Update backend with high-quality catalog and fixes

app/api/seed.py

@@ -48,59 +48,59 @@ SUB_ICONS = {
     "نظارات شمسية": "🕶️",
 }
 
-# Robust Category Hierarchy (Extra.com Style)
+# Robust Category Hierarchy (Optimized for Extra.com Dataset)
 CATEGORY_HIERARCHY = {
     "الأجهزة الإلكترونية": {
         "name_en": "Electronics & Mobiles",
         "icon": "📱",
         "subs": [
-            {"en": "Electronics", "ar": "الهواتف والإلكترونيات"},
             {"en": "Smartphones", "ar": "جوالات"},
             {"en": "Laptops", "ar": "أجهزة الكمبيوتر"},
+            {"en": "Tablets", "ar": "أجهزة لوحية"},
+            {"en": "Audio", "ar": "أجهزة الصوت"},
         ]
     },
     "ملحقات واكسسوارات": {
-        "name_en": "Accessories & Gaming",
-        "icon": "🚗",
+        "name_en": "Accessories & Gadgets",
+        "icon": "🔌",
         "subs": [
-            {"en": "Accessories", "ar": "اكسسوارات الأجهزة"},
-            {"en": "Gaming", "ar": "ألعاب إلكترونية"},
-            {"en": "Security Cameras", "ar": "كاميرات مراقبة"},
-            {"en": "Car Accessories", "ar": "ملحقات السيارات"},
+            {"en": "Accessories", "ar": "اكسسوارات"},
+            {"en": "Cables & Power", "ar": "كابلات وشواحن"},
+            {"en": "Wearables", "ar": "أجهزة قابلة للارتداء"},
+            {"en": "Security", "ar": "كاميرات وأمان"},
+            {"en": "Car Accessories", "ar": "ملحقات سيارات"},
         ]
     },
-    "الأجهزة المنزلية": {
-        "name_en": "Large Appliances",
-        "icon": "🏠",
+    "ألعاب جيمنج": {
+        "name_en": "Gaming & Entertainment",
+        "icon": "🎮",
         "subs": [
-            {"en": "Home Appliances", "ar": "المستلزمات المنزلية"},
-            {"en": "Kitchen", "ar": "المنزل والمطبخ"},
+            {"en": "Gaming Console", "ar": "أجهزة ألعاب"},
+            {"en": "Gaming Accessories", "ar": "ملحقات ألعاب"},
+            {"en": "Toys", "ar": "ألعاب أطفال"},
         ]
     },
-    "تصنيفات أخرى": {
-        "name_en": "Other Categories",
-        "icon": "✨",
+    "الأجهزة المنزلية": {
+        "name_en": "Home & Kitchen Appliances",
+        "icon": "🏠",
         "subs": [
-            {"en": "Beauty", "ar": "العطور والتجميل"},
-            {"en": "Watches", "ar": "الساعات والإكسسوارات"},
+            {"en": "Large Appliances", "ar": "أجهزة منزلية كبيرة"},
+            {"en": "Small Appliances", "ar": "أجهزة منزلية صغيرة"},
+            {"en": "Kitchenware", "ar": "أدوات المطبخ"},
+            {"en": "Personal Care", "ar": "عناية شخصية"},
         ]
     }
 }
 
-# Map scraped category strings (EN/AR) to target subcategories
-# Format: { "scraped_name": "target_ar_name" }
 SCRAPED_TO_TARGET_MAP = {
-    "Electronics": "الهواتف والإلكترونيات",
-    "Smartphones": "جوالات",
+    "Electronics": "Smartphones",
+    "Smartphones": "Smartphones",
     "Laptops": "أجهزة الكمبيوتر",
-    "Home Appliances": "المستلزمات المنزلية",
-    "Accessories": "اكسسوارات الأجهزة",
-    "Gaming": "ألعاب إلكترونية",
-    "Security Cameras": "كاميرات مراقبة",
-    "Car Accessories": "ملحقات السيارات",
-    "Perfumes": "العطور والتجميل",
-    "Fashion": "الساعات والإكسسوارات",
-    "Beauty": "العطور والتجميل",
+    "Home Appliances": "أجهزة منزلية كبيرة",
+    "Accessories": "اكسسوارات",
+    "Gaming": "أجهزة ألعاب",
+    "Security": "كاميرات وأمان",
+    "Car": "ملحقات سيارات",
 }
 
 @router.api_route("", methods=["GET", "POST"], response_model=AuthResponse)
@@ -165,13 +165,13 @@ async def seed_database(clear: bool = False, db: Session = Depends(get_db)):
             all_sub_cats[s["en"]] = sub_cat # Map both names to the same object
 
 
-    # Search for real_products_200.json in multiple likely locations
+    # Search for real_products_200.json or the full extra_products_vortex.json
     possible_paths = [
+        os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), "kaggle", "extra_products_vortex.json"),
         os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), "backend", "real_products_200.json"),
-        os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), "real_products_200.json"),
+        os.path.abspath("kaggle/extra_products_vortex.json"),
         os.path.abspath("real_products_200.json"),
-        os.path.abspath("backend/real_products_200.json"),
-        "/app/real_products_200.json",
+        "/app/kaggle/extra_products_vortex.json",
     ]
     
     json_path = None
@@ -230,10 +230,16 @@ async def seed_database(clear: bool = False, db: Session = Depends(get_db)):
                 KEYWORD_MAP = {
                     "جوالات": ["iphone", "galaxy", "phone", "mobile", "pixel", "هاتف", "جوال"],
                     "أجهزة الكمبيوتر": ["laptop", "macbook", "notebook", "pc", "computer", "لابتوب", "حاسوب"],
-                    "ألعاب إلكترونية": ["game", "playstation", "xbox", "nintendo", "controller", "ألعاب", "بلايستيشن"],
-                    "المستلزمات المنزلية": ["vacuum", "cleaner", "iron", "washer", "مكنسة", "غسالة", "مكواة"],
-                    "ملحقات السيارات": ["car", "dashcam", "charger", "سيارة", "شاحن"],
-                    "العطور والتجميل": ["perfume", "beauty", "cream", "عطر", "تجميل", "كريم"]
+                    "أجهزة لوحية": ["ipad", "tablet", "tab", "لوحي"],
+                    "أجهزة الصوت": ["headphone", "earbud", "speaker", "audio", "سماعة", "مكبر صوت"],
+                    "أجهزة ألعاب": ["playstation", "xbox", "nintendo", "console", "بلايستيشن", "إكس بوكس"],
+                    "ملحقات ألعاب": ["controller", "joystick", "gaming mouse", "gaming keyboard", "يد تحكم"],
+                    "ألعاب أطفال": ["lego", "toy", "doll", "لعبة"],
+                    "ملحقات سيارات": ["dashcam", "car charger", "car holder", "سيارة"],
+                    "أدوات المطبخ": ["air fryer", "blender", "coffee", "mixer", "قلاية", "خلاط"],
+                    "عناية شخصية": ["shaver", "hair", "brush", "عناية", "حلاقة"],
+                    "أجهزة منزلية كبيرة": ["fridge", "dryer", "washer", "غسالة", "ثلاجة"],
+                    "أجهزة منزلية صغيرة": ["vacuum", "cleaner", "iron", "مكنسة", "مكواة"]
                 }
                 
                 for target, keywords in KEYWORD_MAP.items():