"""
Part-of-Speech Tagging Module
Performs advanced POS tagging and analysis

Developer: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277
Year: 2026
"""

import spacy
from collections import Counter
from text_preprocessing import TextPreprocessor

class POSTagger:
    """
    Part-of-Speech tagging class
    Developer: RSK World - https://rskworld.in
    """
    
    def __init__(self):
        """Initialize POS tagger"""
        try:
            self.nlp = spacy.load("en_core_web_sm")
        except OSError:
            print("Warning: spaCy model not found for POS tagging")
            self.nlp = None
        
        self.preprocessor = TextPreprocessor()
    
    def tag_text(self, text):
        """
        Tag all words with their part of speech
        
        Args:
            text (str): Input text
            
        Returns:
            dict: POS tagging results
        """
        if self.nlp is None:
            return {
                'error': 'spaCy model not available'
            }
        
        try:
            doc = self.nlp(text)
            
            tagged_words = []
            pos_counts = Counter()
            
            for token in doc:
                if not token.is_punct and not token.is_space:
                    tagged_words.append({
                        'word': token.text,
                        'pos': token.pos_,
                        'tag': token.tag_,
                        'lemma': token.lemma_,
                        'description': spacy.explain(token.pos_)
                    })
                    pos_counts[token.pos_] += 1
            
            return {
                'tagged_words': tagged_words,
                'pos_distribution': dict(pos_counts),
                'total_words': len(tagged_words),
                'unique_pos': len(pos_counts)
            }
        except Exception as e:
            print(f"Error in POS tagging: {e}")
            return {
                'error': str(e)
            }
    
    def get_pos_statistics(self, text):
        """
        Get statistics about parts of speech
        
        Args:
            text (str): Input text
            
        Returns:
            dict: POS statistics
        """
        result = self.tag_text(text)
        
        if 'error' in result:
            return result
        
        pos_dist = result['pos_distribution']
        total = result['total_words']
        
        # Calculate percentages
        pos_percentages = {
            pos: (count / total * 100) if total > 0 else 0
            for pos, count in pos_dist.items()
        }
        
        return {
            'pos_distribution': pos_dist,
            'pos_percentages': pos_percentages,
            'total_words': total,
            'most_common_pos': max(pos_dist.items(), key=lambda x: x[1])[0] if pos_dist else None
        }