Source code for nltk.tokenize.api
# Natural Language Toolkit: Tokenizer Interface
#
# Copyright (C) 2001-2024 NLTK Project
# Author: Edward Loper <edloper@gmail.com>
# Steven Bird <stevenbird1@gmail.com>
# 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
[docs]
class TokenizerI(ABC):
"""
A processing interface for tokenizing a string.
Subclasses must define ``tokenize()`` or ``tokenize_sents()`` (or both).
"""
[docs]
@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]
[docs]
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()
[docs]
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]
[docs]
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))
[docs]
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
[docs]
def tokenize(self, s):
return s.split(self._string)
[docs]
def span_tokenize(self, s):
yield from string_span_tokenize(s, self._string)