import os
import uuid
import csv
import pytz
from datetime import datetime
from pathlib import Path
from huggingface_hub import CommitScheduler, hf_hub_download

# --- CONFIGURAZIONE ---
DATASET_REPO_ID = "NextGenTech/ngt-ai-platform-logs" 
LOG_DIR = Path("data/logs")
LOG_FILE = LOG_DIR / "access_logs.csv"
HF_TOKEN = os.environ.get("HF_TOKEN")
ITALY_TZ = pytz.timezone("Europe/Rome")
TIME = 5 # Minuti di intervallo tra ogni aggiornamento del dataset

LOG_DIR.mkdir(parents=True, exist_ok=True)

if HF_TOKEN:
    try:
        print("📥 Controllo presenza log remoti...")
        hf_hub_download(
            repo_id=DATASET_REPO_ID,
            filename="logs/access_logs.csv",
            repo_type="dataset",
            token=HF_TOKEN,
            local_dir="data", 
            local_dir_use_symlinks=False
        )
        print("✅ Storico log scaricato e ripristinato!")
    except Exception as e:
        print(f"⚠️ Nessun log remoto trovato (o primo avvio): {e}")
        print("🆕 Si partirà con un nuovo file di log.")

if not LOG_FILE.exists() or LOG_FILE.stat().st_size == 0:
    print("🆕 Creazione header file di log...")
    
    with open(LOG_FILE, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f, lineterminator='\n')
        writer.writerow([
            "timestamp", "session_id", "module", "action", 
            "ip_address", "user_agent", "language", "input_size", "input_text" ,"processing_time"
        ])

scheduler = CommitScheduler(
    repo_id=DATASET_REPO_ID,
    repo_type="dataset",
    folder_path=LOG_DIR,
    path_in_repo="logs",
    every=TIME,
    token=HF_TOKEN
)

def log_interaction(request, module_name, action, input_data=None, execution_time=0.0):
    try:
        if request:
            headers = request.headers
            ip = headers.get("x-forwarded-for", request.client.host)
            user_agent = headers.get("user-agent", "Unknown")
            language = headers.get("accept-language", "Unknown").split(',')[0]
        else:
            ip, user_agent, language = "LOCAL", "Dev-Mode", "it"

        session_raw = f"{ip}{user_agent}{datetime.now().date()}"
        session_id = str(uuid.uuid5(uuid.NAMESPACE_DNS, session_raw))[:8]

        input_meta = "0"
        input_text_content = ""

        now_italy = datetime.now(ITALY_TZ)

        if isinstance(input_data, str):
            input_meta = f"{len(input_data)} chars"
            clean_text = input_data.replace('\n', ' ').replace('\r', '')
            input_text_content = (clean_text[:1000] + '..') if len(clean_text) > 1000 else clean_text
        elif hasattr(input_data, 'shape'):
            input_meta = f"{input_data.shape}"
            input_text_content = "[IMAGE/BINARY]"
        elif input_data is not None:
            input_meta = "Binary/File"
            input_text_content = "[FILE]"

        # Scrittura Log (Append)
        with scheduler.lock:
            with open(LOG_FILE, "a", newline="", encoding="utf-8") as f:
                writer = csv.writer(f, lineterminator='\n')
                writer.writerow([
                    now_italy.isoformat(),
                    session_id,
                    module_name,
                    action,
                    ip,
                    user_agent,
                    language,
                    input_meta,
                    input_text_content, 
                    f"{execution_time:.4f}s"
                ])
        
        print(f"📝 LOG SALVATO: {module_name}")

    except Exception as e:
        print(f"❌ ERRORE LOGGING: {e}")