feat(sec): A3 slice 1 — SEC client + CIK/SIC resolution + composite revision
First A3 implementation checkpoint (design: docs/dolt-sec-a3-design.md). - sec_client.py: async SEC EDGAR client honoring fair-access — identifying User-Agent (config), request spacing < 10 req/s, exponential backoff on 429, and 403 -> SecForbiddenError (alert and stop, never retry-loop). Fetchers: company_tickers (normalised, multi-class share CIK), submissions (merges the paginated filings.files shards so full history is visible), companyfacts, daily_index (fixed-width form.idx parse), latest_index_date. - sec_universe.py: resolve_ciks (tickers.cik backfill), refresh_sic (sic/sic_description), and the composite-revision pieces — universe_fingerprint (a new ticker changes the revision, so it's never no_op'd/starved), index_content_hash, compose_revision. - config + .env.example: SEC_USER_AGENT (must be a real contact email) + spacing / retries / timeout. Verified live against real SEC: AAPL->320193, GOOG==GOOGL, BRK-B resolved; submissions shard-merge proven (131 filings back to 1993); daily index parsed. Tests: 11 (mocked-transport parsing + 403/429 handling + resolution/fingerprint). Full suite 713 passed. Next slice: companyfacts -> snapshot parser + importer. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Claude Opus 4.8
@@ -43,6 +43,14 @@ DOLT_MIN_FREE_DISK_GB=5.0
|
||||
# import connection + advisory lock.
|
||||
DOLT_COMMAND_TIMEOUT_SECONDS=600.0
|
||||
|
||||
# SEC EDGAR (fundamentals, workstream A). SEC fair-access REQUIRES an identifying
|
||||
# User-Agent with a REAL contact email — set it, or requests get 403'd. Stay well
|
||||
# under 10 req/s (spacing below).
|
||||
SEC_USER_AGENT=signal-platform/1.0 (contact: you@example.com)
|
||||
SEC_REQUEST_SPACING_SECONDS=0.2
|
||||
SEC_MAX_RETRIES=4
|
||||
SEC_REQUEST_TIMEOUT_SECONDS=30.0
|
||||
|
||||
# Regime Monitor — FRED (VIX + HY credit spreads). Free key: https://fred.stlouisfed.org/docs/api/api_key.html
|
||||
# Optional: without it the volatility (V1) and credit (C1) pillars show as n/a.
|
||||
FRED_API_KEY=
|
||||
|
||||
@@ -52,6 +52,15 @@ class Settings(BaseSettings):
|
||||
# connection + advisory lock indefinitely.
|
||||
dolt_command_timeout_seconds: float = 600.0
|
||||
|
||||
# SEC EDGAR (workstream A, fundamentals). Fair-access policy REQUIRES an
|
||||
# identifying User-Agent with a contact email — set a real one. Stay well
|
||||
# under 10 req/s (spacing below); 403 means the UA/pattern is wrong → the
|
||||
# client alerts and stops rather than retry-looping.
|
||||
sec_user_agent: str = "signal-platform/1.0 (contact: set-a-real-email@example.com)"
|
||||
sec_request_spacing_seconds: float = 0.2
|
||||
sec_max_retries: int = 4
|
||||
sec_request_timeout_seconds: float = 30.0
|
||||
|
||||
# Regime Monitor — FRED (VIX level + HY credit spreads). Optional: without it
|
||||
# the volatility (P5) and credit-spread (F2) signals are reported as n/a.
|
||||
fred_api_key: str = ""
|
||||
|
||||
@@ -0,0 +1,289 @@
|
||||
"""Async SEC EDGAR client for the fundamentals importer (workstream A).
|
||||
|
||||
All access is batch (never at request time). This wraps the three SEC products
|
||||
the A3 design uses — `company_tickers.json`, `submissions/`, `companyfacts/`, and
|
||||
the daily filing index — behind one client that honors SEC's fair-access policy:
|
||||
|
||||
- an identifying ``User-Agent`` with a contact email on every request (config);
|
||||
- request spacing well under the 10 req/s limit;
|
||||
- exponential backoff + retry on 429;
|
||||
- **403 → alert and stop** (raise ``SecForbiddenError``), never a retry-loop — a
|
||||
403 means the UA or request pattern is wrong and retrying won't fix it.
|
||||
|
||||
Parsing lives here (index fixed-width, submissions pagination); DB writes and the
|
||||
snapshot mapping live in the importer. No conditional GETs — the companyfacts
|
||||
endpoint exposes no ETag/Last-Modified (verified), which is why the importer is
|
||||
daily-index driven rather than polling archives.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
from datetime import date, datetime
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
|
||||
from app.config import settings
|
||||
from app.exceptions import ProviderError
|
||||
from app.services.earnings_alignment import normalise_symbol
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_WWW = "https://www.sec.gov"
|
||||
_DATA = "https://data.sec.gov"
|
||||
|
||||
# Resolve CA bundle for explicit httpx verify (matches app/providers/fmp.py).
|
||||
_CA = os.environ.get("SSL_CERT_FILE", "")
|
||||
_CA_VERIFY: str | bool = _CA if _CA and Path(_CA).exists() else True
|
||||
|
||||
_FORMS_10 = frozenset({"10-K", "10-Q", "10-K/A", "10-Q/A"})
|
||||
|
||||
|
||||
class SecError(ProviderError):
|
||||
"""SEC request failed."""
|
||||
|
||||
|
||||
class SecForbiddenError(SecError):
|
||||
"""SEC returned 403 — User-Agent/pattern rejected. Alert and stop."""
|
||||
|
||||
|
||||
def cik10(cik: int | str) -> str:
|
||||
"""Zero-pad a CIK to the 10-digit form SEC URLs use (320193 -> 0000320193)."""
|
||||
return str(int(cik)).zfill(10)
|
||||
|
||||
|
||||
class SecClient:
|
||||
"""Fair-access SEC HTTP client. Use as ``async with SecClient() as c:``."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
user_agent: str | None = None,
|
||||
spacing_seconds: float | None = None,
|
||||
max_retries: int | None = None,
|
||||
timeout: float | None = None,
|
||||
transport: httpx.AsyncBaseTransport | None = None,
|
||||
) -> None:
|
||||
self._ua = user_agent or settings.sec_user_agent
|
||||
self._spacing = (
|
||||
spacing_seconds if spacing_seconds is not None else settings.sec_request_spacing_seconds
|
||||
)
|
||||
self._max_retries = (
|
||||
max_retries if max_retries is not None else settings.sec_max_retries
|
||||
)
|
||||
self._timeout = timeout if timeout is not None else settings.sec_request_timeout_seconds
|
||||
self._transport = transport # injectable for tests
|
||||
self._client: httpx.AsyncClient | None = None
|
||||
self._lock = asyncio.Lock()
|
||||
self._last_request = 0.0
|
||||
|
||||
async def __aenter__(self) -> "SecClient":
|
||||
self._client = httpx.AsyncClient(
|
||||
headers={"User-Agent": self._ua, "Accept-Encoding": "gzip, deflate"},
|
||||
timeout=self._timeout,
|
||||
verify=_CA_VERIFY,
|
||||
transport=self._transport,
|
||||
)
|
||||
return self
|
||||
|
||||
async def __aexit__(self, *exc) -> None:
|
||||
if self._client is not None:
|
||||
await self._client.aclose()
|
||||
self._client = None
|
||||
|
||||
async def _throttle(self) -> None:
|
||||
async with self._lock:
|
||||
now = asyncio.get_event_loop().time()
|
||||
wait = self._spacing - (now - self._last_request)
|
||||
if wait > 0:
|
||||
await asyncio.sleep(wait)
|
||||
self._last_request = asyncio.get_event_loop().time()
|
||||
|
||||
async def _get(self, url: str) -> httpx.Response:
|
||||
assert self._client is not None, "use `async with SecClient()`"
|
||||
attempt = 0
|
||||
while True:
|
||||
await self._throttle()
|
||||
resp = await self._client.get(url)
|
||||
if resp.status_code == 403:
|
||||
raise SecForbiddenError(
|
||||
f"SEC 403 for {url} — User-Agent/pattern rejected; set a real "
|
||||
"sec_user_agent contact email"
|
||||
)
|
||||
if resp.status_code == 429:
|
||||
attempt += 1
|
||||
if attempt > self._max_retries:
|
||||
raise SecError(f"SEC 429 after {self._max_retries} retries: {url}")
|
||||
backoff = min(2.0**attempt, 30.0)
|
||||
logger.warning("SEC 429 for %s — backoff %.1fs (attempt %d)", url, backoff, attempt)
|
||||
await asyncio.sleep(backoff)
|
||||
continue
|
||||
if resp.status_code >= 400:
|
||||
raise SecError(f"SEC {resp.status_code} for {url}")
|
||||
return resp
|
||||
|
||||
async def get_json(self, url: str) -> Any:
|
||||
return (await self._get(url)).json()
|
||||
|
||||
async def get_text(self, url: str) -> str:
|
||||
return (await self._get(url)).text
|
||||
|
||||
# -- domain fetchers ---------------------------------------------------
|
||||
|
||||
async def company_tickers(self) -> dict[str, int]:
|
||||
"""Map normalised ticker -> CIK (int). Multi-class tickers share a CIK."""
|
||||
data = await self.get_json(f"{_WWW}/files/company_tickers.json")
|
||||
out: dict[str, int] = {}
|
||||
for row in data.values():
|
||||
sym = normalise_symbol(row.get("ticker"))
|
||||
if sym:
|
||||
out[sym] = int(row["cik_str"])
|
||||
return out
|
||||
|
||||
async def submissions(self, cik: int | str) -> dict[str, Any]:
|
||||
"""Issuer metadata + the FULL merged filing history.
|
||||
|
||||
``filings.recent`` caps at 1000; older accessions live in
|
||||
``filings.files[]`` shards. This merges them so backfill sees every
|
||||
filing's reportDate / acceptanceDateTime / isXBRL.
|
||||
"""
|
||||
base = await self.get_json(f"{_DATA}/submissions/CIK{cik10(cik)}.json")
|
||||
filings = _rows_from_arrays(base["filings"]["recent"])
|
||||
for shard in base["filings"].get("files") or []:
|
||||
shard_data = await self.get_json(f"{_DATA}/submissions/{shard['name']}")
|
||||
filings.extend(_rows_from_arrays(shard_data))
|
||||
return {
|
||||
"cik": int(base["cik"]),
|
||||
"name": base.get("name"),
|
||||
"sic": base.get("sic"),
|
||||
"sic_description": base.get("sicDescription"),
|
||||
"fiscal_year_end": base.get("fiscalYearEnd"),
|
||||
"tickers": base.get("tickers") or [],
|
||||
"filings": filings,
|
||||
}
|
||||
|
||||
async def companyfacts(self, cik: int | str) -> dict[str, Any]:
|
||||
"""Raw companyfacts JSON ({cik, entityName, facts})."""
|
||||
return await self.get_json(f"{_DATA}/api/xbrl/companyfacts/CIK{cik10(cik)}.json")
|
||||
|
||||
async def latest_index_date(self, today: date | None = None) -> date | None:
|
||||
"""The most recent published daily-index date (drives the revision). Checks
|
||||
the current quarter, falling back to the previous one at a quarter boundary."""
|
||||
today = today or date.today()
|
||||
for year, qtr in _quarters_back(today, 2):
|
||||
url = f"{_WWW}/Archives/edgar/daily-index/{year}/QTR{qtr}/index.json"
|
||||
try:
|
||||
idx = await self.get_json(url)
|
||||
except SecError:
|
||||
continue
|
||||
dates = [
|
||||
d
|
||||
for item in idx.get("directory", {}).get("item", [])
|
||||
if (d := _index_file_date(item.get("name", ""))) is not None
|
||||
and d <= today
|
||||
]
|
||||
if dates:
|
||||
return max(dates)
|
||||
return None
|
||||
|
||||
async def daily_index(self, day: date) -> list[dict[str, Any]]:
|
||||
"""Parse the daily form index into 10-K/10-Q(/A) rows for all issuers.
|
||||
|
||||
Returns [{form, cik, accession, company}]. The caller filters to the
|
||||
tracked universe. A missing index (weekend/holiday/not-yet-published)
|
||||
returns [] rather than raising.
|
||||
"""
|
||||
qtr = (day.month - 1) // 3 + 1
|
||||
url = f"{_WWW}/Archives/edgar/daily-index/{day.year}/QTR{qtr}/form.{day:%Y%m%d}.idx"
|
||||
try:
|
||||
text = await self.get_text(url)
|
||||
except SecError as exc:
|
||||
logger.info("no daily index for %s (%s)", day, exc)
|
||||
return []
|
||||
return _parse_form_index(text)
|
||||
|
||||
|
||||
def _rows_from_arrays(arrays: dict[str, list]) -> list[dict[str, Any]]:
|
||||
"""Turn SEC's parallel-array filing block into row dicts (keeping only 10-K/10-Q
|
||||
family filings — the ones that carry XBRL fundamentals)."""
|
||||
forms = arrays.get("form", [])
|
||||
out: list[dict[str, Any]] = []
|
||||
for i, form in enumerate(forms):
|
||||
if form not in _FORMS_10:
|
||||
continue
|
||||
out.append(
|
||||
{
|
||||
"accession": arrays["accessionNumber"][i],
|
||||
"form": form,
|
||||
"report_date": arrays["reportDate"][i] or None,
|
||||
"acceptance_datetime": arrays["acceptanceDateTime"][i] or None,
|
||||
"is_xbrl": bool(arrays.get("isXBRL", [0] * len(forms))[i]),
|
||||
}
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def _parse_form_index(text: str) -> list[dict[str, Any]]:
|
||||
"""Parse a daily ``form.YYYYMMDD.idx`` (fixed columns: Form / Company / CIK /
|
||||
Date Filed / File Name-with-accession)."""
|
||||
rows: list[dict[str, Any]] = []
|
||||
started = False
|
||||
for line in text.splitlines():
|
||||
if not started:
|
||||
if set(line.strip()) == {"-"}: # the dashed separator row
|
||||
started = True
|
||||
continue
|
||||
parts = line.split()
|
||||
if len(parts) < 5:
|
||||
continue
|
||||
form = parts[0]
|
||||
if form not in _FORMS_10:
|
||||
continue
|
||||
path = parts[-1] # edgar/data/<cik>/<accession>.txt
|
||||
cik = _cik_from_path(path)
|
||||
accession = _accession_from_path(path)
|
||||
if cik is None or accession is None:
|
||||
continue
|
||||
rows.append({"form": form, "cik": cik, "accession": accession, "path": path})
|
||||
return rows
|
||||
|
||||
|
||||
def _index_file_date(name: str) -> date | None:
|
||||
if name.startswith("form.") and name.endswith(".idx"):
|
||||
try:
|
||||
return datetime.strptime(name[5:13], "%Y%m%d").date()
|
||||
except ValueError:
|
||||
return None
|
||||
return None
|
||||
|
||||
|
||||
def _quarters_back(today: date, n: int) -> list[tuple[int, int]]:
|
||||
"""(year, quarter) for `today`'s quarter and the previous n-1, newest first."""
|
||||
q = (today.month - 1) // 3 + 1
|
||||
out = []
|
||||
y = today.year
|
||||
for _ in range(n):
|
||||
out.append((y, q))
|
||||
q -= 1
|
||||
if q == 0:
|
||||
q = 4
|
||||
y -= 1
|
||||
return out
|
||||
|
||||
|
||||
def _cik_from_path(path: str) -> int | None:
|
||||
segs = path.split("/")
|
||||
if len(segs) >= 3 and segs[2].isdigit():
|
||||
return int(segs[2])
|
||||
return None
|
||||
|
||||
|
||||
def _accession_from_path(path: str) -> str | None:
|
||||
stem = path.rsplit("/", 1)[-1]
|
||||
if stem.endswith(".txt"):
|
||||
stem = stem[:-4]
|
||||
return stem or None
|
||||
@@ -0,0 +1,87 @@
|
||||
"""Tracked-universe CIK/SIC resolution and the SEC importer's composite revision.
|
||||
|
||||
Resolves the app's tracked tickers to SEC issuers (CIK) and back-fills
|
||||
``tickers.cik/sic/sic_description``. Also builds the **universe fingerprint** that
|
||||
goes into the importer's composite revision, so that adding a ticker changes the
|
||||
revision and forces a run instead of being ``no_op``'d away or starved waiting for
|
||||
its issuer to file (A3 design, Decision 1 review fix).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import logging
|
||||
from typing import Iterable
|
||||
|
||||
from sqlalchemy import select
|
||||
|
||||
from app.models.ticker import Ticker
|
||||
from app.services.earnings_alignment import normalise_symbol
|
||||
from app.services.sec_client import SecClient
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def resolve_ciks(db, client: SecClient) -> dict[str, int]:
|
||||
"""Resolve tracked tickers to CIKs via company_tickers.json and persist
|
||||
``tickers.cik`` where it changed. Returns {normalised symbol: cik} for the
|
||||
tracked tickers that resolved (multi-class tickers share a CIK)."""
|
||||
ticker_to_cik = await client.company_tickers()
|
||||
rows = (await db.execute(select(Ticker))).scalars().all()
|
||||
|
||||
resolved: dict[str, int] = {}
|
||||
changed = 0
|
||||
for t in rows:
|
||||
if not t.symbol:
|
||||
continue
|
||||
sym = normalise_symbol(t.symbol)
|
||||
cik = ticker_to_cik.get(sym)
|
||||
if cik is None:
|
||||
continue # e.g. ADRs / non-SEC issuers — snapshots simply absent
|
||||
resolved[sym] = cik
|
||||
cik_str = f"{cik:010d}"
|
||||
if t.cik != cik_str:
|
||||
t.cik = cik_str
|
||||
changed += 1
|
||||
logger.info("resolve_ciks: %d tracked resolved, %d cik updates", len(resolved), changed)
|
||||
return resolved
|
||||
|
||||
|
||||
async def refresh_sic(db, client: SecClient, ciks: Iterable[int]) -> int:
|
||||
"""Fetch submissions for the given CIKs and set sic/sic_description on every
|
||||
tracked ticker sharing each CIK. Returns the number of CIKs refreshed. Callers
|
||||
pass only the CIKs that need it (e.g. those still missing a SIC) to stay light."""
|
||||
refreshed = 0
|
||||
for cik in sorted(set(int(c) for c in ciks)):
|
||||
sub = await client.submissions(cik)
|
||||
cik_str = f"{cik:010d}"
|
||||
rows = (
|
||||
await db.execute(select(Ticker).where(Ticker.cik == cik_str))
|
||||
).scalars().all()
|
||||
for t in rows:
|
||||
t.sic = str(sub["sic"]) if sub.get("sic") else None
|
||||
t.sic_description = sub.get("sic_description")
|
||||
refreshed += 1
|
||||
return refreshed
|
||||
|
||||
|
||||
def universe_fingerprint(symbol_to_cik: dict[str, int]) -> str:
|
||||
"""Stable short hash of the tracked symbol->CIK set. Changes whenever a ticker
|
||||
is added/removed or its CIK mapping changes."""
|
||||
canonical = ";".join(f"{sym}:{cik}" for sym, cik in sorted(symbol_to_cik.items()))
|
||||
return hashlib.blake2b(canonical.encode("utf-8"), digest_size=12).hexdigest()
|
||||
|
||||
|
||||
def compose_revision(
|
||||
index_date, index_content_hash: str, symbol_to_cik: dict[str, int]
|
||||
) -> str:
|
||||
"""The importer's composite revision: latest processed index date + a hash of
|
||||
the index content consumed this run + the universe fingerprint. Equal revision
|
||||
across runs ⇒ nothing new to import ⇒ no_op."""
|
||||
return f"{index_date}:{index_content_hash}:{universe_fingerprint(symbol_to_cik)}"
|
||||
|
||||
|
||||
def index_content_hash(index_rows: Iterable[dict]) -> str:
|
||||
"""Order-independent hash of the tracked index accessions consumed this run."""
|
||||
keys = sorted(f"{r['cik']}/{r['accession']}" for r in index_rows)
|
||||
return hashlib.blake2b("|".join(keys).encode("utf-8"), digest_size=12).hexdigest()
|
||||
@@ -0,0 +1,159 @@
|
||||
"""Tests for the SEC client's parsing and fair-access behavior, via a mocked
|
||||
httpx transport (no network)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import date
|
||||
|
||||
import httpx
|
||||
import pytest
|
||||
|
||||
from app.services import sec_client as sc
|
||||
from app.services.sec_client import SecClient, SecError, SecForbiddenError
|
||||
|
||||
COMPANY_TICKERS = {
|
||||
"0": {"cik_str": 320193, "ticker": "AAPL", "title": "Apple Inc."},
|
||||
"1": {"cik_str": 1652044, "ticker": "GOOGL", "title": "Alphabet"},
|
||||
"2": {"cik_str": 1652044, "ticker": "GOOG", "title": "Alphabet"},
|
||||
"3": {"cik_str": 1067983, "ticker": "BRK-B", "title": "Berkshire"},
|
||||
}
|
||||
|
||||
SUBMISSIONS_BASE = {
|
||||
"cik": 320193,
|
||||
"name": "Apple Inc.",
|
||||
"sic": "3571",
|
||||
"sicDescription": "Electronic Computers",
|
||||
"fiscalYearEnd": "0926",
|
||||
"tickers": ["AAPL"],
|
||||
"filings": {
|
||||
"recent": {
|
||||
"accessionNumber": ["0000320193-26-000013", "0000320193-26-000006", "0000320193-26-000099"],
|
||||
"form": ["10-Q", "10-K", "8-K"],
|
||||
"reportDate": ["2026-03-28", "2025-09-27", "2026-04-01"],
|
||||
"acceptanceDateTime": ["2026-05-01T10:01:00.000Z", "2025-10-31T10:01:26.000Z", "2026-04-02T09:00:00.000Z"],
|
||||
"isXBRL": [1, 1, 0],
|
||||
},
|
||||
"files": [{"name": "CIK0000320193-submissions-001.json", "filingFrom": "1994-01-26", "filingTo": "2015-05-27"}],
|
||||
},
|
||||
}
|
||||
|
||||
SUBMISSIONS_SHARD = {
|
||||
"accessionNumber": ["0000320193-94-000002"],
|
||||
"form": ["10-Q"],
|
||||
"reportDate": ["1993-12-31"],
|
||||
"acceptanceDateTime": ["1994-01-26T05:00:00.000Z"],
|
||||
"isXBRL": [0],
|
||||
}
|
||||
|
||||
FORM_IDX = """Description: Daily Index of EDGAR Dissemination Feed by Form Type
|
||||
|
||||
Form Type Company Name CIK Date Filed File Name
|
||||
-------------------------------------------------------------------------------
|
||||
10-K/A Starfighters Space, Inc. 1947016 20260721 edgar/data/1947016/0001062993-26-003746.txt
|
||||
10-Q 3M CO 66740 20260721 edgar/data/66740/0000066740-26-000246.txt
|
||||
8-K Some Corp 12345 20260721 edgar/data/12345/0000012345-26-000001.txt
|
||||
10-Q CALIX, INC 1406666 20260721 edgar/data/1406666/0001406666-26-000034.txt
|
||||
"""
|
||||
|
||||
DIR_JSON = {"directory": {"item": [
|
||||
{"name": "form.20260720.idx"}, {"name": "form.20260721.idx"}, {"name": "company.20260721.idx"},
|
||||
]}}
|
||||
|
||||
|
||||
def _handler(request: httpx.Request) -> httpx.Response:
|
||||
url = str(request.url)
|
||||
if url.endswith("company_tickers.json"):
|
||||
return httpx.Response(200, json=COMPANY_TICKERS)
|
||||
if url.endswith("submissions/CIK0000320193.json"):
|
||||
return httpx.Response(200, json=SUBMISSIONS_BASE)
|
||||
if url.endswith("CIK0000320193-submissions-001.json"):
|
||||
return httpx.Response(200, json=SUBMISSIONS_SHARD)
|
||||
if url.endswith("form.20260721.idx"):
|
||||
return httpx.Response(200, text=FORM_IDX)
|
||||
if url.endswith("QTR3/index.json"):
|
||||
return httpx.Response(200, json=DIR_JSON)
|
||||
return httpx.Response(404)
|
||||
|
||||
|
||||
def _client(**kw):
|
||||
return SecClient(transport=httpx.MockTransport(_handler), spacing_seconds=0, **kw)
|
||||
|
||||
|
||||
async def test_company_tickers_normalised_and_multiclass():
|
||||
async with _client() as c:
|
||||
m = await c.company_tickers()
|
||||
assert m["AAPL"] == 320193
|
||||
assert m["GOOGL"] == m["GOOG"] == 1652044 # multi-class share one CIK
|
||||
assert m["BRK-B"] == 1067983 # dash form
|
||||
|
||||
|
||||
async def test_submissions_merges_shards_and_filters_forms():
|
||||
async with _client() as c:
|
||||
sub = await c.submissions(320193)
|
||||
assert sub["sic"] == "3571" and sub["fiscal_year_end"] == "0926"
|
||||
accns = {f["accession"] for f in sub["filings"]}
|
||||
# 10-Q + 10-K from recent, 10-Q from the shard; the 8-K is filtered out
|
||||
assert accns == {"0000320193-26-000013", "0000320193-26-000006", "0000320193-94-000002"}
|
||||
older = next(f for f in sub["filings"] if f["accession"] == "0000320193-94-000002")
|
||||
assert older["report_date"] == "1993-12-31" and older["is_xbrl"] is False
|
||||
|
||||
|
||||
async def test_daily_index_parses_10kq_rows():
|
||||
async with _client() as c:
|
||||
rows = await c.daily_index(date(2026, 7, 21))
|
||||
forms = {r["form"] for r in rows}
|
||||
assert forms == {"10-K/A", "10-Q"} # 8-K excluded
|
||||
mmm = next(r for r in rows if r["cik"] == 66740)
|
||||
assert mmm["accession"] == "0000066740-26-000246"
|
||||
|
||||
|
||||
async def test_latest_index_date():
|
||||
async with _client() as c:
|
||||
d = await c.latest_index_date(today=date(2026, 7, 22))
|
||||
assert d == date(2026, 7, 21)
|
||||
|
||||
|
||||
async def test_403_raises_forbidden_no_retry():
|
||||
calls = {"n": 0}
|
||||
|
||||
def handler(request):
|
||||
calls["n"] += 1
|
||||
return httpx.Response(403)
|
||||
|
||||
async with SecClient(transport=httpx.MockTransport(handler), spacing_seconds=0) as c:
|
||||
with pytest.raises(SecForbiddenError):
|
||||
await c.get_json("https://data.sec.gov/x")
|
||||
assert calls["n"] == 1 # alert and stop, never retry-loop
|
||||
|
||||
|
||||
async def test_429_retries_then_succeeds(monkeypatch):
|
||||
async def _instant(_):
|
||||
return None
|
||||
|
||||
monkeypatch.setattr(sc.asyncio, "sleep", _instant) # no real backoff wait
|
||||
calls = {"n": 0}
|
||||
|
||||
def handler(request):
|
||||
calls["n"] += 1
|
||||
if calls["n"] < 3:
|
||||
return httpx.Response(429)
|
||||
return httpx.Response(200, json={"ok": True})
|
||||
|
||||
async with SecClient(transport=httpx.MockTransport(handler), spacing_seconds=0, max_retries=5) as c:
|
||||
data = await c.get_json("https://data.sec.gov/y")
|
||||
assert data == {"ok": True} and calls["n"] == 3
|
||||
|
||||
|
||||
async def test_429_gives_up_after_max_retries(monkeypatch):
|
||||
async def _instant(_):
|
||||
return None
|
||||
|
||||
monkeypatch.setattr(sc.asyncio, "sleep", _instant)
|
||||
|
||||
def handler(request):
|
||||
return httpx.Response(429)
|
||||
|
||||
async with SecClient(transport=httpx.MockTransport(handler), spacing_seconds=0, max_retries=2) as c:
|
||||
with pytest.raises(SecError):
|
||||
await c.get_json("https://data.sec.gov/z")
|
||||
@@ -0,0 +1,105 @@
|
||||
"""Tests for CIK/SIC resolution and the composite-revision fingerprint."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import tempfile
|
||||
|
||||
import pytest
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||||
|
||||
from app.database import Base
|
||||
import app.models # noqa: F401
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import sec_universe as su
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
async def factory():
|
||||
fd, path = tempfile.mkstemp(suffix=".db")
|
||||
os.close(fd)
|
||||
eng = create_async_engine(f"sqlite+aiosqlite:///{path}")
|
||||
async with eng.begin() as conn:
|
||||
await conn.run_sync(Base.metadata.create_all)
|
||||
try:
|
||||
yield async_sessionmaker(eng, class_=AsyncSession, expire_on_commit=False)
|
||||
finally:
|
||||
await eng.dispose()
|
||||
try:
|
||||
os.unlink(path)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
|
||||
class FakeSecClient:
|
||||
def __init__(self, tickers, submissions=None):
|
||||
self._tickers = tickers
|
||||
self._submissions = submissions or {}
|
||||
|
||||
async def company_tickers(self):
|
||||
return dict(self._tickers)
|
||||
|
||||
async def submissions(self, cik):
|
||||
return self._submissions[int(cik)]
|
||||
|
||||
|
||||
async def test_resolve_ciks_sets_cik_and_returns_mapping(factory):
|
||||
async with factory() as s:
|
||||
for sym in ["AAPL", "GOOGL", "GOOG", "ZZZZ"]: # ZZZZ not in SEC
|
||||
s.add(Ticker(symbol=sym))
|
||||
await s.commit()
|
||||
|
||||
client = FakeSecClient({"AAPL": 320193, "GOOGL": 1652044, "GOOG": 1652044})
|
||||
async with factory() as s:
|
||||
mapping = await su.resolve_ciks(s, client)
|
||||
await s.commit()
|
||||
|
||||
assert mapping == {"AAPL": 320193, "GOOGL": 1652044, "GOOG": 1652044}
|
||||
async with factory() as s:
|
||||
ciks = {t.symbol: t.cik for t in (await s.execute(select(Ticker))).scalars()}
|
||||
assert ciks["AAPL"] == "0000320193"
|
||||
assert ciks["GOOGL"] == ciks["GOOG"] == "0001652044" # multi-class share CIK
|
||||
assert ciks["ZZZZ"] is None # unresolved stays null
|
||||
|
||||
|
||||
async def test_refresh_sic_updates_all_tickers_of_a_cik(factory):
|
||||
async with factory() as s:
|
||||
for sym in ["GOOGL", "GOOG"]:
|
||||
s.add(Ticker(symbol=sym, cik="0001652044"))
|
||||
await s.commit()
|
||||
|
||||
client = FakeSecClient(
|
||||
{}, submissions={1652044: {"sic": "7370", "sic_description": "Services-Computer"}}
|
||||
)
|
||||
async with factory() as s:
|
||||
n = await su.refresh_sic(s, client, [1652044])
|
||||
await s.commit()
|
||||
|
||||
assert n == 1
|
||||
async with factory() as s:
|
||||
rows = {t.symbol: (t.sic, t.sic_description) for t in (await s.execute(select(Ticker))).scalars()}
|
||||
assert rows["GOOGL"] == ("7370", "Services-Computer")
|
||||
assert rows["GOOG"] == ("7370", "Services-Computer")
|
||||
|
||||
|
||||
def test_universe_fingerprint_changes_on_membership():
|
||||
a = su.universe_fingerprint({"AAPL": 320193, "MSFT": 789019})
|
||||
same = su.universe_fingerprint({"MSFT": 789019, "AAPL": 320193}) # order-independent
|
||||
added = su.universe_fingerprint({"AAPL": 320193, "MSFT": 789019, "NVDA": 1045810})
|
||||
remapped = su.universe_fingerprint({"AAPL": 999, "MSFT": 789019})
|
||||
assert a == same
|
||||
assert a != added # new ticker forces a new revision
|
||||
assert a != remapped # changed CIK mapping forces a new revision
|
||||
|
||||
|
||||
def test_compose_revision_and_index_hash():
|
||||
rows = [
|
||||
{"cik": 320193, "accession": "a-1"},
|
||||
{"cik": 66740, "accession": "b-2"},
|
||||
]
|
||||
h1 = su.index_content_hash(rows)
|
||||
h2 = su.index_content_hash(list(reversed(rows)))
|
||||
assert h1 == h2 # order-independent
|
||||
rev = su.compose_revision("2026-07-21", h1, {"AAPL": 320193})
|
||||
assert rev.startswith("2026-07-21:") and rev.count(":") == 2
|
||||
Reference in New Issue
Block a user