# tests/test_shelve_ods.py """Unit tests for scripts/shelve_ods.py.""" from __future__ import annotations import sqlite3 from pathlib import Path import pytest from scripts.shelve_ods import run, ROWS_PER_CHUNK @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.ods','pending')" ) conn.commit() conn.close() vec_db_path = str(tmp_path / "vecs.db") return db_path, vec_db_path def _make_ods(path: Path, big_sheet: bool = False) -> None: from odf.opendocument import OpenDocumentSpreadsheet from odf.table import Table, TableRow, TableCell from odf.text import P def _row(vals): row = TableRow() for v in vals: cell = TableCell() cell.addElement(P(text=v)) row.addElement(cell) return row doc = OpenDocumentSpreadsheet() t1 = Table(name="Config") t1.addElement(_row(["Field", "Value"])) t1.addElement(_row(["Default IP", "192.168.1.50"])) t1.addElement(_row(["AVC-X Model", "AVC-X200"])) doc.spreadsheet.addElement(t1) t2 = Table(name="Parts List") t2.addElement(_row(["Part Number", "Description"])) if big_sheet: for i in range(ROWS_PER_CHUNK + 50): t2.addElement(_row([f"P{i:04d}", f"Widget {i}"])) else: t2.addElement(_row(["P0001", "Filter cartridge"])) doc.spreadsheet.addElement(t2) doc.save(str(path)) def test_shelve_ods_sets_status_ready_on_success(shelve_db, tmp_path): db_path, vec_db_path = shelve_db ods_path = tmp_path / "test.ods" _make_ods(ods_path) run(doc_id="d1", file_path=str(ods_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 def test_shelve_ods_serializes_rows_with_header(shelve_db, tmp_path): db_path, vec_db_path = shelve_db ods_path = tmp_path / "test.ods" _make_ods(ods_path) run(doc_id="d1", file_path=str(ods_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 "Sheet: Config" in rows[0][0] assert "Field | Value" in rows[0][0] assert "Default IP | 192.168.1.50" in rows[0][0] assert "Sheet: Parts List" in rows[1][0] assert "P0001 | Filter cartridge" in rows[1][0] def test_shelve_ods_splits_large_sheet_into_row_windows(shelve_db, tmp_path): db_path, vec_db_path = shelve_db ods_path = tmp_path / "test.ods" _make_ods(ods_path, big_sheet=True) run(doc_id="d1", file_path=str(ods_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) >= 3 parts_list_chunks = [r[0] for r in rows if "Sheet: Parts List" in r[0]] assert len(parts_list_chunks) >= 2 for chunk_text in parts_list_chunks: assert "Part Number | Description" in chunk_text def test_shelve_ods_sets_error_status_on_failure(shelve_db, tmp_path): db_path, vec_db_path = shelve_db missing_path = tmp_path / "does-not-exist.ods" 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_ods_skips_embeddings_without_ollama_url(shelve_db, tmp_path, monkeypatch): db_path, vec_db_path = shelve_db monkeypatch.delenv("PAGEPIPER_OLLAMA_URL", raising=False) ods_path = tmp_path / "test.ods" _make_ods(ods_path) run(doc_id="d1", file_path=str(ods_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"