broker-sync/tests/fixtures/invest_engine/html_partial_match.eml
Viktor Barzin 87526898e6 Pin InvestEngine parser failure modes — empty-on-junk + partial-match
Context: The port's graceful-failure contract was implicit in the way
each strategy returns None/[] on malformed input, but without tests it
was an accidental property that could regress silently. Codify it.

Two invariants, each backed by a fixture:

1. Junk email → empty list, never raise.
   `unparseable.eml` is a pure-marketing IE newsletter with no order
   data. All three strategies try and fail; parse_invest_engine_email
   returns []. No exception leaks.

2. Partial HTML email → intact orders only.
   `html_partial_match.eml` has two nested summary tables: one with a
   valid VUAG order, one that is missing both the ticker and "Bought N
   @ £P" rows (simulates IE dropping content mid-render). The parser
   returns just the VUAG order.

No implementation change needed — the behaviour existed as a side
effect of _try_html_summary_table returning None on missing fields.
These tests lock it down so future refactors can't quietly break it.

Test plan:
  poetry run pytest tests/providers/parsers/ -q   →  8 passed in 0.19s
  poetry run mypy broker_sync/providers/parsers/invest_engine.py tests/providers/parsers/test_invest_engine.py   →  clean
  poetry run ruff check broker_sync/providers/parsers/invest_engine.py tests/providers/parsers/test_invest_engine.py   →  All checks passed!
  poetry run yapf --diff   →  clean (no diff)

Manual verification:
- Load unparseable.eml → parse returns [].
- Load html_partial_match.eml → parse returns exactly 1 activity (VUAG).
2026-04-17 22:02:48 +00:00

40 lines
947 B
Text

From: InvestEngine <no-reply@investengine.com>
To: viktorbarzin@example.com
Subject: Your portfolio has been updated
Date: Wed, 15 Apr 2026 11:00:00 +0000
MIME-Version: 1.0
Content-Type: multipart/alternative; boundary="----=_Part_PM"
------=_Part_PM
Content-Type: text/plain; charset=UTF-8
(HTML-only view — your client does not render HTML emails.)
------=_Part_PM
Content-Type: text/html; charset=UTF-8
<html><body>
<table><tr><td>Logo</td></tr></table>
<table>
<tr><td> Date: 15 April 2026 </td></tr>
<tr>
<td>
<table>
<tr><td>Vanguard S&amp;P 500: VUAG</td></tr>
<tr><td>Bought 3.0 @ &pound;61.25 per share</td></tr>
<tr><td>Total: &pound;183.75</td></tr>
</table>
</td>
</tr>
<tr>
<td>
<table>
<tr><td>Some broken order with no ticker and no bought line</td></tr>
<tr><td>(Malformed — IE dropped a row mid-render)</td></tr>
</table>
</td>
</tr>
</table>
</body></html>
------=_Part_PM--