#!/usr/bin/env python3
"""
Calculate percentiles (p50/p90/p99/p999) from epoch soak CSV data.
"""

import sys
import csv
import statistics

def percentile(data, p):
    """Calculate percentile p (0-100) from sorted data."""
    n = len(data)
    if n == 0:
        return 0
    k = (n - 1) * p / 100.0
    f = int(k)
    c = int(k) + 1
    if c >= n:
        return data[-1]
    d0 = data[f]
    d1 = data[c]
    return d0 + (d1 - d0) * (k - f)

def calculate_percentiles(csv_file):
    """Calculate percentiles from CSV file containing throughput data."""
    throughputs = []

    with open(csv_file, 'r') as f:
        reader = csv.DictReader(f)
        for row in reader:
            throughput = float(row['throughput_ops_s'])
            throughputs.append(throughput)

    if not throughputs:
        print(f"Error: No data found in {csv_file}", file=sys.stderr)
        return None

    throughputs_sorted = sorted(throughputs)

    # Calculate percentiles
    p50 = percentile(throughputs_sorted, 50)
    p90 = percentile(throughputs_sorted, 90)
    p99 = percentile(throughputs_sorted, 99)
    p999 = percentile(throughputs_sorted, 99.9)

    # Calculate latency proxy (1/throughput in nanoseconds)
    # throughput is in ops/sec, so 1/throughput gives sec/op
    # multiply by 1e9 to get ns/op
    latencies = [1e9 / t for t in throughputs]
    latencies_sorted = sorted(latencies)
    lat_p50 = percentile(latencies_sorted, 50)
    lat_p90 = percentile(latencies_sorted, 90)
    lat_p99 = percentile(latencies_sorted, 99)
    lat_p999 = percentile(latencies_sorted, 99.9)

    return {
        'throughput': {
            'p50': p50,
            'p90': p90,
            'p99': p99,
            'p999': p999,
            'mean': statistics.mean(throughputs),
            'min': min(throughputs),
            'max': max(throughputs),
            'std': statistics.stdev(throughputs) if len(throughputs) > 1 else 0,
        },
        'latency_ns': {
            'p50': lat_p50,
            'p90': lat_p90,
            'p99': lat_p99,
            'p999': lat_p999,
            'mean': statistics.mean(latencies),
            'min': min(latencies),
            'max': max(latencies),
            'std': statistics.stdev(latencies) if len(latencies) > 1 else 0,
        }
    }

def format_number(n, decimals=2):
    """Format number with commas and fixed decimals."""
    return f"{n:,.{decimals}f}"

def main():
    if len(sys.argv) != 2:
        print("Usage: calculate_percentiles.py <csv_file>")
        sys.exit(1)

    csv_file = sys.argv[1]
    results = calculate_percentiles(csv_file)

    if results is None:
        sys.exit(1)

    print(f"Results for: {csv_file}")
    print("\n=== Throughput (ops/sec) ===")
    print(f"  p50:  {format_number(results['throughput']['p50'], 0)}")
    print(f"  p90:  {format_number(results['throughput']['p90'], 0)}")
    print(f"  p99:  {format_number(results['throughput']['p99'], 0)}")
    print(f"  p999: {format_number(results['throughput']['p999'], 0)}")
    print(f"  mean: {format_number(results['throughput']['mean'], 0)}")
    print(f"  std:  {format_number(results['throughput']['std'], 0)}")
    print(f"  min:  {format_number(results['throughput']['min'], 0)}")
    print(f"  max:  {format_number(results['throughput']['max'], 0)}")

    print("\n=== Latency Proxy (ns/op) ===")
    print(f"  p50:  {format_number(results['latency_ns']['p50'], 2)}")
    print(f"  p90:  {format_number(results['latency_ns']['p90'], 2)}")
    print(f"  p99:  {format_number(results['latency_ns']['p99'], 2)}")
    print(f"  p999: {format_number(results['latency_ns']['p999'], 2)}")
    print(f"  mean: {format_number(results['latency_ns']['mean'], 2)}")
    print(f"  std:  {format_number(results['latency_ns']['std'], 2)}")
    print(f"  min:  {format_number(results['latency_ns']['min'], 2)}")
    print(f"  max:  {format_number(results['latency_ns']['max'], 2)}")

if __name__ == '__main__':
    main()