validate username

submit.py

@@ -8,7 +8,7 @@ from datetime import datetime
 import uuid
 
 from constants import API, SUBMISSIONS_REPO
-from validation import validate_csv_file
+from validation import validate_csv_file, validate_username
 
 
 def make_submission(
@@ -19,6 +19,8 @@ def make_submission(
     if user_state is None:
         raise gr.Error("You must submit your username to submit a file.")
 
+    validate_username(user_state)
+
     if submitted_file is None:
         raise gr.Error("Please upload a CSV file before submitting.")
 

validation.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import io
 import gradio as gr
+import requests
 from constants import (
     REQUIRED_COLUMNS,
     ASSAY_LIST,
@@ -10,6 +11,61 @@ from constants import (
 )
 
 
+def validate_username(username: str) -> bool:
+    """
+    Validate that the username corresponds to a real Hugging Face profile.
+    Just check https://huggingface.co/username exists.
+
+    Parameters
+    ----------
+    username: str
+        The username to validate
+
+    Returns
+    -------
+    bool
+        True if the username is valid and profile exists, False otherwise
+
+    Raises
+    ------
+    gr.Error: If username is invalid or profile doesn't exist
+    """
+    username = username.strip()
+
+    # Check if the Hugging Face profile exists
+    profile_url = f"https://huggingface.co/{username}"
+
+    try:
+        response = requests.get(profile_url, timeout=10)
+
+        if response.status_code == 200:
+            # Additional check: make sure it's actually a user profile page
+            # and not some other page that happens to exist
+            if "profile" in response.text.lower() or "models" in response.text.lower():
+                return True
+            else:
+                raise gr.Error(
+                    f"❌ '{username}' does not appear to be a valid Hugging Face user profile"
+                )
+        elif response.status_code == 404:
+            raise gr.Error(
+                f"❌ Hugging Face user '{username}' does not exist. Please check the username or create an account at https://huggingface.co"
+            )
+        else:
+            raise gr.Error(
+                f"❌ Unable to verify username '{username}'. Please try again later."
+            )
+
+    except requests.exceptions.Timeout:
+        raise gr.Error("❌ Timeout while checking username. Please try again.")
+    except requests.exceptions.ConnectionError:
+        raise gr.Error(
+            "❌ Unable to connect to Hugging Face. Please check your internet connection."
+        )
+    except requests.exceptions.RequestException as e:
+        raise gr.Error(f"❌ Error validating username: {str(e)}")
+
+
 def validate_csv_can_be_read(file_content: str) -> pd.DataFrame:
     """
     Validate that the CSV file can be read and parsed.