The bundle-only gate returned UNMEASURED and exit 3 on the very arm it was
built for: no metric computable from a bundle alone reaches boundary recall.
`boundary_share` -- declared boundaries that became a concept, over declared
boundaries -- is the one metric measured that orders the arms correctly, and it
needs the publisher's own structure, so it arrives as an input.
Measurement first, threshold after, which is what the order asked for.
P1, the normalisation, derived rather than guessed: stripping all whitespace
and lowercasing reproduces the fasit's own `norm` from its own `title` on
2 761 of 2 761 rows (alphanumerics-only scores 58). P1's own bar is 99 % on the
known-good arm and the literal reading of it reaches 22 of 2 761 -- not because
the normalisation is wrong but because okf's default route moves the numbering
token a publisher glues into a heading over into the concept id. The pair form
(concept's own directory, residual title) reaches 2 737, either reaches 2 759
(99.9 %). Both forms ship and neither is a fallback: `r761-2025-d1` is the
control in the opposite direction at 2 727 literal, 0 paired.
P2, the single corpus, is in the OUTPUT and not only in the document: the bar
is declared `corpora = 1`, every boundary row prints `N = 1 corpus`, and the
line states that `--fasit` is the caller's ASSERTION that this bundle is a
build of the document the fasit describes -- the posture `okf consume --ref`
has. Measured: the K2 reference and `n100-2023` score 0 of 2 761 and read FAIL,
which is the assertion being wrong rather than the bundle being bad.
One bar, at the pinned artifact's own value, 2 759/2 761. It is tight and the
cost is published rather than tuned away: 2 of 4 R761 builds fall under it
(2 752 and 2 727), while any bar between 41.6 % and 98.8 % separates the
known-bad arm from every R761 build measured. The known-bad arm
(`860019-mdb-100`) is 1 148 of 2 761 -- FAIL and exit 1, where the bundle-only
gate gave exit 3.
A fasit is validated at the door: not a list, a row missing `title` or `norm`,
or anything that is not JSON exits 2 with the reason, never a quiet UNMEASURED.
A fasit under five rows is UNMEASURED -- the document floor in the fasit's own
unit.
Without `--fasit` the command is byte-for-byte what it was, held by a test.
`okf check` is untouched; no version bump and no tag. 17 tests red on
assertions before the implementation, the two new doc pins each driven red and
back. Suite 1 869 passed / 1 skipped / 1 870 collected (base 5e5d01c: 1 851).
docs/2026-09-12-g37-terskler.md SS 7 carries the premises re-measured, the
seven bundles, the interval any bar could sit in, and the honesty limits --
including the correction of SS 2's own grep claim, which went false in the
commit that wrote it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
496 lines
22 KiB
Python
496 lines
22 KiB
Python
"""`okf quality` -- the per-file-type verdict, and what it refuses to say.
|
|
|
|
`okf check` is a CONTRACT check: it asks whether a payload carries what a claim
|
|
must rest on. Measured 2026-09-10 by `vegnormal-okf`, it returned 0 findings and
|
|
exit 0 on three arms over one corpus whose hit@k ranged from 6 of 6 to 0 of 6.
|
|
This module is the other question -- did the cut find anything worth reading --
|
|
and its whole discipline is that it answers it PER FILE TYPE, with the
|
|
denominator printed, and never answers PASS for a type it has no measurement
|
|
for.
|
|
|
|
Each rule below is exercised in both directions on purpose: a rule that has only
|
|
ever been run against the case it fires on has not been measured, it has been
|
|
asserted. The thresholds themselves, and the four evidence corpora they were
|
|
read off, live in `docs/2026-09-12-g37-terskler.md`.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from llm_ingestion_okf import quality
|
|
|
|
_FRONTMATTER = """---
|
|
type: reference
|
|
title: {title}
|
|
source_file: {source_file}
|
|
ingested_at: 1970-01-01T00:00:00Z
|
|
---
|
|
|
|
{body}
|
|
"""
|
|
|
|
|
|
def _bundle(root: Path, concepts: list[tuple[str, str, str]]) -> Path:
|
|
"""A flat bundle: one root index, one file per concept.
|
|
|
|
`concepts` is `(stem, source_file, body)`. `source_file` may be the empty
|
|
string, which is the shape a bundle from another producer arrives in.
|
|
"""
|
|
root.mkdir(parents=True, exist_ok=True)
|
|
lines = ["---", "okf_version: 0.2", "bundle_id: quality-fixture", "---", ""]
|
|
for stem, source_file, body in concepts:
|
|
(root / f"{stem}.md").parent.mkdir(parents=True, exist_ok=True)
|
|
(root / f"{stem}.md").write_text(
|
|
_FRONTMATTER.format(title=stem, source_file=source_file, body=body),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
lines.append(f"- [{stem}]({stem}.md)")
|
|
(root / "index.md").write_text("\n".join(lines) + "\n", encoding="utf-8", newline="")
|
|
return root
|
|
|
|
|
|
def _pdf_documents(count: int, *, single: int) -> list[tuple[str, str, str]]:
|
|
"""`count` PDF documents, `single` of them yielding one concept only."""
|
|
concepts: list[tuple[str, str, str]] = []
|
|
for index in range(count):
|
|
source = f"doc-{index}.pdf"
|
|
segments = 1 if index < single else 3
|
|
for segment in range(segments):
|
|
concepts.append((f"doc-{index}-{segment}", source, "Body text enough to count."))
|
|
return concepts
|
|
|
|
|
|
def test_a_type_at_its_measured_reference_passes(tmp_path: Path) -> None:
|
|
"""The known-positive: 8 of 32 is the reference, and 8 of 32 is not worse."""
|
|
root = _bundle(tmp_path / "at-reference", _pdf_documents(32, single=8))
|
|
report = quality.measure_bundle(root)
|
|
row = report.row(".pdf")
|
|
assert row.verdict == "PASS"
|
|
assert (row.structure_null, row.documents) == (8, 32)
|
|
|
|
|
|
def test_a_type_worse_than_its_reference_fails(tmp_path: Path) -> None:
|
|
"""The known-negative for the same rule: 9 of 32 is worse than 8 of 32."""
|
|
root = _bundle(tmp_path / "over-reference", _pdf_documents(32, single=9))
|
|
report = quality.measure_bundle(root)
|
|
assert report.row(".pdf").verdict == "FAIL"
|
|
assert report.exit_code == 1
|
|
|
|
|
|
def test_an_empty_concept_fails_a_type_that_has_no_threshold(tmp_path: Path) -> None:
|
|
"""FAIL is reachable for every type; PASS is not. `.md` has no threshold."""
|
|
root = _bundle(
|
|
tmp_path / "empty-body",
|
|
[("a", "note.md", "Body text."), ("b", "note.md", " \n")],
|
|
)
|
|
report = quality.measure_bundle(root)
|
|
row = report.row(".md")
|
|
assert row.verdict == "FAIL"
|
|
assert (row.empty, row.concepts) == (1, 2)
|
|
|
|
|
|
def test_a_healthy_type_without_a_threshold_is_unmeasured_and_never_pass(
|
|
tmp_path: Path,
|
|
) -> None:
|
|
"""The other direction of the same rule: nothing wrong, and still not PASS."""
|
|
root = _bundle(
|
|
tmp_path / "no-threshold",
|
|
[("a", "note.md", "Body text."), ("b", "note.md", "More body text.")],
|
|
)
|
|
report = quality.measure_bundle(root)
|
|
assert report.row(".md").verdict == "UNMEASURED"
|
|
assert report.exit_code == 3
|
|
|
|
|
|
def test_concepts_without_a_source_file_are_unmeasured(tmp_path: Path) -> None:
|
|
"""The shape three of the four evidence corpora arrive in.
|
|
|
|
`n100-2023`, `n200-2024` and `n500-2024` carry `source_file` on 0 of 446,
|
|
0 of 1 133 and 0 of 270 concepts, so a per-file-type gate has no type to
|
|
speak about. Measured 2026-09-12; the gate says so instead of passing them.
|
|
"""
|
|
root = _bundle(tmp_path / "foreign", [("a", "", "Body text."), ("b", "", "More text.")])
|
|
report = quality.measure_bundle(root)
|
|
row = report.row(quality.NO_SOURCE_FILE)
|
|
assert row.verdict == "UNMEASURED"
|
|
assert report.exit_code == 3
|
|
|
|
|
|
def test_a_failing_type_outweighs_a_passing_one(tmp_path: Path) -> None:
|
|
concepts = _pdf_documents(32, single=9)
|
|
for index in range(5): # five documents: the floor a rate needs to be a rate
|
|
concepts.append((f"note-{index}-0", f"note-{index}.docx", "Body text."))
|
|
concepts.append((f"note-{index}-1", f"note-{index}.docx", "More body text."))
|
|
report = quality.measure_bundle(_bundle(tmp_path / "mixed", concepts))
|
|
assert report.row(".docx").verdict == "PASS"
|
|
assert report.row(".pdf").verdict == "FAIL"
|
|
assert report.exit_code == 1
|
|
|
|
|
|
def test_every_row_prints_its_denominator(tmp_path: Path) -> None:
|
|
root = _bundle(tmp_path / "printed", _pdf_documents(32, single=8))
|
|
rendered = quality.measure_bundle(root).render()
|
|
assert "8/32" in rendered
|
|
assert "0/80" in rendered # empty concepts, over the concepts of the type
|
|
assert "documents" in rendered
|
|
|
|
|
|
def test_the_bundle_run_log_is_reported_when_the_bundle_carries_one(tmp_path: Path) -> None:
|
|
"""A rejected document leaves NO row in the bundle: the log is the only trace.
|
|
|
|
On the pinned K2 bundle the log reads `N = 43, merged 39, coded rejections
|
|
4`, and the bundle itself shows 39 documents -- so the gate's own
|
|
denominator is the bundle's, never the corpus's, and it says which one it
|
|
is using.
|
|
"""
|
|
root = _bundle(tmp_path / "logged", _pdf_documents(2, single=0))
|
|
(root / "log.md").write_text(
|
|
"* **Ingested**: /x - N = 3 (the corpus directory's file count, computed at "
|
|
"run time), merged = 2 (2 substantive, 0 degenerate), coded rejections = 1.\n",
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
report = quality.measure_bundle(root)
|
|
assert report.run_log == "N = 3, merged = 2, coded rejections = 1"
|
|
assert "coded rejections = 1" in report.render()
|
|
|
|
|
|
def test_a_bundle_without_a_log_says_so_rather_than_reporting_zero(tmp_path: Path) -> None:
|
|
root = _bundle(tmp_path / "unlogged", _pdf_documents(2, single=0))
|
|
report = quality.measure_bundle(root)
|
|
assert report.run_log is None
|
|
assert "no run log" in report.render()
|
|
|
|
|
|
def test_a_missing_bundle_exits_two(tmp_path: Path, capsys) -> None: # type: ignore[no-untyped-def]
|
|
assert quality.main([str(tmp_path / "nowhere")]) == 2
|
|
|
|
|
|
def test_the_cli_reaches_the_gate_through_okf_quality(tmp_path: Path, capsys) -> None: # type: ignore[no-untyped-def]
|
|
from llm_ingestion_okf import cli
|
|
|
|
root = _bundle(tmp_path / "through-cli", _pdf_documents(32, single=9))
|
|
assert cli.main(["quality", str(root)]) == 1
|
|
assert ".pdf" in capsys.readouterr().out
|
|
|
|
|
|
def test_every_threshold_names_the_corpus_and_the_denominator_it_was_read_off() -> None:
|
|
"""A threshold without an N is the thing this whole gate exists to refuse."""
|
|
assert quality.THRESHOLDS, "no thresholds at all would make every type UNMEASURED"
|
|
for extension, threshold in quality.THRESHOLDS.items():
|
|
assert extension.startswith("."), extension
|
|
assert threshold.documents >= quality.MIN_DOCUMENTS_FOR_A_THRESHOLD
|
|
assert threshold.source, f"{extension} threshold names no source"
|
|
assert threshold.limit_documents == threshold.documents
|
|
|
|
|
|
def test_a_rate_over_too_few_documents_is_not_a_rate(tmp_path: Path) -> None:
|
|
"""FOUND BY RUNNING THE GATE, not by reading it.
|
|
|
|
`~/repos/vegnormal-okf/build/sk2-bundle-default` is one PDF cut into 2 182
|
|
concepts. Against the 32-document reference its one-concept share is 0 of 1,
|
|
which the first version of this rule read as PASS -- a verdict resting on a
|
|
denominator of one, which is the exact failure `MIN_DOCUMENTS_FOR_A_THRESHOLD`
|
|
exists to refuse. The floor binds the BUNDLE's denominator too, not only the
|
|
threshold's.
|
|
"""
|
|
root = _bundle(tmp_path / "one-document", _pdf_documents(1, single=0))
|
|
assert quality.measure_bundle(root).row(".pdf").verdict == "UNMEASURED"
|
|
|
|
|
|
def test_the_floor_admits_a_bundle_that_reaches_it(tmp_path: Path) -> None:
|
|
"""The other direction: five documents is the floor, and five is enough."""
|
|
root = _bundle(tmp_path / "five-documents", _pdf_documents(5, single=1))
|
|
assert quality.measure_bundle(root).row(".pdf").verdict == "PASS"
|
|
|
|
|
|
def test_an_empty_concept_fails_even_below_the_floor(tmp_path: Path) -> None:
|
|
"""The empty-body bar is per concept, not a rate, so the floor does not gate it."""
|
|
root = _bundle(tmp_path / "one-document-empty", [("a", "only.pdf", " \n")])
|
|
assert quality.measure_bundle(root).row(".pdf").verdict == "FAIL"
|
|
|
|
|
|
def test_the_no_source_file_row_reports_no_document_count(tmp_path: Path) -> None:
|
|
"""A row that is not a file type has no documents either.
|
|
|
|
Every concept without the key shares the same empty `source_file`, so a
|
|
naive grouping reports `documents 1` and `one-concept documents 0/1` for a
|
|
bundle of 446 concepts -- three numbers that look measured and mean nothing.
|
|
"""
|
|
root = _bundle(tmp_path / "foreign-render", [("a", "", "Body."), ("b", "", "More.")])
|
|
rendered = quality.measure_bundle(root).render()
|
|
assert "documents 1" not in rendered
|
|
assert "one-concept documents" not in rendered
|
|
assert "empty 0/2" in rendered
|
|
assert "no source_file on 2 of 2 concepts" in rendered
|
|
|
|
|
|
# --- G37b: `--fasit` and `boundary_share` -------------------------------------
|
|
#
|
|
# The metric that separates the two arms this gate could not tell apart. It is
|
|
# the ONLY one measured that orders them correctly and it needs the publisher's
|
|
# own declared structure, so it arrives as an input rather than as a constant:
|
|
# `okf quality <bundle> --fasit <json>`.
|
|
#
|
|
# Two things are pinned here that were measured before any of it was written
|
|
# (`docs/2026-09-12-g37-terskler.md` SS 7):
|
|
#
|
|
# 1. The fasit's `norm` key is reproduced from its own `title` by stripping all
|
|
# whitespace and lowercasing -- 2 761 of 2 761 rows, so the normalisation is
|
|
# not a guess.
|
|
# 2. That normalisation ALONE reaches 22 of 2 761 on the known-good arm, not
|
|
# 99 %, because okf's default route moves the numbering token STS glues into
|
|
# `<title>` over into the concept id. The second match form -- the
|
|
# (directory, residual title) pair -- is what takes it to 2 759 of 2 761.
|
|
|
|
_GOOD_ARM = Path.home() / "repos/vegnormal-okf/build/ferdig/r761-2025-generisk"
|
|
_BAD_ARM = Path.home() / "repos/vegnormal-okf/build/860019-mdb-100"
|
|
_OTHER_PRODUCT = Path.home() / "corpora/okf-telling-20260829/K2-bundle-default-20260912"
|
|
_FASIT = Path.home() / "repos/vegnormal-okf/build/sk2-fasit-2761.json"
|
|
|
|
|
|
def _fasit(path: Path, titles: list[str]) -> Path:
|
|
"""A fasit file in the shipped shape: a list of rows carrying title and norm."""
|
|
path.write_text(
|
|
json.dumps(
|
|
[{"title": title, "norm": quality.normalise_title(title)} for title in titles],
|
|
ensure_ascii=False,
|
|
),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
return path
|
|
|
|
|
|
def _declaring(titles: list[str]) -> list[tuple[str, str, str]]:
|
|
"""One concept per declared title, matching it literally."""
|
|
return [(f"c{index}", "doc.xml", "Body text.") for index, _ in enumerate(titles)]
|
|
|
|
|
|
def test_the_normalisation_reproduces_the_fasit_key() -> None:
|
|
"""`norm` is whitespace-stripped, lowercased `title` -- not a guess.
|
|
|
|
Measured over the shipped fasit before anything was written: 2 761 of 2 761
|
|
rows reproduce, and the real file pins it below where it exists.
|
|
"""
|
|
assert quality.normalise_title(" 2.1 Hoved Prosesser\n") == "2.1hovedprosesser"
|
|
assert quality.normalise_title("1Bruksområder for Prosesskoden") == (
|
|
"1bruksområderforprosesskoden"
|
|
)
|
|
|
|
|
|
def test_a_bundle_recovering_every_declared_boundary_passes(tmp_path: Path) -> None:
|
|
"""The known-positive, in miniature: every declared title became a concept."""
|
|
titles = [f"{n} Kapittel {n}" for n in range(1, 7)]
|
|
root = tmp_path / "recovered"
|
|
root.mkdir()
|
|
bundle = _bundle(root, [(quality.normalise_title(t)[:12], "doc.xml", "Body.") for t in titles])
|
|
# The concept titles ARE the declared titles: rewrite the frontmatter.
|
|
for index, title in enumerate(titles):
|
|
stem = quality.normalise_title(title)[:12]
|
|
(bundle / f"{stem}.md").write_text(
|
|
_FRONTMATTER.format(title=title, source_file="doc.xml", body="Body."),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
report = quality.measure_bundle(
|
|
bundle, fasit=quality.load_fasit(_fasit(tmp_path / "f.json", titles))
|
|
)
|
|
assert report.boundaries is not None
|
|
assert (report.boundaries.recovered, report.boundaries.declared) == (6, 6)
|
|
assert report.boundaries.verdict == "PASS"
|
|
assert report.exit_code == 0
|
|
|
|
|
|
def test_a_bundle_recovering_few_declared_boundaries_fails(tmp_path: Path) -> None:
|
|
"""The known-negative for the same rule, and the arm it was built for.
|
|
|
|
`860019-mdb-100` recovers 1 148 of 2 761. Here five of six is already worse
|
|
than the bar of 2 759/2 761 -- the bar is that tight, which is a property of
|
|
a regression bar set at its reference and is said out loud in the document.
|
|
"""
|
|
titles = [f"{n} Kapittel {n}" for n in range(1, 7)]
|
|
root = tmp_path / "lost"
|
|
root.mkdir()
|
|
bundle = _bundle(root, [(f"c{i}", "doc.md", "Body.") for i in range(5)])
|
|
for index, title in enumerate(titles[:5]):
|
|
(bundle / f"c{index}.md").write_text(
|
|
_FRONTMATTER.format(title=title, source_file="doc.md", body="Body."),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
report = quality.measure_bundle(
|
|
bundle, fasit=quality.load_fasit(_fasit(tmp_path / "f.json", titles))
|
|
)
|
|
assert report.boundaries is not None
|
|
assert (report.boundaries.recovered, report.boundaries.declared) == (5, 6)
|
|
assert report.boundaries.verdict == "FAIL"
|
|
assert report.exit_code == 1
|
|
|
|
|
|
def test_the_numbering_token_is_matched_through_the_concept_directory(tmp_path: Path) -> None:
|
|
"""The second match form, and the reason P1's literal reading is not enough.
|
|
|
|
STS glues the numbering into the title (`11.1Fastmerker`); okf's default
|
|
route moves it into the concept id (`11-1/...`) and keeps the residual as
|
|
the title. Measured on the known-good arm: the literal form alone reaches
|
|
22 of 2 761, the pair form 2 737, either 2 759.
|
|
"""
|
|
titles = ["11.1Fastmerker"]
|
|
bundle = _bundle(tmp_path / "paired", [("11-1/p1", "doc.pdf", "Body.")])
|
|
(bundle / "11-1/p1.md").write_text(
|
|
_FRONTMATTER.format(title="Fastmerker", source_file="doc.pdf", body="Body."),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
fasit = quality.load_fasit(_fasit(tmp_path / "f.json", titles))
|
|
report = quality.measure_bundle(bundle, fasit=fasit)
|
|
assert report.boundaries is not None
|
|
assert report.boundaries.literal == 0
|
|
assert report.boundaries.paired == 1
|
|
assert report.boundaries.recovered == 1
|
|
|
|
|
|
def test_without_a_fasit_the_gate_is_byte_for_byte_what_it_was(tmp_path: Path) -> None:
|
|
"""The regression the order asks for: no `--fasit`, no change of any kind."""
|
|
root = _bundle(tmp_path / "unchanged", [("a", "note.md", "Body."), ("b", "note.md", "More.")])
|
|
report = quality.measure_bundle(root)
|
|
assert report.boundaries is None
|
|
assert report.exit_code == 3
|
|
assert "boundary" not in report.render().split("## What this verdict is not")[0].lower()
|
|
|
|
|
|
def test_a_fasit_that_is_not_a_list_exits_two_rather_than_unmeasured(tmp_path: Path) -> None:
|
|
"""An unreadable fasit is a run that did not happen, never a quiet verdict."""
|
|
bad = tmp_path / "object.json"
|
|
bad.write_text('{"title": "x", "norm": "x"}', encoding="utf-8")
|
|
root = _bundle(tmp_path / "b", [("a", "note.md", "Body.")])
|
|
assert quality.main([str(root), "--fasit", str(bad)]) == 2
|
|
|
|
|
|
def test_a_fasit_row_missing_a_key_exits_two(tmp_path: Path) -> None:
|
|
bad = tmp_path / "rows.json"
|
|
bad.write_text('[{"title": "x", "norm": "x"}, {"title": "y"}]', encoding="utf-8")
|
|
root = _bundle(tmp_path / "b", [("a", "note.md", "Body.")])
|
|
assert quality.main([str(root), "--fasit", str(bad)]) == 2
|
|
|
|
|
|
def test_a_fasit_that_is_not_json_exits_two(tmp_path: Path) -> None:
|
|
bad = tmp_path / "broken.json"
|
|
bad.write_text("not json at all", encoding="utf-8")
|
|
root = _bundle(tmp_path / "b", [("a", "note.md", "Body.")])
|
|
assert quality.main([str(root), "--fasit", str(bad)]) == 2
|
|
|
|
|
|
def test_a_missing_fasit_file_exits_two(tmp_path: Path) -> None:
|
|
root = _bundle(tmp_path / "b", [("a", "note.md", "Body.")])
|
|
assert quality.main([str(root), "--fasit", str(tmp_path / "nowhere.json")]) == 2
|
|
|
|
|
|
def test_a_valid_fasit_reaches_the_gate_through_the_cli(tmp_path: Path, capsys) -> None: # type: ignore[no-untyped-def]
|
|
titles = [f"{n} Kapittel {n}" for n in range(1, 7)]
|
|
bundle = _bundle(tmp_path / "cli", [(f"c{i}", "doc.md", "Body.") for i in range(1)])
|
|
(bundle / "c0.md").write_text(
|
|
_FRONTMATTER.format(title=titles[0], source_file="doc.md", body="Body."),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
from llm_ingestion_okf import cli
|
|
|
|
assert (
|
|
cli.main(["quality", str(bundle), "--fasit", str(_fasit(tmp_path / "f.json", titles))]) == 1
|
|
)
|
|
out = capsys.readouterr().out
|
|
assert "boundary_share" in out
|
|
assert "1/6" in out
|
|
|
|
|
|
def test_a_fasit_below_the_floor_is_unmeasured_and_never_pass(tmp_path: Path) -> None:
|
|
"""A share over four declared boundaries is not a rate either."""
|
|
titles = ["1 A", "2 B", "3 C", "4 D"]
|
|
bundle = _bundle(tmp_path / "tiny", [(f"c{i}", "doc.md", "Body.") for i in range(4)])
|
|
for index, title in enumerate(titles):
|
|
(bundle / f"c{index}.md").write_text(
|
|
_FRONTMATTER.format(title=title, source_file="doc.md", body="Body."),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
report = quality.measure_bundle(
|
|
bundle, fasit=quality.load_fasit(_fasit(tmp_path / "f.json", titles))
|
|
)
|
|
assert report.boundaries is not None
|
|
assert report.boundaries.verdict == "UNMEASURED"
|
|
assert report.boundaries.recovered == 4
|
|
|
|
|
|
def test_the_boundary_row_says_its_threshold_rests_on_one_corpus(tmp_path: Path) -> None:
|
|
"""P2, in the printout rather than only in the document."""
|
|
titles = [f"{n} Kapittel {n}" for n in range(1, 7)]
|
|
bundle = _bundle(tmp_path / "caveat", [("c0", "doc.md", "Body.")])
|
|
(bundle / "c0.md").write_text(
|
|
_FRONTMATTER.format(title=titles[0], source_file="doc.md", body="Body."),
|
|
encoding="utf-8",
|
|
newline="",
|
|
)
|
|
rendered = quality.measure_bundle(
|
|
bundle, fasit=quality.load_fasit(_fasit(tmp_path / "f.json", titles))
|
|
).render()
|
|
assert "one product" in rendered
|
|
assert "N = 1" in rendered
|
|
|
|
|
|
def test_the_boundary_threshold_names_its_corpus_and_denominator() -> None:
|
|
bar = quality.BOUNDARY_THRESHOLD
|
|
assert bar.limit_declared >= quality.MIN_DECLARED_FOR_A_THRESHOLD
|
|
assert bar.corpora == 1
|
|
assert bar.source
|
|
|
|
|
|
@pytest.mark.skipif(not (_GOOD_ARM.is_dir() and _FASIT.is_file()), reason="local gold set absent")
|
|
def test_the_known_good_arm_reproduces_its_published_recall() -> None:
|
|
"""2 759 of 2 761, and the decomposition P1 asked for: 22 literal, 2 737 paired."""
|
|
report = quality.measure_bundle(_GOOD_ARM, fasit=quality.load_fasit(_FASIT))
|
|
assert report.boundaries is not None
|
|
assert (report.boundaries.recovered, report.boundaries.declared) == (2759, 2761)
|
|
assert (report.boundaries.literal, report.boundaries.paired) == (22, 2737)
|
|
assert report.boundaries.verdict == "PASS"
|
|
|
|
|
|
@pytest.mark.skipif(not (_BAD_ARM.is_dir() and _FASIT.is_file()), reason="local gold set absent")
|
|
def test_the_known_bad_arm_reproduces_its_published_recall() -> None:
|
|
"""1 148 of 2 761 -- the 41.6 % the whole gate could not previously see."""
|
|
report = quality.measure_bundle(_BAD_ARM, fasit=quality.load_fasit(_FASIT))
|
|
assert report.boundaries is not None
|
|
assert (report.boundaries.recovered, report.boundaries.declared) == (1148, 2761)
|
|
assert report.boundaries.verdict == "FAIL"
|
|
assert report.exit_code == 1
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not (_OTHER_PRODUCT.is_dir() and _FASIT.is_file()), reason="local gold set absent"
|
|
)
|
|
def test_a_bundle_of_another_product_scores_zero_and_that_is_the_assertion(tmp_path: Path) -> None:
|
|
"""The adverse case, measured rather than argued.
|
|
|
|
The fasit describes ONE product. The pinned 43-document K2 bundle is a
|
|
different corpus entirely and scores 0 of 2 761 -- a FAIL that says the
|
|
caller's assertion was wrong, not that the bundle is bad. `--fasit` is an
|
|
assertion by the caller, the way `okf consume --ref` is.
|
|
"""
|
|
report = quality.measure_bundle(_OTHER_PRODUCT, fasit=quality.load_fasit(_FASIT))
|
|
assert report.boundaries is not None
|
|
assert report.boundaries.recovered == 0
|
|
assert report.boundaries.verdict == "FAIL"
|
|
|
|
|
|
@pytest.mark.skipif(not _FASIT.is_file(), reason="local gold set absent")
|
|
def test_the_shipped_fasit_reproduces_its_own_key_under_this_normalisation() -> None:
|
|
"""2 761 of 2 761 rows: `norm` is exactly whitespace-stripped, lowercased title."""
|
|
rows = quality.load_fasit(_FASIT)
|
|
assert len(rows) == 2761
|
|
assert sum(1 for row in rows if quality.normalise_title(row.title) == row.norm) == 2761
|