Files
obsidian-wiki/tests/test_file_assets.py
Codex 2b7688bd75
setup / install-leaves-tree-clean (push) Canceled after 0s
fix(file-index): prune removed active assets on rebuild
Treat the source registry as authoritative during file-index rebuilds while preserving staged uploads. This prevents deleted archived sources from remaining searchable.

Tests: python3 -m unittest tests.test_file_assets tests.test_business_facts
2026-07-23 02:18:11 +00:00

107 lines
4.2 KiB
Python

import json
import tempfile
import unittest
from pathlib import Path
from obsidian_wiki.file_assets import rebuild_from_registry, search_assets
class FileAssetIndexTests(unittest.TestCase):
def setUp(self):
self.tempdir = tempfile.TemporaryDirectory()
self.vault = Path(self.tempdir.name)
(self.vault / "_meta").mkdir()
self.registry_path = self.vault / "_meta" / "source-registry.jsonl"
self.db_path = self.vault / "_meta" / "file-assets.sqlite"
def tearDown(self):
self.tempdir.cleanup()
def test_rebuild_preserves_registry_identifiers_for_part_number_search(self):
drawing_id = "sha256:" + "a" * 64
image_id = "sha256:" + "b" * 64
self._write_registry_record(
source_id=drawing_id,
archive_path="_sources/archive/bjd/pdf/a.pdf",
original_name="北极大-0.5-18客户图.pdf",
title="北极大 FPC 0.5-18 客户图纸",
summary="FPC 0.5-18 客户图 PDF 归档。",
doc_type="drawing",
source_type="pdf",
bjd_part_numbers=["101049-X0XXX0", "101049-20XXX0"],
series=["0.5-18"],
pitch=["0.5"],
pin_count=["18"],
)
self._write_registry_record(
source_id=image_id,
archive_path="_sources/archive/bjd/quality/photo.jpg",
original_name="微信图片_20250714101049.jpg",
title="微信图片_20250714101049",
summary="客诉图片。",
doc_type="evidence_media",
source_type="image",
business_categories=["quality/customer-complaints"],
)
rebuild_from_registry(self.vault, db_path=self.db_path)
rows = search_assets(self.vault, "101049 图纸", db_path=self.db_path, limit=5, read_only=True)
self.assertGreaterEqual(len(rows), 2)
self.assertEqual(rows[0]["file_id"], drawing_id)
self.assertEqual(json.loads(rows[0]["bjd_part_numbers"]), ["101049-X0XXX0", "101049-20XXX0"])
self.assertEqual(json.loads(rows[0]["series"]), ["0.5-18"])
self.assertEqual(json.loads(rows[0]["pitch"]), ["0.5"])
self.assertEqual(json.loads(rows[0]["pin_count"]), ["18"])
def test_rebuild_removes_active_records_removed_from_registry(self):
retained_id = "sha256:" + "c" * 64
removed_id = "sha256:" + "d" * 64
self._write_registry_record(
source_id=retained_id,
archive_path="_sources/archive/bjd/pdf/retained.pdf",
original_name="retained.pdf",
title="Retained source",
)
self._write_registry_record(
source_id=removed_id,
archive_path="_sources/archive/bjd/xlsx/removed.xlsx",
original_name="removed.xlsx",
title="Removed source",
)
rebuild_from_registry(self.vault, db_path=self.db_path)
retained_record = json.loads(self.registry_path.read_text(encoding="utf-8").splitlines()[0])
self.registry_path.write_text(json.dumps(retained_record) + "\n", encoding="utf-8")
rebuild_from_registry(self.vault, db_path=self.db_path)
remaining = search_assets(self.vault, "retained", db_path=self.db_path, limit=5, read_only=True)
removed = search_assets(self.vault, "removed", db_path=self.db_path, limit=5, read_only=True)
self.assertEqual([row["file_id"] for row in remaining], [retained_id])
self.assertEqual(removed, [])
def _write_registry_record(self, **fields):
record = {
"record_type": "source_archive",
"project": "bjd",
"visibility": "internal",
"business_categories": ["products/fpc"],
"product_lines": ["FPC", "FFC"],
"customers": [],
"competitors": [],
"standards": [],
"market_tags": [],
"related_pages": ["projects/bjd/references/example.md"],
"catalog_paths": ["_sources/catalog/bjd/products/fpc.md"],
"classification_confidence": 0.9,
"size_bytes": 1024,
**fields,
}
with self.registry_path.open("a", encoding="utf-8") as fh:
fh.write(json.dumps(record, ensure_ascii=False) + "\n")
if __name__ == "__main__":
unittest.main()