Initial commit: digital reception monorepo (M1-M11 + demo extensions)

2026-05-25 12:59:54 +05:00
commit b9f88194d9
182 changed files with 20578 additions and 0 deletions
@@ -0,0 +1,77 @@
+"""Pytest-фикстуры для face-service.
+
+Подключение к локальному pgvector через DATABASE_URL из корневого .env.
+Тесты re-id логики работают на чистых эмбеддингах — модель InsightFace не нужна.
+"""
+import os
+import sys
+import uuid
+from pathlib import Path
+
+import pytest
+from dotenv import load_dotenv
+
+# Подгружаем корневой .env и .env сервиса.
+load_dotenv(Path(__file__).parent.parent / ".env")
+load_dotenv(Path(__file__).parent.parent.parent.parent / ".env")
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+# Импортируем после load_dotenv, чтобы DATABASE_URL подцепился.
+from database import get_connection  # noqa: E402
+
+
+@pytest.fixture
+def db_conn():
+    conn = get_connection()
+    yield conn
+    conn.close()
+
+
+@pytest.fixture
+def seed_camera_and_track(db_conn):
+    """Создаёт уникальные camera_id + track_id для теста и убирает после."""
+    camera_ids = []
+    track_ids = []
+
+    def _make(zone_code: str = "A"):
+        cam_id = str(uuid.uuid4())
+        zone_id = str(uuid.uuid4())
+        track_id = str(uuid.uuid4())
+        with db_conn.cursor() as cur:
+            cur.execute(
+                "INSERT INTO zones (id, code, name) VALUES (%s, %s::\"ZoneCode\", %s)"
+                " ON CONFLICT (code) DO NOTHING RETURNING id",
+                (zone_id, zone_code, f"test-zone-{zone_code}"),
+            )
+            row = cur.fetchone()
+            if row is None:
+                cur.execute('SELECT id FROM zones WHERE code = %s::"ZoneCode"', (zone_code,))
+                zone_id = str(cur.fetchone()[0])
+            cur.execute(
+                "INSERT INTO cameras (id, name, zone_id) VALUES (%s, %s, %s)",
+                (cam_id, f"test-cam-{cam_id[:6]}", zone_id),
+            )
+            cur.execute(
+                "INSERT INTO tracks (id, status, first_seen_at, last_seen_at, updated_at)"
+                " VALUES (%s, 'UNMATCHED', NOW(), NOW(), NOW())",
+                (track_id,),
+            )
+        db_conn.commit()
+        camera_ids.append(cam_id)
+        track_ids.append(track_id)
+        return cam_id, track_id
+
+    yield _make
+
+    # Cleanup
+    with db_conn.cursor() as cur:
+        if track_ids:
+            cur.execute(
+                "DELETE FROM face_embeddings WHERE track_id = ANY(%s::uuid[])",
+                (track_ids,),
+            )
+            cur.execute("DELETE FROM tracks WHERE id = ANY(%s::uuid[])", (track_ids,))
+        if camera_ids:
+            cur.execute("DELETE FROM cameras WHERE id = ANY(%s::uuid[])", (camera_ids,))
+    db_conn.commit()
@@ -0,0 +1,124 @@
+"""Тесты cross-camera re-id логики.
+
+Используем синтетические 512-мерные эмбеддинги (без InsightFace).
+Проверяем, что find_topk_in_window:
+  1. Возвращает соседей в правильном порядке по cos-дистанции.
+  2. Фильтрует по camera_id (исключает ту же камеру).
+  3. Фильтрует по временному окну.
+"""
+from datetime import datetime, timedelta
+
+import numpy as np
+import pytest
+
+from database import (
+    save_embedding_with_meta,
+    find_topk_in_window,
+    find_nearest_patient,
+    attach_track_to_patient,
+    delete_patient_embeddings,
+)
+
+
+def normed(vec: np.ndarray) -> np.ndarray:
+    return (vec / np.linalg.norm(vec)).astype(np.float32)
+
+
+def make_embedding(seed: int) -> np.ndarray:
+    rng = np.random.default_rng(seed)
+    return normed(rng.standard_normal(512))
+
+
+def test_topk_in_window_basic(seed_camera_and_track):
+    """Из 3 эмбеддингов на 3 разных камерах находим 2 ближайших к query (исключая саму камеру query)."""
+    cam_a, track_a = seed_camera_and_track("A")
+    cam_b, track_b = seed_camera_and_track("B")
+    cam_c, track_c = seed_camera_and_track("C")
+
+    base = make_embedding(seed=42)
+
+    # Соседи: tweak base слегка для cam_b, сильнее для cam_c.
+    near = normed(base + 0.05 * make_embedding(seed=43))
+    far = normed(base + 0.5 * make_embedding(seed=44))
+
+    save_embedding_with_meta(base, track_a, cam_a, quality=0.9, captured_at=datetime.utcnow())
+    save_embedding_with_meta(near, track_b, cam_b, quality=0.9, captured_at=datetime.utcnow())
+    save_embedding_with_meta(far, track_c, cam_c, quality=0.9, captured_at=datetime.utcnow())
+
+    # Запрос с cam_a — должен вернуть cam_b раньше cam_c, cam_a исключаем.
+    results = find_topk_in_window(
+        embedding=base.tolist(),
+        camera_id=cam_a,
+        window_minutes=5,
+        k=5,
+        exclude_same_camera=True,
+    )
+
+    cam_ids_in_results = [r["camera_id"] for r in results]
+    assert cam_a not in cam_ids_in_results
+    assert cam_b in cam_ids_in_results
+    assert cam_c in cam_ids_in_results
+    # Порядок: ближе → дальше
+    assert results[0]["camera_id"] == cam_b
+    assert results[0]["distance"] < results[-1]["distance"]
+
+
+def test_topk_filters_by_window(seed_camera_and_track):
+    """Старый эмбеддинг (вне окна) не должен попадать в результат."""
+    cam_a, track_a = seed_camera_and_track("A")
+    cam_b, track_b = seed_camera_and_track("B")
+
+    base = make_embedding(seed=7)
+
+    save_embedding_with_meta(
+        base, track_b, cam_b, quality=0.9,
+        captured_at=datetime.utcnow() - timedelta(hours=1),  # вне окна 5 мин
+    )
+
+    results = find_topk_in_window(
+        embedding=base.tolist(),
+        camera_id=cam_a,
+        window_minutes=5,
+        k=5,
+    )
+
+    cam_ids = [r["camera_id"] for r in results]
+    assert cam_b not in cam_ids
+
+
+def test_find_nearest_patient_only_consented(db_conn, seed_camera_and_track):
+    """find_nearest_patient ищет только среди эмбеддингов с patient_id IS NOT NULL."""
+    cam_a, track_a = seed_camera_and_track("A")
+    base = make_embedding(seed=100)
+
+    # Сохраняем эмбеддинг без patient_id.
+    save_embedding_with_meta(base, track_a, cam_a, quality=0.9)
+
+    # Ищем — никого не должно найти.
+    assert find_nearest_patient(base.tolist(), threshold=0.5) is None
+
+    # Создаём пациента и привязываем трек.
+    import uuid
+    patient_id = str(uuid.uuid4())
+    with db_conn.cursor() as cur:
+        cur.execute(
+            "INSERT INTO patients (id, full_name, updated_at) VALUES (%s, %s, NOW())",
+            (patient_id, "Тестовый Пациент"),
+        )
+    db_conn.commit()
+
+    affected = attach_track_to_patient(track_a, patient_id)
+    assert affected == 1
+
+    # Теперь должны найти.
+    result = find_nearest_patient(base.tolist(), threshold=0.5)
+    assert result is not None
+    assert result["patient_id"] == patient_id
+    assert result["distance"] < 0.01  # тот же эмбеддинг
+
+    # Очистка.
+    deleted = delete_patient_embeddings(patient_id)
+    assert deleted == 1
+    with db_conn.cursor() as cur:
+        cur.execute("DELETE FROM patients WHERE id = %s", (patient_id,))
+    db_conn.commit()