def test_numeral_tables(tmprepo):
glottolog = Glottolog(tmprepo['glottolog'])
d = list(find_tables([tmprepo['raw'] / 'Abui.htm']))[0]
assert len(d) == 7
entry = NumeralsEntry(
base_name=d[0],
tables=d[1],
file_name=d[2],
title_name=d[3],
codes=glottolog.languoids_by_code(),
iso=glottolog.iso.languages,
source=d[4],
base=d[5],
comment=d[6],
)
assert len(entry.tables) == 8
assert entry.get_numeral_lexemes()[0][0][6][0] == 'tä.ˈlä.mä'
def test_num_entry(tmprepo, x, expected):
raw_htmls = tmprepo['raw']
glottolog = Glottolog(tmprepo['glottolog'])
f = raw_htmls / x
d = list(find_tables([f]))[0]
entry = NumeralsEntry(
base_name=d[0],
tables=d[1],
file_name=d[2],
title_name=d[3],
codes=glottolog.languoids_by_code(),
iso=glottolog.iso.languages,
source=d[4],
base=d[5],
comment=d[6],
)
assert entry.base_name == Path(f).stem
assert entry.glottocodes[0] == expected
def test_fuzzy_number_matching(tmprepo):
glottolog = Glottolog(tmprepo['glottolog'])
d = list(find_tables([tmprepo['raw'] / 'Aari.htm']))[0]
entry = NumeralsEntry(
base_name=d[0],
tables=d[1],
file_name=d[2],
title_name=d[3],
codes=glottolog.languoids_by_code(),
iso=glottolog.iso.languages,
source=d[4],
base=d[5],
comment=d[6],
)
numeral_table = entry.tables[1]
table_elements = numeral_table.find_all('tr')
cell_content = []
for row in table_elements:
cols = row.find_all('td')
cols = [ele.text.strip() for ele in cols]
cell_content.append([ele for ele in cols if ele])
# Table is roughly structured like this:
# 1 | 21
# 2 | 22
# 3 | 23
# ...
# 10 | 30
# ..
# 20 | 2000
assert parse_number(cell_content[0][0]) == 1
assert parse_number(cell_content[0][1]) == 21
assert parse_number(cell_content[9][0]) == 10
assert parse_number(cell_content[19][1]) == 2000