def parse_ibu(ibu_string):
'''
parse ibu to float
ibu might be a float (probably int) or it might be '-' or ???
'''
return (parse_number(ibu_string))
def parse_abv(abv_string):
'''
parse abv to float
abv might be a float with the '%' symbol or it might be '-' or ???
'''
return (parse_number(abv_string, rstrip='%'))
def _test_files(path, language):
for filename in get_test_files(path, f'{language}_'):
with open(filename, "r") as csv_file:
csv_reader = csv.DictReader(csv_file)
for row in csv_reader:
try:
assert parse_number(row['text'], language) == int(row['number'])
except AssertionError as e:
raise AssertionError(F"Failed execution of {row['text']}") from e
def test_zero(self):
self.assertEqual(parse_number('一百零一'), 101)
self.assertEqual(parse_number('三百零五'), 305)
self.assertEqual(parse_number('一千零三十五'), 1035)
self.assertEqual(parse_number('一千零六'), 1006)
self.assertEqual(parse_number('三十萬零二百五十'), 300250)
self.assertEqual(parse_number('八百萬零三百零一'), 8000301)
def normalize_human_input(
*,
human_input: str,
verbose: bool,
debug: bool,
):
if verbose or debug:
ic(human_input)
human_input = normalize_whitespace(
string=human_input,
verbose=verbose,
debug=debug,
)
if verbose or debug:
ic(human_input)
words = []
for word in human_input.split(' '):
#ic(word)
converted_word = parse_number(word)
#ic(converted_word)
if converted_word:
words.append(str(converted_word)) # numbers [/d] come back as ints
else:
words.append(word)
#ic(words)
human_input = ' '.join(words)
#ic(human_input)
if verbose or debug:
ic(human_input)
return human_input
def test_parse_number_digits(expected, test_input):
assert parse_number(test_input, LANG) == expected
def test_parse_number(self, expected, test_input):
assert parse_number(test_input) == expected
def test_parse_number(expected, test_input, lang):
assert parse_number(test_input, language=lang) == expected
def test_kanji_only(self):
self.assertEqual(parse_number('百八十一'), 181)
self.assertEqual(parse_number('二百八十一'), 281)
self.assertEqual(parse_number('千百八十一'), 1181)
self.assertEqual(parse_number('二千百八十一'), 2181)
self.assertEqual(parse_number('一万二千百八十一'), 12181)
self.assertEqual(parse_number('十万二千百八十一'), 102181)
self.assertEqual(parse_number('十一万二千百八十一'), 112181)
self.assertEqual(parse_number('百十一万二千百八十一'), 1112181)
self.assertEqual(parse_number('五百十一万二千百八十一'), 5112181)
self.assertEqual(parse_number('千五百十一万二千百八十一'), 15112181)
self.assertEqual(parse_number('四千五百十一万二千百八十一'), 45112181)
self.assertEqual(parse_number('一億千五百十一万二千百八十一'), 115112181)
self.assertEqual(parse_number('五十億十一'), 5000000011)
self.assertEqual(parse_number('三百二十一億千五百十一万二千百八十一'), 32115112181)
self.assertEqual(parse_number('千億十一'), 100000000011)
self.assertEqual(parse_number('六千三百二十一億千五百十一万二千百八十一'), 632115112181)
def test_separator(self):
self.assertEqual(parse_number('66,728千株'), 66728000)
self.assertEqual(parse_number('12 566 728千株'), 12566728000)
def test_numeric_mix(self):
self.assertEqual(parse_number('1億1511万2181'), 115112181)
self.assertEqual(parse_number('1000億11'), 100000000011)
self.assertEqual(parse_number('6千3百2十1億1511万2千百8十1'), 632115112181)
def test_decimal_mix(self):
self.assertEqual(parse_number('0.6千株'), 600)
self.assertEqual(parse_number('8千株'), 8000)
self.assertEqual(parse_number('7.28千株'), 7280)
self.assertEqual(parse_number('728千3百株'), 728300)
self.assertAlmostEqual(parse_number('66,728.123千株'), 66728123.0)
def test_parse_number_lang_auto(expected, test_input):
assert parse_number(test_input) == expected