Add OAuth authentication to protect the interface and track user contributions

README.md

@@ -1,10 +1,11 @@
 ---
-title: Handwriting OCR Dataset Collection
+title: Handwriting OCR Data Collection
 emoji: ✍️
 colorFrom: blue
 colorTo: indigo
 sdk: gradio
-sdk_version: 5.15.0
+sdk_version: 3.40.0
+python_version: 3.10.6
 app_file: app.py
 pinned: false
 short_description: Collect handwritten text samples for OCR training
@@ -13,6 +14,14 @@ tags:
 - handwriting
 - dataset
 - computer-vision
+
+hf_oauth: true
+hf_oauth_expiration_minutes: 480
+hf_oauth_scopes:
+  - read-repos
+  - write-repos
+  - manage-repos
+  - inference-api
 ---
 
 # Handwriting OCR Dataset Collection

app.py

@@ -2,6 +2,8 @@ import gradio as gr
 import random
 import os
 from datetime import datetime
+from huggingface_hub import HfApi
+from typing import Optional
 
 # The list of sentences from our previous conversation.
 sentences = [
@@ -61,6 +63,7 @@ class OCRDataCollector:
     def __init__(self):
         self.collected_pairs = []
         self.current_text_block = self.get_random_text_block()
+        self.hf_api = HfApi()
 
     def get_random_text_block(self):
         block_length = random.randint(1, 5)
@@ -68,13 +71,18 @@ class OCRDataCollector:
         block = " ".join(sentences[start_index:start_index + block_length])
         return block
 
-    def submit_image(self, image, text_block):
-        if image is not None:
+    def submit_image(self, image, text_block, username: Optional[str] = None):
+        if image is not None and username:
             timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-            self.collected_pairs.append({"text": text_block, "image": image, "timestamp": timestamp})
+            self.collected_pairs.append({
+                "text": text_block, 
+                "image": image, 
+                "timestamp": timestamp,
+                "username": username
+            })
         return self.get_random_text_block()
 
-    def skip_text(self, text_block):
+    def skip_text(self, text_block, username: Optional[str] = None):
         return self.get_random_text_block()
 
 def create_gradio_interface():
@@ -82,30 +90,54 @@ def create_gradio_interface():
     
     with gr.Blocks() as demo:
         gr.Markdown("## Crowdsourcing Handwriting OCR Dataset")
-        gr.Markdown("You will be shown between 1 and 5 consecutive sentences. Please handwrite them on paper and upload an image of your handwriting. If you wish to skip the current text, click 'Skip'.")
-        
-        text_box = gr.Textbox(value=collector.current_text_block, label="Text to Handwrite", interactive=False)
-        image_input = gr.Image(type="pil", label="Upload Handwritten Image", sources=["upload"])
         
         with gr.Row():
-            submit_btn = gr.Button("Submit")
-            skip_btn = gr.Button("Skip")
+            user_info = gr.Markdown("")
+
+        def update_user_info(request: gr.Request):
+            if request.username:
+                return f"Logged in as: {request.username}", gr.update(visible=True)
+            return "Please log in with your Hugging Face account to contribute to the dataset.", gr.update(visible=False)
+
+        with gr.Column(visible=False) as main_interface:
+            gr.Markdown("You will be shown between 1 and 5 consecutive sentences. Please handwrite them on paper and upload an image of your handwriting. If you wish to skip the current text, click 'Skip'.")
+            
+            text_box = gr.Textbox(value=collector.current_text_block, label="Text to Handwrite", interactive=False)
+            image_input = gr.Image(type="pil", label="Upload Handwritten Image", sources=["upload"])
+            
+            with gr.Row():
+                submit_btn = gr.Button("Submit")
+                skip_btn = gr.Button("Skip")
+        
+        def check_login(request: gr.Request):
+            if request.username is None:
+                raise gr.Error("Please log in to use this application")
+            return request.username
+            
+        def protected_submit(image, text_block, request: gr.Request):
+            username = check_login(request)
+            return collector.submit_image(image, text_block, username)
+            
+        def protected_skip(text_block, request: gr.Request):
+            username = check_login(request)
+            return collector.skip_text(text_block, username)
+        
+        demo.load(update_user_info, outputs=[user_info, main_interface])
         
         submit_btn.click(
-            fn=collector.submit_image,
+            fn=protected_submit,
             inputs=[image_input, text_box],
             outputs=text_box
         )
         
         skip_btn.click(
-            fn=collector.skip_text,
-            inputs=text_box,
+            fn=protected_skip,
+            inputs=[text_box],
             outputs=text_box
         )
-        
     
     return demo
 
 if __name__ == "__main__":
     demo = create_gradio_interface()
-    demo.launch()
+    demo.launch(auth_message="Please login with your Hugging Face account to contribute to the dataset.")

requirements.txt

@@ -1,4 +1,5 @@
-gradio>=3.50.2
+gradio>=3.40.0
+huggingface-hub>=0.19.0
 Pillow>=10.0.0
 pytest>=7.0.0
 pytest-playwright>=0.4.0