def tag(string):
""" Tags a string.
Parameters
----------
string : str,
Returns
-------
tuples : list of tuples and boolean
Examples
--------
"""
sentence_with_no_accent = remove_accents(string)
for tag in regex_segmenting_order:
for compiled_regex in compiled_regex_segmenting_dict[tag]:
if compiled_regex.search(sentence_with_no_accent):
if tag in ["HELLO", "GREETINGS", "THANKS"]:
# We search for words of the flag list who mean the sentence contains information as body
for regex, value in regex_flags_dict.items():
if re.search(pattern=regex,
string=sentence_with_no_accent,
flags=re.IGNORECASE):
return string, False
return [(string, tag)], True
return string, False
def tag(string):
""" Tags a string.
Parameters
----------
string : str,
Returns
-------
tuples : list of tuples and boolean
Examples
--------
"""
regex_parts = compiled_regex_segmenting_dict.items()
sentence_with_no_accent = remove_accents(string)
for k, compiled_regex_list in regex_parts:
for compiled_regex in compiled_regex_list:
if compiled_regex.search(sentence_with_no_accent):
return [(string, k)], True
return string, False
def tag(string):
""" Tags a string.
Parameters
----------
string : str,
Returns
-------
tuples : list of tuples and boolean
Examples
--------
"""
regex_parts = regex_segmenting_dict.items()
sentence_with_no_accent = remove_accents(string)
for k, reg in regex_parts:
for r in reg:
r = r.replace(" ", regex_tag)
if re.search(r, sentence_with_no_accent, re.I):
return [(string, k)], True
return string, False
def test_remove_accents():
input_str = "éèëêàù"
expected_str = "eeeeau"
result = remove_accents(input_str)
np.testing.assert_string_equal(result, expected_str)