duckrun 0.2.6__tar.gz → 0.2.8.dev0__tar.gz

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.6
+Version: 0.2.8.dev0
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT
@@ -26,7 +26,8 @@ A helper package for stuff that made my life easier when working with Fabric Pyt
 
 **Requirements:**
 - Lakehouse must have a schema (e.g., `dbo`, `sales`, `analytics`)
-- **Workspace and lakehouse names with spaces are now fully supported!** ✅
+- **Workspace names with spaces are fully supported!** ✅
+
 
 **Delta Lake Version:** This package uses an older version of deltalake to maintain row size control capabilities, which is crucial for Power BI performance optimization. The newer Rust-based deltalake versions don't yet support the row group size parameters that are essential for optimal DirectLake performance.
 
@@ -47,23 +48,40 @@ pip install duckrun[local]
 
 ## Quick Start
 
+### Simple Example for New Users
+
+```python
+import duckrun
+
+# Connect to a workspace and manage lakehouses
+con = duckrun.connect('My Workspace')
+con.list_lakehouses()                           # See what lakehouses exist
+con.create_lakehouse_if_not_exists('data')      # Create if needed
+
+# Connect to a specific lakehouse and query data
+con = duckrun.connect("My Workspace/data.lakehouse/dbo")
+con.sql("SELECT * FROM my_table LIMIT 10").show()
+```
+
+### Full Feature Overview
+
 ```python
 import duckrun
 
 # 1. Workspace Management (list and create lakehouses)
 ws = duckrun.connect("My Workspace")
 lakehouses = ws.list_lakehouses()  # Returns list of lakehouse names
-ws.create_lakehouse_if_not_exists("New Lakehouse")
+ws.create_lakehouse_if_not_exists("New_Lakehouse")
 
 # 2. Connect to lakehouse with a specific schema
-con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+con = duckrun.connect("My Workspace/MyLakehouse.lakehouse/dbo")
 
-# Works with workspace names containing spaces!
-con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
+# Workspace names with spaces are supported!
+con = duckrun.connect("Data Analytics/SalesData.lakehouse/analytics")
 
 # Schema defaults to 'dbo' if not specified (scans all schemas)
 # ⚠️ WARNING: Scanning all schemas can be slow for large lakehouses!
-con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
+con = duckrun.connect("My Workspace/My_Lakehouse.lakehouse")
 
 # 3. Explore data
 con.sql("SELECT * FROM my_table LIMIT 10").show()

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/README.md

@@ -6,7 +6,8 @@ A helper package for stuff that made my life easier when working with Fabric Pyt
 
 **Requirements:**
 - Lakehouse must have a schema (e.g., `dbo`, `sales`, `analytics`)
-- **Workspace and lakehouse names with spaces are now fully supported!** ✅
+- **Workspace names with spaces are fully supported!** ✅
+
 
 **Delta Lake Version:** This package uses an older version of deltalake to maintain row size control capabilities, which is crucial for Power BI performance optimization. The newer Rust-based deltalake versions don't yet support the row group size parameters that are essential for optimal DirectLake performance.
 
@@ -27,23 +28,40 @@ pip install duckrun[local]
 
 ## Quick Start
 
+### Simple Example for New Users
+
+```python
+import duckrun
+
+# Connect to a workspace and manage lakehouses
+con = duckrun.connect('My Workspace')
+con.list_lakehouses()                           # See what lakehouses exist
+con.create_lakehouse_if_not_exists('data')      # Create if needed
+
+# Connect to a specific lakehouse and query data
+con = duckrun.connect("My Workspace/data.lakehouse/dbo")
+con.sql("SELECT * FROM my_table LIMIT 10").show()
+```
+
+### Full Feature Overview
+
 ```python
 import duckrun
 
 # 1. Workspace Management (list and create lakehouses)
 ws = duckrun.connect("My Workspace")
 lakehouses = ws.list_lakehouses()  # Returns list of lakehouse names
-ws.create_lakehouse_if_not_exists("New Lakehouse")
+ws.create_lakehouse_if_not_exists("New_Lakehouse")
 
 # 2. Connect to lakehouse with a specific schema
-con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+con = duckrun.connect("My Workspace/MyLakehouse.lakehouse/dbo")
 
-# Works with workspace names containing spaces!
-con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
+# Workspace names with spaces are supported!
+con = duckrun.connect("Data Analytics/SalesData.lakehouse/analytics")
 
 # Schema defaults to 'dbo' if not specified (scans all schemas)
 # ⚠️ WARNING: Scanning all schemas can be slow for large lakehouses!
-con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
+con = duckrun.connect("My Workspace/My_Lakehouse.lakehouse")
 
 # 3. Explore data
 con.sql("SELECT * FROM my_table LIMIT 10").show()

duckrun-0.2.8.dev0/duckrun/auth.py

@@ -0,0 +1,240 @@
+"""
+Enhanced authentication module for duckrun - supports multiple notebook environments
+"""
+import os
+from typing import Optional, Tuple
+
+
+def get_token() -> Optional[str]:
+    """
+    Smart authentication that works across multiple environments:
+    - Microsoft Fabric notebooks (uses notebookutils)
+    - Local environments with Azure CLI (uses CLI + browser fallback)
+    - Google Colab (uses device code flow) 
+    - Other headless environments (uses device code flow)
+    - Existing token from environment (uses cached token)
+    
+    Returns:
+        Azure Storage token string or None if authentication fails
+    """
+    # Check if we already have a cached token
+    token_env = os.environ.get("AZURE_STORAGE_TOKEN")
+    if token_env and token_env != "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE":
+        print("✅ Using existing Azure Storage token")
+        return token_env
+
+    print("🔐 Starting Azure authentication...")
+    
+    # Try Fabric notebook environment first
+    try:
+        import notebookutils  # type: ignore
+        print("📓 Microsoft Fabric notebook detected - using notebookutils")
+        token = notebookutils.credentials.getToken("pbi")
+        os.environ["AZURE_STORAGE_TOKEN"] = token
+        print("✅ Fabric notebook authentication successful!")
+        return token
+    except ImportError:
+        pass  # Not in Fabric notebook
+    except Exception as e:
+        print(f"⚠️ Fabric notebook authentication failed: {e}")
+
+    # Detect environment type for fallback authentication
+    try:
+        # Check if we're in Google Colab first
+        try:
+            import google.colab
+            print("🚀 Google Colab detected - using device code flow")
+            return _get_device_code_token()
+        except ImportError:
+            pass
+
+        # For all other environments (including VS Code), try Azure CLI first
+        # This includes local development, VS Code notebooks, etc.
+        print("🖥️ Local/VS Code environment detected - trying Azure CLI first, then browser fallback")
+        return _get_local_token()
+
+    except Exception as e:
+        print(f"❌ Authentication failed: {e}")
+        print("💡 Try refreshing and running again, or check your Azure permissions")
+        return None
+
+
+def _get_device_code_token() -> Optional[str]:
+    """Get token using device code flow for headless environments"""
+    try:
+        from azure.identity import DeviceCodeCredential
+        
+        # Use Azure CLI client ID for device code flow
+        credential = DeviceCodeCredential(
+            client_id="04b07795-8ddb-461a-bbee-02f9e1bf7b46",  # Azure CLI client ID
+            tenant_id="common"
+        )
+        
+        print("🔐 Follow the authentication prompts in your browser...")
+        token_obj = credential.get_token("https://storage.azure.com/.default")
+        
+        os.environ["AZURE_STORAGE_TOKEN"] = token_obj.token
+        print("✅ Device code authentication successful!")
+        return token_obj.token
+        
+    except Exception as e:
+        print(f"❌ Device code authentication failed: {e}")
+        return None
+
+
+def _get_local_token() -> Optional[str]:
+    """Get token using CLI first, then browser fallback for local environments"""
+    # First try Azure CLI directly
+    try:
+        from azure.identity import AzureCliCredential
+        print("🔐 Trying Azure CLI authentication...")
+        
+        cli_credential = AzureCliCredential()
+        token_obj = cli_credential.get_token("https://storage.azure.com/.default")
+        
+        os.environ["AZURE_STORAGE_TOKEN"] = token_obj.token
+        print("✅ Azure CLI authentication successful!")
+        return token_obj.token
+        
+    except Exception as cli_error:
+        print(f"⚠️ Azure CLI authentication failed: {cli_error}")
+        print("🔐 Falling back to interactive browser authentication...")
+        
+        # Fallback to interactive browser
+        try:
+            from azure.identity import InteractiveBrowserCredential
+            
+            browser_credential = InteractiveBrowserCredential()
+            token_obj = browser_credential.get_token("https://storage.azure.com/.default")
+            
+            os.environ["AZURE_STORAGE_TOKEN"] = token_obj.token
+            print("✅ Interactive browser authentication successful!")
+            return token_obj.token
+            
+        except Exception as browser_error:
+            print(f"❌ Interactive browser authentication failed: {browser_error}")
+            return None
+
+
+def get_fabric_api_token() -> Optional[str]:
+    """
+    Get token for Fabric API operations (different scope than storage)
+    
+    Returns:
+        Fabric API token string or None if authentication fails
+    """
+    print("🔐 Getting Fabric API token...")
+    
+    # Try Fabric notebook environment first
+    try:
+        import notebookutils  # type: ignore
+        print("📓 Microsoft Fabric notebook detected - using notebookutils")
+        token = notebookutils.credentials.getToken("pbi")
+        print("✅ Fabric API token obtained!")
+        return token
+    except ImportError:
+        pass  # Not in Fabric notebook
+    except Exception as e:
+        print(f"⚠️ Fabric notebook token failed: {e}")
+
+    # Fallback to azure-identity for external environments
+    try:
+        # Check if we're in Google Colab
+        try:
+            import google.colab
+            print("💻 Using device code flow for Fabric API (Colab)")
+            from azure.identity import DeviceCodeCredential
+            credential = DeviceCodeCredential(
+                client_id="04b07795-8ddb-461a-bbee-02f9e1bf7b46",
+                tenant_id="common"
+            )
+        except ImportError:
+            # For all other environments, try CLI first then browser
+            print("🖥️ Using CLI + browser fallback for Fabric API")
+            
+            # Try CLI first
+            try:
+                from azure.identity import AzureCliCredential
+                print("🔐 Trying Azure CLI for Fabric API...")
+                credential = AzureCliCredential()
+                token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
+                print("✅ Fabric API token obtained via Azure CLI!")
+                return token_obj.token
+            except Exception as cli_error:
+                print(f"⚠️ Azure CLI failed for Fabric API: {cli_error}")
+                print("🔐 Falling back to interactive browser for Fabric API...")
+                from azure.identity import InteractiveBrowserCredential
+                credential = InteractiveBrowserCredential()
+        
+        token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
+        print("✅ Fabric API token obtained!")
+        return token_obj.token
+        
+    except Exception as e:
+        print(f"❌ Fabric API authentication failed: {e}")
+        return None
+
+
+def authenticate_for_environment() -> Tuple[bool, Optional[str]]:
+    """
+    Main authentication entry point - detects environment and authenticates appropriately
+    
+    Returns:
+        Tuple of (success: bool, token: Optional[str])
+    """
+    print("\n🔍 Detecting execution environment...")
+    
+    # Check environment
+    try:
+        import notebookutils  # type: ignore
+        env_type = "Microsoft Fabric Notebook"
+    except ImportError:
+        try:
+            import google.colab
+            env_type = "Google Colab"
+        except ImportError:
+            # For all other environments (VS Code, local Python, etc.)
+            # we'll treat as local and try Azure CLI first
+            env_type = "Local/VS Code Environment"
+    
+    print(f"📍 Environment: {env_type}")
+    
+    token = get_token()
+    if token:
+        print(f"✅ Authentication successful for {env_type}")
+        return True, token
+    else:
+        print(f"❌ Authentication failed for {env_type}")
+        return False, None
+
+
+# For backward compatibility - expose the same interface as before
+def get_storage_token() -> str:
+    """
+    Backward compatible method - returns token or placeholder
+    """
+    token = get_token()
+    return token if token else "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE"
+
+
+# Example usage function for testing
+def test_authentication():
+    """
+    Test authentication in current environment
+    """
+    print("=" * 60)
+    print("🧪 TESTING DUCKRUN AUTHENTICATION")
+    print("=" * 60)
+    
+    success, token = authenticate_for_environment()
+    
+    if success:
+        print("\n✅ Authentication test successful!")
+        print(f"Token length: {len(token) if token else 0} characters")
+        print(f"Token starts with: {token[:20] if token else 'None'}...")
+    else:
+        print("\n❌ Authentication test failed!")
+        print("Please check your Azure setup and permissions.")
+    
+    print("=" * 60)
+    return success

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/duckrun/core.py

@@ -196,18 +196,19 @@ class Duckrun:
         print(f"🔍 Resolving '{workspace_name}' workspace and '{lakehouse_name}' lakehouse to GUIDs (workspace has spaces)...")
         
         try:
-            # Get authentication token (try notebook environment first, then azure-identity)
+            # Get authentication token using enhanced auth system
+            from .auth import get_fabric_api_token
+            token = get_fabric_api_token()
+            if not token:
+                raise ValueError("Failed to obtain Fabric API token")
+                
+            # Try to get current workspace ID if in notebook environment
+            current_workspace_id = None
             try:
                 import notebookutils  # type: ignore
-                token = notebookutils.credentials.getToken("pbi")
                 current_workspace_id = notebookutils.runtime.context.get("workspaceId")
             except ImportError:
-                current_workspace_id = None
-                # Fallback to azure-identity for external environments
-                from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-                credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-                token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
-                token = token_obj.token
+                pass  # Not in notebook environment
             
             # Resolve workspace name to ID 
             if current_workspace_id:
@@ -302,19 +303,23 @@ class Duckrun:
         return WorkspaceConnection(workspace_name)
 
     def _get_storage_token(self):
-        return os.environ.get("AZURE_STORAGE_TOKEN", "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE")
+        from .auth import get_storage_token
+        return get_storage_token()
 
     def _create_onelake_secret(self):
         token = self._get_storage_token()
         if token != "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE":
             self.con.sql(f"CREATE OR REPLACE SECRET onelake (TYPE AZURE, PROVIDER ACCESS_TOKEN, ACCESS_TOKEN '{token}')")
         else:
-            print("Authenticating with Azure (trying CLI, will fallback to browser if needed)...")
-            from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-            credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-            token = credential.get_token("https://storage.azure.com/.default")
-            os.environ["AZURE_STORAGE_TOKEN"] = token.token
-            self.con.sql("CREATE OR REPLACE PERSISTENT SECRET onelake (TYPE azure, PROVIDER credential_chain, CHAIN 'cli', ACCOUNT_NAME 'onelake')")
+            # Enhanced authentication - try all methods
+            from .auth import get_token
+            token = get_token()
+            if token:
+                os.environ["AZURE_STORAGE_TOKEN"] = token
+                self.con.sql(f"CREATE OR REPLACE SECRET onelake (TYPE AZURE, PROVIDER ACCESS_TOKEN, ACCESS_TOKEN '{token}')")
+            else:
+                # Final fallback to persistent secret
+                self.con.sql("CREATE OR REPLACE PERSISTENT SECRET onelake (TYPE azure, PROVIDER credential_chain, CHAIN 'cli', ACCOUNT_NAME 'onelake')")
 
     def _discover_tables_fast(self) -> List[Tuple[str, str]]:
         """
@@ -326,12 +331,12 @@ class Duckrun:
         """
         token = self._get_storage_token()
         if token == "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE":
-            print("Authenticating with Azure for table discovery (trying CLI, will fallback to browser if needed)...")
-            from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-            credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-            token_obj = credential.get_token("https://storage.azure.com/.default")
-            token = token_obj.token
-            os.environ["AZURE_STORAGE_TOKEN"] = token
+            print("Authenticating with Azure for table discovery (detecting environment automatically)...")
+            from .auth import get_token
+            token = get_token()
+            if not token:
+                print("❌ Failed to authenticate for table discovery")
+                return []
         
         url = f"abfss://{self.workspace}@{self.storage_account}.dfs.fabric.microsoft.com/"
         store = AzureStore.from_url(url, bearer_token=token)
@@ -579,19 +584,22 @@ class Duckrun:
             List of lakehouse names
         """
         try:
-            # Try to get token from notebook environment first
+            # Get authentication token using enhanced auth system
+            from .auth import get_fabric_api_token
+            token = get_fabric_api_token()
+            if not token:
+                print("❌ Failed to authenticate for listing lakehouses")
+                return []
+            
+            # Try to get current workspace ID if in notebook environment
+            workspace_id = None
             try:
                 import notebookutils  # type: ignore
-                token = notebookutils.credentials.getToken("pbi")
                 workspace_id = notebookutils.runtime.context.get("workspaceId")
             except ImportError:
-                # Fallback to azure-identity
-                print("Getting authentication token...")
-                from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-                credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-                token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
-                token = token_obj.token
-                
+                pass  # Not in notebook environment
+            
+            if not workspace_id:
                 # Get workspace ID by name
                 workspace_id = self._get_workspace_id_by_name(token, self.workspace)
                 if not workspace_id:
@@ -626,19 +634,22 @@ class Duckrun:
             True if lakehouse exists or was created successfully, False otherwise
         """
         try:
-            # Try to get token from notebook environment first
+            # Get authentication token using enhanced auth system
+            from .auth import get_fabric_api_token
+            token = get_fabric_api_token()
+            if not token:
+                print("❌ Failed to authenticate for lakehouse creation")
+                return False
+            
+            # Try to get current workspace ID if in notebook environment
+            workspace_id = None
             try:
                 import notebookutils  # type: ignore
-                token = notebookutils.credentials.getToken("pbi")
                 workspace_id = notebookutils.runtime.context.get("workspaceId")
             except ImportError:
-                # Fallback to azure-identity
-                print("Getting authentication token...")
-                from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-                credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-                token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
-                token = token_obj.token
-                
+                pass  # Not in notebook environment
+            
+            if not workspace_id:
                 # Get workspace ID by name
                 workspace_id = self._get_workspace_id_by_name(token, self.workspace)
                 if not workspace_id:
@@ -718,28 +729,18 @@ class WorkspaceConnection:
             List of lakehouse names
         """
         try:
-            # Try to get token from notebook environment first
-            try:
-                import notebookutils  # type: ignore
-                token = notebookutils.credentials.getToken("pbi")
-                # Always resolve workspace name to ID, even in notebook environment
-                workspace_id = self._get_workspace_id_by_name(token, self.workspace_name)
-                if not workspace_id:
-                    print(f"Workspace '{self.workspace_name}' not found")
-                    return []
-            except ImportError:
-                # Fallback to azure-identity
-                print("Getting authentication token...")
-                from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-                credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-                token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
-                token = token_obj.token
-                
-                # Get workspace ID by name
-                workspace_id = self._get_workspace_id_by_name(token, self.workspace_name)
-                if not workspace_id:
-                    print(f"Workspace '{self.workspace_name}' not found")
-                    return []
+            # Get authentication token using enhanced auth system
+            from .auth import get_fabric_api_token
+            token = get_fabric_api_token()
+            if not token:
+                print("❌ Failed to authenticate for listing lakehouses")
+                return []
+            
+            # Always resolve workspace name to ID, even in notebook environment
+            workspace_id = self._get_workspace_id_by_name(token, self.workspace_name)
+            if not workspace_id:
+                print(f"Workspace '{self.workspace_name}' not found")
+                return []
             
             # List lakehouses
             url = f"https://api.fabric.microsoft.com/v1/workspaces/{workspace_id}/lakehouses"
@@ -768,28 +769,18 @@ class WorkspaceConnection:
             True if lakehouse exists or was created successfully, False otherwise
         """
         try:
-            # Try to get token from notebook environment first
-            try:
-                import notebookutils  # type: ignore
-                token = notebookutils.credentials.getToken("pbi")
-                # Always resolve workspace name to ID, even in notebook environment
-                workspace_id = self._get_workspace_id_by_name(token, self.workspace_name)
-                if not workspace_id:
-                    print(f"Workspace '{self.workspace_name}' not found")
-                    return False
-            except ImportError:
-                # Fallback to azure-identity
-                print("Getting authentication token...")
-                from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-                credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-                token_obj = credential.get_token("https://api.fabric.microsoft.com/.default")
-                token = token_obj.token
-                
-                # Get workspace ID by name
-                workspace_id = self._get_workspace_id_by_name(token, self.workspace_name)
-                if not workspace_id:
-                    print(f"Workspace '{self.workspace_name}' not found")
-                    return False
+            # Get authentication token using enhanced auth system
+            from .auth import get_fabric_api_token
+            token = get_fabric_api_token()
+            if not token:
+                print("❌ Failed to authenticate for lakehouse creation")
+                return False
+            
+            # Always resolve workspace name to ID, even in notebook environment
+            workspace_id = self._get_workspace_id_by_name(token, self.workspace_name)
+            if not workspace_id:
+                print(f"Workspace '{self.workspace_name}' not found")
+                return False
             
             # Check if lakehouse already exists
             url = f"https://api.fabric.microsoft.com/v1/workspaces/{workspace_id}/lakehouses"

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/duckrun/files.py

@@ -41,15 +41,15 @@ def copy(duckrun_instance, local_folder: str, remote_folder: str,
         print(f"❌ Path is not a directory: {local_folder}")
         return False
         
-    # Get Azure token
+    # Get Azure token using enhanced auth system
+    from .auth import get_token
     token = duckrun_instance._get_storage_token()
     if token == "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE":
-        print("Authenticating with Azure for file upload (trying CLI, will fallback to browser if needed)...")
-        from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-        credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-        token_obj = credential.get_token("https://storage.azure.com/.default")
-        token = token_obj.token
-        os.environ["AZURE_STORAGE_TOKEN"] = token
+        print("Authenticating with Azure for file upload (detecting environment automatically)...")
+        token = get_token()
+        if not token:
+            print("❌ Failed to authenticate for file upload")
+            return False
     
     # Setup OneLake Files URL (use correct format without .Lakehouse suffix)
     files_base_url = duckrun_instance.files_base_url
@@ -150,15 +150,15 @@ def download(duckrun_instance, remote_folder: str = "", local_folder: str = "./d
         # Download only CSV files from a specific subfolder
         dr.download("daily_reports", "./reports", ['.csv'])
     """
-    # Get Azure token
+    # Get Azure token using enhanced auth system
+    from .auth import get_token
     token = duckrun_instance._get_storage_token()
     if token == "PLACEHOLDER_TOKEN_TOKEN_NOT_AVAILABLE":
-        print("Authenticating with Azure for file download (trying CLI, will fallback to browser if needed)...")
-        from azure.identity import AzureCliCredential, InteractiveBrowserCredential, ChainedTokenCredential
-        credential = ChainedTokenCredential(AzureCliCredential(), InteractiveBrowserCredential())
-        token_obj = credential.get_token("https://storage.azure.com/.default")
-        token = token_obj.token
-        os.environ["AZURE_STORAGE_TOKEN"] = token
+        print("Authenticating with Azure for file download (detecting environment automatically)...")
+        token = get_token()
+        if not token:
+            print("❌ Failed to authenticate for file download")
+            return False
     
     # Setup OneLake Files URL (use correct format without .Lakehouse suffix)
     files_base_url = duckrun_instance.files_base_url

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/duckrun/runner.py

@@ -15,7 +15,7 @@ def _build_write_deltalake_args(path, df, mode, schema_mode=None, partition_by=N
     """
     Build arguments for write_deltalake based on requirements:
     - If schema_mode='merge': use rust engine (no row group params)
-    - Otherwise: use pyarrow engine with row group optimization
+    - Otherwise: use pyarrow engine with row group optimization (if supported)
     """
     args = {
         'table_or_uri': path,
@@ -33,10 +33,17 @@ def _build_write_deltalake_args(path, df, mode, schema_mode=None, partition_by=N
         args['schema_mode'] = 'merge'
         args['engine'] = 'rust'
     else:
-        # Use pyarrow engine with row group optimization (default)
-        args['max_rows_per_file'] = RG
-        args['max_rows_per_group'] = RG
-        args['min_rows_per_group'] = RG
+        # Try to use pyarrow engine with row group optimization
+        # Check if row group parameters are supported by inspecting function signature
+        import inspect
+        sig = inspect.signature(write_deltalake)
+        
+        if 'max_rows_per_file' in sig.parameters:
+            # Older deltalake version - use row group optimization
+            args['max_rows_per_file'] = RG
+            args['max_rows_per_group'] = RG
+            args['min_rows_per_group'] = RG
+        # For newer versions, just use default parameters
     
     return args
 

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/duckrun/writer.py

@@ -12,7 +12,7 @@ def _build_write_deltalake_args(path, df, mode, schema_mode=None, partition_by=N
     """
     Build arguments for write_deltalake based on requirements:
     - If schema_mode='merge': use rust engine (no row group params)
-    - Otherwise: use pyarrow engine with row group optimization
+    - Otherwise: use pyarrow engine with row group optimization (if supported)
     """
     args = {
         'table_or_uri': path,
@@ -30,10 +30,17 @@ def _build_write_deltalake_args(path, df, mode, schema_mode=None, partition_by=N
         args['schema_mode'] = 'merge'
         args['engine'] = 'rust'
     else:
-        # Use pyarrow engine with row group optimization (default)
-        args['max_rows_per_file'] = RG
-        args['max_rows_per_group'] = RG
-        args['min_rows_per_group'] = RG
+        # Try to use pyarrow engine with row group optimization
+        # Check if row group parameters are supported by inspecting function signature
+        import inspect
+        sig = inspect.signature(write_deltalake)
+        
+        if 'max_rows_per_file' in sig.parameters:
+            # Older deltalake version - use row group optimization
+            args['max_rows_per_file'] = RG
+            args['max_rows_per_group'] = RG
+            args['min_rows_per_group'] = RG
+        # For newer versions, just use default parameters
     
     return args
 

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.6
+Version: 0.2.8.dev0
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT
@@ -26,7 +26,8 @@ A helper package for stuff that made my life easier when working with Fabric Pyt
 
 **Requirements:**
 - Lakehouse must have a schema (e.g., `dbo`, `sales`, `analytics`)
-- **Workspace and lakehouse names with spaces are now fully supported!** ✅
+- **Workspace names with spaces are fully supported!** ✅
+
 
 **Delta Lake Version:** This package uses an older version of deltalake to maintain row size control capabilities, which is crucial for Power BI performance optimization. The newer Rust-based deltalake versions don't yet support the row group size parameters that are essential for optimal DirectLake performance.
 
@@ -47,23 +48,40 @@ pip install duckrun[local]
 
 ## Quick Start
 
+### Simple Example for New Users
+
+```python
+import duckrun
+
+# Connect to a workspace and manage lakehouses
+con = duckrun.connect('My Workspace')
+con.list_lakehouses()                           # See what lakehouses exist
+con.create_lakehouse_if_not_exists('data')      # Create if needed
+
+# Connect to a specific lakehouse and query data
+con = duckrun.connect("My Workspace/data.lakehouse/dbo")
+con.sql("SELECT * FROM my_table LIMIT 10").show()
+```
+
+### Full Feature Overview
+
 ```python
 import duckrun
 
 # 1. Workspace Management (list and create lakehouses)
 ws = duckrun.connect("My Workspace")
 lakehouses = ws.list_lakehouses()  # Returns list of lakehouse names
-ws.create_lakehouse_if_not_exists("New Lakehouse")
+ws.create_lakehouse_if_not_exists("New_Lakehouse")
 
 # 2. Connect to lakehouse with a specific schema
-con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+con = duckrun.connect("My Workspace/MyLakehouse.lakehouse/dbo")
 
-# Works with workspace names containing spaces!
-con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
+# Workspace names with spaces are supported!
+con = duckrun.connect("Data Analytics/SalesData.lakehouse/analytics")
 
 # Schema defaults to 'dbo' if not specified (scans all schemas)
 # ⚠️ WARNING: Scanning all schemas can be slow for large lakehouses!
-con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
+con = duckrun.connect("My Workspace/My_Lakehouse.lakehouse")
 
 # 3. Explore data
 con.sql("SELECT * FROM my_table LIMIT 10").show()

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/duckrun.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ LICENSE
 README.md
 pyproject.toml
 duckrun/__init__.py
+duckrun/auth.py
 duckrun/core.py
 duckrun/files.py
 duckrun/lakehouse.py

{duckrun-0.2.6 → duckrun-0.2.8.dev0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.6"
+version = "0.2.8.dev0"
 description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
 readme = "README.md"
 license = {text = "MIT"}