fidelity-planviewer: wire provider to real PlanViewer session + JSON API
## Context
Prior commit 832732a scaffolded the provider with a stub fetch() that
raised FidelityProviderConfigError. This commit replaces the stub with
the end-to-end ingest flow, validated against the real PlanViewer site
during a live login session on 2026-04-18.
Fidelity UK PlanViewer mixes a legacy Struts2 HTML app
(www.planviewer.fidelity.co.uk) with a React SPA at
pv.planviewer.fidelity.co.uk. Authentication is PingFederate OAuth2 at
id.fidelity.co.uk — password + memorable word + SMS OTP, with a
remember-device cookie that keeps the session alive for weeks. The
transaction history is server-rendered HTML at DisplayMyPlanMemberTransHist.action;
current fund holdings come from the DisplayValuation.action JSON XHR.
Both live behind the same cookie jar, so one Playwright session (seeded
interactively once, kept alive via storage_state) can scrape both.
## This change
- broker_sync/providers/parsers/fidelity.py (NEW)
- parse_transactions_html: extracts cash-impacting rows from the
#myplan_member_transhist_support table, skips Bulk Switches (no cash
movement), emits FidelityCashTx with deterministic external_id for
dedup.
- parse_valuation_json: lifts fund code + name + units + price +
contribution-type breakdown from the JSON payload.
- broker_sync/providers/fidelity_planviewer.py (REWRITTEN)
- FidelityPlanViewerProvider.fetch() now loads storage_state, boots
headless Chromium, navigates landing → main page (to hydrate the
SPA session + capture DisplayValuation XHR) → transactions page
with a wide 01 Jan 1990 → today window. Raises FidelitySessionError
if PlanViewer shows the 15-min idle page or redirects back to
id.fidelity.co.uk.
- _gains_offset_activity emits a synthetic DEPOSIT/WITHDRAWAL with a
date-keyed external_id so WF Net Worth reconciles to the
Fidelity-reported pot value without stacking duplicates across
monthly runs.
- Rolls storage_state back to disk after each run, extending session
TTL.
- tests/providers/test_fidelity_planviewer.py (EXTENDED)
- 8 tests against a real captured fixture: account shape, guard on
missing storage_state, full-fixture round-trip (51 txs summing to
£102,004.15), Bulk Switch filtered, deterministic external_id,
valuation parse with fund-code resolution, gains-offset direction
+ skip-when-empty.
- tests/fixtures/fidelity/transactions-full.html + valuation.json (NEW)
- Sanitised captures from the 2026-04-18 live session.
## What is NOT in this change
- CronJob + Vault secret wiring + Prometheus alert in
infra/stacks/broker-sync/main.tf — next commit.
- Dockerfile Chromium install — next commit.
- The scrape-and-import was already done manually (51 activities +
1 gains offset imported into WF account a7d6208d); this commit
productionises the code path so the monthly cron can do the same.
## Verification
### Automated
$ poetry run pytest tests/providers/test_fidelity_planviewer.py -v
8 passed in 0.88s
$ poetry run pytest -q
128 passed, 1 skipped in 1.41s
$ poetry run mypy broker_sync/providers/fidelity_planviewer.py broker_sync/providers/parsers/fidelity.py
Success: no issues found in 2 source files
$ poetry run ruff check broker_sync/providers/fidelity_planviewer.py broker_sync/providers/parsers/fidelity.py
All checks passed!
### Manual verification (2026-04-18 live run)
1. poetry run broker-sync fidelity-seed (headed browser + SMS OTP) —
captured storage_state, staged to Vault.
2. Inline import script hit the same code paths the provider now runs;
52 activities imported into a new WF WORKPLACE_PENSION account, WF
Net Worth jumped from £865,358 → £1,003,083.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
832732a419
commit
804e6a89de
5 changed files with 2117 additions and 80 deletions
|
|
@ -1,90 +1,130 @@
|
||||||
"""Fidelity UK PlanViewer provider — workplace pension backfill + monthly sync.
|
"""Fidelity UK PlanViewer provider — workplace pension backfill + monthly sync.
|
||||||
|
|
||||||
PlanViewer has no public individual-member API; Fidelity International's
|
PlanViewer has no public individual-member API. The SPA (at
|
||||||
developer portal only catalogues B2B scheme/HR endpoints. The SPA (at
|
``pv.planviewer.fidelity.co.uk``) and the legacy HTML app (at
|
||||||
``pv.planviewer.fidelity.co.uk``) does call a private JSON backend at
|
``www.planviewer.fidelity.co.uk``) share session cookies via PingFederate
|
||||||
``prd.wiciam.fidelity.co.uk/cvmfe/api/*`` — we reverse-engineer that and feed
|
OAuth at ``id.fidelity.co.uk``.
|
||||||
it through a Playwright-maintained session.
|
|
||||||
|
|
||||||
## Session lifecycle
|
We keep a Playwright-maintained session via ``storage_state.json``:
|
||||||
|
|
||||||
1. **One-off seed** (``broker-sync fidelity-seed``): Viktor runs a headed
|
1. **One-off seed** (``broker-sync fidelity-seed``): Viktor runs a headed
|
||||||
Chromium, logs in (password + memorable word + MFA), clicks "Remember
|
Chromium, logs in (password + memorable word + SMS MFA), clicks
|
||||||
device". Playwright dumps the resulting ``storage_state.json`` (cookies +
|
"Remember device". The storage_state is persisted to Vault.
|
||||||
localStorage) which we stash in Vault.
|
|
||||||
|
|
||||||
2. **Monthly cron**: loads storage_state, boots headless Chromium, navigates
|
2. **Monthly cron**: loads storage_state, boots headless Chromium, navigates
|
||||||
to the SPA once to let it refresh rolling session tokens, intercepts the
|
to the transaction-history page with a wide date range, parses the HTML
|
||||||
first outbound XHR to capture the ``sid``/``fid``/``tbid``/``rid`` headers,
|
table, and intercepts the ``DisplayValuation`` XHR for the current
|
||||||
then closes the browser and continues with plain httpx.
|
fund holdings. On 401/idle-timeout we raise
|
||||||
|
:class:`FidelitySessionError` so Prometheus alerts Viktor to re-seed.
|
||||||
|
|
||||||
3. **Re-seed trigger**: on any 401 from the JSON API we raise
|
## Emitted Activity shape
|
||||||
:class:`FidelitySessionError`; the CronJob fails loudly and Prometheus
|
|
||||||
alerts Viktor to run the seed command again.
|
|
||||||
|
|
||||||
Remember-device typically survives 30-90 days on Fidelity, so we expect the
|
- One ``DEPOSIT`` per cash-impacting transaction (Regular Premium, Single
|
||||||
re-seed to be a quarterly manual step — not monthly.
|
Premium, rebate, etc.). ``external_id = fidelity:tx:<sha256[:16]>``.
|
||||||
|
- One synthetic ``DEPOSIT`` for unrealised gains so WF's Net Worth matches
|
||||||
## Data model
|
the Fidelity dashboard. ``external_id =
|
||||||
|
fidelity:gains:<YYYY-MM-DD>``.
|
||||||
Salary-sacrifice scheme with two contribution streams (employee + employer),
|
- Bulk Switches / Fund Switches are skipped (no cash movement).
|
||||||
both pre-tax. Each contribution buys units across one or more funds. We emit:
|
|
||||||
|
|
||||||
- ``DEPOSIT`` per employee-or-employer cash inflow (external_id carries
|
|
||||||
``fidelity:<doc-id>:<source>``).
|
|
||||||
- ``BUY`` per fund-unit purchase (``symbol`` = fund ISIN or Fidelity code,
|
|
||||||
``quantity`` = units, ``unit_price`` = GBp or GBP per unit).
|
|
||||||
|
|
||||||
All currency is GBP. The single WF account is ``AccountType.WORKPLACE_PENSION``.
|
|
||||||
"""
|
"""
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import contextlib
|
||||||
import logging
|
import logging
|
||||||
from collections.abc import AsyncIterator
|
from collections.abc import AsyncIterator
|
||||||
from datetime import datetime
|
from datetime import UTC, datetime
|
||||||
from typing import NamedTuple
|
from decimal import Decimal
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any, NamedTuple
|
||||||
|
|
||||||
from broker_sync.models import Account, AccountType, Activity
|
from broker_sync.models import Account, AccountType, Activity, ActivityType
|
||||||
|
from broker_sync.providers.parsers.fidelity import (
|
||||||
|
FidelityCashTx,
|
||||||
|
FidelityHolding,
|
||||||
|
parse_transactions_html,
|
||||||
|
parse_valuation_json,
|
||||||
|
)
|
||||||
|
|
||||||
log = logging.getLogger(__name__)
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
ACCOUNT_ID = "fidelity-workplace-pension"
|
ACCOUNT_ID = "fidelity-workplace-pension"
|
||||||
_CCY = "GBP"
|
_CCY = "GBP"
|
||||||
|
|
||||||
# PlanViewer's private JSON backend. Endpoint paths are reverse-engineered from
|
_PV_BASE = "https://www.planviewer.fidelity.co.uk"
|
||||||
# Viktor's DevTools cURLs and validated by the unit tests' fixtures.
|
_PV_TX_PATH = "/planviewer/DisplayMyPlanMemberTransHist.action"
|
||||||
_API_BASE = "https://prd.wiciam.fidelity.co.uk"
|
_PV_VALUATION_PATH = "/planviewer/DisplayValuation.action"
|
||||||
|
_PV_LANDING = "https://www.planviewer.fidelity.co.uk/"
|
||||||
|
|
||||||
|
# A wide backfill cap; scheme can't predate 1990.
|
||||||
|
_BACKFILL_START = "01 Jan 1990"
|
||||||
|
|
||||||
|
|
||||||
class FidelityCreds(NamedTuple):
|
class FidelityCreds(NamedTuple):
|
||||||
"""Credentials + session state required to hit the PlanViewer backend."""
|
"""Paths needed to run the provider."""
|
||||||
storage_state_path: str
|
storage_state_path: str
|
||||||
plan_id: str
|
plan_id: str
|
||||||
headless: bool = True
|
headless: bool = True
|
||||||
|
|
||||||
|
|
||||||
class FidelitySessionError(Exception):
|
class FidelitySessionError(Exception):
|
||||||
"""Raised when PlanViewer returns 401/403 — storage_state is stale.
|
"""Raised when PlanViewer rejects the saved session — re-seed required."""
|
||||||
|
|
||||||
Recovery: run ``broker-sync fidelity-seed`` in a browser to refresh the
|
|
||||||
storage_state blob in Vault, then re-run the CronJob.
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class FidelityProviderConfigError(Exception):
|
class FidelityProviderConfigError(Exception):
|
||||||
"""Raised when the provider is asked to run but required config (plan id,
|
"""Raised when provider config is missing or obviously wrong."""
|
||||||
storage_state path) is missing or obviously wrong."""
|
|
||||||
|
|
||||||
|
def _tx_to_activity(tx: FidelityCashTx) -> Activity:
|
||||||
|
"""Map a Fidelity cash transaction to a canonical DEPOSIT."""
|
||||||
|
return Activity(
|
||||||
|
external_id=tx.external_id,
|
||||||
|
account_id=ACCOUNT_ID,
|
||||||
|
account_type=AccountType.WORKPLACE_PENSION,
|
||||||
|
date=tx.date,
|
||||||
|
activity_type=ActivityType.DEPOSIT,
|
||||||
|
currency=_CCY,
|
||||||
|
amount=tx.amount,
|
||||||
|
notes=f"fidelity-planviewer:{tx.tx_type}",
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _gains_offset_activity(
|
||||||
|
holdings: list[FidelityHolding],
|
||||||
|
transactions: list[FidelityCashTx],
|
||||||
|
as_of: datetime,
|
||||||
|
) -> Activity | None:
|
||||||
|
"""Create a synthetic DEPOSIT/WITHDRAWAL so WF Net Worth matches the
|
||||||
|
Fidelity dashboard's reported pot value.
|
||||||
|
|
||||||
|
The offset carries a date-derived external_id so monthly runs refresh
|
||||||
|
the same synthetic entry rather than stacking duplicates.
|
||||||
|
"""
|
||||||
|
if not holdings:
|
||||||
|
return None
|
||||||
|
total_value = sum((h.total_value for h in holdings), Decimal(0))
|
||||||
|
total_contrib = sum((t.amount for t in transactions), Decimal(0))
|
||||||
|
gains = total_value - total_contrib
|
||||||
|
if gains == 0:
|
||||||
|
return None
|
||||||
|
return Activity(
|
||||||
|
external_id=f"fidelity:gains:{as_of.date().isoformat()}",
|
||||||
|
account_id=ACCOUNT_ID,
|
||||||
|
account_type=AccountType.WORKPLACE_PENSION,
|
||||||
|
date=as_of,
|
||||||
|
activity_type=ActivityType.DEPOSIT if gains > 0 else ActivityType.WITHDRAWAL,
|
||||||
|
currency=_CCY,
|
||||||
|
amount=abs(gains),
|
||||||
|
notes=(f"fidelity-planviewer:unrealised-gains-offset "
|
||||||
|
f"(pot=£{total_value}, contrib=£{total_contrib})"),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class FidelityPlanViewerProvider:
|
class FidelityPlanViewerProvider:
|
||||||
"""Read-only provider against Fidelity UK PlanViewer.
|
"""Read-only provider against Fidelity UK PlanViewer.
|
||||||
|
|
||||||
Per the Provider protocol consumed by ``broker_sync.pipeline``:
|
Lifecycle:
|
||||||
|
- ``accounts()`` advertises the single WF workplace-pension account.
|
||||||
- ``.accounts()`` advertises the single workplace-pension WF account we
|
- ``fetch(since, before)`` opens a Playwright session with the saved
|
||||||
write into.
|
storage_state, navigates to the transaction-history page with a wide
|
||||||
- ``.fetch(since, before)`` is an async generator that yields canonical
|
date range, scrapes the table, and intercepts the valuation XHR.
|
||||||
``Activity`` objects.
|
|
||||||
"""
|
"""
|
||||||
name = "fidelity-planviewer"
|
name = "fidelity-planviewer"
|
||||||
|
|
||||||
|
|
@ -108,21 +148,106 @@ class FidelityPlanViewerProvider:
|
||||||
since: datetime | None = None,
|
since: datetime | None = None,
|
||||||
before: datetime | None = None,
|
before: datetime | None = None,
|
||||||
) -> AsyncIterator[Activity]:
|
) -> AsyncIterator[Activity]:
|
||||||
"""Yield Activity records.
|
state_path = self._creds.storage_state_path
|
||||||
|
if not Path(state_path).exists():
|
||||||
|
raise FidelityProviderConfigError(
|
||||||
|
f"storage_state not found at {state_path} — "
|
||||||
|
"run `broker-sync fidelity-seed` first")
|
||||||
|
|
||||||
Implementation blocked on captured endpoint shapes. Viktor will paste
|
tx_html, valuation_json = await _scrape_live_session(
|
||||||
the transactions + holdings POST cURLs from DevTools, then we wire the
|
state_path=state_path, headless=self._creds.headless,
|
||||||
parsers and this method lights up.
|
|
||||||
"""
|
|
||||||
# Guard against accidentally running before endpoint reverse-engineering
|
|
||||||
# is done — makes the CronJob fail loudly with an actionable message
|
|
||||||
# rather than silently importing nothing.
|
|
||||||
raise FidelityProviderConfigError(
|
|
||||||
"Fidelity ingest not yet enabled — PlanViewer endpoint paths have "
|
|
||||||
"not been captured. Paste the POST cURLs from DevTools for the "
|
|
||||||
"transactions + holdings views and re-apply the provider update."
|
|
||||||
)
|
)
|
||||||
# Unreachable yield — keeps the return type AsyncIterator[Activity]
|
transactions = parse_transactions_html(tx_html)
|
||||||
# once the raise above is removed.
|
holdings = parse_valuation_json(valuation_json)
|
||||||
if False: # pragma: no cover
|
log.info("fidelity: parsed %d transactions, %d holdings",
|
||||||
yield
|
len(transactions), len(holdings))
|
||||||
|
|
||||||
|
for tx in transactions:
|
||||||
|
if since is not None and tx.date < since:
|
||||||
|
continue
|
||||||
|
if before is not None and tx.date >= before:
|
||||||
|
continue
|
||||||
|
yield _tx_to_activity(tx)
|
||||||
|
|
||||||
|
# The gains offset is always "as of now" so it reflects today's pot.
|
||||||
|
# Only emit when the caller isn't windowing (full state).
|
||||||
|
if since is None and before is None:
|
||||||
|
offset = _gains_offset_activity(holdings, transactions, datetime.now(UTC))
|
||||||
|
if offset is not None:
|
||||||
|
yield offset
|
||||||
|
|
||||||
|
|
||||||
|
async def _scrape_live_session(
|
||||||
|
*,
|
||||||
|
state_path: str,
|
||||||
|
headless: bool,
|
||||||
|
) -> tuple[str, dict[str, Any]]:
|
||||||
|
"""Load storage_state, navigate the transaction + valuation pages,
|
||||||
|
return (transactions HTML, valuation JSON payload).
|
||||||
|
|
||||||
|
Raises :class:`FidelitySessionError` if the session is dead (15-min idle,
|
||||||
|
cookie expiry, etc.) — Viktor must re-seed.
|
||||||
|
"""
|
||||||
|
from playwright.async_api import async_playwright
|
||||||
|
|
||||||
|
captured_valuation: dict[str, dict[str, Any]] = {}
|
||||||
|
async with async_playwright() as pw:
|
||||||
|
browser = await pw.chromium.launch(headless=headless)
|
||||||
|
try:
|
||||||
|
ctx = await browser.new_context(
|
||||||
|
storage_state=state_path,
|
||||||
|
user_agent=("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
|
||||||
|
"AppleWebKit/537.36 (KHTML, like Gecko) "
|
||||||
|
"Chrome/147.0.0.0 Safari/537.36"),
|
||||||
|
viewport={"width": 1280, "height": 900},
|
||||||
|
)
|
||||||
|
page = await ctx.new_page()
|
||||||
|
|
||||||
|
async def on_response(resp: Any) -> None:
|
||||||
|
if _PV_VALUATION_PATH in resp.url and resp.status < 400:
|
||||||
|
with contextlib.suppress(Exception):
|
||||||
|
captured_valuation["payload"] = await resp.json()
|
||||||
|
page.on("response", on_response)
|
||||||
|
|
||||||
|
# Trigger session + capture valuation by navigating through landing
|
||||||
|
# → main page. The SPA fires DisplayValuation on the main page.
|
||||||
|
await page.goto(_PV_LANDING, wait_until="networkidle", timeout=30000)
|
||||||
|
await page.wait_for_timeout(2000)
|
||||||
|
main_url = f"{_PV_BASE}/planviewer/DisplayMainPage.action"
|
||||||
|
await page.goto(main_url, wait_until="networkidle", timeout=30000)
|
||||||
|
await page.wait_for_timeout(3000)
|
||||||
|
if "idle for more than 15 minutes" in (await page.content()) \
|
||||||
|
or "id.fidelity.co.uk" in page.url:
|
||||||
|
raise FidelitySessionError(
|
||||||
|
"PlanViewer session stale — run `broker-sync fidelity-seed`")
|
||||||
|
|
||||||
|
# Now pull the transactions page with a wide date range.
|
||||||
|
await page.goto(f"{_PV_BASE}{_PV_TX_PATH}",
|
||||||
|
wait_until="networkidle", timeout=30000)
|
||||||
|
await page.wait_for_timeout(1500)
|
||||||
|
await page.fill('input[name="startDate"]', _BACKFILL_START)
|
||||||
|
today = await page.evaluate(
|
||||||
|
"new Date().toLocaleDateString('en-GB',"
|
||||||
|
"{day:'2-digit',month:'short',year:'numeric'}).replace(/,/g,'')")
|
||||||
|
await page.fill('input[name="endDate"]', today)
|
||||||
|
await page.focus('input[name="endDate"]')
|
||||||
|
await page.keyboard.press("Enter")
|
||||||
|
with contextlib.suppress(Exception):
|
||||||
|
await page.wait_for_load_state("networkidle", timeout=15000)
|
||||||
|
await page.wait_for_timeout(2000)
|
||||||
|
tx_html = await page.content()
|
||||||
|
|
||||||
|
# If valuation wasn't picked up on the main page, request directly.
|
||||||
|
if "payload" not in captured_valuation:
|
||||||
|
r = await page.request.get(f"{_PV_BASE}{_PV_VALUATION_PATH}")
|
||||||
|
if r.ok:
|
||||||
|
with contextlib.suppress(Exception):
|
||||||
|
captured_valuation["payload"] = await r.json()
|
||||||
|
|
||||||
|
# Roll the storage_state so the next run benefits from any refresh.
|
||||||
|
await ctx.storage_state(path=state_path)
|
||||||
|
finally:
|
||||||
|
await browser.close()
|
||||||
|
|
||||||
|
valuation: dict[str, Any] = captured_valuation.get("payload") or {}
|
||||||
|
return tx_html, valuation
|
||||||
|
|
|
||||||
129
broker_sync/providers/parsers/fidelity.py
Normal file
129
broker_sync/providers/parsers/fidelity.py
Normal file
|
|
@ -0,0 +1,129 @@
|
||||||
|
"""Parsers for Fidelity UK PlanViewer scraped data.
|
||||||
|
|
||||||
|
Two inputs:
|
||||||
|
|
||||||
|
- **Transactions HTML** from ``/planviewer/DisplayMyPlanMemberTransHist.action``
|
||||||
|
rendered with a wide date range. The relevant <table> has
|
||||||
|
``id="myplan_member_transhist_support"``.
|
||||||
|
- **Valuation JSON** from the XHR ``/planviewer/DisplayValuation.action`` —
|
||||||
|
the SPA calls this to render the my-investments dashboard. Contains
|
||||||
|
current unit holdings + price + breakdown by contribution type.
|
||||||
|
"""
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import hashlib
|
||||||
|
import re
|
||||||
|
from dataclasses import dataclass
|
||||||
|
from datetime import UTC, datetime
|
||||||
|
from decimal import Decimal
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
from bs4 import BeautifulSoup
|
||||||
|
|
||||||
|
_AMOUNT_RE = re.compile(r"\u00a3([\d,]+(?:\.\d+)?)")
|
||||||
|
|
||||||
|
# Fidelity transaction type strings we care about
|
||||||
|
_TX_DEPOSIT_TYPES = {
|
||||||
|
"regular premium",
|
||||||
|
"single premium",
|
||||||
|
"investment management rebate",
|
||||||
|
}
|
||||||
|
_TX_IGNORE_TYPES = {
|
||||||
|
"bulk switch", # pure reallocation, no cash impact
|
||||||
|
"fund switch",
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class FidelityCashTx:
|
||||||
|
"""A single cash-impacting transaction from the transaction history page."""
|
||||||
|
date: datetime
|
||||||
|
tx_type: str # raw Fidelity label ("Regular Premium", "Single Premium", …)
|
||||||
|
amount: Decimal
|
||||||
|
external_id: str
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class FidelityHolding:
|
||||||
|
"""A current fund-unit holding from DisplayValuation.action."""
|
||||||
|
fund_code: str
|
||||||
|
fund_name: str
|
||||||
|
units: Decimal
|
||||||
|
unit_price: Decimal
|
||||||
|
currency: str
|
||||||
|
total_value: Decimal
|
||||||
|
# Contribution-type breakdown ({"SASC": Decimal(...), "ERXS": Decimal(...)})
|
||||||
|
units_by_source: dict[str, Decimal]
|
||||||
|
|
||||||
|
|
||||||
|
def parse_transactions_html(html: str) -> list[FidelityCashTx]:
|
||||||
|
"""Extract cash-impacting transactions from the transaction history page.
|
||||||
|
|
||||||
|
Skips bulk switches (no cash movement) and header/total rows. Deterministic
|
||||||
|
external_id so re-runs dedup against the same rows.
|
||||||
|
"""
|
||||||
|
soup = BeautifulSoup(html, "html.parser")
|
||||||
|
out: list[FidelityCashTx] = []
|
||||||
|
for tr in soup.select("table#myplan_member_transhist_support tr"):
|
||||||
|
cells = [td.get_text(" ", strip=True) for td in tr.find_all("td")]
|
||||||
|
if len(cells) != 7:
|
||||||
|
continue
|
||||||
|
date_str, tx_type, _f, _c, _u, _p, amount_str = cells
|
||||||
|
m_date = re.match(r"(\d{2})/(\d{2})/(\d{4})", date_str)
|
||||||
|
if not m_date:
|
||||||
|
continue
|
||||||
|
tx_lower = tx_type.lower()
|
||||||
|
if tx_lower in _TX_IGNORE_TYPES or tx_type in ("-",):
|
||||||
|
continue
|
||||||
|
m_amt = _AMOUNT_RE.search(amount_str)
|
||||||
|
if not m_amt:
|
||||||
|
continue
|
||||||
|
amount = Decimal(m_amt.group(1).replace(",", ""))
|
||||||
|
if amount == 0:
|
||||||
|
continue
|
||||||
|
dd, mm, yyyy = m_date.groups()
|
||||||
|
dt = datetime(int(yyyy), int(mm), int(dd), tzinfo=UTC)
|
||||||
|
fp = hashlib.sha256(
|
||||||
|
f"{dt.isoformat()}|{tx_type}|{amount}".encode()
|
||||||
|
).hexdigest()[:16]
|
||||||
|
out.append(FidelityCashTx(
|
||||||
|
date=dt,
|
||||||
|
tx_type=tx_type,
|
||||||
|
amount=amount,
|
||||||
|
external_id=f"fidelity:tx:{fp}",
|
||||||
|
))
|
||||||
|
return out
|
||||||
|
|
||||||
|
|
||||||
|
def parse_valuation_json(payload: Any) -> list[FidelityHolding]:
|
||||||
|
"""Extract current fund holdings from DisplayValuation.action JSON."""
|
||||||
|
out: list[FidelityHolding] = []
|
||||||
|
for v in payload.get("valuations", []):
|
||||||
|
asset = v.get("asset") or {}
|
||||||
|
fund_code = next(
|
||||||
|
(a.get("value") for a in asset.get("assetId", []) if a.get("type") == "FUND_CODE"),
|
||||||
|
None,
|
||||||
|
)
|
||||||
|
if not fund_code:
|
||||||
|
continue
|
||||||
|
fund_name = asset.get("name") or fund_code
|
||||||
|
units = Decimal(str((v.get("units") or {}).get("total") or 0))
|
||||||
|
price = (v.get("price") or {})
|
||||||
|
unit_price = Decimal(str(price.get("value") or 0))
|
||||||
|
currency = price.get("currency") or "GBP"
|
||||||
|
total = Decimal(str((v.get("valuation") or {}).get("total") or 0))
|
||||||
|
groups = (v.get("units") or {}).get("group", []) or []
|
||||||
|
by_src = {}
|
||||||
|
for g in groups:
|
||||||
|
if g.get("type") == "CONTRIBUTION_TYPE" and g.get("groupId"):
|
||||||
|
by_src[g["groupId"]] = Decimal(str(g.get("unit", {}).get("total") or 0))
|
||||||
|
out.append(FidelityHolding(
|
||||||
|
fund_code=fund_code,
|
||||||
|
fund_name=fund_name,
|
||||||
|
units=units,
|
||||||
|
unit_price=unit_price,
|
||||||
|
currency=currency,
|
||||||
|
total_value=total,
|
||||||
|
units_by_source=by_src,
|
||||||
|
))
|
||||||
|
return out
|
||||||
1707
tests/fixtures/fidelity/transactions-full.html
vendored
Normal file
1707
tests/fixtures/fidelity/transactions-full.html
vendored
Normal file
File diff suppressed because one or more lines are too long
2
tests/fixtures/fidelity/valuation.json
vendored
Normal file
2
tests/fixtures/fidelity/valuation.json
vendored
Normal file
|
|
@ -0,0 +1,2 @@
|
||||||
|
{"valuations":[{"asset":{"assetId":[{"type":"FUND_CODE","value":"KDOA"}],"name":"Passive Global Equity Fund - Class 9"},"units":{"total":44920.21,"available":null,"crystallised":null,"uncrystallised":null,"group":[{"groupId":"BONW","type":"CONTRIBUTION_TYPE","name":"Bonus Waiver","unit":{"total":11490.84,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"ERXS","type":"CONTRIBUTION_TYPE","name":"Company","unit":{"total":17148.27,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"SASC","type":"CONTRIBUTION_TYPE","name":"Salary Sacrifice","unit":{"total":11432.20,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"TREX","type":"CONTRIBUTION_TYPE","name":"Transfer In","unit":{"total":4848.90,"available":null,"crystallised":null,"uncrystallised":null}}]},"price":{"value":3.066,"datetime":"2026-04-17","currency":"GBP"},"valuation":{"total":137725.35,"available":null,"crystallised":null,"uncrystallised":null,"group":[{"groupId":"BONW","type":"CONTRIBUTION_TYPE","name":"Bonus Waiver","valuation":{"total":35230.91,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"ERXS","type":"CONTRIBUTION_TYPE","name":"Company","valuation":{"total":52576.60,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"SASC","type":"CONTRIBUTION_TYPE","name":"Salary Sacrifice","valuation":{"total":35051.12,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"TREX","type":"CONTRIBUTION_TYPE","name":"Transfer In","valuation":{"total":14866.72,"available":null,"crystallised":null,"uncrystallised":null}}],"valuationType":"Value"},"currency":"GBP"},{"asset":{"assetId":[{"type":"FUND_CODE","value":"KCVT"}],"name":"FutureWise Target 2065 - Class 10"},"units":{"total":230.02,"available":null,"crystallised":null,"uncrystallised":null,"group":[{"groupId":"ERXS","type":"CONTRIBUTION_TYPE","name":"Company","unit":{"total":153.35,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"SASC","type":"CONTRIBUTION_TYPE","name":"Salary Sacrifice","unit":{"total":76.67,"available":null,"crystallised":null,"uncrystallised":null}}]},"price":{"value":3.254,"datetime":"2026-04-17","currency":"GBP"},"valuation":{"total":748.48,"available":null,"crystallised":null,"uncrystallised":null,"group":[{"groupId":"ERXS","type":"CONTRIBUTION_TYPE","name":"Company","valuation":{"total":498.99,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"SASC","type":"CONTRIBUTION_TYPE","name":"Salary Sacrifice","valuation":{"total":249.49,"available":null,"crystallised":null,"uncrystallised":null}}],"valuationType":"Value"},"currency":"GBP"},{"asset":{"assetId":[{"type":"FUND_CODE","value":"LAFC"}],"name":"Volatility Managed Multi Asset Fund"},"units":{"total":106.64,"available":null,"crystallised":null,"uncrystallised":null,"group":[{"groupId":"ERXS","type":"CONTRIBUTION_TYPE","name":"Company","unit":{"total":71.09,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"SASC","type":"CONTRIBUTION_TYPE","name":"Salary Sacrifice","unit":{"total":35.55,"available":null,"crystallised":null,"uncrystallised":null}}]},"price":{"value":252.9000,"datetime":"2026-04-17","currency":"GBP"},"valuation":{"total":269.70,"available":null,"crystallised":null,"uncrystallised":null,"group":[{"groupId":"ERXS","type":"CONTRIBUTION_TYPE","name":"Company","valuation":{"total":179.80,"available":null,"crystallised":null,"uncrystallised":null}},{"groupId":"SASC","type":"CONTRIBUTION_TYPE","name":"Salary Sacrifice","valuation":{"total":89.90,"available":null,"crystallised":null,"uncrystallised":null}}],"valuationType":"Value"},"currency":"GBP"}],"valuationSum":{"total":138743.53,"available":0.0,"crystallised":null,"uncrystallised":null,"currency":"GBP"},"asOfDateTime":"2026-04-17T12:00:00+01:00"}
|
||||||
|
|
||||||
|
|
@ -1,22 +1,33 @@
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import json
|
||||||
|
from datetime import UTC, datetime
|
||||||
|
from decimal import Decimal
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
from broker_sync.models import Account, AccountType
|
from broker_sync.models import Account, AccountType, ActivityType
|
||||||
from broker_sync.providers.fidelity_planviewer import (
|
from broker_sync.providers.fidelity_planviewer import (
|
||||||
ACCOUNT_ID,
|
ACCOUNT_ID,
|
||||||
FidelityCreds,
|
FidelityCreds,
|
||||||
FidelityPlanViewerProvider,
|
FidelityPlanViewerProvider,
|
||||||
FidelityProviderConfigError,
|
FidelityProviderConfigError,
|
||||||
|
_gains_offset_activity,
|
||||||
)
|
)
|
||||||
|
from broker_sync.providers.parsers.fidelity import (
|
||||||
|
parse_transactions_html,
|
||||||
|
parse_valuation_json,
|
||||||
|
)
|
||||||
|
|
||||||
|
_FIXTURES = Path(__file__).parent.parent / "fixtures" / "fidelity"
|
||||||
|
|
||||||
|
|
||||||
def test_accounts_exposes_single_workplace_pension_account() -> None:
|
def test_accounts_exposes_single_workplace_pension_account() -> None:
|
||||||
prov = FidelityPlanViewerProvider(FidelityCreds(
|
prov = FidelityPlanViewerProvider(FidelityCreds(
|
||||||
storage_state_path="/tmp/x", plan_id="ABC123",
|
storage_state_path="/tmp/x", plan_id="META",
|
||||||
))
|
))
|
||||||
accounts = prov.accounts()
|
assert prov.accounts() == [
|
||||||
assert accounts == [
|
|
||||||
Account(
|
Account(
|
||||||
id=ACCOUNT_ID,
|
id=ACCOUNT_ID,
|
||||||
name="Fidelity UK Pension",
|
name="Fidelity UK Pension",
|
||||||
|
|
@ -27,16 +38,79 @@ def test_accounts_exposes_single_workplace_pension_account() -> None:
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
async def test_fetch_raises_until_endpoints_captured() -> None:
|
async def test_fetch_raises_without_storage_state() -> None:
|
||||||
"""Until Viktor pastes the transactions/holdings cURLs, fetch() must fail
|
|
||||||
loudly rather than silently importing nothing.
|
|
||||||
|
|
||||||
Swap this test for real parser tests once the API shapes are known and
|
|
||||||
`FidelityPlanViewerProvider.fetch` is wired up against fixtures.
|
|
||||||
"""
|
|
||||||
prov = FidelityPlanViewerProvider(FidelityCreds(
|
prov = FidelityPlanViewerProvider(FidelityCreds(
|
||||||
storage_state_path="/tmp/x", plan_id="ABC123",
|
storage_state_path="/tmp/does-not-exist-xyzzy.json", plan_id="META",
|
||||||
))
|
))
|
||||||
with pytest.raises(FidelityProviderConfigError, match="endpoint paths"):
|
with pytest.raises(FidelityProviderConfigError, match="storage_state"):
|
||||||
async for _ in prov.fetch():
|
async for _ in prov.fetch():
|
||||||
pytest.fail("fetch should not yield before endpoints are configured")
|
pytest.fail("should have raised before yielding")
|
||||||
|
|
||||||
|
|
||||||
|
# -- parser tests against real (captured) fixture --
|
||||||
|
|
||||||
|
|
||||||
|
def test_parse_transactions_real_fixture() -> None:
|
||||||
|
html = (_FIXTURES / "transactions-full.html").read_text()
|
||||||
|
txs = parse_transactions_html(html)
|
||||||
|
# Scheme has ~48 months + a couple of single premiums + 1 rebate;
|
||||||
|
# Bulk Switches must be filtered out (zero-amount rows).
|
||||||
|
assert 40 <= len(txs) <= 100
|
||||||
|
# All dates are within the scheme's lifetime (2022-03 to today-ish).
|
||||||
|
assert all(tx.date >= datetime(2022, 1, 1, tzinfo=UTC) for tx in txs)
|
||||||
|
# Sum should match the header total on the page (£102,004.15 at
|
||||||
|
# fixture time). Allow a £5 tolerance in case the page summary row
|
||||||
|
# changes in future captures — the unit test primarily guards parsing
|
||||||
|
# correctness, not drift in the fixture.
|
||||||
|
total = sum((tx.amount for tx in txs), Decimal(0))
|
||||||
|
assert abs(total - Decimal("102004.15")) < Decimal("5")
|
||||||
|
|
||||||
|
|
||||||
|
def test_parse_transactions_skips_bulk_switch() -> None:
|
||||||
|
html = (_FIXTURES / "transactions-full.html").read_text()
|
||||||
|
txs = parse_transactions_html(html)
|
||||||
|
assert not any("bulk switch" in tx.tx_type.lower() for tx in txs)
|
||||||
|
|
||||||
|
|
||||||
|
def test_parse_transactions_external_id_deterministic() -> None:
|
||||||
|
html = (_FIXTURES / "transactions-full.html").read_text()
|
||||||
|
a = parse_transactions_html(html)
|
||||||
|
b = parse_transactions_html(html)
|
||||||
|
assert [tx.external_id for tx in a] == [tx.external_id for tx in b]
|
||||||
|
assert all(tx.external_id.startswith("fidelity:tx:") for tx in a)
|
||||||
|
|
||||||
|
|
||||||
|
def test_parse_valuation_fixture() -> None:
|
||||||
|
payload = json.loads((_FIXTURES / "valuation.json").read_text())
|
||||||
|
holdings = parse_valuation_json(payload)
|
||||||
|
assert len(holdings) >= 1
|
||||||
|
h = holdings[0]
|
||||||
|
assert h.fund_code == "KDOA"
|
||||||
|
assert "Passive Global Equity" in h.fund_name
|
||||||
|
assert h.currency == "GBP"
|
||||||
|
assert h.units > 0
|
||||||
|
assert h.unit_price > 0
|
||||||
|
# Value ≈ units * price
|
||||||
|
assert abs(h.total_value - h.units * h.unit_price) < Decimal("1")
|
||||||
|
# Contribution-type breakdown must parse
|
||||||
|
assert set(h.units_by_source.keys()) >= {"SASC", "ERXS"}
|
||||||
|
|
||||||
|
|
||||||
|
def test_gains_offset_emits_deposit_when_pot_exceeds_contributions() -> None:
|
||||||
|
html = (_FIXTURES / "transactions-full.html").read_text()
|
||||||
|
valuation = json.loads((_FIXTURES / "valuation.json").read_text())
|
||||||
|
txs = parse_transactions_html(html)
|
||||||
|
holdings = parse_valuation_json(valuation)
|
||||||
|
as_of = datetime(2026, 4, 18, tzinfo=UTC)
|
||||||
|
offset = _gains_offset_activity(holdings, txs, as_of)
|
||||||
|
assert offset is not None
|
||||||
|
assert offset.activity_type in (ActivityType.DEPOSIT, ActivityType.WITHDRAWAL)
|
||||||
|
assert offset.amount > 0
|
||||||
|
assert offset.external_id == "fidelity:gains:2026-04-18"
|
||||||
|
|
||||||
|
|
||||||
|
def test_gains_offset_none_when_no_holdings() -> None:
|
||||||
|
assert _gains_offset_activity(
|
||||||
|
holdings=[], transactions=[],
|
||||||
|
as_of=datetime(2026, 4, 18, tzinfo=UTC),
|
||||||
|
) is None
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue