6 +141,20 @@ class ComdirectDepot(ComdirectBase):
def parse_decimals(cls, decimal_in: str) -> Decimal:
return _parse_decimal_german(decimal_in)
def parameters_to_dict(self) -> dict[str, str]:
parameters = dict(**super().parameters_to_dict())
parameters.update(
{
"Geschäftstag": self._date2str(self.date_val),
"Stück / Nom.": decimal2str(self.num),
"Bezeichnung": self.name,
"WKN": self.wkn,
"Währung": self.currency,
"Ausführungskurs": decimal2str(self.spot_price),
}
)
return parameters
class ComdirectBaseDb(IngestdbBase):
__abstract__ = True
+30 -6
View File
@@ -1,4 +1,5 @@
from decimal import Decimal
from typing import Any
from faker import Faker
from polyfactory.factories.pydantic_factory import ModelFactory
@@ -10,6 +11,12 @@ from src.models.comdirect import ComdirectCreditCard, ComdirectDepot, ComdirectG
DEFAULT_CATEGORY = "root_category:parent_category:leaf_category"
def _faker_or_none(faker: Faker, non_default: Any, default: Any = None, p_value=0.5):
if faker.pyfloat(min_value=0.0, max_value=1.0) < p_value:
return default
return non_default
def _amount() -> Decimal:
return B4wExportFactory.__faker__.pydecimal(
left_digits=6,
@@ -19,6 +26,18 @@ def _amount() -> Decimal:
)
def _amount_eur() -> str:
"""Generate German-formatted decimal string (e.g., '32,43')."""
val = B4wExportFactory.__faker__.pydecimal(
left_digits=6,
right_digits=2,
positive=True,
min_value=Decimal("0.01"),
)
# Format as German string with comma decimal separator
return f"{val:.2f}".replace(".", ",").strip()
def _sentence() -> str:
return B4wExportFactory.__faker__.sentence(
nb_words=8,
@@ -34,6 +53,11 @@ def _iban() -> str:
return B4wExportFactory.__faker__.iban()
def _iban_or_none() -> str:
faker = B4wExportFactory.__faker__
return _faker_or_none(faker, faker.iban(), default="")
class B4wExportFactory(ModelFactory[B4wExport]):
__faker__ = Faker("de_DE")
__use_examples__ = True
@@ -43,22 +67,22 @@ class B4wExportFactory(ModelFactory[B4wExport]):
Notes = Use(_sentence)
RmtdNm = Use(_names)
OwnrAcctIBAN = Use(_iban)
RmtdAcctIBAN = Use(_iban)
RmtdAcctIBAN = Use(_iban_or_none)
class ComdirectGiroFactory(ModelFactory[ComdirectGiro]):
__faker__ = Faker("de_DE")
__use_example__ = True
__use_examples__ = True
Buchungstext = Use(_sentence)
text = Use(_sentence)
amount_eur = Use(_amount_eur)
class ComdirectCreditCardFactory(ModelFactory[ComdirectCreditCard]):
__faker__ = Faker("de_DE")
__use_example__ = True
__use_examples__ = True
class ComdirectDepotFactory(ModelFactory[ComdirectDepot]):
__faker__ = Faker("de_DE")
__use_example__ = True
__use_examples__ = True
+21
View File
@@ -33,6 +33,27 @@ def test_b4w_export_account_iban_to_short():
_ = B4wExportFactory.build(OwnrAcctIBAN="DE123")
def test_b4w_export_other_iban_empty_is_none():
data = B4wExportFactory.build(RmtdAcctIBAN="")
assert data.other_iban is None
def test_b4w_export_other_iban_blank_is_none():
data = B4wExportFactory.build(RmtdAcctIBAN=" ")
assert data.other_iban is None
def test_b4w_export_other_iban_invalid():
with pytest.raises(ValidationError):
_ = B4wExportFactory.build(RmtdAcctIBAN="not an IBAN")
def test_b4w_export_other_iban_repr_round_trip_empty():
data = B4wExportFactory.build(RmtdAcctIBAN="")
data2 = eval(str(data))
assert data == data2
def test_b4w_export_parameters_to_dict():
data = B4wExportFactory.build()
params = data.parameters_to_dict()
+24
View File
@@ -0,0 +1,24 @@
from src.models.comdirect import ComdirectGiro
from tests.factories import ComdirectGiroFactory
def test_comdirect_giro_basic_and_stringification():
data = ComdirectGiroFactory.build()
assert data
assert isinstance(data, ComdirectGiro)
orig_headers = data.get_orig_headers()
assert orig_headers
assert isinstance(orig_headers, str)
header_list = orig_headers.split(";")
assert len(header_list) > 0
assert set(header_list) == {
'"Wertstellung (Valuta)"',
'"Umsatz in EUR"',
'"Buchungstag"',
'"Vorgang"',
'"Buchungstext"',
}
orig_row = data.get_orig_row()
assert orig_row
assert isinstance(orig_row, str)
assert len(orig_row.split(";")) > 0