duckrun 0.2.5.dev4__tar.gz → 0.2.6__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (17) hide show
  1. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/PKG-INFO +29 -15
  2. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/README.md +28 -14
  3. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/core.py +0 -1
  4. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun.egg-info/PKG-INFO +29 -15
  5. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/pyproject.toml +1 -1
  6. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/LICENSE +0 -0
  7. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/__init__.py +0 -0
  8. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/files.py +0 -0
  9. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/lakehouse.py +0 -0
  10. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/runner.py +0 -0
  11. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/stats.py +0 -0
  12. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/writer.py +0 -0
  13. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun.egg-info/SOURCES.txt +0 -0
  14. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun.egg-info/dependency_links.txt +0 -0
  15. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun.egg-info/requires.txt +0 -0
  16. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun.egg-info/top_level.txt +0 -0
  17. {duckrun-0.2.5.dev4 → duckrun-0.2.6}/setup.cfg +0 -0
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: duckrun
3
- Version: 0.2.5.dev4
3
+ Version: 0.2.6
4
4
  Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
5
5
  Author: mim
6
6
  License: MIT
@@ -26,12 +26,10 @@ A helper package for stuff that made my life easier when working with Fabric Pyt
26
26
 
27
27
  **Requirements:**
28
28
  - Lakehouse must have a schema (e.g., `dbo`, `sales`, `analytics`)
29
- - Workspace and lakehouse names cannot contain spaces
29
+ - **Workspace and lakehouse names with spaces are now fully supported!** ✅
30
30
 
31
31
  **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.
32
32
 
33
- **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`.
34
-
35
33
  ## What It Does
36
34
 
37
35
  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]
52
50
  ```python
53
51
  import duckrun
54
52
 
55
- # Connect to your Fabric lakehouse with a specific schema
56
- con = duckrun.connect("my_workspace/my_lakehouse.lakehouse/dbo")
53
+ # 1. Workspace Management (list and create lakehouses)
54
+ ws = duckrun.connect("My Workspace")
55
+ lakehouses = ws.list_lakehouses() # Returns list of lakehouse names
56
+ ws.create_lakehouse_if_not_exists("New Lakehouse")
57
+
58
+ # 2. Connect to lakehouse with a specific schema
59
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
60
+
61
+ # Works with workspace names containing spaces!
62
+ con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
57
63
 
58
64
  # Schema defaults to 'dbo' if not specified (scans all schemas)
59
65
  # ⚠️ WARNING: Scanning all schemas can be slow for large lakehouses!
60
- con = duckrun.connect("my_workspace/my_lakehouse.lakehouse")
66
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
61
67
 
62
- # Explore data
68
+ # 3. Explore data
63
69
  con.sql("SELECT * FROM my_table LIMIT 10").show()
64
70
 
65
- # Write to Delta tables (Spark-style API)
71
+ # 4. Write to Delta tables (Spark-style API)
66
72
  con.sql("SELECT * FROM source").write.mode("overwrite").saveAsTable("target")
67
73
 
68
- # Upload/download files to/from OneLake Files
74
+ # 5. Upload/download files to/from OneLake Files
69
75
  con.copy("./local_folder", "target_folder") # Upload files
70
76
  con.download("target_folder", "./downloaded") # Download files
71
77
  ```
@@ -75,15 +81,23 @@ That's it! No `sql_folder` needed for data exploration.
75
81
  ## Connection Format
76
82
 
77
83
  ```python
78
- # With schema (recommended for better performance)
79
- con = duckrun.connect("workspace/lakehouse.lakehouse/schema")
84
+ # Workspace management (list and create lakehouses)
85
+ ws = duckrun.connect("My Workspace")
86
+ ws.list_lakehouses() # Returns: ['lakehouse1', 'lakehouse2', ...]
87
+ ws.create_lakehouse_if_not_exists("New Lakehouse")
88
+
89
+ # Lakehouse connection with schema (recommended for best performance)
90
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
91
+
92
+ # Supports workspace names with spaces!
93
+ con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
80
94
 
81
95
  # Without schema (defaults to 'dbo', scans all schemas)
82
96
  # ⚠️ This can be slow for large lakehouses!
83
- con = duckrun.connect("workspace/lakehouse.lakehouse")
97
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
84
98
 
85
- # With options
86
- con = duckrun.connect("workspace/lakehouse.lakehouse/dbo", sql_folder="./sql")
99
+ # With SQL folder for pipeline orchestration
100
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo", sql_folder="./sql")
87
101
  ```
88
102
 
89
103
  ### Multi-Schema Support
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/README.md RENAMED
@@ -6,12 +6,10 @@ A helper package for stuff that made my life easier when working with Fabric Pyt
6
6
 
7
7
  **Requirements:**
8
8
  - Lakehouse must have a schema (e.g., `dbo`, `sales`, `analytics`)
9
- - Workspace and lakehouse names cannot contain spaces
9
+ - **Workspace and lakehouse names with spaces are now fully supported!** ✅
10
10
 
11
11
  **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.
12
12
 
13
- **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`.
14
-
15
13
  ## What It Does
16
14
 
17
15
  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]
32
30
  ```python
33
31
  import duckrun
34
32
 
35
- # Connect to your Fabric lakehouse with a specific schema
36
- con = duckrun.connect("my_workspace/my_lakehouse.lakehouse/dbo")
33
+ # 1. Workspace Management (list and create lakehouses)
34
+ ws = duckrun.connect("My Workspace")
35
+ lakehouses = ws.list_lakehouses() # Returns list of lakehouse names
36
+ ws.create_lakehouse_if_not_exists("New Lakehouse")
37
+
38
+ # 2. Connect to lakehouse with a specific schema
39
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
40
+
41
+ # Works with workspace names containing spaces!
42
+ con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
37
43
 
38
44
  # Schema defaults to 'dbo' if not specified (scans all schemas)
39
45
  # ⚠️ WARNING: Scanning all schemas can be slow for large lakehouses!
40
- con = duckrun.connect("my_workspace/my_lakehouse.lakehouse")
46
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
41
47
 
42
- # Explore data
48
+ # 3. Explore data
43
49
  con.sql("SELECT * FROM my_table LIMIT 10").show()
44
50
 
45
- # Write to Delta tables (Spark-style API)
51
+ # 4. Write to Delta tables (Spark-style API)
46
52
  con.sql("SELECT * FROM source").write.mode("overwrite").saveAsTable("target")
47
53
 
48
- # Upload/download files to/from OneLake Files
54
+ # 5. Upload/download files to/from OneLake Files
49
55
  con.copy("./local_folder", "target_folder") # Upload files
50
56
  con.download("target_folder", "./downloaded") # Download files
51
57
  ```
@@ -55,15 +61,23 @@ That's it! No `sql_folder` needed for data exploration.
55
61
  ## Connection Format
56
62
 
57
63
  ```python
58
- # With schema (recommended for better performance)
59
- con = duckrun.connect("workspace/lakehouse.lakehouse/schema")
64
+ # Workspace management (list and create lakehouses)
65
+ ws = duckrun.connect("My Workspace")
66
+ ws.list_lakehouses() # Returns: ['lakehouse1', 'lakehouse2', ...]
67
+ ws.create_lakehouse_if_not_exists("New Lakehouse")
68
+
69
+ # Lakehouse connection with schema (recommended for best performance)
70
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
71
+
72
+ # Supports workspace names with spaces!
73
+ con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
60
74
 
61
75
  # Without schema (defaults to 'dbo', scans all schemas)
62
76
  # ⚠️ This can be slow for large lakehouses!
63
- con = duckrun.connect("workspace/lakehouse.lakehouse")
77
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
64
78
 
65
- # With options
66
- con = duckrun.connect("workspace/lakehouse.lakehouse/dbo", sql_folder="./sql")
79
+ # With SQL folder for pipeline orchestration
80
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo", sql_folder="./sql")
67
81
  ```
68
82
 
69
83
  ### Multi-Schema Support
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/core.py RENAMED
@@ -751,7 +751,6 @@ class WorkspaceConnection:
751
751
  lakehouses = response.json().get("value", [])
752
752
  lakehouse_names = [lh.get("displayName", "") for lh in lakehouses]
753
753
 
754
- print(f"Found {len(lakehouse_names)} lakehouses: {lakehouse_names}")
755
754
  return lakehouse_names
756
755
 
757
756
  except Exception as e:
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun.egg-info/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: duckrun
3
- Version: 0.2.5.dev4
3
+ Version: 0.2.6
4
4
  Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
5
5
  Author: mim
6
6
  License: MIT
@@ -26,12 +26,10 @@ A helper package for stuff that made my life easier when working with Fabric Pyt
26
26
 
27
27
  **Requirements:**
28
28
  - Lakehouse must have a schema (e.g., `dbo`, `sales`, `analytics`)
29
- - Workspace and lakehouse names cannot contain spaces
29
+ - **Workspace and lakehouse names with spaces are now fully supported!** ✅
30
30
 
31
31
  **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.
32
32
 
33
- **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`.
34
-
35
33
  ## What It Does
36
34
 
37
35
  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]
52
50
  ```python
53
51
  import duckrun
54
52
 
55
- # Connect to your Fabric lakehouse with a specific schema
56
- con = duckrun.connect("my_workspace/my_lakehouse.lakehouse/dbo")
53
+ # 1. Workspace Management (list and create lakehouses)
54
+ ws = duckrun.connect("My Workspace")
55
+ lakehouses = ws.list_lakehouses() # Returns list of lakehouse names
56
+ ws.create_lakehouse_if_not_exists("New Lakehouse")
57
+
58
+ # 2. Connect to lakehouse with a specific schema
59
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
60
+
61
+ # Works with workspace names containing spaces!
62
+ con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
57
63
 
58
64
  # Schema defaults to 'dbo' if not specified (scans all schemas)
59
65
  # ⚠️ WARNING: Scanning all schemas can be slow for large lakehouses!
60
- con = duckrun.connect("my_workspace/my_lakehouse.lakehouse")
66
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
61
67
 
62
- # Explore data
68
+ # 3. Explore data
63
69
  con.sql("SELECT * FROM my_table LIMIT 10").show()
64
70
 
65
- # Write to Delta tables (Spark-style API)
71
+ # 4. Write to Delta tables (Spark-style API)
66
72
  con.sql("SELECT * FROM source").write.mode("overwrite").saveAsTable("target")
67
73
 
68
- # Upload/download files to/from OneLake Files
74
+ # 5. Upload/download files to/from OneLake Files
69
75
  con.copy("./local_folder", "target_folder") # Upload files
70
76
  con.download("target_folder", "./downloaded") # Download files
71
77
  ```
@@ -75,15 +81,23 @@ That's it! No `sql_folder` needed for data exploration.
75
81
  ## Connection Format
76
82
 
77
83
  ```python
78
- # With schema (recommended for better performance)
79
- con = duckrun.connect("workspace/lakehouse.lakehouse/schema")
84
+ # Workspace management (list and create lakehouses)
85
+ ws = duckrun.connect("My Workspace")
86
+ ws.list_lakehouses() # Returns: ['lakehouse1', 'lakehouse2', ...]
87
+ ws.create_lakehouse_if_not_exists("New Lakehouse")
88
+
89
+ # Lakehouse connection with schema (recommended for best performance)
90
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo")
91
+
92
+ # Supports workspace names with spaces!
93
+ con = duckrun.connect("Data Analytics/Sales Data.lakehouse/analytics")
80
94
 
81
95
  # Without schema (defaults to 'dbo', scans all schemas)
82
96
  # ⚠️ This can be slow for large lakehouses!
83
- con = duckrun.connect("workspace/lakehouse.lakehouse")
97
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
84
98
 
85
- # With options
86
- con = duckrun.connect("workspace/lakehouse.lakehouse/dbo", sql_folder="./sql")
99
+ # With SQL folder for pipeline orchestration
100
+ con = duckrun.connect("My Workspace/My Lakehouse.lakehouse/dbo", sql_folder="./sql")
87
101
  ```
88
102
 
89
103
  ### Multi-Schema Support
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/pyproject.toml RENAMED
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "duckrun"
7
- version = "0.2.5.dev4"
7
+ version = "0.2.6"
8
8
  description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
9
9
  readme = "README.md"
10
10
  license = {text = "MIT"}
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/LICENSE RENAMED
File without changes
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/files.py RENAMED
File without changes
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/runner.py RENAMED
File without changes
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/stats.py RENAMED
File without changes
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/duckrun/writer.py RENAMED
File without changes
{duckrun-0.2.5.dev4 → duckrun-0.2.6}/setup.cfg RENAMED
File without changes