revert

app.py

@@ -121,6 +121,15 @@ def process_pdfs(
             ),
         )
 
+    if oauth_token is None:
+        return (
+            None,
+            None,
+            gr.Markdown(
+                "⚠️ Not logged in to Hugging Face. Please log in to upload to a Hugging Face dataset."
+            ),
+        )
+
     try:
         temp_dir = tempfile.mkdtemp()
         images_dir = os.path.join(temp_dir, "images")
@@ -157,67 +166,61 @@ def process_pdfs(
             message += f"\nCreated zip file with {len(images)} images"
 
         if hf_repo:
-            if oauth_token is None:
-                message += "\n⚠️ Not logged in to Hugging Face. Please log in to upload to a Hugging Face dataset."
-            else:
-                try:
-                    hf_api = HfApi(token=oauth_token.token)
-                    hf_api.create_repo(
-                        hf_repo,
-                        repo_type="dataset",
-                        private=private_repo,
-                    )
-                    # Upload only the sampled images directory
-                    hf_api.upload_folder(
-                        folder_path=sampled_images_dir,
-                        repo_id=hf_repo,
-                        repo_type="dataset",
-                        path_in_repo="images",
-                    )
-
-                    # Determine size category
-                    size_category = get_size_category(len(images))
-
-                    # Create DatasetCardData instance
-                    card_data = DatasetCardData(
-                        tags=[
-                            "created-with-pdfs-to-page-images-converter",
-                            "pdf-to-image",
-                        ],
-                        size_categories=[size_category],
-                    )
-
-                    # Create and populate the dataset card
-                    card = DatasetCard.from_template(
-                        card_data,
-                        template_path=None,  # Use default template
-                        hf_repo=hf_repo,
-                        num_images=len(images),
-                        num_pdfs=len(pdf_files),
-                        sample_size=sample_percentage
-                        if sample_percentage > 0
-                        else "All pages",
-                        creation_date=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
-                    )
-
-                    # Add our custom content to the card
-                    card.text = DATASET_CARD_TEMPLATE.format(
-                        hf_repo=hf_repo,
-                        num_images=len(images),
-                        num_pdfs=len(pdf_files),
-                        sample_size=sample_percentage
-                        if sample_percentage > 0
-                        else "All pages",
-                        creation_date=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
-                        size_category=size_category,
-                    )
-
-                    repo_url = f"https://huggingface.co/datasets/{hf_repo}"
-                    message += f"\nUploaded dataset card to Hugging Face repo: [{hf_repo}]({repo_url})"
-
-                    card.push_to_hub(hf_repo, token=oauth_token.token)
-                except Exception as e:
-                    message += f"\nFailed to upload to Hugging Face: {str(e)}"
+            try:
+                hf_api = HfApi(token=oauth_token.token)
+                hf_api.create_repo(
+                    hf_repo,
+                    repo_type="dataset",
+                    private=private_repo,
+                )
+                # Upload only the sampled images directory
+                hf_api.upload_folder(
+                    folder_path=sampled_images_dir,
+                    repo_id=hf_repo,
+                    repo_type="dataset",
+                    path_in_repo="images",
+                )
+
+                # Determine size category
+                size_category = get_size_category(len(images))
+
+                # Create DatasetCardData instance
+                card_data = DatasetCardData(
+                    tags=["created-with-pdfs-to-page-images-converter", "pdf-to-image"],
+                    size_categories=[size_category],
+                )
+
+                # Create and populate the dataset card
+                card = DatasetCard.from_template(
+                    card_data,
+                    template_path=None,  # Use default template
+                    hf_repo=hf_repo,
+                    num_images=len(images),
+                    num_pdfs=len(pdf_files),
+                    sample_size=sample_percentage
+                    if sample_percentage > 0
+                    else "All pages",
+                    creation_date=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+                )
+
+                # Add our custom content to the card
+                card.text = DATASET_CARD_TEMPLATE.format(
+                    hf_repo=hf_repo,
+                    num_images=len(images),
+                    num_pdfs=len(pdf_files),
+                    sample_size=sample_percentage
+                    if sample_percentage > 0
+                    else "All pages",
+                    creation_date=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+                    size_category=size_category,
+                )
+
+                repo_url = f"https://huggingface.co/datasets/{hf_repo}"
+                message += f"\nUploaded dataset card to Hugging Face repo: [{hf_repo}]({repo_url})"
+
+                card.push_to_hub(hf_repo, token=oauth_token.token)
+            except Exception as e:
+                message += f"\nFailed to upload to Hugging Face: {str(e)}"
 
         return images, zip_path, message
     except Exception as e: