test(fixtures): replace sector-specific example material with generic, fictitious examples — green
Every fixture, test document, tool example and document now uses an invented kitchen-and-baking handbook series, written in this repository. The package's behaviour is unchanged; src/ changes are comments and help text only. - Generated fixtures are regenerated from their generators. Their structural counts are identical before and after: elements, images, rows, cells, headings, bookmarks and the witness inventory's per-document totals. The image-inbox and accounting documents are renamed kapittel-84-*. - tools/okf_accounting_gate.py: the two options that named one real corpus each are replaced by a generic, repeatable --corpus PATH with no default. Row 5 compares the PDF pair alone. Gate verdict unchanged: RED rows 2, 3, 6. - tools/okf_witness.py: the STS JSON reader for one publisher's delivery is removed, along with its three twins and five tests. The mutation harness loses W09. - docs/: 13 dated reports that documented runs on a retired reference corpus are removed, and 40 are neutralized. Dead links are removed, and no new dangling path is introduced. - The synthetic MCP-gate corpus and the residual probe words are neutral. Valgt: keep the `okf quality --fasit` bar value (the measured fraction, one corpus) and rewrite only its provenance, because the verdict stays unchanged and the number names nothing. Term check with the local list: 0 of 411 tracked files, 0 file names, 0 of 27 binary fixtures. Suite after git add: 2457 passed, 1 skipped. The base tree had 2460 passed and 2 skipped; five tests went with the JSON reader and four were added by the term check. ruff, ruff format and mypy --strict src/ are clean. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
parent
1e7345a401
commit
9d1f4b14ed
174 changed files with 1889 additions and 6512 deletions
|
|
@ -138,7 +138,7 @@ def test_a_type_with_no_reader_is_refused_rather_than_scored_zero(tmp_path: Path
|
|||
|
||||
SLIDE_XML = """<?xml version="1.0"?>
|
||||
<p:sld xmlns:a="a" xmlns:p="p"><p:cSld><p:spTree>
|
||||
<p:sp><p:txBody><a:p><a:r><a:t>Kravspesifikasjon for tunnel</a:t></a:r></a:p></p:txBody></p:sp>
|
||||
<p:sp><p:txBody><a:p><a:r><a:t>Kravspesifikasjon for kjeller</a:t></a:r></a:p></p:txBody></p:sp>
|
||||
<p:graphicFrame><a:tbl><a:tr>
|
||||
<a:tc><a:txBody><a:p><a:r><a:t>Navn tilbyder:</a:t></a:r></a:p></a:txBody></a:tc>
|
||||
<a:tc><a:txBody><a:p><a:r><a:t>Entreprenoer AS</a:t></a:r></a:p></a:txBody></a:tc>
|
||||
|
|
@ -149,7 +149,7 @@ SLIDE_XML = """<?xml version="1.0"?>
|
|||
CONTENT_XML = """<?xml version="1.0"?>
|
||||
<office:document-content xmlns:office="o" xmlns:text="t" xmlns:table="tb">
|
||||
<office:body><office:text>
|
||||
<text:h text:outline-level="1">Kravspesifikasjon for tunnel</text:h>
|
||||
<text:h text:outline-level="1">Kravspesifikasjon for kjeller</text:h>
|
||||
<table:table><table:table-row>
|
||||
<table:table-cell><text:p>Navn <text:span>tilbyder</text:span>:</text:p></table:table-cell>
|
||||
<table:table-cell><text:p>Entreprenoer AS</text:p></table:table-cell>
|
||||
|
|
@ -159,7 +159,7 @@ CONTENT_XML = """<?xml version="1.0"?>
|
|||
|
||||
RTF_STREAM = (
|
||||
"{\\rtf1\\ansi\\deff0{\\fonttbl{\\f0\\froman Times New Roman;}}\n"
|
||||
"\\pard Kravspesifikasjon for tunnel\\par\n"
|
||||
"\\pard Kravspesifikasjon for kjeller\\par\n"
|
||||
"\\trowd\\cellx3000\\cellx6000\n"
|
||||
"\\pard\\intbl Navn tilbyder:\\cell \\pard\\intbl Entrepren\\u248 ?r AS\\cell \\row\n"
|
||||
"}"
|
||||
|
|
@ -189,7 +189,7 @@ def rtf(tmp_path: Path) -> Path:
|
|||
def test_a_presentations_slide_text_is_read(tmp_path: Path) -> None:
|
||||
"""One string per `a:p`, table cells included -- a cell is a paragraph."""
|
||||
assert set(okf_fidelity.source_strings(pptx(tmp_path))) == {
|
||||
"kravspesifikasjon for tunnel",
|
||||
"kravspesifikasjon for kjeller",
|
||||
"navn tilbyder:",
|
||||
"entreprenoer as",
|
||||
}
|
||||
|
|
@ -198,7 +198,7 @@ def test_a_presentations_slide_text_is_read(tmp_path: Path) -> None:
|
|||
def test_an_odf_bodys_paragraphs_are_read(tmp_path: Path) -> None:
|
||||
"""Headings count, and a run split across a `text:span` is still one string."""
|
||||
assert set(okf_fidelity.source_strings(odt(tmp_path))) == {
|
||||
"kravspesifikasjon for tunnel",
|
||||
"kravspesifikasjon for kjeller",
|
||||
"navn tilbyder:",
|
||||
"entreprenoer as",
|
||||
}
|
||||
|
|
@ -207,7 +207,7 @@ def test_an_odf_bodys_paragraphs_are_read(tmp_path: Path) -> None:
|
|||
def test_an_rtf_streams_paragraphs_and_cells_are_read(tmp_path: Path) -> None:
|
||||
"""The control words are markup; the text between them is the document."""
|
||||
assert set(okf_fidelity.source_strings(rtf(tmp_path))) == {
|
||||
"kravspesifikasjon for tunnel",
|
||||
"kravspesifikasjon for kjeller",
|
||||
"navn tilbyder:",
|
||||
"entreprenør as",
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue