Enhance Dockerfile and Streamlit app for improved temporary file management

- Added directory creation and permission settings in Dockerfile for temp files.
- Updated Streamlit app to use system temp directory, with fallback options for permission issues.
- Improved error handling and logging for temp file operations, ensuring better user feedback and stability.

Dockerfile

@@ -9,8 +9,14 @@ RUN apt-get update && apt-get install -y \
     git \
     && rm -rf /var/lib/apt/lists/*
 
+# Create necessary directories with proper permissions
+RUN mkdir -p /app/.streamlit /tmp/docling_temp && \
+    chmod 755 /app/.streamlit && \
+    chmod 777 /tmp/docling_temp
+
 COPY requirements.txt ./
 COPY src/ ./src/
+COPY .streamlit/ ./.streamlit/
 
 RUN pip3 install -r requirements.txt
 

src/streamlit_app.py

@@ -13,6 +13,14 @@ import difflib
 import re
 import time
 
+# Configure logging early to avoid issues
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s %(levelname)s %(name)s: %(message)s",
+    stream=sys.stdout,
+    force=True
+)
+
 # Load environment variables from .env
 load_dotenv()
 
@@ -21,9 +29,47 @@ AZURE_OPENAI_KEY = os.getenv("AZURE_OPENAI_KEY")
 AZURE_OPENAI_VERSION = os.getenv("AZURE_OPENAI_VERSION")
 AZURE_OPENAI_DEPLOYMENT = os.getenv("AZURE_OPENAI_DEPLOYMENT")
 
-# Create temp directory if it doesn't exist
-TEMP_DIR = "temp_files"
-os.makedirs(TEMP_DIR, exist_ok=True)
+# Use system temp directory instead of local directory to avoid permission issues
+TEMP_DIR = os.path.join(tempfile.gettempdir(), "docling_temp")
+try:
+    os.makedirs(TEMP_DIR, exist_ok=True)
+    logging.info(f"Using temp directory: {TEMP_DIR}")
+except PermissionError as e:
+    logging.warning(f"Permission error creating temp dir {TEMP_DIR}: {e}")
+    # Fallback to a subdirectory of the current working directory if temp dir fails
+    TEMP_DIR = os.path.join(os.getcwd(), "temp_files")
+    try:
+        os.makedirs(TEMP_DIR, exist_ok=True)
+        logging.info(f"Using fallback temp directory: {TEMP_DIR}")
+    except PermissionError as e2:
+        logging.warning(f"Permission error creating fallback temp dir {TEMP_DIR}: {e2}")
+        # Last resort: use a directory that should be writable
+        TEMP_DIR = "/tmp/docling_temp"
+        try:
+            os.makedirs(TEMP_DIR, exist_ok=True)
+            logging.info(f"Using last resort temp directory: {TEMP_DIR}")
+        except Exception as e3:
+            logging.error(f"Failed to create any temp directory: {e3}")
+            # Use current directory as absolute last resort
+            TEMP_DIR = "."
+            logging.warning(f"Using current directory as temp: {TEMP_DIR}")
+
+# Configure Streamlit to use writable directories
+os.environ['STREAMLIT_SERVER_FILE_WATCHER_TYPE'] = 'none'
+os.environ['STREAMLIT_SERVER_HEADLESS'] = 'true'
+os.environ['STREAMLIT_BROWSER_GATHER_USAGE_STATS'] = 'false'
+
+# Additional environment variables for Hugging Face deployment
+os.environ['STREAMLIT_SERVER_ENABLE_CORS'] = 'false'
+os.environ['STREAMLIT_SERVER_ENABLE_XSRF_PROTECTION'] = 'false'
+
+# Log startup information
+logging.info("=" * 50)
+logging.info("Docling Streamlit App Starting")
+logging.info(f"Temp directory: {TEMP_DIR}")
+logging.info(f"Current working directory: {os.getcwd()}")
+logging.info(f"Python version: {sys.version}")
+logging.info("=" * 50)
 
 def cleanup_temp_files():
     """Clean up temporary files in the temp directory."""
@@ -32,8 +78,18 @@ def cleanup_temp_files():
             for filename in os.listdir(TEMP_DIR):
                 file_path = os.path.join(TEMP_DIR, filename)
                 if os.path.isfile(file_path):
-                    os.remove(file_path)
+                    try:
+                        os.remove(file_path)
+                        logging.info(f"Removed temp file: {filename}")
+                    except PermissionError as e:
+                        logging.warning(f"Permission error removing {filename}: {e}")
+                    except Exception as e:
+                        logging.warning(f"Error removing {filename}: {e}")
             logging.info(f"Cleaned up temporary files in {TEMP_DIR}")
+        else:
+            logging.info(f"Temp directory {TEMP_DIR} does not exist")
+    except PermissionError as e:
+        logging.warning(f"Permission error accessing temp directory {TEMP_DIR}: {e}")
     except Exception as e:
         logging.warning(f"Error cleaning up temp files: {e}")
 
@@ -67,18 +123,29 @@ def clear_all_data():
 
 def get_temp_files_info():
     """Get information about temporary files (count and total size)."""
-    if not os.path.exists(TEMP_DIR):
+    try:
+        if not os.path.exists(TEMP_DIR):
+            return 0, 0
+        
+        files = os.listdir(TEMP_DIR)
+        total_size = 0
+        
+        for filename in files:
+            try:
+                file_path = os.path.join(TEMP_DIR, filename)
+                if os.path.isfile(file_path):
+                    total_size += os.path.getsize(file_path)
+            except (PermissionError, OSError) as e:
+                logging.warning(f"Error accessing file {filename}: {e}")
+                continue
+        
+        return len(files), total_size
+    except PermissionError as e:
+        logging.warning(f"Permission error accessing temp directory {TEMP_DIR}: {e}")
+        return 0, 0
+    except Exception as e:
+        logging.warning(f"Error getting temp files info: {e}")
         return 0, 0
-    
-    files = os.listdir(TEMP_DIR)
-    total_size = 0
-    
-    for filename in files:
-        file_path = os.path.join(TEMP_DIR, filename)
-        if os.path.isfile(file_path):
-            total_size += os.path.getsize(file_path)
-    
-    return len(files), total_size
 
 def format_file_size(size_bytes):
     """Format file size in human readable format."""
@@ -103,17 +170,13 @@ def save_uploaded_file(uploaded_file, filename):
             f.write(file_bytes)
         logging.info(f"Saved uploaded file to {temp_path}")
         return temp_path
+    except PermissionError as e:
+        logging.error(f"Permission error saving uploaded file to {temp_path}: {e}")
+        raise PermissionError(f"Cannot save file due to permission restrictions. Please try clearing data or contact support.")
     except Exception as e:
         logging.error(f"Error saving uploaded file: {e}")
         raise
 
-logging.basicConfig(
-    level=logging.INFO,  # or DEBUG for more verbosity
-    format="%(asctime)s %(levelname)s %(name)s: %(message)s",
-    stream=sys.stdout,
-    force=True
-)
-
 # Configure page layout to use wide mode
 st.set_page_config(
     page_title="Medical Document Parser & Redactor",

test_permissions.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""
+Test script to check permissions and directory creation in Hugging Face environment.
+"""
+
+import os
+import tempfile
+import logging
+
+def test_permissions():
+    """Test if we can create directories and files in various locations."""
+    print("=== Testing Permissions ===")
+    
+    # Test 1: System temp directory
+    print("\n1. Testing system temp directory...")
+    try:
+        temp_dir = os.path.join(tempfile.gettempdir(), "docling_test")
+        os.makedirs(temp_dir, exist_ok=True)
+        test_file = os.path.join(temp_dir, "test.txt")
+        with open(test_file, "w") as f:
+            f.write("test")
+        os.remove(test_file)
+        os.rmdir(temp_dir)
+        print(f"✅ Success: {temp_dir}")
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+    
+    # Test 2: Current working directory
+    print("\n2. Testing current working directory...")
+    try:
+        cwd = os.getcwd()
+        test_dir = os.path.join(cwd, "test_temp")
+        os.makedirs(test_dir, exist_ok=True)
+        test_file = os.path.join(test_dir, "test.txt")
+        with open(test_file, "w") as f:
+            f.write("test")
+        os.remove(test_file)
+        os.rmdir(test_dir)
+        print(f"✅ Success: {test_dir}")
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+    
+    # Test 3: /tmp directory
+    print("\n3. Testing /tmp directory...")
+    try:
+        tmp_dir = "/tmp/docling_test"
+        os.makedirs(tmp_dir, exist_ok=True)
+        test_file = os.path.join(tmp_dir, "test.txt")
+        with open(test_file, "w") as f:
+            f.write("test")
+        os.remove(test_file)
+        os.rmdir(tmp_dir)
+        print(f"✅ Success: {tmp_dir}")
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+    
+    # Test 4: Environment variables
+    print("\n4. Testing environment variables...")
+    env_vars = [
+        'STREAMLIT_SERVER_FILE_WATCHER_TYPE',
+        'STREAMLIT_SERVER_HEADLESS', 
+        'STREAMLIT_BROWSER_GATHER_USAGE_STATS'
+    ]
+    for var in env_vars:
+        value = os.environ.get(var, 'NOT_SET')
+        print(f"   {var}: {value}")
+    
+    # Test 5: Current directory permissions
+    print("\n5. Testing current directory permissions...")
+    try:
+        cwd = os.getcwd()
+        print(f"   Current directory: {cwd}")
+        print(f"   Readable: {os.access(cwd, os.R_OK)}")
+        print(f"   Writable: {os.access(cwd, os.W_OK)}")
+        print(f"   Executable: {os.access(cwd, os.X_OK)}")
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+
+if __name__ == "__main__":
+    test_permissions()