让我们将nlp.tokenizer更改为一个自定义Tokenizer，并使用token_match正则表达式：

import re
import spacy
from spacy.tokenizer import Tokenizer

nlp = spacy.load('en_core_web_sm')
text = "This is it's"
print("Before:", [tok for tok in nlp(text)])

nlp.tokenizer = Tokenizer(nlp.vocab, token_match=re.compile(r'\S+').match)
print("After :", [tok for tok in nlp(text)])

Before: [This, is, it, 's]
After : [This, is, it's]

您可以通过添加自定义后缀、前缀和中缀规则来进一步调整Tokenizer。
另一种更细粒度的方法是找出为什么it's令牌像nlp.tokenizer.explain()一样被拆分：

import spacy
from spacy.tokenizer import Tokenizer
nlp = spacy.load('en_core_web_sm')
text = "This is it's. I'm fine"
nlp.tokenizer.explain(text)

你会发现拆分是由SPECIAL规则引起的：

[('TOKEN', 'This'),
 ('TOKEN', 'is'),
 ('SPECIAL-1', 'it'),
 ('SPECIAL-2', "'s"),
 ('SUFFIX', '.'),
 ('SPECIAL-1', 'I'),
 ('SPECIAL-2', "'m"),
 ('TOKEN', 'fine')]

可以更新以从例外中删除“it's”，例如：

exceptions = nlp.Defaults.tokenizer_exceptions
filtered_exceptions = {k:v for k,v in exceptions.items() if k!="it's"}
nlp.tokenizer = Tokenizer(nlp.vocab, rules = filtered_exceptions)
[tok for tok in nlp(text)]

[This, is, it's., I, 'm, fine]

或完全删除撇号上的分裂：

filtered_exceptions = {k:v for k,v in exceptions.items() if "'" not in k}
nlp.tokenizer = Tokenizer(nlp.vocab, rules = filtered_exceptions)
[tok for tok in nlp(text)]

[This, is, it's., I'm, fine]

请注意标记上附加的点，这是由于未指定后缀规则。

你可以在spaCy文档中找到这个问题的解决方案：简单https://spacy.io/usage/linguistic-features#custom-tokenizer-example地说，你创建了一个函数，它接受一个字符串text并返回一个Doc对象，然后将这个可调用函数赋给nlp.tokenizer：

import spacy
from spacy.tokens import Doc

class WhitespaceTokenizer(object):
    def __init__(self, vocab):
        self.vocab = vocab

    def __call__(self, text):
        words = text.split(' ')
        # All tokens 'own' a subsequent space character in this tokenizer
        spaces = [True] * len(words)
        return Doc(self.vocab, words=words, spaces=spaces)

nlp = spacy.load("en_core_web_sm")
nlp.tokenizer = WhitespaceTokenizer(nlp.vocab)
doc = nlp("What's happened to me? he thought. It wasn't a dream.")
print([t.text for t in doc])

根据文件
https://spacy.io/usage/spacy-101#annotations-token www.example.com
-- splitting on whitespace是Tokenizer的基本行为。
因此，这个简单的解决方案应该有效：

import spacy    
from spacy.tokenizer import Tokenizer

nlp = spacy.blank("en")
tokenizer = Tokenizer(nlp.vocab)

有一个小小的警告。您没有指定如何处理多个空格。SpaCy将这些标记作为单独的标记，以便可以从标记中恢复确切的原始文本。"hello world"（有两个空格）将标记为"hello", " ", "world"。（对于一个空格，它当然只是"hello", "world"）。