Bug Fix: Inconsistent Field Naming - avatar vs imageUrl (#89)

vrajpatelll · pre-commit-ci[bot] · Devasy · web-flow · commit e3d170a3693a · 2025-07-29T21:30:01.000+05:30
* fix(services): fix mismatch between imageUrl and avatar * feat(migration-script): add migration, rollback and backup script * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix(review): address coderabbit review comments * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Devasy Patel <110348311+Devasy23@users.noreply.github.com>
diff --git a/backend/app/auth/schemas.py b/backend/app/auth/schemas.py
@@ -42,7 +42,7 @@ class UserResponse(BaseModel):
     id: str = Field(alias="_id")
     email: str
     name: str
-    avatar: Optional[str] = None
+    imageUrl: Optional[str] = None
     currency: str = "USD"
     created_at: datetime
 
diff --git a/backend/app/auth/service.py b/backend/app/auth/service.py
@@ -115,7 +115,7 @@ async def create_user_with_email(
             "email": email,
             "hashed_password": get_password_hash(password),
             "name": name,
-            "avatar": None,
+            "imageUrl": None,
             "currency": "USD",
             "created_at": datetime.now(timezone.utc),
             "auth_provider": "email",
@@ -202,8 +202,8 @@ async def authenticate_with_google(self, id_token: str) -> Dict[str, Any]:
                 update_data = {}
                 if user.get("firebase_uid") != firebase_uid:
                     update_data["firebase_uid"] = firebase_uid
-                if user.get("avatar") != picture and picture:
-                    update_data["avatar"] = picture
+                if user.get("imageUrl") != picture and picture:
+                    update_data["imageUrl"] = picture
 
                 if update_data:
                     await db.users.update_one(
@@ -215,7 +215,7 @@ async def authenticate_with_google(self, id_token: str) -> Dict[str, Any]:
                 user_doc = {
                     "email": email,
                     "name": name,
-                    "avatar": picture,
+                    "imageUrl": picture,
                     "currency": "USD",
                     "created_at": datetime.now(timezone.utc),
                     "auth_provider": "google",
diff --git a/backend/app/groups/service.py b/backend/app/groups/service.py
@@ -54,17 +54,13 @@ async def _enrich_members_with_user_details(
                                     if user
                                     else f"{member_user_id}@example.com"
                                 ),
-                                "avatar": (
-                                    user.get("imageUrl") or user.get("avatar")
-                                    if user
-                                    else None
-                                ),
+                                "imageUrl": (user.get("imageUrl") if user else None),
                             }
                             if user
                             else {
                                 "name": f"User {member_user_id[-4:]}",
                                 "email": f"{member_user_id}@example.com",
-                                "avatar": None,
+                                "imageUrl": None,
                             }
                         ),
                     }
@@ -79,7 +75,7 @@ async def _enrich_members_with_user_details(
                             "user": {
                                 "name": f"User {member_user_id[-4:]}",
                                 "email": f"{member_user_id}@example.com",
-                                "avatar": None,
+                                "imageUrl": None,
                             },
                         }
                     )
diff --git a/backend/app/user/service.py b/backend/app/user/service.py
@@ -41,7 +41,7 @@ def iso(dt):
             "id": user_id,
             "name": user.get("name"),
             "email": user.get("email"),
-            "imageUrl": user.get("imageUrl") or user.get("avatar"),
+            "imageUrl": user.get("imageUrl"),
             "currency": user.get("currency", "USD"),
             "createdAt": iso(user.get("created_at")),
             "updatedAt": iso(user.get("updated_at") or user.get("created_at")),
diff --git a/backend/scripts/backup_db.py b/backend/scripts/backup_db.py
@@ -0,0 +1,81 @@
+"""
+Database backup script for Splitwiser.
+Creates a backup of all collections before performing migrations.
+"""
+
+import json
+import os
+from datetime import datetime
+
+from dotenv import load_dotenv
+from pymongo import MongoClient
+
+# Get the script's directory and backend directory
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+BACKEND_DIR = os.path.dirname(SCRIPT_DIR)
+
+# Load environment variables from .env file in backend directory
+load_dotenv(os.path.join(BACKEND_DIR, ".env"))
+
+# Get MongoDB connection details from environment
+MONGODB_URL = os.getenv("MONGODB_URL")
+DATABASE_NAME = os.getenv("DATABASE_NAME")
+
+
+def create_backup():
+    """Create a backup of all collections."""
+    try:
+        # Create backup directory if it doesn't exist
+        backup_dir = "backups"
+        backup_time = datetime.now().strftime("%Y%m%d_%H%M%S")
+        backup_path = os.path.join(backup_dir, f"backup_{backup_time}")
+        os.makedirs(backup_path, exist_ok=True)
+
+        # Connect to MongoDB
+        client = MongoClient(MONGODB_URL)
+        db = client[DATABASE_NAME]
+
+        # Get all collections
+        collections = db.list_collection_names()
+        backup_stats = {}
+
+        for collection_name in collections:
+            collection = db[collection_name]
+            documents = list(collection.find({}))
+
+            # Convert ObjectId to string for JSON serialization
+            for doc in documents:
+                doc["_id"] = str(doc["_id"])
+
+            # Save to file
+            backup_file = os.path.join(backup_path, f"{collection_name}.json")
+            with open(backup_file, "w") as f:
+                json.dump(documents, f, indent=2, default=str)
+
+            backup_stats[collection_name] = len(documents)
+
+        # Save backup metadata
+        metadata = {
+            "timestamp": datetime.now().isoformat(),
+            "database": DATABASE_NAME,
+            "collections": backup_stats,
+            "total_documents": sum(backup_stats.values()),
+        }
+
+        with open(os.path.join(backup_path, "backup_metadata.json"), "w") as f:
+            json.dump(metadata, f, indent=2)
+
+        return backup_path, metadata
+
+    except Exception as e:
+        print(f"Backup failed: {str(e)}")
+        raise
+
+
+if __name__ == "__main__":
+    backup_path, metadata = create_backup()
+    print(f"Backup created successfully at: {backup_path}")
+    print("\nBackup statistics:")
+    print(f"Total documents: {metadata['total_documents']}")
+    for coll, count in metadata["collections"].items():
+        print(f"{coll}: {count} documents")
diff --git a/backend/scripts/migrate_avatar_to_imageurl.py b/backend/scripts/migrate_avatar_to_imageurl.py
@@ -0,0 +1,167 @@
+"""
+Migration script to standardize user avatar fields to imageUrl.
+This script:
+1. Identifies users with avatar field but no imageUrl field
+2. Copies avatar values to imageUrl field
+3. Removes the deprecated avatar field
+4. Logs migration statistics
+"""
+
+import json
+import logging
+import os
+import sys
+from datetime import datetime
+
+from backup_db import create_backup
+from bson import ObjectId
+from dotenv import load_dotenv
+from pymongo import MongoClient, UpdateOne
+
+# Add the script's directory to Python path
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(SCRIPT_DIR)
+
+
+# Load environment variables from the backend directory
+BACKEND_DIR = os.path.dirname(SCRIPT_DIR)
+load_dotenv(os.path.join(BACKEND_DIR, ".env"))
+
+# Get MongoDB connection details from environment
+MONGODB_URL = os.getenv("MONGODB_URL")
+DATABASE_NAME = os.getenv("DATABASE_NAME")
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Set up file logging
+log_dir = "logs"
+os.makedirs(log_dir, exist_ok=True)
+log_file = os.path.join(
+    log_dir, f"migration_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log"
+)
+file_handler = logging.FileHandler(log_file)
+file_handler.setFormatter(
+    logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
+)
+logger.addHandler(file_handler)
+
+# Validate required environment variables
+if not MONGODB_URL:
+    logger.error("MONGODB_URL environment variable is required")
+    sys.exit(1)
+if not DATABASE_NAME:
+    logger.error("DATABASE_NAME environment variable is required")
+    sys.exit(1)
+
+
+def migrate_avatar_to_imageurl():
+    """
+    Migrate avatar field to imageUrl in users collection.
+    Returns statistics about the migration.
+    """
+    try:
+        # First create a backup
+        logger.info("Creating database backup...")
+        backup_path, backup_metadata = create_backup()
+        logger.info(f"Backup created at: {backup_path}")
+
+        # Connect to MongoDB
+        client = MongoClient(MONGODB_URL)
+        db = client[DATABASE_NAME]
+        users = db.users
+
+        # Find users with avatar field
+        users_with_avatar = users.find({"avatar": {"$exists": True}})
+        users_to_update = []
+        stats = {
+            "total_users": users.count_documents({}),
+            "users_with_avatar": 0,
+            "users_with_both_fields": 0,
+            "users_updated": 0,
+            "conflicts": 0,
+        }
+
+        for user in users_with_avatar:
+            stats["users_with_avatar"] += 1
+
+            # Check for conflicts (users with both fields)
+            if "imageUrl" in user and user["imageUrl"] is not None:
+                if user["imageUrl"] != user["avatar"]:
+                    logger.warning(
+                        f"Conflict found for user {user['_id']}: "
+                        f"avatar='{user['avatar']}', imageUrl='{user['imageUrl']}'"
+                    )
+                    stats["conflicts"] += 1
+                    continue
+                stats["users_with_both_fields"] += 1
+
+            # Prepare update
+            users_to_update.append(
+                UpdateOne(
+                    {"_id": user["_id"]},
+                    {"$set": {"imageUrl": user["avatar"]}, "$unset": {
+                        "avatar": ""}},
+                )
+            )
+
+        # Perform bulk update if there are users to update
+        if users_to_update:
+            result = users.bulk_write(users_to_update)
+            stats["users_updated"] = result.modified_count
+            logger.info(f"Successfully updated {result.modified_count} users")
+
+        return stats
+
+    except Exception as e:
+        logger.error(f"Migration failed: {str(e)}")
+        raise
+
+
+def rollback_migration(backup_path):
+    """
+    Rollback the migration using a specified backup.
+    """
+    try:
+        client = MongoClient(MONGODB_URL)
+        db = client[DATABASE_NAME]
+
+        backup_file_path = os.path.join(backup_path, "users.json")
+        if not os.path.exists(backup_file_path):
+            raise FileNotFoundError(
+                f"Backup file not found: {backup_file_path}")
+
+        # Read users collection backup
+        with open(backup_file_path, "r") as f:
+            users_backup = json.load(f)
+
+        # Convert string IDs back to ObjectId
+        for user in users_backup:
+            user["_id"] = ObjectId(user["_id"])
+
+        # Replace current users collection with backup
+        db.users.drop()
+        if users_backup:
+            db.users.insert_many(users_backup)
+
+        logger.info(f"Successfully rolled back to backup: {backup_path}")
+        return True
+
+    except Exception as e:
+        logger.error(f"Rollback failed: {str(e)}")
+        raise
+
+
+if __name__ == "__main__":
+    logger.info("Starting avatar to imageUrl migration...")
+    stats = migrate_avatar_to_imageurl()
+
+    logger.info("\nMigration completed. Statistics:")
+    logger.info(f"Total users: {stats['total_users']}")
+    logger.info(f"Users with avatar field: {stats['users_with_avatar']}")
+    logger.info(f"Users with both fields: {stats['users_with_both_fields']}")
+    logger.info(f"Users updated: {stats['users_updated']}")
+    logger.info(f"Conflicts found: {stats['conflicts']}")
+
+    print("\nMigration completed. Check the log file for details:", log_file)
diff --git a/backend/tests/auth/test_auth_routes.py b/backend/tests/auth/test_auth_routes.py
@@ -168,7 +168,7 @@ async def test_login_with_email_success(mock_db):
             "email": user_email,
             "hashed_password": hashed_password,
             "name": "Login User",
-            "avatar": None,
+            "imageUrl": None,
             "currency": "USD",
             # Ensure datetime is used
             "created_at": datetime.now(timezone.utc),

Original file line number	Diff line number	Diff line change
`@@ -54,17 +54,13 @@ async def _enrich_members_with_user_details(`
`54`	`54`	`if user`
`55`	`55`	`else f"{member_user_id}@example.com"`
`56`	`56`	`),`
`57`		`- "avatar": (`
`58`		`- user.get("imageUrl") or user.get("avatar")`
`59`		`- if user`
`60`		`- else None`
`61`		`- ),`
	`57`	`+ "imageUrl": (user.get("imageUrl") if user else None),`
`62`	`58`	`}`
`63`	`59`	`if user`
`64`	`60`	`else {`
`65`	`61`	`"name": f"User {member_user_id[-4:]}",`
`66`	`62`	`"email": f"{member_user_id}@example.com",`
`67`		`- "avatar": None,`
	`63`	`+ "imageUrl": None,`
`68`	`64`	`}`
`69`	`65`	`),`
`70`	`66`	`}`
`@@ -79,7 +75,7 @@ async def _enrich_members_with_user_details(`
`79`	`75`	`"user": {`
`80`	`76`	`"name": f"User {member_user_id[-4:]}",`
`81`	`77`	`"email": f"{member_user_id}@example.com",`
`82`		`- "avatar": None,`
	`78`	`+ "imageUrl": None,`
`83`	`79`	`},`
`84`	`80`	`}`
`85`	`81`	`)`