Auto-discovery slug must match Home Assistant's real slugify (P2 fix) (#181)

tests/conftest.py

@@ -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.

tests/test_sensors.py

@@ -12,6 +12,7 @@ from __future__ import annotations
 import datetime
 
 import pytest
+from homeassistant.util import slugify
 
 from conftest import StubSnapshotClient, set_coordinator_client, wire_entry_to_registry
 
@@ -637,8 +638,9 @@ async def test_empty_household_publishes_an_empty_roster(
 
 
 def test_slugify_mirrors_home_assistant_entity_id_derivation() -> None:
-    """The slug mirror matches homeassistant.util.slugify for the names
-    children are registered with (verified against HA's own slugify)."""
+    """The roster slugs match homeassistant.util.slugify — the real
+    slugifier HA derives entity ids from, composed with the entity-id
+    length cap the entity registry applies to ``sensor.`` ids."""
     assert _slugify("Ada") == "ada"
     assert _slugify("Mary Jane") == "mary_jane"
     assert _slugify("Mary-Jane") == "mary_jane"
@@ -652,3 +654,52 @@ def test_slugify_mirrors_home_assistant_entity_id_derivation() -> None:
     # The registry caps the entity_id at 64 characters, so the slugged
     # object id alone is capped at 64 - len("sensor.").
     assert _slugify("a" * 80) == "a" * (64 - len("sensor."))
+
+
+def test_slugify_transliterates_non_latin_names_like_home_assistant() -> None:
+    """HA's slugifier transliterates every script through unidecode,
+    so a non-Latin child name slugs to its romanization — never to the
+    ``unknown`` sentinel — and the roster publishes the same slug HA's
+    entity-id derivation produces for that name."""
+    assert _slugify("Дана") == "dana"
+    assert _slugify("京子") == "jing_zi"
+    assert _slugify("Zoë") == "zoe"
+
+
+async def test_non_latin_child_names_resolve_auto_discovery(
+    hass, make_entry
+) -> None:
+    """A non-Latin child name slugs through the real slugifier, so the
+    roster slug IS the object id of the per-child sensor's entity_id
+    and the cards' auto-discovery resolves that child.
+
+    HA derives the per-child entity id from the entity NAME ("NestQuest
+    京子 quests due today") with the same slugifier the roster uses, so
+    the two must agree exactly; the reviewed mirror dropped non-Latin
+    characters (slugging "京子" to "unknown"), so the cards built
+    "sensor.nestquest_unknown_…" ids that no entity had."""
+    payload = _payload(
+        [
+            _child(ADA, "Дана", [_instance(7, ADA)]),
+            _child(BO, "京子", [_instance(8, BO)]),
+        ]
+    )
+    entry, _coordinator, _client = await _setup_entry(hass, make_entry, payload)
+    roster = hass.entities[
+        "nestquest_household_quests_due_today"
+    ].extra_state_attributes["child_roster"]
+    assert roster == [
+        {"child_id": ADA, "name": "Дана", "slug": "dana"},
+        {"child_id": BO, "name": "京子", "slug": "jing_zi"},
+    ]
+    for roster_entry in roster:
+        due_entity = _sensor(hass, roster_entry["child_id"], "quests_due_today")
+        assert due_entity.name == (
+            f"NestQuest {roster_entry['name']} quests due today"
+        )
+        # The entity id HA's registry derives for this entity (from the
+        # same slugifier) embeds exactly the slug the roster publishes:
+        # the card builds sensor.nestquest_<slug>_quests_due_today.
+        assert slugify(due_entity.name) == (
+            f"nestquest_{roster_entry['slug']}_quests_due_today"
+        )