File size: 5,538 Bytes
4300fed |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 |
import collections
import re
from enum import Enum
import six
_DEF_PUNCS = ';:,.!?¡¿—…"«»“”'
_PUNC_IDX = collections.namedtuple("_punc_index", ["punc", "position"])
class PuncPosition(Enum):
"""Enum for the punctuations positions"""
BEGIN = 0
END = 1
MIDDLE = 2
ALONE = 3
class Punctuation:
"""Handle punctuations in text.
Just strip punctuations from text or strip and restore them later.
Args:
puncs (str): The punctuations to be processed. Defaults to `_DEF_PUNCS`.
Example:
>>> punc = Punctuation()
>>> punc.strip("This is. example !")
'This is example'
>>> text_striped, punc_map = punc.strip_to_restore("This is. example !")
>>> ' '.join(text_striped)
'This is example'
>>> text_restored = punc.restore(text_striped, punc_map)
>>> text_restored[0]
'This is. example !'
"""
def __init__(self, puncs: str = _DEF_PUNCS):
self.puncs = puncs
@staticmethod
def default_puncs():
"""Return default set of punctuations."""
return _DEF_PUNCS
@property
def puncs(self):
return self._puncs
@puncs.setter
def puncs(self, value):
if not isinstance(value, six.string_types):
raise ValueError("[!] Punctuations must be of type str.")
self._puncs = "".join(list(dict.fromkeys(list(value)))) # remove duplicates without changing the oreder
self.puncs_regular_exp = re.compile(rf"(\s*[{re.escape(self._puncs)}]+\s*)+")
def strip(self, text):
"""Remove all the punctuations by replacing with `space`.
Args:
text (str): The text to be processed.
Example::
"This is. example !" -> "This is example "
"""
return re.sub(self.puncs_regular_exp, " ", text).rstrip().lstrip()
def strip_to_restore(self, text):
"""Remove punctuations from text to restore them later.
Args:
text (str): The text to be processed.
Examples ::
"This is. example !" -> [["This is", "example"], [".", "!"]]
"""
text, puncs = self._strip_to_restore(text)
return text, puncs
def _strip_to_restore(self, text):
"""Auxiliary method for Punctuation.preserve()"""
matches = list(re.finditer(self.puncs_regular_exp, text))
if not matches:
return [text], []
# the text is only punctuations
if len(matches) == 1 and matches[0].group() == text:
return [], [_PUNC_IDX(text, PuncPosition.ALONE)]
# build a punctuation map to be used later to restore punctuations
puncs = []
for match in matches:
position = PuncPosition.MIDDLE
if match == matches[0] and text.startswith(match.group()):
position = PuncPosition.BEGIN
elif match == matches[-1] and text.endswith(match.group()):
position = PuncPosition.END
puncs.append(_PUNC_IDX(match.group(), position))
# convert str text to a List[str], each item is separated by a punctuation
splitted_text = []
for idx, punc in enumerate(puncs):
split = text.split(punc.punc)
prefix, suffix = split[0], punc.punc.join(split[1:])
splitted_text.append(prefix)
# if the text does not end with a punctuation, add it to the last item
if idx == len(puncs) - 1 and len(suffix) > 0:
splitted_text.append(suffix)
text = suffix
while splitted_text[0] == '':
splitted_text = splitted_text[1:]
return splitted_text, puncs
@classmethod
def restore(cls, text, puncs):
"""Restore punctuation in a text.
Args:
text (str): The text to be processed.
puncs (List[str]): The list of punctuations map to be used for restoring.
Examples ::
['This is', 'example'], ['.', '!'] -> "This is. example!"
"""
return cls._restore(text, puncs, 0)
@classmethod
def _restore(cls, text, puncs, num): # pylint: disable=too-many-return-statements
"""Auxiliary method for Punctuation.restore()"""
if not puncs:
return text
# nothing have been phonemized, returns the puncs alone
if not text:
return ["".join(m.punc for m in puncs)]
current = puncs[0]
if current.position == PuncPosition.BEGIN:
return cls._restore([current.punc + text[0]] + text[1:], puncs[1:], num)
if current.position == PuncPosition.END:
return [text[0] + current.punc] + cls._restore(text[1:], puncs[1:], num + 1)
if current.position == PuncPosition.ALONE:
return [current.mark] + cls._restore(text, puncs[1:], num + 1)
# POSITION == MIDDLE
if len(text) == 1: # pragma: nocover
# a corner case where the final part of an intermediate
# mark (I) has not been phonemized
return cls._restore([text[0] + current.punc], puncs[1:], num)
return cls._restore([text[0] + current.punc + text[1]] + text[2:], puncs[1:], num)
# if __name__ == "__main__":
# punc = Punctuation()
# text = "This is. This is, example!"
# print(punc.strip(text))
# split_text, puncs = punc.strip_to_restore(text)
# print(split_text, " ---- ", puncs)
# restored_text = punc.restore(split_text, puncs)
# print(restored_text) |