"""Sample container CPU and memory during a sizing run.

WHY: the sizing table claims specific vCPU and RAM figures. Those can only be
confirmed by watching the container under load, not by reasoning about greenlet
size. This records peak RSS and CPU so a claimed "4 GB is enough" is either
demonstrated or falsified.

Runs on the HOST (needs the docker CLI), unlike the generators.

Usage:
    python sample_resources.py --container shopdb-sizing-api --seconds 120
"""
import argparse
import json
import re
import statistics
import subprocess
import time


def parse_size(text):
    """Docker stats prints like '1.234GiB' / '512MiB'. Return megabytes."""
    match = re.match(r'^([0-9.]+)\s*([KMGT]?i?B)$', text.strip())
    if not match:
        return 0.0
    value = float(match.group(1))
    unit = match.group(2).upper().replace('I', '')
    factors = {'B': 1.0 / (1024 * 1024), 'KB': 1.0 / 1024, 'MB': 1.0,
               'GB': 1024.0, 'TB': 1024.0 * 1024.0}
    return value * factors.get(unit, 1.0)


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--container', required=True)
    parser.add_argument('--seconds', type=int, default=120)
    parser.add_argument('--interval', type=float, default=2.0)
    arguments = parser.parse_args()

    cpu_samples = []
    memory_samples = []
    deadline = time.monotonic() + arguments.seconds

    while time.monotonic() < deadline:
        try:
            output = subprocess.check_output(
                ['docker', 'stats', '--no-stream', '--format',
                 '{{.CPUPerc}}|{{.MemUsage}}', arguments.container],
                stderr=subprocess.DEVNULL, text=True).strip()
        except subprocess.CalledProcessError:
            break
        if not output:
            break
        cpu_text, memory_text = output.split('|', 1)
        cpu_samples.append(float(cpu_text.replace('%', '').strip()))
        used = memory_text.split('/')[0]
        memory_samples.append(parse_size(used))
        time.sleep(arguments.interval)

    def summarize(values):
        if not values:
            return {'samples': 0}
        ordered = sorted(values)
        index = min(int(len(ordered) * 0.95), len(ordered) - 1)
        return {
            'samples': len(values),
            'median': round(statistics.median(values), 1),
            'p95': round(ordered[index], 1),
            'max': round(max(values), 1),
        }

    print(json.dumps({
        'container': arguments.container,
        'cpu_percent': summarize(cpu_samples),
        'memory_mb': summarize(memory_samples),
    }, indent=2))


if __name__ == '__main__':
    main()