open/llm-ingestion-okf
1
0
Fork 0
Code Issues Releases 4 Activity

test(fixtures): the STS fixtures and fixture codes are fictitious

Browse source 
Three STS fixtures still carried the section titles and labels of one real
reference document, and three identifiers were copies of its codes with a
letter or a word swapped. They now describe an invented kitchen counter and
cookbook series: the titles, labels and descriptions of sts-identity.xml,
sts-inherit.xml and sts-empty-label.xml, the P350/P351 document codes, the
99-0001 delivery prefix and chapter 7 of the image and accounting corpora.
Generated fixtures are regenerated and the witness inventory's per-document
totals are identical before and after; only names and text move.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-23 14:50:44 +02:00
commit 88cf67f12e
65 changed files with 396 additions and 390 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/test_content_accounting.py
View file

@ -66,7 +66,7 @@ def test_a_file_carried_through_a_document_is_not_a_coded_rejection(tmp_path: Pa
def test_an_unpointed_image_beside_a_document_stays_a_coded_rejection(tmp_path: Path) -> None:
pytest.importorskip("pypandoc")
inbox = _inbox(tmp_path, CORPUS)
shutil.copy(inbox / "graphics" / "figur-84-1.png", inbox / "graphics" / "ubrukt.png")
shutil.copy(inbox / "graphics" / "figur-7-1.png", inbox / "graphics" / "ubrukt.png")
report = cli.build(inbox, tmp_path / "b", bundle_id="acc", okf_version="0.2")
assert report.carried_files == 2
assert dict(report.codes)["extractor_unknown"] == 1
@ -195,12 +195,12 @@ def test_the_classes_this_package_does_not_count_are_named(name: str) -> None:
def test_the_inventory_resolves_the_files_a_document_points_at() -> None:
got = accounting.inventory(CORPUS, CORPUS / "kapittel-84-sts.xml")
assert got.pointed_files() == {"graphics/tabell-84-2.png", "graphics/figur-84-1.png"}
got = accounting.inventory(CORPUS, CORPUS / "kapittel-7-sts.xml")
assert got.pointed_files() == {"graphics/tabell-7-2.png", "graphics/figur-7-1.png"}
def test_the_inventory_of_an_unread_type_is_empty() -> None:
got = accounting.inventory(CORPUS, CORPUS / "graphics" / "figur-84-1.png")
got = accounting.inventory(CORPUS, CORPUS / "graphics" / "figur-7-1.png")
assert got.counts() == {}
@ -245,8 +245,8 @@ def test_the_door_books_every_element_of_the_fixture_corpus_but_the_known_losses
found[(document["source_file"], kind)] = (booked, number)
assert found == KNOWN_LOSSES
files = {entry["source_file"]: entry["fate"] for entry in data["files"]}
assert files == {"graphics/figur-84-1.png": "carried", "graphics/tabell-84-2.png": "carried"}
web = next(d for d in data["documents"] if d["source_file"] == "kapittel-84-web.html")
assert files == {"graphics/figur-7-1.png": "carried", "graphics/tabell-7-2.png": "carried"}
web = next(d for d in data["documents"] if d["source_file"] == "kapittel-7-web.html")
assert web["fates"]["image"] == {"carried": 2, "pointer": 1, "rejected": {}}