"""docs/sources-egress.yaml stays valid for sand-boxer and in step with the prose allowlist."""
from pathlib import Path
import re
import unittest

import yaml

ROOT = Path(__file__).resolve().parent.parent
EGRESS = ROOT / 'docs' / 'sources-egress.yaml'
ALLOWLIST = ROOT / 'docs' / 'sources-allowlist.md'
# sand-boxer bwrap-egress: exact lowercase DNS name, port 443, no wildcard or IP literal.
HOST = re.compile(r'^(?=.{1,253}:443$)([a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z]{2,63}:443$')
MAX_HOSTS = 24  # every host is a whole-host trust decision; raise only deliberately


class SourcesEgressTests(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        cls.doc = yaml.safe_load(EGRESS.read_text(encoding='utf-8'))
        cls.hosts = cls.doc['hosts']
        cls.prose = ALLOWLIST.read_text(encoding='utf-8')

    def test_version(self):
        self.assertEqual(self.doc['version'], 1)

    def test_host_format(self):
        for entry in self.hosts:
            self.assertRegex(entry['host'], HOST)

    def test_no_duplicates_and_bounded(self):
        names = [e['host'] for e in self.hosts]
        self.assertEqual(len(names), len(set(names)))
        self.assertLessEqual(len(names), MAX_HOSTS)

    def test_entries_complete(self):
        for entry in self.hosts:
            self.assertEqual(set(entry), {'host', 'axes', 'channel', 'why'}, entry['host'])
            self.assertTrue(entry['why'].strip(), entry['host'])
            self.assertTrue(set(entry['axes']) <= set('ABCD'), entry['host'])

    def test_every_axis_covered(self):
        covered = {axis for e in self.hosts for axis in e['axes']}
        self.assertEqual(covered, set('ABCD'))

    def test_channel_named_in_prose_allowlist(self):
        for entry in self.hosts:
            self.assertIn(entry['channel'], self.prose, entry['host'])


if __name__ == '__main__':
    unittest.main()