duckrun 0.2.5.dev4__py3-none-any.whl → 0.2.6__py3-none-any.whl
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.
- duckrun/core.py +0 -1
- {duckrun-0.2.5.dev4.dist-info → duckrun-0.2.6.dist-info}/METADATA +29 -15
- duckrun-0.2.6.dist-info/RECORD +12 -0
- duckrun-0.2.5.dev4.dist-info/RECORD +0 -12
- {duckrun-0.2.5.dev4.dist-info → duckrun-0.2.6.dist-info}/WHEEL +0 -0
- {duckrun-0.2.5.dev4.dist-info → duckrun-0.2.6.dist-info}/licenses/LICENSE +0 -0
- {duckrun-0.2.5.dev4.dist-info → duckrun-0.2.6.dist-info}/top_level.txt +0 -0
duckrun/core.py
CHANGED
@@ -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:
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: duckrun
|
3
|
-
Version: 0.2.
|
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
|
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
|
-
#
|
56
|
-
|
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("
|
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
|
-
#
|
79
|
-
|
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("
|
97
|
+
con = duckrun.connect("My Workspace/My Lakehouse.lakehouse")
|
84
98
|
|
85
|
-
# With
|
86
|
-
con = duckrun.connect("
|
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
|
@@ -0,0 +1,12 @@
|
|
1
|
+
duckrun/__init__.py,sha256=XA85pL2vK1AkmBic8e7WxeqNvcd6SjFX4zsQpImDO6E,230
|
2
|
+
duckrun/core.py,sha256=Y4-5H83Xw0mZa12QM5pcC7qOPidrDFASLcGIoUW3zwY,39394
|
3
|
+
duckrun/files.py,sha256=piWRU5w9jHrW-wuV4Gf-SKY_jhFv9eflxgWO8AZCQTI,10495
|
4
|
+
duckrun/lakehouse.py,sha256=j--Z3zo8AOWt1GF9VzRosmmTAy6ey2D0LVubti58twU,14109
|
5
|
+
duckrun/runner.py,sha256=XsQqWlesFD2cuhH2gsQj3Astg0XN7xhW15WPmr8D65I,13797
|
6
|
+
duckrun/stats.py,sha256=2FTqoQNVjD84-H1HjStHxZkOpAGKXS79M55B00pOlok,9804
|
7
|
+
duckrun/writer.py,sha256=eWrGtDQTbXi8H3sSt2WucYTdEQUjK97KmQxzCbqAuMs,6221
|
8
|
+
duckrun-0.2.6.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
|
9
|
+
duckrun-0.2.6.dist-info/METADATA,sha256=i8kvmnqpsddtJGq5GD44SFif0YTN-UFFviPyQZMPHn0,18799
|
10
|
+
duckrun-0.2.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
11
|
+
duckrun-0.2.6.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
|
12
|
+
duckrun-0.2.6.dist-info/RECORD,,
|
@@ -1,12 +0,0 @@
|
|
1
|
-
duckrun/__init__.py,sha256=XA85pL2vK1AkmBic8e7WxeqNvcd6SjFX4zsQpImDO6E,230
|
2
|
-
duckrun/core.py,sha256=6Us3dRuQFCziK12r0j2CuwgcDQeV78iEeLcA40IwIiA,39476
|
3
|
-
duckrun/files.py,sha256=piWRU5w9jHrW-wuV4Gf-SKY_jhFv9eflxgWO8AZCQTI,10495
|
4
|
-
duckrun/lakehouse.py,sha256=j--Z3zo8AOWt1GF9VzRosmmTAy6ey2D0LVubti58twU,14109
|
5
|
-
duckrun/runner.py,sha256=XsQqWlesFD2cuhH2gsQj3Astg0XN7xhW15WPmr8D65I,13797
|
6
|
-
duckrun/stats.py,sha256=2FTqoQNVjD84-H1HjStHxZkOpAGKXS79M55B00pOlok,9804
|
7
|
-
duckrun/writer.py,sha256=eWrGtDQTbXi8H3sSt2WucYTdEQUjK97KmQxzCbqAuMs,6221
|
8
|
-
duckrun-0.2.5.dev4.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
|
9
|
-
duckrun-0.2.5.dev4.dist-info/METADATA,sha256=HE5rFI5A227bw-prSq3cHv9wR9-etSYJD31lIrKjpzs,18344
|
10
|
-
duckrun-0.2.5.dev4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
11
|
-
duckrun-0.2.5.dev4.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
|
12
|
-
duckrun-0.2.5.dev4.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|