#!/usr/bin/env python3
"""capacity-scan.py — deterministic capacity facts for /capacity-review.

Python standard library only. Emits a JSON object to stdout.

Reads physical capacities and workload allocations from the machine-readable
tables in docs/hardware/reference.md, computes per-node allocated-vs-physical
rollups, and cross-checks workload hostnames against `terraform output -json`
and `ansible-inventory --list` to surface drift. Degrades gracefully when
nothing is provisioned. Live usage stats are a documented future hook.

Usage: python3 scripts/capacity-scan.py [--env staging] [--reference PATH]
"""
import argparse
import json
import os
import subprocess
import sys

REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))


def parse_table(markdown, required_cols):
    """Return row dicts for the first markdown table whose header contains all
    required_cols. Keys are header names; values are raw cell strings.
    Rows whose cell count does not match the header are skipped."""
    lines = markdown.splitlines()
    required = set(required_cols)
    for i, raw in enumerate(lines):
        line = raw.strip()
        if not line.startswith("|"):
            continue
        headers = [c.strip() for c in line.strip("|").split("|")]
        if not required.issubset(set(headers)):
            continue
        rows = []
        # i + 2 skips the header's GFM separator row (|---|---|)
        for body in lines[i + 2:]:
            if not body.strip().startswith("|"):
                break
            cells = [c.strip() for c in body.strip().strip("|").split("|")]
            if len(cells) == len(headers):
                rows.append(dict(zip(headers, cells)))
        return rows
    return []