import sys
import re
import json
import logging
import numpy as np
from datetime import datetime

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def detect_highlights(chat_file, min_duration=10, threshold=2.0):
    """Detecta highlights por chat saturado"""
    
    logger.info("Analizando picos de chat...")
    
    # Leer mensajes
    messages = []
    with open(chat_file, 'r', encoding='utf-8') as f:
        for line in f:
            match = re.match(r'\[(\d{4}-\d{2}-\d{2}T[\d:.]+Z?)\]', line)
            if match:
                timestamp_str = match.group(1).replace('Z', '+00:00')
                try:
                    timestamp = datetime.fromisoformat(timestamp_str)
                    messages.append((timestamp, line))
                except:
                    pass
    
    if not messages:
        logger.error("No se encontraron mensajes")
        return []
    
    start_time = messages[0][0]
    end_time = messages[-1][0]
    duration = (end_time - start_time).total_seconds()
    
    logger.info(f"Chat: {len(messages)} mensajes, duración: {duration:.1f}s")
    
    # Agrupar por segundo
    time_buckets = {}
    for timestamp, _ in messages:
        second = int((timestamp - start_time).total_seconds())
        time_buckets[second] = time_buckets.get(second, 0) + 1
    
    # Calcular estadísticas
    counts = list(time_buckets.values())
    mean_count = np.mean(counts)
    std_count = np.std(counts)
    
    logger.info(f"Stats: media={mean_count:.1f}, std={std_count:.1f}")
    
    # Detectar picos
    peak_seconds = []
    for second, count in time_buckets.items():
        if std_count > 0:
            z_score = (count - mean_count) / std_count
            if z_score > threshold:
                peak_seconds.append(second)
    
    logger.info(f"Picos encontrados: {len(peak_seconds)}")
    
    # Unir segundos consecutivos
    if not peak_seconds:
        return []
    
    intervals = []
    start = peak_seconds[0]
    prev = peak_seconds[0]
    
    for second in peak_seconds[1:]:
        if second - prev > 1:
            if second - start >= min_duration:
                intervals.append((start, prev))
            start = second
        prev = second
    
    if prev - start >= min_duration:
        intervals.append((start, prev))
    
    return intervals


if __name__ == "__main__":
    chat_file = "chat.txt"
    
    highlights = detect_highlights(chat_file)
    
    print(f"\nHighlights encontrados: {len(highlights)}")
    for i, (start, end) in enumerate(highlights):
        print(f"  {i+1}. {start}s - {end}s (duración: {end-start}s)")
    
    # Guardar JSON
    with open("highlights.json", "w") as f:
        json.dump(highlights, f)
    print(f"\nGuardado en highlights.json")