duckrun 0.2.5.dev1__tar.gz → 0.2.5.dev4__tar.gz

{duckrun-0.2.5.dev1 → duckrun-0.2.5.dev4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.5.dev1
+Version: 0.2.5.dev4
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT

{duckrun-0.2.5.dev1 → duckrun-0.2.5.dev4}/duckrun/core.py

@@ -61,10 +61,20 @@ class Duckrun:
         self.scan_all_schemas = scan_all_schemas
         self.storage_account = storage_account
         
-        # Construct proper ABFSS URLs using GUIDs
-        # Both Tables and Files use lakehouse GUID directly (no .Lakehouse suffix)
-        self.table_base_url = f'abfss://{workspace_id}@{storage_account}.dfs.fabric.microsoft.com/{lakehouse_id}/Tables/'
-        self.files_base_url = f'abfss://{workspace_id}@{storage_account}.dfs.fabric.microsoft.com/{lakehouse_id}/Files/'
+        # Construct proper ABFSS URLs
+        import re
+        guid_pattern = re.compile(r'^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$', re.IGNORECASE)
+        # If lakehouse_id is a GUID, use as-is
+        if guid_pattern.match(lakehouse_id):
+            lakehouse_url_part = lakehouse_id
+        else:
+            # If workspace name has no spaces, always append .lakehouse unless already present
+            if " " not in workspace_id and not lakehouse_id.endswith('.lakehouse'):
+                lakehouse_url_part = f'{lakehouse_id}.lakehouse'
+            else:
+                lakehouse_url_part = lakehouse_id
+        self.table_base_url = f'abfss://{workspace_id}@{storage_account}.dfs.fabric.microsoft.com/{lakehouse_url_part}/Tables/'
+        self.files_base_url = f'abfss://{workspace_id}@{storage_account}.dfs.fabric.microsoft.com/{lakehouse_url_part}/Files/'
         
         # Keep legacy properties for backward compatibility
         self.workspace = workspace_id  
@@ -326,7 +336,19 @@ class Duckrun:
         url = f"abfss://{self.workspace}@{self.storage_account}.dfs.fabric.microsoft.com/"
         store = AzureStore.from_url(url, bearer_token=token)
         
-        base_path = f"{self.lakehouse_name}/Tables/"
+        # Use the same lakehouse URL part logic as in __init__ to ensure .lakehouse suffix is added when needed
+        import re
+        guid_pattern = re.compile(r'^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$', re.IGNORECASE)
+        if guid_pattern.match(self.lakehouse_id):
+            lakehouse_url_part = self.lakehouse_id
+        else:
+            # If workspace name has no spaces, always append .lakehouse unless already present
+            if " " not in self.workspace_id and not self.lakehouse_id.endswith('.lakehouse'):
+                lakehouse_url_part = f'{self.lakehouse_id}.lakehouse'
+            else:
+                lakehouse_url_part = self.lakehouse_id
+        
+        base_path = f"{lakehouse_url_part}/Tables/"
         tables_found = []
         
         if self.scan_all_schemas:
@@ -419,6 +441,26 @@ class Duckrun:
             print(f"❌ Error attaching lakehouse: {e}")
             print("Continuing without pre-attached tables.")
 
+    def get_workspace_id(self) -> str:
+        """
+        Get the workspace ID (GUID or name without spaces).
+        Use this when passing workspace parameter to Python functions.
+        
+        Returns:
+            Workspace ID - either a GUID or workspace name without spaces
+        """
+        return self.workspace_id
+    
+    def get_lakehouse_id(self) -> str:
+        """
+        Get the lakehouse ID (GUID or name).
+        Use this when passing lakehouse parameter to Python functions.
+        
+        Returns:
+            Lakehouse ID - either a GUID or lakehouse name
+        """
+        return self.lakehouse_id
+
     def run(self, pipeline: List[Tuple]) -> bool:
         """
         Execute pipeline of tasks.
@@ -680,7 +722,11 @@ class WorkspaceConnection:
             try:
                 import notebookutils  # type: ignore
                 token = notebookutils.credentials.getToken("pbi")
-                workspace_id = notebookutils.runtime.context.get("workspaceId")
+                # 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...")
@@ -727,7 +773,11 @@ class WorkspaceConnection:
             try:
                 import notebookutils  # type: ignore
                 token = notebookutils.credentials.getToken("pbi")
-                workspace_id = notebookutils.runtime.context.get("workspaceId")
+                # 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...")

{duckrun-0.2.5.dev1 → duckrun-0.2.5.dev4}/duckrun/runner.py

@@ -110,12 +110,40 @@ def run(duckrun_instance, pipeline: List[Tuple]) -> bool:
 
 
 def _run_python(duckrun_instance, name: str, args: tuple) -> Any:
-    """Execute Python task, return result"""
+    """
+    Execute Python task, return result.
+    
+    Automatically substitutes workspace/lakehouse names in args with their resolved IDs
+    to prevent URL encoding issues with names containing spaces.
+    """
     duckrun_instance._create_onelake_secret()
     func = _load_py_function(duckrun_instance, name)
     if not func:
         raise RuntimeError(f"Python function '{name}' not found")
     
+    # Get original and resolved names
+    original_workspace = duckrun_instance.workspace
+    original_lakehouse = duckrun_instance.lakehouse_name
+    resolved_workspace = duckrun_instance.workspace_id
+    resolved_lakehouse = duckrun_instance.lakehouse_id
+    
+    # Substitute workspace/lakehouse names in args if they differ
+    # This prevents URL encoding issues when names contain spaces
+    substituted_args = []
+    needs_substitution = (original_workspace != resolved_workspace or 
+                         original_lakehouse != resolved_lakehouse)
+    
+    if needs_substitution:
+        for arg in args:
+            if arg == original_workspace:
+                substituted_args.append(resolved_workspace)
+            elif arg == original_lakehouse:
+                substituted_args.append(resolved_lakehouse)
+            else:
+                substituted_args.append(arg)
+        args = tuple(substituted_args)
+        print(f"📝 Auto-substituted workspace/lakehouse names in args for URL compatibility")
+    
     print(f"Running Python: {name}{args}")
     result = func(*args)
     print(f"✅ Python '{name}' completed")

{duckrun-0.2.5.dev1 → duckrun-0.2.5.dev4}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.5.dev1
+Version: 0.2.5.dev4
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT

{duckrun-0.2.5.dev1 → duckrun-0.2.5.dev4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.5.dev1"
+version = "0.2.5.dev4"
 description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
 readme = "README.md"
 license = {text = "MIT"}