duckrun 0.2.16.dev1__py3-none-any.whl → 0.2.17__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.

Potentially problematic release.


This version of duckrun might be problematic. Click here for more details.

duckrun/runner.py CHANGED
@@ -7,45 +7,7 @@ import importlib.util
7
7
  from typing import List, Tuple, Dict, Optional, Callable, Any
8
8
  from string import Template
9
9
  from deltalake import DeltaTable, write_deltalake
10
- # Row Group configuration for optimal Delta Lake performance
11
- RG = 8_000_000
12
-
13
-
14
- def _build_write_deltalake_args(path, df, mode, schema_mode=None, partition_by=None):
15
- """
16
- Build arguments for write_deltalake based on requirements:
17
- - If schema_mode='merge': use rust engine (no row group params)
18
- - Otherwise: use pyarrow engine with row group optimization (if supported)
19
- """
20
- args = {
21
- 'table_or_uri': path,
22
- 'data': df,
23
- 'mode': mode
24
- }
25
-
26
- # Add partition_by if specified
27
- if partition_by:
28
- args['partition_by'] = partition_by
29
-
30
- # Engine selection based on schema_mode
31
- if schema_mode == 'merge':
32
- # Use rust engine for schema merging (no row group params supported)
33
- args['schema_mode'] = 'merge'
34
- args['engine'] = 'rust'
35
- else:
36
- # Try to use pyarrow engine with row group optimization
37
- # Check if row group parameters are supported by inspecting function signature
38
- import inspect
39
- sig = inspect.signature(write_deltalake)
40
-
41
- if 'max_rows_per_file' in sig.parameters:
42
- # Older deltalake version - use row group optimization
43
- args['max_rows_per_file'] = RG
44
- args['max_rows_per_group'] = RG
45
- args['min_rows_per_group'] = RG
46
- # For newer versions, just use default parameters
47
-
48
- return args
10
+ from .writer import _build_write_deltalake_args
49
11
 
50
12
 
51
13
  def run(duckrun_instance, pipeline: List[Tuple]) -> bool:
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: duckrun
3
- Version: 0.2.16.dev1
3
+ Version: 0.2.17
4
4
  Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
5
5
  Author: mim
6
6
  License: MIT
@@ -3,12 +3,12 @@ duckrun/auth.py,sha256=EMaf-L2zeNOjbHOT97xYxfZNfWo4WrwrU1h3vBQTgEc,9624
3
3
  duckrun/core.py,sha256=c98sASAWlq0DDIR9gYbj5ZaKOa6MoO8Z09qhRhG4JWI,67097
4
4
  duckrun/files.py,sha256=Fvdjg3DyHJzIVzKo8M_j-eGz4zU61lOB38Y_onbQJkI,10137
5
5
  duckrun/lakehouse.py,sha256=j--Z3zo8AOWt1GF9VzRosmmTAy6ey2D0LVubti58twU,14109
6
- duckrun/runner.py,sha256=JnRJoQ_Db__iXlhjTohplXR83NUJxItgyaa7AzrDxwE,14833
6
+ duckrun/runner.py,sha256=NGVyerJA44UP2umRdndfL0fuFM_gdOZmuJUz-PLOFf0,13461
7
7
  duckrun/semantic_model.py,sha256=obzlN2-dbEW3JmDop-vrZGGGLi9u3ThhTbgtDjou7uY,29509
8
8
  duckrun/stats.py,sha256=EqrCN1xwGo5nZgwezBvb6RepXT6b8H7xgK0yJJGFLfE,15155
9
9
  duckrun/writer.py,sha256=wIsU77DSj4J7d9_bIhvk6AbC51uUrLW0e6pcSPQOY1c,9424
10
- duckrun-0.2.16.dev1.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
11
- duckrun-0.2.16.dev1.dist-info/METADATA,sha256=RmwiOuQMHpS94rUjY0Sveu8Yzwbwp8ekZfta0d8tNAg,20771
12
- duckrun-0.2.16.dev1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
13
- duckrun-0.2.16.dev1.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
14
- duckrun-0.2.16.dev1.dist-info/RECORD,,
10
+ duckrun-0.2.17.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
11
+ duckrun-0.2.17.dist-info/METADATA,sha256=Id1vgyEEjsd4-sklkqOy1w1g3sdydmTdFFj6DMPd6bY,20766
12
+ duckrun-0.2.17.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
13
+ duckrun-0.2.17.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
14
+ duckrun-0.2.17.dist-info/RECORD,,