File size: 2,357 Bytes
d916065
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Natural Language Toolkit: Tokenizer Interface
#
# Copyright (C) 2001-2023 NLTK Project
# Author: Edward Loper <[email protected]>
#         Steven Bird <[email protected]>
# URL: <https://www.nltk.org/>
# For license information, see LICENSE.TXT

"""

Tokenizer Interface

"""

from abc import ABC, abstractmethod
from typing import Iterator, List, Tuple

from nltk.internals import overridden
from nltk.tokenize.util import string_span_tokenize


class TokenizerI(ABC):
    """

    A processing interface for tokenizing a string.

    Subclasses must define ``tokenize()`` or ``tokenize_sents()`` (or both).

    """

    @abstractmethod
    def tokenize(self, s: str) -> List[str]:
        """

        Return a tokenized copy of *s*.



        :rtype: List[str]

        """
        if overridden(self.tokenize_sents):
            return self.tokenize_sents([s])[0]

    def span_tokenize(self, s: str) -> Iterator[Tuple[int, int]]:
        """

        Identify the tokens using integer offsets ``(start_i, end_i)``,

        where ``s[start_i:end_i]`` is the corresponding token.



        :rtype: Iterator[Tuple[int, int]]

        """
        raise NotImplementedError()

    def tokenize_sents(self, strings: List[str]) -> List[List[str]]:
        """

        Apply ``self.tokenize()`` to each element of ``strings``.  I.e.:



            return [self.tokenize(s) for s in strings]



        :rtype: List[List[str]]

        """
        return [self.tokenize(s) for s in strings]

    def span_tokenize_sents(

        self, strings: List[str]

    ) -> Iterator[List[Tuple[int, int]]]:
        """

        Apply ``self.span_tokenize()`` to each element of ``strings``.  I.e.:



            return [self.span_tokenize(s) for s in strings]



        :yield: List[Tuple[int, int]]

        """
        for s in strings:
            yield list(self.span_tokenize(s))


class StringTokenizer(TokenizerI):
    """A tokenizer that divides a string into substrings by splitting

    on the specified string (defined in subclasses).

    """

    @property
    @abstractmethod
    def _string(self):
        raise NotImplementedError

    def tokenize(self, s):
        return s.split(self._string)

    def span_tokenize(self, s):
        yield from string_span_tokenize(s, self._string)