MCP server for Confusables

README.md

@@ -1,13 +1,11 @@
 ---
-title: Confusables Mcp
+title: Confusables Tools MCP
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
 sdk: gradio
-sdk_version: 5.0.1
+sdk_version: 5.35.0
 app_file: app.py
 pinned: false
 license: apache-2.0
 ---
-
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,64 +1,99 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+from confusables import is_confusable, confusable_characters, confusable_regex, normalize
 
+def gr_is_confusable(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", "Ʀỏ𝕍3ℛ")  # True
+    """
+    return is_confusable(str1, str2)
+
+def gr_confusable_characters(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")  # ['ċ', 'ᴄ', '𝔠', ...]
+    """
+    return confusable_characters(char)
+
+def gr_confusable_regex(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)
+
+def gr_normalize(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("Ʀỏ𝕍3ℛ", True)  # ['rov3r', 'rover']
+    """
+    return normalize(string, prioritize_alpha)
+
+with gr.Blocks() as demo:
+    gr.Markdown("""# MCP Server - Confusables API\nMain features of the confusables library exposed as tools.""")
+    with gr.Tab("is_confusable"):
+        gr.Interface(
+            fn=gr_is_confusable,
+            inputs=[gr.Textbox(label="String 1"), gr.Textbox(label="String 2")],
+            outputs=gr.Textbox(label="Confusable? (True/False)"),
+            allow_flagging="never"
+        ).render()
+    with gr.Tab("confusable_characters"):
+        gr.Interface(
+            fn=gr_confusable_characters,
+            inputs=gr.Textbox(label="Character"),
+            outputs=gr.Textbox(label="Confusable characters"),
+            allow_flagging="never"
+        ).render()
+    with gr.Tab("confusable_regex"):
+        gr.Interface(
+            fn=gr_confusable_regex,
+            inputs=[gr.Textbox(label="String"), gr.Checkbox(label="Include character padding")],
+            outputs=gr.Textbox(label="Regex"),
+            allow_flagging="never"
+        ).render()
+    with gr.Tab("normalize"):
+        gr.Interface(
+            fn=gr_normalize,
+            inputs=[gr.Textbox(label="String"), gr.Checkbox(label="Prioritize alpha")],
+            outputs=gr.Textbox(label="Normalized forms"),
+            allow_flagging="never"
+        ).render()
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(mcp_server=True)

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.25.2
+gradio[mcp]
+confusables