user2595/codex-py
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ingest): key formulas/figures on papers.id, not filename stem (audit C-10)

Browse Source 
extract_formulas/extract_figures derive paper_id from Path(pdf_path).stem, which
need not equal papers.id (and won't, given canonical ids). Inserting that stem
violated the formulas/figures -> papers(id) FK on rich (.pdf) ingest. The DELETE
already used paper.id; the INSERTs now do too.

Strengthened the rich-ingest test: the fake formula/figure carry a filename-stem
paper_id distinct from papers.id, and the test asserts the inserted rows are
keyed on papers.id.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Tarik Moussa
2026-06-15 12:09:38 +02:00
parent c36e7c6ee7
commit 8e2f9e037d
2 changed files with 20 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
codex/ingest.py
View File

@@ -294,7 +294,10 @@ def ingest_paper(
VALUES (%s, %s, %s, %s, %s)
""",
[
(f.paper_id, f.page, f.raw_latex, f.context, f.eq_label)
# paper.id, not f.paper_id: the extractor derives its
# paper_id from the PDF filename stem, which need not match
# papers.id and would violate the FK (audit C-10).
(paper.id, f.page, f.raw_latex, f.context, f.eq_label)
for f in formulas
],
)
@@ -308,7 +311,8 @@ def ingest_paper(
VALUES (%s, %s, %s, %s)
""",
[
(fig.paper_id, fig.page, fig.caption, fig.image_path)
# paper.id, not fig.paper_id (filename stem) — see C-10 above.
(paper.id, fig.page, fig.caption, fig.image_path)
for fig in figures
],
)

16
tests/ingest/test_ingest.py
View File

@@ -351,9 +351,11 @@ def test_ingest_paper_rich_calls_formula_and_figure_parsers(tmp_path: Any) -> No
mock_conn.executemany = MagicMock()
mock_conn.commit = MagicMock()
fake_formula = FormulaChunk(paper_id=paper.id, page=1, raw_latex=r"\alpha", context="test")
# Extractors derive paper_id from the PDF filename stem ("paper"), which differs
# from papers.id — ingest must insert papers.id, not this stem (audit C-10).
fake_formula = FormulaChunk(paper_id="paper", page=1, raw_latex=r"\alpha", context="test")
fake_figure = FigureChunk(
paper_id=paper.id, page=1, image_path="/tmp/fig.png", caption="Figure 1."
paper_id="paper", page=1, image_path="/tmp/fig.png", caption="Figure 1."
)
mock_settings = MagicMock()
@@ -380,6 +382,16 @@ def test_ingest_paper_rich_calls_formula_and_figure_parsers(tmp_path: Any) -> No
assert result.formulas_upserted == 1
assert result.figures_upserted == 1
# C-10: formula/figure rows must be keyed on papers.id, not the extractor's
# filename-stem paper_id, or the FK to papers(id) is violated.
cursor = mock_conn.cursor.return_value.__enter__.return_value
inserted_paper_ids = {
row[0] for call in cursor.executemany.call_args_list for row in call[0][1]
}
assert inserted_paper_ids == {paper.id}, (
f"formula/figure inserts must use papers.id, got {inserted_paper_ids}"
)
def test_ingest_paper_no_rich_skips_parsers(tmp_path: Any) -> None:
"""When rich=False (default), formula and figure parsers are NOT called."""