Update app.py

app.py

@@ -1,306 +1,3 @@
-# import fitz  # PyMuPDF
-# import numpy as np
-# import cv2
-# import torch
-# import torch.serialization
-# import os
-# from typing import Optional, Tuple
-# from ultralytics import YOLO
-# import logging
-# import gradio as gr
-# import shutil
-# import tempfile
-# import json # Still needed for simple JSON logging
-
-# # ============================================================================
-# # --- Global Patches and Setup ---
-# # ============================================================================
-
-# # Patch torch.load to prevent weights_only error with older models
-# _original_torch_load = torch.load
-# def patched_torch_load(*args, **kwargs):
-#     kwargs["weights_only"] = False
-#     return _original_torch_load(*args, **kwargs)
-# torch.load = patched_torch_load
-
-# logging.basicConfig(level=logging.WARNING)
-
-# # ============================================================================
-# # --- CONFIGURATION AND CONSTANTS ---
-# # ============================================================================
-
-# WEIGHTS_PATH = 'best.pt' 
-
-# # Detection parameters (Required for your box combination logic)
-# CONF_THRESHOLD = 0.2
-# TARGET_CLASSES = ['figure', 'equation']
-# IOU_MERGE_THRESHOLD = 0.4
-# IOA_SUPPRESSION_THRESHOLD = 0.7
-
-# # Global counters (Reset per run)
-# GLOBAL_FIGURE_COUNT = 0
-# GLOBAL_EQUATION_COUNT = 0
-
-# # ============================================================================
-# # --- BOX COMBINATION LOGIC (Retained from your original script) ---
-# # ============================================================================
-
-# def calculate_iou(box1, box2):
-#     x1_a, y1_a, x2_a, y2_a = box1
-#     x1_b, y1_b, x2_b, y2_b = box2
-#     x_left = max(x1_a, x1_b)
-#     y_top = max(y1_a, y1_b)
-#     x_right = min(x2_a, x2_b)
-#     y_bottom = min(y2_a, y2_b)
-#     intersection_area = max(0, x_right - x_left) * max(0, y_bottom - y_top)
-#     box_a_area = (x2_a - x1_a) * (y2_a - y1_a)
-#     box_b_area = (x2_b - x1_b) * (y2_b - y1_b)
-#     union_area = float(box_a_area + box_b_area - intersection_area)
-#     return intersection_area / union_area if union_area > 0 else 0
-
-
-# def filter_nested_boxes(detections, ioa_threshold=0.80):
-#     if not detections: return []
-#     for d in detections:
-#         x1, y1, x2, y2 = d['coords']
-#         d['area'] = (x2 - x1) * (y2 - y1)
-#     detections.sort(key=lambda x: x['area'], reverse=True)
-#     keep_indices = []
-#     is_suppressed = [False] * len(detections)
-#     for i in range(len(detections)):
-#         if is_suppressed[i]: continue
-#         keep_indices.append(i)
-#         box_a = detections[i]['coords']
-#         for j in range(i + 1, len(detections)):
-#             if is_suppressed[j]: continue
-#             box_b = detections[j]['coords']
-#             x_left = max(box_a[0], box_b[0])
-#             y_top = max(box_a[1], box_b[1])
-#             x_right = min(box_a[2], box_b[2])
-#             y_bottom = min(box_a[3], box_b[3])
-#             intersection = max(0, x_right - x_left) * max(0, y_bottom - y_top)
-#             area_b = detections[j]['area']
-#             if area_b > 0 and intersection / area_b > ioa_threshold:
-#                 is_suppressed[j] = True
-#     return [detections[i] for i in keep_indices]
-
-
-# def merge_overlapping_boxes(detections, iou_threshold):
-#     if not detections: return []
-#     detections.sort(key=lambda d: d['conf'], reverse=True)
-#     merged_detections = []
-#     is_merged = [False] * len(detections)
-#     for i in range(len(detections)):
-#         if is_merged[i]: continue
-#         current_box = detections[i]['coords']
-#         current_class = detections[i]['class']
-#         merged_x1, merged_y1, merged_x2, merged_y2 = current_box
-#         for j in range(i + 1, len(detections)):
-#             if is_merged[j] or detections[j]['class'] != current_class: continue
-#             other_box = detections[j]['coords']
-#             iou = calculate_iou(current_box, other_box)
-#             if iou > iou_threshold:
-#                 merged_x1 = min(merged_x1, other_box[0])
-#                 merged_y1 = min(merged_y1, other_box[1])
-#                 merged_x2 = max(merged_x2, other_box[2])
-#                 merged_y2 = max(merged_y2, other_box[3])
-#                 is_merged[j] = True
-#         merged_detections.append({
-#             'coords': (merged_x1, merged_y1, merged_x2, merged_y2),
-#             'y1': merged_y1, 'class': current_class, 'conf': detections[i]['conf']
-#         })
-#     return merged_detections
-
-# # ============================================================================
-# # --- UTILITY FUNCTIONS (Minimally Required) ---
-# # ============================================================================
-
-# def pixmap_to_numpy(pix: fitz.Pixmap) -> np.ndarray:
-#     """Converts a PyMuPDF Pixmap to a NumPy array for OpenCV/YOLO."""
-#     img = np.frombuffer(pix.samples, dtype=np.uint8).reshape(
-#         (pix.h, pix.w, pix.n)
-#     )
-#     if pix.n == 4:
-#         img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
-#     elif pix.n == 1:
-#         img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
-#     return img
-
-
-# def run_yolo_detection_and_count(
-#         image: np.ndarray, model: YOLO, page_num: int
-# ) -> Tuple[int, int]:
-#     """
-#     Runs YOLO inference, applies NMS/filtering, and updates global counters.
-#     Returns the counts for the current page.
-#     """
-#     global GLOBAL_FIGURE_COUNT, GLOBAL_EQUATION_COUNT
-    
-#     yolo_detections = []
-#     page_equations = 0
-#     page_figures = 0
-    
-#     try:
-#         # Run prediction
-#         results = model.predict(image, conf=CONF_THRESHOLD, verbose=False)
-        
-#         if results and results[0].boxes:
-#             for box in results[0].boxes.data.tolist():
-#                 x1, y1, x2, y2, conf, cls_id = box
-#                 cls_name = model.names[int(cls_id)]
-                
-#                 if cls_name in TARGET_CLASSES:
-#                     yolo_detections.append({
-#                         'coords': (x1, y1, x2, y2), 
-#                         'class': cls_name, 
-#                         'conf': conf
-#                     })
-#     except Exception as e:
-#         logging.error(f"YOLO inference failed on page {page_num}: {e}")
-#         return 0, 0 
-
-#     # Apply NMS/Merging/Filtering based on your provided logic
-#     merged_detections = merge_overlapping_boxes(yolo_detections, IOU_MERGE_THRESHOLD)
-#     final_detections = filter_nested_boxes(merged_detections, IOA_SUPPRESSION_THRESHOLD)
-
-#     # Update Global Counters
-#     for det in final_detections:
-#         if det['class'] == 'figure':
-#             GLOBAL_FIGURE_COUNT += 1
-#             page_figures += 1
-#         elif det['class'] == 'equation':
-#             GLOBAL_EQUATION_COUNT += 1
-#             page_equations += 1
-            
-#     logging.warning(f"  -> Page {page_num}: EQs={page_equations}, Figs={page_figures}")
-#     return page_equations, page_figures
-
-
-# # ============================================================================
-# # --- MAIN DOCUMENT PROCESSING FUNCTION (Modified for Minimal Output) ---
-# # ============================================================================
-
-# def run_single_pdf_preprocessing(pdf_path: str) -> Tuple[int, int, int, str]:
-#     """
-#     Runs the pipeline and returns just the counts and a report.
-#     No intermediate JSON saving or complex output structure.
-#     """
-#     global GLOBAL_FIGURE_COUNT, GLOBAL_EQUATION_COUNT
-
-#     # Reset globals
-#     GLOBAL_FIGURE_COUNT = 0
-#     GLOBAL_EQUATION_COUNT = 0
-
-#     if not os.path.exists(pdf_path):
-#         report = f"❌ FATAL ERROR: Input PDF not found at {pdf_path}."
-#         return 0, 0, 0, report
-    
-#     # Model Loading (CRITICAL: Requires best.pt)
-#     try:
-#         model = YOLO(WEIGHTS_PATH)
-#         logging.warning(f"✅ Loaded YOLO model from: {WEIGHTS_PATH}")
-#     except Exception as e:
-#         report = f"❌ ERROR loading YOLO model: {e}\n(Ensure 'best.pt' is available and valid.)"
-#         return 0, 0, 0, report
-
-#     try:
-#         doc = fitz.open(pdf_path)
-#         total_pages = doc.page_count
-#         logging.warning(f"✅ Opened PDF: {doc.page_count} pages")
-#     except Exception as e:
-#         report = f"❌ ERROR loading PDF file: {e}"
-#         return 0, 0, 0, report
-
-#     mat = fitz.Matrix(2.0, 2.0)
-    
-#     for page_num_0_based in range(doc.page_count):
-#         fitz_page = doc.load_page(page_num_0_based)
-#         page_num = page_num_0_based + 1
-
-#         try:
-#             pix = fitz_page.get_pixmap(matrix=mat)
-#             original_img = pixmap_to_numpy(pix)
-#         except Exception as e:
-#             logging.error(f"Error converting page {page_num} to image: {e}. Skipping.")
-#             continue
-
-#         # Core Detection and Counting
-#         run_yolo_detection_and_count(original_img, model, page_num)
-    
-#     doc.close()
-
-#     # Final Report Generation
-#     report = (
-#         f"✅ **YOLO Counting Complete!**\n\n"
-#         f"**1) Total Pages Detected in PDF:** **{total_pages}**\n"
-#         f"**2) Total Equations Detected:** **{GLOBAL_EQUATION_COUNT}**\n"
-#         f"**3) Total Figures Detected:** **{GLOBAL_FIGURE_COUNT}**"
-#     )
-
-#     return total_pages, GLOBAL_EQUATION_COUNT, GLOBAL_FIGURE_COUNT, report
-
-
-# # ============================================================================
-# # --- GRADIO INTERFACE FUNCTION (Modified for minimal output) ---
-# # ============================================================================
-
-# def gradio_process_pdf(pdf_file) -> Tuple[str, str, str, str]:
-#     """
-#     Gradio wrapper function to handle file upload and return all results as strings.
-#     """
-#     if pdf_file is None:
-#         return "N/A", "N/A", "N/A", "Please upload a PDF file."
-    
-#     pdf_path = pdf_file.name
-
-#     try:
-#         # Run the core logic
-#         num_pages, num_equations, num_figures, report = run_single_pdf_preprocessing(pdf_path)
-        
-#         # Return results as formatted strings
-#         return str(num_pages), str(num_equations), str(num_figures), report
-            
-#     except Exception as e:
-#         error_msg = f"An unexpected error occurred: {e}"
-#         return "Error", "Error", "Error", error_msg
-
-
-# # ============================================================================
-# # --- GRADIO INTERFACE DEFINITION ---
-# # ============================================================================
-
-# if __name__ == "__main__":
-    
-#     if not os.path.exists(WEIGHTS_PATH):
-#         logging.error(f"❌ FATAL ERROR: YOLO weight file '{WEIGHTS_PATH}' not found. Cannot run live inference.")
-        
-#     input_file = gr.File(label="Upload PDF Document", type="filepath", file_types=[".pdf"])
-    
-#     # Outputs are now discrete number fields and a final markdown report
-#     output_pages = gr.Textbox(label="Total Pages in PDF", interactive=False)
-#     output_equations = gr.Textbox(label="Total Equations Detected", interactive=False)
-#     output_figures = gr.Textbox(label="Total Figures Detected", interactive=False)
-#     output_report = gr.Markdown(label="Processing Summary")
-    
-#     interface = gr.Interface(
-#         fn=gradio_process_pdf,
-#         inputs=input_file,
-#         outputs=[output_pages, output_equations, output_figures, output_report],
-#         title="🎯 Minimalist YOLO Counting for PDF Elements",
-#         description=(
-#             "Upload a PDF to instantly run YOLO detection using your **`best.pt`** model "
-#             "and get the total counts for pages, equations, and figures."
-#         ),
-#     )
-
-#     print("\nStarting Gradio application...")
-#     interface.launch(inbrowser=True)
-
-
-
-
-
-
 import fitz  # PyMuPDF
 import numpy as np
 import cv2
@@ -493,7 +190,7 @@ def run_yolo_detection_and_count(
 
 
 # ============================================================================
-# --- MAIN DOCUMENT PROCESSING FUNCTION (Fixed for Gradio Gallery) ---
+# --- MAIN DOCUMENT PROCESSING FUNCTION ---
 # ============================================================================
 
 def run_single_pdf_preprocessing(pdf_path: str, temp_output_dir: str) -> Tuple[int, int, int, str, List[str]]:
@@ -551,14 +248,14 @@ def run_single_pdf_preprocessing(pdf_path: str, temp_output_dir: str) -> Tuple[i
             bbox = eq['bbox_pdf'] 
             
             try:
-                # FIX 1 (PyMuPDF Rect): Only instantiate Rect, no .prerotate()
+                # Fixed Rect object creation
                 rect = fitz.Rect(bbox) 
                 clip_rect = rect + (0, 0, 5, 5) # Add small padding
                 
                 # Get the pixmap for the cropped area (high-res render)
                 eq_pix = fitz_page.get_pixmap(matrix=fitz.Matrix(3.0, 3.0), clip=clip_rect)
                 
-                # FIX 2 (Gradio Gallery): Save to a temporary file path
+                # Save to a temporary file path
                 img_bytes = eq_pix.tobytes("png")
                 filename = f"eq_{GLOBAL_EQUATION_COUNT}_p{page_num}.png"
                 output_path = os.path.join(temp_output_dir, filename)
@@ -586,18 +283,22 @@ def run_single_pdf_preprocessing(pdf_path: str, temp_output_dir: str) -> Tuple[i
 
 
 # ============================================================================
-# --- GRADIO INTERFACE FUNCTION (Fixed for temp dir management) ---
+# --- GRADIO INTERFACE FUNCTION (Fixed for temp dir cleanup) ---
 # ============================================================================
 
 def gradio_process_pdf(pdf_file) -> Tuple[str, str, str, str, List[str]]:
     """
     Gradio wrapper function to handle file upload, manage temporary directory, and return file paths.
+    
+    The cleanup block is REMOVED to allow Gradio's front-end to access the images
+    before the files are deleted. Gradio will eventually handle the cleanup.
     """
     if pdf_file is None:
         return "N/A", "N/A", "N/A", "Please upload a PDF file.", []
     
     pdf_path = pdf_file.name
-    temp_output_dir = tempfile.mkdtemp() # Create temp directory
+    # Create temp directory
+    temp_output_dir = tempfile.mkdtemp() 
 
     try:
         # Run the core logic, passing the temp directory
@@ -611,10 +312,12 @@ def gradio_process_pdf(pdf_file) -> Tuple[str, str, str, str, List[str]]:
     except Exception as e:
         error_msg = f"An unexpected error occurred: {e}"
         logging.error(error_msg, exc_info=True)
-        return "Error", "Error", "Error", error_msg, []
-    finally:
-        # CRUCIAL: Clean up the temporary directory containing the image files
+        # Still clean up in case of a hard error
         shutil.rmtree(temp_output_dir, ignore_errors=True)
+        return "Error", "Error", "Error", error_msg, []
+    
+    # NOTE: The final cleanup block for success case is intentionally removed 
+    # to prevent files from being deleted before Gradio can serve them.
 
 
 # ============================================================================