Hugging Face's logo

Spaces:
kokluch
/
confusables-mcp
Running

App Files Community
confusables-mcp
File size: 2,412 Bytes 
944fd03
542f4c2
9e2c10a
944fd03
 
 
 
 
 
 
 
542f4c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
944fd03
 
542f4c2
 
 
 
 
 
 
 
 
 
 
 
 
 
944fd03
 
542f4c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
944fd03
 
542f4c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9e2c10a
944fd03
 
 
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
 
from fastmcp import FastMCP
from confusables import is_confusable, confusable_characters, confusable_regex, normalize

mcp = FastMCP(
    "Confusables MCP Server",
    host="0.0.0.0",
    port=7860
)

@mcp.tool
def is_confusable_tool(str1: str, str2: str) -> bool:
    """
    Check if two strings are visually confusable (i.e., they look similar to a human, but may use different Unicode characters).

    Args:
        str1: The first string to compare.
        str2: The second string to compare.

    Returns:
        True if the two strings are visually confusable, False otherwise.

    Example:
        gr_is_confusable("rover", "Ʀỏ𝕍3β„›")  # True
    """
    return is_confusable(str1, str2)

@mcp.tool
def confusable_characters_tool(char: str) -> list[str]:
    """
    List all Unicode characters or character sequences that are visually confusable with the given character.

    Args:
        char: The character to analyze (must be a single character).

    Returns:
        A list of confusable characters or sequences.

    Example:
        gr_confusable_characters("c")  # ['Δ‹', 'α΄„', '𝔠', ...]
    """
    return confusable_characters(char)

@mcp.tool
def confusable_regex_tool(string: str, include_character_padding: bool) -> str:
    """
    Generate a regular expression string that matches all visually confusable variants of the input string.

    Args:
        string: The reference string.
        include_character_padding: If True, the regex will allow for character padding (extra confusable characters between the main ones).

    Returns:
        A regex pattern string.

    Example:
        gr_confusable_regex("bore", True)
    """
    return confusable_regex(string, include_character_padding)

@mcp.tool
def normalize_tool(string: str, prioritize_alpha: bool) -> list[str]:
    """
    Return all possible normalized forms of a string, converting confusable Unicode characters to their closest ASCII or Latin-alphabet equivalents.

    Args:
        string: The string to normalize.
        prioritize_alpha: If True, prioritizes conversion to Latin alphabet characters.

    Returns:
        A list of possible normalized forms.

    Example:
        gr_normalize("Ʀỏ𝕍3β„›", True)  # ['rov3r', 'rover']
    """
    return normalize(string, prioritize_alpha)

if __name__ == "__main__":
    print("Running server with SSE transport")
    mcp.run(transport='sse')