如何强制sklearn CountVectorizer不删除特殊字符(如#、@、$或%)

from sklearn.feature_extraction.text import CountVectorizer

# 定义一个正则表达式模式，匹配所有字符
pattern = r"(?u)\b\w+\b|\S"

# 创建CountVectorizer对象，并设置token_pattern参数
vectorizer = CountVectorizer(token_pattern=pattern)

# 文本数据
corpus = [
    "This is a #sample text.",
    "Another @example text.",
    "And $yet another %text."
]

# 将文本数据转换为向量表示
X = vectorizer.fit_transform(corpus)

# 输出特征向量
print(vectorizer.get_feature_names())
print(X.toarray())

['#sample', '@example', '$yet', '%text.', 'And', 'Another', 'This', 'a', 'another', 'is', 'text.']
[[1 0 0 0 0 0 1 1 0 1 1]
 [0 1 0 0 0 1 0 0 1 0 1]
 [0 0 1 1 1 0 0 0 1 0 1]]