first commit

cleaner.py

@@ -0,0 +1,72 @@
+"""
+Response cleaner module.
+Removes markdown formatting and special characters from AI responses.
+"""
+import re
+
+
+def clean_response(text: str) -> str:
+    """
+    Clean AI response from markdown formatting and special characters.
+    
+    Args:
+        text: Raw AI response with possible markdown
+        
+    Returns:
+        Clean text suitable for TTS
+    """
+    if not text:
+        return ""
+    
+    # Remove citation references like [1], [2], [citation], etc.
+    text = re.sub(r'\[\d+\]', '', text)
+    text = re.sub(r'\[citation\s*needed\]', '', text, flags=re.IGNORECASE)
+    text = re.sub(r'\[source\]', '', text, flags=re.IGNORECASE)
+    
+    # Remove markdown bold **text** and __text__
+    text = re.sub(r'\*\*(.+?)\*\*', r'\1', text)
+    text = re.sub(r'__(.+?)__', r'\1', text)
+    
+    # Remove markdown italic *text* and _text_
+    text = re.sub(r'\*(.+?)\*', r'\1', text)
+    text = re.sub(r'(?<!\w)_(.+?)_(?!\w)', r'\1', text)
+    
+    # Remove markdown strikethrough ~~text~~
+    text = re.sub(r'~~(.+?)~~', r'\1', text)
+    
+    # Remove markdown headers # ## ### etc.
+    text = re.sub(r'^#{1,6}\s*', '', text, flags=re.MULTILINE)
+    
+    # Remove markdown links [text](url) -> text
+    text = re.sub(r'\[([^\]]+)\]\([^)]+\)', r'\1', text)
+    
+    # Remove markdown images ![alt](url)
+    text = re.sub(r'!\[([^\]]*)\]\([^)]+\)', '', text)
+    
+    # Remove inline code `code`
+    text = re.sub(r'`([^`]+)`', r'\1', text)
+    
+    # Remove code blocks ```code```
+    text = re.sub(r'```[\s\S]*?```', '', text)
+    
+    # Remove markdown list markers (-, *, +, numbered)
+    text = re.sub(r'^\s*[-*+]\s+', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^\s*\d+\.\s+', '', text, flags=re.MULTILINE)
+    
+    # Remove blockquotes
+    text = re.sub(r'^\s*>\s*', '', text, flags=re.MULTILINE)
+    
+    # Remove horizontal rules
+    text = re.sub(r'^[-*_]{3,}\s*$', '', text, flags=re.MULTILINE)
+    
+    # Remove HTML tags if any
+    text = re.sub(r'<[^>]+>', '', text)
+    
+    # Remove extra whitespace
+    text = re.sub(r'\n{3,}', '\n\n', text)
+    text = re.sub(r'  +', ' ', text)
+    
+    # Clean up and return
+    text = text.strip()
+    
+    return text