Update backend with high-quality catalog and fixes

app/api/seed.py

@@ -17,60 +17,35 @@ from app.services.external_catalog import ExternalCatalogService
 
 router = APIRouter(prefix="/seed", tags=["Seed Data"])
 
-# Mapping distinct categories from Excel to a hierarchical structure
+# Syncing with High-Quality Catalog Categories
 CATEGORY_MAP = {
-    # Parents (Keys) : Subcategories (Values)
-    "الأزياء": ["الملابس الرجالية", "الملابس النسائية"],
-    "الأحذية والحقائب": ["الأحذية", "الحقائب"],
-    "الأطفال والألعاب": ["الأطفال"],
-    "المنزل والمطبخ": ["المنزل والمطبخ", "المستلزمات المنزلية", "مستلزمات المطبخ", "ديكور المنزل", "الأثاث", "الإضاءة"],
-    "العطور والتجميل": ["العطور", "التجميل والعناية", "الجمال", "العناية بالبشرة"],
     "الأجهزة الإلكترونية": ["الهواتف والإلكترونيات", "الهواتف الذكية", "أجهزة الكمبيوتر"],
+    "ملحقات السيارات": ["ملحقات السيارات", "إكسسوارات السيارات"],
+    "المنزل والمطبخ": ["المنزل والمطبخ", "المستلزمات المنزلية", "مستلزمات المطبخ", "ديكور المنزل", "الأثاث"],
+    "العطور والتجميل": ["العطور", "التجميل والعناية", "الجمال", "العناية بالبشرة"],
     "الساعات والإكسسوارات": ["الساعات والاكسسوارات", "ساعات نسائية", "ساعات رجالية", "نظارات شمسية"],
     "الرياضة واللياقة": ["الرياضة واللياقة", "إكسسوارات رياضية"],
-    "ملحقات السيارات": ["ملحقات السيارات", "إكسسوارات السيارات", "إكسسوارات الدراجات"],
-}
-
-# Emoji icons for frontend display
-PARENT_ICONS = {
-    "الأزياء": "👗", "الأحذية والحقائب": "👟", "الأطفال والألعاب": "🧸",
-    "المنزل والمطبخ": "🏠", "العطور والتجميل": "✨", "الأجهزة الإلكترونية": "📱",
-    "الساعات والإكسسوارات": "⌚", "الرياضة واللياقة": "🏋️",
-}
-SUB_ICONS = {
-    "الملابس الرجالية": "👔", "الملابس النسائية": "👗", "الأحذية": "👟",
-    "الحقائب": "👜", "الأطفال": "🧸", "المنزل والمطبخ": "🏠",
-    "المستلزمات المنزلية": "🧹", "العطور": "🌸", "التجميل والعناية": "💄",
-    "الهواتف والإلكترونيات": "📱", "الساعات والاكسسوارات": "⌚",
-    "الرياضة واللياقة": "🏋️", "مستلزمات المطبخ": "🍳", "ديكور المنزل": "🪑",
-    "الأثاث": "🛋️", "الإضاءة": "💡", "الجمال": "💅", "العناية بالبشرة": "🧴",
-    "الهواتف الذكية": "📱", "أجهزة الكمبيوتر": "💻", "ساعات نسائية": "⌚",
-    "ساعات رجالية": "⌚", "نظارات شمسية": "🕶️", "إكسسوارات رياضية": "🏃",
-    "إكسسوارات السيارات": "🚗", "إكسسوارات الدراجات": "🏍️",
 }
 
 @router.api_route("", methods=["GET", "POST"], response_model=AuthResponse)
 async def seed_database(clear: bool = False, db: Session = Depends(get_db)):
     """Populate database with proper product data, optionally clearing existing data first."""
     if clear:
-        # Clear existing data using raw SQL to avoid materialization errors if enums changed
+        # Clear existing data
         db.execute(text("DELETE FROM product_images"))
         db.execute(text("DELETE FROM products"))
         db.execute(text("DELETE FROM categories"))
         db.execute(text("DELETE FROM coupons"))
-        # Optional: clear users if you want a fresh start, or just fix the admin
-        db.execute(text("UPDATE users SET role = 'ADMIN' WHERE role = 'admin'")) # Fix legacy enums
+        db.execute(text("UPDATE users SET role = 'ADMIN' WHERE role = 'admin'"))
         
-        # Patch schema: add specs column if missing (SQLite doesn't support IF NOT EXISTS in ALTER)
         try:
             db.execute(text("ALTER TABLE products ADD COLUMN specs JSON"))
         except Exception:
-            pass # Already exists or other issue
+            pass
             
         db.commit()
 
     # Always ensure admin user exists
-    # Use raw SQL to check for admin to avoid LookupError if data is inconsistent
     admin_exists = db.execute(text("SELECT id FROM users WHERE email = 'admin@vortex.com'")).fetchone()
     if not admin_exists:
         admin_user = User(
@@ -83,16 +58,6 @@ async def seed_database(clear: bool = False, db: Session = Depends(get_db)):
         db.add(admin_user)
         db.commit()
 
-    # Check if products are already seeded (Skip if clearing)
-    if not clear:
-        existing = db.query(Category).count()
-        if existing > 0:
-            return AuthResponse(
-                isSuccess=True,
-                value={"message": "Database already has data. Admin user ensured."},
-                statusCode=200,
-            )
-
     json_path = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), "backend", "real_products_1000.json")
     if not os.path.exists(json_path):
         json_path = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), "real_products_1000.json")
@@ -141,38 +106,50 @@ async def seed_database(clear: bool = False, db: Session = Depends(get_db)):
                     db.refresh(sub_cat)
                 sub_cats[sub_name] = {"model": sub_cat, "parent_name": parent_name}
 
+        # Cache existing products to prevent duplicates when clear=False
+        existing_products_ar = set(r[0] for r in db.execute(text("SELECT name_ar FROM products")).fetchall())
+        existing_products_en = set(r[0] for r in db.execute(text("SELECT name_en FROM products")).fetchall())
+
         # 3. Create Products
         inserted_count = 0
-        used_names = set() # Avoid absolute name duplicates in current seed run
+        skipped_count = 0
         
         for item in products_data:
-            # Handle both formats (real_products_500.json vs products_dump.json)
-            cat_name = item.get("category_name") or item.get("الفئة")
+            cat_name = item.get("category_name")
             if not cat_name or cat_name not in sub_cats:
-                continue
+                # Automatic fallback mapping for consistency
+                if not cat_name: continue
+                # Try to find best match
+                matched = False
+                for sub, info in sub_cats.items():
+                    if cat_name in sub or sub in cat_name:
+                        cat_name = sub
+                        matched = True
+                        break
+                if not matched: continue
+            
+            product_name_ar = item.get("name_ar", "").strip()
+            product_name_en = item.get("name_en", "").strip()
             
-            product_name_ar = item.get("name_ar") or item.get("اسم المنتج", "").strip()
-            if not product_name_ar or product_name_ar in used_names:
+            # Smart Duplicate Prevention: Skip if name already exists in DB
+            if product_name_ar in existing_products_ar or product_name_en in existing_products_en:
+                skipped_count += 1
                 continue
             
             sub_cat_info = sub_cats[cat_name]
-            used_names.add(product_name_ar)
-            
-            price = float(item.get("price") or item.get("سعر البيع (ريال)", 0))
-            compare_price = float(item.get("compare_price") or (price * 1.2))
             
             prod = Product(
                 name_ar=product_name_ar,
-                name_en=item.get("name_en") or product_name_ar,
-                description_ar=item.get("description_ar") or item.get("الوصف التسويقي", ""),
-                description_en=item.get("description_en") or item.get("الوصف التسويقي", ""),
-                price=price,
-                compare_price=round(compare_price, 2),
-                stock=item.get("stock") or random.randint(10, 100),
+                name_en=product_name_en,
+                description_ar=item.get("description_ar", ""),
+                description_en=item.get("description_en", ""),
+                price=float(item.get("price", 0)),
+                compare_price=round(float(item.get("compare_price", price * 1.2)), 2),
+                stock=item.get("stock", random.randint(10, 100)),
                 category_id=sub_cat_info["model"].id,
-                rating=round(random.uniform(3.5, 5.0), 1),
-                rating_count=random.randint(0, 50),
-                is_featured=item.get("is_featured", random.choice([True, False])),
+                rating=item.get("rating", 4.5),
+                rating_count=item.get("rating_count", 20),
+                is_featured=item.get("is_featured", False),
                 is_active=item.get("is_active", True),
                 specs=item.get("specs", {})
             )
@@ -180,38 +157,32 @@ async def seed_database(clear: bool = False, db: Session = Depends(get_db)):
             db.flush()
             
             # 4. Handle Images
-            raw_images = item.get("images", [])
-            for i, img_url in enumerate(raw_images):
-                prod_img = ProductImage(
+            for i, img_url in enumerate(item.get("images", [])):
+                db.add(ProductImage(
                     product_id=prod.id,
                     image_url=img_url,
                     alt_text=prod.name_ar,
                     sort_order=i
-                )
-                db.add(prod_img)
+                ))
             
             inserted_count += 1
+            existing_products_ar.add(product_name_ar)
+            existing_products_en.add(product_name_en)
 
-        # Seed Coupons
-        DEMO_COUPONS = [
-            {"code": "WELCOME10", "discount_percent": 10.0, "is_active": True},
-            {"code": "VORTEX20", "discount_percent": 20.0, "is_active": True},
-            {"code": "SUMMER50", "discount_percent": 50.0, "is_active": False},
-        ]
-
-        for coupon_data in DEMO_COUPONS:
-            coupon = Coupon(**coupon_data)
-            db.add(coupon)
+        # Ensure Demo Coupons
+        for code, discount in [("WELCOME10", 10.0), ("VORTEX20", 20.0)]:
+            if not db.query(Coupon).filter(Coupon.code == code).first():
+                db.add(Coupon(code=code, discount_percent=discount, is_active=True))
 
         db.commit()
 
         return AuthResponse(
             isSuccess=True,
             value={
-                "message": "تم تهيئة قاعدة البيانات بالمنتجات الحقيقية بنجاح",
-                "categories_count": db.query(Category).count(),
-                "total_products": inserted_count,
-                "coupons_count": len(DEMO_COUPONS),
+                "message": "تمت عملية المزامنة بنجاح" if not clear else "تمت تهيئة قاعدة البيانات بنجاح",
+                "total_products": db.query(Product).count(),
+                "inserted_new": inserted_count,
+                "skipped_duplicates": skipped_count,
             },
             statusCode=201,
         )

seed_products.py

@@ -2,6 +2,7 @@ import json
 import random
 import sys
 import os
+from sqlalchemy import text
 from sqlalchemy.orm import Session
 from app.db.base import SessionLocal, engine, Base
 from app.models.product import Product, Category, ProductImage
@@ -60,18 +61,35 @@ def seed_database(clear=False):
                     db.refresh(sub_cat)
                 cat_cache[parent_name] = sub_cat.id
 
+        # Cache existing products for duplicate check
+        existing_names = set(n[0] for n in db.execute(text("SELECT name_en FROM products")).fetchall())
+        existing_names.update(n[0] for n in db.execute(text("SELECT name_ar FROM products")).fetchall())
+
         # 2. Insert Products
         print("Feeding database with Saudi trends...")
         inserted = 0
+        skipped = 0
         for item in products_data:
+            name_en = item.get("name_en")
+            name_ar = item.get("name_ar")
+            
+            if name_en in existing_names or name_ar in existing_names:
+                skipped += 1
+                continue
+
             cat_id = cat_cache.get(item.get("category_name"))
             if not cat_id:
-                # Fallback to first available if category mismatch
-                cat_id = list(cat_cache.values())[0]
+                # Try to match subcategories
+                matched_id = None
+                for cat_name, cid in cat_cache.items():
+                    if item.get("category_name") in cat_name:
+                        matched_id = cid
+                        break
+                cat_id = matched_id or list(cat_cache.values())[0]
 
             prod = Product(
-                name_ar=item.get("name_ar"),
-                name_en=item.get("name_en"),
+                name_ar=name_ar,
+                name_en=name_en,
                 description_ar=item.get("description_ar"),
                 description_en=item.get("description_en"),
                 price=item.get("price"),
@@ -82,7 +100,7 @@ def seed_database(clear=False):
                 category_id=cat_id,
                 is_featured=item.get("is_featured", False),
                 is_active=True,
-                specs=item.get("specs") # New: Save embedded variants and specs
+                specs=item.get("specs")
             )
             db.add(prod)
             db.flush()
@@ -97,11 +115,17 @@ def seed_database(clear=False):
                 ))
             
             inserted += 1
+            existing_names.add(name_en)
+            existing_names.add(name_ar)
+            
             if inserted % 100 == 0:
-                print(f"  -> Progress: {inserted}/1000")
+                print(f"  -> Progress: {inserted} added, {skipped} skipped")
 
         db.commit()
-        print(f"\n[SUCCESS] Seeding complete! {inserted} items in database.")
+        print(f"\n[SUCCESS] Seeding complete!")
+        print(f"  -> Total New: {inserted}")
+        print(f"  -> Skipped Duplicates: {skipped}")
+        print(f"  -> Current DB Count: {db.query(Product).count()}")
 
     except Exception as e:
         db.rollback()