def extractnumber(text, lang="en-us"):
"""Takes in a string and extracts a number.
Args:
text (str): the string to extract a number from
lang (str): the code for the language text is in
Returns:
(str): The number extracted or the original text.
"""
lang_lower = str(lang).lower()
if lang_lower.startswith("en"):
# return extractnumber_en(text, remove_articles)
return extractnumber_en(text)
elif lang_lower.startswith("pt"):
return extractnumber_pt(text)
elif lang_lower.startswith("it"):
return extractnumber_it(text)
elif lang_lower.startswith("fr"):
return extractnumber_fr(text)
elif lang_lower.startswith("sv"):
return extractnumber_sv(text)
elif lang_lower.startswith("de"):
return extractnumber_de(text)
# TODO: extractnumber for other languages
return text
def extract_number(text, short_scale=True, ordinals=False, lang="en-us"):
"""Takes in a string and extracts a number.
Args:
text (str): the string to extract a number from
short_scale (bool): Use "short scale" or "long scale" for large
numbers -- over a million. The default is short scale, which
is now common in most English speaking countries.
See https://en.wikipedia.org/wiki/Names_of_large_numbers
ordinals (bool): consider ordinal numbers, e.g. third=3 instead of 1/3
lang (str): the BCP-47 code for the language to use
Returns:
(int, float or False): The number extracted or False if the input
text contains no numbers
"""
lang_lower = str(lang).lower()
if lang_lower.startswith("en"):
return extractnumber_en(text,
short_scale=short_scale,
ordinals=ordinals)
elif lang_lower.startswith("pt"):
return extractnumber_pt(text)
elif lang_lower.startswith("it"):
return extractnumber_it(text)
elif lang_lower.startswith("fr"):
return extractnumber_fr(text)
elif lang_lower.startswith("sv"):
return extractnumber_sv(text)
elif lang_lower.startswith("de"):
return extractnumber_de(text)
# TODO: extractnumber for other languages
return text
def extract_number(text, short_scale=True, lang="en-us"):
"""Takes in a string and extracts a number.
Args:
text (str): the string to extract a number from
short_scale (bool): use short or long scale. See
https://en.wikipedia.org/wiki/Names_of_large_numbers
lang (str): the code for the language text is in
Returns:
(int, float or False): The number extracted or False if the input
text contains no numbers
"""
lang_lower = str(lang).lower()
if lang_lower.startswith("en"):
return extractnumber_en(text, short_scale)
elif lang_lower.startswith("pt"):
return extractnumber_pt(text)
elif lang_lower.startswith("it"):
return extractnumber_it(text)
elif lang_lower.startswith("fr"):
return extractnumber_fr(text)
elif lang_lower.startswith("sv"):
return extractnumber_sv(text)
elif lang_lower.startswith("de"):
return extractnumber_de(text)
# TODO: extractnumber for other languages
return text
def extract_number(text, short_scale=True, ordinals=False, lang=None):
"""Takes in a string and extracts a number.
Args:
text (str): the string to extract a number from
short_scale (bool): Use "short scale" or "long scale" for large
numbers -- over a million. The default is short scale, which
is now common in most English speaking countries.
See https://en.wikipedia.org/wiki/Names_of_large_numbers
ordinals (bool): consider ordinal numbers, e.g. third=3 instead of 1/3
lang (str): the BCP-47 code for the language to use, None uses default
Returns:
(int, float or False): The number extracted or False if the input
text contains no numbers
"""
lang_code = get_primary_lang_code(lang)
if lang_code == "en":
return extractnumber_en(text,
short_scale=short_scale,
ordinals=ordinals)
elif lang_code == "es":
return extractnumber_es(text)
elif lang_code == "pt":
return extractnumber_pt(text)
elif lang_code == "it":
return extractnumber_it(text,
short_scale=short_scale,
ordinals=ordinals)
elif lang_code == "fr":
return extractnumber_fr(text)
elif lang_code == "sv":
return extractnumber_sv(text)
elif lang_code == "de":
return extractnumber_de(text)
elif lang_code == "da":
return extractnumber_da(text)
elif lang_code == "nl":
return extractnumber_nl(text,
short_scale=short_scale,
ordinals=ordinals)
# TODO: extractnumber_xx for other languages
_log_unsupported_language(
lang_lower, ['en', 'es', 'pt', 'it', 'fr', 'sv', 'de', 'da', 'nl'])
return text
def extract_number(text, short_scale=True, ordinals=False, lang=None):
"""Takes in a string and extracts a number.
Args:
text (str): the string to extract a number from
short_scale (bool): Use "short scale" or "long scale" for large
numbers -- over a million. The default is short scale, which
is now common in most English speaking countries.
See https://en.wikipedia.org/wiki/Names_of_large_numbers
ordinals (bool): consider ordinal numbers, e.g. third=3 instead of 1/3
lang (str): the BCP-47 code for the language to use, None uses default
Returns:
(int, float or False): The number extracted or False if the input
text contains no numbers
"""
lang_code = get_primary_lang_code(lang)
if lang_code == "en":
return extractnumber_en(text, short_scale=short_scale,
ordinals=ordinals)
elif lang_code == "es":
return extractnumber_es(text)
elif lang_code == "pt":
return extractnumber_pt(text)
elif lang_code == "it":
return extractnumber_it(text, short_scale=short_scale,
ordinals=ordinals)
elif lang_code == "fr":
return extractnumber_fr(text)
elif lang_code == "sv":
return extractnumber_sv(text)
elif lang_code == "de":
return extractnumber_de(text)
elif lang_code == "da":
return extractnumber_da(text)
# TODO: extractnumber_xx for other languages
_log_unsupported_language(lang_lower,
['en', 'es', 'pt', 'it', 'fr', 'sv', 'de', 'da'])
return text
def extract_number(text, short_scale=True, ordinals=False, lang="en-us"):
"""Takes in a string and extracts a number.
Args:
text (str): the string to extract a number from
short_scale (bool): Use "short scale" or "long scale" for large
numbers -- over a million. The default is short scale, which
is now common in most English speaking countries.
See https://en.wikipedia.org/wiki/Names_of_large_numbers
ordinals (bool): consider ordinal numbers, e.g. third=3 instead of 1/3
lang (str): the BCP-47 code for the language to use
Returns:
(int, float or False): The number extracted or False if the input
text contains no numbers
"""
lang_lower = str(lang).lower()
if lang_lower.startswith("en"):
return extractnumber_en(text, short_scale=short_scale,
ordinals=ordinals)
elif lang_lower.startswith("es"):
return extractnumber_es(text)
elif lang_lower.startswith("pt"):
return extractnumber_pt(text)
elif lang_lower.startswith("it"):
return extractnumber_it(text)
elif lang_lower.startswith("fr"):
return extractnumber_fr(text)
elif lang_lower.startswith("sv"):
return extractnumber_sv(text)
elif lang_lower.startswith("de"):
return extractnumber_de(text)
# TODO: extractnumber_xx for other languages
LOG.warning('Language "{}" not recognized! Please make sure your '
'language is one of the following: '
'en, es, pt, it, fr, sv, de.'.format(lang_lower))
return text