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

feat(F-16): chunk quality gate + section classification

Browse Source 
3-signal quality filter (length/alpha-ratio/bib-score) + rule-based section classifier + retroactive CLI pass. 35 new tests, 287 total green.
This commit is contained in:
user2595
2026-06-15 01:22:44 +00:00
parent 1a9afb4433
commit 9647897173
9 changed files with 529 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ingest/test_ingest.py
View File

@@ -131,6 +131,7 @@ def test_ingest_paper_source_tex(tmp_path: Any) -> None:
patch("codex.ingest.get_conn", side_effect=_make_conn_cm(mock_conn)),
patch("codex.parsing.tex.latex_to_text", return_value="Hello world. Intro text."),
patch("codex.parsing.tex.chunk_text", return_value=fake_chunks),
patch("codex.ingest.filter_chunks", side_effect=lambda chunks, settings: chunks),
):
result = ingest_paper(paper.id, source_path=str(tex_file))
@@ -178,6 +179,7 @@ def test_ingest_paper_source_pdf(tmp_path: Any) -> None:
patch("codex.parsing.nougat.pdf_to_markdown", return_value="pdf markdown text."),
patch("codex.parsing.tex.chunk_text", return_value=fake_chunks),
patch("codex.parsing.grobid.extract_references", return_value=grobid_refs),
patch("codex.ingest.filter_chunks", side_effect=lambda chunks, settings: chunks),
):
result = ingest_paper(paper.id, source_path=str(pdf_file))