ben/scrape-giant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Make canonical auto-linking more conservative

Browse Source
This commit is contained in:
ben
2026-03-17 15:07:48 -04:00
parent 56a03bcb1d
commit 08e2a86cbd
2 changed files with 43 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/test_canonical_layer.py
View File

@@ -4,7 +4,7 @@ import build_canonical_layer
class CanonicalLayerTests(unittest.TestCase):
def test_build_canonical_layer_auto_links_exact_upc_and_name_size(self):
def test_build_canonical_layer_auto_links_exact_upc_and_name_size_only(self):
observed_rows = [
{
"observed_product_id": "gobs_1",
@@ -81,6 +81,21 @@ class CanonicalLayerTests(unittest.TestCase):
"is_discount_line": "false",
"is_coupon_line": "false",
},
{
"observed_product_id": "gobs_6",
"representative_upc": "",
"representative_retailer_item_id": "",
"representative_name_norm": "LIME",
"representative_brand": "",
"representative_variant": "",
"representative_size_value": "",
"representative_size_unit": "",
"representative_pack_qty": "",
"representative_measure_type": "each",
"is_fee": "false",
"is_discount_line": "false",
"is_coupon_line": "false",
},
]
canonicals, links = build_canonical_layer.build_canonical_layer(observed_rows)
@@ -93,6 +108,11 @@ class CanonicalLayerTests(unittest.TestCase):
self.assertEqual("exact_name_size", methods["gobs_3"])
self.assertEqual("exact_name_size", methods["gobs_4"])
self.assertNotIn("gobs_5", methods)
self.assertNotIn("gobs_6", methods)
def test_clean_canonical_name_removes_packaging_noise(self):
self.assertEqual("LIME", build_canonical_layer.clean_canonical_name("LIME . / ."))
self.assertEqual("EGG", build_canonical_layer.clean_canonical_name("5DZ EGG / /"))
if __name__ == "__main__":