Update app.py

app.py

@@ -3,6 +3,7 @@ import gradio as gr
 import os
 import json
 import shutil
+import subprocess
 from datetime import datetime
 from pathlib import Path
 from typing import Tuple
@@ -11,6 +12,47 @@ from typing import Tuple
 from main6_pix2text import extract_all_text_advanced_pix2text, initialize_pix2text
 from eval import evaluate_ocr_accuracy, clean_control_characters
 
+def check_system_dependencies():
+    """Check and report system dependencies status."""
+    print("🔍 Checking system dependencies...")
+    
+    # Check Tesseract
+    try:
+        result = subprocess.run(['tesseract', '--version'], capture_output=True, text=True)
+        if result.returncode == 0:
+            print("✅ Tesseract is available")
+        else:
+            print("❌ Tesseract check failed")
+    except FileNotFoundError:
+        print("❌ Tesseract not found in PATH")
+    
+    # Check Poppler
+    poppler_tools = ['pdftoppm', 'pdfinfo']
+    for tool in poppler_tools:
+        try:
+            result = subprocess.run(['which', tool], capture_output=True, text=True)
+            if result.returncode == 0:
+                print(f"✅ {tool} is available")
+            else:
+                print(f"❌ {tool} not found")
+        except FileNotFoundError:
+            print(f"❌ {tool} not available")
+    
+    # Check pdf2image
+    try:
+        import importlib.util
+        if importlib.util.find_spec("pdf2image") is not None:
+            print("✅ pdf2image is available")
+        else:
+            print("❌ pdf2image module not found")
+    except Exception as e:
+        print(f"❌ pdf2image check failed: {e}")
+    
+    print(f"📍 PATH: {os.environ.get('PATH', 'NOT SET')}")
+
+# Run dependency check on startup
+check_system_dependencies()
+
 
 # Initialize directories
 def create_directories():
@@ -90,7 +132,44 @@ def process_pdf_ocr(pdf_file) -> Tuple[str, str, str]:
         return extracted_text, json_display, analysis_display
 
     except Exception as e:
-        error_msg = f"❌ Error processing PDF: {str(e)}"
+        error_msg = str(e)
+
+        # Provide specific guidance for common errors
+        if (
+            "poppler" in error_msg.lower()
+            or "unable to get page count" in error_msg.lower()
+        ):
+            error_msg = """❌ PDF Processing Error: Poppler not found
+            
+🔧 This error occurs because Poppler (PDF utilities) is not properly installed.
+
+📋 For Hugging Face Spaces:
+1. Ensure your setup.sh script runs during deployment
+2. Check that poppler-utils is installed in the container
+3. Verify the setup logs show successful poppler installation
+
+💡 The setup.sh script should install these packages:
+   - poppler-utils
+   - libpoppler-cpp-dev
+   - pkg-config
+
+🚨 Original error: {error_msg}
+
+🔄 Try restarting the space if this persists."""
+        elif "tesseract" in error_msg.lower():
+            error_msg = f"""❌ OCR Engine Error: Tesseract issue
+            
+🔧 This error is related to Tesseract OCR engine.
+
+📋 Possible solutions:
+1. Check Tesseract installation in setup.sh
+2. Verify language data files are available
+3. Ensure proper permissions on tessdata directory
+
+🚨 Original error: {error_msg}"""
+        else:
+            error_msg = f"❌ Error processing PDF: {error_msg}"
+
         return error_msg, "", ""
 
 
@@ -397,11 +476,6 @@ except Exception as e:
 # Create and launch the interface
 if __name__ == "__main__":
     app = create_interface()
-    
+
     # Launch with proper configuration for Hugging Face Spaces
-    app.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        share=False,
-        show_error=True
-    )
+    app.launch(server_name="0.0.0.0", server_port=7860, share=False, show_error=True)