Extends Pagepiper's document shelving pipeline (renamed from "ingest" — see below) to cover the formats most likely to appear in a real-world engineering document corpus, prompted by scoping a STERIS licensing pitch that needs DOCX/ODT coverage. - Rename the ingest pipeline to "shelve" throughout (scripts/, app/api, tests, docs, frontend). "Glean" (Turnstone's term) was considered and rejected — that's a harvest metaphor for log/knowledge extraction, not a fit for documents entering a library. Documented as a general CF naming principle in the org-level CLAUDE.md. - Wire DOCX into the upload/scan UI, README, and docs — the extraction logic (heading-based chunking, table serialization) already existed but wasn't exposed to users or covered by tests. - Add ODT support via odfpy, mirroring DOCX's chunking strategy. - Add Apple Pages support via headless LibreOffice conversion to ODT. No maintained Python library parses the IWA format directly; libreoffice bundles libetonyek, the only real open-source Pages parser. Adds libreoffice-writer to the Docker image (~300-400MB) for this. - 24 new/updated tests across shelve_docx, shelve_odt, and shelve_pages; full suite (72 tests) passing. Known gaps not addressed here: no Windchill/DocPortal connector exists yet (metadata-only PowerShell recon only), Excel/.xlsx is unsupported, and circuitforge_core.tasks.dispatch_task does not currently exist in circuitforge-core — cf-orch dispatch is dead code, always falling through to local BackgroundTasks. See circuitforge-plans/pagepiper/superpowers/plans/2026-07-10-steris-licensing-pitch.md for the full writeup.
129 lines
4.4 KiB
Python
129 lines
4.4 KiB
Python
# tests/test_shelve_docx.py
|
|
"""Unit tests for scripts/shelve_docx.py."""
|
|
from __future__ import annotations
|
|
|
|
import sqlite3
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from scripts.shelve_docx import run
|
|
|
|
|
|
@pytest.fixture
|
|
def shelve_db(tmp_path) -> tuple[str, str]:
|
|
db_path = str(tmp_path / "test.db")
|
|
schema = Path("migrations/001_initial_schema.sql").read_text()
|
|
conn = sqlite3.connect(db_path)
|
|
conn.executescript(schema)
|
|
conn.execute(
|
|
"INSERT INTO documents(id, title, file_path, status) VALUES ('d1','Test','test.docx','pending')"
|
|
)
|
|
conn.commit()
|
|
conn.close()
|
|
vec_db_path = str(tmp_path / "vecs.db")
|
|
return db_path, vec_db_path
|
|
|
|
|
|
def _make_docx(path: Path, with_headings: bool = True, with_table: bool = False) -> None:
|
|
import docx
|
|
|
|
doc = docx.Document()
|
|
if with_headings:
|
|
doc.add_heading("Setting the IP", level=1)
|
|
doc.add_paragraph("Connect to the device over the service port.")
|
|
doc.add_heading("Verifying the Change", level=1)
|
|
doc.add_paragraph("Ping the new address to confirm.")
|
|
else:
|
|
doc.add_paragraph("Some unstructured procedure text with no headings at all.")
|
|
if with_table:
|
|
table = doc.add_table(rows=2, cols=2)
|
|
table.rows[0].cells[0].text = "Field"
|
|
table.rows[0].cells[1].text = "Value"
|
|
table.rows[1].cells[0].text = "IP Address"
|
|
table.rows[1].cells[1].text = "10.0.0.5"
|
|
doc.save(str(path))
|
|
|
|
|
|
def test_shelve_docx_sets_status_ready_on_success(shelve_db, tmp_path):
|
|
db_path, vec_db_path = shelve_db
|
|
docx_path = tmp_path / "test.docx"
|
|
_make_docx(docx_path)
|
|
|
|
run(doc_id="d1", file_path=str(docx_path), db_path=db_path, vec_db_path=vec_db_path)
|
|
|
|
conn = sqlite3.connect(db_path)
|
|
row = conn.execute("SELECT status, page_count FROM documents WHERE id='d1'").fetchone()
|
|
conn.close()
|
|
assert row[0] == "ready"
|
|
assert row[1] == 2 # one chunk per heading section
|
|
|
|
|
|
def test_shelve_docx_splits_by_heading(shelve_db, tmp_path):
|
|
db_path, vec_db_path = shelve_db
|
|
docx_path = tmp_path / "test.docx"
|
|
_make_docx(docx_path)
|
|
|
|
run(doc_id="d1", file_path=str(docx_path), db_path=db_path, vec_db_path=vec_db_path)
|
|
|
|
conn = sqlite3.connect(db_path)
|
|
rows = conn.execute(
|
|
"SELECT text FROM page_chunks WHERE doc_id='d1' ORDER BY page_number"
|
|
).fetchall()
|
|
conn.close()
|
|
assert len(rows) == 2
|
|
assert "Setting the IP" in rows[0][0]
|
|
assert "Verifying the Change" in rows[1][0]
|
|
|
|
|
|
def test_shelve_docx_falls_back_to_wordcount_chunks_without_headings(shelve_db, tmp_path):
|
|
db_path, vec_db_path = shelve_db
|
|
docx_path = tmp_path / "test.docx"
|
|
_make_docx(docx_path, with_headings=False)
|
|
|
|
run(doc_id="d1", file_path=str(docx_path), db_path=db_path, vec_db_path=vec_db_path)
|
|
|
|
conn = sqlite3.connect(db_path)
|
|
rows = conn.execute("SELECT text FROM page_chunks WHERE doc_id='d1'").fetchall()
|
|
conn.close()
|
|
assert len(rows) == 1
|
|
assert "unstructured procedure text" in rows[0][0]
|
|
|
|
|
|
def test_shelve_docx_serializes_tables_inline(shelve_db, tmp_path):
|
|
db_path, vec_db_path = shelve_db
|
|
docx_path = tmp_path / "test.docx"
|
|
_make_docx(docx_path, with_table=True)
|
|
|
|
run(doc_id="d1", file_path=str(docx_path), db_path=db_path, vec_db_path=vec_db_path)
|
|
|
|
conn = sqlite3.connect(db_path)
|
|
rows = conn.execute("SELECT text FROM page_chunks WHERE doc_id='d1'").fetchall()
|
|
conn.close()
|
|
joined = "\n".join(r[0] for r in rows)
|
|
assert "IP Address | 10.0.0.5" in joined
|
|
|
|
|
|
def test_shelve_docx_sets_error_status_on_failure(shelve_db, tmp_path):
|
|
db_path, vec_db_path = shelve_db
|
|
missing_path = tmp_path / "does-not-exist.docx"
|
|
|
|
with pytest.raises(Exception):
|
|
run(doc_id="d1", file_path=str(missing_path), db_path=db_path, vec_db_path=vec_db_path)
|
|
|
|
conn = sqlite3.connect(db_path)
|
|
row = conn.execute("SELECT status, error_msg FROM documents WHERE id='d1'").fetchone()
|
|
conn.close()
|
|
assert row[0] == "error"
|
|
assert row[1]
|
|
|
|
|
|
def test_shelve_docx_skips_embeddings_without_ollama_url(shelve_db, tmp_path, monkeypatch):
|
|
db_path, vec_db_path = shelve_db
|
|
monkeypatch.delenv("PAGEPIPER_OLLAMA_URL", raising=False)
|
|
docx_path = tmp_path / "test.docx"
|
|
_make_docx(docx_path)
|
|
|
|
run(doc_id="d1", file_path=str(docx_path), db_path=db_path, vec_db_path=vec_db_path)
|
|
|
|
assert not Path(vec_db_path).exists(), "vec DB should not be created without OLLAMA_URL"
|