src/utils.py

"""
Utility functions for Smart Auto-Complete
Provides common functionality for text processing, logging, and validation
"""

import logging
import re
import sys
from typing import Dict, List, Optional, Tuple
import html
import unicodedata


def setup_logging(level: str = "INFO") -> logging.Logger:
    """
    Set up logging configuration for the application
    
    Args:
        level: Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
        
    Returns:
        Configured logger instance
    """
    # Create logger
    logger = logging.getLogger("smart_autocomplete")
    logger.setLevel(getattr(logging, level.upper()))
    
    # Remove existing handlers to avoid duplicates
    for handler in logger.handlers[:]:
        logger.removeHandler(handler)
    
    # Create console handler with formatting
    console_handler = logging.StreamHandler(sys.stdout)
    console_handler.setLevel(getattr(logging, level.upper()))
    
    # Create formatter
    formatter = logging.Formatter(
        '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
        datefmt='%Y-%m-%d %H:%M:%S'
    )
    console_handler.setFormatter(formatter)
    
    # Add handler to logger
    logger.addHandler(console_handler)
    
    return logger


def sanitize_input(text: str) -> str:
    """
    Sanitize and clean input text for processing
    
    Args:
        text: Raw input text
        
    Returns:
        Cleaned and sanitized text
    """
    if not text:
        return ""
    
    # Convert to string if not already
    text = str(text)
    
    # HTML escape to prevent injection
    text = html.escape(text)
    
    # Normalize unicode characters
    text = unicodedata.normalize('NFKC', text)
    
    # Remove excessive whitespace but preserve structure
    text = re.sub(r'\n\s*\n\s*\n', '\n\n', text)  # Max 2 consecutive newlines
    text = re.sub(r'[ \t]+', ' ', text)  # Multiple spaces/tabs to single space
    
    # Remove control characters except newlines and tabs
    text = ''.join(char for char in text if ord(char) >= 32 or char in '\n\t')
    
    # Trim leading/trailing whitespace
    text = text.strip()
    
    return text


def extract_context_hints(text: str) -> Dict[str, any]:
    """
    Extract contextual hints from the input text to improve suggestions
    
    Args:
        text: Input text to analyze
        
    Returns:
        Dictionary containing context hints
    """
    hints = {
        'length': len(text),
        'word_count': len(text.split()),
        'has_greeting': False,
        'has_signature': False,
        'has_code_markers': False,
        'has_questions': False,
        'tone': 'neutral',
        'language_style': 'general'
    }
    
    text_lower = text.lower()
    
    # Check for email patterns
    email_greetings = ['dear', 'hello', 'hi', 'greetings', 'good morning', 'good afternoon']
    email_signatures = ['sincerely', 'best regards', 'thank you', 'yours truly', 'kind regards']
    
    hints['has_greeting'] = any(greeting in text_lower for greeting in email_greetings)
    hints['has_signature'] = any(signature in text_lower for signature in email_signatures)
    
    # Check for code patterns
    code_markers = ['//', '/*', '*/', '#', 'def ', 'function', 'class ', 'import ', 'from ']
    hints['has_code_markers'] = any(marker in text_lower for marker in code_markers)
    
    # Check for questions
    hints['has_questions'] = '?' in text or any(q in text_lower for q in ['what', 'how', 'why', 'when', 'where', 'who'])
    
    # Determine tone
    formal_words = ['please', 'kindly', 'respectfully', 'sincerely', 'professional']
    casual_words = ['hey', 'yeah', 'cool', 'awesome', 'thanks']
    
    formal_count = sum(1 for word in formal_words if word in text_lower)
    casual_count = sum(1 for word in casual_words if word in text_lower)
    
    if formal_count > casual_count:
        hints['tone'] = 'formal'
    elif casual_count > formal_count:
        hints['tone'] = 'casual'
    
    # Determine language style
    if hints['has_code_markers']:
        hints['language_style'] = 'technical'
    elif hints['has_greeting'] or hints['has_signature']:
        hints['language_style'] = 'business'
    elif any(creative in text_lower for creative in ['once upon', 'story', 'character', 'plot']):
        hints['language_style'] = 'creative'
    
    return hints


def validate_api_key(api_key: str, provider: str) -> bool:
    """
    Validate API key format for different providers
    
    Args:
        api_key: The API key to validate
        provider: The provider name (openai, anthropic)
        
    Returns:
        True if the key format is valid, False otherwise
    """
    if not api_key or not isinstance(api_key, str):
        return False
    
    api_key = api_key.strip()
    
    if provider.lower() == 'openai':
        # OpenAI keys start with 'sk-' and are typically 51 characters
        return api_key.startswith('sk-') and len(api_key) >= 40
    elif provider.lower() == 'anthropic':
        # Anthropic keys start with 'sk-ant-' 
        return api_key.startswith('sk-ant-') and len(api_key) >= 40
    
    return False


def truncate_text(text: str, max_length: int, preserve_words: bool = True) -> str:
    """
    Truncate text to a maximum length while optionally preserving word boundaries
    
    Args:
        text: Text to truncate
        max_length: Maximum allowed length
        preserve_words: Whether to preserve word boundaries
        
    Returns:
        Truncated text
    """
    if len(text) <= max_length:
        return text
    
    if not preserve_words:
        return text[:max_length].rstrip() + "..."
    
    # Find the last space before the max_length
    truncated = text[:max_length]
    last_space = truncated.rfind(' ')
    
    if last_space > max_length * 0.8:  # Only use word boundary if it's not too far back
        return text[:last_space].rstrip() + "..."
    else:
        return text[:max_length].rstrip() + "..."


def format_suggestions_for_display(suggestions: List[str], max_display_length: int = 100) -> List[Dict[str, str]]:
    """
    Format suggestions for display in the UI
    
    Args:
        suggestions: List of suggestion strings
        max_display_length: Maximum length for display
        
    Returns:
        List of formatted suggestion dictionaries
    """
    formatted = []
    
    for i, suggestion in enumerate(suggestions, 1):
        # Clean the suggestion
        clean_suggestion = sanitize_input(suggestion)
        
        # Create display version (truncated if needed)
        display_text = truncate_text(clean_suggestion, max_display_length)
        
        formatted.append({
            'id': i,
            'text': clean_suggestion,
            'display_text': display_text,
            'length': len(clean_suggestion),
            'word_count': len(clean_suggestion.split())
        })
    
    return formatted


def calculate_text_similarity(text1: str, text2: str) -> float:
    """
    Calculate similarity between two texts using simple word overlap
    
    Args:
        text1: First text
        text2: Second text
        
    Returns:
        Similarity score between 0 and 1
    """
    if not text1 or not text2:
        return 0.0
    
    # Convert to lowercase and split into words
    words1 = set(text1.lower().split())
    words2 = set(text2.lower().split())
    
    # Calculate Jaccard similarity
    intersection = len(words1.intersection(words2))
    union = len(words1.union(words2))
    
    return intersection / union if union > 0 else 0.0


def get_text_stats(text: str) -> Dict[str, int]:
    """
    Get basic statistics about the text
    
    Args:
        text: Text to analyze
        
    Returns:
        Dictionary with text statistics
    """
    if not text:
        return {'characters': 0, 'words': 0, 'sentences': 0, 'paragraphs': 0}
    
    # Count characters (excluding whitespace)
    char_count = len(text.replace(' ', '').replace('\n', '').replace('\t', ''))
    
    # Count words
    word_count = len(text.split())
    
    # Count sentences (rough estimate)
    sentence_count = len(re.findall(r'[.!?]+', text))
    
    # Count paragraphs
    paragraph_count = len([p for p in text.split('\n\n') if p.strip()])
    
    return {
        'characters': char_count,
        'words': word_count,
        'sentences': max(1, sentence_count),  # At least 1 sentence
        'paragraphs': max(1, paragraph_count)  # At least 1 paragraph
    }