duckrun 0.2.16.dev2__tar.gz → 0.2.18__tar.gz

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.16.dev2
-Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
+Version: 0.2.18
+Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT
 Project-URL: Homepage, https://github.com/djouallah/duckrun

duckrun-0.2.18/duckrun/__init__.py

@@ -0,0 +1,11 @@
+"""Duckrun - Lakehouse task runner powered by DuckDB"""
+
+from duckrun.core import Duckrun
+from duckrun.notebook import import_notebook_from_web, import_notebook
+
+__version__ = "0.2.18"
+
+# Expose unified connect method at module level
+connect = Duckrun.connect
+
+__all__ = ["Duckrun", "connect", "import_notebook_from_web", "import_notebook"]

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/duckrun/core.py

@@ -12,7 +12,71 @@ from .runner import run as _run
 from .files import copy as _copy, download as _download
 from .writer import QueryResult
 
-class Duckrun:
+
+class WorkspaceOperationsMixin:
+    """
+    Mixin class for workspace-level operations that work for both
+    full Duckrun connections and workspace-only connections.
+    """
+    
+    def import_notebook_from_web(self, url: str, 
+                                  notebook_name: Optional[str] = None,
+                                  overwrite: bool = False) -> dict:
+        """
+        Import a Jupyter notebook from a web URL into the workspace.
+        
+        Args:
+            url: URL to the notebook file (e.g., GitHub raw URL). Required.
+            notebook_name: Name for the imported notebook. Optional - derived from URL if not provided.
+            overwrite: Whether to overwrite if notebook already exists (default: False)
+            
+        Returns:
+            Dictionary with import result
+            
+        Examples:
+            con = duckrun.connect("workspace/lakehouse.lakehouse")
+            result = con.import_notebook_from_web(
+                url="https://raw.githubusercontent.com/user/repo/main/notebook.ipynb"
+            )
+            
+            ws = duckrun.connect("workspace")
+            result = ws.import_notebook_from_web(
+                url="https://raw.githubusercontent.com/user/repo/main/notebook.ipynb"
+            )
+        """
+        from .notebook import import_notebook_from_web as _import_notebook_from_web
+        
+        # Get workspace name from either self.workspace or self.workspace_name
+        workspace_name = getattr(self, 'workspace', None) or getattr(self, 'workspace_name', None)
+        
+        return _import_notebook_from_web(
+            url=url,
+            notebook_name=notebook_name,
+            overwrite=overwrite,
+            workspace_name=workspace_name
+        )
+    
+    def _get_workspace_id_by_name(self, token: str, workspace_name: str) -> Optional[str]:
+        """Helper method to get workspace ID from name"""
+        try:
+            url = "https://api.fabric.microsoft.com/v1/workspaces"
+            headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
+            
+            response = requests.get(url, headers=headers)
+            response.raise_for_status()
+            
+            workspaces = response.json().get("value", [])
+            for workspace in workspaces:
+                if workspace.get("displayName") == workspace_name:
+                    return workspace.get("id")
+            
+            return None
+            
+        except Exception:
+            return None
+
+
+class Duckrun(WorkspaceOperationsMixin):
     """
     OneLake task runner with clean tuple-based API.
     Supports lakehouses, warehouses, databases, and other OneLake items.
@@ -971,12 +1035,13 @@ class Duckrun:
         """Get underlying DuckDB connection"""
         return self.con
 
-    def get_stats(self, source: str):
+    def get_stats(self, source: str = None):
         """
         Get comprehensive statistics for Delta Lake tables.
         
         Args:
-            source: Can be one of:
+            source: Optional. Can be one of:
+                   - None: Use all tables in the connection's schema (default)
                    - Table name: 'table_name' (uses current schema)
                    - Schema.table: 'schema.table_name' (specific table in schema)
                    - Schema only: 'schema' (all tables in schema)
@@ -988,6 +1053,9 @@ class Duckrun:
         Examples:
             con = duckrun.connect("tmp/data.lakehouse/aemo")
             
+            # All tables in current schema (aemo)
+            stats = con.get_stats()
+            
             # Single table in current schema
             stats = con.get_stats('price')
             
@@ -1111,7 +1179,7 @@ class Duckrun:
             return False
 
     def deploy(self, bim_url: str, dataset_name: Optional[str] = None, 
-               wait_seconds: int = 5) -> int:
+               wait_seconds: int = 5, refresh: str = "full") -> int:
         """
         Deploy a semantic model from a BIM file using DirectLake mode.
         
@@ -1120,8 +1188,11 @@ class Duckrun:
                 - URL: "https://raw.githubusercontent.com/.../model.bim"
                 - Local file: "model.bim"
                 - Workspace/Model: "workspace_name/model_name"
-            dataset_name: Name for the semantic model (default: source model name if workspace/model format, else lakehouse_schema)
+            dataset_name: Name for the semantic model (default: schema name)
             wait_seconds: Seconds to wait for permission propagation (default: 5)
+            refresh: Refresh strategy:
+                - "full": Clear values and process full refresh (default)
+                - "ignore": Skip refresh entirely
         
         Returns:
             1 for success, 0 for failure
@@ -1129,14 +1200,17 @@ class Duckrun:
         Examples:
             dr = Duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
             
+            # Deploy with schema name as dataset name (dbo)
+            dr.deploy("https://github.com/.../model.bim")
+            
             # Deploy from workspace/model (uses same name by default)
             dr.deploy("Source Workspace/Source Model")  # Creates "Source Model"
             
             # Deploy with custom name
-            dr.deploy("Source Workspace/Source Model", dataset_name="Sales Model Copy")
+            dr.deploy("https://github.com/.../model.bim", dataset_name="Sales Model")
             
-            # Deploy from URL or local file
-            dr.deploy("https://raw.githubusercontent.com/.../model.bim", dataset_name="My Model")
+            # Deploy without refresh
+            dr.deploy("https://github.com/.../model.bim", refresh="ignore")
         """
         from .semantic_model import deploy_semantic_model
         
@@ -1148,9 +1222,9 @@ class Duckrun:
                 if len(parts) == 2:
                     dataset_name = parts[1]  # Use the model name
                 else:
-                    dataset_name = f"{self.lakehouse_name}_{self.schema}"
+                    dataset_name = self.schema  # Use schema name
             else:
-                dataset_name = f"{self.lakehouse_name}_{self.schema}"
+                dataset_name = self.schema  # Use schema name
         
         # Call the deployment function (DirectLake only)
         return deploy_semantic_model(
@@ -1159,28 +1233,10 @@ class Duckrun:
             schema_name=self.schema,
             dataset_name=dataset_name,
             bim_url_or_path=bim_url,
-            wait_seconds=wait_seconds
+            wait_seconds=wait_seconds,
+            refresh=refresh
         )
 
-    def _get_workspace_id_by_name(self, token: str, workspace_name: str) -> Optional[str]:
-        """Helper method to get workspace ID from name"""
-        try:
-            url = "https://api.fabric.microsoft.com/v1/workspaces"
-            headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
-            
-            response = requests.get(url, headers=headers)
-            response.raise_for_status()
-            
-            workspaces = response.json().get("value", [])
-            for workspace in workspaces:
-                if workspace.get("displayName") == workspace_name:
-                    return workspace.get("id")
-            
-            return None
-            
-        except Exception:
-            return None
-
     def close(self):
         """Close DuckDB connection"""
         if self.con:
@@ -1188,7 +1244,7 @@ class Duckrun:
             print("Connection closed")
 
 
-class WorkspaceConnection:
+class WorkspaceConnection(WorkspaceOperationsMixin):
     """
     Simple workspace connection for lakehouse management operations.
     """
@@ -1428,23 +1484,4 @@ class WorkspaceConnection:
             print(f"❌ Error downloading semantic model: {e}")
             import traceback
             traceback.print_exc()
-            return None
-    
-    def _get_workspace_id_by_name(self, token: str, workspace_name: str) -> Optional[str]:
-        """Helper method to get workspace ID from name"""
-        try:
-            url = "https://api.fabric.microsoft.com/v1/workspaces"
-            headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
-            
-            response = requests.get(url, headers=headers)
-            response.raise_for_status()
-            
-            workspaces = response.json().get("value", [])
-            for workspace in workspaces:
-                if workspace.get("displayName") == workspace_name:
-                    return workspace.get("id")
-            
-            return None
-            
-        except Exception:
             return None

duckrun-0.2.18/duckrun/notebook.py

@@ -0,0 +1,324 @@
+"""
+Notebook operations functionality for duckrun - Import notebooks from web using Fabric REST API
+"""
+import requests
+import base64
+from typing import Optional
+
+
+def import_notebook_from_web(
+    url: str,
+    notebook_name: Optional[str] = None,
+    overwrite: bool = False,
+    workspace_name: Optional[str] = None
+) -> dict:
+    """
+    Import a Jupyter notebook from a web URL into Microsoft Fabric workspace using REST API only.
+    Uses duckrun.connect context by default or explicit workspace name.
+    
+    Args:
+        url: URL to the notebook file (e.g., GitHub raw URL). Required.
+        notebook_name: Name for the imported notebook in Fabric. Optional - will use filename from URL if not provided.
+        overwrite: Whether to overwrite if notebook already exists (default: False)
+        workspace_name: Target workspace name. Optional - will use current workspace from duckrun context if available.
+        
+    Returns:
+        Dictionary with import result:
+        {
+            "success": bool,
+            "message": str,
+            "notebook": dict (if successful),
+            "overwritten": bool
+        }
+        
+    Examples:
+        # Basic usage with duckrun context
+        import duckrun
+        dr = duckrun.connect("MyWorkspace/MyLakehouse.lakehouse")
+        from duckrun.notebook import import_notebook_from_web
+        
+        result = import_notebook_from_web(
+            url="https://raw.githubusercontent.com/user/repo/main/notebook.ipynb",
+            notebook_name="MyNotebook"
+        )
+        
+        # With explicit workspace
+        result = import_notebook_from_web(
+            url="https://raw.githubusercontent.com/user/repo/main/notebook.ipynb",
+            notebook_name="MyNotebook",
+            workspace_name="Analytics Workspace",
+            overwrite=True
+        )
+        
+        # Minimal usage - derives name from URL
+        result = import_notebook_from_web(
+            url="https://raw.githubusercontent.com/user/repo/main/RunPerfScenario.ipynb"
+        )
+    """
+    try:
+        # Get authentication token
+        from duckrun.auth import get_fabric_api_token
+        token = get_fabric_api_token()
+        if not token:
+            return {
+                "success": False,
+                "message": "Failed to get authentication token",
+                "notebook": None,
+                "overwritten": False
+            }
+        
+        base_url = "https://api.fabric.microsoft.com/v1"
+        headers = {
+            "Authorization": f"Bearer {token}",
+            "Content-Type": "application/json"
+        }
+        
+        # Determine workspace ID
+        workspace_id = None
+        
+        # Try to get from duckrun context if not provided
+        if not workspace_name:
+            try:
+                # Try to get from notebook context first
+                import notebookutils  # type: ignore
+                workspace_id = notebookutils.runtime.context.get("workspaceId")
+                print("📓 Using current workspace from Fabric notebook context")
+            except (ImportError, Exception):
+                # Not in notebook, try to get from environment/last connection
+                pass
+        
+        # If still no workspace_id, resolve from workspace_name
+        if not workspace_id:
+            if not workspace_name:
+                return {
+                    "success": False,
+                    "message": "workspace_name must be provided when not in Fabric notebook context",
+                    "notebook": None,
+                    "overwritten": False
+                }
+            
+            # Get workspace ID by name
+            print(f"🔍 Resolving workspace: {workspace_name}")
+            ws_url = f"{base_url}/workspaces"
+            response = requests.get(ws_url, headers=headers)
+            response.raise_for_status()
+            
+            workspaces = response.json().get("value", [])
+            workspace = next((ws for ws in workspaces if ws.get("displayName") == workspace_name), None)
+            
+            if not workspace:
+                return {
+                    "success": False,
+                    "message": f"Workspace '{workspace_name}' not found",
+                    "notebook": None,
+                    "overwritten": False
+                }
+            
+            workspace_id = workspace.get("id")
+            print(f"✓ Found workspace: {workspace_name}")
+        
+        # Derive notebook name from URL if not provided
+        if not notebook_name:
+            # Extract filename from URL
+            notebook_name = url.split("/")[-1]
+            if notebook_name.endswith(".ipynb"):
+                notebook_name = notebook_name[:-6]  # Remove .ipynb extension
+            print(f"📝 Using notebook name from URL: {notebook_name}")
+        
+        # Check if notebook already exists
+        notebooks_url = f"{base_url}/workspaces/{workspace_id}/notebooks"
+        response = requests.get(notebooks_url, headers=headers)
+        response.raise_for_status()
+        
+        notebooks = response.json().get("value", [])
+        existing_notebook = next((nb for nb in notebooks if nb.get("displayName") == notebook_name), None)
+        
+        if existing_notebook and not overwrite:
+            return {
+                "success": True,
+                "message": f"Notebook '{notebook_name}' already exists (use overwrite=True to replace)",
+                "notebook": existing_notebook,
+                "overwritten": False
+            }
+        
+        # Download notebook content from URL
+        print(f"⬇️ Downloading notebook from: {url}")
+        response = requests.get(url)
+        response.raise_for_status()
+        notebook_content = response.text
+        print(f"✓ Notebook downloaded successfully")
+        
+        # Convert notebook content to base64
+        notebook_base64 = base64.b64encode(notebook_content.encode('utf-8')).decode('utf-8')
+        
+        # Prepare the payload for creating/updating the notebook
+        if existing_notebook and overwrite:
+            # Update existing notebook
+            notebook_id = existing_notebook.get("id")
+            print(f"🔄 Updating existing notebook: {notebook_name}")
+            
+            update_url = f"{base_url}/workspaces/{workspace_id}/notebooks/{notebook_id}/updateDefinition"
+            payload = {
+                "definition": {
+                    "format": "ipynb",
+                    "parts": [
+                        {
+                            "path": "notebook-content.py",
+                            "payload": notebook_base64,
+                            "payloadType": "InlineBase64"
+                        }
+                    ]
+                }
+            }
+            
+            response = requests.post(update_url, headers=headers, json=payload)
+            response.raise_for_status()
+            
+            # Handle long-running operation
+            if response.status_code == 202:
+                operation_id = response.headers.get('x-ms-operation-id')
+                if operation_id:
+                    _wait_for_operation(operation_id, headers)
+            
+            return {
+                "success": True,
+                "message": f"Notebook '{notebook_name}' updated successfully",
+                "notebook": existing_notebook,
+                "overwritten": True
+            }
+        else:
+            # Create new notebook
+            print(f"➕ Creating new notebook: {notebook_name}")
+            
+            payload = {
+                "displayName": notebook_name,
+                "definition": {
+                    "format": "ipynb",
+                    "parts": [
+                        {
+                            "path": "notebook-content.py",
+                            "payload": notebook_base64,
+                            "payloadType": "InlineBase64"
+                        }
+                    ]
+                }
+            }
+            
+            response = requests.post(notebooks_url, headers=headers, json=payload)
+            response.raise_for_status()
+            
+            # Handle long-running operation
+            if response.status_code == 202:
+                operation_id = response.headers.get('x-ms-operation-id')
+                if operation_id:
+                    _wait_for_operation(operation_id, headers)
+            
+            created_notebook = response.json()
+            
+            return {
+                "success": True,
+                "message": f"Notebook '{notebook_name}' created successfully",
+                "notebook": created_notebook,
+                "overwritten": False
+            }
+            
+    except requests.exceptions.RequestException as e:
+        return {
+            "success": False,
+            "message": f"HTTP Error: {str(e)}",
+            "notebook": None,
+            "overwritten": False
+        }
+    except Exception as e:
+        return {
+            "success": False,
+            "message": f"Error: {str(e)}",
+            "notebook": None,
+            "overwritten": False
+        }
+
+
+def _wait_for_operation(operation_id: str, headers: dict, max_attempts: int = 30) -> bool:
+    """
+    Wait for a long-running Fabric API operation to complete.
+    
+    Args:
+        operation_id: The operation ID to monitor
+        headers: Request headers with authentication
+        max_attempts: Maximum number of polling attempts (default: 30)
+        
+    Returns:
+        True if operation succeeded, False otherwise
+    """
+    import time
+    
+    status_url = f"https://api.fabric.microsoft.com/v1/operations/{operation_id}"
+    
+    for attempt in range(max_attempts):
+        time.sleep(2)
+        
+        try:
+            response = requests.get(status_url, headers=headers)
+            response.raise_for_status()
+            
+            status_data = response.json()
+            status = status_data.get('status')
+            
+            if status == 'Succeeded':
+                print(f"✓ Operation completed successfully")
+                return True
+            elif status == 'Failed':
+                error = status_data.get('error', {})
+                print(f"❌ Operation failed: {error.get('message', 'Unknown error')}")
+                return False
+            else:
+                print(f"⏳ Operation in progress... ({status})")
+                
+        except Exception as e:
+            print(f"⚠️ Error checking operation status: {e}")
+            return False
+    
+    print(f"⚠️ Operation timed out after {max_attempts} attempts")
+    return False
+
+
+# Convenience wrapper for the try-except pattern mentioned in the request
+def import_notebook(
+    url: str,
+    notebook_name: Optional[str] = None,
+    overwrite: bool = False,
+    workspace_name: Optional[str] = None
+) -> None:
+    """
+    Convenience wrapper that prints results and handles errors.
+    
+    Args:
+        url: URL to the notebook file
+        notebook_name: Name for the imported notebook
+        overwrite: Whether to overwrite if exists
+        workspace_name: Target workspace name
+        
+    Examples:
+        from duckrun.notebook import import_notebook
+        
+        import_notebook(
+            url="https://raw.githubusercontent.com/djouallah/fabric_demo/refs/heads/main/Benchmark/RunPerfScenario.ipynb",
+            notebook_name="RunPerfScenario",
+            overwrite=False
+        )
+    """
+    try:
+        result = import_notebook_from_web(
+            url=url,
+            notebook_name=notebook_name,
+            overwrite=overwrite,
+            workspace_name=workspace_name
+        )
+        
+        if result["success"]:
+            print(f"✅ {result['message']}")
+        else:
+            print(f"❌ {result['message']}")
+            
+    except Exception as e:
+        print(f"Error: {e}")

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/duckrun/semantic_model.py

@@ -129,29 +129,136 @@ def check_dataset_exists(dataset_name, workspace_id, client):
         return False
 
 
-def refresh_dataset(dataset_name, workspace_id, client, dataset_id=None):
-    """Refresh a dataset and monitor progress using Power BI API"""
+def refresh_dataset(dataset_name, workspace_id, client, dataset_id=None, refresh="full"):
+    """Refresh a dataset and monitor progress using Power BI API
+    
+    For DirectLake models, performs refresh based on refresh parameter:
+    - refresh="full": Two-step refresh (clearValues + full reframe)
+    - refresh="ignore": Skip refresh entirely
+    
+    If a refresh is already in progress, waits for it to complete before starting a new one.
+    """
+    
+    # Skip refresh entirely if refresh is "ignore"
+    if refresh == "ignore":
+        print("   Ignoring refresh - skipping refresh")
+        return
     
     # If dataset_id not provided, look it up by name
     if not dataset_id:
         dataset_id = get_dataset_id(dataset_name, workspace_id, client)
     
-    payload = {
-        "type": "full",
+    # Use Power BI API for refresh (not Fabric API)
+    powerbi_url = f"https://api.powerbi.com/v1.0/myorg/datasets/{dataset_id}/refreshes"
+    headers = client._get_headers()
+    
+    # Check for in-progress refreshes
+    print("   Checking for in-progress refreshes...")
+    try:
+        status_response = requests.get(f"{powerbi_url}?$top=1", headers=headers)
+        if status_response.status_code == 200:
+            refreshes = status_response.json().get('value', [])
+            if refreshes:
+                latest_refresh = refreshes[0]
+                status = latest_refresh.get('status')
+                if status in ['InProgress', 'Unknown']:
+                    refresh_id = latest_refresh.get('requestId')
+                    print(f"   ⚠️  Found in-progress refresh (ID: {refresh_id})")
+                    print(f"   Waiting for current refresh to complete...")
+                    
+                    # Wait for the in-progress refresh to complete
+                    max_wait_attempts = 60
+                    for attempt in range(max_wait_attempts):
+                        time.sleep(5)
+                        check_response = requests.get(f"{powerbi_url}/{refresh_id}", headers=headers)
+                        if check_response.status_code == 200:
+                            current_status = check_response.json().get('status')
+                            
+                            if current_status == 'Completed':
+                                print(f"   ✓ Previous refresh completed")
+                                break
+                            elif current_status == 'Failed':
+                                print(f"   ⚠️  Previous refresh failed, continuing with new refresh")
+                                break
+                            elif current_status == 'Cancelled':
+                                print(f"   ⚠️  Previous refresh was cancelled, continuing with new refresh")
+                                break
+                            
+                            if attempt % 6 == 0:
+                                print(f"   Still waiting... (status: {current_status})")
+                    else:
+                        print(f"   ⚠️  Timeout waiting for previous refresh, will attempt new refresh anyway")
+    except Exception as e:
+        print(f"   ⚠️  Could not check refresh status: {e}")
+        print(f"   Continuing with refresh attempt...")
+    
+    # Step 1: clearValues - Purge data from memory
+    print("   Step 1: Clearing values from memory...")
+    clearvalues_payload = {
+        "type": "clearValues",
         "commitMode": "transactional",
         "maxParallelism": 10,
         "retryCount": 2,
         "objects": []
     }
     
-    # Use Power BI API for refresh (not Fabric API)
-    powerbi_url = f"https://api.powerbi.com/v1.0/myorg/datasets/{dataset_id}/refreshes"
-    headers = client._get_headers()
+    response = requests.post(powerbi_url, headers=headers, json=clearvalues_payload)
     
-    response = requests.post(powerbi_url, headers=headers, json=payload)
+    if response.status_code in [200, 202]:
+        # For 202, monitor the clearValues operation
+        if response.status_code == 202:
+            location = response.headers.get('Location')
+            if location:
+                clear_refresh_id = location.split('/')[-1]
+                print("   ✓ Clear values initiated, monitoring progress...")
+                
+                max_attempts = 60
+                for attempt in range(max_attempts):
+                    time.sleep(2)
+                    
+                    status_url = f"https://api.powerbi.com/v1.0/myorg/datasets/{dataset_id}/refreshes/{clear_refresh_id}"
+                    status_response = requests.get(status_url, headers=headers)
+                    status_response.raise_for_status()
+                    status = status_response.json().get('status')
+                    
+                    if status == 'Completed':
+                        print(f"   ✓ Clear values completed")
+                        break
+                    elif status == 'Failed':
+                        error = status_response.json().get('serviceExceptionJson', '')
+                        raise Exception(f"Clear values failed: {error}")
+                    elif status == 'Cancelled':
+                        raise Exception("Clear values was cancelled")
+                    
+                    if attempt % 10 == 0 and attempt > 0:
+                        print(f"   Clear values status: {status}...")
+                else:
+                    raise Exception(f"Clear values timed out")
+        else:
+            print("   ✓ Clear values completed")
+    else:
+        # Provide detailed error message
+        try:
+            error_details = response.json()
+            error_message = error_details.get('error', {}).get('message', response.text)
+            raise Exception(f"Clear values failed with status {response.status_code}: {error_message}")
+        except (json.JSONDecodeError, ValueError):
+            response.raise_for_status()
+    
+    # Step 2: full refresh - Reframe data from Delta tables
+    print("   Step 2: Full refresh to reframe data...")
+    full_payload = {
+        "type": "full",
+        "commitMode": "transactional",
+        "maxParallelism": 10,
+        "retryCount": 2,
+        "objects": []
+    }
+    
+    response = requests.post(powerbi_url, headers=headers, json=full_payload)
     
     if response.status_code in [200, 202]:
-        print(f"✓ Refresh initiated")
+        print(f"   ✓ Refresh initiated")
         
         # For 202, get the refresh_id from the Location header
         if response.status_code == 202:
@@ -183,7 +290,13 @@ def refresh_dataset(dataset_name, workspace_id, client, dataset_id=None):
                 
                 raise Exception(f"Refresh timed out")
     else:
-        response.raise_for_status()
+        # Provide detailed error message
+        try:
+            error_details = response.json()
+            error_message = error_details.get('error', {}).get('message', response.text)
+            raise Exception(f"Refresh request failed with status {response.status_code}: {error_message}")
+        except (json.JSONDecodeError, ValueError):
+            response.raise_for_status()
 
 
 def download_bim_from_github(url_or_path):
@@ -431,7 +544,7 @@ def create_dataset_from_bim(dataset_name, bim_content, workspace_id, client):
 
 
 def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_name, dataset_name, 
-                         bim_url_or_path, wait_seconds=5):
+                         bim_url_or_path, wait_seconds=5, refresh="full"):
     """
     Deploy a semantic model using DirectLake mode.
     
@@ -442,6 +555,9 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         dataset_name: Name for the semantic model
         bim_url_or_path: URL to the BIM file or local file path (e.g., 'model.bim' or 'https://...')
         wait_seconds: Seconds to wait before refresh (default: 5)
+        refresh: Refresh strategy (default: "full")
+            - "full": Clear values and process full refresh
+            - "ignore": Skip refresh entirely
     
     Returns:
         1 for success, 0 for failure
@@ -454,6 +570,9 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         # Using a local file
         dr.deploy("./my_model.bim")
         dr.deploy("C:/path/to/model.bim")
+        
+        # Deploy without refresh
+        dr.deploy("./my_model.bim", refresh="ignore")
     """
     print("=" * 70)
     print("Semantic Model Deployment (DirectLake)")
@@ -471,14 +590,14 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         dataset_exists = check_dataset_exists(dataset_name, workspace_id, client)
         
         if dataset_exists:
-            print(f"\n✓ Dataset exists - refreshing...")
+            print(f"✓ Dataset '{dataset_name}' already exists - skipping deployment")
             
             if wait_seconds > 0:
                 print(f"   Waiting {wait_seconds} seconds...")
                 time.sleep(wait_seconds)
             
-            print("\n[Step 6/6] Refreshing semantic model...")
-            refresh_dataset(dataset_name, workspace_id, client)
+            print("\n[Step 3/3] Refreshing existing semantic model...")
+            refresh_dataset(dataset_name, workspace_id, client, refresh=refresh)
             
             print("\n" + "=" * 70)
             print("🎉 Refresh Completed!")
@@ -510,7 +629,7 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         
         # Step 6: Refresh using the dataset ID returned from creation
         print("\n[Step 6/6] Refreshing semantic model...")
-        refresh_dataset(dataset_name, workspace_id, client, dataset_id=dataset_id)
+        refresh_dataset(dataset_name, workspace_id, client, dataset_id=dataset_id, refresh=refresh)
         
         print("\n" + "=" * 70)
         print("🎉 Deployment Completed!")
@@ -537,7 +656,7 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         return 0
 
 
-def copy_model(ws_source, model_name, destination, new_model_name=None, wait_seconds=5):
+def copy_model(ws_source, model_name, destination, new_model_name=None, wait_seconds=5, refresh="full"):
     """
     Copy a semantic model from one workspace to another.
     
@@ -550,6 +669,9 @@ def copy_model(ws_source, model_name, destination, new_model_name=None, wait_sec
         destination: Destination in format "workspace/lakehouse.lakehouse/schema"
         new_model_name: Name for the new semantic model (default: same as source)
         wait_seconds: Seconds to wait before refresh (default: 5)
+        refresh: Refresh strategy (default: "full")
+            - "full": Clear values and process full refresh
+            - "ignore": Skip refresh entirely
     
     Returns:
         1 for success, 0 for failure
@@ -562,6 +684,9 @@ def copy_model(ws_source, model_name, destination, new_model_name=None, wait_sec
         copy_model("Source WS", "Production Model", "Target WS/Data Lake.lakehouse/analytics", 
                    new_model_name="Production Model - Copy")
         
+        # Copy without refresh
+        copy_model("Source WS", "Model", "Target WS/LH.lakehouse/dbo", refresh="ignore")
+        
         # Using the connect pattern
         import duckrun
         duckrun.semantic_model.copy_model("Source", "Model", "Target/LH.lakehouse/dbo")
@@ -688,7 +813,8 @@ def copy_model(ws_source, model_name, destination, new_model_name=None, wait_sec
             schema_name=schema,
             dataset_name=new_model_name,
             bim_url_or_path=temp_bim_path,
-            wait_seconds=wait_seconds
+            wait_seconds=wait_seconds,
+            refresh=refresh
         )
         
         # Clean up temp file

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/duckrun/stats.py

@@ -60,16 +60,61 @@ def _get_existing_tables_in_schema(duckrun_instance, schema_name: str) -> list:
         return []
 
 
-def get_stats(duckrun_instance, source: str):
+def _match_tables_by_pattern(duckrun_instance, pattern: str) -> dict:
+    """Match tables across all schemas using a wildcard pattern.
+    Pattern can be:
+    - '*.summary' - matches 'summary' table in all schemas
+    - '*summary' - matches any table ending with 'summary'
+    - 'schema.*' - matches all tables in 'schema'
+    Returns a dict mapping schema names to lists of matching table names."""
+    import fnmatch
+    
+    try:
+        # Query all schemas and tables in one go
+        query = """
+            SELECT table_schema, table_name 
+            FROM information_schema.tables 
+            WHERE table_schema NOT LIKE 'pg_%' 
+            AND table_schema != 'information_schema'
+            AND table_name NOT LIKE 'tbl_%'
+        """
+        result = duckrun_instance.con.execute(query).fetchall()
+        
+        matched = {}
+        
+        # Check if pattern contains a dot (schema.table pattern)
+        if '.' in pattern:
+            schema_pattern, table_pattern = pattern.split('.', 1)
+            for schema, table in result:
+                if fnmatch.fnmatch(schema, schema_pattern) and fnmatch.fnmatch(table, table_pattern):
+                    if schema not in matched:
+                        matched[schema] = []
+                    matched[schema].append(table)
+        else:
+            # Pattern matches only table names
+            for schema, table in result:
+                if fnmatch.fnmatch(table, pattern):
+                    if schema not in matched:
+                        matched[schema] = []
+                    matched[schema].append(table)
+        
+        return matched
+    except:
+        return {}
+
+
+def get_stats(duckrun_instance, source: str = None):
     """
     Get comprehensive statistics for Delta Lake tables.
     
     Args:
         duckrun_instance: The Duckrun connection instance
-        source: Can be one of:
+        source: Optional. Can be one of:
+               - None: Use all tables in the connection's schema (default)
                - Table name: 'table_name' (uses main schema in DuckDB)
                - Schema.table: 'schema.table_name' (specific table in schema, if multi-schema)
                - Schema only: 'schema' (all tables in schema, if multi-schema)
+               - Wildcard pattern: '*.summary' (matches tables across all schemas)
     
     Returns:
         Arrow table with statistics including total rows, file count, row groups, 
@@ -78,6 +123,9 @@ def get_stats(duckrun_instance, source: str):
     Examples:
         con = duckrun.connect("tmp/data.lakehouse/test")
         
+        # All tables in the connection's schema
+        stats = con.get_stats()
+        
         # Single table in main schema (DuckDB uses 'main', not 'test')
         stats = con.get_stats('price_today')
         
@@ -86,6 +134,9 @@ def get_stats(duckrun_instance, source: str):
         
         # All tables in a schema (only if multi-schema enabled)
         stats = con.get_stats('aemo')
+        
+        # Wildcard pattern across all schemas (only if multi-schema enabled)
+        stats = con.get_stats('*.summary')
     """
     timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
     
@@ -93,8 +144,31 @@ def get_stats(duckrun_instance, source: str):
     duckdb_schema = "main"
     url_schema = duckrun_instance.schema  # This is from the connection URL path
     
+    # If source is not provided, default to all tables in the connection's schema
+    if source is None:
+        source = url_schema
+    
+    # Check if source contains wildcard characters
+    if '*' in source or '?' in source:
+        # Wildcard pattern mode - only valid if multi-schema is enabled
+        if not duckrun_instance.scan_all_schemas:
+            raise ValueError(f"Wildcard pattern '{source}' not supported. Connection was made to a specific schema '{url_schema}'. Enable multi-schema mode to use wildcards.")
+        
+        matched_tables = _match_tables_by_pattern(duckrun_instance, source)
+        
+        if not matched_tables:
+            raise ValueError(f"No tables found matching pattern '{source}'")
+        
+        # Flatten the matched tables into a list with schema info
+        tables_with_schemas = []
+        for schema, tables in matched_tables.items():
+            for table in tables:
+                tables_with_schemas.append((schema, table))
+        
+        print(f"Found {len(tables_with_schemas)} tables matching pattern '{source}'")
+        
     # Parse the source and validate existence
-    if '.' in source:
+    elif '.' in source:
         # Format: schema.table - only valid if multi-schema is enabled
         schema_name, table_name = source.split('.', 1)
         
@@ -105,46 +179,45 @@ def get_stats(duckrun_instance, source: str):
         if not _table_exists(duckrun_instance, schema_name, table_name):
             raise ValueError(f"Table '{table_name}' does not exist in schema '{schema_name}'")
         
-        list_tables = [table_name]
+        tables_with_schemas = [(schema_name, table_name)]
     else:
         # Could be just table name or schema name
         if duckrun_instance.scan_all_schemas:
             # Multi-schema mode: DuckDB has actual schemas
             # First check if it's a table in main schema
             if _table_exists(duckrun_instance, duckdb_schema, source):
-                list_tables = [source]
-                schema_name = duckdb_schema
+                tables_with_schemas = [(duckdb_schema, source)]
             # Otherwise, check if it's a schema name
             elif _schema_exists(duckrun_instance, source):
                 schema_name = source
                 list_tables = _get_existing_tables_in_schema(duckrun_instance, source)
                 if not list_tables:
                     raise ValueError(f"Schema '{source}' exists but contains no tables")
+                tables_with_schemas = [(schema_name, tbl) for tbl in list_tables]
             else:
                 raise ValueError(f"Neither table '{source}' in main schema nor schema '{source}' exists")
         else:
             # Single-schema mode: tables are in DuckDB's main schema, use URL schema for file paths
             if _table_exists(duckrun_instance, duckdb_schema, source):
                 # It's a table name
-                list_tables = [source]
-                schema_name = url_schema  # Use URL schema for file path construction
+                tables_with_schemas = [(url_schema, source)]
             elif source == url_schema:
                 # Special case: user asked for stats on the URL schema name - list all tables
                 list_tables = _get_existing_tables_in_schema(duckrun_instance, duckdb_schema)
-                schema_name = url_schema  # Use URL schema for file path construction
                 if not list_tables:
                     raise ValueError(f"No tables found in schema '{url_schema}'")
+                tables_with_schemas = [(url_schema, tbl) for tbl in list_tables]
             else:
                 raise ValueError(f"Table '{source}' does not exist in the current context (schema: {url_schema})")
     
     # Use the existing connection
     con = duckrun_instance.con
     
-    print(f"Processing {len(list_tables)} tables: {list_tables}")
+    print(f"Processing {len(tables_with_schemas)} tables from {len(set(s for s, t in tables_with_schemas))} schema(s)")
     
     successful_tables = []
-    for idx, tbl in enumerate(list_tables):
-        print(f"[{idx+1}/{len(list_tables)}] Processing table '{tbl}'...")
+    for idx, (schema_name, tbl) in enumerate(tables_with_schemas):
+        print(f"[{idx+1}/{len(tables_with_schemas)}] Processing table '{schema_name}.{tbl}'...")
         # Construct lakehouse path using correct ABFSS URL format (no .Lakehouse suffix)
         table_path = f"{duckrun_instance.table_base_url}{schema_name}/{tbl}"
         
@@ -171,8 +244,18 @@ def get_stats(duckrun_instance, source: str):
                     print(f"Warning: Could not convert RecordBatch for table '{tbl}': Unexpected type {type(add_actions)}")
                     xx = {}
             
-            # Check if VORDER exists
-            vorder = 'tags.VORDER' in xx.keys()
+            # Check if VORDER exists - handle both formats:
+            # 1. Flattened format: 'tags.VORDER' or 'tags.vorder' in keys
+            # 2. Nested format: check in 'tags' dict for 'VORDER' or 'vorder'
+            vorder = False
+            if 'tags.VORDER' in xx.keys() or 'tags.vorder' in xx.keys():
+                vorder = True
+            elif 'tags' in xx.keys() and xx['tags']:
+                # Check nested tags dictionary (tags is a list of dicts, one per file)
+                for tag_dict in xx['tags']:
+                    if tag_dict and ('VORDER' in tag_dict or 'vorder' in tag_dict):
+                        vorder = True
+                        break
             
             # Calculate total size
             total_size = sum(xx['size_bytes']) if xx['size_bytes'] else 0
@@ -187,6 +270,7 @@ def get_stats(duckrun_instance, source: str):
                 con.execute(f'''
                     CREATE OR REPLACE TEMP TABLE tbl_{idx} AS
                     SELECT 
+                        '{schema_name}' as schema,
                         '{tbl}' as tbl,
                         'empty' as file_name,
                         0 as num_rows,
@@ -202,6 +286,7 @@ def get_stats(duckrun_instance, source: str):
                 con.execute(f'''
                     CREATE OR REPLACE TEMP TABLE tbl_{idx} AS
                     SELECT 
+                        '{schema_name}' as schema,
                         '{tbl}' as tbl,
                         fm.file_name,
                         fm.num_rows,
@@ -237,6 +322,7 @@ def get_stats(duckrun_instance, source: str):
                     con.execute(f'''
                         CREATE OR REPLACE TEMP TABLE tbl_{idx} AS
                         SELECT 
+                            '{schema_name}' as schema,
                             '{tbl}' as tbl,
                             'empty' as file_name,
                             0 as num_rows,
@@ -264,6 +350,7 @@ def get_stats(duckrun_instance, source: str):
                     con.execute(f'''
                         CREATE OR REPLACE TEMP TABLE tbl_{idx} AS
                         SELECT 
+                            '{schema_name}' as schema,
                             '{tbl}' as tbl,
                             fm.file_name,
                             fm.num_rows,
@@ -291,7 +378,7 @@ def get_stats(duckrun_instance, source: str):
         # No tables were processed successfully - return empty dataframe
         print("⚠️  No tables could be processed successfully")
         import pandas as pd
-        return pd.DataFrame(columns=['tbl', 'total_rows', 'num_files', 'num_row_group', 
+        return pd.DataFrame(columns=['schema', 'tbl', 'total_rows', 'num_files', 'num_row_group', 
                                      'average_row_group', 'file_size_MB', 'vorder', 'compression', 'timestamp'])
     
     # Union all successfully processed temp tables
@@ -301,6 +388,7 @@ def get_stats(duckrun_instance, source: str):
     # Generate final summary
     final_result = con.execute(f'''
         SELECT 
+            schema,
             tbl,
             SUM(num_rows) as total_rows,
             COUNT(*) as num_files,
@@ -312,7 +400,7 @@ def get_stats(duckrun_instance, source: str):
             ANY_VALUE(timestamp) as timestamp
         FROM ({union_query})
         WHERE tbl IS NOT NULL
-        GROUP BY tbl
+        GROUP BY schema, tbl
         ORDER BY total_rows DESC
     ''').df()
     

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/duckrun.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.16.dev2
-Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
+Version: 0.2.18
+Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT
 Project-URL: Homepage, https://github.com/djouallah/duckrun

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/duckrun.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ duckrun/auth.py
 duckrun/core.py
 duckrun/files.py
 duckrun/lakehouse.py
+duckrun/notebook.py
 duckrun/runner.py
 duckrun/semantic_model.py
 duckrun/stats.py

{duckrun-0.2.16.dev2 → duckrun-0.2.18}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.16.dev2"
-description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
+version = "0.2.18"
+description = "Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)"
 readme = "README.md"
 license = {text = "MIT"}
 authors = [

duckrun-0.2.16.dev2/duckrun/__init__.py

@@ -1,10 +0,0 @@
-"""Duckrun - Lakehouse task runner powered by DuckDB"""
-
-from duckrun.core import Duckrun
-
-__version__ = "0.2.14.dev2"
-
-# Expose unified connect method at module level
-connect = Duckrun.connect
-
-__all__ = ["Duckrun", "connect"]