def remove_mentions(text) -> str:
"""
Function that removes words preceded with a '@'
Parameters
----------
text : str
Returns
-------
string
"""
text = normalize_whitespace(constants.AT_PATTERN.sub('', text))
return text
def remove_html_tags(text) -> str:
"""
Function that removes words between < and >
Parameters
----------
text : str
Returns
-------
string
"""
text = normalize_whitespace(constants.HTML_TAG_PATTERN.sub('', text))
return text
def remove_hashtag(text) -> str:
"""
Function that removes words preceded with a '#'
eg. "I take care of my skin #selfcare#selfestim" --> "I take care of my skin"
Parameters
----------
text : str
Returns
-------
str
text of a post without hashtags
"""
text = normalize_whitespace(constants.HASHTAG_PATTERN.sub('', text))
return text
def test_normalize_whitespace(input_str, expected_str):
result = normalize_whitespace(input_str)
np.testing.assert_equal(result, expected_str)