cribl-control-plane 0.0.13__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.
- cribl_control_plane/__init__.py +17 -0
- cribl_control_plane/_hooks/__init__.py +5 -0
- cribl_control_plane/_hooks/clientcredentials.py +211 -0
- cribl_control_plane/_hooks/registration.py +13 -0
- cribl_control_plane/_hooks/sdkhooks.py +81 -0
- cribl_control_plane/_hooks/types.py +112 -0
- cribl_control_plane/_version.py +15 -0
- cribl_control_plane/auth_sdk.py +184 -0
- cribl_control_plane/basesdk.py +358 -0
- cribl_control_plane/errors/__init__.py +60 -0
- cribl_control_plane/errors/apierror.py +38 -0
- cribl_control_plane/errors/criblcontrolplaneerror.py +26 -0
- cribl_control_plane/errors/error.py +24 -0
- cribl_control_plane/errors/healthstatus_error.py +38 -0
- cribl_control_plane/errors/no_response_error.py +13 -0
- cribl_control_plane/errors/responsevalidationerror.py +25 -0
- cribl_control_plane/health.py +166 -0
- cribl_control_plane/httpclient.py +126 -0
- cribl_control_plane/models/__init__.py +7305 -0
- cribl_control_plane/models/addhectokenrequest.py +34 -0
- cribl_control_plane/models/authtoken.py +13 -0
- cribl_control_plane/models/createinputhectokenbyidop.py +45 -0
- cribl_control_plane/models/createinputop.py +24 -0
- cribl_control_plane/models/createoutputop.py +24 -0
- cribl_control_plane/models/createoutputtestbyidop.py +46 -0
- cribl_control_plane/models/criblevent.py +14 -0
- cribl_control_plane/models/deleteinputbyidop.py +37 -0
- cribl_control_plane/models/deleteoutputbyidop.py +37 -0
- cribl_control_plane/models/deleteoutputpqbyidop.py +36 -0
- cribl_control_plane/models/getinputbyidop.py +37 -0
- cribl_control_plane/models/getoutputbyidop.py +37 -0
- cribl_control_plane/models/getoutputpqbyidop.py +36 -0
- cribl_control_plane/models/getoutputsamplesbyidop.py +37 -0
- cribl_control_plane/models/healthstatus.py +36 -0
- cribl_control_plane/models/input.py +199 -0
- cribl_control_plane/models/inputappscope.py +448 -0
- cribl_control_plane/models/inputazureblob.py +308 -0
- cribl_control_plane/models/inputcollection.py +208 -0
- cribl_control_plane/models/inputconfluentcloud.py +585 -0
- cribl_control_plane/models/inputcribl.py +165 -0
- cribl_control_plane/models/inputcriblhttp.py +341 -0
- cribl_control_plane/models/inputcribllakehttp.py +342 -0
- cribl_control_plane/models/inputcriblmetrics.py +175 -0
- cribl_control_plane/models/inputcribltcp.py +299 -0
- cribl_control_plane/models/inputcrowdstrike.py +410 -0
- cribl_control_plane/models/inputdatadogagent.py +364 -0
- cribl_control_plane/models/inputdatagen.py +180 -0
- cribl_control_plane/models/inputedgeprometheus.py +551 -0
- cribl_control_plane/models/inputelastic.py +494 -0
- cribl_control_plane/models/inputeventhub.py +360 -0
- cribl_control_plane/models/inputexec.py +213 -0
- cribl_control_plane/models/inputfile.py +259 -0
- cribl_control_plane/models/inputfirehose.py +341 -0
- cribl_control_plane/models/inputgooglepubsub.py +247 -0
- cribl_control_plane/models/inputgrafana_union.py +1247 -0
- cribl_control_plane/models/inputhttp.py +403 -0
- cribl_control_plane/models/inputhttpraw.py +407 -0
- cribl_control_plane/models/inputjournalfiles.py +208 -0
- cribl_control_plane/models/inputkafka.py +581 -0
- cribl_control_plane/models/inputkinesis.py +363 -0
- cribl_control_plane/models/inputkubeevents.py +182 -0
- cribl_control_plane/models/inputkubelogs.py +256 -0
- cribl_control_plane/models/inputkubemetrics.py +233 -0
- cribl_control_plane/models/inputloki.py +468 -0
- cribl_control_plane/models/inputmetrics.py +290 -0
- cribl_control_plane/models/inputmodeldriventelemetry.py +274 -0
- cribl_control_plane/models/inputmsk.py +654 -0
- cribl_control_plane/models/inputnetflow.py +224 -0
- cribl_control_plane/models/inputoffice365mgmt.py +384 -0
- cribl_control_plane/models/inputoffice365msgtrace.py +449 -0
- cribl_control_plane/models/inputoffice365service.py +377 -0
- cribl_control_plane/models/inputopentelemetry.py +516 -0
- cribl_control_plane/models/inputprometheus.py +464 -0
- cribl_control_plane/models/inputprometheusrw.py +470 -0
- cribl_control_plane/models/inputrawudp.py +207 -0
- cribl_control_plane/models/inputs3.py +416 -0
- cribl_control_plane/models/inputs3inventory.py +440 -0
- cribl_control_plane/models/inputsecuritylake.py +425 -0
- cribl_control_plane/models/inputsnmp.py +274 -0
- cribl_control_plane/models/inputsplunk.py +387 -0
- cribl_control_plane/models/inputsplunkhec.py +478 -0
- cribl_control_plane/models/inputsplunksearch.py +537 -0
- cribl_control_plane/models/inputsqs.py +320 -0
- cribl_control_plane/models/inputsyslog_union.py +759 -0
- cribl_control_plane/models/inputsystemmetrics.py +533 -0
- cribl_control_plane/models/inputsystemstate.py +417 -0
- cribl_control_plane/models/inputtcp.py +359 -0
- cribl_control_plane/models/inputtcpjson.py +334 -0
- cribl_control_plane/models/inputwef.py +498 -0
- cribl_control_plane/models/inputwindowsmetrics.py +457 -0
- cribl_control_plane/models/inputwineventlogs.py +222 -0
- cribl_control_plane/models/inputwiz.py +334 -0
- cribl_control_plane/models/inputzscalerhec.py +439 -0
- cribl_control_plane/models/listinputop.py +24 -0
- cribl_control_plane/models/listoutputop.py +24 -0
- cribl_control_plane/models/logininfo.py +16 -0
- cribl_control_plane/models/output.py +229 -0
- cribl_control_plane/models/outputazureblob.py +471 -0
- cribl_control_plane/models/outputazuredataexplorer.py +660 -0
- cribl_control_plane/models/outputazureeventhub.py +321 -0
- cribl_control_plane/models/outputazurelogs.py +386 -0
- cribl_control_plane/models/outputclickhouse.py +650 -0
- cribl_control_plane/models/outputcloudwatch.py +273 -0
- cribl_control_plane/models/outputconfluentcloud.py +591 -0
- cribl_control_plane/models/outputcriblhttp.py +494 -0
- cribl_control_plane/models/outputcribllake.py +396 -0
- cribl_control_plane/models/outputcribltcp.py +387 -0
- cribl_control_plane/models/outputcrowdstrikenextgensiem.py +410 -0
- cribl_control_plane/models/outputdatadog.py +472 -0
- cribl_control_plane/models/outputdataset.py +437 -0
- cribl_control_plane/models/outputdefault.py +55 -0
- cribl_control_plane/models/outputdevnull.py +50 -0
- cribl_control_plane/models/outputdiskspool.py +89 -0
- cribl_control_plane/models/outputdls3.py +560 -0
- cribl_control_plane/models/outputdynatracehttp.py +454 -0
- cribl_control_plane/models/outputdynatraceotlp.py +486 -0
- cribl_control_plane/models/outputelastic.py +494 -0
- cribl_control_plane/models/outputelasticcloud.py +407 -0
- cribl_control_plane/models/outputexabeam.py +297 -0
- cribl_control_plane/models/outputfilesystem.py +357 -0
- cribl_control_plane/models/outputgooglechronicle.py +486 -0
- cribl_control_plane/models/outputgooglecloudlogging.py +557 -0
- cribl_control_plane/models/outputgooglecloudstorage.py +499 -0
- cribl_control_plane/models/outputgooglepubsub.py +274 -0
- cribl_control_plane/models/outputgrafanacloud_union.py +1024 -0
- cribl_control_plane/models/outputgraphite.py +225 -0
- cribl_control_plane/models/outputhoneycomb.py +369 -0
- cribl_control_plane/models/outputhumiohec.py +389 -0
- cribl_control_plane/models/outputinfluxdb.py +523 -0
- cribl_control_plane/models/outputkafka.py +581 -0
- cribl_control_plane/models/outputkinesis.py +312 -0
- cribl_control_plane/models/outputloki.py +425 -0
- cribl_control_plane/models/outputminio.py +512 -0
- cribl_control_plane/models/outputmsk.py +654 -0
- cribl_control_plane/models/outputnetflow.py +80 -0
- cribl_control_plane/models/outputnewrelic.py +424 -0
- cribl_control_plane/models/outputnewrelicevents.py +401 -0
- cribl_control_plane/models/outputopentelemetry.py +669 -0
- cribl_control_plane/models/outputprometheus.py +485 -0
- cribl_control_plane/models/outputring.py +121 -0
- cribl_control_plane/models/outputrouter.py +83 -0
- cribl_control_plane/models/outputs3.py +556 -0
- cribl_control_plane/models/outputsamplesresponse.py +14 -0
- cribl_control_plane/models/outputsecuritylake.py +505 -0
- cribl_control_plane/models/outputsentinel.py +488 -0
- cribl_control_plane/models/outputsentineloneaisiem.py +505 -0
- cribl_control_plane/models/outputservicenow.py +543 -0
- cribl_control_plane/models/outputsignalfx.py +369 -0
- cribl_control_plane/models/outputsnmp.py +80 -0
- cribl_control_plane/models/outputsns.py +274 -0
- cribl_control_plane/models/outputsplunk.py +383 -0
- cribl_control_plane/models/outputsplunkhec.py +434 -0
- cribl_control_plane/models/outputsplunklb.py +558 -0
- cribl_control_plane/models/outputsqs.py +328 -0
- cribl_control_plane/models/outputstatsd.py +224 -0
- cribl_control_plane/models/outputstatsdext.py +225 -0
- cribl_control_plane/models/outputsumologic.py +378 -0
- cribl_control_plane/models/outputsyslog.py +415 -0
- cribl_control_plane/models/outputtcpjson.py +413 -0
- cribl_control_plane/models/outputtestrequest.py +15 -0
- cribl_control_plane/models/outputtestresponse.py +29 -0
- cribl_control_plane/models/outputwavefront.py +369 -0
- cribl_control_plane/models/outputwebhook.py +689 -0
- cribl_control_plane/models/outputxsiam.py +415 -0
- cribl_control_plane/models/schemeclientoauth.py +24 -0
- cribl_control_plane/models/security.py +36 -0
- cribl_control_plane/models/updatehectokenrequest.py +31 -0
- cribl_control_plane/models/updateinputbyidop.py +44 -0
- cribl_control_plane/models/updateinputhectokenbyidandtokenop.py +52 -0
- cribl_control_plane/models/updateoutputbyidop.py +44 -0
- cribl_control_plane/outputs.py +1615 -0
- cribl_control_plane/py.typed +1 -0
- cribl_control_plane/sdk.py +164 -0
- cribl_control_plane/sdkconfiguration.py +36 -0
- cribl_control_plane/sources.py +1355 -0
- cribl_control_plane/types/__init__.py +21 -0
- cribl_control_plane/types/basemodel.py +39 -0
- cribl_control_plane/utils/__init__.py +187 -0
- cribl_control_plane/utils/annotations.py +55 -0
- cribl_control_plane/utils/datetimes.py +23 -0
- cribl_control_plane/utils/enums.py +74 -0
- cribl_control_plane/utils/eventstreaming.py +238 -0
- cribl_control_plane/utils/forms.py +223 -0
- cribl_control_plane/utils/headers.py +136 -0
- cribl_control_plane/utils/logger.py +27 -0
- cribl_control_plane/utils/metadata.py +118 -0
- cribl_control_plane/utils/queryparams.py +205 -0
- cribl_control_plane/utils/requestbodies.py +66 -0
- cribl_control_plane/utils/retries.py +217 -0
- cribl_control_plane/utils/security.py +207 -0
- cribl_control_plane/utils/serializers.py +249 -0
- cribl_control_plane/utils/unmarshal_json_response.py +24 -0
- cribl_control_plane/utils/url.py +155 -0
- cribl_control_plane/utils/values.py +137 -0
- cribl_control_plane-0.0.13.dist-info/METADATA +489 -0
- cribl_control_plane-0.0.13.dist-info/RECORD +197 -0
- cribl_control_plane-0.0.13.dist-info/WHEEL +4 -0
|
@@ -0,0 +1,560 @@
|
|
|
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 OutputDlS3Type(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
15
|
+
DL_S3 = "dl_s3"
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
class OutputDlS3AuthenticationMethod(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
19
|
+
r"""AWS authentication method. Choose Auto to use IAM roles."""
|
|
20
|
+
|
|
21
|
+
AUTO = "auto"
|
|
22
|
+
MANUAL = "manual"
|
|
23
|
+
SECRET = "secret"
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
class OutputDlS3SignatureVersion(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
27
|
+
r"""Signature version to use for signing S3 requests"""
|
|
28
|
+
|
|
29
|
+
V2 = "v2"
|
|
30
|
+
V4 = "v4"
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
class OutputDlS3ObjectACL(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
34
|
+
r"""Object ACL to assign to uploaded objects"""
|
|
35
|
+
|
|
36
|
+
PRIVATE = "private"
|
|
37
|
+
PUBLIC_READ = "public-read"
|
|
38
|
+
PUBLIC_READ_WRITE = "public-read-write"
|
|
39
|
+
AUTHENTICATED_READ = "authenticated-read"
|
|
40
|
+
AWS_EXEC_READ = "aws-exec-read"
|
|
41
|
+
BUCKET_OWNER_READ = "bucket-owner-read"
|
|
42
|
+
BUCKET_OWNER_FULL_CONTROL = "bucket-owner-full-control"
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
class OutputDlS3StorageClass(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
46
|
+
r"""Storage class to select for uploaded objects"""
|
|
47
|
+
|
|
48
|
+
STANDARD = "STANDARD"
|
|
49
|
+
REDUCED_REDUNDANCY = "REDUCED_REDUNDANCY"
|
|
50
|
+
STANDARD_IA = "STANDARD_IA"
|
|
51
|
+
ONEZONE_IA = "ONEZONE_IA"
|
|
52
|
+
INTELLIGENT_TIERING = "INTELLIGENT_TIERING"
|
|
53
|
+
GLACIER = "GLACIER"
|
|
54
|
+
GLACIER_IR = "GLACIER_IR"
|
|
55
|
+
DEEP_ARCHIVE = "DEEP_ARCHIVE"
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
class OutputDlS3ServerSideEncryptionForUploadedObjects(
|
|
59
|
+
str, Enum, metaclass=utils.OpenEnumMeta
|
|
60
|
+
):
|
|
61
|
+
AES256 = "AES256"
|
|
62
|
+
AWS_KMS = "aws:kms"
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
class OutputDlS3DataFormat(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
66
|
+
r"""Format of the output data"""
|
|
67
|
+
|
|
68
|
+
JSON = "json"
|
|
69
|
+
RAW = "raw"
|
|
70
|
+
PARQUET = "parquet"
|
|
71
|
+
|
|
72
|
+
|
|
73
|
+
class OutputDlS3BackpressureBehavior(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
74
|
+
r"""How to handle events when all receivers are exerting backpressure"""
|
|
75
|
+
|
|
76
|
+
BLOCK = "block"
|
|
77
|
+
DROP = "drop"
|
|
78
|
+
|
|
79
|
+
|
|
80
|
+
class OutputDlS3DiskSpaceProtection(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
81
|
+
r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
|
|
82
|
+
|
|
83
|
+
BLOCK = "block"
|
|
84
|
+
DROP = "drop"
|
|
85
|
+
|
|
86
|
+
|
|
87
|
+
class OutputDlS3Compression(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
88
|
+
r"""Data compression format to apply to HTTP content before it is delivered"""
|
|
89
|
+
|
|
90
|
+
NONE = "none"
|
|
91
|
+
GZIP = "gzip"
|
|
92
|
+
|
|
93
|
+
|
|
94
|
+
class OutputDlS3CompressionLevel(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
95
|
+
r"""Compression level to apply before moving files to final destination"""
|
|
96
|
+
|
|
97
|
+
BEST_SPEED = "best_speed"
|
|
98
|
+
NORMAL = "normal"
|
|
99
|
+
BEST_COMPRESSION = "best_compression"
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
class OutputDlS3ParquetVersion(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
103
|
+
r"""Determines which data types are supported and how they are represented"""
|
|
104
|
+
|
|
105
|
+
PARQUET_1_0 = "PARQUET_1_0"
|
|
106
|
+
PARQUET_2_4 = "PARQUET_2_4"
|
|
107
|
+
PARQUET_2_6 = "PARQUET_2_6"
|
|
108
|
+
|
|
109
|
+
|
|
110
|
+
class OutputDlS3DataPageVersion(str, Enum, metaclass=utils.OpenEnumMeta):
|
|
111
|
+
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."""
|
|
112
|
+
|
|
113
|
+
DATA_PAGE_V1 = "DATA_PAGE_V1"
|
|
114
|
+
DATA_PAGE_V2 = "DATA_PAGE_V2"
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
class OutputDlS3KeyValueMetadatumTypedDict(TypedDict):
|
|
118
|
+
value: str
|
|
119
|
+
key: NotRequired[str]
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
class OutputDlS3KeyValueMetadatum(BaseModel):
|
|
123
|
+
value: str
|
|
124
|
+
|
|
125
|
+
key: Optional[str] = ""
|
|
126
|
+
|
|
127
|
+
|
|
128
|
+
class OutputDlS3TypedDict(TypedDict):
|
|
129
|
+
bucket: str
|
|
130
|
+
r"""Name of the destination S3 bucket. Must be a JavaScript expression (which can evaluate to a constant value), enclosed in quotes or backticks. Can be evaluated only at initialization time. Example referencing a Global Variable: `myBucket-${C.vars.myVar}`"""
|
|
131
|
+
id: NotRequired[str]
|
|
132
|
+
r"""Unique ID for this output"""
|
|
133
|
+
type: NotRequired[OutputDlS3Type]
|
|
134
|
+
pipeline: NotRequired[str]
|
|
135
|
+
r"""Pipeline to process data before sending out to this output"""
|
|
136
|
+
system_fields: NotRequired[List[str]]
|
|
137
|
+
r"""Fields to automatically add to events, such as cribl_pipe. Supports wildcards."""
|
|
138
|
+
environment: NotRequired[str]
|
|
139
|
+
r"""Optionally, enable this config only on a specified Git branch. If empty, will be enabled everywhere."""
|
|
140
|
+
streamtags: NotRequired[List[str]]
|
|
141
|
+
r"""Tags for filtering and grouping in @{product}"""
|
|
142
|
+
region: NotRequired[str]
|
|
143
|
+
r"""Region where the S3 bucket is located"""
|
|
144
|
+
aws_secret_key: NotRequired[str]
|
|
145
|
+
r"""Secret key. This value can be a constant or a JavaScript expression. Example: `${C.env.SOME_SECRET}`)"""
|
|
146
|
+
aws_authentication_method: NotRequired[OutputDlS3AuthenticationMethod]
|
|
147
|
+
r"""AWS authentication method. Choose Auto to use IAM roles."""
|
|
148
|
+
endpoint: NotRequired[str]
|
|
149
|
+
r"""S3 service endpoint. If empty, defaults to the AWS Region-specific endpoint. Otherwise, it must point to S3-compatible endpoint."""
|
|
150
|
+
signature_version: NotRequired[OutputDlS3SignatureVersion]
|
|
151
|
+
r"""Signature version to use for signing S3 requests"""
|
|
152
|
+
reuse_connections: NotRequired[bool]
|
|
153
|
+
r"""Reuse connections between requests, which can improve performance"""
|
|
154
|
+
reject_unauthorized: NotRequired[bool]
|
|
155
|
+
r"""Reject certificates that cannot be verified against a valid CA, such as self-signed certificates"""
|
|
156
|
+
enable_assume_role: NotRequired[bool]
|
|
157
|
+
r"""Use Assume Role credentials to access S3"""
|
|
158
|
+
assume_role_arn: NotRequired[str]
|
|
159
|
+
r"""Amazon Resource Name (ARN) of the role to assume"""
|
|
160
|
+
assume_role_external_id: NotRequired[str]
|
|
161
|
+
r"""External ID to use when assuming role"""
|
|
162
|
+
duration_seconds: NotRequired[float]
|
|
163
|
+
r"""Duration of the assumed role's session, in seconds. Minimum is 900 (15 minutes), default is 3600 (1 hour), and maximum is 43200 (12 hours)."""
|
|
164
|
+
stage_path: NotRequired[str]
|
|
165
|
+
r"""Filesystem location in which to buffer files, before compressing and moving to final destination. Use performant and stable storage."""
|
|
166
|
+
add_id_to_stage_path: NotRequired[bool]
|
|
167
|
+
r"""Add the Output ID value to staging location"""
|
|
168
|
+
dest_path: NotRequired[str]
|
|
169
|
+
r"""Prefix to append 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: `myKeyPrefix-${C.vars.myVar}`"""
|
|
170
|
+
object_acl: NotRequired[OutputDlS3ObjectACL]
|
|
171
|
+
r"""Object ACL to assign to uploaded objects"""
|
|
172
|
+
storage_class: NotRequired[OutputDlS3StorageClass]
|
|
173
|
+
r"""Storage class to select for uploaded objects"""
|
|
174
|
+
server_side_encryption: NotRequired[
|
|
175
|
+
OutputDlS3ServerSideEncryptionForUploadedObjects
|
|
176
|
+
]
|
|
177
|
+
kms_key_id: NotRequired[str]
|
|
178
|
+
r"""ID or ARN of the KMS customer-managed key to use for encryption"""
|
|
179
|
+
remove_empty_dirs: NotRequired[bool]
|
|
180
|
+
r"""Remove empty staging directories after moving files"""
|
|
181
|
+
format_: NotRequired[OutputDlS3DataFormat]
|
|
182
|
+
r"""Format of the output data"""
|
|
183
|
+
base_file_name: NotRequired[str]
|
|
184
|
+
r"""JavaScript expression to define the output filename prefix (can be constant)"""
|
|
185
|
+
file_name_suffix: NotRequired[str]
|
|
186
|
+
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`)."""
|
|
187
|
+
max_file_size_mb: NotRequired[float]
|
|
188
|
+
r"""Maximum uncompressed output file size. Files of this size will be closed and moved to final output location."""
|
|
189
|
+
max_open_files: NotRequired[float]
|
|
190
|
+
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."""
|
|
191
|
+
header_line: NotRequired[str]
|
|
192
|
+
r"""If set, this line will be written to the beginning of each output file"""
|
|
193
|
+
write_high_water_mark: NotRequired[float]
|
|
194
|
+
r"""Buffer size used to write to a file"""
|
|
195
|
+
on_backpressure: NotRequired[OutputDlS3BackpressureBehavior]
|
|
196
|
+
r"""How to handle events when all receivers are exerting backpressure"""
|
|
197
|
+
deadletter_enabled: NotRequired[bool]
|
|
198
|
+
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"""
|
|
199
|
+
on_disk_full_backpressure: NotRequired[OutputDlS3DiskSpaceProtection]
|
|
200
|
+
r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
|
|
201
|
+
max_file_open_time_sec: NotRequired[float]
|
|
202
|
+
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."""
|
|
203
|
+
max_file_idle_time_sec: NotRequired[float]
|
|
204
|
+
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."""
|
|
205
|
+
max_concurrent_file_parts: NotRequired[float]
|
|
206
|
+
r"""Maximum number of parts to upload in parallel per file. Minimum part size is 5MB."""
|
|
207
|
+
verify_permissions: NotRequired[bool]
|
|
208
|
+
r"""Disable if you can access files within the bucket but not the bucket itself"""
|
|
209
|
+
max_closing_files_to_backpressure: NotRequired[float]
|
|
210
|
+
r"""Maximum number of files that can be waiting for upload before backpressure is applied"""
|
|
211
|
+
partitioning_fields: NotRequired[List[str]]
|
|
212
|
+
r"""List of fields to partition the path by, in addition to time, which is included automatically. The effective partition will be YYYY/MM/DD/HH/<list/of/fields>."""
|
|
213
|
+
description: NotRequired[str]
|
|
214
|
+
aws_api_key: NotRequired[str]
|
|
215
|
+
r"""This value can be a constant or a JavaScript expression (`${C.env.SOME_ACCESS_KEY}`)"""
|
|
216
|
+
aws_secret: NotRequired[str]
|
|
217
|
+
r"""Select or create a stored secret that references your access key and secret key"""
|
|
218
|
+
compress: NotRequired[OutputDlS3Compression]
|
|
219
|
+
r"""Data compression format to apply to HTTP content before it is delivered"""
|
|
220
|
+
compression_level: NotRequired[OutputDlS3CompressionLevel]
|
|
221
|
+
r"""Compression level to apply before moving files to final destination"""
|
|
222
|
+
automatic_schema: NotRequired[bool]
|
|
223
|
+
r"""Automatically calculate the schema based on the events of each Parquet file generated"""
|
|
224
|
+
parquet_version: NotRequired[OutputDlS3ParquetVersion]
|
|
225
|
+
r"""Determines which data types are supported and how they are represented"""
|
|
226
|
+
parquet_data_page_version: NotRequired[OutputDlS3DataPageVersion]
|
|
227
|
+
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."""
|
|
228
|
+
parquet_row_group_length: NotRequired[float]
|
|
229
|
+
r"""The number of rows that every group will contain. The final group can contain a smaller number of rows."""
|
|
230
|
+
parquet_page_size: NotRequired[str]
|
|
231
|
+
r"""Target memory size for page segments, such as 1MB or 128MB. Generally, lower values improve reading speed, while higher values improve compression."""
|
|
232
|
+
should_log_invalid_rows: NotRequired[bool]
|
|
233
|
+
r"""Log up to 3 rows that @{product} skips due to data mismatch"""
|
|
234
|
+
key_value_metadata: NotRequired[List[OutputDlS3KeyValueMetadatumTypedDict]]
|
|
235
|
+
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\" """
|
|
236
|
+
enable_statistics: NotRequired[bool]
|
|
237
|
+
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."""
|
|
238
|
+
enable_write_page_index: NotRequired[bool]
|
|
239
|
+
r"""One page index contains statistics for one data page. Parquet readers use statistics to enable page skipping."""
|
|
240
|
+
enable_page_checksum: NotRequired[bool]
|
|
241
|
+
r"""Parquet tools can use the checksum of a Parquet page to verify data integrity"""
|
|
242
|
+
empty_dir_cleanup_sec: NotRequired[float]
|
|
243
|
+
r"""How frequently, in seconds, to clean up empty directories"""
|
|
244
|
+
deadletter_path: NotRequired[str]
|
|
245
|
+
r"""Storage location for files that fail to reach their final destination after maximum retries are exceeded"""
|
|
246
|
+
max_retry_num: NotRequired[float]
|
|
247
|
+
r"""The maximum number of times a file will attempt to move to its final destination before being dead-lettered"""
|
|
248
|
+
|
|
249
|
+
|
|
250
|
+
class OutputDlS3(BaseModel):
|
|
251
|
+
bucket: str
|
|
252
|
+
r"""Name of the destination S3 bucket. Must be a JavaScript expression (which can evaluate to a constant value), enclosed in quotes or backticks. Can be evaluated only at initialization time. Example referencing a Global Variable: `myBucket-${C.vars.myVar}`"""
|
|
253
|
+
|
|
254
|
+
id: Optional[str] = None
|
|
255
|
+
r"""Unique ID for this output"""
|
|
256
|
+
|
|
257
|
+
type: Annotated[
|
|
258
|
+
Optional[OutputDlS3Type], PlainValidator(validate_open_enum(False))
|
|
259
|
+
] = None
|
|
260
|
+
|
|
261
|
+
pipeline: Optional[str] = None
|
|
262
|
+
r"""Pipeline to process data before sending out to this output"""
|
|
263
|
+
|
|
264
|
+
system_fields: Annotated[
|
|
265
|
+
Optional[List[str]], pydantic.Field(alias="systemFields")
|
|
266
|
+
] = None
|
|
267
|
+
r"""Fields to automatically add to events, such as cribl_pipe. Supports wildcards."""
|
|
268
|
+
|
|
269
|
+
environment: Optional[str] = None
|
|
270
|
+
r"""Optionally, enable this config only on a specified Git branch. If empty, will be enabled everywhere."""
|
|
271
|
+
|
|
272
|
+
streamtags: Optional[List[str]] = None
|
|
273
|
+
r"""Tags for filtering and grouping in @{product}"""
|
|
274
|
+
|
|
275
|
+
region: Optional[str] = None
|
|
276
|
+
r"""Region where the S3 bucket is located"""
|
|
277
|
+
|
|
278
|
+
aws_secret_key: Annotated[Optional[str], pydantic.Field(alias="awsSecretKey")] = (
|
|
279
|
+
None
|
|
280
|
+
)
|
|
281
|
+
r"""Secret key. This value can be a constant or a JavaScript expression. Example: `${C.env.SOME_SECRET}`)"""
|
|
282
|
+
|
|
283
|
+
aws_authentication_method: Annotated[
|
|
284
|
+
Annotated[
|
|
285
|
+
Optional[OutputDlS3AuthenticationMethod],
|
|
286
|
+
PlainValidator(validate_open_enum(False)),
|
|
287
|
+
],
|
|
288
|
+
pydantic.Field(alias="awsAuthenticationMethod"),
|
|
289
|
+
] = OutputDlS3AuthenticationMethod.AUTO
|
|
290
|
+
r"""AWS authentication method. Choose Auto to use IAM roles."""
|
|
291
|
+
|
|
292
|
+
endpoint: Optional[str] = None
|
|
293
|
+
r"""S3 service endpoint. If empty, defaults to the AWS Region-specific endpoint. Otherwise, it must point to S3-compatible endpoint."""
|
|
294
|
+
|
|
295
|
+
signature_version: Annotated[
|
|
296
|
+
Annotated[
|
|
297
|
+
Optional[OutputDlS3SignatureVersion],
|
|
298
|
+
PlainValidator(validate_open_enum(False)),
|
|
299
|
+
],
|
|
300
|
+
pydantic.Field(alias="signatureVersion"),
|
|
301
|
+
] = OutputDlS3SignatureVersion.V4
|
|
302
|
+
r"""Signature version to use for signing S3 requests"""
|
|
303
|
+
|
|
304
|
+
reuse_connections: Annotated[
|
|
305
|
+
Optional[bool], pydantic.Field(alias="reuseConnections")
|
|
306
|
+
] = True
|
|
307
|
+
r"""Reuse connections between requests, which can improve performance"""
|
|
308
|
+
|
|
309
|
+
reject_unauthorized: Annotated[
|
|
310
|
+
Optional[bool], pydantic.Field(alias="rejectUnauthorized")
|
|
311
|
+
] = True
|
|
312
|
+
r"""Reject certificates that cannot be verified against a valid CA, such as self-signed certificates"""
|
|
313
|
+
|
|
314
|
+
enable_assume_role: Annotated[
|
|
315
|
+
Optional[bool], pydantic.Field(alias="enableAssumeRole")
|
|
316
|
+
] = False
|
|
317
|
+
r"""Use Assume Role credentials to access S3"""
|
|
318
|
+
|
|
319
|
+
assume_role_arn: Annotated[Optional[str], pydantic.Field(alias="assumeRoleArn")] = (
|
|
320
|
+
None
|
|
321
|
+
)
|
|
322
|
+
r"""Amazon Resource Name (ARN) of the role to assume"""
|
|
323
|
+
|
|
324
|
+
assume_role_external_id: Annotated[
|
|
325
|
+
Optional[str], pydantic.Field(alias="assumeRoleExternalId")
|
|
326
|
+
] = None
|
|
327
|
+
r"""External ID to use when assuming role"""
|
|
328
|
+
|
|
329
|
+
duration_seconds: Annotated[
|
|
330
|
+
Optional[float], pydantic.Field(alias="durationSeconds")
|
|
331
|
+
] = 3600
|
|
332
|
+
r"""Duration of the assumed role's session, in seconds. Minimum is 900 (15 minutes), default is 3600 (1 hour), and maximum is 43200 (12 hours)."""
|
|
333
|
+
|
|
334
|
+
stage_path: Annotated[Optional[str], pydantic.Field(alias="stagePath")] = (
|
|
335
|
+
"$CRIBL_HOME/state/outputs/staging"
|
|
336
|
+
)
|
|
337
|
+
r"""Filesystem location in which to buffer files, before compressing and moving to final destination. Use performant and stable storage."""
|
|
338
|
+
|
|
339
|
+
add_id_to_stage_path: Annotated[
|
|
340
|
+
Optional[bool], pydantic.Field(alias="addIdToStagePath")
|
|
341
|
+
] = True
|
|
342
|
+
r"""Add the Output ID value to staging location"""
|
|
343
|
+
|
|
344
|
+
dest_path: Annotated[Optional[str], pydantic.Field(alias="destPath")] = ""
|
|
345
|
+
r"""Prefix to append to files before uploading. Must be a JavaScript expression (which can evaluate to a constant value), enclosed in quotes or backticks. Can be evaluated only at init time. Example referencing a Global Variable: `myKeyPrefix-${C.vars.myVar}`"""
|
|
346
|
+
|
|
347
|
+
object_acl: Annotated[
|
|
348
|
+
Annotated[
|
|
349
|
+
Optional[OutputDlS3ObjectACL], PlainValidator(validate_open_enum(False))
|
|
350
|
+
],
|
|
351
|
+
pydantic.Field(alias="objectACL"),
|
|
352
|
+
] = OutputDlS3ObjectACL.PRIVATE
|
|
353
|
+
r"""Object ACL to assign to uploaded objects"""
|
|
354
|
+
|
|
355
|
+
storage_class: Annotated[
|
|
356
|
+
Annotated[
|
|
357
|
+
Optional[OutputDlS3StorageClass], PlainValidator(validate_open_enum(False))
|
|
358
|
+
],
|
|
359
|
+
pydantic.Field(alias="storageClass"),
|
|
360
|
+
] = None
|
|
361
|
+
r"""Storage class to select for uploaded objects"""
|
|
362
|
+
|
|
363
|
+
server_side_encryption: Annotated[
|
|
364
|
+
Annotated[
|
|
365
|
+
Optional[OutputDlS3ServerSideEncryptionForUploadedObjects],
|
|
366
|
+
PlainValidator(validate_open_enum(False)),
|
|
367
|
+
],
|
|
368
|
+
pydantic.Field(alias="serverSideEncryption"),
|
|
369
|
+
] = None
|
|
370
|
+
|
|
371
|
+
kms_key_id: Annotated[Optional[str], pydantic.Field(alias="kmsKeyId")] = None
|
|
372
|
+
r"""ID or ARN of the KMS customer-managed key to use for encryption"""
|
|
373
|
+
|
|
374
|
+
remove_empty_dirs: Annotated[
|
|
375
|
+
Optional[bool], pydantic.Field(alias="removeEmptyDirs")
|
|
376
|
+
] = True
|
|
377
|
+
r"""Remove empty staging directories after moving files"""
|
|
378
|
+
|
|
379
|
+
format_: Annotated[
|
|
380
|
+
Annotated[
|
|
381
|
+
Optional[OutputDlS3DataFormat], PlainValidator(validate_open_enum(False))
|
|
382
|
+
],
|
|
383
|
+
pydantic.Field(alias="format"),
|
|
384
|
+
] = OutputDlS3DataFormat.JSON
|
|
385
|
+
r"""Format of the output data"""
|
|
386
|
+
|
|
387
|
+
base_file_name: Annotated[Optional[str], pydantic.Field(alias="baseFileName")] = (
|
|
388
|
+
"`CriblOut`"
|
|
389
|
+
)
|
|
390
|
+
r"""JavaScript expression to define the output filename prefix (can be constant)"""
|
|
391
|
+
|
|
392
|
+
file_name_suffix: Annotated[
|
|
393
|
+
Optional[str], pydantic.Field(alias="fileNameSuffix")
|
|
394
|
+
] = '`.${C.env["CRIBL_WORKER_ID"]}.${__format}${__compression === "gzip" ? ".gz" : ""}`'
|
|
395
|
+
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`)."""
|
|
396
|
+
|
|
397
|
+
max_file_size_mb: Annotated[
|
|
398
|
+
Optional[float], pydantic.Field(alias="maxFileSizeMB")
|
|
399
|
+
] = 32
|
|
400
|
+
r"""Maximum uncompressed output file size. Files of this size will be closed and moved to final output location."""
|
|
401
|
+
|
|
402
|
+
max_open_files: Annotated[Optional[float], pydantic.Field(alias="maxOpenFiles")] = (
|
|
403
|
+
100
|
|
404
|
+
)
|
|
405
|
+
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."""
|
|
406
|
+
|
|
407
|
+
header_line: Annotated[Optional[str], pydantic.Field(alias="headerLine")] = ""
|
|
408
|
+
r"""If set, this line will be written to the beginning of each output file"""
|
|
409
|
+
|
|
410
|
+
write_high_water_mark: Annotated[
|
|
411
|
+
Optional[float], pydantic.Field(alias="writeHighWaterMark")
|
|
412
|
+
] = 64
|
|
413
|
+
r"""Buffer size used to write to a file"""
|
|
414
|
+
|
|
415
|
+
on_backpressure: Annotated[
|
|
416
|
+
Annotated[
|
|
417
|
+
Optional[OutputDlS3BackpressureBehavior],
|
|
418
|
+
PlainValidator(validate_open_enum(False)),
|
|
419
|
+
],
|
|
420
|
+
pydantic.Field(alias="onBackpressure"),
|
|
421
|
+
] = OutputDlS3BackpressureBehavior.BLOCK
|
|
422
|
+
r"""How to handle events when all receivers are exerting backpressure"""
|
|
423
|
+
|
|
424
|
+
deadletter_enabled: Annotated[
|
|
425
|
+
Optional[bool], pydantic.Field(alias="deadletterEnabled")
|
|
426
|
+
] = False
|
|
427
|
+
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"""
|
|
428
|
+
|
|
429
|
+
on_disk_full_backpressure: Annotated[
|
|
430
|
+
Annotated[
|
|
431
|
+
Optional[OutputDlS3DiskSpaceProtection],
|
|
432
|
+
PlainValidator(validate_open_enum(False)),
|
|
433
|
+
],
|
|
434
|
+
pydantic.Field(alias="onDiskFullBackpressure"),
|
|
435
|
+
] = OutputDlS3DiskSpaceProtection.BLOCK
|
|
436
|
+
r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
|
|
437
|
+
|
|
438
|
+
max_file_open_time_sec: Annotated[
|
|
439
|
+
Optional[float], pydantic.Field(alias="maxFileOpenTimeSec")
|
|
440
|
+
] = 300
|
|
441
|
+
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."""
|
|
442
|
+
|
|
443
|
+
max_file_idle_time_sec: Annotated[
|
|
444
|
+
Optional[float], pydantic.Field(alias="maxFileIdleTimeSec")
|
|
445
|
+
] = 30
|
|
446
|
+
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."""
|
|
447
|
+
|
|
448
|
+
max_concurrent_file_parts: Annotated[
|
|
449
|
+
Optional[float], pydantic.Field(alias="maxConcurrentFileParts")
|
|
450
|
+
] = 4
|
|
451
|
+
r"""Maximum number of parts to upload in parallel per file. Minimum part size is 5MB."""
|
|
452
|
+
|
|
453
|
+
verify_permissions: Annotated[
|
|
454
|
+
Optional[bool], pydantic.Field(alias="verifyPermissions")
|
|
455
|
+
] = True
|
|
456
|
+
r"""Disable if you can access files within the bucket but not the bucket itself"""
|
|
457
|
+
|
|
458
|
+
max_closing_files_to_backpressure: Annotated[
|
|
459
|
+
Optional[float], pydantic.Field(alias="maxClosingFilesToBackpressure")
|
|
460
|
+
] = 100
|
|
461
|
+
r"""Maximum number of files that can be waiting for upload before backpressure is applied"""
|
|
462
|
+
|
|
463
|
+
partitioning_fields: Annotated[
|
|
464
|
+
Optional[List[str]], pydantic.Field(alias="partitioningFields")
|
|
465
|
+
] = None
|
|
466
|
+
r"""List of fields to partition the path by, in addition to time, which is included automatically. The effective partition will be YYYY/MM/DD/HH/<list/of/fields>."""
|
|
467
|
+
|
|
468
|
+
description: Optional[str] = None
|
|
469
|
+
|
|
470
|
+
aws_api_key: Annotated[Optional[str], pydantic.Field(alias="awsApiKey")] = None
|
|
471
|
+
r"""This value can be a constant or a JavaScript expression (`${C.env.SOME_ACCESS_KEY}`)"""
|
|
472
|
+
|
|
473
|
+
aws_secret: Annotated[Optional[str], pydantic.Field(alias="awsSecret")] = None
|
|
474
|
+
r"""Select or create a stored secret that references your access key and secret key"""
|
|
475
|
+
|
|
476
|
+
compress: Annotated[
|
|
477
|
+
Optional[OutputDlS3Compression], PlainValidator(validate_open_enum(False))
|
|
478
|
+
] = OutputDlS3Compression.GZIP
|
|
479
|
+
r"""Data compression format to apply to HTTP content before it is delivered"""
|
|
480
|
+
|
|
481
|
+
compression_level: Annotated[
|
|
482
|
+
Annotated[
|
|
483
|
+
Optional[OutputDlS3CompressionLevel],
|
|
484
|
+
PlainValidator(validate_open_enum(False)),
|
|
485
|
+
],
|
|
486
|
+
pydantic.Field(alias="compressionLevel"),
|
|
487
|
+
] = OutputDlS3CompressionLevel.BEST_SPEED
|
|
488
|
+
r"""Compression level to apply before moving files to final destination"""
|
|
489
|
+
|
|
490
|
+
automatic_schema: Annotated[
|
|
491
|
+
Optional[bool], pydantic.Field(alias="automaticSchema")
|
|
492
|
+
] = False
|
|
493
|
+
r"""Automatically calculate the schema based on the events of each Parquet file generated"""
|
|
494
|
+
|
|
495
|
+
parquet_version: Annotated[
|
|
496
|
+
Annotated[
|
|
497
|
+
Optional[OutputDlS3ParquetVersion],
|
|
498
|
+
PlainValidator(validate_open_enum(False)),
|
|
499
|
+
],
|
|
500
|
+
pydantic.Field(alias="parquetVersion"),
|
|
501
|
+
] = OutputDlS3ParquetVersion.PARQUET_2_6
|
|
502
|
+
r"""Determines which data types are supported and how they are represented"""
|
|
503
|
+
|
|
504
|
+
parquet_data_page_version: Annotated[
|
|
505
|
+
Annotated[
|
|
506
|
+
Optional[OutputDlS3DataPageVersion],
|
|
507
|
+
PlainValidator(validate_open_enum(False)),
|
|
508
|
+
],
|
|
509
|
+
pydantic.Field(alias="parquetDataPageVersion"),
|
|
510
|
+
] = OutputDlS3DataPageVersion.DATA_PAGE_V2
|
|
511
|
+
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."""
|
|
512
|
+
|
|
513
|
+
parquet_row_group_length: Annotated[
|
|
514
|
+
Optional[float], pydantic.Field(alias="parquetRowGroupLength")
|
|
515
|
+
] = 10000
|
|
516
|
+
r"""The number of rows that every group will contain. The final group can contain a smaller number of rows."""
|
|
517
|
+
|
|
518
|
+
parquet_page_size: Annotated[
|
|
519
|
+
Optional[str], pydantic.Field(alias="parquetPageSize")
|
|
520
|
+
] = "1MB"
|
|
521
|
+
r"""Target memory size for page segments, such as 1MB or 128MB. Generally, lower values improve reading speed, while higher values improve compression."""
|
|
522
|
+
|
|
523
|
+
should_log_invalid_rows: Annotated[
|
|
524
|
+
Optional[bool], pydantic.Field(alias="shouldLogInvalidRows")
|
|
525
|
+
] = None
|
|
526
|
+
r"""Log up to 3 rows that @{product} skips due to data mismatch"""
|
|
527
|
+
|
|
528
|
+
key_value_metadata: Annotated[
|
|
529
|
+
Optional[List[OutputDlS3KeyValueMetadatum]],
|
|
530
|
+
pydantic.Field(alias="keyValueMetadata"),
|
|
531
|
+
] = None
|
|
532
|
+
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\" """
|
|
533
|
+
|
|
534
|
+
enable_statistics: Annotated[
|
|
535
|
+
Optional[bool], pydantic.Field(alias="enableStatistics")
|
|
536
|
+
] = True
|
|
537
|
+
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."""
|
|
538
|
+
|
|
539
|
+
enable_write_page_index: Annotated[
|
|
540
|
+
Optional[bool], pydantic.Field(alias="enableWritePageIndex")
|
|
541
|
+
] = True
|
|
542
|
+
r"""One page index contains statistics for one data page. Parquet readers use statistics to enable page skipping."""
|
|
543
|
+
|
|
544
|
+
enable_page_checksum: Annotated[
|
|
545
|
+
Optional[bool], pydantic.Field(alias="enablePageChecksum")
|
|
546
|
+
] = False
|
|
547
|
+
r"""Parquet tools can use the checksum of a Parquet page to verify data integrity"""
|
|
548
|
+
|
|
549
|
+
empty_dir_cleanup_sec: Annotated[
|
|
550
|
+
Optional[float], pydantic.Field(alias="emptyDirCleanupSec")
|
|
551
|
+
] = 300
|
|
552
|
+
r"""How frequently, in seconds, to clean up empty directories"""
|
|
553
|
+
|
|
554
|
+
deadletter_path: Annotated[
|
|
555
|
+
Optional[str], pydantic.Field(alias="deadletterPath")
|
|
556
|
+
] = "$CRIBL_HOME/state/outputs/dead-letter"
|
|
557
|
+
r"""Storage location for files that fail to reach their final destination after maximum retries are exceeded"""
|
|
558
|
+
|
|
559
|
+
max_retry_num: Annotated[Optional[float], pydantic.Field(alias="maxRetryNum")] = 20
|
|
560
|
+
r"""The maximum number of times a file will attempt to move to its final destination before being dead-lettered"""
|