#!/usr/bin/env python3
"""
Convert NQ.FUT DBN file to Parquet format.

Agent: W12-08
Input: test_data/NQ_FUT_180d.dbn (Zstandard compressed)
Output: test_data/NQ_FUT_180d.parquet (Snappy compressed)
"""

import os
import sys
import databento as db
import pyarrow.parquet as pq

INPUT_FILE = "test_data/NQ_FUT_180d.dbn"
OUTPUT_FILE = "test_data/NQ_FUT_180d.parquet"

def main():
    """Convert NQ.FUT DBN to Parquet."""
    print("=" * 80)
    print("NQ.FUT DBN → Parquet Converter (Agent W12-08)")
    print("=" * 80)
    print()

    # Check input file
    if not os.path.exists(INPUT_FILE):
        print(f"❌ ERROR: Input file not found: {INPUT_FILE}")
        sys.exit(1)

    input_size = os.path.getsize(INPUT_FILE)
    print(f"📁 Input:  {INPUT_FILE} ({input_size / (1024*1024):.2f} MB)")
    print(f"📂 Output: {OUTPUT_FILE}")
    print()

    # Load DBN file
    try:
        print("⚙️  Loading DBN file...")
        store = db.DBNStore.from_file(INPUT_FILE)

        # Convert to DataFrame
        print("⚙️  Converting to DataFrame...")
        df = store.to_df()

        bar_count = len(df)
        print(f"✅ Loaded {bar_count:,} bars")
        print()

        # Show sample data
        print("📊 Data Preview:")
        print(f"  Columns: {list(df.columns)}")
        print(f"  First timestamp: {df.index[0]}")
        print(f"  Last timestamp: {df.index[-1]}")
        print(f"  Price range: ${df['close'].min():.2f} - ${df['close'].max():.2f}")
        print(f"  Total volume: {df['volume'].sum():,.0f}")
        print()

        # Convert to Parquet
        print("⚙️  Writing Parquet file...")
        df.to_parquet(OUTPUT_FILE, compression='snappy', engine='pyarrow')

        output_size = os.path.getsize(OUTPUT_FILE)
        compression_ratio = (1 - output_size / input_size) * 100

        print()
        print("=" * 80)
        print("✅ SUCCESS: Conversion complete!")
        print("=" * 80)
        print()
        print(f"📊 Conversion Results:")
        print(f"  Bar count: {bar_count:,}")
        print(f"  Input size: {input_size / (1024*1024):.2f} MB")
        print(f"  Output size: {output_size / (1024*1024):.2f} MB")
        print(f"  Compression: {compression_ratio:.1f}% smaller")
        print()
        print(f"📦 Output file ready for ML training:")
        print(f"   {OUTPUT_FILE}")
        print()

    except Exception as e:
        print()
        print(f"❌ Conversion failed: {e}")
        import traceback
        traceback.print_exc()
        sys.exit(1)


if __name__ == "__main__":
    main()