-
Notifications
You must be signed in to change notification settings - Fork 108
Expand file tree
/
Copy pathpipeline.py
More file actions
1024 lines (793 loc) · 36 KB
/
pipeline.py
File metadata and controls
1024 lines (793 loc) · 36 KB
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 logging
import time
from datetime import datetime
import pandas
import warnings
import pyarrow
from typing import List, Dict, Callable, Optional, Generator, Mapping, Any, Tuple
from collections import deque
from queue import Queue
from feldera.rest.errors import FelderaAPIError
from feldera.enums import PipelineStatus, ProgramStatus, CheckpointStatus
from feldera.rest.pipeline import Pipeline as InnerPipeline
from feldera.rest.feldera_client import FelderaClient
from feldera._callback_runner import _CallbackRunnerInstruction, CallbackRunner
from feldera.output_handler import OutputHandler
from feldera._helpers import ensure_dataframe_has_columns, chunk_dataframe
from feldera.rest.sql_table import SQLTable
from feldera.rest.sql_view import SQLView
class Pipeline:
def __init__(self, client: FelderaClient):
self.client: FelderaClient = client
self._inner: InnerPipeline | None = None
self.views_tx: List[Dict[str, Queue]] = []
@staticmethod
def _from_inner(inner: InnerPipeline, client: FelderaClient) -> "Pipeline":
pipeline = Pipeline(client)
pipeline._inner = inner
return pipeline
def __setup_output_listeners(self):
"""
Internal function used to set up the output listeners.
:meta private:
"""
for view_queue in self.views_tx:
for view_name, queue in view_queue.items():
# sends a message to the callback runner to start listening
queue.put(_CallbackRunnerInstruction.PipelineStarted)
# block until the callback runner is ready
queue.join()
def refresh(self):
"""
Calls the backend to get the updated, latest version of the pipeline.
:raises FelderaConnectionError: If there is an issue connecting to the backend.
"""
self._inner = self.client.get_pipeline(self.name)
def status(self) -> PipelineStatus:
"""
Return the current status of the pipeline.
"""
try:
self.refresh()
return PipelineStatus.from_str(self._inner.deployment_status)
except FelderaAPIError as err:
if err.status_code == 404:
return PipelineStatus.NOT_FOUND
else:
raise err
def input_pandas(self, table_name: str, df: pandas.DataFrame, force: bool = False):
"""
Push all rows in a pandas DataFrame to the pipeline.
The pipeline must either be in RUNNING or PAUSED states to push data.
An error will be raised if the pipeline is in any other state.
The dataframe must have the same columns as the table in the pipeline.
:param table_name: The name of the table to insert data into.
:param df: The pandas DataFrame to be pushed to the pipeline.
:param force: `True` to push data even if the pipeline is paused. `False` by default.
:raises ValueError: If the table does not exist in the pipeline.
:raises RuntimeError: If the pipeline is not in a valid state to push data.
:raises RuntimeError: If the pipeline is paused and force is not set to `True`.
"""
status = self.status()
if status not in [
PipelineStatus.RUNNING,
PipelineStatus.PAUSED,
]:
raise RuntimeError("Pipeline must be running or paused to push data")
if not force and status == PipelineStatus.PAUSED:
raise RuntimeError("Pipeline is paused, set force=True to push data")
ensure_dataframe_has_columns(df)
pipeline = self.client.get_pipeline(self.name)
if table_name.lower() != "now" and table_name.lower() not in [
tbl.name.lower() for tbl in pipeline.tables
]:
raise ValueError(
f"Cannot push to table '{
table_name
}': table with this name does not exist in the '{self.name}' pipeline"
)
else:
# consider validating the schema here
for datum in chunk_dataframe(df):
self.client.push_to_pipeline(
self.name,
table_name,
"json",
datum.to_json(orient="records", date_format="epoch"),
json_flavor="pandas",
array=True,
serialize=False,
force=force,
)
return
def input_json(
self,
table_name: str,
data: Dict | list,
update_format: str = "raw",
force: bool = False,
):
"""
Push this JSON data to the specified table of the pipeline.
The pipeline must either be in RUNNING or PAUSED states to push data.
An error will be raised if the pipeline is in any other state.
:param table_name: The name of the table to push data into.
:param data: The JSON encoded data to be pushed to the pipeline. The data should be in the form:
`{'col1': 'val1', 'col2': 'val2'}` or `[{'col1': 'val1', 'col2': 'val2'}, {'col1': 'val1', 'col2': 'val2'}]`
:param update_format: The update format of the JSON data to be pushed to the pipeline. Must be one of:
"raw", "insert_delete". <https://docs.feldera.com/formats/json#the-insertdelete-format>
:param force: `True` to push data even if the pipeline is paused. `False` by default.
:raises ValueError: If the update format is invalid.
:raises FelderaAPIError: If the pipeline is not in a valid state to push data.
:raises RuntimeError: If the pipeline is paused and `force` is not set to `True`.
"""
status = self.status()
if not force and status == PipelineStatus.PAUSED:
raise RuntimeError("Pipeline is paused, set force=True to push data")
if update_format not in ["raw", "insert_delete"]:
raise ValueError("update_format must be one of raw or insert_delete")
array = True if isinstance(data, list) else False
self.client.push_to_pipeline(
self.name,
table_name,
"json",
data,
update_format=update_format,
array=array,
force=force,
)
def pause_connector(self, table_name: str, connector_name: str):
"""
Pause the specified input connector.
Connectors allow feldera to fetch data from a source or write data to a sink.
This method allows users to **PAUSE** a specific **INPUT** connector.
All connectors are RUNNING by default.
Refer to the connector documentation for more information:
<https://docs.feldera.com/connectors/#input-connector-orchestration>
:param table_name: The name of the table that the connector is attached to.
:param connector_name: The name of the connector to pause.
:raises FelderaAPIError: If the connector is not found, or if the pipeline is not running.
"""
self.client.pause_connector(self.name, table_name, connector_name)
def resume_connector(self, table_name: str, connector_name: str):
"""
Resume the specified connector.
Connectors allow feldera to fetch data from a source or write data to a sink.
This method allows users to **RESUME / START** a specific **INPUT** connector.
All connectors are RUNNING by default.
Refer to the connector documentation for more information:
<https://docs.feldera.com/connectors/#input-connector-orchestration>
:param table_name: The name of the table that the connector is attached to.
:param connector_name: The name of the connector to resume.
:raises FelderaAPIError: If the connector is not found, or if the pipeline is not running.
"""
self.client.resume_connector(self.name, table_name, connector_name)
def listen(self, view_name: str, case_sensitive: bool = False) -> OutputHandler:
"""
Follow the change stream (i.e., the output) of the provided view.
Returns an output handler to read the changes.
When the pipeline is shutdown, these listeners are dropped.
You must call this method before starting the pipeline to get the entire output of the view.
If this method is called once the pipeline has started, you will only get the output from that point onwards.
:param view_name: The name of the view to listen to.
:param case_sensitive: True if the view name is case sensitive.
"""
queue: Optional[Queue] = None
if self.status() not in [PipelineStatus.PAUSED, PipelineStatus.RUNNING]:
queue = Queue(maxsize=1)
self.views_tx.append({view_name: queue})
handler = OutputHandler(
self.client, self.name, view_name, queue, case_sensitive
)
handler.start()
return handler
def foreach_chunk(
self,
view_name: str,
callback: Callable[[pandas.DataFrame, int], None],
case_sensitive: bool = False,
):
"""
Run the given callback on each chunk of the output of the specified view.
You must call this method before starting the pipeline to operate on the entire output.
You can call this method after the pipeline has started, but you will only get the output from that point onwards.
:param view_name: The name of the view.
:param callback: The callback to run on each chunk. The callback should take two arguments:
- **chunk** -> The chunk as a pandas DataFrame
- **seq_no** -> The sequence number. The sequence number is a monotonically increasing integer that
starts from 0. Note that the sequence number is unique for each chunk, but not necessarily contiguous.
:param case_sensitive: True if the view name is case sensitive.
Please note that the callback is run in a separate thread, so it should be thread-safe.
Please note that the callback should not block for a long time, as by default, backpressure is enabled and
will block the pipeline.
.. note::
- The callback must be thread-safe as it will be run in a separate thread.
"""
queue: Optional[Queue] = None
if self.status() not in [PipelineStatus.RUNNING, PipelineStatus.PAUSED]:
queue = Queue(maxsize=1)
self.views_tx.append({view_name: queue})
handler = CallbackRunner(
self.client, self.name, view_name, callback, queue, case_sensitive
)
handler.start()
def wait_for_completion(
self, shutdown: bool = False, timeout_s: Optional[float] = None
):
"""
Block until the pipeline has completed processing all input records.
This method blocks until (1) all input connectors attached to the pipeline
have finished reading their input data sources and issued end-of-input
notifications to the pipeline, and (2) all inputs received from these
connectors have been fully processed and corresponding outputs have been
sent out through the output connectors.
This method will block indefinitely if at least one of the input
connectors attached to the pipeline is a streaming connector, such as
Kafka, that does not issue the end-of-input notification.
:param shutdown: If True, the pipeline will be shutdown after completion. False by default.
:param timeout_s: Optional. The maximum time (in seconds) to wait for the pipeline to complete.
The default is None, which means wait indefinitely.
:raises RuntimeError: If the pipeline returns unknown metrics.
"""
if self.status() not in [
PipelineStatus.RUNNING,
PipelineStatus.INITIALIZING,
PipelineStatus.PROVISIONING,
]:
raise RuntimeError("Pipeline must be running to wait for completion")
start_time = time.monotonic()
while True:
if timeout_s is not None:
elapsed = time.monotonic() - start_time
if elapsed > timeout_s:
raise TimeoutError(
f"timeout ({timeout_s}s) reached while waiting for pipeline '{
self.name
}' to complete"
)
logging.debug(
f"waiting for pipeline {self.name} to complete: elapsed time {
elapsed
}s, timeout: {timeout_s}s"
)
metrics: dict = self.client.get_pipeline_stats(self.name).get(
"global_metrics"
)
pipeline_complete: bool = metrics.get("pipeline_complete")
if pipeline_complete is None:
raise RuntimeError(
"received unknown metrics from the pipeline, pipeline_complete is None"
)
if pipeline_complete:
break
time.sleep(1)
if shutdown:
self.shutdown()
def __failed_check(self, next):
"""
Checks if the pipeline is in FAILED state and raises an error if it is.
:meta private:
"""
status = self.status()
if status == PipelineStatus.FAILED:
deployment_error = self.client.get_pipeline(self.name).deployment_error
error_msg = deployment_error.get("message", "")
raise RuntimeError(
f"""Cannot {next} pipeline '{self.name}' in FAILED state.
The pipeline must be in SHUTDOWN state before it can be started, but it is currently in FAILED state.
Use `Pipeline.shutdown()` method to shut down the pipeline.
Error Message:
{error_msg}"""
)
def start(self, timeout_s: Optional[float] = None):
"""
.. _start:
Starts this pipeline.
The pipeline must be in SHUTDOWN state to start.
If the pipeline is in any other state, an error will be raised.
If the pipeline is in PAUSED state, use `.meth:resume` instead.
If the pipeline is in FAILED state, it must be shutdown before starting it again.
:param timeout_s: The maximum time (in seconds) to wait for the pipeline to start.
:raises RuntimeError: If the pipeline is not in SHUTDOWN state.
"""
self.__failed_check("start")
status = self.status()
if status != PipelineStatus.SHUTDOWN:
raise RuntimeError(
f"""Cannot start pipeline '{self.name}' in state '{str(status.name)}'.
The pipeline must be in SHUTDOWN state before it can be started.
You can either shut down the pipeline using the `Pipeline.shutdown()` method or use `Pipeline.resume()` to \
resume a paused pipeline."""
)
self.client.pause_pipeline(
self.name, "Unable to START the pipeline.", timeout_s
)
self.__setup_output_listeners()
self.resume(timeout_s)
def restart(self, timeout_s: Optional[float] = None):
"""
Restarts the pipeline.
This method **SHUTS DOWN** the pipeline regardless of its current state and then starts it again.
:param timeout_s: The maximum time (in seconds) to wait for the pipeline to restart.
"""
self.shutdown(timeout_s)
self.start(timeout_s)
def wait_for_idle(
self,
idle_interval_s: float = 5.0,
timeout_s: float = 600.0,
poll_interval_s: float = 0.2,
):
"""
Wait for the pipeline to become idle and then returns.
Idle is defined as a sufficiently long interval in which the number of
input and processed records reported by the pipeline do not change, and
they equal each other (thus, all input records present at the pipeline
have been processed).
:param idle_interval_s: Idle interval duration (default is 5.0 seconds).
:param timeout_s: Timeout waiting for idle (default is 600.0 seconds).
:param poll_interval_s: Polling interval, should be set substantially
smaller than the idle interval (default is 0.2 seconds).
:raises ValueError: If idle interval is larger than timeout, poll interval
is larger than timeout, or poll interval is larger than idle interval.
:raises RuntimeError: If the metrics are missing or the timeout was
reached.
"""
if idle_interval_s > timeout_s:
raise ValueError(
f"idle interval ({idle_interval_s}s) cannot be larger than timeout ({
timeout_s
}s)"
)
if poll_interval_s > timeout_s:
raise ValueError(
f"poll interval ({poll_interval_s}s) cannot be larger than timeout ({
timeout_s
}s)"
)
if poll_interval_s > idle_interval_s:
raise ValueError(
f"poll interval ({poll_interval_s}s) cannot be larger "
f"than idle interval ({idle_interval_s}s)"
)
start_time_s = time.monotonic()
idle_started_s = None
prev = (0, 0)
while True:
now_s = time.monotonic()
# Metrics retrieval
metrics: dict = self.client.get_pipeline_stats(self.name).get(
"global_metrics"
)
total_input_records: int | None = metrics.get("total_input_records")
total_processed_records: int | None = metrics.get("total_processed_records")
if total_input_records is None:
raise RuntimeError(
"total_input_records is missing from the pipeline metrics"
)
if total_processed_records is None:
raise RuntimeError(
"total_processed_records is missing from the pipeline metrics"
)
# Idle check
unchanged = (
prev[0] == total_input_records and prev[1] == total_processed_records
)
equal = total_input_records == total_processed_records
prev = (total_input_records, total_processed_records)
if unchanged and equal:
if idle_started_s is None:
idle_started_s = now_s
else:
idle_started_s = None
if idle_started_s is not None and now_s - idle_started_s >= idle_interval_s:
return
# Timeout
if now_s - start_time_s >= timeout_s:
raise RuntimeError(f"waiting for idle reached timeout ({timeout_s}s)")
time.sleep(poll_interval_s)
def pause(self, timeout_s: Optional[float] = None):
"""
Pause the pipeline.
The pipeline can only transition to the PAUSED state from the RUNNING state.
If the pipeline is already paused, it will remain in the PAUSED state.
:param timeout_s: The maximum time (in seconds) to wait for the pipeline to pause.
:raises FelderaAPIError: If the pipeline is in FAILED state.
"""
self.__failed_check("pause")
self.client.pause_pipeline(self.name, timeout_s=timeout_s)
def shutdown(self, timeout_s: Optional[float] = None):
"""
Shut down the pipeline.
Shuts down the pipeline regardless of its current state.
:param timeout_s: The maximum time (in seconds) to wait for the pipeline to shut down.
"""
if len(self.views_tx) > 0:
for _, queue in self.views_tx.pop().items():
# sends a message to the callback runner to stop listening
queue.put(_CallbackRunnerInstruction.RanToCompletion)
# block until the callback runner has been stopped
queue.join()
self.client.shutdown_pipeline(self.name, timeout_s=timeout_s)
def suspend(self, timeout_s: Optional[float] = None):
"""
Suspends the pipeline to storage.
:param timeout_s: The maximum time (in seconds) to wait for the pipeline to suspend.
"""
if len(self.views_tx) > 0:
for _, queue in self.views_tx.pop().items():
# sends a message to the callback runner to stop listening
queue.put(_CallbackRunnerInstruction.RanToCompletion)
# block until the callback runner has been stopped
queue.join()
self.client.suspend_pipeline(self.name, timeout_s=timeout_s)
def resume(self, timeout_s: Optional[float] = None):
"""
Resumes the pipeline from the PAUSED state. If the pipeline is already running, it will remain in the RUNNING state.
:param timeout_s: The maximum time (in seconds) to wait for the pipeline to shut down.
:raises FelderaAPIError: If the pipeline is in FAILED state.
"""
self.__failed_check("resume")
self.client.start_pipeline(self.name, timeout_s=timeout_s)
def delete(self):
"""
Deletes the pipeline.
The pipeline must be shutdown before it can be deleted.
:raises FelderaAPIError: If the pipeline is not in SHUTDOWN state.
"""
self.client.delete_pipeline(self.name)
@staticmethod
def get(name: str, client: FelderaClient) -> "Pipeline":
"""
Get the pipeline if it exists.
:param name: The name of the pipeline.
:param client: The FelderaClient instance.
"""
try:
inner = client.get_pipeline(name)
return Pipeline._from_inner(inner, client)
except FelderaAPIError as err:
if err.status_code == 404:
raise RuntimeError(f"Pipeline with name {name} not found")
def checkpoint(self, wait: bool = False, timeout_s=300) -> int:
"""
Checkpoints this pipeline, if fault-tolerance is enabled.
Fault Tolerance in Feldera: <https://docs.feldera.com/pipelines/fault-tolerance/>
:param wait: If true, will block until the checkpoint completes.
:param timeout_s: The maximum time (in seconds) to wait for the checkpoint to complete.
:raises FelderaAPIError: If checkpointing is not enabled.
"""
seq = self.client.checkpoint_pipeline(self.name)
if not wait:
return seq
start = time.time()
while True:
elapsed = time.monotonic() - start
if elapsed > timeout_s:
raise TimeoutError(
f"timeout ({timeout_s}s) reached while waiting for pipeline '{
self.name
}' to make checkpoint '{seq}'"
)
status = self.checkpoint_status(seq)
if status == CheckpointStatus.InProgress:
time.sleep(0.1)
continue
return status
return seq
def checkpoint_status(self, seq: int) -> CheckpointStatus:
"""
Checks the status of the given checkpoint.
:param seq: The checkpoint sequence number.
"""
resp = self.client.checkpoint_pipeline_status(self.name)
success = resp.get("success")
if seq == success:
return CheckpointStatus.Success
fail = resp.get("failure") or {}
if seq == fail.get("sequence_number"):
failure = CheckpointStatus.Failure
failure.error = fail.get("error", "")
return failure
if (success is None) or seq > success:
return CheckpointStatus.InProgress
if seq < success:
return CheckpointStatus.Unknown
def sync_checkpoint(self, wait: bool = False, timeout_s=300) -> str:
"""
Syncs this checkpoint to object store.
:param wait: If true, will block until the checkpoint sync opeartion completes.
:param timeout_s: The maximum time (in seconds) to wait for the checkpoint to complete syncing.
:raises FelderaAPIError: If no checkpoints have been made.
"""
uuid = self.client.sync_checkpoint(self.name)
if not wait:
return uuid
start = time.time()
while True:
elapsed = time.monotonic() - start
if elapsed > timeout_s:
raise TimeoutError(
f"timeout ({timeout_s}s) reached while waiting for pipeline '{
self.name
}' to sync checkpoint '{uuid}'"
)
status = self.sync_checkpoint_status(uuid)
if status in [CheckpointStatus.InProgress, CheckpointStatus.Unknown]:
time.sleep(0.1)
continue
return status
return uuid
def sync_checkpoint_status(self, uuid: str) -> CheckpointStatus:
"""
Checks the status of the given checkpoint sync operation.
If the checkpoint is currently being synchronized, returns
`CheckpointStatus.Unknown`.
:param uuid: The checkpoint uuid.
"""
resp = self.client.sync_checkpoint_status(self.name)
success = resp.get("success")
if uuid == success:
return CheckpointStatus.Success
fail = resp.get("failure") or {}
if uuid == fail.get("uuid"):
failure = CheckpointStatus.Failure
failure.error = fail.get("error", "")
return failure
return CheckpointStatus.Unknown
def query(self, query: str) -> Generator[Mapping[str, Any], None, None]:
"""
Executes an ad-hoc SQL query on this pipeline and returns a generator that yields the rows of the result as Python dictionaries.
For ``INSERT`` and ``DELETE`` queries, consider using :meth:`.execute` instead.
All floating-point numbers are deserialized as Decimal objects to avoid precision loss.
Note:
You can only ``SELECT`` from materialized tables and views.
Important:
This method is lazy. It returns a generator and is not evaluated until you consume the result.
:param query: The SQL query to be executed.
:return: A generator that yields the rows of the result as Python dictionaries.
:raises FelderaAPIError: If the pipeline is not in a RUNNING or PAUSED state.
:raises FelderaAPIError: If querying a non materialized table or view.
:raises FelderaAPIError: If the query is invalid.
"""
warnings.warn(
"function query is deprecated and will be removed in a future version",
category=DeprecationWarning,
stacklevel=2,
)
return self.client.query_as_json(self.name, query)
def query_pyarrow(self, query: str) -> pyarrow.Table:
"""
Executes an ad-hoc SQL query on this pipeline and returns a
:class:`.pyarrow.Table` containing all the results.
Note:
You can only ``SELECT`` from materialized tables and views.
:param query: The SQL query to be executed.
:raises FelderaAPIError: If the pipeline is not in a RUNNING or PAUSED
state.
:raises FelderaAPIError: If querying a non materialized table or view.
:raises FelderaAPIError: If the query is invalid.
"""
return self.client.query_as_pyarrow(self.name, query)
def query_pylist(self, query: str) -> List[List[Tuple[str, Any]]]:
"""
Executes an ad-hoc SQL query on this pipeline and returns the results
as a list of rows. Each row is represented as a list of
(column_name, value) tuples.
Note:
You can only ``SELECT`` from materialized tables and views.
:param query: The SQL query to be executed.
:return: A list of rows, where each row is a list of
(column_name, value) tuples.
:raises FelderaAPIError: If the pipeline is not in a RUNNING or PAUSED
state.
:raises FelderaAPIError: If querying a non materialized table or view.
:raises FelderaAPIError: If the query is invalid.
"""
table = self.query_pyarrow(query)
columns = [col.to_pylist() for col in table.itercolumns()]
return [list(zip(table.schema.names, row)) for row in zip(*columns)]
def query_parquet(self, query: str, path: str):
"""
Executes an ad-hoc SQL query on this pipeline and saves the result to the specified path as a parquet file.
If the extension isn't `parquet`, it will be automatically appended to `path`.
Note:
You can only ``SELECT`` from materialized tables and views.
:param query: The SQL query to be executed.
:param path: The path of the parquet file.
:raises FelderaAPIError: If the pipeline is not in a RUNNING or PAUSED state.
:raises FelderaAPIError: If querying a non materialized table or view.
:raises FelderaAPIError: If the query is invalid.
"""
self.client.query_as_parquet(self.name, query, path)
def query_tabular(self, query: str) -> Generator[str, None, None]:
"""
Executes a SQL query on this pipeline and returns the result as a formatted string.
Note:
You can only ``SELECT`` from materialized tables and views.
Important:
This method is lazy. It returns a generator and is not evaluated until you consume the result.
:param query: The SQL query to be executed.
:return: A generator that yields a string representing the query result in a human-readable, tabular format.
:raises FelderaAPIError: If the pipeline is not in a RUNNING or PAUSED state.
:raises FelderaAPIError: If querying a non materialized table or view.
:raises FelderaAPIError: If the query is invalid.
"""
return self.client.query_as_text(self.name, query)
def execute(self, query: str):
"""
Executes an ad-hoc SQL query on the current pipeline, discarding its result.
Unlike the :meth:`.query` method which returns a generator for retrieving query results lazily,
this method processes the query eagerly and fully before returning.
This method is suitable for SQL operations like ``INSERT`` and ``DELETE``, where the user needs
confirmation of successful query execution, but does not require the query result.
If the query fails, an exception will be raised.
Important:
If you try to ``INSERT`` or ``DELETE`` data from a table while the pipeline is paused,
it will block until the pipeline is resumed.
:param query: The SQL query to be executed.
:raises FelderaAPIError: If the pipeline is not in a RUNNING state.
:raises FelderaAPIError: If the query is invalid.
"""
gen = self.query_tabular(query)
deque(gen, maxlen=0)
@property
def name(self) -> str:
"""
Return the name of the pipeline.
"""
return self._inner.name
def program_code(self) -> str:
"""
Return the program SQL code of the pipeline.
"""
self.refresh()
return self._inner.program_code
def program_status(self) -> ProgramStatus:
"""
Return the program status of the pipeline.
Program status is the status of compilation of this SQL program.
We first compile the SQL program to Rust code, and then compile the Rust code to a binary.
"""
self.refresh()
return ProgramStatus.from_value(self._inner.program_status)
def program_status_since(self) -> datetime:
"""
Return the timestamp when the current program status was set.
"""
self.refresh()
return datetime.fromisoformat(self._inner.program_status_since)
def udf_rust(self) -> str:
"""
Return the Rust code for UDFs.
"""
self.refresh()
return self._inner.udf_rust
def udf_toml(self) -> str:
"""
Return the Rust dependencies required by UDFs (in the TOML format).
"""
self.refresh()
return self._inner.udf_toml
def program_config(self) -> Mapping[str, Any]:
"""
Return the program config of the pipeline.
"""
self.refresh()
return self._inner.program_config
def runtime_config(self) -> Mapping[str, Any]:
"""
Return the runtime config of the pipeline.
"""
self.refresh()
return self._inner.runtime_config
def id(self) -> str:
"""
Return the ID of the pipeline.
"""
self.refresh()
return self._inner.id
def description(self) -> str:
"""
Return the description of the pipeline.
"""
self.refresh()
return self._inner.description
def tables(self) -> List[SQLTable]:
"""
Return the tables of the pipeline.
"""
self.refresh()
return self._inner.tables
def views(self) -> List[SQLView]:
"""
Return the views of the pipeline.
"""
self.refresh()
return self._inner.views
def created_at(self) -> datetime:
"""
Return the creation time of the pipeline.
"""
self.refresh()
return datetime.fromisoformat(self._inner.created_at)
def version(self) -> int:
"""
Return the version of the pipeline.
"""
self.refresh()
return self._inner.version
def program_version(self) -> int:
"""
Return the program version of the pipeline.
"""
self.refresh()
return self._inner.program_version
def deployment_status_since(self) -> datetime:
"""
Return the timestamp when the current deployment status of the pipeline was set.
"""
self.refresh()
return datetime.fromisoformat(self._inner.deployment_status_since)
def deployment_config(self) -> Mapping[str, Any]:
"""
Return the deployment config of the pipeline.
"""
self.refresh()
return self._inner.deployment_config
def deployment_desired_status(self) -> PipelineStatus:
"""
Return the desired deployment status of the pipeline.
This is the next state that the pipeline should transition to.
"""
self.refresh()
return PipelineStatus.from_str(self._inner.deployment_desired_status)
def deployment_error(self) -> Mapping[str, Any]:
"""
Return the deployment error of the pipeline.
Returns an empty string if there is no error.
"""
self.refresh()
return self._inner.deployment_error
def deployment_location(self) -> str:
"""
Return the deployment location of the pipeline.
Deployment location is the location where the pipeline can be reached at runtime (a TCP port number or a URI).
"""
self.refresh()
return self._inner.deployment_location
def program_binary_url(self) -> str:
"""
Return the program binary URL of the pipeline.
This is the URL where the compiled program binary can be downloaded from.
"""
self.refresh()
return self._inner.program_binary_url
def program_info(self) -> Mapping[str, Any]:
"""
Return the program info of the pipeline.
This is the output returned by the SQL compiler, including: the list of input and output connectors, the generated Rust code for the pipeline, and the SQL program schema.
"""
self.refresh()
return self._inner.program_info