Kjell Tore Guttormsen
e03bd79876
Speiler MAF I2 fra shared/ingest-spec.md alene: manifest → CSV-konnektor → materialisert OKF-bundle, byte-identisk med den delte golden-fasiten. - ingest.py: ManifestContract (pydantic, fail-fast, file-kilde, verdict-reservasjon §3, id-grammatikk, max_rows), CSV-konnektor (boundary-checked fail-closed), materialisering (§5-frontmatter eksakt rekkefølge, markdown-tabell m/ escaping, LF-only, SHA-256 manifest-stamp), index-generering (§6), replacement §3/§5. - okf.py: _parse_index_entry — tolererer frontmatterløs index (method-spec §3: index rendres via body = summary, ikke som typet concept-fil). Golden var spec-konform; D7-okf var strengere enn standarden. Scoped: non-index concept- filer krever fortsatt type (honesty-test). - examples/ingest-golden-file/: repo-lokal golden (byte-frossen kopi av I2s fasit). - Speiltester (I2s load-bearing-sett, alle detach-bevist røde): golden byte-fasit + mutasjonskontroller · provenance/navigability/verdict-reservasjon/re-ingest-safety · kontrakt fail-fast/max_rows/boundary/kollisjon · spec-integritet §11. - docs/2026-07-04-I3-brief.md: brief + de to operatør-avgjorte beslutningene. Suite 239 passed uten nøkkel/nettverk (189 + 50 nye) · ruff + mypy --strict rene. [skip-docs] README + docs/extending.md er bevisst utsatt til I7 per sesjonsplan (programmet batcher ingest-doc der, avgrenset til det D7 faktisk har — CSV nå, SQL/HTTP senere). Endringen er dokumentert i docs/2026-07-04-I3-brief.md. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017MM6BWb1hWmJZuXFZ7rjxT
86 lines
3.6 KiB
Python
86 lines
3.6 KiB
Python
"""Ingest golden regression (ingest-spec §11) — the shared byte-for-byte fasit.
|
|
|
|
D7 mirror of MAF I2. Consumes the repo-local ``examples/ingest-golden-file/``
|
|
(a byte-frozen copy of MAF I2's golden — the SAME shared extraction, so this test
|
|
proves D7's independent implementation reproduces MAF's exact bytes from the shared
|
|
spec alone). ``expected-bundle/`` is compared file by file, byte for byte.
|
|
|
|
The mutation controls prove the net is taut: one changed determinism input (a CSV
|
|
cell, the timestamp, the manifest bytes) must diverge from the golden bytes.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
from portfolio_optimiser_claude.ingest import materialize
|
|
|
|
GOLDEN = Path(__file__).resolve().parents[1] / "examples" / "ingest-golden-file"
|
|
|
|
|
|
def _ingested_at() -> str:
|
|
return (GOLDEN / "ingested-at.txt").read_text(encoding="utf-8").strip()
|
|
|
|
|
|
def test_materializes_golden_byte_for_byte(tmp_path: Path) -> None:
|
|
bundle = tmp_path / "bundle"
|
|
bundle.mkdir()
|
|
materialize(GOLDEN / "manifest.json", bundle, _ingested_at())
|
|
|
|
expected = GOLDEN / "expected-bundle"
|
|
expected_names = sorted(p.name for p in expected.iterdir())
|
|
produced_names = sorted(p.name for p in bundle.iterdir())
|
|
assert produced_names == expected_names # no missing, no extra files
|
|
for name in expected_names:
|
|
assert (bundle / name).read_bytes() == (expected / name).read_bytes(), name
|
|
|
|
|
|
def test_reingest_is_idempotent(tmp_path: Path) -> None:
|
|
# ingest-spec §10: same source content, manifest, ingested_at → byte-identical,
|
|
# repeated runs idempotent.
|
|
bundle = tmp_path / "bundle"
|
|
bundle.mkdir()
|
|
materialize(GOLDEN / "manifest.json", bundle, _ingested_at())
|
|
first = {p.name: p.read_bytes() for p in bundle.iterdir()}
|
|
materialize(GOLDEN / "manifest.json", bundle, _ingested_at())
|
|
second = {p.name: p.read_bytes() for p in bundle.iterdir()}
|
|
assert first == second
|
|
|
|
|
|
class TestMutationControl:
|
|
"""One changed determinism input → divergence from the golden bytes."""
|
|
|
|
def _case(self, tmp_path: Path) -> Path:
|
|
case = tmp_path / "case"
|
|
shutil.copytree(GOLDEN, case)
|
|
return case
|
|
|
|
def test_changed_cell_diverges(self, tmp_path: Path) -> None:
|
|
case = self._case(tmp_path)
|
|
csv = case / "fixture" / "costs.csv"
|
|
csv.write_bytes(csv.read_bytes().replace(b"120000", b"999999"))
|
|
bundle = tmp_path / "bundle"
|
|
bundle.mkdir()
|
|
materialize(case / "manifest.json", bundle, _ingested_at())
|
|
golden_bytes = (GOLDEN / "expected-bundle" / "ingest-costs.md").read_bytes()
|
|
assert (bundle / "ingest-costs.md").read_bytes() != golden_bytes
|
|
|
|
def test_changed_timestamp_diverges(self, tmp_path: Path) -> None:
|
|
bundle = tmp_path / "bundle"
|
|
bundle.mkdir()
|
|
materialize(GOLDEN / "manifest.json", bundle, "2099-01-01T00:00:00Z")
|
|
golden_bytes = (GOLDEN / "expected-bundle" / "ingest-costs.md").read_bytes()
|
|
assert (bundle / "ingest-costs.md").read_bytes() != golden_bytes
|
|
|
|
def test_changed_manifest_bytes_change_the_stamp(self, tmp_path: Path) -> None:
|
|
# The ingest_manifest stamp is SHA-256 of the manifest's raw bytes (§5) —
|
|
# a whitespace-only edit still re-stamps every generated file.
|
|
case = self._case(tmp_path)
|
|
manifest = case / "manifest.json"
|
|
manifest.write_bytes(manifest.read_bytes() + b"\n")
|
|
bundle = tmp_path / "bundle"
|
|
bundle.mkdir()
|
|
materialize(manifest, bundle, _ingested_at())
|
|
golden_bytes = (GOLDEN / "expected-bundle" / "ingest-costs.md").read_bytes()
|
|
assert (bundle / "ingest-costs.md").read_bytes() != golden_bytes
|