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

Improve product review display workflow

Browse Source
This commit is contained in:
ben
2026-03-17 12:25:47 -04:00
parent e494386e64
commit 7b8141cd42
5 changed files with 372 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
tests/test_purchases.py
View File

@@ -41,6 +41,7 @@ class PurchaseLogTests(unittest.TestCase):
"order_date": "2026-03-01",
"item_name": "FRESH BANANA",
"item_name_norm": "BANANA",
"image_url": "https://example.test/banana.jpg",
"retailer_item_id": "100",
"upc": "4011",
"qty": "1",
@@ -99,24 +100,18 @@ class PurchaseLogTests(unittest.TestCase):
}
]
<<<<<<< HEAD
rows, _observed, _canon, _links = build_purchases.build_purchase_rows(
=======
rows = build_purchases.build_purchase_rows(
>>>>>>> be1bf63 (Build pivot-ready purchase log)
[giant_row],
[costco_row],
giant_orders,
costco_orders,
<<<<<<< HEAD
[],
=======
>>>>>>> be1bf63 (Build pivot-ready purchase log)
)
self.assertEqual(2, len(rows))
self.assertTrue(all(row["canonical_product_id"] for row in rows))
self.assertEqual({"giant", "costco"}, {row["retailer"] for row in rows})
self.assertEqual("https://example.test/banana.jpg", rows[0]["image_url"])
def test_main_writes_purchase_and_example_csvs(self):
with tempfile.TemporaryDirectory() as tmpdir:
@@ -124,11 +119,13 @@ class PurchaseLogTests(unittest.TestCase):
costco_items = Path(tmpdir) / "costco_items.csv"
giant_orders = Path(tmpdir) / "giant_orders.csv"
costco_orders = Path(tmpdir) / "costco_orders.csv"
resolutions_csv = Path(tmpdir) / "review_resolutions.csv"
catalog_csv = Path(tmpdir) / "canonical_catalog.csv"
links_csv = Path(tmpdir) / "product_links.csv"
purchases_csv = Path(tmpdir) / "combined" / "purchases.csv"
examples_csv = Path(tmpdir) / "combined" / "comparison_examples.csv"
fieldnames = enrich_costco.OUTPUT_FIELDS
rows = []
giant_row = {field: "" for field in fieldnames}
giant_row.update(
{
@@ -178,7 +175,6 @@ class PurchaseLogTests(unittest.TestCase):
"is_fee": "false",
}
)
rows.extend([giant_row, costco_row])
for path, source_rows in [
(giant_items, [giant_row]),
@@ -189,12 +185,35 @@ class PurchaseLogTests(unittest.TestCase):
writer.writeheader()
writer.writerows(source_rows)
order_fields = ["order_id", "store_name", "store_number", "store_city", "store_state"]
for path, source_rows in [
(giant_orders, [{"order_id": "g1", "store_name": "Giant", "store_number": "42", "store_city": "Springfield", "store_state": "VA"}]),
(costco_orders, [{"order_id": "c1", "store_name": "MT VERNON", "store_number": "1115", "store_city": "ALEXANDRIA", "store_state": "VA"}]),
(
giant_orders,
[
{
"order_id": "g1",
"store_name": "Giant",
"store_number": "42",
"store_city": "Springfield",
"store_state": "VA",
}
],
),
(
costco_orders,
[
{
"order_id": "c1",
"store_name": "MT VERNON",
"store_number": "1115",
"store_city": "ALEXANDRIA",
"store_state": "VA",
}
],
),
]:
with path.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=["order_id", "store_name", "store_number", "store_city", "store_state"])
writer = csv.DictWriter(handle, fieldnames=order_fields)
writer.writeheader()
writer.writerows(source_rows)
@@ -203,12 +222,9 @@ class PurchaseLogTests(unittest.TestCase):
costco_items_enriched_csv=str(costco_items),
giant_orders_csv=str(giant_orders),
costco_orders_csv=str(costco_orders),
<<<<<<< HEAD
resolutions_csv=str(Path(tmpdir) / "review_resolutions.csv"),
catalog_csv=str(Path(tmpdir) / "canonical_catalog.csv"),
links_csv=str(Path(tmpdir) / "product_links.csv"),
=======
>>>>>>> be1bf63 (Build pivot-ready purchase log)
resolutions_csv=str(resolutions_csv),
catalog_csv=str(catalog_csv),
links_csv=str(links_csv),
output_csv=str(purchases_csv),
examples_csv=str(examples_csv),
)
@@ -222,7 +238,6 @@ class PurchaseLogTests(unittest.TestCase):
self.assertEqual(2, len(purchase_rows))
self.assertEqual(1, len(example_rows))
<<<<<<< HEAD
def test_build_purchase_rows_applies_manual_resolution(self):
fieldnames = enrich_costco.OUTPUT_FIELDS
giant_row = {field: "" for field in fieldnames}
@@ -255,7 +270,15 @@ class PurchaseLogTests(unittest.TestCase):
rows, _observed, _canon, _links = build_purchases.build_purchase_rows(
[giant_row],
[],
[{"order_id": "g1", "store_name": "Giant", "store_number": "42", "store_city": "Springfield", "store_state": "VA"}],
[
{
"order_id": "g1",
"store_name": "Giant",
"store_number": "42",
"store_city": "Springfield",
"store_state": "VA",
}
],
[],
[
{
@@ -273,8 +296,6 @@ class PurchaseLogTests(unittest.TestCase):
self.assertEqual("approved", rows[0]["review_status"])
self.assertEqual("create", rows[0]["resolution_action"])
=======
>>>>>>> be1bf63 (Build pivot-ready purchase log)
if __name__ == "__main__":
unittest.main()

139
tests/test_review_workflow.py
View File

@@ -4,6 +4,8 @@ import unittest
from pathlib import Path
from unittest import mock
from click.testing import CliRunner
import review_products
@@ -37,6 +39,135 @@ class ReviewWorkflowTests(unittest.TestCase):
self.assertEqual("gobs_1", queue_rows[0]["observed_product_id"])
self.assertIn("SB BAGGED ICE 20LB", queue_rows[0]["raw_item_names"])
def test_build_canonical_suggestions_prefers_upc_then_name(self):
suggestions = review_products.build_canonical_suggestions(
[
{
"normalized_item_name": "MIXED PEPPER",
"upc": "12345",
}
],
[
{
"canonical_product_id": "gcan_1",
"canonical_name": "MIXED PEPPER",
"upc": "",
},
{
"canonical_product_id": "gcan_2",
"canonical_name": "MIXED PEPPER 6 PACK",
"upc": "12345",
},
],
)
self.assertEqual("gcan_2", suggestions[0]["canonical_product_id"])
self.assertEqual("exact upc", suggestions[0]["reason"])
self.assertEqual("gcan_1", suggestions[1]["canonical_product_id"])
def test_review_products_displays_position_items_and_suggestions(self):
with tempfile.TemporaryDirectory() as tmpdir:
purchases_csv = Path(tmpdir) / "purchases.csv"
queue_csv = Path(tmpdir) / "review_queue.csv"
resolutions_csv = Path(tmpdir) / "review_resolutions.csv"
catalog_csv = Path(tmpdir) / "canonical_catalog.csv"
purchase_fields = [
"purchase_date",
"retailer",
"order_id",
"line_no",
"observed_product_id",
"canonical_product_id",
"raw_item_name",
"normalized_item_name",
"image_url",
"upc",
"line_total",
]
with purchases_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=purchase_fields)
writer.writeheader()
writer.writerows(
[
{
"purchase_date": "2026-03-14",
"retailer": "costco",
"order_id": "c2",
"line_no": "2",
"observed_product_id": "gobs_mix",
"canonical_product_id": "",
"raw_item_name": "MIXED PEPPER 6-PACK",
"normalized_item_name": "MIXED PEPPER",
"image_url": "",
"upc": "",
"line_total": "7.49",
},
{
"purchase_date": "2026-03-12",
"retailer": "costco",
"order_id": "c1",
"line_no": "1",
"observed_product_id": "gobs_mix",
"canonical_product_id": "",
"raw_item_name": "MIXED PEPPER 6-PACK",
"normalized_item_name": "MIXED PEPPER",
"image_url": "https://example.test/mixed-pepper.jpg",
"upc": "",
"line_total": "6.99",
},
]
)
with catalog_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=review_products.build_purchases.CATALOG_FIELDS)
writer.writeheader()
writer.writerow(
{
"canonical_product_id": "gcan_mix",
"canonical_name": "MIXED PEPPER",
"category": "produce",
"product_type": "pepper",
"brand": "",
"variant": "",
"size_value": "",
"size_unit": "",
"pack_qty": "",
"measure_type": "",
"notes": "",
"created_at": "",
"updated_at": "",
}
)
runner = CliRunner()
result = runner.invoke(
review_products.main,
[
"--purchases-csv",
str(purchases_csv),
"--queue-csv",
str(queue_csv),
"--resolutions-csv",
str(resolutions_csv),
"--catalog-csv",
str(catalog_csv),
],
input="q\n",
color=True,
)
self.assertEqual(0, result.exit_code)
self.assertIn("Review observed product (1/1)", result.output)
self.assertIn("Resolve this observed product group", result.output)
self.assertIn("actions: [l]ink existing [n]ew canonical e[x]clude [s]kip [q]uit", result.output)
first_item = result.output.index("2026-03-14 | 7.49")
second_item = result.output.index("2026-03-12 | 6.99")
self.assertLess(first_item, second_item)
self.assertIn("image: https://example.test/mixed-pepper.jpg", result.output)
self.assertIn("gcan_mix | MIXED PEPPER (exact normalized name)", result.output)
self.assertIn("\x1b[", result.output)
def test_review_products_creates_canonical_and_resolution(self):
with tempfile.TemporaryDirectory() as tmpdir:
purchases_csv = Path(tmpdir) / "purchases.csv"
@@ -48,25 +179,33 @@ class ReviewWorkflowTests(unittest.TestCase):
writer = csv.DictWriter(
handle,
fieldnames=[
"purchase_date",
"observed_product_id",
"canonical_product_id",
"retailer",
"raw_item_name",
"normalized_item_name",
"image_url",
"upc",
"line_total",
"order_id",
"line_no",
],
)
writer.writeheader()
writer.writerow(
{
"purchase_date": "2026-03-15",
"observed_product_id": "gobs_ice",
"canonical_product_id": "",
"retailer": "giant",
"raw_item_name": "SB BAGGED ICE 20LB",
"normalized_item_name": "BAGGED ICE",
"image_url": "",
"upc": "",
"line_total": "3.50",
"order_id": "g1",
"line_no": "1",
}
)