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:
2026-07-22 14:15:56 +02:00
co-authored by Claude Opus 4.8
parent b1397fa82e
commit cc67aebe61
6 changed files with 657 additions and 0 deletions
+105
View File
@@ -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