foxhunt/services/backtesting_service/tests/test_data_helpers.rs

//! Test Data Helpers for Real DBN Data
//!
//! Provides reusable fixtures for backtesting unit tests using real DBN market data.
//! This module ensures tests remain fast (<100ms) while using production-quality data.

use anyhow::Result;
use backtesting_service::dbn_data_source::DbnDataSource;
use backtesting_service::strategy_engine::{BacktestTrade, MarketData, TradeSide};
use chrono::{DateTime, Duration, Utc};
use num_traits::ToPrimitive;
use rust_decimal::Decimal;
use std::collections::HashMap;
use std::sync::Arc;
use tokio::sync::OnceCell;

/// Cached DBN data source (loaded once per test run)
static DBN_DATA_SOURCE: OnceCell<Arc<DbnDataSource>> = OnceCell::const_new();

/// Cached market data (loaded once per test run)
static CACHED_ES_BARS: OnceCell<Arc<Vec<MarketData>>> = OnceCell::const_new();

/// Get absolute path to the test DBN file
///
/// Resolves the path from the project root, handling different working directories.
pub fn get_dbn_test_file_path() -> String {
    // Try to find project root by looking for Cargo.toml
    let mut current = std::env::current_dir().expect("INVARIANT: Current directory should be accessible");

    // If we're in a subdirectory, go up until we find the workspace root
    while !current.join("Cargo.toml").exists() || !current.join("test_data").exists() {
        if !current.pop() {
            // Fallback to relative path if we can't find root
            return "../../test_data/real/databento/ES.FUT_ohlcv-1m_2024-01-02.dbn".to_string();
        }
    }

    current
        .join("test_data/real/databento/ES.FUT_ohlcv-1m_2024-01-02.dbn")
        .to_string_lossy()
        .to_string()
}

/// Get or create the shared DBN data source (singleton pattern)
pub async fn get_dbn_data_source() -> Result<Arc<DbnDataSource>> {
    DBN_DATA_SOURCE
        .get_or_try_init(|| async {
            let mut file_mapping = HashMap::new();
            file_mapping.insert("ES.FUT".to_string(), get_dbn_test_file_path());

            let data_source = DbnDataSource::new(file_mapping).await?;
            Ok(Arc::new(data_source))
        })
        .await
        .map(|arc| arc.clone())
}

/// Get cached ES.FUT bars (loaded once per test run for performance)
///
/// **Performance**: First call ~5-10ms, subsequent calls ~0.1μs
pub async fn get_cached_es_bars() -> Result<Arc<Vec<MarketData>>> {
    CACHED_ES_BARS
        .get_or_try_init(|| async {
            let data_source = get_dbn_data_source().await?;
            let bars = data_source.load_ohlcv_bars("ES.FUT").await?;
            Ok(Arc::new(bars))
        })
        .await
        .map(|arc| arc.clone())
}

/// Get a small sample of real market data (fast, for unit tests)
///
/// Returns the first N bars from the cached DBN data.
///
/// # Arguments
///
/// * `num_bars` - Number of bars to return (default: 50)
///
/// # Returns
///
/// Vec of MarketData with real ES.FUT prices
///
/// # Performance
///
/// ~1μs (data already cached)
pub async fn get_sample_real_data(num_bars: usize) -> Result<Vec<MarketData>> {
    let all_bars = get_cached_es_bars().await?;
    let sample_size = num_bars.min(all_bars.len());
    Ok(all_bars[0..sample_size].to_vec())
}

/// Get real market data for a specific time window
///
/// # Arguments
///
/// * `start_offset_minutes` - Minutes from first bar (0 = first bar)
/// * `duration_minutes` - Duration window in minutes
///
/// # Returns
///
/// Vec of MarketData within the time window
pub async fn get_time_window_data(
    start_offset_minutes: i64,
    duration_minutes: i64,
) -> Result<Vec<MarketData>> {
    let all_bars = get_cached_es_bars().await?;

    if all_bars.is_empty() {
        return Ok(Vec::new());
    }

    let first_timestamp = all_bars[0].timestamp;
    let start_time = first_timestamp + Duration::minutes(start_offset_minutes);
    let end_time = start_time + Duration::minutes(duration_minutes);

    let filtered: Vec<MarketData> = all_bars
        .iter()
        .filter(|bar| bar.timestamp >= start_time && bar.timestamp <= end_time)
        .cloned()
        .collect();

    Ok(filtered)
}

/// Convert real market data to BacktestTrade (for metrics tests)
///
/// Simulates a buy-and-sell trade based on actual price movements.
///
/// # Arguments
///
/// * `entry_bar` - Market data for entry
/// * `exit_bar` - Market data for exit
/// * `quantity` - Position size
/// * `trade_id` - Unique trade identifier
///
/// # Returns
///
/// BacktestTrade with real PnL calculations
pub fn create_trade_from_bars(
    entry_bar: &MarketData,
    exit_bar: &MarketData,
    quantity: f64,
    trade_id: u32,
) -> BacktestTrade {
    let entry_price = entry_bar.close;
    let exit_price = exit_bar.close;

    let entry_f64 = entry_price.to_f64().unwrap_or(0.0);
    let exit_f64 = exit_price.to_f64().unwrap_or(0.0);

    let pnl = (exit_f64 - entry_f64) * quantity;
    let return_percent = pnl / (entry_f64 * quantity);

    BacktestTrade {
        trade_id: format!("real_trade_{}", trade_id),
        symbol: entry_bar.symbol.clone(),
        side: TradeSide::Buy,
        quantity: Decimal::from_f64_retain(quantity).unwrap_or(Decimal::ZERO),
        entry_price,
        exit_price,
        entry_time: entry_bar.timestamp,
        exit_time: exit_bar.timestamp,
        pnl: Decimal::from_f64_retain(pnl).unwrap_or(Decimal::ZERO),
        return_percent: Decimal::from_f64_retain(return_percent).unwrap_or(Decimal::ZERO),
        entry_signal: "real_data_buy".to_string(),
        exit_signal: "real_data_sell".to_string(),
    }
}

/// Generate multiple trades from real data windows
///
/// Creates trades by pairing consecutive bars (buy bar N, sell bar N+1).
///
/// # Arguments
///
/// * `num_trades` - Number of trades to generate
///
/// # Returns
///
/// Vec of BacktestTrade with real price movements
pub async fn generate_real_trades(num_trades: usize) -> Result<Vec<BacktestTrade>> {
    let bars = get_sample_real_data(num_trades * 2).await?;

    let mut trades = Vec::new();
    for i in 0..num_trades.min(bars.len() / 2) {
        let entry_bar = &bars[i * 2];
        let exit_bar = &bars[i * 2 + 1];

        let trade = create_trade_from_bars(entry_bar, exit_bar, 1.0, i as u32);
        trades.push(trade);
    }

    Ok(trades)
}

/// Create a mixed trade sequence (wins and losses from real data)
///
/// Samples bars with varying price movements to create realistic win/loss patterns.
///
/// # Returns
///
/// Vec of BacktestTrade with realistic PnL distribution
pub async fn generate_mixed_trades() -> Result<Vec<BacktestTrade>> {
    let bars = get_sample_real_data(100).await?;

    if bars.len() < 20 {
        return Ok(Vec::new());
    }

    let mut trades = Vec::new();

    // Strategy: Sample bars at specific intervals to get price variation
    // Every 5 bars creates different price movements (wins and losses)
    for i in 0..10 {
        let entry_idx = i * 5;
        let exit_idx = (i * 5 + 3).min(bars.len() - 1);

        if exit_idx >= bars.len() {
            break;
        }

        let entry_bar = &bars[entry_idx];
        let exit_bar = &bars[exit_idx];

        let trade = create_trade_from_bars(entry_bar, exit_bar, 1.0, i as u32);
        trades.push(trade);
    }

    Ok(trades)
}

/// Get real Sharpe ratio expected range from actual data
///
/// Analyzes real data to provide realistic expectation bounds for tests.
///
/// # Returns
///
/// (min_sharpe, max_sharpe) - Expected Sharpe ratio range for ES.FUT data
pub async fn get_real_sharpe_range() -> Result<(f64, f64)> {
    // ES.FUT intraday 1-minute data typically shows:
    // - Low Sharpe: -1.0 to 0.5 (choppy markets)
    // - High Sharpe: 0.5 to 2.0 (trending moves)
    // - Extreme: 2.0+ (strong directional moves)

    Ok((-1.0, 3.0)) // Conservative range for test assertions
}

/// Get real drawdown expected range from actual data
///
/// # Returns
///
/// (min_drawdown_pct, max_drawdown_pct) - Expected drawdown range
pub async fn get_real_drawdown_range() -> Result<(f64, f64)> {
    // ES.FUT intraday typically:
    // - Small drawdown: 0.5% - 2%
    // - Medium drawdown: 2% - 5%
    // - Large drawdown: 5% - 15%

    Ok((0.0, 20.0)) // Conservative range for test assertions
}

/// Get realistic volatility range from actual data
///
/// # Returns
///
/// (min_volatility_pct, max_volatility_pct) - Expected annualized volatility
pub async fn get_real_volatility_range() -> Result<(f64, f64)> {
    // ES.FUT intraday 1-minute bars:
    // - Annualized volatility typically 15% - 35%
    // - Can spike to 50%+ during extreme events

    Ok((0.0, 100.0)) // Very conservative for test robustness
}

#[cfg(test)]
mod tests {
    use super::*;

    #[tokio::test]
    async fn test_load_cached_data() -> Result<()> {
        let bars = get_cached_es_bars().await?;
        assert!(!bars.is_empty(), "Should load real DBN data");
        assert!(bars.len() > 300, "ES.FUT 2024-01-02 should have ~390 bars");
        Ok(())
    }

    #[tokio::test]
    async fn test_sample_data() -> Result<()> {
        let sample = get_sample_real_data(50).await?;
        assert_eq!(sample.len(), 50, "Should return requested sample size");
        assert_eq!(sample[0].symbol, "ES.FUT");
        Ok(())
    }

    #[tokio::test]
    async fn test_time_window_data() -> Result<()> {
        let window = get_time_window_data(0, 60).await?;
        assert!(!window.is_empty(), "Should have data in first hour");

        // Validate timestamp ordering
        for i in 1..window.len() {
            assert!(window[i].timestamp >= window[i - 1].timestamp);
        }
        Ok(())
    }

    #[tokio::test]
    async fn test_generate_real_trades() -> Result<()> {
        let trades = generate_real_trades(10).await?;
        assert_eq!(trades.len(), 10, "Should generate requested trades");

        // Validate trade structure
        for trade in &trades {
            assert_eq!(trade.symbol, "ES.FUT");
            assert!(trade.exit_time > trade.entry_time);
        }
        Ok(())
    }

    #[tokio::test]
    async fn test_mixed_trades() -> Result<()> {
        let trades = generate_mixed_trades().await?;
        assert!(!trades.is_empty(), "Should generate mixed trades");

        // Should have both wins and losses
        let wins = trades.iter().filter(|t| t.pnl > Decimal::ZERO).count();
        let losses = trades.iter().filter(|t| t.pnl < Decimal::ZERO).count();

        // Real data should have variation (not all wins or all losses)
        assert!(wins > 0 || losses > 0, "Should have some PnL variation");
        Ok(())
    }
}

/// Create a simple trade for testing (with explicit parameters)
///
/// This is a simplified helper for unit tests that need to create trades
/// without loading real DBN data.
///
/// # Arguments
///
/// * `trade_id` - Unique trade identifier
/// * `symbol` - Trading symbol
/// * `side` - Trade side (Buy/Sell)
/// * `quantity` - Position size
/// * `entry_price` - Entry price
/// * `exit_price` - Exit price
/// * `entry_time` - Entry timestamp (days from now)
/// * `exit_time` - Exit timestamp (days from now)
///
/// # Returns
///
/// BacktestTrade with calculated PnL
pub fn create_trade(
    trade_id: u32,
    symbol: &str,
    side: TradeSide,
    quantity: f64,
    entry_price: f64,
    exit_price: f64,
    entry_time: i64,
    exit_time: i64,
) -> BacktestTrade {
    let pnl = match side {
        TradeSide::Buy => (exit_price - entry_price) * quantity,
        TradeSide::Sell => (entry_price - exit_price) * quantity,
    };
    let return_percent = pnl / (entry_price * quantity);

    let now = Utc::now();
    let entry_timestamp = now - Duration::days(entry_time);
    let exit_timestamp = now - Duration::days(exit_time);

    BacktestTrade {
        trade_id: format!("test_trade_{}", trade_id),
        symbol: symbol.to_string(),
        side,
        quantity: Decimal::from_f64_retain(quantity).unwrap_or(Decimal::ZERO),
        entry_price: Decimal::from_f64_retain(entry_price).unwrap_or(Decimal::ZERO),
        exit_price: Decimal::from_f64_retain(exit_price).unwrap_or(Decimal::ZERO),
        entry_time: entry_timestamp,
        exit_time: exit_timestamp,
        pnl: Decimal::from_f64_retain(pnl).unwrap_or(Decimal::ZERO),
        return_percent: Decimal::from_f64_retain(return_percent).unwrap_or(Decimal::ZERO),
        entry_signal: "test_entry".to_string(),
        exit_signal: "test_exit".to_string(),
    }
}