email parsing.

app.py

@@ -12,6 +12,8 @@ from werkzeug.security import generate_password_hash, check_password_hash
 import markdown
 import logging
 import re
+from email import message_from_string
+from email.mime.text import MIMEText
 from whoosh.index import create_in, open_dir
 from whoosh.fields import Schema, TEXT, ID
 from whoosh.qparser import QueryParser
@@ -123,6 +125,94 @@ def is_authenticated(filepath):
     authenticated_files = session.get('authenticated_files', {})
     return authenticated_files.get(file_key, False)
 
+def extract_email_text(email_content):
+    """
+    Extract readable text content from an email message.
+    Handles multipart messages, various encodings (base64, quoted-printable), and prefers text/plain.
+    Returns formatted email with headers and body.
+    """
+    try:
+        msg = message_from_string(email_content)
+        
+        # Extract key headers in order
+        headers_order = ['From', 'To', 'Cc', 'Bcc', 'Subject', 'Date']
+        headers = {}
+        for header in headers_order:
+            value = msg.get(header)
+            if value:
+                # Clean up header values (remove extra whitespace/newlines)
+                value = ' '.join(value.split())
+                headers[header] = value
+        
+        # Extract body content
+        body_text = None
+        body_html = None
+        
+        # Handle multipart messages
+        if msg.is_multipart():
+            for part in msg.walk():
+                content_type = part.get_content_type()
+                
+                # Skip container parts and non-text content
+                if content_type.startswith('multipart'):
+                    continue
+                    
+                # Skip if no content
+                try:
+                    content = part.get_payload(decode=True)
+                    if not content:
+                        continue
+                except Exception:
+                    continue
+                
+                try:
+                    text = content.decode('utf-8', errors='replace')
+                except Exception:
+                    text = str(content)
+                
+                text = text.strip()
+                if not text:
+                    continue
+                
+                # Prefer text/plain, but save html as fallback
+                if content_type == 'text/plain' and not body_text:
+                    body_text = text
+                elif content_type == 'text/html' and not body_html:
+                    body_html = text
+        else:
+            # Single part message
+            try:
+                body_text = msg.get_payload(decode=True).decode('utf-8', errors='replace').strip()
+            except Exception:
+                body_text = msg.get_payload()
+        
+        # Use text if available, otherwise html
+        body = body_text if body_text else body_html
+        
+        if not body:
+            body = "(No message body found)"
+        
+        # Format the output
+        formatted_email = []
+        
+        # Add headers in order
+        for header in headers_order:
+            if header in headers:
+                formatted_email.append(f"{header}: {headers[header]}")
+        
+        if headers:
+            formatted_email.append("")  # Blank line between headers and body
+        
+        # Add body
+        formatted_email.append(body)
+        
+        return '\n'.join(formatted_email)
+    
+    except Exception as e:
+        logger.error(f"Error parsing email: {e}")
+        # Return original content if parsing fails
+        return email_content
+
 # Initialize search index
 def create_search_index():
     """Create or open the search index."""
@@ -439,20 +529,21 @@ def serve_file(filepath):
             
             # Check if content is base64 encoded
             # Base64 content is ASCII and contains only base64 characters
-            is_base64 = False
             try:
                 if content.strip() and all(c in 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=\n\r' for c in content):
                     decoded = base64.b64decode(content, validate=True).decode('utf-8', errors='ignore')
                     # If it looks like an email (has headers), use decoded version
                     if 'From:' in decoded or 'To:' in decoded or 'Subject:' in decoded:
                         content = decoded
-                        is_base64 = True
             except Exception:
                 # Not valid base64, use original content
                 pass
             
+            # Extract and format the email content
+            formatted_email = extract_email_text(content)
+            
             # Return as text/plain for viewing in browser
-            response = make_response(content)
+            response = make_response(formatted_email)
             response.headers['Content-Type'] = 'text/plain; charset=utf-8'
             response.headers['Content-Disposition'] = f'inline; filename="{os.path.basename(file_path)}"'
             return response