Show page progress for PDFs, rename button to Categorize Data

app.py

@@ -24,6 +24,17 @@ MAX_CATEGORIES = 10
 INITIAL_CATEGORIES = 3
 MAX_FILE_SIZE_MB = 100
 
+def count_pdf_pages(pdf_path):
+    """Count the number of pages in a PDF file."""
+    try:
+        import fitz  # PyMuPDF
+        doc = fitz.open(pdf_path)
+        page_count = len(doc)
+        doc.close()
+        return page_count
+    except Exception:
+        return 1  # Default to 1 if can't read
+
 # Free models (uses Space secrets - no user API key needed)
 FREE_MODEL_CHOICES = [
     "Qwen/Qwen3-VL-235B-A22B-Instruct:novita",
@@ -961,7 +972,7 @@ with col_input:
             model = st.selectbox("Model", options=PAID_MODEL_CHOICES, key="classify_model_paid")
             api_key = st.text_input("API Key", type="password", key="classify_api_key")
 
-        if st.button("Classify Data", type="primary", use_container_width=True):
+        if st.button("Categorize Data", type="primary", use_container_width=True):
             if input_data is None:
                 st.error("Please upload data first")
             elif not categories_entered:
@@ -982,7 +993,18 @@ with col_input:
                     st.error(f"{provider} API key not configured")
                 else:
                     model_source = get_model_source(model)
-                    total_items = len(input_data) if isinstance(input_data, list) else 1
+                    items_list = input_data if isinstance(input_data, list) else [input_data]
+
+                    # For PDFs, count total pages; for others, count items
+                    if input_type_selected == "pdf":
+                        # Build list of (pdf_path, page_count) and calculate total pages
+                        pdf_page_counts = [(pdf_path, count_pdf_pages(pdf_path)) for pdf_path in items_list]
+                        total_pages = sum(pc for _, pc in pdf_page_counts)
+                        progress_unit = "page"
+                        total_units = total_pages
+                    else:
+                        total_units = len(items_list)
+                        progress_unit = "item"
 
                     # Progress UI
                     progress_bar = st.progress(0)
@@ -990,23 +1012,33 @@ with col_input:
 
                     all_results = []
                     start_time = time.time()
+                    processed_units = 0
 
-                    for i, item in enumerate(input_data if isinstance(input_data, list) else [input_data]):
-                        # Update progress
-                        progress = (i / total_items)
-                        progress_bar.progress(progress)
+                    for i, item in enumerate(items_list):
+                        # For PDFs, get page count for this document
+                        if input_type_selected == "pdf":
+                            item_pages = pdf_page_counts[i][1]
+                        else:
+                            item_pages = 1
+
+                        # Update progress before processing
+                        progress = processed_units / total_units if total_units > 0 else 0
+                        progress_bar.progress(min(progress, 1.0))
 
                         # Calculate ETA
                         elapsed = time.time() - start_time
-                        if i > 0:
-                            avg_time_per_item = elapsed / i
-                            remaining_items = total_items - i
-                            eta_seconds = avg_time_per_item * remaining_items
+                        if processed_units > 0:
+                            avg_time_per_unit = elapsed / processed_units
+                            remaining_units = total_units - processed_units
+                            eta_seconds = avg_time_per_unit * remaining_units
                             eta_str = f" | ETA: {eta_seconds:.0f}s" if eta_seconds < 60 else f" | ETA: {eta_seconds/60:.1f}m"
                         else:
                             eta_str = ""
 
-                        status_text.text(f"Processing item {i+1} of {total_items} ({progress*100:.0f}%){eta_str}")
+                        if input_type_selected == "pdf":
+                            status_text.text(f"Processing page {processed_units + 1} of {total_units} ({progress*100:.0f}%){eta_str}")
+                        else:
+                            status_text.text(f"Processing {progress_unit} {processed_units + 1} of {total_units} ({progress*100:.0f}%){eta_str}")
 
                         try:
                             classify_kwargs = {
@@ -1023,14 +1055,26 @@ with col_input:
 
                             item_result = catllm.classify(**classify_kwargs)
                             all_results.append(item_result)
+
+                            # Update processed count (pages for PDFs, 1 for others)
+                            processed_units += item_pages
+
+                            # Update progress after processing
+                            progress = processed_units / total_units if total_units > 0 else 1.0
+                            progress_bar.progress(min(progress, 1.0))
+
                         except Exception as e:
-                            st.warning(f"Error on item {i+1}: {str(e)}")
+                            st.warning(f"Error on {progress_unit} {i+1}: {str(e)}")
+                            processed_units += item_pages  # Still count as processed
                             continue
 
                     # Complete progress
                     progress_bar.progress(1.0)
                     processing_time = time.time() - start_time
-                    status_text.text(f"Completed {total_items} items in {processing_time:.1f}s")
+                    if input_type_selected == "pdf":
+                        status_text.text(f"Completed {total_pages} pages in {processing_time:.1f}s")
+                    else:
+                        status_text.text(f"Completed {total_units} items in {processing_time:.1f}s")
 
                     if all_results:
                         # Combine results
@@ -1125,7 +1169,7 @@ with col_output:
         with st.expander("See the Code"):
             st.code(results['code'], language='python')
     else:
-        st.info("Upload data, select categories, and click 'Classify Data' to see results here.")
+        st.info("Upload data, select categories, and click 'Categorize Data' to see results here.")
 
 # Bottom buttons
 col_reset, col_code = st.columns(2)