Error related to docx filenames

app.py

@@ -365,6 +365,46 @@ def strip_html_tags(text):
     text = re.sub(r'</span>', '', text)
     return text
 
+def sanitize_filename(text, max_length=100):
+    """
+    Sanitizes text to create a safe filename for both filesystems and HTTP headers.
+
+    Args:
+        text: The text to sanitize
+        max_length: Maximum length for the sanitized text (default 100)
+
+    Returns:
+        A sanitized string safe for use in filenames and HTTP Content-Disposition headers
+    """
+    if not text:
+        return "lesson"
+
+    # Replace newlines, tabs, and other whitespace with single space
+    text = re.sub(r'[\n\r\t\v\f]+', ' ', text)
+
+    # Replace multiple spaces with single space
+    text = re.sub(r'\s+', ' ', text)
+
+    # Remove or replace unsafe characters for filenames and HTTP headers
+    # Keep only alphanumeric, spaces, hyphens, and underscores
+    text = re.sub(r'[^\w\s\-]', '', text)
+
+    # Replace spaces with underscores
+    text = text.replace(' ', '_')
+
+    # Remove leading/trailing underscores
+    text = text.strip('_')
+
+    # Truncate to max_length while avoiding cutting mid-word
+    if len(text) > max_length:
+        text = text[:max_length].rsplit('_', 1)[0]
+
+    # Ensure we have at least some text
+    if not text:
+        return "lesson"
+
+    return text
+
 def create_docx_file(lessons_data, lesson_topic, lesson_length, model_name):
     """
     Creates a DOCX file from a sequence of lessons.
@@ -646,10 +686,14 @@ else:
                             st.session_state.lesson_length,
                             model_name
                         )
+                        # Sanitize filename components
+                        safe_model_name = sanitize_filename(model_name, max_length=50)
+                        safe_topic = sanitize_filename(st.session_state.lesson_topic, max_length=80)
+
                         st.download_button(
                             label=f"Download {model_name} (DOCX)",
                             data=docx_file,
-                            file_name=f"{model_name.replace(' ', '_')}_lesson_sequence_{st.session_state.lesson_topic.replace(' ', '_')}.docx",
+                            file_name=f"{safe_model_name}_lesson_sequence_{safe_topic}.docx",
                             mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                             key=f"download_docx_{model_name}"
                         )