Update app.py

app.py

@@ -7,6 +7,11 @@ from huggingface_hub import HfApi
 from huggingface_hub.utils import HfHubHTTPError
 import time
 
+def sanitize_filename(title):
+    # Remove invalid characters and replace spaces with underscores
+    sanitized = re.sub(r'[\\/*?:"<>|]', "", title)
+    return sanitized.replace(" ", "_")
+
 def extract_full_paper_with_labels(pdf_path, progress=None):
     print(f"📄 Starting PDF Processing: {os.path.basename(pdf_path)}")
     doc = fitz.open(pdf_path)
@@ -98,7 +103,7 @@ def extract_full_paper_with_labels(pdf_path, progress=None):
                 elif re.search(r"=|∑|√|±|×|π|μ|σ", text):
                     content += f"<EQUATION>{text}</EQUATION>\n"
 
-                # ✅ Improved Code Block Detection
+                # Code Blocks (enhanced detection)
                 elif re.search(code_pattern, text) and len(text.split()) <= 50:
                     content += f"<CODE>{text}</CODE>\n"
 
@@ -119,44 +124,12 @@ def extract_full_paper_with_labels(pdf_path, progress=None):
     print(f"✅ Finished Processing PDF: {os.path.basename(pdf_path)}")
     return {
         "filename": os.path.basename(pdf_path),
+        "title": title if title else "Untitled_Paper",
         "content": content
     }
 
-
-def upload_with_progress(file_path, repo_id, token, progress):
-    """
-    Upload file to Hugging Face Dataset using upload_file() API method.
-    """
-    print(f"📤 Starting upload of Parquet: {file_path}")
-    file_size = os.path.getsize(file_path)
-
-    api = HfApi()
-
-    try:
-        # Use upload_file() method from huggingface_hub
-        api.upload_file(
-            path_or_fileobj=file_path,
-            path_in_repo=os.path.basename(file_path),
-            repo_id=repo_id,
-            repo_type="dataset",
-            token=token
-        )
-
-        if progress is not None:
-            progress(1, desc="✅ Upload Complete")
-
-        print(f"✅ Successfully uploaded to {repo_id}")
-        return f"✅ Successfully uploaded to {repo_id}"
-
-    except HfHubHTTPError as e:
-        print(f"❌ Upload failed: {e}")
-        return f"❌ Upload failed: {str(e)}"
-    except Exception as e:
-        print(f"❌ Unexpected error: {e}")
-        return f"❌ Unexpected error: {str(e)}"
-
 def pdf_to_parquet_and_upload(pdf_files, hf_token, dataset_repo_id, action_choice, progress=gr.Progress()):
-    all_data = []
+    upload_message = ""
 
     total_files = len(pdf_files)
     print("🚀 Starting PDF to Parquet Conversion Process")
@@ -167,29 +140,28 @@ def pdf_to_parquet_and_upload(pdf_files, hf_token, dataset_repo_id, action_choic
 
         # ✅ Step 1: Process PDF with Full Labels
         extracted_data = extract_full_paper_with_labels(pdf_file.name, progress=progress)
-        all_data.append(extracted_data)
 
-    print("🟡 Converting Processed Data to Parquet")
-    # ✅ Step 2: Convert to Parquet
-    df = pd.DataFrame(all_data)
-    parquet_file = 'fully_labeled_papers.parquet'
+        # ✅ Step 2: Use Title for Parquet Filename
+        sanitized_title = sanitize_filename(extracted_data["title"])
+        parquet_file = f"{sanitized_title}.parquet"
 
-    try:
-        df.to_parquet(parquet_file, engine='pyarrow', index=False)
-        print("✅ Parquet Conversion Completed")
-    except Exception as e:
-        print(f"❌ Parquet Conversion Failed: {str(e)}")
-        return None, f"❌ Parquet Conversion Failed: {str(e)}"
+        # Convert to DataFrame
+        df = pd.DataFrame([extracted_data])
 
-    upload_message = "Skipped Upload"
-
-    # ✅ Step 3: Upload Parquet (if selected)
-    if action_choice in ["Upload to Hugging Face", "Both"]:
         try:
-            upload_message = upload_with_progress(parquet_file, dataset_repo_id, hf_token, progress)
+            df.to_parquet(parquet_file, engine='pyarrow', index=False)
+            print(f"✅ Parquet saved as: {parquet_file}")
         except Exception as e:
-            print(f"❌ Upload Failed: {str(e)}")
-            upload_message = f"❌ Upload failed: {str(e)}"
+            print(f"❌ Parquet Conversion Failed: {str(e)}")
+            return None, f"❌ Parquet Conversion Failed: {str(e)}"
+
+        # ✅ Step 3: Upload Parquet (if selected)
+        if action_choice in ["Upload to Hugging Face", "Both"]:
+            try:
+                upload_message = upload_with_progress(parquet_file, dataset_repo_id, hf_token, progress)
+            except Exception as e:
+                print(f"❌ Upload Failed: {str(e)}")
+                upload_message = f"❌ Upload failed: {str(e)}"
 
     print("🏁 Process Completed")
     return parquet_file, upload_message
@@ -207,9 +179,10 @@ iface = gr.Interface(
         gr.File(label="Download Parquet File"), 
         gr.Textbox(label="Status")
     ],
-    title="PDF to Parquet Converter with Full Labeling",
-    description="Upload your PDFs, convert them to Parquet with full section labeling, and upload to your Hugging Face Dataset."
+    title="PDF to Parquet Converter with Title-Based Naming",
+    description="Upload your PDFs, convert them to Parquet files named after the paper title, and upload to your Hugging Face Dataset."
 )
 
 iface.launch()
 
+