Initial Aurora Core 0.1 implementation

Production-grade media metadata backend per docs/aurora-core-spec.md: Aurora-owned UUIDv7 identity system, normalized movie/TV/people/credits schema, provider abstraction with a TMDb adapter, an idempotent async ingestion pipeline (normalize -> match -> upsert -> provenance), a Postgres FTS/trigram search layer, a stateless FastAPI v1 API with Redis caching/rate-limiting, arq workers, dev/prod Docker Compose topologies, unit + integration + load tests, CI, and architecture/ database/API/ERD documentation. Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-09-04 17:34:03 -05:00
commit c20df1c503
111 changed files with 10041 additions and 0 deletions
@@ -0,0 +1,73 @@
+"""Unit tests for the Aurora ID system (app/core/ids.py) — section 3."""
+
+from __future__ import annotations
+
+import pytest
+
+from app.core.ids import (
+    ENTITY_PREFIXES,
+    aurora_id,
+    is_valid_aurora_id,
+    new_uuid7,
+    parse_aurora_id,
+)
+
+
+def test_new_uuid7_is_unique_and_well_formed():
+    ids = {new_uuid7() for _ in range(1000)}
+    assert len(ids) == 1000
+    for value in list(ids)[:5]:
+        assert len(value) == 36  # canonical hyphenated form
+
+
+def test_aurora_id_roundtrips_through_parse():
+    u = new_uuid7()
+    aid = aurora_id("movie", u)
+    assert aid.startswith("aur_movie_")
+    assert parse_aurora_id(aid, expected_type="movie") == u
+
+
+def test_aurora_id_never_leaks_provider_identity():
+    # Aurora IDs must not be derived from or embed provider IDs (section 3).
+    u = new_uuid7()
+    aid = aurora_id("movie", u)
+    assert "550" not in aid  # a plausible TMDb id, just shouldn't appear
+    assert "tmdb" not in aid
+
+
+def test_every_entity_prefix_produces_a_parseable_id():
+    for entity_type in ENTITY_PREFIXES:
+        aid = aurora_id(entity_type, new_uuid7())
+        assert is_valid_aurora_id(aid, expected_type=entity_type)
+
+
+def test_parse_rejects_wrong_entity_type():
+    aid = aurora_id("movie", new_uuid7())
+    with pytest.raises(ValueError):
+        parse_aurora_id(aid, expected_type="person")
+    assert is_valid_aurora_id(aid, expected_type="person") is False
+
+
+@pytest.mark.parametrize(
+    "malformed",
+    [
+        "",
+        "not-an-aurora-id",
+        "aur_movie_",
+        "aur_movie_tooshort",
+        "aur_unknownprefix_" + "0" * 26,
+        "aur_movie_" + "!" * 26,
+    ],
+)
+def test_parse_rejects_malformed_ids(malformed: str):
+    with pytest.raises(ValueError):
+        parse_aurora_id(malformed)
+    assert is_valid_aurora_id(malformed) is False
+
+
+def test_aurora_ids_sort_in_creation_order():
+    # UUIDv7 is time-ordered, and the Crockford base32 encoding preserves
+    # byte order, so IDs generated later should sort later.
+    first = aurora_id("movie", new_uuid7())
+    second = aurora_id("movie", new_uuid7())
+    assert first < second