forked from feldera/feldera
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathfeldera_client.py
More file actions
605 lines (479 loc) · 20.1 KB
/
feldera_client.py
File metadata and controls
605 lines (479 loc) · 20.1 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
import pathlib
from typing import Optional
import logging
import time
import json
from decimal import Decimal
from typing import Generator
from feldera.rest.config import Config
from feldera.rest.errors import FelderaTimeoutError
from feldera.rest.pipeline import Pipeline
from feldera.rest._httprequests import HttpRequests
def _prepare_boolean_input(value: bool) -> str:
return "true" if value else "false"
class FelderaClient:
"""
A client for the Feldera HTTP API
A client instance is needed for every Feldera API method to know the location of
Feldera and its permissions.
"""
def __init__(
self,
url: str,
api_key: Optional[str] = None,
timeout: Optional[float] = None,
) -> None:
"""
:param url: The url to Feldera API (ex: https://try.feldera.com)
:param api_key: The optional API key for Feldera
:param timeout: (optional) The amount of time in seconds that the client will wait for a response before timing
out.
"""
self.config = Config(url, api_key, timeout=timeout)
self.http = HttpRequests(self.config)
try:
self.pipelines()
except Exception as e:
logging.error(f"Failed to connect to Feldera API: {e}")
raise e
@staticmethod
def localhost(port: int = 8080) -> "FelderaClient":
"""
Create a FelderaClient that connects to the local Feldera instance
"""
return FelderaClient(f"http://localhost:{port}")
def get_pipeline(self, pipeline_name) -> Pipeline:
"""
Get a pipeline by name
:param pipeline_name: The name of the pipeline
"""
resp = self.http.get(f"/pipelines/{pipeline_name}")
return Pipeline.from_dict(resp)
def get_runtime_config(self, pipeline_name) -> dict:
"""
Get the runtime config of a pipeline by name
:param pipeline_name: The name of the pipeline
"""
resp: dict = self.http.get(f"/pipelines/{pipeline_name}")
return resp.get("runtime_config")
def pipelines(self) -> list[Pipeline]:
"""
Get all pipelines
"""
resp = self.http.get(
path="/pipelines",
)
return [Pipeline.from_dict(pipeline) for pipeline in resp]
def __wait_for_compilation(self, name: str):
wait = ["Pending", "CompilingSql", "SqlCompiled", "CompilingRust"]
while True:
p = self.get_pipeline(name)
status = p.program_status
if status == "Success":
return p
elif status not in wait:
# error handling for SQL compilation errors
if isinstance(status, dict):
sql_errors = status.get("SqlError")
if sql_errors:
err_msg = f"Pipeline {name} failed to compile:\n"
for sql_error in sql_errors:
err_msg += (
f"{sql_error['error_type']}\n{sql_error['message']}\n"
)
err_msg += f"Code snippet:\n{sql_error['snippet']}"
raise RuntimeError(err_msg)
raise RuntimeError(f"The program failed to compile: {status}")
logging.debug("still compiling %s, waiting for 100 more milliseconds", name)
time.sleep(0.1)
def create_pipeline(self, pipeline: Pipeline) -> Pipeline:
"""
Create a pipeline if it doesn't exist and wait for it to compile
:name: The name of the pipeline
"""
body = {
"name": pipeline.name,
"program_code": pipeline.program_code,
"udf_rust": pipeline.udf_rust,
"udf_toml": pipeline.udf_toml,
"program_config": pipeline.program_config,
"runtime_config": pipeline.runtime_config,
"description": pipeline.description or "",
}
self.http.post(
path="/pipelines",
body=body,
)
return self.__wait_for_compilation(pipeline.name)
def create_or_update_pipeline(self, pipeline: Pipeline) -> Pipeline:
"""
Create a pipeline if it doesn't exist or update a pipeline and wait for it to compile
"""
body = {
"name": pipeline.name,
"program_code": pipeline.program_code,
"udf_rust": pipeline.udf_rust,
"udf_toml": pipeline.udf_toml,
"program_config": pipeline.program_config,
"runtime_config": pipeline.runtime_config,
"description": pipeline.description or "",
}
self.http.put(
path=f"/pipelines/{pipeline.name}",
body=body,
)
return self.__wait_for_compilation(pipeline.name)
def patch_pipeline(self, name: str, sql: str):
"""
Incrementally update the pipeline SQL
:param name: The name of the pipeline
:param sql: The SQL snippet. Replaces the existing SQL code with this one.
"""
self.http.patch(
path=f"/pipelines/{name}",
body={"program_code": sql},
)
def delete_pipeline(self, name: str):
"""
Deletes a pipeline by name
:param name: The name of the pipeline
"""
self.http.delete(
path=f"/pipelines/{name}",
)
def get_pipeline_stats(self, name: str) -> dict:
"""
Get the pipeline metrics and performance counters
:param name: The name of the pipeline
"""
resp = self.http.get(
path=f"/pipelines/{name}/stats",
)
return resp
def start_pipeline(self, pipeline_name: str, timeout_s: Optional[float] = 300):
"""
:param pipeline_name: The name of the pipeline to start
:param timeout_s: The amount of time in seconds to wait for the pipeline to start. 300 seconds by default.
"""
if timeout_s is None:
timeout_s = 300
self.http.post(
path=f"/pipelines/{pipeline_name}/start",
)
start_time = time.monotonic()
while True:
if timeout_s is not None:
elapsed = time.monotonic() - start_time
if elapsed > timeout_s:
raise TimeoutError(
f"Timed out waiting for pipeline {pipeline_name} to start"
)
resp = self.get_pipeline(pipeline_name)
status = resp.deployment_status
if status == "Running":
break
elif status == "Failed":
raise RuntimeError(
f"""Unable to START the pipeline.
Reason: The pipeline is in a FAILED state due to the following error:
{resp.deployment_error.get("message", "")}"""
)
logging.debug(
"still starting %s, waiting for 100 more milliseconds", pipeline_name
)
time.sleep(0.1)
def pause_pipeline(
self,
pipeline_name: str,
error_message: str = None,
timeout_s: Optional[float] = 300,
):
"""
Stop a pipeline
:param pipeline_name: The name of the pipeline to stop
:param error_message: The error message to show if the pipeline is in FAILED state
:param timeout_s: The amount of time in seconds to wait for the pipeline to pause. 300 seconds by default.
"""
if timeout_s is None:
timeout_s = 300
self.http.post(
path=f"/pipelines/{pipeline_name}/pause",
)
if error_message is None:
error_message = "Unable to PAUSE the pipeline.\n"
start_time = time.monotonic()
while True:
if timeout_s is not None:
elapsed = time.monotonic() - start_time
if elapsed > timeout_s:
raise TimeoutError(
f"Timed out waiting for pipeline {pipeline_name} to pause"
)
resp = self.get_pipeline(pipeline_name)
status = resp.deployment_status
if status == "Paused":
break
elif status == "Failed":
raise RuntimeError(
error_message
+ f"""Reason: The pipeline is in a FAILED state due to the following error:
{resp.deployment_error.get("message", "")}"""
)
logging.debug(
"still pausing %s, waiting for 100 more milliseconds", pipeline_name
)
time.sleep(0.1)
def shutdown_pipeline(self, pipeline_name: str, timeout_s: Optional[float] = 300):
"""
Shutdown a pipeline
:param pipeline_name: The name of the pipeline to shut down
:param timeout_s: The amount of time in seconds to wait for the pipeline to shut down. Default is 15 seconds.
"""
if timeout_s is None:
timeout_s = 300
self.http.post(
path=f"/pipelines/{pipeline_name}/shutdown",
)
start = time.monotonic()
while time.monotonic() - start < timeout_s:
status = self.get_pipeline(pipeline_name).deployment_status
if status == "Shutdown":
return
logging.debug(
"still shutting down %s, waiting for 100 more milliseconds",
pipeline_name,
)
time.sleep(0.1)
raise FelderaTimeoutError(
f"timeout error: pipeline '{pipeline_name}' did not shutdown in {timeout_s} seconds"
)
def checkpoint_pipeline(self, pipeline_name: str):
"""
Checkpoint a fault-tolerant pipeline
:param pipeline_name: The name of the pipeline to checkpoint
"""
self.http.post(
path=f"/pipelines/{pipeline_name}/checkpoint",
)
def push_to_pipeline(
self,
pipeline_name: str,
table_name: str,
format: str,
data: list[list | str | dict],
array: bool = False,
force: bool = False,
update_format: str = "raw",
json_flavor: str = None,
serialize: bool = True,
):
"""
Insert data into a pipeline
:param pipeline_name: The name of the pipeline
:param table_name: The name of the table
:param format: The format of the data, either "json" or "csv"
:param array: True if updates in this stream are packed into JSON arrays, used in conjunction with the
"json" format
:param force: If True, the data will be inserted even if the pipeline is paused
:param update_format: JSON data change event format, used in conjunction with the "json" format,
the default value is "insert_delete", other supported formats: "weighted", "debezium", "snowflake", "raw"
:param json_flavor: JSON encoding used for individual table records, the default value is "default", other supported encodings:
"debezium_mysql", "snowflake", "kafka_connect_json_converter", "pandas"
:param data: The data to insert
:param serialize: If True, the data will be serialized to JSON. True by default
"""
if format not in ["json", "csv"]:
raise ValueError("format must be either 'json' or 'csv'")
if update_format not in [
"insert_delete",
"weighted",
"debezium",
"snowflake",
"raw",
]:
raise ValueError(
"update_format must be one of 'insert_delete', 'weighted', 'debezium', 'snowflake', 'raw'"
)
if json_flavor is not None and json_flavor not in [
"default",
"debezium_mysql",
"snowflake",
"kafka_connect_json_converter",
"pandas",
]:
raise ValueError(
"json_flavor must be one of 'default', 'debezium_mysql', 'snowflake', 'kafka_connect_json_converter', 'pandas'"
)
# python sends `True` which isn't accepted by the backend
array = _prepare_boolean_input(array)
force = _prepare_boolean_input(force)
params = {
"force": force,
"format": format,
}
if format == "json":
params["array"] = array
params["update_format"] = update_format
if json_flavor is not None:
params["json_flavor"] = json_flavor
content_type = "application/json"
if format == "csv":
content_type = "text/csv"
data = bytes(str(data), "utf-8")
self.http.post(
path=f"/pipelines/{pipeline_name}/ingress/{table_name}",
params=params,
content_type=content_type,
body=data,
serialize=serialize,
)
def listen_to_pipeline(
self,
pipeline_name: str,
table_name: str,
format: str,
backpressure: bool = True,
array: bool = False,
timeout: Optional[float] = None,
):
"""
Listen for updates to views for pipeline, yields the chunks of data
:param pipeline_name: The name of the pipeline
:param table_name: The name of the table to listen to
:param format: The format of the data, either "json" or "csv"
:param backpressure: When the flag is True (the default), this method waits for the consumer to receive each
chunk and blocks the pipeline if the consumer cannot keep up. When this flag is False, the pipeline drops
data chunks if the consumer is not keeping up with its output. This prevents a slow consumer from slowing
down the entire pipeline.
:param array: Set True to group updates in this stream into JSON arrays, used in conjunction with the
"json" format, the default value is False
:param timeout: The amount of time in seconds to listen to the stream for
"""
params = {
"format": format,
"backpressure": _prepare_boolean_input(backpressure),
}
if format == "json":
params["array"] = _prepare_boolean_input(array)
resp = self.http.post(
path=f"/pipelines/{pipeline_name}/egress/{table_name}",
params=params,
stream=True,
)
end = time.monotonic() + timeout if timeout else None
# Using the default chunk size below makes `iter_lines` extremely
# inefficient when dealing with long lines.
for chunk in resp.iter_lines(chunk_size=50000000):
if end and time.monotonic() > end:
break
if chunk:
yield json.loads(chunk, parse_float=Decimal)
def query_as_text(
self, pipeline_name: str, query: str
) -> Generator[str, None, None]:
"""
Executes an ad-hoc query on the specified pipeline and returns a generator that yields lines of the table.
:param pipeline_name: The name of the pipeline to query.
:param query: The SQL query to be executed.
:return: A generator yielding the query result in tabular format, one line at a time.
"""
params = {
"pipeline_name": pipeline_name,
"sql": query,
"format": "text",
}
resp = self.http.get(
path=f"/pipelines/{pipeline_name}/query",
params=params,
stream=True,
)
chunk: bytes
for chunk in resp.iter_lines(chunk_size=50000000):
if chunk:
yield chunk.decode("utf-8")
def query_as_parquet(self, pipeline_name: str, query: str, path: str):
"""
Executes an ad-hoc query on the specified pipeline and saves the result to a parquet file.
If the extension isn't `parquet`, it will be automatically appended to `path`.
:param pipeline_name: The name of the pipeline to query.
:param query: The SQL query to be executed.
:param path: The path including the file name to save the resulting parquet file in.
"""
params = {
"pipeline_name": pipeline_name,
"sql": query,
"format": "parquet",
}
resp = self.http.get(
path=f"/pipelines/{pipeline_name}/query",
params=params,
stream=True,
)
path: pathlib.Path = pathlib.Path(path)
ext = ".parquet"
if path.suffix != ext:
path = path.with_suffix(ext)
file = open(path, "wb")
chunk: bytes
for chunk in resp.iter_content(chunk_size=1024):
if chunk:
file.write(chunk)
file.close()
def query_as_json(
self, pipeline_name: str, query: str
) -> Generator[dict, None, None]:
"""
Executes an ad-hoc query on the specified pipeline and returns the result as a generator that yields
rows of the query as Python dictionaries.
All floating-point numbers are deserialized as Decimal objects to avoid precision loss.
:param pipeline_name: The name of the pipeline to query.
:param query: The SQL query to be executed.
:return: A generator that yields each row of the result as a Python dictionary, deserialized from JSON.
"""
params = {
"pipeline_name": pipeline_name,
"sql": query,
"format": "json",
}
resp = self.http.get(
path=f"/pipelines/{pipeline_name}/query",
params=params,
stream=True,
)
for chunk in resp.iter_lines(chunk_size=50000000):
if chunk:
yield json.loads(chunk, parse_float=Decimal)
def pause_connector(self, pipeline_name, table_name, connector_name):
"""
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 pipeline_name: The name of the pipeline.
:param table_name: The name of the table associated with this connector.
:param connector_name: The name of the connector.
:raises FelderaAPIError: If the connector cannot be found, or if the pipeline is not running.
"""
self.http.post(
path=f"/pipelines/{pipeline_name}/tables/{table_name}/connectors/{connector_name}/pause",
)
def resume_connector(
self, pipeline_name: str, 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 pipeline_name: The name of the pipeline.
:param table_name: The name of the table associated with this connector.
:param connector_name: The name of the connector.
:raises FelderaAPIError: If the connector cannot be found, or if the pipeline is not running.
"""
self.http.post(
path=f"/pipelines/{pipeline_name}/tables/{table_name}/connectors/{connector_name}/start",
)