#!/usr/bin/env python3
"""Canonical YAML normalization used by every HA import path.

One function, one style, used everywhere data lands in the repo (see
services/home-assistant/DESIGN.md, "Canonical format"): block collections,
indent width 2, unlimited line width, sorted keys, UTF-8.
"""
import json
import sys

import yaml


class _CanonicalDumper(yaml.SafeDumper):
    pass


def _represent_none(dumper, _value):
    return dumper.represent_scalar("tag:yaml.org,2002:null", "")


_CanonicalDumper.add_representer(type(None), _represent_none)


def dump_canonical_yaml(data):
    """Render `data` as canonical YAML text."""
    return yaml.dump(
        data,
        Dumper=_CanonicalDumper,
        default_flow_style=False,
        sort_keys=True,
        allow_unicode=True,
        width=1 << 31,
        indent=2,
    )


def normalize_yaml_text(text):
    """Parse YAML text then re-dump it through the canonical formatter."""
    data = yaml.safe_load(text)
    return dump_canonical_yaml(data)


def normalize_json_text(text):
    """Parse JSON text (e.g. a `.storage/*` file) and dump as canonical YAML."""
    data = json.loads(text)
    return dump_canonical_yaml(data)


def main(argv):
    if len(argv) != 3 or argv[1] not in ("yaml", "json"):
        print("usage: normalize.py <yaml|json> <input-path>", file=sys.stderr)
        return 2
    mode, path = argv[1], argv[2]
    with open(path, "r", encoding="utf-8") as f:
        text = f.read()
    out = normalize_yaml_text(text) if mode == "yaml" else normalize_json_text(text)
    sys.stdout.write(out)
    return 0


if __name__ == "__main__":
    raise SystemExit(main(sys.argv))