#!/usr/bin/env python3
"""
Download Gold Futures OHLCV-1m data from Databento using timeseries API.
"""

import os
import databento as db
from databento import SType

def main():
    # Initialize client
    client = db.Historical()

    # Parameters - try continuous contract
    dataset = "GLBX.MDP3"
    # Try using continuous front month contract
    symbols = "GC.c.0"  # Continuous front month
    schema = "ohlcv-1m"
    start_date = "2024-01-02"
    end_date = "2024-01-31"
    output_path = "test_data/real/databento/GC_continuous_ohlcv-1m_2024-01-02_to_2024-01-31.dbn"

    print("=" * 80)
    print("DATABENTO GOLD FUTURES DOWNLOAD (Timeseries API)")
    print("=" * 80)
    print(f"Dataset: {dataset}")
    print(f"Symbol: {symbols}")
    print(f"Schema: {schema}")
    print(f"Date Range: {start_date} to {end_date}")
    print(f"Output: {output_path}")
    print()

    # Step 1: Estimate cost
    print("Step 1: Estimating cost...")
    try:
        cost = client.metadata.get_cost(
            dataset=dataset,
            symbols=symbols,
            schema=schema,
            start=start_date,
            end=end_date,
            stype_in=SType.CONTINUOUS,  # Use continuous symbology
        )
        print(f"Estimated cost: ${cost:.2f}")
        print()

        if cost > 1.0:
            print(f"⚠️  WARNING: Cost ${cost:.2f} exceeds $1.00 threshold!")
            response = input("Continue anyway? (yes/no): ")
            if response.lower() != 'yes':
                print("Download cancelled.")
                return 1
    except Exception as e:
        print(f"Error estimating cost: {e}")
        print("Trying download anyway...")
        print()

    # Step 2: Download using timeseries API
    print("Step 2: Downloading data...")
    try:
        # Use timeseries.get_range instead of batch API
        data = client.timeseries.get_range(
            dataset=dataset,
            symbols=symbols,
            schema=schema,
            start=start_date,
            end=end_date,
            stype_in=SType.CONTINUOUS,
        )

        # Save to file
        os.makedirs(os.path.dirname(output_path), exist_ok=True)
        data.to_file(output_path)

        # Get file size
        file_size = os.path.getsize(output_path)
        file_size_mb = file_size / (1024 * 1024)

        print(f"✅ Download complete!")
        print(f"File size: {file_size_mb:.2f} MB ({file_size:,} bytes)")
        print()

        # Step 3: Verify data quality
        print("Step 3: Verifying data quality...")
        df = data.to_df()

        record_count = len(df)
        print(f"Total records: {record_count:,}")

        if 'open' in df.columns:
            # Check for price spikes
            df['price_change_pct'] = df['close'].pct_change() * 100
            max_spike = df['price_change_pct'].abs().max()

            print(f"Max price change: {max_spike:.2f}%")

            if max_spike > 20:
                print(f"⚠️  WARNING: Price spike detected ({max_spike:.2f}%)")
            else:
                print("✅ No significant price spikes")

            # Statistics
            print()
            print("Price Statistics:")
            print(f"  Open:  ${df['open'].mean():.2f} ± ${df['open'].std():.2f}")
            print(f"  High:  ${df['high'].mean():.2f} ± ${df['high'].std():.2f}")
            print(f"  Low:   ${df['low'].mean():.2f} ± ${df['low'].std():.2f}")
            print(f"  Close: ${df['close'].mean():.2f} ± ${df['close'].std():.2f}")

            if 'volume' in df.columns:
                print(f"  Volume: {df['volume'].mean():.0f} ± {df['volume'].std():.0f}")

        print()
        print("=" * 80)
        print("DOWNLOAD SUMMARY")
        print("=" * 80)
        print(f"Status: ✅ SUCCESS")
        print(f"Output: {output_path}")
        print(f"Size: {file_size_mb:.2f} MB")
        print(f"Records: {record_count:,}")
        try:
            print(f"Cost: ${cost:.2f}")
        except:
            pass
        print("=" * 80)

    except Exception as e:
        print(f"❌ Error: {e}")
        import traceback
        traceback.print_exc()
        return 1

    return 0

if __name__ == "__main__":
    exit(main())