duckrun 0.2.5.dev2__tar.gz → 0.2.6__tar.gz

{duckrun-0.2.5.dev2 → duckrun-0.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.5.dev2
+Version: 0.2.6
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT
@@ -26,12 +26,10 @@ 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 cannot contain spaces
+- **Workspace and lakehouse names with spaces are now 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.
 
-**Why no spaces?** Duckrun uses simple name-based paths instead of GUIDs. This keeps the code clean and readable, which is perfect for data engineering workspaces where naming conventions are already well-established. Just use underscores or hyphens instead: `my_workspace` or `my-lakehouse`.
-
 ## What It Does
 
 It does orchestration, arbitrary SQL statements, and file manipulation. That's it - just stuff I encounter in my daily workflow when working with Fabric notebooks.
@@ -52,20 +50,28 @@ pip install duckrun[local]
 ```python
 import duckrun
 
-# Connect to your Fabric lakehouse with a specific schema
-con = duckrun.connect("my_workspace/my_lakehouse.lakehouse/dbo")
+# 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")
+
+# 2. Connect to lakehouse with a specific schema
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+
+# Works with workspace names containing spaces!
+con = duckrun.connect("Data Analytics/Sales Data.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")
 
-# Explore data
+# 3. Explore data
 con.sql("SELECT * FROM my_table LIMIT 10").show()
 
-# Write to Delta tables (Spark-style API)
+# 4. Write to Delta tables (Spark-style API)
 con.sql("SELECT * FROM source").write.mode("overwrite").saveAsTable("target")
 
-# Upload/download files to/from OneLake Files
+# 5. Upload/download files to/from OneLake Files
 con.copy("./local_folder", "target_folder")  # Upload files
 con.download("target_folder", "./downloaded")  # Download files
 ```
@@ -75,15 +81,23 @@ That's it! No `sql_folder` needed for data exploration.
 ## Connection Format
 
 ```python
-# With schema (recommended for better performance)
-con = duckrun.connect("workspace/lakehouse.lakehouse/schema")
+# Workspace management (list and create lakehouses)
+ws = duckrun.connect("My Workspace")
+ws.list_lakehouses()  # Returns: ['lakehouse1', 'lakehouse2', ...]
+ws.create_lakehouse_if_not_exists("New Lakehouse")
+
+# Lakehouse connection with schema (recommended for best performance)
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+
+# Supports workspace names with spaces!
+con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
 
 # Without schema (defaults to 'dbo', scans all schemas)
 # ⚠️ This can be slow for large lakehouses!
-con = duckrun.connect("workspace/lakehouse.lakehouse")
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
 
-# With options
-con = duckrun.connect("workspace/lakehouse.lakehouse/dbo", sql_folder="./sql")
+# With SQL folder for pipeline orchestration
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo", sql_folder="./sql")
 ```
 
 ### Multi-Schema Support

{duckrun-0.2.5.dev2 → duckrun-0.2.6}/README.md

@@ -6,12 +6,10 @@ 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 cannot contain spaces
+- **Workspace and lakehouse names with spaces are now 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.
 
-**Why no spaces?** Duckrun uses simple name-based paths instead of GUIDs. This keeps the code clean and readable, which is perfect for data engineering workspaces where naming conventions are already well-established. Just use underscores or hyphens instead: `my_workspace` or `my-lakehouse`.
-
 ## What It Does
 
 It does orchestration, arbitrary SQL statements, and file manipulation. That's it - just stuff I encounter in my daily workflow when working with Fabric notebooks.
@@ -32,20 +30,28 @@ pip install duckrun[local]
 ```python
 import duckrun
 
-# Connect to your Fabric lakehouse with a specific schema
-con = duckrun.connect("my_workspace/my_lakehouse.lakehouse/dbo")
+# 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")
+
+# 2. Connect to lakehouse with a specific schema
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+
+# Works with workspace names containing spaces!
+con = duckrun.connect("Data Analytics/Sales Data.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")
 
-# Explore data
+# 3. Explore data
 con.sql("SELECT * FROM my_table LIMIT 10").show()
 
-# Write to Delta tables (Spark-style API)
+# 4. Write to Delta tables (Spark-style API)
 con.sql("SELECT * FROM source").write.mode("overwrite").saveAsTable("target")
 
-# Upload/download files to/from OneLake Files
+# 5. Upload/download files to/from OneLake Files
 con.copy("./local_folder", "target_folder")  # Upload files
 con.download("target_folder", "./downloaded")  # Download files
 ```
@@ -55,15 +61,23 @@ That's it! No `sql_folder` needed for data exploration.
 ## Connection Format
 
 ```python
-# With schema (recommended for better performance)
-con = duckrun.connect("workspace/lakehouse.lakehouse/schema")
+# Workspace management (list and create lakehouses)
+ws = duckrun.connect("My Workspace")
+ws.list_lakehouses()  # Returns: ['lakehouse1', 'lakehouse2', ...]
+ws.create_lakehouse_if_not_exists("New Lakehouse")
+
+# Lakehouse connection with schema (recommended for best performance)
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+
+# Supports workspace names with spaces!
+con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
 
 # Without schema (defaults to 'dbo', scans all schemas)
 # ⚠️ This can be slow for large lakehouses!
-con = duckrun.connect("workspace/lakehouse.lakehouse")
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
 
-# With options
-con = duckrun.connect("workspace/lakehouse.lakehouse/dbo", sql_folder="./sql")
+# With SQL folder for pipeline orchestration
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo", sql_folder="./sql")
 ```
 
 ### Multi-Schema Support

{duckrun-0.2.5.dev2 → duckrun-0.2.6}/duckrun/core.py

@@ -441,6 +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.
@@ -702,7 +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 +751,6 @@ class WorkspaceConnection:
             lakehouses = response.json().get("value", [])
             lakehouse_names = [lh.get("displayName", "") for lh in lakehouses]
             
-            print(f"Found {len(lakehouse_names)} lakehouses: {lakehouse_names}")
             return lakehouse_names
             
         except Exception as e:
@@ -749,7 +772,11 @@ 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.dev2 → duckrun-0.2.6}/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.dev2 → duckrun-0.2.6}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.5.dev2
+Version: 0.2.6
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 Author: mim
 License: MIT
@@ -26,12 +26,10 @@ 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 cannot contain spaces
+- **Workspace and lakehouse names with spaces are now 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.
 
-**Why no spaces?** Duckrun uses simple name-based paths instead of GUIDs. This keeps the code clean and readable, which is perfect for data engineering workspaces where naming conventions are already well-established. Just use underscores or hyphens instead: `my_workspace` or `my-lakehouse`.
-
 ## What It Does
 
 It does orchestration, arbitrary SQL statements, and file manipulation. That's it - just stuff I encounter in my daily workflow when working with Fabric notebooks.
@@ -52,20 +50,28 @@ pip install duckrun[local]
 ```python
 import duckrun
 
-# Connect to your Fabric lakehouse with a specific schema
-con = duckrun.connect("my_workspace/my_lakehouse.lakehouse/dbo")
+# 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")
+
+# 2. Connect to lakehouse with a specific schema
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+
+# Works with workspace names containing spaces!
+con = duckrun.connect("Data Analytics/Sales Data.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")
 
-# Explore data
+# 3. Explore data
 con.sql("SELECT * FROM my_table LIMIT 10").show()
 
-# Write to Delta tables (Spark-style API)
+# 4. Write to Delta tables (Spark-style API)
 con.sql("SELECT * FROM source").write.mode("overwrite").saveAsTable("target")
 
-# Upload/download files to/from OneLake Files
+# 5. Upload/download files to/from OneLake Files
 con.copy("./local_folder", "target_folder")  # Upload files
 con.download("target_folder", "./downloaded")  # Download files
 ```
@@ -75,15 +81,23 @@ That's it! No `sql_folder` needed for data exploration.
 ## Connection Format
 
 ```python
-# With schema (recommended for better performance)
-con = duckrun.connect("workspace/lakehouse.lakehouse/schema")
+# Workspace management (list and create lakehouses)
+ws = duckrun.connect("My Workspace")
+ws.list_lakehouses()  # Returns: ['lakehouse1', 'lakehouse2', ...]
+ws.create_lakehouse_if_not_exists("New Lakehouse")
+
+# Lakehouse connection with schema (recommended for best performance)
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
+
+# Supports workspace names with spaces!
+con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
 
 # Without schema (defaults to 'dbo', scans all schemas)
 # ⚠️ This can be slow for large lakehouses!
-con = duckrun.connect("workspace/lakehouse.lakehouse")
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
 
-# With options
-con = duckrun.connect("workspace/lakehouse.lakehouse/dbo", sql_folder="./sql")
+# With SQL folder for pipeline orchestration
+con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo", sql_folder="./sql")
 ```
 
 ### Multi-Schema Support

{duckrun-0.2.5.dev2 → duckrun-0.2.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.5.dev2"
+version = "0.2.6"
 description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
 readme = "README.md"
 license = {text = "MIT"}