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

18
tests/test_asset_limits.py
View file

@ -60,7 +60,7 @@ def test_a_remote_reference_is_not_a_markdown_image_link() -> None:
def test_the_pointer_block_of_a_carried_image_is_unchanged() -> None:
"""The known-positive beside it: a local image keeps its image block, or
the fix has merely disarmed the whole capability."""
image = assets.read_image((FIXTURES / "graphics" / "figur-84-1.png").read_bytes(), name="f.png")
image = assets.read_image((FIXTURES / "graphics" / "figur-7-1.png").read_bytes(), name="f.png")
assert IMAGE_POINTER.search(assets.render_block(image)) is not None
@ -89,7 +89,7 @@ def test_no_reader_writes_a_live_link_for_a_remote_reference(document: str, ref:
def test_a_data_uri_image_is_carried_and_leaves_no_foreign_link() -> None:
png = (FIXTURES / "graphics" / "figur-84-1.png").read_bytes()
png = (FIXTURES / "graphics" / "figur-7-1.png").read_bytes()
import base64
uri = "data:image/png;base64," + base64.b64encode(png).decode("ascii")
@ -482,13 +482,19 @@ def test_the_caption_of_a_remote_reference_is_still_stated() -> None:
against 0.10.0 and against this module's own reason for writing the line:
a reader cannot weigh an absence they were never shown."""
line = render_missing(
"p.gif", reason="the source is off this machine", label="Figur 84-1 Tverrprofil", href=None
"p.gif",
reason="the source is off this machine",
label="Figur 7-1 Prinsippskisse",
href=None,
)
assert "Figur 84-1 Tverrprofil" in line
assert "Figur 7-1 Prinsippskisse" in line
with_href = render_missing(
REMOTE, reason="the source is off this machine", label="Figur 84-1 Tverrprofil", href=REMOTE
REMOTE,
reason="the source is off this machine",
label="Figur 7-1 Prinsippskisse",
href=REMOTE,
)
assert "Figur 84-1 Tverrprofil" in with_href
assert "Figur 7-1 Prinsippskisse" in with_href
# --- BLOCKER of the 18.09 PM checkpoint: the CHAIN, not only its first link --