def test_merge_differing_capitalization(self):
# this tests #19
insert_rows(self.scratch_db, 'brand', [
dict(brand='CardScan',
company='Newell Rubbermaid',
scraper_id='sr.campaign.hrc'),
dict(brand='Cardscan',
company='Newell Rubbermaid',
scraper_id='sr.campaign.hrc'),
])
insert_row(self.output_db, 'scraper_company_map', dict(
company='Newell Rubbermaid',
scraper_company='Newell Rubbermaid',
scraper_id='sr.campaign.hrc')
)
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[dict(brand='CardScan',
company='Newell Rubbermaid',
scraper_brand='CardScan',
scraper_company='Newell Rubbermaid',
scraper_id='sr.campaign.hrc'),
dict(brand='CardScan',
company='Newell Rubbermaid',
scraper_brand='Cardscan',
scraper_company='Newell Rubbermaid',
scraper_id='sr.campaign.hrc'),
])
def test_dont_push_brand_to_unrelated_subsidiary(self):
# tests #59
insert_rows(self.scratch_db, 'brand', [
dict(brand='Dove',
company='Unilever',
scraper_id='campaign.hrc'),
])
insert_rows(self.output_db, 'scraper_company_map', [
dict(company='Unilever',
scraper_company='Unilever',
scraper_id='campaign.hrc'),
])
insert_rows(self.output_db, 'subsidiary', [
dict(company='Unilever',
company_depth=0,
subsidiary="Ben & Jerry's",
subsidiary_depth=1),
])
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[dict(brand='Dove',
company='Unilever',
scraper_brand='Dove',
scraper_company='Unilever',
scraper_id='campaign.hrc'),
])
def test_match_brand_to_subsidiary_name(self):
insert_rows(self.scratch_db, 'brand', [
dict(brand='Puma',
company='Kering SA',
scraper_id='campaign.rankabrand'),
])
insert_rows(self.output_db, 'scraper_company_map', [
dict(company='Kering',
scraper_company='Kering SA',
scraper_id='campaign.rankabrand'),
])
insert_rows(self.output_db, 'subsidiary', [
dict(company='Kering',
company_depth=0,
subsidiary='Puma',
subsidiary_depth=1),
])
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[dict(brand='Puma',
company='Puma',
scraper_brand='Puma',
scraper_company='Kering SA',
scraper_id='campaign.rankabrand'),
])
def test_dump_empty_brand(self):
insert_rows(self.scratch_db, 'brand', [
dict(brand='™',
company='Voidcorp',
scraper_id='s'),
])
insert_rows(self.output_db, 'scraper_company_map', [
dict(company='Voidcorp',
scraper_company='Voidcorp',
scraper_id='s'),
])
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[])
def test_prefer_subsidiary_for_brand(self):
# tests #16
insert_rows(self.scratch_db, 'brand', [
dict(brand='Puma',
company='Puma',
scraper_id='campaign.btb_fashion'),
dict(brand='Puma',
company='Kering SA',
scraper_id='campaign.rankabrand'),
])
insert_rows(self.output_db, 'scraper_company_map', [
dict(company='Puma',
scraper_company='Puma',
scraper_id='campaign.btb_fashion'),
dict(company='Kering',
scraper_company='Kering SA',
scraper_id='campaign.rankabrand'),
])
insert_rows(self.output_db, 'subsidiary', [
dict(company='Kering',
company_depth=0,
subsidiary='Puma',
subsidiary_depth=1),
])
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[dict(brand='Puma',
company='Puma',
scraper_brand='Puma',
scraper_company='Kering SA',
scraper_id='campaign.rankabrand'),
dict(brand='Puma',
company='Puma',
scraper_brand='Puma',
scraper_company='Puma',
scraper_id='campaign.btb_fashion'),
])
def test_match_canonical_company_name_only(self):
# tests #40
insert_rows(self.scratch_db, 'brand', [
dict(brand='Asus',
company='Asus',
scraper_id='campaign.btb_electronics'),
dict(brand='Asus',
company='ASUSTeK Computer Incorporated',
scraper_id='campaign.rankabrand'),
])
# we picked ASUS as the canonical name based on company_name
insert_rows(self.output_db, 'scraper_company_map', [
dict(company='ASUS',
scraper_id='campaign.btb_electronics',
scraper_company='Asus'),
dict(company='ASUS',
scraper_id='campaign.rankabrand',
scraper_company='ASUSTeK Computer Incorporated'),
])
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[
dict(brand='ASUS',
company='ASUS',
scraper_brand='Asus',
scraper_company='ASUSTeK Computer Incorporated',
scraper_id='campaign.rankabrand'),
dict(brand='ASUS',
company='ASUS',
scraper_brand='Asus',
scraper_company='Asus',
scraper_id='campaign.btb_electronics'),
])
def test_merge_hyphens(self):
# tests #31
insert_rows(self.scratch_db, 'brand', [
dict(brand='Liquid Plumr',
company='Clorox',
scraper_id='company.clorox'),
dict(brand='Liquid-Plumr',
company='Clorox',
scraper_id='campaign.hrc'),
])
insert_rows(self.output_db, 'scraper_company_map', [
dict(company='Clorox',
scraper_id='company.clorox',
scraper_company='Clorox'),
dict(company='Clorox',
scraper_id='campaign.hrc',
scraper_company='Clorox'),
])
build_scraper_brand_map_table(self.output_db, self.scratch_db)
self.assertEqual(
select_all(self.output_db, 'scraper_brand_map'),
[
dict(brand='Liquid-Plumr',
company='Clorox',
scraper_brand='Liquid Plumr',
scraper_company='Clorox',
scraper_id='company.clorox'),
dict(brand='Liquid-Plumr',
company='Clorox',
scraper_brand='Liquid-Plumr',
scraper_company='Clorox',
scraper_id='campaign.hrc'),
])
