Skip to content

Modules

stringpod

Main module.

contains_chinese(text)

Check if the text contains Chinese characters.

Example:

contains_chinese('你好，世界！') True contains_chinese('Hello, world!') False

Source code in stringpod/stringpod.py 
10
11
12
13
14
15
16
17
18
19
def contains_chinese(text: str) -> bool:
    """Check if the text contains Chinese characters.

    Example:
    >>> contains_chinese('你好，世界！')
    True
    >>> contains_chinese('Hello, world!')
    False
    """
    return bool(hanzidentifier.has_chinese(text))

contains_email(text)

Check if the text contains an email.

Example:

contains_email('test@example.com') True contains_email('test@example.com.tw') True contains_email('test@example') False

Source code in stringpod/stringpod.py 
110
111
112
113
114
115
116
117
118
119
120
121
def contains_email(text: str) -> bool:
    """Check if the text contains an email.

    Example:
    >>> contains_email('test@example.com')
    True
    >>> contains_email('test@example.com.tw')
    True
    >>> contains_email('test@example')
    False
    """
    return bool(re.search(r"^\S+@\S+\.\S+$", text))

contains_english(text)

Check if the text contains English characters.

Example:

contains_english('Hello, world!') True contains_english('你好，世界！') False contains_english('HelloWorld') True

Source code in stringpod/stringpod.py 
22
23
24
25
26
27
28
29
30
31
32
33
def contains_english(text: str) -> bool:
    """Check if the text contains English characters.

    Example:
    >>> contains_english('Hello, world!')
    True
    >>> contains_english('你好，世界！')
    False
    >>> contains_english('HelloWorld')
    True
    """
    return bool(re.search(r"[a-zA-Z]", text))

contains_number(text)

Check if the text contains numbers.

Example:

contains_number('Hello, world!') False contains_number('你好，世界！') False contains_number('你好123') True

Source code in stringpod/stringpod.py 
36
37
38
39
40
41
42
43
44
45
46
47
def contains_number(text: str) -> bool:
    """Check if the text contains numbers.

    Example:
    >>> contains_number('Hello, world!')
    False
    >>> contains_number('你好，世界！')
    False
    >>> contains_number('你好123')
    True
    """
    return bool(re.search(r"\d", text))

contains_punctuation(text)

Check if the text contains punctuation.

Example:

contains_punctuation('Hello, world!') True contains_punctuation('你好，世界！') True contains_punctuation('你好世界') False

Source code in stringpod/stringpod.py 
50
51
52
53
54
55
56
57
58
59
60
61
def contains_punctuation(text: str) -> bool:
    """Check if the text contains punctuation.

    Example:
    >>> contains_punctuation('Hello, world!')
    True
    >>> contains_punctuation('你好，世界！')
    True
    >>> contains_punctuation('你好世界')
    False
    """
    return bool(re.search(r"[^\w\s]", text))

contains_special_character(text)

Check if the text contains special characters.

Example:

contains_special_character('Hello,world!') True contains_special_character('Helloworld!') True contains_special_character('Hello World') False contains_special_character('HelloWorld') False

Source code in stringpod/stringpod.py 
64
65
66
67
68
69
70
71
72
73
74
75
76
77
def contains_special_character(text: str) -> bool:
    """Check if the text contains special characters.

    Example:
    >>> contains_special_character('Hello,world!')
    True
    >>> contains_special_character('Helloworld!')
    True
    >>> contains_special_character('Hello World')
    False
    >>> contains_special_character('HelloWorld')
    False
    """
    return bool(re.search(r"[^a-zA-Z0-9\s]", text))

contains_substring(text, substring, options=None)

Check if the text contains a substring.

Text will undergo the following transformations before checking: - Normalize to lowercase - Remove whitespace - Remove punctuation - Remove special characters - Romanize Chinese characters

The following will be checked: - Traditional and Simplified Chinese (If the substring is in Traditional Chinese, it will also be checked in Simplified Chinese)

Example:

contains_substring('你好，世界！', '你好') True options = NormalizerOptions(ignore_chinese_variant=True) contains_substring('計算機', '计算', options) True options_all = NormalizerOptions.enable_all() contains_substring('計算機', 'Ji', options_all) False

Parameters:

Name Type Description Default
text str

The text to check

 required
substring str

The substring to check for

 required
options NormalizerOptions | None

Normalization options to apply

 None

Returns:

Type Description
bool

True if the text contains the substring, False otherwise
Source code in stringpod/stringpod.py 
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
def contains_substring(text: str, substring: str, options: NormalizerOptions | None = None) -> bool:
    """Check if the text contains a substring.

    Text will undergo the following transformations before checking:
    - Normalize to lowercase
    - Remove whitespace
    - Remove punctuation
    - Remove special characters
    - Romanize Chinese characters

    The following will be checked:
    - Traditional and Simplified Chinese
        (If the substring is in Traditional Chinese, it will also be checked in Simplified Chinese)

    Example:

    >>> contains_substring('你好，世界！', '你好')
    True
    >>> options = NormalizerOptions(ignore_chinese_variant=True)
    >>> contains_substring('計算機', '计算', options)
    True
    >>> options_all = NormalizerOptions.enable_all()
    >>> contains_substring('計算機', 'Ji', options_all)
    False

    Args:
        text: The text to check
        substring: The substring to check for
        options: Normalization options to apply

    Returns:
        True if the text contains the substring, False otherwise
    """
    normalizer = Normalizer(options=options)
    text_normalized = normalizer.normalize(text)
    substring_normalized = normalizer.normalize(substring)

    # Check if the substring is in Simplified Chinese
    return bool(re.search(substring_normalized, text_normalized))

contains_url(text)

Check if the text contains a URL.

Example:

contains_url('https://www.google.com') True contains_url('http://www.google.com') True contains_url('www.google.com') False contains_url('google.com') False

Source code in stringpod/stringpod.py 
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
def contains_url(text: str) -> bool:
    """Check if the text contains a URL.

    Example:
    >>> contains_url('https://www.google.com')
    True
    >>> contains_url('http://www.google.com')
    True
    >>> contains_url('www.google.com')
    False
    >>> contains_url('google.com')
    False
    """
    return bool(re.search(r"https?://", text))

contains_whitespace(text)

Check if the text contains whitespace.

Example:

contains_whitespace('Hello, world!') True contains_whitespace('Hello world!') True contains_whitespace('HelloWorld!') False

Source code in stringpod/stringpod.py 
80
81
82
83
84
85
86
87
88
89
90
91
def contains_whitespace(text: str) -> bool:
    """Check if the text contains whitespace.

    Example:
    >>> contains_whitespace('Hello, world!')
    True
    >>> contains_whitespace('Hello world!')
    True
    >>> contains_whitespace('HelloWorld!')
    False
    """
    return bool(re.search(r"\s", text))