cribl-control-plane 0.1.0b1__py3-none-any.whl → 0.2.0a1__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 cribl-control-plane might be problematic. Click here for more details.

Files changed (36) hide show
  1. cribl_control_plane/_hooks/clientcredentials.py +91 -41
  2. cribl_control_plane/_version.py +4 -4
  3. cribl_control_plane/errors/apierror.py +1 -1
  4. cribl_control_plane/errors/criblcontrolplaneerror.py +1 -1
  5. cribl_control_plane/errors/error.py +1 -1
  6. cribl_control_plane/errors/healthstatus_error.py +1 -1
  7. cribl_control_plane/errors/no_response_error.py +1 -1
  8. cribl_control_plane/errors/responsevalidationerror.py +1 -1
  9. cribl_control_plane/httpclient.py +0 -1
  10. cribl_control_plane/lakedatasets.py +12 -12
  11. cribl_control_plane/models/__init__.py +106 -57
  12. cribl_control_plane/models/appmode.py +14 -0
  13. cribl_control_plane/models/cribllakedatasetupdate.py +81 -0
  14. cribl_control_plane/models/gitinfo.py +14 -3
  15. cribl_control_plane/models/hbcriblinfo.py +3 -14
  16. cribl_control_plane/models/heartbeatmetadata.py +0 -3
  17. cribl_control_plane/models/inputconfluentcloud.py +18 -0
  18. cribl_control_plane/models/inputkafka.py +17 -0
  19. cribl_control_plane/models/inputmsk.py +17 -0
  20. cribl_control_plane/models/inputsqs.py +8 -10
  21. cribl_control_plane/models/nodeprovidedinfo.py +0 -3
  22. cribl_control_plane/models/output.py +3 -3
  23. cribl_control_plane/models/outputchronicle.py +431 -0
  24. cribl_control_plane/models/outputconfluentcloud.py +18 -0
  25. cribl_control_plane/models/outputgooglechronicle.py +5 -4
  26. cribl_control_plane/models/outputgooglecloudlogging.py +9 -4
  27. cribl_control_plane/models/outputkafka.py +17 -0
  28. cribl_control_plane/models/outputmsk.py +17 -0
  29. cribl_control_plane/models/outputsqs.py +8 -10
  30. cribl_control_plane/models/routecloneconf.py +13 -0
  31. cribl_control_plane/models/routeconf.py +4 -3
  32. cribl_control_plane/models/updatecribllakedatasetbylakeidandidop.py +9 -5
  33. {cribl_control_plane-0.1.0b1.dist-info → cribl_control_plane-0.2.0a1.dist-info}/METADATA +1 -8
  34. {cribl_control_plane-0.1.0b1.dist-info → cribl_control_plane-0.2.0a1.dist-info}/RECORD +35 -32
  35. cribl_control_plane/models/outputdatabricks.py +0 -439
  36. {cribl_control_plane-0.1.0b1.dist-info → cribl_control_plane-0.2.0a1.dist-info}/WHEEL +0 -0
@@ -1,439 +0,0 @@
1
- """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
2
-
3
- from __future__ import annotations
4
- from cribl_control_plane import utils
5
- from cribl_control_plane.types import BaseModel
6
- from cribl_control_plane.utils import validate_open_enum
7
- from enum import Enum
8
- import pydantic
9
- from pydantic.functional_validators import PlainValidator
10
- from typing import List, Optional
11
- from typing_extensions import Annotated, NotRequired, TypedDict
12
-
13
-
14
- class OutputDatabricksType(str, Enum):
15
- DATABRICKS = "databricks"
16
-
17
-
18
- class OutputDatabricksDataFormat(str, Enum, metaclass=utils.OpenEnumMeta):
19
- r"""Format of the output data"""
20
-
21
- JSON = "json"
22
- RAW = "raw"
23
- PARQUET = "parquet"
24
-
25
-
26
- class OutputDatabricksBackpressureBehavior(str, Enum, metaclass=utils.OpenEnumMeta):
27
- r"""How to handle events when all receivers are exerting backpressure"""
28
-
29
- BLOCK = "block"
30
- DROP = "drop"
31
-
32
-
33
- class OutputDatabricksDiskSpaceProtection(str, Enum, metaclass=utils.OpenEnumMeta):
34
- r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
35
-
36
- BLOCK = "block"
37
- DROP = "drop"
38
-
39
-
40
- class OutputDatabricksAuthenticationMethod(str, Enum, metaclass=utils.OpenEnumMeta):
41
- r"""Unity Catalog authentication method. Choose Manual to enter credentials directly, or Secret to use a stored secret."""
42
-
43
- MANUAL = "manual"
44
- SECRET = "secret"
45
-
46
-
47
- class OutputDatabricksCompression(str, Enum, metaclass=utils.OpenEnumMeta):
48
- r"""Data compression format to apply to HTTP content before it is delivered"""
49
-
50
- NONE = "none"
51
- GZIP = "gzip"
52
-
53
-
54
- class OutputDatabricksCompressionLevel(str, Enum, metaclass=utils.OpenEnumMeta):
55
- r"""Compression level to apply before moving files to final destination"""
56
-
57
- BEST_SPEED = "best_speed"
58
- NORMAL = "normal"
59
- BEST_COMPRESSION = "best_compression"
60
-
61
-
62
- class OutputDatabricksParquetVersion(str, Enum, metaclass=utils.OpenEnumMeta):
63
- r"""Determines which data types are supported and how they are represented"""
64
-
65
- PARQUET_1_0 = "PARQUET_1_0"
66
- PARQUET_2_4 = "PARQUET_2_4"
67
- PARQUET_2_6 = "PARQUET_2_6"
68
-
69
-
70
- class OutputDatabricksDataPageVersion(str, Enum, metaclass=utils.OpenEnumMeta):
71
- r"""Serialization format of data pages. Note that some reader implementations use Data page V2's attributes to work more efficiently, while others ignore it."""
72
-
73
- DATA_PAGE_V1 = "DATA_PAGE_V1"
74
- DATA_PAGE_V2 = "DATA_PAGE_V2"
75
-
76
-
77
- class OutputDatabricksKeyValueMetadatumTypedDict(TypedDict):
78
- value: str
79
- key: NotRequired[str]
80
-
81
-
82
- class OutputDatabricksKeyValueMetadatum(BaseModel):
83
- value: str
84
-
85
- key: Optional[str] = ""
86
-
87
-
88
- class OutputDatabricksTypedDict(TypedDict):
89
- type: OutputDatabricksType
90
- id: NotRequired[str]
91
- r"""Unique ID for this output"""
92
- pipeline: NotRequired[str]
93
- r"""Pipeline to process data before sending out to this output"""
94
- system_fields: NotRequired[List[str]]
95
- r"""Fields to automatically add to events, such as cribl_pipe. Supports wildcards."""
96
- environment: NotRequired[str]
97
- r"""Optionally, enable this config only on a specified Git branch. If empty, will be enabled everywhere."""
98
- streamtags: NotRequired[List[str]]
99
- r"""Tags for filtering and grouping in @{product}"""
100
- dest_path: NotRequired[str]
101
- r"""Optional path to prepend to files before uploading. Must be a JavaScript expression (which can evaluate to a constant value), enclosed in quotes or backticks. Can be evaluated only at init time. Example referencing a Global Variable: `myEventsVolumePath-${C.vars.myVar}`"""
102
- stage_path: NotRequired[str]
103
- r"""Filesystem location in which to buffer files before compressing and moving to final destination. Use performant, stable storage."""
104
- add_id_to_stage_path: NotRequired[bool]
105
- r"""Add the Output ID value to staging location"""
106
- remove_empty_dirs: NotRequired[bool]
107
- r"""Remove empty staging directories after moving files"""
108
- partition_expr: NotRequired[str]
109
- r"""JavaScript expression defining how files are partitioned and organized. Default is date-based. If blank, Stream will fall back to the event's __partition field value – if present – otherwise to each location's root directory."""
110
- format_: NotRequired[OutputDatabricksDataFormat]
111
- r"""Format of the output data"""
112
- base_file_name: NotRequired[str]
113
- r"""JavaScript expression to define the output filename prefix (can be constant)"""
114
- file_name_suffix: NotRequired[str]
115
- r"""JavaScript expression to define the output filename suffix (can be constant). The `__format` variable refers to the value of the `Data format` field (`json` or `raw`). The `__compression` field refers to the kind of compression being used (`none` or `gzip`)."""
116
- max_file_size_mb: NotRequired[float]
117
- r"""Maximum uncompressed output file size. Files of this size will be closed and moved to final output location."""
118
- max_file_open_time_sec: NotRequired[float]
119
- r"""Maximum amount of time to write to a file. Files open for longer than this will be closed and moved to final output location."""
120
- max_file_idle_time_sec: NotRequired[float]
121
- r"""Maximum amount of time to keep inactive files open. Files open for longer than this will be closed and moved to final output location."""
122
- max_open_files: NotRequired[float]
123
- r"""Maximum number of files to keep open concurrently. When exceeded, @{product} will close the oldest open files and move them to the final output location."""
124
- header_line: NotRequired[str]
125
- r"""If set, this line will be written to the beginning of each output file"""
126
- write_high_water_mark: NotRequired[float]
127
- r"""Buffer size used to write to a file"""
128
- on_backpressure: NotRequired[OutputDatabricksBackpressureBehavior]
129
- r"""How to handle events when all receivers are exerting backpressure"""
130
- deadletter_enabled: NotRequired[bool]
131
- r"""If a file fails to move to its final destination after the maximum number of retries, move it to a designated directory to prevent further errors"""
132
- on_disk_full_backpressure: NotRequired[OutputDatabricksDiskSpaceProtection]
133
- r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
134
- unity_auth_method: NotRequired[OutputDatabricksAuthenticationMethod]
135
- r"""Unity Catalog authentication method. Choose Manual to enter credentials directly, or Secret to use a stored secret."""
136
- login_url: NotRequired[str]
137
- r"""URL for Unity Catalog OAuth token endpoint (example: 'https://your-workspace.cloud.databricks.com/oauth/token')"""
138
- client_id: NotRequired[str]
139
- r"""JavaScript expression to compute the OAuth client ID for Unity Catalog authentication. Can be a constant."""
140
- client_secret: NotRequired[str]
141
- r"""JavaScript expression to compute the OAuth client secret for Unity Catalog authentication. Can be a constant."""
142
- client_text_secret: NotRequired[str]
143
- r"""Select or create a stored secret that references your Client ID and Client Secret"""
144
- scope: NotRequired[str]
145
- r"""OAuth scope for Unity Catalog authentication"""
146
- token_timeout_secs: NotRequired[float]
147
- r"""How often the OAuth token should be refreshed"""
148
- default_catalog: NotRequired[str]
149
- r"""Name of the catalog to use for the output"""
150
- default_schema: NotRequired[str]
151
- r"""Name of the catalog schema to use for the output"""
152
- events_volume_name: NotRequired[str]
153
- r"""Name of the events volume in Databricks"""
154
- over_write_files: NotRequired[bool]
155
- r"""Uploaded files should be overwritten if they already exist. If disabled, upload will fail if a file already exists."""
156
- description: NotRequired[str]
157
- compress: NotRequired[OutputDatabricksCompression]
158
- r"""Data compression format to apply to HTTP content before it is delivered"""
159
- compression_level: NotRequired[OutputDatabricksCompressionLevel]
160
- r"""Compression level to apply before moving files to final destination"""
161
- automatic_schema: NotRequired[bool]
162
- r"""Automatically calculate the schema based on the events of each Parquet file generated"""
163
- parquet_version: NotRequired[OutputDatabricksParquetVersion]
164
- r"""Determines which data types are supported and how they are represented"""
165
- parquet_data_page_version: NotRequired[OutputDatabricksDataPageVersion]
166
- r"""Serialization format of data pages. Note that some reader implementations use Data page V2's attributes to work more efficiently, while others ignore it."""
167
- parquet_row_group_length: NotRequired[float]
168
- r"""The number of rows that every group will contain. The final group can contain a smaller number of rows."""
169
- parquet_page_size: NotRequired[str]
170
- r"""Target memory size for page segments, such as 1MB or 128MB. Generally, lower values improve reading speed, while higher values improve compression."""
171
- should_log_invalid_rows: NotRequired[bool]
172
- r"""Log up to 3 rows that @{product} skips due to data mismatch"""
173
- key_value_metadata: NotRequired[List[OutputDatabricksKeyValueMetadatumTypedDict]]
174
- r"""The metadata of files the Destination writes will include the properties you add here as key-value pairs. Useful for tagging. Examples: \"key\":\"OCSF Event Class\", \"value\":\"9001\" """
175
- enable_statistics: NotRequired[bool]
176
- r"""Statistics profile an entire file in terms of minimum/maximum values within data, numbers of nulls, etc. You can use Parquet tools to view statistics."""
177
- enable_write_page_index: NotRequired[bool]
178
- r"""One page index contains statistics for one data page. Parquet readers use statistics to enable page skipping."""
179
- enable_page_checksum: NotRequired[bool]
180
- r"""Parquet tools can use the checksum of a Parquet page to verify data integrity"""
181
- empty_dir_cleanup_sec: NotRequired[float]
182
- r"""How frequently, in seconds, to clean up empty directories"""
183
- deadletter_path: NotRequired[str]
184
- r"""Storage location for files that fail to reach their final destination after maximum retries are exceeded"""
185
- max_retry_num: NotRequired[float]
186
- r"""The maximum number of times a file will attempt to move to its final destination before being dead-lettered"""
187
-
188
-
189
- class OutputDatabricks(BaseModel):
190
- type: OutputDatabricksType
191
-
192
- id: Optional[str] = None
193
- r"""Unique ID for this output"""
194
-
195
- pipeline: Optional[str] = None
196
- r"""Pipeline to process data before sending out to this output"""
197
-
198
- system_fields: Annotated[
199
- Optional[List[str]], pydantic.Field(alias="systemFields")
200
- ] = None
201
- r"""Fields to automatically add to events, such as cribl_pipe. Supports wildcards."""
202
-
203
- environment: Optional[str] = None
204
- r"""Optionally, enable this config only on a specified Git branch. If empty, will be enabled everywhere."""
205
-
206
- streamtags: Optional[List[str]] = None
207
- r"""Tags for filtering and grouping in @{product}"""
208
-
209
- dest_path: Annotated[Optional[str], pydantic.Field(alias="destPath")] = ""
210
- r"""Optional path to prepend to files before uploading. Must be a JavaScript expression (which can evaluate to a constant value), enclosed in quotes or backticks. Can be evaluated only at init time. Example referencing a Global Variable: `myEventsVolumePath-${C.vars.myVar}`"""
211
-
212
- stage_path: Annotated[Optional[str], pydantic.Field(alias="stagePath")] = (
213
- "$CRIBL_HOME/state/outputs/staging"
214
- )
215
- r"""Filesystem location in which to buffer files before compressing and moving to final destination. Use performant, stable storage."""
216
-
217
- add_id_to_stage_path: Annotated[
218
- Optional[bool], pydantic.Field(alias="addIdToStagePath")
219
- ] = True
220
- r"""Add the Output ID value to staging location"""
221
-
222
- remove_empty_dirs: Annotated[
223
- Optional[bool], pydantic.Field(alias="removeEmptyDirs")
224
- ] = True
225
- r"""Remove empty staging directories after moving files"""
226
-
227
- partition_expr: Annotated[Optional[str], pydantic.Field(alias="partitionExpr")] = (
228
- "C.Time.strftime(_time ? _time : Date.now()/1000, '%Y/%m/%d')"
229
- )
230
- r"""JavaScript expression defining how files are partitioned and organized. Default is date-based. If blank, Stream will fall back to the event's __partition field value – if present – otherwise to each location's root directory."""
231
-
232
- format_: Annotated[
233
- Annotated[
234
- Optional[OutputDatabricksDataFormat],
235
- PlainValidator(validate_open_enum(False)),
236
- ],
237
- pydantic.Field(alias="format"),
238
- ] = OutputDatabricksDataFormat.JSON
239
- r"""Format of the output data"""
240
-
241
- base_file_name: Annotated[Optional[str], pydantic.Field(alias="baseFileName")] = (
242
- "`CriblOut`"
243
- )
244
- r"""JavaScript expression to define the output filename prefix (can be constant)"""
245
-
246
- file_name_suffix: Annotated[
247
- Optional[str], pydantic.Field(alias="fileNameSuffix")
248
- ] = '`.${C.env["CRIBL_WORKER_ID"]}.${__format}${__compression === "gzip" ? ".gz" : ""}`'
249
- r"""JavaScript expression to define the output filename suffix (can be constant). The `__format` variable refers to the value of the `Data format` field (`json` or `raw`). The `__compression` field refers to the kind of compression being used (`none` or `gzip`)."""
250
-
251
- max_file_size_mb: Annotated[
252
- Optional[float], pydantic.Field(alias="maxFileSizeMB")
253
- ] = 32
254
- r"""Maximum uncompressed output file size. Files of this size will be closed and moved to final output location."""
255
-
256
- max_file_open_time_sec: Annotated[
257
- Optional[float], pydantic.Field(alias="maxFileOpenTimeSec")
258
- ] = 300
259
- r"""Maximum amount of time to write to a file. Files open for longer than this will be closed and moved to final output location."""
260
-
261
- max_file_idle_time_sec: Annotated[
262
- Optional[float], pydantic.Field(alias="maxFileIdleTimeSec")
263
- ] = 30
264
- r"""Maximum amount of time to keep inactive files open. Files open for longer than this will be closed and moved to final output location."""
265
-
266
- max_open_files: Annotated[Optional[float], pydantic.Field(alias="maxOpenFiles")] = (
267
- 100
268
- )
269
- r"""Maximum number of files to keep open concurrently. When exceeded, @{product} will close the oldest open files and move them to the final output location."""
270
-
271
- header_line: Annotated[Optional[str], pydantic.Field(alias="headerLine")] = ""
272
- r"""If set, this line will be written to the beginning of each output file"""
273
-
274
- write_high_water_mark: Annotated[
275
- Optional[float], pydantic.Field(alias="writeHighWaterMark")
276
- ] = 64
277
- r"""Buffer size used to write to a file"""
278
-
279
- on_backpressure: Annotated[
280
- Annotated[
281
- Optional[OutputDatabricksBackpressureBehavior],
282
- PlainValidator(validate_open_enum(False)),
283
- ],
284
- pydantic.Field(alias="onBackpressure"),
285
- ] = OutputDatabricksBackpressureBehavior.BLOCK
286
- r"""How to handle events when all receivers are exerting backpressure"""
287
-
288
- deadletter_enabled: Annotated[
289
- Optional[bool], pydantic.Field(alias="deadletterEnabled")
290
- ] = False
291
- r"""If a file fails to move to its final destination after the maximum number of retries, move it to a designated directory to prevent further errors"""
292
-
293
- on_disk_full_backpressure: Annotated[
294
- Annotated[
295
- Optional[OutputDatabricksDiskSpaceProtection],
296
- PlainValidator(validate_open_enum(False)),
297
- ],
298
- pydantic.Field(alias="onDiskFullBackpressure"),
299
- ] = OutputDatabricksDiskSpaceProtection.BLOCK
300
- r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
301
-
302
- unity_auth_method: Annotated[
303
- Annotated[
304
- Optional[OutputDatabricksAuthenticationMethod],
305
- PlainValidator(validate_open_enum(False)),
306
- ],
307
- pydantic.Field(alias="unityAuthMethod"),
308
- ] = OutputDatabricksAuthenticationMethod.MANUAL
309
- r"""Unity Catalog authentication method. Choose Manual to enter credentials directly, or Secret to use a stored secret."""
310
-
311
- login_url: Annotated[Optional[str], pydantic.Field(alias="loginUrl")] = None
312
- r"""URL for Unity Catalog OAuth token endpoint (example: 'https://your-workspace.cloud.databricks.com/oauth/token')"""
313
-
314
- client_id: Annotated[Optional[str], pydantic.Field(alias="clientId")] = None
315
- r"""JavaScript expression to compute the OAuth client ID for Unity Catalog authentication. Can be a constant."""
316
-
317
- client_secret: Annotated[Optional[str], pydantic.Field(alias="clientSecret")] = None
318
- r"""JavaScript expression to compute the OAuth client secret for Unity Catalog authentication. Can be a constant."""
319
-
320
- client_text_secret: Annotated[
321
- Optional[str], pydantic.Field(alias="clientTextSecret")
322
- ] = None
323
- r"""Select or create a stored secret that references your Client ID and Client Secret"""
324
-
325
- scope: Optional[str] = "all-apis"
326
- r"""OAuth scope for Unity Catalog authentication"""
327
-
328
- token_timeout_secs: Annotated[
329
- Optional[float], pydantic.Field(alias="tokenTimeoutSecs")
330
- ] = 3600
331
- r"""How often the OAuth token should be refreshed"""
332
-
333
- default_catalog: Annotated[
334
- Optional[str], pydantic.Field(alias="defaultCatalog")
335
- ] = "main"
336
- r"""Name of the catalog to use for the output"""
337
-
338
- default_schema: Annotated[Optional[str], pydantic.Field(alias="defaultSchema")] = (
339
- "external"
340
- )
341
- r"""Name of the catalog schema to use for the output"""
342
-
343
- events_volume_name: Annotated[
344
- Optional[str], pydantic.Field(alias="eventsVolumeName")
345
- ] = "events"
346
- r"""Name of the events volume in Databricks"""
347
-
348
- over_write_files: Annotated[
349
- Optional[bool], pydantic.Field(alias="overWriteFiles")
350
- ] = False
351
- r"""Uploaded files should be overwritten if they already exist. If disabled, upload will fail if a file already exists."""
352
-
353
- description: Optional[str] = None
354
-
355
- compress: Annotated[
356
- Optional[OutputDatabricksCompression], PlainValidator(validate_open_enum(False))
357
- ] = OutputDatabricksCompression.GZIP
358
- r"""Data compression format to apply to HTTP content before it is delivered"""
359
-
360
- compression_level: Annotated[
361
- Annotated[
362
- Optional[OutputDatabricksCompressionLevel],
363
- PlainValidator(validate_open_enum(False)),
364
- ],
365
- pydantic.Field(alias="compressionLevel"),
366
- ] = OutputDatabricksCompressionLevel.BEST_SPEED
367
- r"""Compression level to apply before moving files to final destination"""
368
-
369
- automatic_schema: Annotated[
370
- Optional[bool], pydantic.Field(alias="automaticSchema")
371
- ] = False
372
- r"""Automatically calculate the schema based on the events of each Parquet file generated"""
373
-
374
- parquet_version: Annotated[
375
- Annotated[
376
- Optional[OutputDatabricksParquetVersion],
377
- PlainValidator(validate_open_enum(False)),
378
- ],
379
- pydantic.Field(alias="parquetVersion"),
380
- ] = OutputDatabricksParquetVersion.PARQUET_2_6
381
- r"""Determines which data types are supported and how they are represented"""
382
-
383
- parquet_data_page_version: Annotated[
384
- Annotated[
385
- Optional[OutputDatabricksDataPageVersion],
386
- PlainValidator(validate_open_enum(False)),
387
- ],
388
- pydantic.Field(alias="parquetDataPageVersion"),
389
- ] = OutputDatabricksDataPageVersion.DATA_PAGE_V2
390
- r"""Serialization format of data pages. Note that some reader implementations use Data page V2's attributes to work more efficiently, while others ignore it."""
391
-
392
- parquet_row_group_length: Annotated[
393
- Optional[float], pydantic.Field(alias="parquetRowGroupLength")
394
- ] = 10000
395
- r"""The number of rows that every group will contain. The final group can contain a smaller number of rows."""
396
-
397
- parquet_page_size: Annotated[
398
- Optional[str], pydantic.Field(alias="parquetPageSize")
399
- ] = "1MB"
400
- r"""Target memory size for page segments, such as 1MB or 128MB. Generally, lower values improve reading speed, while higher values improve compression."""
401
-
402
- should_log_invalid_rows: Annotated[
403
- Optional[bool], pydantic.Field(alias="shouldLogInvalidRows")
404
- ] = None
405
- r"""Log up to 3 rows that @{product} skips due to data mismatch"""
406
-
407
- key_value_metadata: Annotated[
408
- Optional[List[OutputDatabricksKeyValueMetadatum]],
409
- pydantic.Field(alias="keyValueMetadata"),
410
- ] = None
411
- r"""The metadata of files the Destination writes will include the properties you add here as key-value pairs. Useful for tagging. Examples: \"key\":\"OCSF Event Class\", \"value\":\"9001\" """
412
-
413
- enable_statistics: Annotated[
414
- Optional[bool], pydantic.Field(alias="enableStatistics")
415
- ] = True
416
- r"""Statistics profile an entire file in terms of minimum/maximum values within data, numbers of nulls, etc. You can use Parquet tools to view statistics."""
417
-
418
- enable_write_page_index: Annotated[
419
- Optional[bool], pydantic.Field(alias="enableWritePageIndex")
420
- ] = True
421
- r"""One page index contains statistics for one data page. Parquet readers use statistics to enable page skipping."""
422
-
423
- enable_page_checksum: Annotated[
424
- Optional[bool], pydantic.Field(alias="enablePageChecksum")
425
- ] = False
426
- r"""Parquet tools can use the checksum of a Parquet page to verify data integrity"""
427
-
428
- empty_dir_cleanup_sec: Annotated[
429
- Optional[float], pydantic.Field(alias="emptyDirCleanupSec")
430
- ] = 300
431
- r"""How frequently, in seconds, to clean up empty directories"""
432
-
433
- deadletter_path: Annotated[
434
- Optional[str], pydantic.Field(alias="deadletterPath")
435
- ] = "$CRIBL_HOME/state/outputs/dead-letter"
436
- r"""Storage location for files that fail to reach their final destination after maximum retries are exceeded"""
437
-
438
- max_retry_num: Annotated[Optional[float], pydantic.Field(alias="maxRetryNum")] = 20
439
- r"""The maximum number of times a file will attempt to move to its final destination before being dead-lettered"""