""" Tests for the product gallery's matching logic. The embedding model is injected, so these run without torch or a GPU: what is being tested is the retrieval contract - best view wins, several views per SKU count as one answer, and a stranger is rejected rather than named. """ from __future__ import annotations import os import sys import unittest import numpy as np current_dir = os.path.dirname(os.path.abspath(__file__)) project_root = os.path.dirname(current_dir) if os.path.exists(os.path.join(project_root, "stock")): os.chdir(project_root) if current_dir not in sys.path: sys.path.insert(0, current_dir) from gallery import GalleryEntry, ProductGallery # noqa: E402 def a_gallery(views, threshold=0.55): """A gallery with hand-made embeddings: no model, no files.""" skus = sorted({sku for sku, _ in views}) gallery = ProductGallery("does-not-exist", skus, threshold=threshold) embeddings = [] entries = [] for index, (sku, vector) in enumerate(views): vector = np.asarray(vector, dtype=np.float32) vector /= np.linalg.norm(vector) embeddings.append(vector) entries.append(GalleryEntry(sku_id=sku, view=f"{sku}_{index}", embedding=vector)) gallery._entries = entries gallery._matrix = np.stack(embeddings) gallery._available = True return gallery def unit(vector): vector = np.asarray(vector, dtype=np.float32) return (vector / np.linalg.norm(vector)).tolist() class MatchingTests(unittest.TestCase): def test_the_nearest_view_names_the_product(self): gallery = a_gallery([("sku_a", unit([1, 0, 0])), ("sku_b", unit([0, 1, 0]))]) gallery.embed = lambda crop: np.array([0.9, 0.1, 0.0], dtype=np.float32) match = gallery.match(object()) self.assertFalse(match.rejected) self.assertEqual(match.sku_id, "sku_a") self.assertAlmostEqual(match.similarity, 0.9, places=3) def test_several_views_of_one_sku_are_one_answer(self): # The second view of sku_b is closer than any view of sku_a, but sku_a must # still win on its best view: a SKU is not outvoted by having more photos. gallery = a_gallery([ ("sku_a", unit([1, 0, 0])), ("sku_b", unit([0, 1, 0])), ("sku_b", unit([0.2, 0.98, 0])), ]) gallery.embed = lambda crop: np.array([1.0, 0.05, 0.0], dtype=np.float32) match = gallery.match(object()) self.assertEqual(match.sku_id, "sku_a") self.assertEqual(match.runner_up, "sku_b") def test_a_stranger_is_rejected_not_named(self): gallery = a_gallery([("sku_a", unit([1, 0, 0])), ("sku_b", unit([0, 1, 0]))]) gallery.embed = lambda crop: np.array([0.0, 0.0, 1.0], dtype=np.float32) match = gallery.match(object()) self.assertTrue(match.rejected) self.assertIsNone(match.sku_id) def test_the_threshold_moves_the_rejection_line(self): gallery = a_gallery([("sku_a", unit([1, 0, 0]))], threshold=0.99) gallery.embed = lambda crop: np.array([0.9, 0.4, 0.0], dtype=np.float32) self.assertTrue(gallery.match(object()).rejected) self.assertFalse(gallery.match(object(), threshold=0.5).rejected) def test_margin_separates_a_confident_match_from_a_close_one(self): gallery = a_gallery([("sku_a", unit([1, 0, 0])), ("sku_b", unit([0.9, 0.44, 0]))]) gallery.embed = lambda crop: np.array([1.0, 0.1, 0.0], dtype=np.float32) confident = gallery.match(object()) gallery.embed = lambda crop: np.array([0.95, 0.3, 0.0], dtype=np.float32) close = gallery.match(object()) self.assertGreater(confident.margin, close.margin) def test_an_unloaded_gallery_rejects_everything(self): gallery = ProductGallery("does-not-exist", ["sku_a"]) match = gallery.match(object()) self.assertTrue(match.rejected) class EnrollmentTests(unittest.TestCase): def test_views_are_found_by_sku_prefix(self): import tempfile with tempfile.TemporaryDirectory() as directory: for name in ("sku_a.jpeg", "sku_a_1.jpeg", "sku_a-2.jpeg", "sku_ab.jpeg", "notes.txt"): open(os.path.join(directory, name), "wb").close() gallery = ProductGallery(directory, ["sku_a", "sku_ab"]) self.assertEqual(len(gallery._views_for("sku_a")), 3, "one view, two extra views, and not sku_ab") self.assertEqual(len(gallery._views_for("sku_ab")), 1) if __name__ == "__main__": unittest.main()