def get_checklist_for_renewal(Renewal_Notice):
temp = np.int64(Renewal_Notice // 30)
return [
str(temp) + " months",
n2w.convert(temp) + " months",
n2w.convert(temp) + " month",
str(temp) + " month"
]
def get_hint(num):
url = 'https://en.wikipedia.org/wiki/' + str(num) + '_(number)'
html = requests.get(url)
bs = BeautifulSoup(html.text, 'html.parser')
divs = bs.find('div', attrs={'id': 'mw-content-text'}).findAll('div')
hint = ''
for i in range(100):
hint = get_hint_text(divs)
if len(hint) > 40:
text_num = n2w.convert(num)
num_rep_list = [text_num, text_num.title(), text_num.upper()]
num_rep_list_dash = [x.replace(' ', '-') for x in num_rep_list]
num_rep_list_nospace = [x.replace(' ', '') for x in num_rep_list]
num_rep_list = [
num
] + num_rep_list + num_rep_list_dash + num_rep_list_nospace
for num_rep in num_rep_list:
try:
hint = hint.replace(num_rep, '????')
except:
hint = ''
break
if not hint.strip():
hint = 'No hint for you'
return hint
def preprocessDataset(dataset, foreign_characters, url, numbers, lemmatize):
processed_set = dataset
if foreign_characters:
aux_set = []
for line in processed_set:
aux_set.append(" ".join([
element for element in re.sub(r'[^\x00-\x7F]+', ' ',
line).rstrip().split(' ')
if element != ''
]))
processed_set = aux_set
if numbers:
aux_set = []
for line in processed_set:
aux_set.append(" ".join([
element if isNumber(element) == False else convert(element)
for element in line.rstrip().split(' ')
]))
processed_set = aux_set
if url:
aux_set = []
for line in processed_set:
aux_set.append(" ".join([
'REDACTEDURL' if bool(urlparse(element)[1]) else element
for element in line.rstrip().split(' ')
]))
processed_set = aux_set
if lemmatize:
tk = LemmaTokenizer()
processed_set = [" ".join(tk(line.lower())) for line in processed_set]
return processed_set
def arqmath_post_read_html5_worker(args):
post_id, html5_tokens = args
xml_document = html5_unicode_to_tree(html5_tokens)
math_tokens = {}
for math_element_number, math_element in enumerate(
xml_document.xpath('//span[@class="math-container"]')):
math_element_token = 'math_element_{}___'.format(
re.sub(r'\s+', '_', n2w.convert(math_element_number)))
replacement = etree.Element("span")
replacement.text = math_element_token
if math_element.tail:
replacement.text += ' ' + math_element.tail
math_element.getparent().replace(math_element, replacement)
if 'id' in math_element.attrib:
math_element_id = math_element.attrib['id']
else:
math_element_id = None
math_element_text = re.sub(r'^(\$*)(.*)\1', r'\2', math_element.text
or '')
math_tokens[math_element_token] = (math_element_id,
Math(math_element_text))
document = [
math_tokens[token] if token in math_tokens else Text(token)
for token in simple_preprocess(' '.join(xml_document.itertext()))
]
return (post_id, document)
def ntcir_article_read_html5_worker(args):
zip_filename, filename, only_latex = args
try:
with ZipFile(zip_filename, 'r') as zf:
with zf.open(filename, 'r') as f:
if only_latex:
html5_parser = etree.HTMLParser(huge_tree=True)
xml_document = etree.parse(f, html5_parser)
else:
html5_tokens = f.read().decode('utf-8')
xml_tokens = mathmlcan(html5_to_xhtml(html5_tokens))
xml_document = unicode_to_tree(xml_tokens)
math_tokens = {}
for math_element_number, math_element in enumerate(
xml_document.xpath('//math')):
math_element_token = 'math_element_{}___'.format(
re.sub(r'\s+', '_', n2w.convert(math_element_number)))
replacement = etree.Element("span")
replacement.text = math_element_token
if math_element.tail:
replacement.text += ' ' + math_element.tail
math_element.getparent().replace(math_element, replacement)
math_tokens[math_element_token] = Math(
tree_to_unicode(math_element))
document = [[
math_tokens[token] if token in math_tokens else Text(token)
for token in simple_preprocess(' '.join(paragraph.itertext()))
] for paragraph in xml_document.xpath(
'//div[contains(@class, "ltx_para")]')]
except (etree.Error, UnicodeDecodeError) as e:
document = []
return (zip_filename, filename, document)
def test_challenge4(self):
i = 3
while i < 20:
num = fibonacci(i)
print(str(num), " - ", (n2w.convert(num)))
i += 1
def __name(file_name: str) -> str:
name = file_name.split('.')[0].split('@')[0].replace(' ', '')
if name[0].isdigit():
# find numbers in the begin of the asset name
number = [int(s) for s in re.findall(r'-?\d+\.?\d*', name)][0]
# convert number in words
number_name = n2w.convert(number)
# remove numbers from name
name = name[len(str(number)):]
# join number words to name without number in begin
name = number_name + ' ' + name
# convert to snake case to convert after to camelcase (don't work convert directly to camel case)
name = stringcase.snakecase(name)
name = stringcase.camelcase(name)
return name
def process_line(line):
""" Preprocessing of the text data:
:1: Characters not in [A-Za-z0-9\s'] removed
:2: Arabic numbers are converted to English numbers
like 1000 to one thousand
:3: Repeated whitespace characters are squeezed to
one and the beginning whitespace characters are removed
:4: All characters are converted to lowercase
"""
# Splitting will remove repeated white spaces
line = re.sub(r"[^a-zA-z0-9\s]", "", line).split()
for index, word in enumerate(line):
line[index] = line[index].lower()
if word.isdigit():
try:
line[index] = convert(int(word))
except:
pass
return " ".join(line) + "\n"
import datetime
import n2w
nowTime = datetime.datetime.now()
print(nowTime)
print(nowTime.hour)
print(nowTime.minute)
print(nowTime.day)
print(nowTime.month)
print(nowTime.strftime("%B"))
print(nowTime.year)
print(nowTime.strftime('%A %d %B %Y'))
print(nowTime.strftime('%A %d %B'))
print(n2w.convert(2017))
ampm = " A M "
hour = int(nowTime.hour)
if hour > 12:
hour -= 12
ampm = " P M "
timeInWords = str(hour) + " " + str(nowTime.minute) + ampm
print(timeInWords)
dateInwords = nowTime.strftime('%A %d %B') + " " + n2w.convert(2017)
print(dateInwords)
import n2w from colorama import init, Fore, Back init() print(Back.YELLOW + Fore.RED + "Enter your number:") y=input() print(n2w.convert(y))
#q17 python
import n2w
letter_counter = 0
for i in range(1000) :
name = n2w.convert(i)
name = name.replace(" ", "")
letter_counter+=len(name)
if i % 100 != 0 :
letter_counter += 3
print letter_counter
def translate(num):
number = n2w.convert(num) #Converts integer to its equivalent word (e.g.: 1 -> 'one')
return translator.translate(number, dest='pt').text #Translates the previously created word into portuguese
import n2w as n from colorama import init, Fore, Back init() print ( Back.BLUE+ Fore.YELLOW + 'Enter any number: ') number = input() print ( n.convert(number))
