fix(sec): A3 slice-2a review — shares fallback, robust context, hardening

1. Multi-class shares: prefer the single dei:EntityCommonStockSharesOutstanding
   cover-page fact; else fall back to us-gaap:CommonStockSharesOutstanding at
   period end (Alphabet has no dei fact). Never sum class facts (companyfacts is
   non-dimensional) and never use weighted-average/diluted; conflicting values ->
   null, counted as an "ambiguous shares outstanding" note in validation. Plan's
   "sum class-specific" wording corrected. Verified live: Alphabet shares now
   populate (12.1B), Apple still uses its dei cover date.
2. Fiscal context is the majority (fy, fp) among facts ending at reportDate, with
   ties rejected — no longer the arbitrary first fact.
3. Hardening: catalog selectors require taxonomy == "us-gaap"; indexing drops
   malformed facts (missing accession/end, non-finite value) so a custom concept
   or bad date can't be selected.

Tests: +8 (dei precedence, us-gaap fallback, conflict->null, no weighted-average,
tie-context skip, foreign-taxonomy/malformed ignored, ambiguous-shares note).
14 passed, 1 skipped.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-22 16:40:05 +02:00
co-authored by Claude Opus 4.8
parent 7413de9301
commit 4754dbc17b
3 changed files with 183 additions and 35 deletions
+91
View File
@@ -13,6 +13,8 @@ from app.services.sec_facts_parser import (
FilingMeta,
_compose_cash,
_compose_debt,
_fiscal_context,
_select_shares,
parse_snapshots,
)
@@ -135,6 +137,95 @@ def test_cash_picks_one_st_investment_source():
assert _compose_cash(facts, rd) == 45000
RD = date(2026, 3, 28)
def _dei(end, val):
return Fact("dei", "EntityCommonStockSharesOutstanding", "shares", None, end, val, 2026, "Q2")
def _gaap_shares(end, val):
return Fact("us-gaap", "CommonStockSharesOutstanding", "shares", None, end, val, 2026, "Q2")
def test_shares_prefers_dei_cover_page():
facts = [_dei(date(2026, 4, 17), 100), _gaap_shares(RD, 999)]
assert _select_shares(facts, RD) == (100.0, date(2026, 4, 17), False)
def test_shares_falls_back_to_usgaap_at_report_date():
# Alphabet case: no dei fact; us-gaap current + a prior comparative.
facts = [_gaap_shares(date(2025, 12, 31), 888), _gaap_shares(RD, 12116)]
assert _select_shares(facts, RD) == (12116.0, RD, False) # comparative excluded
def test_shares_conflict_returns_null_ambiguous():
facts = [_dei(RD, 100), _dei(RD, 200)] # two differing consolidated values
assert _select_shares(facts, RD) == (None, None, True)
def test_shares_never_uses_weighted_average():
facts = [Fact("us-gaap", "WeightedAverageNumberOfDilutedSharesOutstanding", "shares", None, RD, 5, 2026, "Q2")]
assert _select_shares(facts, RD) == (None, None, False) # not a shares source
def test_conflicting_fiscal_context_is_rejected():
facts = [
Fact("us-gaap", "Revenues", "USD", date(2025, 9, 28), RD, 1, 2026, "Q2"),
Fact("us-gaap", "NetIncomeLoss", "USD", date(2025, 9, 28), RD, 2, 2025, "Q3"),
] # 1-1 tie between two contexts at reportDate
assert _fiscal_context(facts, RD) == (None, None)
# a clear majority wins
facts.append(Fact("us-gaap", "OperatingIncomeLoss", "USD", date(2025, 9, 28), RD, 3, 2026, "Q2"))
assert _fiscal_context(facts, RD) == (2026, "Q2")
def test_conflicting_context_skips_row():
cf = {"cik": 1, "facts": {"us-gaap": {
"Revenues": {"units": {"USD": [_dur("2025-09-28", "2026-03-28", 1, "B", fp="Q2")]}},
"NetIncomeLoss": {"units": {"USD": [_dur("2025-09-28", "2026-03-28", 2, "B", fy=2025, fp="Q3")]}},
}}}
filings = {"B": FilingMeta(RD, date(2026, 5, 1), datetime(2026, 5, 1, tzinfo=UTC), "10-Q")}
rows, skips = parse_snapshots(cf, filings, {"B"})
assert rows == [] and skips == [{"accession": "B", "reason": "no usable period identity"}]
def test_foreign_taxonomy_and_malformed_facts_ignored():
cf = {"cik": 1, "facts": {
"us-gaap": {
"Revenues": {"units": {"USD": [_dur("2025-09-28", "2026-03-28", 500, "B")]}},
"NetIncomeLoss": {"units": {"USD": [
{"start": "2025-09-28", "end": "2026-03-28", "val": None, "fy": 2026, "fp": "Q2", "accn": "B"},
]}},
"OperatingIncomeLoss": {"units": {"USD": [
{"start": "2025-09-28", "end": "2026-03-28", "val": float("nan"), "fy": 2026, "fp": "Q2", "accn": "B"},
]}},
},
"acme": {"RevenueFromContractWithCustomerExcludingAssessedTax": {"units": {"USD": [
_dur("2025-09-28", "2026-03-28", 99999, "B"), # custom taxonomy — must be ignored
]}}},
}}
filings = {"B": FilingMeta(RD, date(2026, 5, 1), datetime(2026, 5, 1, tzinfo=UTC), "10-Q")}
rows, _ = parse_snapshots(cf, filings, {"B"})
assert rows[0].revenue == 500 # us-gaap Revenues, not the acme concept
assert rows[0].net_income is None # val None ignored
assert rows[0].operating_income is None # NaN ignored
def test_ambiguous_shares_produces_row_plus_note():
cf = {"cik": 1, "facts": {
"us-gaap": {"Revenues": {"units": {"USD": [_dur("2025-09-28", "2026-03-28", 500, "B")]}}},
"dei": {"EntityCommonStockSharesOutstanding": {"units": {"shares": [
{"end": "2026-04-17", "val": 100, "fy": 2026, "fp": "Q2", "accn": "B"},
{"end": "2026-04-17", "val": 200, "fy": 2026, "fp": "Q2", "accn": "B"},
]}}},
}}
filings = {"B": FilingMeta(RD, date(2026, 5, 1), datetime(2026, 5, 1, tzinfo=UTC), "10-Q")}
rows, skips = parse_snapshots(cf, filings, {"B"})
assert len(rows) == 1 and rows[0].shares_outstanding is None # row kept, shares null
assert {"accession": "B", "reason": "ambiguous shares outstanding"} in skips
# Opt-in live check against real Apple companyfacts. Skips unless SEC_LIVE=1 and a
# real SEC_USER_AGENT are set (network + fair-access contact email).
@pytest.mark.skipif(