aws-sdk-glue 1.112.0 → 1.115.0

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.
@@ -3752,6 +3752,18 @@ module Aws::Glue
3752
3752
  # * `CONNECTION_URL` - The URL for connecting to a general (non-JDBC)
3753
3753
  # data source.
3754
3754
  #
3755
+ # * `SECRET_ID` - The secret ID used for the secret manager of
3756
+ # credentials.
3757
+ #
3758
+ # * `CONNECTOR_URL` - The connector URL for a MARKETPLACE or CUSTOM
3759
+ # connection.
3760
+ #
3761
+ # * `CONNECTOR_TYPE` - The connector type for a MARKETPLACE or CUSTOM
3762
+ # connection.
3763
+ #
3764
+ # * `CONNECTOR_CLASS_NAME` - The connector class name for a
3765
+ # MARKETPLACE or CUSTOM connection.
3766
+ #
3755
3767
  # * `KAFKA_BOOTSTRAP_SERVERS` - A comma-separated list of host and
3756
3768
  # port pairs that are the addresses of the Apache Kafka brokers in a
3757
3769
  # Kafka cluster to which a Kafka client will connect to and
@@ -3768,18 +3780,6 @@ module Aws::Glue
3768
3780
  # algorithms: SHA256withRSA, SHA384withRSA and SHA512withRSA.
3769
3781
  # Default value is "false".
3770
3782
  #
3771
- # * `SECRET_ID` - The secret ID used for the secret manager of
3772
- # credentials.
3773
- #
3774
- # * `CONNECTOR_URL` - The connector URL for a MARKETPLACE or CUSTOM
3775
- # connection.
3776
- #
3777
- # * `CONNECTOR_TYPE` - The connector type for a MARKETPLACE or CUSTOM
3778
- # connection.
3779
- #
3780
- # * `CONNECTOR_CLASS_NAME` - The connector class name for a
3781
- # MARKETPLACE or CUSTOM connection.
3782
- #
3783
3783
  # * `KAFKA_CLIENT_KEYSTORE` - The Amazon S3 location of the client
3784
3784
  # keystore file for Kafka client side authentication (Optional).
3785
3785
  #
@@ -3797,6 +3797,45 @@ module Aws::Glue
3797
3797
  # * `ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD` - The encrypted version of
3798
3798
  # the Kafka client key password (if the user has the Glue encrypt
3799
3799
  # passwords setting selected).
3800
+ #
3801
+ # * `KAFKA_SASL_MECHANISM` - `"SCRAM-SHA-512"` or `"GSSAPI"`. These
3802
+ # are the two supported [SASL Mechanisms][1].
3803
+ #
3804
+ # * `KAFKA_SASL_SCRAM_USERNAME` - A plaintext username used to
3805
+ # authenticate with the "SCRAM-SHA-512" mechanism.
3806
+ #
3807
+ # * `KAFKA_SASL_SCRAM_PASSWORD` - A plaintext password used to
3808
+ # authenticate with the "SCRAM-SHA-512" mechanism.
3809
+ #
3810
+ # * `ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD` - The encrypted version of
3811
+ # the Kafka SASL SCRAM password (if the user has the Glue encrypt
3812
+ # passwords setting selected).
3813
+ #
3814
+ # * `KAFKA_SASL_GSSAPI_KEYTAB` - The S3 location of a Kerberos
3815
+ # `keytab` file. A keytab stores long-term keys for one or more
3816
+ # principals. For more information, see [MIT Kerberos Documentation:
3817
+ # Keytab][2].
3818
+ #
3819
+ # * `KAFKA_SASL_GSSAPI_KRB5_CONF` - The S3 location of a Kerberos
3820
+ # `krb5.conf` file. A krb5.conf stores Kerberos configuration
3821
+ # information, such as the location of the KDC server. For more
3822
+ # information, see [MIT Kerberos Documentation: krb5.conf][3].
3823
+ #
3824
+ # * `KAFKA_SASL_GSSAPI_SERVICE` - The Kerberos service name, as set
3825
+ # with `sasl.kerberos.service.name` in your [Kafka
3826
+ # Configuration][4].
3827
+ #
3828
+ # * `KAFKA_SASL_GSSAPI_PRINCIPAL` - The name of the Kerberos princial
3829
+ # used by Glue. For more information, see [Kafka Documentation:
3830
+ # Configuring Kafka Brokers][5].
3831
+ #
3832
+ #
3833
+ #
3834
+ # [1]: https://www.iana.org/assignments/sasl-mechanisms/sasl-mechanisms.xhtml
3835
+ # [2]: https://web.mit.edu/kerberos/krb5-latest/doc/basic/keytab_def.html
3836
+ # [3]: https://web.mit.edu/kerberos/krb5-1.12/doc/admin/conf_files/krb5_conf.html
3837
+ # [4]: https://kafka.apache.org/documentation/#brokerconfigs_sasl.kerberos.service.name
3838
+ # [5]: https://kafka.apache.org/documentation/#security_sasl_kerberos_clientconfig
3800
3839
  # @return [Hash<String,String>]
3801
3840
  #
3802
3841
  # @!attribute [rw] physical_connection_requirements
@@ -4124,8 +4163,8 @@ module Aws::Glue
4124
4163
  # @return [String]
4125
4164
  #
4126
4165
  # @!attribute [rw] lake_formation_configuration
4127
- # Specifies whether the crawler should use AWS Lake Formation
4128
- # credentials for the crawler instead of the IAM role credentials.
4166
+ # Specifies whether the crawler should use Lake Formation credentials
4167
+ # for the crawler instead of the IAM role credentials.
4129
4168
  # @return [Types::LakeFormationConfiguration]
4130
4169
  #
4131
4170
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/Crawler AWS API Documentation
@@ -4155,6 +4194,67 @@ module Aws::Glue
4155
4194
  include Aws::Structure
4156
4195
  end
4157
4196
 
4197
+ # Contains the information for a run of a crawler.
4198
+ #
4199
+ # @!attribute [rw] crawl_id
4200
+ # A UUID identifier for each crawl.
4201
+ # @return [String]
4202
+ #
4203
+ # @!attribute [rw] state
4204
+ # The state of the crawl.
4205
+ # @return [String]
4206
+ #
4207
+ # @!attribute [rw] start_time
4208
+ # The date and time on which the crawl started.
4209
+ # @return [Time]
4210
+ #
4211
+ # @!attribute [rw] end_time
4212
+ # The date and time on which the crawl ended.
4213
+ # @return [Time]
4214
+ #
4215
+ # @!attribute [rw] summary
4216
+ # A run summary for the specific crawl in JSON. Contains the catalog
4217
+ # tables and partitions that were added, updated, or deleted.
4218
+ # @return [String]
4219
+ #
4220
+ # @!attribute [rw] error_message
4221
+ # If an error occurred, the error message associated with the crawl.
4222
+ # @return [String]
4223
+ #
4224
+ # @!attribute [rw] log_group
4225
+ # The log group associated with the crawl.
4226
+ # @return [String]
4227
+ #
4228
+ # @!attribute [rw] log_stream
4229
+ # The log stream associated with the crawl.
4230
+ # @return [String]
4231
+ #
4232
+ # @!attribute [rw] message_prefix
4233
+ # The prefix for a CloudWatch message about this crawl.
4234
+ # @return [String]
4235
+ #
4236
+ # @!attribute [rw] dpu_hour
4237
+ # The number of data processing units (DPU) used in hours for the
4238
+ # crawl.
4239
+ # @return [Float]
4240
+ #
4241
+ # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/CrawlerHistory AWS API Documentation
4242
+ #
4243
+ class CrawlerHistory < Struct.new(
4244
+ :crawl_id,
4245
+ :state,
4246
+ :start_time,
4247
+ :end_time,
4248
+ :summary,
4249
+ :error_message,
4250
+ :log_group,
4251
+ :log_stream,
4252
+ :message_prefix,
4253
+ :dpu_hour)
4254
+ SENSITIVE = []
4255
+ include Aws::Structure
4256
+ end
4257
+
4158
4258
  # Metrics for a specified crawler.
4159
4259
  #
4160
4260
  # @!attribute [rw] crawler_name
@@ -4352,6 +4452,64 @@ module Aws::Glue
4352
4452
  include Aws::Structure
4353
4453
  end
4354
4454
 
4455
+ # A list of fields, comparators and value that you can use to filter the
4456
+ # crawler runs for a specified crawler.
4457
+ #
4458
+ # @note When making an API call, you may pass CrawlsFilter
4459
+ # data as a hash:
4460
+ #
4461
+ # {
4462
+ # field_name: "CRAWL_ID", # accepts CRAWL_ID, STATE, START_TIME, END_TIME, DPU_HOUR
4463
+ # filter_operator: "GT", # accepts GT, GE, LT, LE, EQ, NE
4464
+ # field_value: "GenericString",
4465
+ # }
4466
+ #
4467
+ # @!attribute [rw] field_name
4468
+ # A key used to filter the crawler runs for a specified crawler. Valid
4469
+ # values for each of the field names are:
4470
+ #
4471
+ # * `CRAWL_ID`\: A string representing the UUID identifier for a
4472
+ # crawl.
4473
+ #
4474
+ # * `STATE`\: A string representing the state of the crawl.
4475
+ #
4476
+ # * `START_TIME` and `END_TIME`\: The epoch timestamp in milliseconds.
4477
+ #
4478
+ # * `DPU_HOUR`\: The number of data processing unit (DPU) hours used
4479
+ # for the crawl.
4480
+ # @return [String]
4481
+ #
4482
+ # @!attribute [rw] filter_operator
4483
+ # A defined comparator that operates on the value. The available
4484
+ # operators are:
4485
+ #
4486
+ # * `GT`\: Greater than.
4487
+ #
4488
+ # * `GE`\: Greater than or equal to.
4489
+ #
4490
+ # * `LT`\: Less than.
4491
+ #
4492
+ # * `LE`\: Less than or equal to.
4493
+ #
4494
+ # * `EQ`\: Equal to.
4495
+ #
4496
+ # * `NE`\: Not equal to.
4497
+ # @return [String]
4498
+ #
4499
+ # @!attribute [rw] field_value
4500
+ # The value provided for comparison on the crawl field.
4501
+ # @return [String]
4502
+ #
4503
+ # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/CrawlsFilter AWS API Documentation
4504
+ #
4505
+ class CrawlsFilter < Struct.new(
4506
+ :field_name,
4507
+ :filter_operator,
4508
+ :field_value)
4509
+ SENSITIVE = []
4510
+ include Aws::Structure
4511
+ end
4512
+
4355
4513
  # @note When making an API call, you may pass CreateBlueprintRequest
4356
4514
  # data as a hash:
4357
4515
  #
@@ -4652,7 +4810,7 @@ module Aws::Glue
4652
4810
  # @return [Types::LineageConfiguration]
4653
4811
  #
4654
4812
  # @!attribute [rw] lake_formation_configuration
4655
- # Specifies AWS Lake Formation configuration settings for the crawler.
4813
+ # Specifies Lake Formation configuration settings for the crawler.
4656
4814
  # @return [Types::LakeFormationConfiguration]
4657
4815
  #
4658
4816
  # @!attribute [rw] configuration
@@ -4841,6 +4999,9 @@ module Aws::Glue
4841
4999
  # database_name: "NameString",
4842
5000
  # },
4843
5001
  # },
5002
+ # tags: {
5003
+ # "TagKey" => "TagValue",
5004
+ # },
4844
5005
  # }
4845
5006
  #
4846
5007
  # @!attribute [rw] catalog_id
@@ -4852,11 +5013,16 @@ module Aws::Glue
4852
5013
  # The metadata for the database.
4853
5014
  # @return [Types::DatabaseInput]
4854
5015
  #
5016
+ # @!attribute [rw] tags
5017
+ # The tags you assign to the database.
5018
+ # @return [Hash<String,String>]
5019
+ #
4855
5020
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/CreateDatabaseRequest AWS API Documentation
4856
5021
  #
4857
5022
  class CreateDatabaseRequest < Struct.new(
4858
5023
  :catalog_id,
4859
- :database_input)
5024
+ :database_input,
5025
+ :tags)
4860
5026
  SENSITIVE = []
4861
5027
  include Aws::Structure
4862
5028
  end
@@ -4876,7 +5042,7 @@ module Aws::Glue
4876
5042
  # public_key: "GenericString",
4877
5043
  # public_keys: ["GenericString"],
4878
5044
  # number_of_nodes: 1,
4879
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
5045
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
4880
5046
  # glue_version: "GlueVersionString",
4881
5047
  # number_of_workers: 1,
4882
5048
  # extra_python_libs_s3_path: "GenericString",
@@ -5254,7 +5420,7 @@ module Aws::Glue
5254
5420
  # },
5255
5421
  # glue_version: "GlueVersionString",
5256
5422
  # number_of_workers: 1,
5257
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
5423
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
5258
5424
  # code_gen_configuration_nodes: {
5259
5425
  # "NodeId" => {
5260
5426
  # athena_connector_source: {
@@ -5958,6 +6124,11 @@ module Aws::Glue
5958
6124
  # You can specify arguments here that your own job-execution script
5959
6125
  # consumes, as well as arguments that Glue itself consumes.
5960
6126
  #
6127
+ # Job arguments may be logged. Do not pass plaintext secrets as
6128
+ # arguments. Retrieve secrets from a Glue Connection, Secrets Manager
6129
+ # or other secret management mechanism if you intend to keep them
6130
+ # within the Job.
6131
+ #
5961
6132
  # For information about how to specify and consume your own Job
5962
6133
  # arguments, see the [Calling Glue APIs in Python][1] topic in the
5963
6134
  # developer guide.
@@ -5989,7 +6160,7 @@ module Aws::Glue
5989
6160
  # This parameter is deprecated. Use `MaxCapacity` instead.
5990
6161
  #
5991
6162
  # The number of Glue data processing units (DPUs) to allocate to this
5992
- # Job. You can allocate from 2 to 100 DPUs; the default is 10. A DPU
6163
+ # Job. You can allocate a minimum of 2 DPUs; the default is 10. A DPU
5993
6164
  # is a relative measure of processing power that consists of 4 vCPUs
5994
6165
  # of compute capacity and 16 GB of memory. For more information, see
5995
6166
  # the [Glue pricing page][1].
@@ -6024,8 +6195,8 @@ module Aws::Glue
6024
6195
  #
6025
6196
  # * When you specify an Apache Spark ETL job
6026
6197
  # (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
6027
- # (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
6028
- # 100 DPUs. The default is 10 DPUs. This job type cannot have a
6198
+ # (`JobCommand.Name`="gluestreaming"), you can allocate a minimum
6199
+ # of 2 DPUs. The default is 10 DPUs. This job type cannot have a
6029
6200
  # fractional DPU allocation.
6030
6201
  #
6031
6202
  # For Glue version 2.0 jobs, you cannot instead specify a `Maximum
@@ -6076,14 +6247,11 @@ module Aws::Glue
6076
6247
  # @!attribute [rw] number_of_workers
6077
6248
  # The number of workers of a defined `workerType` that are allocated
6078
6249
  # when a job runs.
6079
- #
6080
- # The maximum number of workers you can define are 299 for `G.1X`, and
6081
- # 149 for `G.2X`.
6082
6250
  # @return [Integer]
6083
6251
  #
6084
6252
  # @!attribute [rw] worker_type
6085
6253
  # The type of predefined worker that is allocated when a job runs.
6086
- # Accepts a value of Standard, G.1X, or G.2X.
6254
+ # Accepts a value of Standard, G.1X, G.2X, or G.025X.
6087
6255
  #
6088
6256
  # * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
6089
6257
  # of memory and a 50GB disk, and 2 executors per worker.
@@ -6095,6 +6263,12 @@ module Aws::Glue
6095
6263
  # * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32
6096
6264
  # GB of memory, 128 GB disk), and provides 1 executor per worker. We
6097
6265
  # recommend this worker type for memory-intensive jobs.
6266
+ #
6267
+ # * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
6268
+ # vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
6269
+ # worker. We recommend this worker type for low volume streaming
6270
+ # jobs. This worker type is only available for Glue version 3.0
6271
+ # streaming jobs.
6098
6272
  # @return [String]
6099
6273
  #
6100
6274
  # @!attribute [rw] code_gen_configuration_nodes
@@ -6201,7 +6375,7 @@ module Aws::Glue
6201
6375
  # role: "RoleString", # required
6202
6376
  # glue_version: "GlueVersionString",
6203
6377
  # max_capacity: 1.0,
6204
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
6378
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
6205
6379
  # number_of_workers: 1,
6206
6380
  # timeout: 1,
6207
6381
  # max_retries: 1,
@@ -6952,7 +7126,7 @@ module Aws::Glue
6952
7126
  # },
6953
7127
  # max_capacity: 1.0,
6954
7128
  # number_of_workers: 1,
6955
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
7129
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
6956
7130
  # security_configuration: "NameString",
6957
7131
  # glue_version: "GlueVersionString",
6958
7132
  # tags: {
@@ -6994,18 +7168,37 @@ module Aws::Glue
6994
7168
  # @return [Types::ConnectionsList]
6995
7169
  #
6996
7170
  # @!attribute [rw] max_capacity
6997
- # The number of AWS Glue data processing units (DPUs) that can be
7171
+ # The number of Glue data processing units (DPUs) that can be
6998
7172
  # allocated when the job runs. A DPU is a relative measure of
6999
7173
  # processing power that consists of 4 vCPUs of compute capacity and 16
7000
7174
  # GB memory.
7001
7175
  # @return [Float]
7002
7176
  #
7003
7177
  # @!attribute [rw] number_of_workers
7004
- # The number of workers to use for the session.
7178
+ # The number of workers of a defined `WorkerType` to use for the
7179
+ # session.
7005
7180
  # @return [Integer]
7006
7181
  #
7007
7182
  # @!attribute [rw] worker_type
7008
- # The Worker Type. Can be one of G.1X, G.2X, Standard
7183
+ # The type of predefined worker that is allocated to use for the
7184
+ # session. Accepts a value of Standard, G.1X, G.2X, or G.025X.
7185
+ #
7186
+ # * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
7187
+ # of memory and a 50GB disk, and 2 executors per worker.
7188
+ #
7189
+ # * For the `G.1X` worker type, each worker maps to 1 DPU (4 vCPU, 16
7190
+ # GB of memory, 64 GB disk), and provides 1 executor per worker. We
7191
+ # recommend this worker type for memory-intensive jobs.
7192
+ #
7193
+ # * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32
7194
+ # GB of memory, 128 GB disk), and provides 1 executor per worker. We
7195
+ # recommend this worker type for memory-intensive jobs.
7196
+ #
7197
+ # * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
7198
+ # vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
7199
+ # worker. We recommend this worker type for low volume streaming
7200
+ # jobs. This worker type is only available for Glue version 3.0
7201
+ # streaming jobs.
7009
7202
  # @return [String]
7010
7203
  #
7011
7204
  # @!attribute [rw] security_configuration
@@ -7015,7 +7208,7 @@ module Aws::Glue
7015
7208
  #
7016
7209
  # @!attribute [rw] glue_version
7017
7210
  # The Glue version determines the versions of Apache Spark and Python
7018
- # that AWS Glue supports. The GlueVersion must be greater than 2.0.
7211
+ # that Glue supports. The GlueVersion must be greater than 2.0.
7019
7212
  # @return [String]
7020
7213
  #
7021
7214
  # @!attribute [rw] tags
@@ -9558,8 +9751,8 @@ module Aws::Glue
9558
9751
  include Aws::Structure
9559
9752
  end
9560
9753
 
9561
- # An edge represents a directed connection between two components on a
9562
- # workflow graph.
9754
+ # An edge represents a directed connection between two Glue components
9755
+ # that are part of the workflow the edge belongs to.
9563
9756
  #
9564
9757
  # @!attribute [rw] source_id
9565
9758
  # The unique of the node within the workflow where the edge starts.
@@ -10504,8 +10697,8 @@ module Aws::Glue
10504
10697
  #
10505
10698
  # @!attribute [rw] hide_password
10506
10699
  # Allows you to retrieve the connection metadata without returning the
10507
- # password. For instance, the AWS Glue console uses this flag to
10508
- # retrieve the connection, and does not display the password. Set this
10700
+ # password. For instance, the Glue console uses this flag to retrieve
10701
+ # the connection, and does not display the password. Set this
10509
10702
  # parameter when the caller might not have permission to use the KMS
10510
10703
  # key to decrypt the password, but it does have permission to access
10511
10704
  # the rest of the connection properties.
@@ -10587,8 +10780,8 @@ module Aws::Glue
10587
10780
  #
10588
10781
  # @!attribute [rw] hide_password
10589
10782
  # Allows you to retrieve the connection metadata without returning the
10590
- # password. For instance, the AWS Glue console uses this flag to
10591
- # retrieve the connection, and does not display the password. Set this
10783
+ # password. For instance, the Glue console uses this flag to retrieve
10784
+ # the connection, and does not display the password. Set this
10592
10785
  # parameter when the caller might not have permission to use the KMS
10593
10786
  # key to decrypt the password, but it does have permission to access
10594
10787
  # the rest of the connection properties.
@@ -13962,7 +14155,10 @@ module Aws::Glue
13962
14155
  include Aws::Structure
13963
14156
  end
13964
14157
 
14158
+ # The blueprint is in an invalid state to perform a requested operation.
14159
+ #
13965
14160
  # @!attribute [rw] message
14161
+ # A message describing the problem.
13966
14162
  # @return [String]
13967
14163
  #
13968
14164
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/IllegalBlueprintStateException AWS API Documentation
@@ -14446,7 +14642,7 @@ module Aws::Glue
14446
14642
  # This field is deprecated. Use `MaxCapacity` instead.
14447
14643
  #
14448
14644
  # The number of Glue data processing units (DPUs) allocated to runs of
14449
- # this job. You can allocate from 2 to 100 DPUs; the default is 10. A
14645
+ # this job. You can allocate a minimum of 2 DPUs; the default is 10. A
14450
14646
  # DPU is a relative measure of processing power that consists of 4
14451
14647
  # vCPUs of compute capacity and 16 GB of memory. For more information,
14452
14648
  # see the [Glue pricing page][1].
@@ -14484,8 +14680,8 @@ module Aws::Glue
14484
14680
  #
14485
14681
  # * When you specify an Apache Spark ETL job
14486
14682
  # (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
14487
- # (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
14488
- # 100 DPUs. The default is 10 DPUs. This job type cannot have a
14683
+ # (`JobCommand.Name`="gluestreaming"), you can allocate a minimum
14684
+ # of 2 DPUs. The default is 10 DPUs. This job type cannot have a
14489
14685
  # fractional DPU allocation.
14490
14686
  #
14491
14687
  # For Glue version 2.0 jobs, you cannot instead specify a `Maximum
@@ -14499,7 +14695,7 @@ module Aws::Glue
14499
14695
  #
14500
14696
  # @!attribute [rw] worker_type
14501
14697
  # The type of predefined worker that is allocated when a job runs.
14502
- # Accepts a value of Standard, G.1X, or G.2X.
14698
+ # Accepts a value of Standard, G.1X, G.2X, or G.025X.
14503
14699
  #
14504
14700
  # * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
14505
14701
  # of memory and a 50GB disk, and 2 executors per worker.
@@ -14511,14 +14707,17 @@ module Aws::Glue
14511
14707
  # * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32
14512
14708
  # GB of memory, 128 GB disk), and provides 1 executor per worker. We
14513
14709
  # recommend this worker type for memory-intensive jobs.
14710
+ #
14711
+ # * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
14712
+ # vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
14713
+ # worker. We recommend this worker type for low volume streaming
14714
+ # jobs. This worker type is only available for Glue version 3.0
14715
+ # streaming jobs.
14514
14716
  # @return [String]
14515
14717
  #
14516
14718
  # @!attribute [rw] number_of_workers
14517
14719
  # The number of workers of a defined `workerType` that are allocated
14518
14720
  # when a job runs.
14519
- #
14520
- # The maximum number of workers you can define are 299 for `G.1X`, and
14521
- # 149 for `G.2X`.
14522
14721
  # @return [Integer]
14523
14722
  #
14524
14723
  # @!attribute [rw] security_configuration
@@ -14820,7 +15019,7 @@ module Aws::Glue
14820
15019
  # 0.0625 or 1 DPU. The default is 0.0625 DPU.
14821
15020
  #
14822
15021
  # * When you specify an Apache Spark ETL job
14823
- # (`JobCommand.Name`="glueetl"), you can allocate from 2 to 100
15022
+ # (`JobCommand.Name`="glueetl"), you can allocate a minimum of 2
14824
15023
  # DPUs. The default is 10 DPUs. This job type cannot have a
14825
15024
  # fractional DPU allocation.
14826
15025
  #
@@ -14831,7 +15030,7 @@ module Aws::Glue
14831
15030
  #
14832
15031
  # @!attribute [rw] worker_type
14833
15032
  # The type of predefined worker that is allocated when a job runs.
14834
- # Accepts a value of Standard, G.1X, or G.2X.
15033
+ # Accepts a value of Standard, G.1X, G.2X, or G.025X.
14835
15034
  #
14836
15035
  # * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
14837
15036
  # of memory and a 50GB disk, and 2 executors per worker.
@@ -14841,14 +15040,17 @@ module Aws::Glue
14841
15040
  #
14842
15041
  # * For the `G.2X` worker type, each worker provides 8 vCPU, 32 GB of
14843
15042
  # memory and a 128GB disk, and 1 executor per worker.
15043
+ #
15044
+ # * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
15045
+ # vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
15046
+ # worker. We recommend this worker type for low volume streaming
15047
+ # jobs. This worker type is only available for Glue version 3.0
15048
+ # streaming jobs.
14844
15049
  # @return [String]
14845
15050
  #
14846
15051
  # @!attribute [rw] number_of_workers
14847
15052
  # The number of workers of a defined `workerType` that are allocated
14848
15053
  # when a job runs.
14849
- #
14850
- # The maximum number of workers you can define are 299 for `G.1X`, and
14851
- # 149 for `G.2X`.
14852
15054
  # @return [Integer]
14853
15055
  #
14854
15056
  # @!attribute [rw] security_configuration
@@ -14960,7 +15162,7 @@ module Aws::Glue
14960
15162
  # allocated_capacity: 1,
14961
15163
  # timeout: 1,
14962
15164
  # max_capacity: 1.0,
14963
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
15165
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
14964
15166
  # number_of_workers: 1,
14965
15167
  # security_configuration: "NameString",
14966
15168
  # notification_property: {
@@ -15696,7 +15898,7 @@ module Aws::Glue
15696
15898
  # This field is deprecated. Use `MaxCapacity` instead.
15697
15899
  #
15698
15900
  # The number of Glue data processing units (DPUs) to allocate to this
15699
- # job. You can allocate from 2 to 100 DPUs; the default is 10. A DPU
15901
+ # job. You can allocate a minimum of 2 DPUs; the default is 10. A DPU
15700
15902
  # is a relative measure of processing power that consists of 4 vCPUs
15701
15903
  # of compute capacity and 16 GB of memory. For more information, see
15702
15904
  # the [Glue pricing page][1].
@@ -15731,8 +15933,8 @@ module Aws::Glue
15731
15933
  #
15732
15934
  # * When you specify an Apache Spark ETL job
15733
15935
  # (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
15734
- # (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
15735
- # 100 DPUs. The default is 10 DPUs. This job type cannot have a
15936
+ # (`JobCommand.Name`="gluestreaming"), you can allocate a minimum
15937
+ # of 2 DPUs. The default is 10 DPUs. This job type cannot have a
15736
15938
  # fractional DPU allocation.
15737
15939
  #
15738
15940
  # For Glue version 2.0 jobs, you cannot instead specify a `Maximum
@@ -15746,7 +15948,7 @@ module Aws::Glue
15746
15948
  #
15747
15949
  # @!attribute [rw] worker_type
15748
15950
  # The type of predefined worker that is allocated when a job runs.
15749
- # Accepts a value of Standard, G.1X, or G.2X.
15951
+ # Accepts a value of Standard, G.1X, G.2X, or G.025X.
15750
15952
  #
15751
15953
  # * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
15752
15954
  # of memory and a 50GB disk, and 2 executors per worker.
@@ -15758,14 +15960,17 @@ module Aws::Glue
15758
15960
  # * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32
15759
15961
  # GB of memory, 128 GB disk), and provides 1 executor per worker. We
15760
15962
  # recommend this worker type for memory-intensive jobs.
15963
+ #
15964
+ # * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
15965
+ # vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
15966
+ # worker. We recommend this worker type for low volume streaming
15967
+ # jobs. This worker type is only available for Glue version 3.0
15968
+ # streaming jobs.
15761
15969
  # @return [String]
15762
15970
  #
15763
15971
  # @!attribute [rw] number_of_workers
15764
15972
  # The number of workers of a defined `workerType` that are allocated
15765
15973
  # when a job runs.
15766
- #
15767
- # The maximum number of workers you can define are 299 for `G.1X`, and
15768
- # 149 for `G.2X`.
15769
15974
  # @return [Integer]
15770
15975
  #
15771
15976
  # @!attribute [rw] security_configuration
@@ -16246,7 +16451,7 @@ module Aws::Glue
16246
16451
  include Aws::Structure
16247
16452
  end
16248
16453
 
16249
- # Specifies AWS Lake Formation configuration settings for the crawler.
16454
+ # Specifies Lake Formation configuration settings for the crawler.
16250
16455
  #
16251
16456
  # @note When making an API call, you may pass LakeFormationConfiguration
16252
16457
  # data as a hash:
@@ -16257,8 +16462,8 @@ module Aws::Glue
16257
16462
  # }
16258
16463
  #
16259
16464
  # @!attribute [rw] use_lake_formation_credentials
16260
- # Specifies whether to use AWS Lake Formation credentials for the
16261
- # crawler instead of the IAM role credentials.
16465
+ # Specifies whether to use Lake Formation credentials for the crawler
16466
+ # instead of the IAM role credentials.
16262
16467
  # @return [Boolean]
16263
16468
  #
16264
16469
  # @!attribute [rw] account_id
@@ -16480,6 +16685,70 @@ module Aws::Glue
16480
16685
  include Aws::Structure
16481
16686
  end
16482
16687
 
16688
+ # @note When making an API call, you may pass ListCrawlsRequest
16689
+ # data as a hash:
16690
+ #
16691
+ # {
16692
+ # crawler_name: "NameString", # required
16693
+ # max_results: 1,
16694
+ # filters: [
16695
+ # {
16696
+ # field_name: "CRAWL_ID", # accepts CRAWL_ID, STATE, START_TIME, END_TIME, DPU_HOUR
16697
+ # filter_operator: "GT", # accepts GT, GE, LT, LE, EQ, NE
16698
+ # field_value: "GenericString",
16699
+ # },
16700
+ # ],
16701
+ # next_token: "Token",
16702
+ # }
16703
+ #
16704
+ # @!attribute [rw] crawler_name
16705
+ # The name of the crawler whose runs you want to retrieve.
16706
+ # @return [String]
16707
+ #
16708
+ # @!attribute [rw] max_results
16709
+ # The maximum number of results to return. The default is 20, and
16710
+ # maximum is 100.
16711
+ # @return [Integer]
16712
+ #
16713
+ # @!attribute [rw] filters
16714
+ # Filters the crawls by the criteria you specify in a list of
16715
+ # `CrawlsFilter` objects.
16716
+ # @return [Array<Types::CrawlsFilter>]
16717
+ #
16718
+ # @!attribute [rw] next_token
16719
+ # A continuation token, if this is a continuation call.
16720
+ # @return [String]
16721
+ #
16722
+ # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/ListCrawlsRequest AWS API Documentation
16723
+ #
16724
+ class ListCrawlsRequest < Struct.new(
16725
+ :crawler_name,
16726
+ :max_results,
16727
+ :filters,
16728
+ :next_token)
16729
+ SENSITIVE = []
16730
+ include Aws::Structure
16731
+ end
16732
+
16733
+ # @!attribute [rw] crawls
16734
+ # A list of `CrawlerHistory` objects representing the crawl runs that
16735
+ # meet your criteria.
16736
+ # @return [Array<Types::CrawlerHistory>]
16737
+ #
16738
+ # @!attribute [rw] next_token
16739
+ # A continuation token for paginating the returned list of tokens,
16740
+ # returned if the current segment of the list is not the last.
16741
+ # @return [String]
16742
+ #
16743
+ # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/ListCrawlsResponse AWS API Documentation
16744
+ #
16745
+ class ListCrawlsResponse < Struct.new(
16746
+ :crawls,
16747
+ :next_token)
16748
+ SENSITIVE = []
16749
+ include Aws::Structure
16750
+ end
16751
+
16483
16752
  # @note When making an API call, you may pass ListCustomEntityTypesRequest
16484
16753
  # data as a hash:
16485
16754
  #
@@ -16914,7 +17183,7 @@ module Aws::Glue
16914
17183
  end
16915
17184
 
16916
17185
  # @!attribute [rw] ids
16917
- # Returns the Id of the session.
17186
+ # Returns the ID of the session.
16918
17187
  # @return [Array<String>]
16919
17188
  #
16920
17189
  # @!attribute [rw] sessions
@@ -16954,6 +17223,7 @@ module Aws::Glue
16954
17223
  # @return [String]
16955
17224
  #
16956
17225
  # @!attribute [rw] next_token
17226
+ # A continuation token, if this is a continuation call.
16957
17227
  # @return [String]
16958
17228
  #
16959
17229
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/ListStatementsRequest AWS API Documentation
@@ -16971,6 +17241,7 @@ module Aws::Glue
16971
17241
  # @return [Array<Types::Statement>]
16972
17242
  #
16973
17243
  # @!attribute [rw] next_token
17244
+ # A continuation token, if not all statements have yet been returned.
16974
17245
  # @return [String]
16975
17246
  #
16976
17247
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/ListStatementsResponse AWS API Documentation
@@ -21102,7 +21373,7 @@ module Aws::Glue
21102
21373
  # @return [Float]
21103
21374
  #
21104
21375
  # @!attribute [rw] max_capacity
21105
- # The number of AWS Glue data processing units (DPUs) that can be
21376
+ # The number of Glue data processing units (DPUs) that can be
21106
21377
  # allocated when the job runs. A DPU is a relative measure of
21107
21378
  # processing power that consists of 4 vCPUs of compute capacity and 16
21108
21379
  # GB memory.
@@ -21115,7 +21386,7 @@ module Aws::Glue
21115
21386
  #
21116
21387
  # @!attribute [rw] glue_version
21117
21388
  # The Glue version determines the versions of Apache Spark and Python
21118
- # that AWS Glue supports. The GlueVersion must be greater than 2.0.
21389
+ # that Glue supports. The GlueVersion must be greater than 2.0.
21119
21390
  # @return [String]
21120
21391
  #
21121
21392
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/Session AWS API Documentation
@@ -21149,7 +21420,7 @@ module Aws::Glue
21149
21420
  # }
21150
21421
  #
21151
21422
  # @!attribute [rw] name
21152
- # Specifies the name of the SessionCommand.Can be 'glueetl' or
21423
+ # Specifies the name of the SessionCommand. Can be 'glueetl' or
21153
21424
  # 'gluestreaming'.
21154
21425
  # @return [String]
21155
21426
  #
@@ -21735,7 +22006,7 @@ module Aws::Glue
21735
22006
  # notification_property: {
21736
22007
  # notify_delay_after: 1,
21737
22008
  # },
21738
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
22009
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
21739
22010
  # number_of_workers: 1,
21740
22011
  # }
21741
22012
  #
@@ -21754,6 +22025,11 @@ module Aws::Glue
21754
22025
  # You can specify arguments here that your own job-execution script
21755
22026
  # consumes, as well as arguments that Glue itself consumes.
21756
22027
  #
22028
+ # Job arguments may be logged. Do not pass plaintext secrets as
22029
+ # arguments. Retrieve secrets from a Glue Connection, Secrets Manager
22030
+ # or other secret management mechanism if you intend to keep them
22031
+ # within the Job.
22032
+ #
21757
22033
  # For information about how to specify and consume your own Job
21758
22034
  # arguments, see the [Calling Glue APIs in Python][1] topic in the
21759
22035
  # developer guide.
@@ -21772,7 +22048,7 @@ module Aws::Glue
21772
22048
  # This field is deprecated. Use `MaxCapacity` instead.
21773
22049
  #
21774
22050
  # The number of Glue data processing units (DPUs) to allocate to this
21775
- # JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A
22051
+ # JobRun. You can allocate a minimum of 2 DPUs; the default is 10. A
21776
22052
  # DPU is a relative measure of processing power that consists of 4
21777
22053
  # vCPUs of compute capacity and 16 GB of memory. For more information,
21778
22054
  # see the [Glue pricing page][1].
@@ -21806,7 +22082,7 @@ module Aws::Glue
21806
22082
  # 0.0625 or 1 DPU. The default is 0.0625 DPU.
21807
22083
  #
21808
22084
  # * When you specify an Apache Spark ETL job
21809
- # (`JobCommand.Name`="glueetl"), you can allocate from 2 to 100
22085
+ # (`JobCommand.Name`="glueetl"), you can allocate a minimum of 2
21810
22086
  # DPUs. The default is 10 DPUs. This job type cannot have a
21811
22087
  # fractional DPU allocation.
21812
22088
  #
@@ -21826,7 +22102,7 @@ module Aws::Glue
21826
22102
  #
21827
22103
  # @!attribute [rw] worker_type
21828
22104
  # The type of predefined worker that is allocated when a job runs.
21829
- # Accepts a value of Standard, G.1X, or G.2X.
22105
+ # Accepts a value of Standard, G.1X, G.2X, or G.025X.
21830
22106
  #
21831
22107
  # * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
21832
22108
  # of memory and a 50GB disk, and 2 executors per worker.
@@ -21836,14 +22112,17 @@ module Aws::Glue
21836
22112
  #
21837
22113
  # * For the `G.2X` worker type, each worker provides 8 vCPU, 32 GB of
21838
22114
  # memory and a 128GB disk, and 1 executor per worker.
22115
+ #
22116
+ # * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
22117
+ # vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
22118
+ # worker. We recommend this worker type for low volume streaming
22119
+ # jobs. This worker type is only available for Glue version 3.0
22120
+ # streaming jobs.
21839
22121
  # @return [String]
21840
22122
  #
21841
22123
  # @!attribute [rw] number_of_workers
21842
22124
  # The number of workers of a defined `workerType` that are allocated
21843
22125
  # when a job runs.
21844
- #
21845
- # The maximum number of workers you can define are 299 for `G.1X`, and
21846
- # 149 for `G.2X`.
21847
22126
  # @return [Integer]
21848
22127
  #
21849
22128
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/StartJobRunRequest AWS API Documentation
@@ -22346,6 +22625,8 @@ module Aws::Glue
22346
22625
  # @return [String]
22347
22626
  #
22348
22627
  # @!attribute [rw] additional_locations
22628
+ # A list of locations that point to the path where a Delta table is
22629
+ # located.
22349
22630
  # @return [Array<String>]
22350
22631
  #
22351
22632
  # @!attribute [rw] input_format
@@ -22583,6 +22864,7 @@ module Aws::Glue
22583
22864
  # @return [String]
22584
22865
  #
22585
22866
  # @!attribute [rw] version_id
22867
+ # The ID of the table version.
22586
22868
  # @return [String]
22587
22869
  #
22588
22870
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/Table AWS API Documentation
@@ -24045,7 +24327,7 @@ module Aws::Glue
24045
24327
  # @return [Types::LineageConfiguration]
24046
24328
  #
24047
24329
  # @!attribute [rw] lake_formation_configuration
24048
- # Specifies AWS Lake Formation configuration settings for the crawler.
24330
+ # Specifies Lake Formation configuration settings for the crawler.
24049
24331
  # @return [Types::LakeFormationConfiguration]
24050
24332
  #
24051
24333
  # @!attribute [rw] configuration
@@ -24397,7 +24679,7 @@ module Aws::Glue
24397
24679
  # allocated_capacity: 1,
24398
24680
  # timeout: 1,
24399
24681
  # max_capacity: 1.0,
24400
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
24682
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
24401
24683
  # number_of_workers: 1,
24402
24684
  # security_configuration: "NameString",
24403
24685
  # notification_property: {
@@ -25081,6 +25363,7 @@ module Aws::Glue
25081
25363
  #
25082
25364
  # @!attribute [rw] job_update
25083
25365
  # Specifies the values with which to update the job definition.
25366
+ # Unspecified configuration is removed or reset to default values.
25084
25367
  # @return [Types::JobUpdate]
25085
25368
  #
25086
25369
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/UpdateJobRequest AWS API Documentation
@@ -25156,7 +25439,7 @@ module Aws::Glue
25156
25439
  # role: "RoleString",
25157
25440
  # glue_version: "GlueVersionString",
25158
25441
  # max_capacity: 1.0,
25159
- # worker_type: "Standard", # accepts Standard, G.1X, G.2X
25442
+ # worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
25160
25443
  # number_of_workers: 1,
25161
25444
  # timeout: 1,
25162
25445
  # max_retries: 1,
@@ -25626,6 +25909,7 @@ module Aws::Glue
25626
25909
  # @return [String]
25627
25910
  #
25628
25911
  # @!attribute [rw] version_id
25912
+ # The version ID at which to update the table contents.
25629
25913
  # @return [String]
25630
25914
  #
25631
25915
  # @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/UpdateTableRequest AWS API Documentation