Мне нужно что-то немного другое, потому что мой ввод от преобразования речи в текст, и решение не всегда состоит в суммировании чисел. Например, «мой почтовый индекс - один два три четыре пять» не должен преобразовываться в «мой почтовый индекс 15».
Я взял ответ Эндрю и настроил его для обработки нескольких других случаев, которые люди отмечали как ошибки, а также добавил поддержку примеров, таких как почтовый индекс, который я упоминал выше. Ниже приведены некоторые базовые тесты, но я уверен, что еще есть возможности для улучшения.
def is_number(x):
if type(x) == str:
x = x.replace(',', '')
try:
float(x)
except:
return False
return True
def text2int (textnum, numwords={}):
units = [
'zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight',
'nine', 'ten', 'eleven', 'twelve', 'thirteen', 'fourteen', 'fifteen',
'sixteen', 'seventeen', 'eighteen', 'nineteen',
]
tens = ['', '', 'twenty', 'thirty', 'forty', 'fifty', 'sixty', 'seventy', 'eighty', 'ninety']
scales = ['hundred', 'thousand', 'million', 'billion', 'trillion']
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5, 'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
if not numwords:
numwords['and'] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
textnum = textnum.replace('-', ' ')
current = result = 0
curstring = ''
onnumber = False
lastunit = False
lastscale = False
def is_numword(x):
if is_number(x):
return True
if word in numwords:
return True
return False
def from_numword(x):
if is_number(x):
scale = 0
increment = int(x.replace(',', ''))
return scale, increment
return numwords[x]
for word in textnum.split():
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
current = current * scale + increment
if scale > 100:
result += current
current = 0
onnumber = True
lastunit = False
lastscale = False
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if (not is_numword(word)) or (word == 'and' and not lastscale):
if onnumber:
# Flush the current number we are building
curstring += repr(result + current) + " "
curstring += word + " "
result = current = 0
onnumber = False
lastunit = False
lastscale = False
else:
scale, increment = from_numword(word)
onnumber = True
if lastunit and (word not in scales):
# Assume this is part of a string of individual numbers to
# be flushed, such as a zipcode "one two three four five"
curstring += repr(result + current)
result = current = 0
if scale > 1:
current = max(1, current)
current = current * scale + increment
if scale > 100:
result += current
current = 0
lastscale = False
lastunit = False
if word in scales:
lastscale = True
elif word in units:
lastunit = True
if onnumber:
curstring += repr(result + current)
return curstring
Некоторые тесты ...
one two three -> 123
three forty five -> 345
three and forty five -> 3 and 45
three hundred and forty five -> 345
three hundred -> 300
twenty five hundred -> 2500
three thousand and six -> 3006
three thousand six -> 3006
nineteenth -> 19
twentieth -> 20
first -> 1
my zip is one two three four five -> my zip is 12345
nineteen ninety six -> 1996
fifty-seventh -> 57
one million -> 1000000
first hundred -> 100
I will buy the first thousand -> I will buy the 1000 # probably should leave ordinal in the string
thousand -> 1000
hundred and six -> 106
1 million -> 1000000