def is_acronym(token, exclude=None):
"""
Pass single token as a string, return True/False if is/is not valid acronym.
Args:
token (str): single word to check for acronym-ness
exclude (Set[str]): if technically valid but not actually good acronyms
are known in advance, pass them in as a set of strings; matching
tokens will return False
Returns:
bool
"""
# exclude certain valid acronyms from consideration
if exclude and token in exclude:
return False
# don't allow empty strings
if not token:
return False
# don't allow spaces
if ' ' in token:
return False
# 2-character acronyms can't have lower-case letters
if len(token) == 2 and not token.isupper():
return False
# acronyms can't be all digits
if token.isdigit():
return False
# acronyms must have at least one upper-case letter or start/end with a digit
if (not any(char.isupper() for char in token)
and not (token[0].isdigit() or token[-1].isdigit())):
return False
# acronyms must have between 2 and 10 alphanumeric characters
if not 2 <= sum(1 for char in token if char.isalnum()) <= 10:
return False
# only certain combinations of letters, digits, and '&/.-' allowed
if not ACRONYM_REGEX.match(token):
return False
return True
def is_acronym(token, exclude=None):
"""
Pass single token as a string, return True/False if is/is not valid acronym.
Args:
token (str): single word to check for acronym-ness
exclude (Set[str]): if technically valid but not actually good acronyms
are known in advance, pass them in as a set of strings; matching
tokens will return False
Returns:
bool
"""
# exclude certain valid acronyms from consideration
if exclude and token in exclude:
return False
# don't allow empty strings
if not token:
return False
# don't allow spaces
if ' ' in token:
return False
# 2-character acronyms can't have lower-case letters
if len(token) == 2 and not token.isupper():
return False
# acronyms can't be all digits
if token.isdigit():
return False
# acronyms must have at least one upper-case letter or start/end with a digit
if (not any(char.isupper() for char in token) and
not (token[0].isdigit() or token[-1].isdigit())):
return False
# acronyms must have between 2 and 10 alphanumeric characters
if not 2 <= sum(1 for char in token if char.isalnum()) <= 10:
return False
# only certain combinations of letters, digits, and '&/.-' allowed
if not ACRONYM_REGEX.match(token):
return False
return True
def test_bad_acronym_regex():
for item in BAD_ACRONYMS:
assert ACRONYM_REGEX.search(item) is None
def test_good_acronym_regex():
for item in GOOD_ACRONYMS:
assert item == ACRONYM_REGEX.search(item).group()
def test_bad_acronym_regex(self):
for item in BAD_ACRONYMS:
self.assertIsNone(ACRONYM_REGEX.search(item))
def test_good_acronym_regex(self):
for item in GOOD_ACRONYMS:
self.assertEqual(item, ACRONYM_REGEX.search(item).group())
def test_bad_acronym_regex(self):
for item in BAD_ACRONYMS:
self.assertIsNone(ACRONYM_REGEX.search(item))
def test_good_acronym_regex(self):
for item in GOOD_ACRONYMS:
self.assertEqual(item, ACRONYM_REGEX.search(item).group())
