private works

app.py

@@ -4,6 +4,7 @@ import os
 from datetime import datetime
 from huggingface_hub import HfApi
 from typing import Optional
+from PIL import Image  # Needed for working with PIL images
 
 # The list of sentences from our previous conversation.
 sentences = [
@@ -85,6 +86,18 @@ class OCRDataCollector:
     def skip_text(self, text_block, username: Optional[str] = None):
         return self.get_random_text_block()
 
+
+def strip_metadata(image: Image.Image) -> Image.Image:
+    """
+    Helper function to strip all metadata from the provided PIL Image.
+    This creates a new image with the same pixel data but no additional info.
+    """
+    data = list(image.getdata())
+    stripped_image = Image.new(image.mode, image.size)
+    stripped_image.putdata(data)
+    return stripped_image
+
+
 def create_gradio_interface():
     collector = OCRDataCollector()
     
@@ -92,44 +105,109 @@ def create_gradio_interface():
         gr.Markdown("## Crowdsourcing Handwriting OCR Dataset")
         gr.LoginButton()
         user_info = gr.Markdown()
+        # Hidden state to hold the user's OAuth profile as JSON.
+        profile_state = gr.JSON(visible=False)
         
-        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'.")
+        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, visible=False)
         image_input = gr.Image(type="pil", label="Upload Handwritten Image", sources=["upload"], visible=False)
+        # Toggle (using a radio button) for dataset choice.
+        dataset_radio = gr.Radio(choices=["Private", "Public"], label="Select Dataset", value="Private", visible=False)
         
         with gr.Row(visible=False) as button_row:
             submit_btn = gr.Button("Submit")
             skip_btn = gr.Button("Skip")
-
-        def update_user_info(profile: gr.OAuthProfile | None) -> str:
-            if profile is None:
-                return "Please log in with your Hugging Face account to contribute to the dataset."
-            return f"Logged in as: {profile.name}"
-
-        def handle_submit(profile: gr.OAuthProfile | None) -> str:
+        
+        def update_user_info(profile: gr.OAuthProfile | None):
             if profile is None:
+                return "Please log in with your Hugging Face account to contribute to the dataset.", {}
+            # Use the username provided by the profile (from the "profile" scope)
+            return f"Logged in as: {profile.username}", {"username": profile.username}
+    
+        def handle_submit(profile, dataset_choice, image, text):
+            """
+            Depending on the dataset toggle selection, this function either:
+              - For 'Private': strips metadata from the image, checks/creates a private HF dataset,
+                pushes the image to it, and logs the submission.
+              - For 'Public': uses the existing `submit_image` logic.
+            """
+            if not profile or "username" not in profile:
                 raise gr.Error("Please log in to use this application")
-            return collector.submit_image(image_input.value, text_box.value, profile.name)
+            username = profile["username"]
+            # Use the username from the OAuth profile directly
+            repo_id = f"{username}/handwriting-ocr-private"
             
-        def handle_skip(profile: gr.OAuthProfile | None) -> str:
-            if profile is None:
+            if dataset_choice == "Private":
+                # Remove all metadata for privacy
+                stripped_image = strip_metadata(image)
+                
+                # Check if the dataset exists; if not, create it as private.
+                try:
+                    collector.hf_api.dataset_info(repo_id)
+                except Exception as e:
+                    collector.hf_api.create_repo(repo_id, repo_type="dataset", private=True)
+                
+                # Save the stripped image to a temporary file
+                timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+                filename = f"{timestamp}.png"
+                temp_dir = "temp"
+                os.makedirs(temp_dir, exist_ok=True)
+                temp_path = os.path.join(temp_dir, filename)
+                stripped_image.save(temp_path)
+                
+                # Upload the file to the Hugging Face dataset repository
+                collector.hf_api.upload_file(
+                    path_or_fileobj=temp_path,
+                    path_in_repo=filename,
+                    repo_id=repo_id,
+                    repo_type="dataset",
+                )
+                
+                # Remove the temporary file
+                os.remove(temp_path)
+                
+                # Log the submission locally with an indicator for the private dataset.
+                collector.collected_pairs.append({
+                    "text": text,
+                    "image": image,  # The original image is recorded locally.
+                    "timestamp": timestamp,
+                    "username": username,
+                    "dataset": "private"
+                })
+                new_text = collector.get_random_text_block()
+                # Return a tuple to clear the image input (set to None) and update the text.
+                return None, new_text
+            else:
+                # Fallback to public submission using the existing logic.
+                new_text = collector.submit_image(image, text, username)
+                return None, new_text
+
+        def handle_skip(profile, text):
+            if not profile or "username" not in profile:
                 raise gr.Error("Please log in to use this application")
-            return collector.skip_text(text_box.value, profile.name)
+            return collector.skip_text(text, profile["username"])
 
         def update_visibility(profile: gr.OAuthProfile | None):
             is_visible = profile is not None
+            # Update the visibility of text_box, image_input, button_row, and dataset_radio.
             return [
+                gr.update(visible=is_visible),
                 gr.update(visible=is_visible),
                 gr.update(visible=is_visible),
                 gr.update(visible=is_visible)
             ]
 
-        demo.load(update_user_info, inputs=None, outputs=user_info)
-        demo.load(update_visibility, inputs=None, outputs=[text_box, image_input, button_row])
+        # On load, update both the display message and the hidden profile state.
+        demo.load(update_user_info, inputs=None, outputs=[user_info, profile_state])
+        demo.load(update_visibility, inputs=None, outputs=[text_box, image_input, button_row, dataset_radio])
         
-        submit_btn.click(handle_submit, inputs=None, outputs=[image_input, text_box])
-        skip_btn.click(handle_skip, inputs=None, outputs=text_box)
+        # Bind the submit and skip actions with updated inputs.
+        submit_btn.click(handle_submit, inputs=[profile_state, dataset_radio, image_input, text_box], outputs=[image_input, text_box])
+        skip_btn.click(handle_skip, inputs=[profile_state, text_box], outputs=text_box)
 
     return demo