broker-sync/tests/providers/parsers/test_schwab.py
Viktor Barzin f089b8b93a Add Schwab email parser (port from finance/)
Schwab's workplace-RSU confirmation emails have 5 data td elements
with class='dark-background-body' align='right': date, direction, qty,
ticker, price-with-currency-sign. One email → one Activity.

- parse_schwab_email(raw_html) -> list[Activity] (1-item or empty)
- Empty on any parse failure (IMAP batch shouldn't crash on one bad mail)
- Deterministic external_id ('schwab📅ticker:type:qty') — stable
  across re-pulls so dedup works
- Hardcoded to account 'schwab-workplace' / AccountType.GIA / USD
- 6 unit tests: SELL + BUY happy path, malformed, missing cells,
  external-id stability, commas in price

Dropped from the original finance port:
- msg_timestamp-based external id (non-deterministic — would re-import
  on every IMAP walk). Replaced with a hash-stable key.
- Currency.from_sign() currency hack. Schwab US is USD-only; we'll add
  FX when that changes.

poetry run pytest -q   →  109 passed, 1 skipped
poetry run mypy        →  clean (added types-python-dateutil)
poetry run ruff check  →  clean
2026-04-17 22:08:40 +00:00

84 lines
2.8 KiB
Python

from __future__ import annotations
from decimal import Decimal
from broker_sync.models import AccountType, ActivityType
from broker_sync.providers.parsers.schwab import parse_schwab_email
_SELL = """
<html><body>
<table>
<tr><td>Date</td><td class="dark-background-body" align="right">Jan 23, 2025</td></tr>
<tr><td>Action</td><td class="dark-background-body" align="right">Sold</td></tr>
<tr><td>Quantity</td><td class="dark-background-body" align="right">100.0</td></tr>
<tr><td>Ticker</td><td class="dark-background-body" align="right">META</td></tr>
<tr><td>Price</td><td class="dark-background-body" align="right">$612.34</td></tr>
</table>
</body></html>
"""
_BUY = """
<html><body><table>
<tr><td class="dark-background-body" align="right">2024-11-15</td></tr>
<tr><td class="dark-background-body" align="right">Bought</td></tr>
<tr><td class="dark-background-body" align="right">5.5</td></tr>
<tr><td class="dark-background-body" align="right">AAPL</td></tr>
<tr><td class="dark-background-body" align="right">$225.00</td></tr>
</table></body></html>
"""
_MALFORMED = "<html><body>no transaction here</body></html>"
_MISSING_CELLS = """
<html><body><table>
<tr><td class="dark-background-body" align="right">Jan 23, 2025</td></tr>
<tr><td class="dark-background-body" align="right">Sold</td></tr>
</table></body></html>
"""
def test_sell_email_parses_to_one_sell_activity() -> None:
acts = parse_schwab_email(_SELL)
assert len(acts) == 1
a = acts[0]
assert a.activity_type is ActivityType.SELL
assert a.symbol == "META"
assert a.quantity == Decimal("100.0")
assert a.unit_price == Decimal("612.34")
assert a.currency == "USD"
assert a.account_id == "schwab-workplace"
assert a.account_type is AccountType.GIA
assert a.date.date().isoformat() == "2025-01-23"
def test_buy_email_becomes_buy_activity() -> None:
acts = parse_schwab_email(_BUY)
assert len(acts) == 1
a = acts[0]
assert a.activity_type is ActivityType.BUY
assert a.symbol == "AAPL"
assert a.quantity == Decimal("5.5")
assert a.unit_price == Decimal("225.00")
def test_malformed_email_returns_empty_list() -> None:
# No matching td cells at all.
assert parse_schwab_email(_MALFORMED) == []
def test_missing_cells_returns_empty_list() -> None:
# Only 2 of the 5 required cells — parser must bail cleanly.
assert parse_schwab_email(_MISSING_CELLS) == []
def test_external_id_is_stable_across_reruns() -> None:
# Same email → same external_id (deterministic, not timestamp-based).
a1 = parse_schwab_email(_SELL)[0]
a2 = parse_schwab_email(_SELL)[0]
assert a1.external_id == a2.external_id
def test_price_with_commas_parses() -> None:
html = _SELL.replace("$612.34", "$1,612.34")
a = parse_schwab_email(html)[0]
assert a.unit_price == Decimal("1612.34")