Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
File size: 4,192 Bytes
19c8b95 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
""" from https://github.com/keithito/tacotron """
import inflect
import re
_inflect = inflect.engine()
_comma_number_re = re.compile(r'([0-9][0-9\,]+[0-9])')
_decimal_number_re = re.compile(r'([0-9]+\.[0-9]+)')
_pounds_re = re.compile(r'£([0-9\,]*[0-9]+)')
_dollars_re = re.compile(r'\$([0-9\.\,]*[0-9]+)')
_ordinal_re = re.compile(r'[0-9]+(st|nd|rd|th)')
_number_re = re.compile(r'[0-9]+')
_magnitudes = ['trillion', 'billion', 'million', 'thousand', 'hundred', 'm', 'b', 't']
_currency_re = re.compile(r'([\$€£₩])([0-9\.\,]*[0-9]+)(?:[ ]?({})(?=[^a-zA-Z]))?'.format("|".join(_magnitudes)), re.IGNORECASE)
_currency_key = {'$': 'dollar', '£': 'pound', '€': 'euro', '₩': 'won'}
_magnitudes_key = {'m': 'million', 'b': 'billion', 't': 'trillion'}
def _remove_commas(m):
return m.group(1).replace(',', '')
def _expand_decimal_point(m):
return m.group(1).replace('.', ' point ')
def _expand_currency(m):
currency = _currency_key[m.group(1)]
quantity = m.group(2)
magnitude = m.group(3)
# remove commas from quantity to be able to convert to numerical
quantity = quantity.replace(',', '')
# check for million, billion, etc...
if magnitude is not None and magnitude.lower() in _magnitudes:
if len(magnitude) == 1:
magnitude = _magnitudes_key[magnitude.lower()]
return "{} {} {}".format(_expand_hundreds(quantity), magnitude, currency+'s')
parts = quantity.split('.')
if len(parts) > 2:
return quantity + " " + currency + "s" # Unexpected format
dollars = int(parts[0]) if parts[0] else 0
cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
if dollars and cents:
dollar_unit = currency if dollars == 1 else currency+'s'
cent_unit = 'cent' if cents == 1 else 'cents'
return "{} {}, {} {}".format(
_expand_hundreds(dollars), dollar_unit,
_inflect.number_to_words(cents), cent_unit)
elif dollars:
dollar_unit = currency if dollars == 1 else currency+'s'
return "{} {}".format(_expand_hundreds(dollars), dollar_unit)
elif cents:
cent_unit = 'cent' if cents == 1 else 'cents'
return "{} {}".format(_inflect.number_to_words(cents), cent_unit)
else:
return 'zero' + ' ' + currency + 's'
def _expand_hundreds(text):
number = float(text)
if 1000 < number < 10000 and (number % 100 == 0) and (number % 1000 != 0):
return _inflect.number_to_words(int(number / 100)) + " hundred"
else:
return _inflect.number_to_words(text)
def _expand_dollars(m):
match = m.group(1)
parts = match.split('.')
if len(parts) > 2:
return match + ' dollars' # Unexpected format
dollars = int(parts[0]) if parts[0] else 0
cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
if dollars and cents:
dollar_unit = 'dollar' if dollars == 1 else 'dollars'
cent_unit = 'cent' if cents == 1 else 'cents'
return '%s %s, %s %s' % (dollars, dollar_unit, cents, cent_unit)
elif dollars:
dollar_unit = 'dollar' if dollars == 1 else 'dollars'
return '%s %s' % (dollars, dollar_unit)
elif cents:
cent_unit = 'cent' if cents == 1 else 'cents'
return '%s %s' % (cents, cent_unit)
else:
return 'zero dollars'
def _expand_ordinal(m):
return _inflect.number_to_words(m.group(0))
def _expand_number(m):
num = int(m.group(0))
if num > 1000 and num < 3000:
if num == 2000:
return 'two thousand'
elif num > 2000 and num < 2010:
return 'two thousand ' + _inflect.number_to_words(num % 100)
elif num % 100 == 0:
return _inflect.number_to_words(num // 100) + ' hundred'
else:
return _inflect.number_to_words(num, andword='', zero='oh', group=2).replace(', ', ' ')
else:
return _inflect.number_to_words(num, andword='')
def normalize_numbers(text):
text = re.sub(_comma_number_re, _remove_commas, text)
text = re.sub(_pounds_re, r'\1 pounds', text)
text = re.sub(_dollars_re, _expand_dollars, text)
text = re.sub(_decimal_number_re, _expand_decimal_point, text)
text = re.sub(_ordinal_re, _expand_ordinal, text)
text = re.sub(_number_re, _expand_number, text)
return text
|