Roster slugs through Home Assistant's real slugify (P2 fix)

The per-child entity ids are derived from the child name by Home
Assistant's real slugifier, which transliterates every script through
unidecode; the hand-rolled Latin-only mirror in sensor.py dropped
non-Latin characters instead (slugging 京子 to "unknown"), so the
roster's slugs diverged from the actual entity ids and the
party-board/strategy auto-discovery silently failed for non-Latin
households.

Use homeassistant.util.slugify at runtime, composing the registry's
64-character entity-id cap the roster needs (verified against HA
2024.6: slugify itself does not truncate; the entity registry
truncates the full <domain>.<slug> id). Give the mock harness a
faithful homeassistant.util.slugify stub — python-slugify's frozen
legacy pipeline with unidecode, verified byte-for-byte against real
python-slugify across Latin, Cyrillic, CJK and Greek name shapes —
and cover the non-Latin resolution contract in tests (roster slug ==
the object id HA's entity-id derivation produces).

Feature-review finding (P2): auto-discovery slug must match Home
Assistant's real slugify.
This commit is contained in:
2026-09-23 12:12:58 -04:00
parent 0354db82ce
commit 2f055f4065
5 changed files with 151 additions and 23 deletions
+68
View File
@@ -24,16 +24,20 @@ from __future__ import annotations
import asyncio
import importlib.util
import inspect
import re
import sys
import tempfile
import unicodedata
import weakref
from dataclasses import dataclass
from html.entities import name2codepoint
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock
import httpx
import pytest
from unidecode import unidecode as _unidecode
from tests.admin_jwt_harness import ADMIN_KEY, KID, AdminRunner, jwks_for
@@ -46,6 +50,7 @@ _HA_MODULES = (
"homeassistant.config_entries",
"homeassistant.data_entry_flow",
"homeassistant.exceptions",
"homeassistant.util",
"homeassistant.helpers",
"homeassistant.helpers.config_validation",
"homeassistant.helpers.entity",
@@ -94,6 +99,7 @@ for _parent, _child in (
("homeassistant", "data_entry_flow"),
("homeassistant", "core"),
("homeassistant", "exceptions"),
("homeassistant", "util"),
("homeassistant", "helpers"),
("homeassistant.helpers", "config_validation"),
("homeassistant.helpers", "entity"),
@@ -218,6 +224,68 @@ _exceptions_mock.ConfigEntryNotReady = ConfigEntryNotReady
_exceptions_mock.Unauthorized = Unauthorized
# ---------------------------------------------------------------------------
# homeassistant.util.slugify: a faithful stand-in for the real slugifier.
#
# Real HA (2024.6) wraps python-slugify's frozen legacy pipeline and answers
# its "unknown" sentinel when a non-empty name slugs to nothing. The stub
# mirrors that pipeline step for step — quotes to dashes, NFKD-normalize,
# TRANSLITERATE through unidecode (the backend python-slugify's "auto" mode
# prefers, and a dev dependency here), decode HTML entities, NFKD again,
# lowercase, drop quotes, fold runs of non-[a-z0-9-] to one dash, collapse
# and strip dashes, then map dashes to the requested separator — and was
# verified byte-for-byte against real python-slugify across Latin, Cyrillic,
# CJK and Greek household-name shapes. Transliteration is the point: HA
# derives the per-child entity ids from a name like "京子" as
# "nestquest_jing_zi_…", so the roster's slugs must transliterate too,
# never dropping characters into "unknown". Deliberately NOT truncating:
# real slugify caps nothing; the entity registry truncates the full
# entity_id instead.
# ---------------------------------------------------------------------------
_HA_QUOTE_PATTERN = re.compile(r"[']+")
_HA_CHAR_ENTITY_PATTERN = re.compile(r"&(%s);" % "|".join(name2codepoint))
_HA_DECIMAL_PATTERN = re.compile(r"&#(\d+);")
_HA_HEX_PATTERN = re.compile(r"&#x([\da-fA-F]+);")
_HA_NUMBERS_PATTERN = re.compile(r"(?<=\d),(?=\d)")
_HA_DISALLOWED_CHARS_PATTERN = re.compile(r"[^-a-zA-Z0-9]+")
_HA_DUPLICATE_DASH_PATTERN = re.compile(r"-{2,}")
def _ha_slugify(text: str | None, *, separator: str = "_") -> str:
"""Faithful homeassistant.util.slugify stand-in (see section above)."""
if text == "" or text is None:
return ""
text = str(text)
text = _HA_QUOTE_PATTERN.sub("-", text)
text = unicodedata.normalize("NFKD", text)
text = _unidecode(text)
text = _HA_CHAR_ENTITY_PATTERN.sub(
lambda match: chr(name2codepoint[match.group(1)]), text
)
try:
text = _HA_DECIMAL_PATTERN.sub(
lambda match: chr(int(match.group(1))), text
)
except (ValueError, OverflowError):
pass
try:
text = _HA_HEX_PATTERN.sub(
lambda match: chr(int(match.group(1), 16)), text
)
except (ValueError, OverflowError):
pass
text = unicodedata.normalize("NFKD", text)
text = text.lower()
text = _HA_QUOTE_PATTERN.sub("", text)
text = _HA_NUMBERS_PATTERN.sub("", text)
text = _HA_DISALLOWED_CHARS_PATTERN.sub("-", text)
text = _HA_DUPLICATE_DASH_PATTERN.sub("-", text).strip("-")
return "unknown" if text == "" else text.replace("-", separator)
_ha_mock("homeassistant.util").slugify = _ha_slugify
@dataclass
class DeviceInfo:
"""Stand-in for homeassistant.helpers.entity.DeviceInfo.