duckrun 0.2.9.dev3__tar.gz → 0.2.9.dev5__tar.gz

{duckrun-0.2.9.dev3 → duckrun-0.2.9.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.9.dev3
+Version: 0.2.9.dev5
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT

{duckrun-0.2.9.dev3 → duckrun-0.2.9.dev5}/duckrun/__init__.py

@@ -2,7 +2,7 @@
 
 from duckrun.core import Duckrun
 
-__version__ = "0.2.9.dev3"
+__version__ = "0.2.9.dev5"
 
 # Expose unified connect method at module level
 connect = Duckrun.connect

{duckrun-0.2.9.dev3 → duckrun-0.2.9.dev5}/duckrun/semantic_model.py

@@ -129,9 +129,12 @@ def check_dataset_exists(dataset_name, workspace_id, client):
         return False
 
 
-def refresh_dataset(dataset_name, workspace_id, client):
-    """Refresh a dataset and monitor progress"""
-    dataset_id = get_dataset_id(dataset_name, workspace_id, client)
+def refresh_dataset(dataset_name, workspace_id, client, dataset_id=None):
+    """Refresh a dataset and monitor progress using Power BI API"""
+    
+    # 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",
@@ -141,39 +144,46 @@ def refresh_dataset(dataset_name, workspace_id, client):
         "objects": []
     }
     
-    response = client.post(
-        f"/v1/workspaces/{workspace_id}/semanticModels/{dataset_id}/refreshes",
-        json=payload
-    )
+    # 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=payload)
     
     if response.status_code in [200, 202]:
         print(f"✓ Refresh initiated")
         
-        refresh_id = response.json().get('id')
-        if refresh_id:
-            print("   Monitoring refresh progress...")
-            max_attempts = 60
-            for attempt in range(max_attempts):
-                time.sleep(5)
-                
-                status_response = client.get(
-                    f"/v1/workspaces/{workspace_id}/semanticModels/{dataset_id}/refreshes/{refresh_id}"
-                )
-                status = status_response.json().get('status')
-                
-                if status == 'Completed':
-                    print(f"✓ Refresh completed successfully")
-                    return
-                elif status == 'Failed':
-                    error = status_response.json().get('error', {})
-                    raise Exception(f"Refresh failed: {error.get('message', 'Unknown error')}")
-                elif status == 'Cancelled':
-                    raise Exception("Refresh was cancelled")
+        # For 202, get the refresh_id from the Location header
+        if response.status_code == 202:
+            location = response.headers.get('Location')
+            if location:
+                refresh_id = location.split('/')[-1]
+                print("   Monitoring refresh progress...")
+                max_attempts = 60
+                for attempt in range(max_attempts):
+                    time.sleep(5)
+                    
+                    # Check refresh status using Power BI API
+                    status_url = f"https://api.powerbi.com/v1.0/myorg/datasets/{dataset_id}/refreshes/{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"✓ Refresh completed successfully")
+                        return
+                    elif status == 'Failed':
+                        error = status_response.json().get('serviceExceptionJson', '')
+                        raise Exception(f"Refresh failed: {error}")
+                    elif status == 'Cancelled':
+                        raise Exception("Refresh was cancelled")
+                    
+                    if attempt % 6 == 0:
+                        print(f"   Status: {status}...")
                 
-                if attempt % 6 == 0:
-                    print(f"   Status: {status}...")
-            
-            raise Exception(f"Refresh timed out")
+                raise Exception(f"Refresh timed out")
+    else:
+        response.raise_for_status()
 
 
 def download_bim_from_github(url):
@@ -246,7 +256,7 @@ def update_bim_for_directlake(bim_content, workspace_id, lakehouse_id, schema_na
 
 
 def create_dataset_from_bim(dataset_name, bim_content, workspace_id, client):
-    """Create semantic model from BIM using Fabric REST API"""
+    """Create semantic model from BIM using Fabric REST API and return the dataset ID"""
     # Convert to base64
     bim_json = json.dumps(bim_content, indent=2)
     bim_base64 = base64.b64encode(bim_json.encode('utf-8')).decode('utf-8')
@@ -280,7 +290,7 @@ def create_dataset_from_bim(dataset_name, bim_content, workspace_id, client):
     
     print(f"✓ Semantic model created")
     
-    # Handle long-running operation
+    # Handle long-running operation and return the dataset ID
     if response.status_code == 202:
         operation_id = response.headers.get('x-ms-operation-id')
         print(f"   Waiting for operation to complete...")
@@ -288,17 +298,38 @@ def create_dataset_from_bim(dataset_name, bim_content, workspace_id, client):
         max_attempts = 30
         for attempt in range(max_attempts):
             time.sleep(2)
+            
+            # Get operation result (not just status)
+            result_response = client.get(f"/v1/operations/{operation_id}/result")
+            
+            # Check if operation is complete by getting the status
             status_response = client.get(f"/v1/operations/{operation_id}")
             status = status_response.json().get('status')
             
             if status == 'Succeeded':
                 print(f"✓ Operation completed")
-                break
+                # Return the created dataset ID from the result
+                result_data = result_response.json()
+                dataset_id = result_data.get('id')
+                if dataset_id:
+                    return dataset_id
+                else:
+                    # Fallback: search for the dataset by name
+                    return get_dataset_id(dataset_name, workspace_id, client)
             elif status == 'Failed':
                 error = status_response.json().get('error', {})
                 raise Exception(f"Operation failed: {error.get('message')}")
             elif attempt == max_attempts - 1:
                 raise Exception(f"Operation timed out")
+    
+    # For non-async responses (status 200/201)
+    result_data = response.json()
+    dataset_id = result_data.get('id')
+    if dataset_id:
+        return dataset_id
+    else:
+        # Fallback: search for the dataset by name
+        return get_dataset_id(dataset_name, workspace_id, client)
 
 
 def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_name, dataset_name, 
@@ -365,17 +396,18 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         modified_bim['name'] = dataset_name
         modified_bim['id'] = dataset_name
         
-        # Step 5: Deploy
+        # Step 5: Deploy and get the dataset ID
         print("\n[Step 5/6] Deploying semantic model...")
-        create_dataset_from_bim(dataset_name, modified_bim, workspace_id, client)
+        dataset_id = create_dataset_from_bim(dataset_name, modified_bim, workspace_id, client)
+        print(f"   Dataset ID: {dataset_id}")
         
         if wait_seconds > 0:
-            print(f"   Waiting {wait_seconds} seconds for permissions...")
+            print(f"   Waiting {wait_seconds} seconds before refresh...")
             time.sleep(wait_seconds)
         
-        # Step 6: Refresh
+        # 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)
+        refresh_dataset(dataset_name, workspace_id, client, dataset_id=dataset_id)
         
         print("\n" + "=" * 70)
         print("🎉 Deployment Completed!")

{duckrun-0.2.9.dev3 → duckrun-0.2.9.dev5}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.9.dev3
+Version: 0.2.9.dev5
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT

{duckrun-0.2.9.dev3 → duckrun-0.2.9.dev5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.9.dev3"
+version = "0.2.9.dev5"
 description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
 readme = "README.md"
 license = {text = "MIT"}