forked from microsoft/semantic-link-labs
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy path_helper_functions.py
1638 lines (1285 loc) · 46.5 KB
/
_helper_functions.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import sempy.fabric as fabric
import re
import json
import base64
import time
import uuid
from sempy.fabric.exceptions import FabricHTTPException
import pandas as pd
from functools import wraps
import datetime
from typing import Optional, Tuple, List
from uuid import UUID
import sempy_labs._icons as icons
from azure.core.credentials import TokenCredential, AccessToken
import urllib.parse
import numpy as np
from IPython.display import display, HTML
import requests
import sempy_labs._authentication as auth
def _build_url(url: str, params: dict) -> str:
"""
Build the url with a list of parameters
"""
url_parts = list(urllib.parse.urlparse(url))
url_parts[4] = urllib.parse.urlencode(params)
url = urllib.parse.urlunparse(url_parts)
return url
def create_abfss_path(
lakehouse_id: UUID,
lakehouse_workspace_id: UUID,
delta_table_name: Optional[str] = None,
) -> str:
"""
Creates an abfss path for a delta table in a Fabric lakehouse.
Parameters
----------
lakehouse_id : uuid.UUID
ID of the Fabric lakehouse.
lakehouse_workspace_id : uuid.UUID
ID of the Fabric workspace.
delta_table_name : str, default=None
Name of the delta table name.
Returns
-------
str
An abfss path which can be used to save/reference a delta table in a Fabric lakehouse or lakehouse.
"""
fp = _get_default_file_path()
path = f"abfss://{lakehouse_workspace_id}@{fp}/{lakehouse_id}"
if delta_table_name is not None:
path += f"/Tables/{delta_table_name}"
return path
def _get_default_file_path() -> str:
default_file_storage = _get_fabric_context_setting(name="fs.defaultFS")
return default_file_storage.split("@")[-1][:-1]
def _split_abfss_path(path: str) -> Tuple[UUID, UUID, str]:
parsed_url = urllib.parse.urlparse(path)
workspace_id = parsed_url.netloc.split("@")[0]
item_id = parsed_url.path.lstrip("/").split("/")[0]
delta_table_name = parsed_url.path.split("/")[-1]
return workspace_id, item_id, delta_table_name
def format_dax_object_name(table: str, column: str) -> str:
"""
Formats a table/column combination to the 'Table Name'[Column Name] format.
Parameters
----------
table : str
The name of the table.
column : str
The name of the column.
Returns
-------
str
The fully qualified object name.
"""
return "'" + table + "'[" + column + "]"
def create_relationship_name(
from_table: str, from_column: str, to_table: str, to_column: str
) -> str:
"""
Formats a relationship's table/columns into a fully qualified name.
Parameters
----------
from_table : str
The name of the table on the 'from' side of the relationship.
from_column : str
The name of the column on the 'from' side of the relationship.
to_table : str
The name of the table on the 'to' side of the relationship.
to_column : str
The name of the column on the 'to' side of the relationship.
Returns
-------
str
The fully qualified relationship name.
"""
return (
format_dax_object_name(from_table, from_column)
+ " -> "
+ format_dax_object_name(to_table, to_column)
)
def resolve_report_id(report: str, workspace: Optional[str | UUID] = None) -> UUID:
"""
Obtains the ID of the Power BI report.
Parameters
----------
report : str
The name of the Power BI report.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
UUID
The ID of the Power BI report.
"""
return fabric.resolve_item_id(item_name=report, type="Report", workspace=workspace)
def resolve_report_name(report_id: UUID, workspace: Optional[str | UUID] = None) -> str:
"""
Obtains the name of the Power BI report.
Parameters
----------
report_id : uuid.UUID
The name of the Power BI report.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
str
The name of the Power BI report.
"""
return fabric.resolve_item_name(
item_id=report_id, type="Report", workspace=workspace
)
def resolve_item_id(
item: str | UUID, type: str, workspace: Optional[str] = None
) -> UUID:
if _is_valid_uuid(item):
return item
else:
return fabric.resolve_item_id(item_name=item, type=type, workspace=workspace)
def resolve_item_name_and_id(
item: str | UUID, type: Optional[str] = None, workspace: Optional[str | UUID] = None
) -> Tuple[str, UUID]:
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
if _is_valid_uuid(item):
item_id = item
item_name = fabric.resolve_item_name(
item_id=item_id, type=type, workspace=workspace_id
)
else:
if type is None:
raise ValueError(
f"{icons.warning} Must specify a 'type' if specifying a name as the 'item'."
)
item_name = item
item_id = fabric.resolve_item_id(
item_name=item, type=type, workspace=workspace_id
)
return item_name, item_id
def resolve_lakehouse_name_and_id(
lakehouse: Optional[str | UUID] = None, workspace: Optional[str | UUID] = None
) -> Tuple[str, UUID]:
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
type = "Lakehouse"
if lakehouse is None:
lakehouse_id = fabric.get_lakehouse_id()
lakehouse_name = fabric.resolve_item_name(
item_id=lakehouse_id, type=type, workspace=workspace_id
)
elif _is_valid_uuid(lakehouse):
lakehouse_id = lakehouse
lakehouse_name = fabric.resolve_item_name(
item_id=lakehouse_id, type=type, workspace=workspace_id
)
else:
lakehouse_name = lakehouse
lakehouse_id = fabric.resolve_item_id(
item_name=lakehouse, type=type, workspace=workspace_id
)
return lakehouse_name, lakehouse_id
def resolve_dataset_name_and_id(
dataset: str | UUID, workspace: Optional[str | UUID] = None
) -> Tuple[str, UUID]:
(dataset_name, dataset_id) = resolve_item_name_and_id(
item=dataset, type="SemanticModel", workspace=workspace
)
return dataset_name, dataset_id
def resolve_dataset_id(
dataset: str | UUID, workspace: Optional[str | UUID] = None
) -> UUID:
"""
Obtains the ID of the semantic model.
Parameters
----------
dataset : str | uuid.UUID
The name or ID of the semantic model.
workspace : str | uuid.UUID, default=None
The Fabric workspace name.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
uuid.UUID
The ID of the semantic model.
"""
if _is_valid_uuid(dataset):
dataset_id = dataset
else:
dataset_id = fabric.resolve_item_id(
item_name=dataset, type="SemanticModel", workspace=workspace
)
return dataset_id
def resolve_dataset_name(
dataset_id: UUID, workspace: Optional[str | UUID] = None
) -> str:
"""
Obtains the name of the semantic model.
Parameters
----------
dataset_id : uuid.UUID
The name of the semantic model.
workspace : str | uuid.UUID, default=None
The Fabric workspace name.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
str
The name of the semantic model.
"""
return fabric.resolve_item_name(
item_id=dataset_id, type="SemanticModel", workspace=workspace
)
def resolve_lakehouse_name(
lakehouse_id: Optional[UUID] = None, workspace: Optional[str | UUID] = None
) -> str:
"""
Obtains the name of the Fabric lakehouse.
Parameters
----------
lakehouse_id : uuid.UUID, default=None
The name of the Fabric lakehouse.
Defaults to None which resolves to the lakehouse attached to the notebook.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
str
The name of the Fabric lakehouse.
"""
if lakehouse_id is None:
lakehouse_id = fabric.get_lakehouse_id()
return fabric.resolve_item_name(
item_id=lakehouse_id, type="Lakehouse", workspace=workspace
)
def resolve_lakehouse_id(
lakehouse: Optional[str | UUID] = None, workspace: Optional[str | UUID] = None
) -> UUID:
"""
Obtains the ID of the Fabric lakehouse.
Parameters
----------
lakehouse : str | uuid.UUID, default=None
The name or ID of the Fabric lakehouse.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
uuid.UUID
The ID of the Fabric lakehouse.
"""
if lakehouse is None:
lakehouse_id = fabric.get_lakehouse_id()
elif _is_valid_uuid(lakehouse):
lakehouse_id = lakehouse
else:
lakehouse_id = fabric.resolve_item_id(
item_name=lakehouse, type="Lakehouse", workspace=workspace
)
return lakehouse_id
def get_direct_lake_sql_endpoint(
dataset: str | UUID, workspace: Optional[str | UUID] = None
) -> UUID:
"""
Obtains the SQL Endpoint ID of the semantic model.
Parameters
----------
dataset : str | uuid.UUID
The name or ID of the semantic model.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
uuid.UUID
The ID of SQL Endpoint.
"""
from sempy_labs.tom import connect_semantic_model
# dfP = fabric.list_partitions(dataset=dataset, workspace=workspace)
# dfP_filt = dfP[dfP["Mode"] == "DirectLake"]
# if len(dfP_filt) == 0:
# raise ValueError(
# f"The '{dataset}' semantic model in the '{workspace}' workspace is not in Direct Lake mode."
# )
with connect_semantic_model(
dataset=dataset, readonly=True, workspace=workspace
) as tom:
sqlEndpointId = None
for e in tom.model.Expressions:
if e.Name == "DatabaseQuery":
expr = e.Expression
matches = re.findall(r'"([^"]+)"', expr)
sqlEndpointId = matches[1]
if sqlEndpointId is None:
raise ValueError(f"{icons.red_dot} SQL Endpoint not found.")
return sqlEndpointId
def generate_embedded_filter(filter: str) -> str:
"""
Converts the filter expression to a filter expression which can be used by a Power BI embedded URL.
Parameters
----------
filter : str
The filter expression for an embedded Power BI report.
Returns
-------
str
A filter expression usable by a Power BI embedded URL.
"""
pattern = r"'[^']+'\[[^\[]+\]"
matches = re.findall(pattern, filter)
for match in matches:
matchReplace = (
match.replace("'", "")
.replace("[", "/")
.replace("]", "")
.replace(" ", "_x0020_")
.replace("@", "_00x40_")
.replace("+", "_0x2B_")
.replace("{", "_007B_")
.replace("}", "_007D_")
)
filter = filter.replace(match, matchReplace)
pattern = r"\[[^\[]+\]"
matches = re.findall(pattern, filter)
for match in matches:
matchReplace = (
match.replace("'", "")
.replace("[", "/")
.replace("]", "")
.replace(" ", "_x0020_")
.replace("@", "_00x40_")
.replace("+", "_0x2B_")
.replace("{", "_007B_")
.replace("}", "_007D_")
)
filter = filter.replace(match, matchReplace)
revised_filter = (
filter.replace("<=", "le")
.replace(">=", "ge")
.replace("<>", "ne")
.replace("!=", "ne")
.replace("==", "eq")
.replace("=", "eq")
.replace("<", "lt")
.replace(">", "gt")
.replace(" && ", " and ")
.replace(" & ", " and ")
.replace(" || ", " or ")
.replace(" | ", " or ")
.replace("{", "(")
.replace("}", ")")
)
return revised_filter
def save_as_delta_table(
dataframe,
delta_table_name: str,
write_mode: str,
merge_schema: bool = False,
schema: Optional[dict] = None,
lakehouse: Optional[str | UUID] = None,
workspace: Optional[str | UUID] = None,
):
"""
Saves a pandas dataframe as a delta table in a Fabric lakehouse.
Parameters
----------
dataframe : pandas.DataFrame
The dataframe to be saved as a delta table.
delta_table_name : str
The name of the delta table.
write_mode : str
The write mode for the save operation. Options: 'append', 'overwrite'.
merge_schema : bool, default=False
Merges the schemas of the dataframe to the delta table.
schema : dict, default=None
A dictionary showing the schema of the columns and their data types.
lakehouse : str | uuid.UUID, default=None
The Fabric lakehouse name or ID.
Defaults to None which resolves to the lakehouse attached to the notebook.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
"""
from pyspark.sql import SparkSession
from pyspark.sql.types import (
StringType,
IntegerType,
FloatType,
DateType,
StructType,
StructField,
BooleanType,
LongType,
DoubleType,
TimestampType,
)
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
(lakehouse_name, lakehouse_id) = resolve_lakehouse_name_and_id(
lakehouse=lakehouse, workspace=workspace_id
)
write_modes = ["append", "overwrite"]
write_mode = write_mode.lower()
if write_mode not in write_modes:
raise ValueError(
f"{icons.red_dot} Invalid 'write_type' parameter. Choose from one of the following values: {write_modes}."
)
if " " in delta_table_name:
raise ValueError(
f"{icons.red_dot} Invalid 'delta_table_name'. Delta tables in the lakehouse cannot have spaces in their names."
)
dataframe.columns = dataframe.columns.str.replace(" ", "_")
spark = _create_spark_session()
type_mapping = {
"string": StringType(),
"str": StringType(),
"integer": IntegerType(),
"int": IntegerType(),
"float": FloatType(),
"date": DateType(),
"bool": BooleanType(),
"boolean": BooleanType(),
"long": LongType(),
"double": DoubleType(),
"timestamp": TimestampType(),
}
if isinstance(dataframe, pd.DataFrame):
if schema is None:
spark_df = spark.createDataFrame(dataframe)
else:
schema_map = StructType(
[
StructField(column_name, type_mapping[data_type], True)
for column_name, data_type in schema.items()
]
)
spark_df = spark.createDataFrame(dataframe, schema_map)
else:
spark_df = dataframe
filePath = create_abfss_path(
lakehouse_id=lakehouse_id,
lakehouse_workspace_id=workspace_id,
delta_table_name=delta_table_name,
)
if merge_schema:
spark_df.write.mode(write_mode).format("delta").option(
"mergeSchema", "true"
).save(filePath)
else:
spark_df.write.mode(write_mode).format("delta").save(filePath)
print(
f"{icons.green_dot} The dataframe has been saved as the '{delta_table_name}' table in the '{lakehouse_name}' lakehouse within the '{workspace_name}' workspace."
)
def language_validate(language: str):
"""
Validateds that the language specified exists within the supported langauges.
Parameters
----------
language : str
The language code.
Returns
-------
bool
A True/False indication as to whether the language code is supported.
"""
url = "https://learn.microsoft.com/azure/ai-services/translator/language-support"
tables = pd.read_html(url)
df = tables[0]
df_filt = df[df["Language code"] == language]
df_filt2 = df[df["Language"] == language.capitalize()]
if len(df_filt) == 1:
lang = df_filt["Language"].iloc[0]
elif len(df_filt2) == 1:
lang = df_filt2["Language"].iloc[0]
else:
raise ValueError(
f"{icons.red_dot} The '{language}' language is not a valid language code. Please refer to this link for a list of valid language codes: {url}."
)
return lang
def resolve_workspace_name_and_id(
workspace: Optional[str | UUID] = None,
) -> Tuple[str, str]:
"""
Obtains the name and ID of the Fabric workspace.
Parameters
----------
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
str, str
The name and ID of the Fabric workspace.
"""
if workspace is None:
workspace_id = fabric.get_workspace_id()
workspace_name = fabric.resolve_workspace_name(workspace_id)
elif _is_valid_uuid(workspace):
workspace_id = workspace
workspace_name = fabric.resolve_workspace_name(workspace_id)
else:
workspace_name = workspace
workspace_id = fabric.resolve_workspace_id(workspace_name)
return str(workspace_name), str(workspace_id)
def _extract_json(dataframe: pd.DataFrame) -> dict:
payload = dataframe["payload"].iloc[0]
json_file = _decode_b64(payload)
return json.loads(json_file)
def _conv_b64(file):
loadJson = json.dumps(file)
f = base64.b64encode(loadJson.encode("utf-8")).decode("utf-8")
return f
def _decode_b64(file, format: Optional[str] = "utf-8"):
return base64.b64decode(file).decode(format)
def is_default_semantic_model(
dataset: str, workspace: Optional[str | UUID] = None
) -> bool:
"""
Identifies whether a semantic model is a default semantic model.
Parameters
----------
dataset : str
The name of the semantic model.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
bool
A True/False value indicating whether the semantic model is a default semantic model.
"""
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
dfI = fabric.list_items(workspace=workspace_id)
filtered_df = dfI.groupby("Display Name").filter(
lambda x: set(["Warehouse", "SemanticModel"]).issubset(set(x["Type"]))
or set(["Lakehouse", "SemanticModel"]).issubset(set(x["Type"]))
)
default_semantic_models = filtered_df["Display Name"].unique().tolist()
return dataset in default_semantic_models
def resolve_item_type(item_id: UUID, workspace: Optional[str | UUID] = None) -> str:
"""
Obtains the item type for a given Fabric Item Id within a Fabric workspace.
Parameters
----------
item_id : uuid.UUID
The item/artifact Id.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
str
The item type for the item Id.
"""
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
dfI = fabric.list_items(workspace=workspace_id)
dfI_filt = dfI[dfI["Id"] == item_id]
if dfI_filt.empty:
raise ValueError(
f"{icons.red_dot} Invalid 'item_id' parameter. The '{item_id}' item was not found in the '{workspace_name}' workspace."
)
return dfI_filt["Type"].iloc[0]
def resolve_dataset_from_report(
report: str | UUID, workspace: Optional[str | UUID] = None
) -> Tuple[UUID, str, UUID, str]:
"""
Obtains the basic semantic model properties from which the report's data is sourced.
Parameters
----------
report : str | uuid.UUID
The name or ID of the Power BI report.
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
Tuple[uuid.UUID, str, uuid.UUID, str]
The semantic model UUID, semantic model name, semantic model workspace UUID, semantic model workspace name
"""
from sempy_labs.report._generate_report import _get_report
dfR = _get_report(report=report, workspace=workspace)
dataset_id = dfR["Dataset Id"].iloc[0]
dataset_workspace_id = dfR["Dataset Workspace Id"].iloc[0]
dataset_workspace = fabric.resolve_workspace_name(dataset_workspace_id)
dataset_name = resolve_dataset_name(
dataset_id=dataset_id, workspace=dataset_workspace
)
return dataset_id, dataset_name, dataset_workspace_id, dataset_workspace
def _add_part(target_dict, path, payload):
part = {"path": path, "payload": payload, "payloadType": "InlineBase64"}
target_dict["definition"]["parts"].append(part)
def resolve_workspace_capacity(
workspace: Optional[str | UUID] = None,
) -> Tuple[UUID, str]:
"""
Obtains the capacity Id and capacity name for a given workspace.
Parameters
----------
workspace : str | uuid.UUID, default=None
The Fabric workspace name or UUID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
Tuple[uuid.UUID, str]
capacity Id; capacity came.
"""
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
filter_condition = urllib.parse.quote(workspace_id)
dfW = fabric.list_workspaces(filter=f"id eq '{filter_condition}'")
capacity_id = dfW["Capacity Id"].iloc[0]
dfC = fabric.list_capacities()
dfC_filt = dfC[dfC["Id"] == capacity_id]
if len(dfC_filt) == 1:
capacity_name = dfC_filt["Display Name"].iloc[0]
else:
capacity_name = None
return capacity_id, capacity_name
def get_capacity_id(workspace: Optional[str | UUID] = None) -> UUID:
"""
Obtains the Capacity Id for a given workspace.
Parameters
----------
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
uuid.UUID
The capacity Id.
"""
if workspace is None:
capacity_id = _get_fabric_context_setting(name="trident.capacity.id")
else:
(workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
filter_condition = urllib.parse.quote(workspace_id)
dfW = fabric.list_workspaces(filter=f"id eq '{filter_condition}'")
if len(dfW) == 0:
raise ValueError(f"{icons.red_dot} The '{workspace_name}' does not exist'.")
capacity_id = dfW["Capacity Id"].iloc[0]
return capacity_id
def get_capacity_name(workspace: Optional[str | UUID] = None) -> str:
"""
Obtains the capacity name for a given workspace.
Parameters
----------
workspace : str | uuid.UUID, default=None
The Fabric workspace name or ID.
Defaults to None which resolves to the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the workspace of the notebook.
Returns
-------
str
The capacity name.
"""
capacity_id = get_capacity_id(workspace)
dfC = fabric.list_capacities()
dfC_filt = dfC[dfC["Id"] == capacity_id]
if dfC_filt.empty:
raise ValueError(
f"{icons.red_dot} The '{capacity_id}' capacity Id does not exist."
)
return dfC_filt["Display Name"].iloc[0]
def resolve_capacity_name(capacity_id: Optional[UUID] = None) -> str:
"""
Obtains the capacity name for a given capacity Id.
Parameters
----------
capacity_id : uuid.UUID, default=None
The capacity Id.
Defaults to None which resolves to the capacity name of the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the capacity name of the workspace of the notebook.
Returns
-------
str
The capacity name.
"""
if capacity_id is None:
return get_capacity_name()
dfC = fabric.list_capacities()
dfC_filt = dfC[dfC["Id"] == capacity_id]
if dfC_filt.empty:
raise ValueError(
f"{icons.red_dot} The '{capacity_id}' capacity Id does not exist."
)
return dfC_filt["Display Name"].iloc[0]
def resolve_capacity_id(capacity_name: Optional[str] = None) -> UUID:
"""
Obtains the capacity Id for a given capacity name.
Parameters
----------
capacity_name : str, default=None
The capacity name.
Defaults to None which resolves to the capacity id of the workspace of the attached lakehouse
or if no lakehouse attached, resolves to the capacity name of the workspace of the notebook.
Returns
-------
uuid.UUID
The capacity Id.
"""
if capacity_name is None:
return get_capacity_id()
dfC = fabric.list_capacities()
dfC_filt = dfC[dfC["Display Name"] == capacity_name]
if dfC_filt.empty:
raise ValueError(
f"{icons.red_dot} The '{capacity_name}' capacity does not exist."
)
return dfC_filt["Id"].iloc[0]
def retry(sleep_time: int, timeout_error_message: str):
def decorator(func):
@wraps(func)
def wrapper(*args, **kwargs):
start_time = datetime.datetime.now()
timeout = datetime.timedelta(minutes=1)
while datetime.datetime.now() - start_time <= timeout:
try:
return func(*args, **kwargs)
except Exception:
time.sleep(sleep_time)
raise TimeoutError(timeout_error_message)
return wrapper
return decorator
def lro(
client,
response,
status_codes: Optional[List[str]] = [200, 202],
sleep_time: Optional[int] = 1,
return_status_code: bool = False,
):
if response.status_code not in status_codes:
raise FabricHTTPException(response)
if response.status_code == status_codes[0]:
if return_status_code:
result = response.status_code
else:
result = response
if response.status_code == status_codes[1]:
operationId = response.headers["x-ms-operation-id"]
response = client.get(f"/v1/operations/{operationId}")
response_body = json.loads(response.content)
while response_body["status"] not in ["Succeeded", "Failed"]:
time.sleep(sleep_time)
response = client.get(f"/v1/operations/{operationId}")
response_body = json.loads(response.content)
if response_body["status"] != "Succeeded":
raise FabricHTTPException(response)
if return_status_code:
result = response.status_code
else:
response = client.get(f"/v1/operations/{operationId}/result")
result = response
return result
def pagination(client, response):
responses = []
response_json = response.json()
responses.append(response_json)
# Check for pagination