Access to a resource was denied.
+ * + * @throws {@link EntityNotFoundException} (client fault) + *A specified entity does not exist
+ * * @throws {@link InternalServiceException} (server fault) *An internal service error occurred.
* + * @throws {@link InvalidInputException} (client fault) + *The input provided was not valid.
+ * + * @throws {@link ThrottlingException} (client fault) + *The throttling threshhold was exceeded.
+ * * @throws {@link GlueServiceException} *Base exception class for all service exceptions from Glue service.
* diff --git a/clients/client-glue/src/commands/CancelDataQualityRulesetEvaluationRunCommand.ts b/clients/client-glue/src/commands/CancelDataQualityRulesetEvaluationRunCommand.ts index 59f8d13e5fa4..8854742b428d 100644 --- a/clients/client-glue/src/commands/CancelDataQualityRulesetEvaluationRunCommand.ts +++ b/clients/client-glue/src/commands/CancelDataQualityRulesetEvaluationRunCommand.ts @@ -9,7 +9,7 @@ import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from import { CancelDataQualityRulesetEvaluationRunRequest, CancelDataQualityRulesetEvaluationRunResponse, -} from "../models/models_0"; +} from "../models/models_1"; import { de_CancelDataQualityRulesetEvaluationRunCommand, se_CancelDataQualityRulesetEvaluationRunCommand, diff --git a/clients/client-glue/src/commands/CancelMLTaskRunCommand.ts b/clients/client-glue/src/commands/CancelMLTaskRunCommand.ts index f4bbe1000aa5..656053db9708 100644 --- a/clients/client-glue/src/commands/CancelMLTaskRunCommand.ts +++ b/clients/client-glue/src/commands/CancelMLTaskRunCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { CancelMLTaskRunRequest, CancelMLTaskRunResponse } from "../models/models_0"; +import { CancelMLTaskRunRequest, CancelMLTaskRunResponse } from "../models/models_1"; import { de_CancelMLTaskRunCommand, se_CancelMLTaskRunCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/CancelStatementCommand.ts b/clients/client-glue/src/commands/CancelStatementCommand.ts index 38652f66ac98..3bd9570e16ff 100644 --- a/clients/client-glue/src/commands/CancelStatementCommand.ts +++ b/clients/client-glue/src/commands/CancelStatementCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { CancelStatementRequest, CancelStatementResponse } from "../models/models_0"; +import { CancelStatementRequest, CancelStatementResponse } from "../models/models_1"; import { de_CancelStatementCommand, se_CancelStatementCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/CheckSchemaVersionValidityCommand.ts b/clients/client-glue/src/commands/CheckSchemaVersionValidityCommand.ts index f64671179e0f..4f1e2c7b8dd5 100644 --- a/clients/client-glue/src/commands/CheckSchemaVersionValidityCommand.ts +++ b/clients/client-glue/src/commands/CheckSchemaVersionValidityCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { CheckSchemaVersionValidityInput, CheckSchemaVersionValidityResponse } from "../models/models_0"; +import { CheckSchemaVersionValidityInput, CheckSchemaVersionValidityResponse } from "../models/models_1"; import { de_CheckSchemaVersionValidityCommand, se_CheckSchemaVersionValidityCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/CreateTableOptimizerCommand.ts b/clients/client-glue/src/commands/CreateTableOptimizerCommand.ts index 94cbe0f00851..5f9dd8ad981e 100644 --- a/clients/client-glue/src/commands/CreateTableOptimizerCommand.ts +++ b/clients/client-glue/src/commands/CreateTableOptimizerCommand.ts @@ -39,10 +39,23 @@ export interface CreateTableOptimizerCommandOutput extends CreateTableOptimizerR * CatalogId: "STRING_VALUE", // required * DatabaseName: "STRING_VALUE", // required * TableName: "STRING_VALUE", // required - * Type: "compaction", // required + * Type: "compaction" || "retention" || "orphan_file_deletion", // required * TableOptimizerConfiguration: { // TableOptimizerConfiguration * roleArn: "STRING_VALUE", * enabled: true || false, + * retentionConfiguration: { // RetentionConfiguration + * icebergConfiguration: { // IcebergRetentionConfiguration + * snapshotRetentionPeriodInDays: Number("int"), + * numberOfSnapshotsToRetain: Number("int"), + * cleanExpiredFiles: true || false, + * }, + * }, + * orphanFileDeletionConfiguration: { // OrphanFileDeletionConfiguration + * icebergConfiguration: { // IcebergOrphanFileDeletionConfiguration + * orphanFileRetentionPeriodInDays: Number("int"), + * location: "STRING_VALUE", + * }, + * }, * }, * }; * const command = new CreateTableOptimizerCommand(input); @@ -72,6 +85,12 @@ export interface CreateTableOptimizerCommandOutput extends CreateTableOptimizerR * @throws {@link InvalidInputException} (client fault) *The input provided was not valid.
* + * @throws {@link ThrottlingException} (client fault) + *The throttling threshhold was exceeded.
+ * + * @throws {@link ValidationException} (client fault) + *A value could not be validated.
+ * * @throws {@link GlueServiceException} *Base exception class for all service exceptions from Glue service.
* diff --git a/clients/client-glue/src/commands/DeleteTableOptimizerCommand.ts b/clients/client-glue/src/commands/DeleteTableOptimizerCommand.ts index a26864c39947..458183890a9b 100644 --- a/clients/client-glue/src/commands/DeleteTableOptimizerCommand.ts +++ b/clients/client-glue/src/commands/DeleteTableOptimizerCommand.ts @@ -39,7 +39,7 @@ export interface DeleteTableOptimizerCommandOutput extends DeleteTableOptimizerR * CatalogId: "STRING_VALUE", // required * DatabaseName: "STRING_VALUE", // required * TableName: "STRING_VALUE", // required - * Type: "compaction", // required + * Type: "compaction" || "retention" || "orphan_file_deletion", // required * }; * const command = new DeleteTableOptimizerCommand(input); * const response = await client.send(command); @@ -65,6 +65,9 @@ export interface DeleteTableOptimizerCommandOutput extends DeleteTableOptimizerR * @throws {@link InvalidInputException} (client fault) *The input provided was not valid.
* + * @throws {@link ThrottlingException} (client fault) + *The throttling threshhold was exceeded.
+ * * @throws {@link GlueServiceException} *Base exception class for all service exceptions from Glue service.
* diff --git a/clients/client-glue/src/commands/GetMLTransformCommand.ts b/clients/client-glue/src/commands/GetMLTransformCommand.ts index 9f6e32872200..0d33daf40f20 100644 --- a/clients/client-glue/src/commands/GetMLTransformCommand.ts +++ b/clients/client-glue/src/commands/GetMLTransformCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { GetMLTransformRequest, GetMLTransformResponse } from "../models/models_1"; +import { GetMLTransformRequest, GetMLTransformResponse } from "../models/models_2"; import { de_GetMLTransformCommand, se_GetMLTransformCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/GetTableOptimizerCommand.ts b/clients/client-glue/src/commands/GetTableOptimizerCommand.ts index c111009da3c9..5627d2226840 100644 --- a/clients/client-glue/src/commands/GetTableOptimizerCommand.ts +++ b/clients/client-glue/src/commands/GetTableOptimizerCommand.ts @@ -39,7 +39,7 @@ export interface GetTableOptimizerCommandOutput extends GetTableOptimizerRespons * CatalogId: "STRING_VALUE", // required * DatabaseName: "STRING_VALUE", // required * TableName: "STRING_VALUE", // required - * Type: "compaction", // required + * Type: "compaction" || "retention" || "orphan_file_deletion", // required * }; * const command = new GetTableOptimizerCommand(input); * const response = await client.send(command); @@ -48,10 +48,23 @@ export interface GetTableOptimizerCommandOutput extends GetTableOptimizerRespons * // DatabaseName: "STRING_VALUE", * // TableName: "STRING_VALUE", * // TableOptimizer: { // TableOptimizer - * // type: "compaction", + * // type: "compaction" || "retention" || "orphan_file_deletion", * // configuration: { // TableOptimizerConfiguration * // roleArn: "STRING_VALUE", * // enabled: true || false, + * // retentionConfiguration: { // RetentionConfiguration + * // icebergConfiguration: { // IcebergRetentionConfiguration + * // snapshotRetentionPeriodInDays: Number("int"), + * // numberOfSnapshotsToRetain: Number("int"), + * // cleanExpiredFiles: true || false, + * // }, + * // }, + * // orphanFileDeletionConfiguration: { // OrphanFileDeletionConfiguration + * // icebergConfiguration: { // IcebergOrphanFileDeletionConfiguration + * // orphanFileRetentionPeriodInDays: Number("int"), + * // location: "STRING_VALUE", + * // }, + * // }, * // }, * // lastRun: { // TableOptimizerRun * // eventType: "starting" || "completed" || "failed" || "in_progress", @@ -64,6 +77,30 @@ export interface GetTableOptimizerCommandOutput extends GetTableOptimizerRespons * // JobDurationInHour: "STRING_VALUE", * // }, * // error: "STRING_VALUE", + * // compactionMetrics: { // CompactionMetrics + * // IcebergMetrics: { // IcebergCompactionMetrics + * // NumberOfBytesCompacted: Number("long"), + * // NumberOfFilesCompacted: Number("long"), + * // NumberOfDpus: Number("int"), + * // JobDurationInHour: Number("double"), + * // }, + * // }, + * // retentionMetrics: { // RetentionMetrics + * // IcebergMetrics: { // IcebergRetentionMetrics + * // NumberOfDataFilesDeleted: Number("long"), + * // NumberOfManifestFilesDeleted: Number("long"), + * // NumberOfManifestListsDeleted: Number("long"), + * // NumberOfDpus: Number("int"), + * // JobDurationInHour: Number("double"), + * // }, + * // }, + * // orphanFileDeletionMetrics: { // OrphanFileDeletionMetrics + * // IcebergMetrics: { // IcebergOrphanFileDeletionMetrics + * // NumberOfOrphanFilesDeleted: Number("long"), + * // NumberOfDpus: Number("int"), + * // JobDurationInHour: Number("double"), + * // }, + * // }, * // }, * // }, * // }; @@ -88,6 +125,9 @@ export interface GetTableOptimizerCommandOutput extends GetTableOptimizerRespons * @throws {@link InvalidInputException} (client fault) *The input provided was not valid.
* + * @throws {@link ThrottlingException} (client fault) + *The throttling threshhold was exceeded.
+ * * @throws {@link GlueServiceException} *Base exception class for all service exceptions from Glue service.
* diff --git a/clients/client-glue/src/commands/ListTableOptimizerRunsCommand.ts b/clients/client-glue/src/commands/ListTableOptimizerRunsCommand.ts index 1824d11408de..dff2f252642d 100644 --- a/clients/client-glue/src/commands/ListTableOptimizerRunsCommand.ts +++ b/clients/client-glue/src/commands/ListTableOptimizerRunsCommand.ts @@ -39,7 +39,7 @@ export interface ListTableOptimizerRunsCommandOutput extends ListTableOptimizerR * CatalogId: "STRING_VALUE", // required * DatabaseName: "STRING_VALUE", // required * TableName: "STRING_VALUE", // required - * Type: "compaction", // required + * Type: "compaction" || "retention" || "orphan_file_deletion", // required * MaxResults: Number("int"), * NextToken: "STRING_VALUE", * }; @@ -62,6 +62,30 @@ export interface ListTableOptimizerRunsCommandOutput extends ListTableOptimizerR * // JobDurationInHour: "STRING_VALUE", * // }, * // error: "STRING_VALUE", + * // compactionMetrics: { // CompactionMetrics + * // IcebergMetrics: { // IcebergCompactionMetrics + * // NumberOfBytesCompacted: Number("long"), + * // NumberOfFilesCompacted: Number("long"), + * // NumberOfDpus: Number("int"), + * // JobDurationInHour: Number("double"), + * // }, + * // }, + * // retentionMetrics: { // RetentionMetrics + * // IcebergMetrics: { // IcebergRetentionMetrics + * // NumberOfDataFilesDeleted: Number("long"), + * // NumberOfManifestFilesDeleted: Number("long"), + * // NumberOfManifestListsDeleted: Number("long"), + * // NumberOfDpus: Number("int"), + * // JobDurationInHour: Number("double"), + * // }, + * // }, + * // orphanFileDeletionMetrics: { // OrphanFileDeletionMetrics + * // IcebergMetrics: { // IcebergOrphanFileDeletionMetrics + * // NumberOfOrphanFilesDeleted: Number("long"), + * // NumberOfDpus: Number("int"), + * // JobDurationInHour: Number("double"), + * // }, + * // }, * // }, * // ], * // }; @@ -86,6 +110,12 @@ export interface ListTableOptimizerRunsCommandOutput extends ListTableOptimizerR * @throws {@link InvalidInputException} (client fault) *The input provided was not valid.
* + * @throws {@link ThrottlingException} (client fault) + *The throttling threshhold was exceeded.
+ * + * @throws {@link ValidationException} (client fault) + *A value could not be validated.
+ * * @throws {@link GlueServiceException} *Base exception class for all service exceptions from Glue service.
* diff --git a/clients/client-glue/src/commands/UpdateTableCommand.ts b/clients/client-glue/src/commands/UpdateTableCommand.ts index 4fafaef53fa8..59f9b6340a4f 100644 --- a/clients/client-glue/src/commands/UpdateTableCommand.ts +++ b/clients/client-glue/src/commands/UpdateTableCommand.ts @@ -6,7 +6,8 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { UpdateTableRequest, UpdateTableResponse } from "../models/models_2"; +import { UpdateTableRequest } from "../models/models_2"; +import { UpdateTableResponse } from "../models/models_3"; import { de_UpdateTableCommand, se_UpdateTableCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/UpdateTableOptimizerCommand.ts b/clients/client-glue/src/commands/UpdateTableOptimizerCommand.ts index 81a6f023fbb7..5362ef5c01e1 100644 --- a/clients/client-glue/src/commands/UpdateTableOptimizerCommand.ts +++ b/clients/client-glue/src/commands/UpdateTableOptimizerCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { UpdateTableOptimizerRequest, UpdateTableOptimizerResponse } from "../models/models_2"; +import { UpdateTableOptimizerRequest, UpdateTableOptimizerResponse } from "../models/models_3"; import { de_UpdateTableOptimizerCommand, se_UpdateTableOptimizerCommand } from "../protocols/Aws_json1_1"; /** @@ -39,10 +39,23 @@ export interface UpdateTableOptimizerCommandOutput extends UpdateTableOptimizerR * CatalogId: "STRING_VALUE", // required * DatabaseName: "STRING_VALUE", // required * TableName: "STRING_VALUE", // required - * Type: "compaction", // required + * Type: "compaction" || "retention" || "orphan_file_deletion", // required * TableOptimizerConfiguration: { // TableOptimizerConfiguration * roleArn: "STRING_VALUE", * enabled: true || false, + * retentionConfiguration: { // RetentionConfiguration + * icebergConfiguration: { // IcebergRetentionConfiguration + * snapshotRetentionPeriodInDays: Number("int"), + * numberOfSnapshotsToRetain: Number("int"), + * cleanExpiredFiles: true || false, + * }, + * }, + * orphanFileDeletionConfiguration: { // OrphanFileDeletionConfiguration + * icebergConfiguration: { // IcebergOrphanFileDeletionConfiguration + * orphanFileRetentionPeriodInDays: Number("int"), + * location: "STRING_VALUE", + * }, + * }, * }, * }; * const command = new UpdateTableOptimizerCommand(input); @@ -60,6 +73,9 @@ export interface UpdateTableOptimizerCommandOutput extends UpdateTableOptimizerR * @throws {@link AccessDeniedException} (client fault) *Access to a resource was denied.
* + * @throws {@link ConcurrentModificationException} (client fault) + *Two processes are trying to modify a resource simultaneously.
+ * * @throws {@link EntityNotFoundException} (client fault) *A specified entity does not exist
* @@ -69,6 +85,12 @@ export interface UpdateTableOptimizerCommandOutput extends UpdateTableOptimizerR * @throws {@link InvalidInputException} (client fault) *The input provided was not valid.
* + * @throws {@link ThrottlingException} (client fault) + *The throttling threshhold was exceeded.
+ * + * @throws {@link ValidationException} (client fault) + *A value could not be validated.
+ * * @throws {@link GlueServiceException} *Base exception class for all service exceptions from Glue service.
* diff --git a/clients/client-glue/src/commands/UpdateTriggerCommand.ts b/clients/client-glue/src/commands/UpdateTriggerCommand.ts index 309f6a7b0535..0fd6e9957c7f 100644 --- a/clients/client-glue/src/commands/UpdateTriggerCommand.ts +++ b/clients/client-glue/src/commands/UpdateTriggerCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { UpdateTriggerRequest, UpdateTriggerResponse } from "../models/models_2"; +import { UpdateTriggerRequest, UpdateTriggerResponse } from "../models/models_3"; import { de_UpdateTriggerCommand, se_UpdateTriggerCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/UpdateUsageProfileCommand.ts b/clients/client-glue/src/commands/UpdateUsageProfileCommand.ts index 3659d87e4f18..00de00ba382e 100644 --- a/clients/client-glue/src/commands/UpdateUsageProfileCommand.ts +++ b/clients/client-glue/src/commands/UpdateUsageProfileCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { UpdateUsageProfileRequest, UpdateUsageProfileResponse } from "../models/models_2"; +import { UpdateUsageProfileRequest, UpdateUsageProfileResponse } from "../models/models_3"; import { de_UpdateUsageProfileCommand, se_UpdateUsageProfileCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/UpdateUserDefinedFunctionCommand.ts b/clients/client-glue/src/commands/UpdateUserDefinedFunctionCommand.ts index 98d30f35ffd0..3dcd1ff77829 100644 --- a/clients/client-glue/src/commands/UpdateUserDefinedFunctionCommand.ts +++ b/clients/client-glue/src/commands/UpdateUserDefinedFunctionCommand.ts @@ -6,7 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { UpdateUserDefinedFunctionRequest, UpdateUserDefinedFunctionResponse } from "../models/models_2"; +import { UpdateUserDefinedFunctionRequest, UpdateUserDefinedFunctionResponse } from "../models/models_3"; import { de_UpdateUserDefinedFunctionCommand, se_UpdateUserDefinedFunctionCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/commands/UpdateWorkflowCommand.ts b/clients/client-glue/src/commands/UpdateWorkflowCommand.ts index 5aa7e586e7c5..9d3299f459c0 100644 --- a/clients/client-glue/src/commands/UpdateWorkflowCommand.ts +++ b/clients/client-glue/src/commands/UpdateWorkflowCommand.ts @@ -6,8 +6,7 @@ import { MetadataBearer as __MetadataBearer } from "@smithy/types"; import { commonParams } from "../endpoint/EndpointParameters"; import { GlueClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../GlueClient"; -import { UpdateWorkflowRequest } from "../models/models_2"; -import { UpdateWorkflowResponse } from "../models/models_3"; +import { UpdateWorkflowRequest, UpdateWorkflowResponse } from "../models/models_3"; import { de_UpdateWorkflowCommand, se_UpdateWorkflowCommand } from "../protocols/Aws_json1_1"; /** diff --git a/clients/client-glue/src/models/models_0.ts b/clients/client-glue/src/models/models_0.ts index 67d29098d1b3..62fa15fcc07a 100644 --- a/clients/client-glue/src/models/models_0.ts +++ b/clients/client-glue/src/models/models_0.ts @@ -7466,6 +7466,8 @@ export class InvalidStateException extends __BaseException { */ export const TableOptimizerType = { COMPACTION: "compaction", + ORPHAN_FILE_DELETION: "orphan_file_deletion", + RETENTION: "retention", } as const; /** @@ -7550,6 +7552,72 @@ export interface BatchGetTableOptimizerError { type?: TableOptimizerType; } +/** + *The configuration for an Iceberg orphan file deletion optimizer.
+ * @public + */ +export interface IcebergOrphanFileDeletionConfiguration { + /** + *The number of days that orphan files should be retained before file deletion. If an input is not provided, the default value 3 will be used.
+ * @public + */ + orphanFileRetentionPeriodInDays?: number; + + /** + *Specifies a directory in which to look for files (defaults to the table's location). You may choose a sub-directory rather than the top-level table location.
+ * @public + */ + location?: string; +} + +/** + *The configuration for an orphan file deletion optimizer.
+ * @public + */ +export interface OrphanFileDeletionConfiguration { + /** + *The configuration for an Iceberg orphan file deletion optimizer.
+ * @public + */ + icebergConfiguration?: IcebergOrphanFileDeletionConfiguration; +} + +/** + *The configuration for an Iceberg snapshot retention optimizer.
+ * @public + */ +export interface IcebergRetentionConfiguration { + /** + *The number of days to retain the Iceberg snapshots. If an input is not provided, the corresponding Iceberg table configuration field will be used or if not present, the default value 5 will be used.
+ * @public + */ + snapshotRetentionPeriodInDays?: number; + + /** + *The number of Iceberg snapshots to retain within the retention period. If an input is not provided, the corresponding Iceberg table configuration field will be used or if not present, the default value 1 will be used.
+ * @public + */ + numberOfSnapshotsToRetain?: number; + + /** + *If set to false, snapshots are only deleted from table metadata, and the underlying data and metadata files are not deleted.
+ * @public + */ + cleanExpiredFiles?: boolean; +} + +/** + *The configuration for a snapshot retention optimizer.
+ * @public + */ +export interface RetentionConfiguration { + /** + *The configuration for an Iceberg snapshot retention optimizer.
+ * @public + */ + icebergConfiguration?: IcebergRetentionConfiguration; +} + /** *Contains details on the configuration of a table optimizer. You pass this configuration when creating or updating a table optimizer.
* @public @@ -7562,10 +7630,64 @@ export interface TableOptimizerConfiguration { roleArn?: string; /** - *Whether table optimization is enabled.
+ *Whether table optimization is enabled.
* @public */ enabled?: boolean; + + /** + *The configuration for a snapshot retention optimizer.
+ * @public + */ + retentionConfiguration?: RetentionConfiguration; + + /** + *The configuration for an orphan file deletion optimizer.
+ * @public + */ + orphanFileDeletionConfiguration?: OrphanFileDeletionConfiguration; +} + +/** + *Compaction metrics for Iceberg for the optimizer run.
+ * @public + */ +export interface IcebergCompactionMetrics { + /** + *The number of bytes removed by the compaction job run.
+ * @public + */ + NumberOfBytesCompacted?: number; + + /** + *The number of files removed by the compaction job run.
+ * @public + */ + NumberOfFilesCompacted?: number; + + /** + *The number of DPU hours consumed by the job.
+ * @public + */ + NumberOfDpus?: number; + + /** + *The duration of the job in hours.
+ * @public + */ + JobDurationInHour?: number; +} + +/** + *A structure that contains compaction metrics for the optimizer run.
+ * @public + */ +export interface CompactionMetrics { + /** + *A structure containing the Iceberg compaction metrics for the optimizer run.
+ * @public + */ + IcebergMetrics?: IcebergCompactionMetrics; } /** @@ -7586,6 +7708,7 @@ export type TableOptimizerEventType = (typeof TableOptimizerEventType)[keyof typ /** *Metrics for the optimizer run.
+ *This structure is deprecated. See the individual metric members for compaction, retention, and orphan file deletion.
* @public */ export interface RunMetrics { @@ -7614,6 +7737,90 @@ export interface RunMetrics { JobDurationInHour?: string; } +/** + *Orphan file deletion metrics for Iceberg for the optimizer run.
+ * @public + */ +export interface IcebergOrphanFileDeletionMetrics { + /** + *The number of orphan files deleted by the orphan file deletion job run.
+ * @public + */ + NumberOfOrphanFilesDeleted?: number; + + /** + *The number of DPU hours consumed by the job.
+ * @public + */ + NumberOfDpus?: number; + + /** + *The duration of the job in hours.
+ * @public + */ + JobDurationInHour?: number; +} + +/** + *A structure that contains orphan file deletion metrics for the optimizer run.
+ * @public + */ +export interface OrphanFileDeletionMetrics { + /** + *A structure containing the Iceberg orphan file deletion metrics for the optimizer run.
+ * @public + */ + IcebergMetrics?: IcebergOrphanFileDeletionMetrics; +} + +/** + *Snapshot retention metrics for Iceberg for the optimizer run.
+ * @public + */ +export interface IcebergRetentionMetrics { + /** + *The number of data files deleted by the retention job run.
+ * @public + */ + NumberOfDataFilesDeleted?: number; + + /** + *The number of manifest files deleted by the retention job run.
+ * @public + */ + NumberOfManifestFilesDeleted?: number; + + /** + *The number of manifest lists deleted by the retention job run.
+ * @public + */ + NumberOfManifestListsDeleted?: number; + + /** + *The number of DPU hours consumed by the job.
+ * @public + */ + NumberOfDpus?: number; + + /** + *The duration of the job in hours.
+ * @public + */ + JobDurationInHour?: number; +} + +/** + *A structure that contains retention metrics for the optimizer run.
+ * @public + */ +export interface RetentionMetrics { + /** + *A structure containing the Iceberg retention metrics for the optimizer run.
+ * @public + */ + IcebergMetrics?: IcebergRetentionMetrics; +} + /** *Contains details for a table optimizer run.
* @public @@ -7638,7 +7845,10 @@ export interface TableOptimizerRun { endTimestamp?: Date; /** + * @deprecated + * *A RunMetrics object containing metrics for the optimizer run.
This member is deprecated. See the individual metric members for compaction, retention, and orphan file deletion.
* @public */ metrics?: RunMetrics; @@ -7648,6 +7858,24 @@ export interface TableOptimizerRun { * @public */ error?: string; + + /** + *A CompactionMetrics object containing metrics for the optimizer run.
A RetentionMetrics object containing metrics for the optimizer run.
An OrphanFileDeletionMetrics object containing metrics for the optimizer run.
The type of table optimizer. Currently, the only valid value is compaction.
The type of table optimizer. The valid values are:
+ *
+ * compaction: for managing compaction with a table optimizer.
+ * retention: for managing the retention of snapshot with a table optimizer.
+ * orphan_file_deletion: for managing the deletion of orphan files with a table optimizer.
A TableOptimizer object that contains details on the configuration and last run of a table optimzer.
A TableOptimizer object that contains details on the configuration and last run of a table optimizer.
The throttling threshhold was exceeded.
+ * @public + */ +export class ThrottlingException extends __BaseException { + readonly name: "ThrottlingException" = "ThrottlingException"; + readonly $fault: "client" = "client"; + /** + *A message describing the problem.
+ * @public + */ + Message?: string; + /** + * @internal + */ + constructor(opts: __ExceptionOptionTypeThe unique run identifier associated with this run.
- * @public - */ - RunId: string | undefined; -} - -/** - * @public - */ -export interface CancelDataQualityRulesetEvaluationRunResponse {} - -/** - * @public - */ -export interface CancelMLTaskRunRequest { - /** - *The unique identifier of the machine learning transform.
- * @public - */ - TransformId: string | undefined; - - /** - *A unique identifier for the task run.
- * @public - */ - TaskRunId: string | undefined; -} - -/** - * @public - * @enum - */ -export const TaskStatusType = { - FAILED: "FAILED", - RUNNING: "RUNNING", - STARTING: "STARTING", - STOPPED: "STOPPED", - STOPPING: "STOPPING", - SUCCEEDED: "SUCCEEDED", - TIMEOUT: "TIMEOUT", -} as const; - -/** - * @public - */ -export type TaskStatusType = (typeof TaskStatusType)[keyof typeof TaskStatusType]; - -/** - * @public - */ -export interface CancelMLTaskRunResponse { - /** - *The unique identifier of the machine learning transform.
- * @public - */ - TransformId?: string; - - /** - *The unique identifier for the task run.
- * @public - */ - TaskRunId?: string; - - /** - *The status for this run.
- * @public - */ - Status?: TaskStatusType; -} - -/** - * @public - */ -export interface CancelStatementRequest { - /** - *The Session ID of the statement to be cancelled.
- * @public - */ - SessionId: string | undefined; - - /** - *The ID of the statement to be cancelled.
- * @public - */ - Id: number | undefined; - - /** - *The origin of the request to cancel the statement.
- * @public - */ - RequestOrigin?: string; -} - -/** - * @public - */ -export interface CancelStatementResponse {} - -/** - *The session is in an invalid state to perform a requested operation.
- * @public - */ -export class IllegalSessionStateException extends __BaseException { - readonly name: "IllegalSessionStateException" = "IllegalSessionStateException"; - readonly $fault: "client" = "client"; - /** - *A message describing the problem.
- * @public - */ - Message?: string; - /** - * @internal - */ - constructor(opts: __ExceptionOptionTypeThe data format of the schema definition. Currently AVRO, JSON and PROTOBUF are supported.
The definition of the schema that has to be validated.
- * @public - */ - SchemaDefinition: string | undefined; -} - -/** - * @public - */ -export interface CheckSchemaVersionValidityResponse { - /** - *Return true, if the schema is valid and false otherwise.
- * @public - */ - Valid?: boolean; - - /** - *A validation failure error message.
- * @public - */ - Error?: string; -} - /** * @internal */ diff --git a/clients/client-glue/src/models/models_1.ts b/clients/client-glue/src/models/models_1.ts index 8d8fcbfbeca8..df56b64da288 100644 --- a/clients/client-glue/src/models/models_1.ts +++ b/clients/client-glue/src/models/models_1.ts @@ -12,7 +12,6 @@ import { ConnectionsList, Crawler, CrawlerTargets, - DataFormat, DataQualityAnalyzerResult, DataQualityAnalyzerResultFilterSensitiveLog, DataQualityObservation, @@ -36,11 +35,188 @@ import { StorageDescriptor, TableOptimizerConfiguration, TableOptimizerType, - TaskStatusType, TriggerType, WorkerType, } from "./models_0"; +/** + * @public + */ +export interface CancelDataQualityRulesetEvaluationRunRequest { + /** + *The unique run identifier associated with this run.
+ * @public + */ + RunId: string | undefined; +} + +/** + * @public + */ +export interface CancelDataQualityRulesetEvaluationRunResponse {} + +/** + * @public + */ +export interface CancelMLTaskRunRequest { + /** + *The unique identifier of the machine learning transform.
+ * @public + */ + TransformId: string | undefined; + + /** + *A unique identifier for the task run.
+ * @public + */ + TaskRunId: string | undefined; +} + +/** + * @public + * @enum + */ +export const TaskStatusType = { + FAILED: "FAILED", + RUNNING: "RUNNING", + STARTING: "STARTING", + STOPPED: "STOPPED", + STOPPING: "STOPPING", + SUCCEEDED: "SUCCEEDED", + TIMEOUT: "TIMEOUT", +} as const; + +/** + * @public + */ +export type TaskStatusType = (typeof TaskStatusType)[keyof typeof TaskStatusType]; + +/** + * @public + */ +export interface CancelMLTaskRunResponse { + /** + *The unique identifier of the machine learning transform.
+ * @public + */ + TransformId?: string; + + /** + *The unique identifier for the task run.
+ * @public + */ + TaskRunId?: string; + + /** + *The status for this run.
+ * @public + */ + Status?: TaskStatusType; +} + +/** + * @public + */ +export interface CancelStatementRequest { + /** + *The Session ID of the statement to be cancelled.
+ * @public + */ + SessionId: string | undefined; + + /** + *The ID of the statement to be cancelled.
+ * @public + */ + Id: number | undefined; + + /** + *The origin of the request to cancel the statement.
+ * @public + */ + RequestOrigin?: string; +} + +/** + * @public + */ +export interface CancelStatementResponse {} + +/** + *The session is in an invalid state to perform a requested operation.
+ * @public + */ +export class IllegalSessionStateException extends __BaseException { + readonly name: "IllegalSessionStateException" = "IllegalSessionStateException"; + readonly $fault: "client" = "client"; + /** + *A message describing the problem.
+ * @public + */ + Message?: string; + /** + * @internal + */ + constructor(opts: __ExceptionOptionTypeThe data format of the schema definition. Currently AVRO, JSON and PROTOBUF are supported.
The definition of the schema that has to be validated.
+ * @public + */ + SchemaDefinition: string | undefined; +} + +/** + * @public + */ +export interface CheckSchemaVersionValidityResponse { + /** + *Return true, if the schema is valid and false otherwise.
+ * @public + */ + Valid?: boolean; + + /** + *A validation failure error message.
+ * @public + */ + Error?: string; +} + /** * @public */ @@ -7661,414 +7837,6 @@ export interface GetMLTaskRunsResponse { NextToken?: string; } -/** - * @public - */ -export interface GetMLTransformRequest { - /** - *The unique identifier of the transform, generated at the time that the transform was - * created.
- * @public - */ - TransformId: string | undefined; -} - -/** - *A structure containing the column name and column importance score for a column.
- *Column importance helps you understand how columns contribute to your model, by identifying which columns in your records are more important than others.
- * @public - */ -export interface ColumnImportance { - /** - *The name of a column.
- * @public - */ - ColumnName?: string; - - /** - *The column importance score for the column, as a decimal.
- * @public - */ - Importance?: number; -} - -/** - *The confusion matrix shows you what your transform is predicting accurately and what types of errors it is making.
- *For more information, see Confusion matrix in Wikipedia.
- * @public - */ -export interface ConfusionMatrix { - /** - *The number of matches in the data that the transform correctly found, in the confusion matrix for your transform.
- * @public - */ - NumTruePositives?: number; - - /** - *The number of nonmatches in the data that the transform incorrectly classified as a match, - * in the confusion matrix for your transform.
- * @public - */ - NumFalsePositives?: number; - - /** - *The number of nonmatches in the data that the transform correctly rejected, in the - * confusion matrix for your transform.
- * @public - */ - NumTrueNegatives?: number; - - /** - *The number of matches in the data that the transform didn't find, in the confusion matrix for your transform.
- * @public - */ - NumFalseNegatives?: number; -} - -/** - *The evaluation metrics for the find matches algorithm. The quality of your machine - * learning transform is measured by getting your transform to predict some matches and comparing - * the results to known matches from the same dataset. The quality metrics are based on a subset - * of your data, so they are not precise.
- * @public - */ -export interface FindMatchesMetrics { - /** - *The area under the precision/recall curve (AUPRC) is a single number measuring the overall - * quality of the transform, that is independent of the choice made for precision vs. recall. - * Higher values indicate that you have a more attractive precision vs. recall tradeoff.
- *For more information, see Precision and recall in Wikipedia.
- * @public - */ - AreaUnderPRCurve?: number; - - /** - *The precision metric indicates when often your transform is correct when it predicts a match. Specifically, it measures how well the transform finds true positives from the total true positives possible.
- *For more information, see Precision and recall in Wikipedia.
- * @public - */ - Precision?: number; - - /** - *The recall metric indicates that for an actual match, how often your transform predicts - * the match. Specifically, it measures how well the transform finds true positives from the - * total records in the source data.
- *For more information, see Precision and recall in Wikipedia.
- * @public - */ - Recall?: number; - - /** - *The maximum F1 metric indicates the transform's accuracy between 0 and 1, where 1 is the best accuracy.
- *For more information, see F1 score in Wikipedia.
- * @public - */ - F1?: number; - - /** - *The confusion matrix shows you what your transform is predicting accurately and what types of errors it is making.
- *For more information, see Confusion matrix in Wikipedia.
- * @public - */ - ConfusionMatrix?: ConfusionMatrix; - - /** - *A list of ColumnImportance structures containing column importance metrics, sorted in order of descending importance.
Evaluation metrics provide an estimate of the quality of your machine learning transform.
- * @public - */ -export interface EvaluationMetrics { - /** - *The type of machine learning transform.
- * @public - */ - TransformType: TransformType | undefined; - - /** - *The evaluation metrics for the find matches algorithm.
- * @public - */ - FindMatchesMetrics?: FindMatchesMetrics; -} - -/** - *A key-value pair representing a column and data type that this transform can
- * run against. The Schema parameter of the MLTransform may contain up to 100 of these structures.
The name of the column.
- * @public - */ - Name?: string; - - /** - *The type of data in the column.
- * @public - */ - DataType?: string; -} - -/** - * @public - * @enum - */ -export const TransformStatusType = { - DELETING: "DELETING", - NOT_READY: "NOT_READY", - READY: "READY", -} as const; - -/** - * @public - */ -export type TransformStatusType = (typeof TransformStatusType)[keyof typeof TransformStatusType]; - -/** - * @public - */ -export interface GetMLTransformResponse { - /** - *The unique identifier of the transform, generated at the time that the transform was - * created.
- * @public - */ - TransformId?: string; - - /** - *The unique name given to the transform when it was created.
- * @public - */ - Name?: string; - - /** - *A description of the transform.
- * @public - */ - Description?: string; - - /** - *The last known status of the transform (to indicate whether it can be used or not). One of "NOT_READY", "READY", or "DELETING".
- * @public - */ - Status?: TransformStatusType; - - /** - *The date and time when the transform was created.
- * @public - */ - CreatedOn?: Date; - - /** - *The date and time when the transform was last modified.
- * @public - */ - LastModifiedOn?: Date; - - /** - *A list of Glue table definitions used by the transform.
- * @public - */ - InputRecordTables?: GlueTable[]; - - /** - *The configuration parameters that are specific to the algorithm used.
- * @public - */ - Parameters?: TransformParameters; - - /** - *The latest evaluation metrics.
- * @public - */ - EvaluationMetrics?: EvaluationMetrics; - - /** - *The number of labels available for this transform.
- * @public - */ - LabelCount?: number; - - /** - *The Map object that represents the schema that this
- * transform accepts. Has an upper bound of 100 columns.
The name or Amazon Resource Name (ARN) of the IAM role with the required - * permissions.
- * @public - */ - Role?: string; - - /** - *This value determines which version of Glue this machine learning transform is compatible with. Glue 1.0 is recommended for most customers. If the value is not set, the Glue compatibility defaults to Glue 0.9. For more information, see Glue Versions in the developer guide.
- * @public - */ - GlueVersion?: string; - - /** - *The number of Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. A DPU is a relative measure of - * processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more - * information, see the Glue pricing - * page.
- *When the WorkerType field is set to a value other than Standard, the MaxCapacity field is set automatically and becomes read-only.
The type of predefined worker that is allocated when this task runs. Accepts a value of Standard, G.1X, or G.2X.
- *For the Standard worker type, each worker provides 4 vCPU, 16 GB of memory and a 50GB disk, and 2 executors per worker.
For the G.1X worker type, each worker provides 4 vCPU, 16 GB of memory and a 64GB disk, and 1 executor per worker.
For the G.2X worker type, each worker provides 8 vCPU, 32 GB of memory and a 128GB disk, and 1 executor per worker.
The number of workers of a defined workerType that are allocated when this task runs.
The timeout for a task run for this transform in minutes. This is the maximum time that a task run for this transform can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours).
The maximum number of times to retry a task for this transform after a task run fails.
- * @public - */ - MaxRetries?: number; - - /** - *The encryption-at-rest settings of the transform that apply to accessing user data. Machine learning transforms can access user data encrypted in Amazon S3 using KMS.
- * @public - */ - TransformEncryption?: TransformEncryption; -} - -/** - *The criteria used to filter the machine learning transforms.
- * @public - */ -export interface TransformFilterCriteria { - /** - *A unique transform name that is used to filter the machine learning transforms.
- * @public - */ - Name?: string; - - /** - *The type of machine learning transform that is used to filter the machine learning - * transforms.
- * @public - */ - TransformType?: TransformType; - - /** - *Filters the list of machine learning transforms by the last known status of the transforms (to indicate whether a transform can be used or not). One of "NOT_READY", "READY", or "DELETING".
- * @public - */ - Status?: TransformStatusType; - - /** - *This value determines which version of Glue this machine learning transform is compatible with. Glue 1.0 is recommended for most customers. If the value is not set, the Glue compatibility defaults to Glue 0.9. For more information, see Glue Versions in the developer guide.
- * @public - */ - GlueVersion?: string; - - /** - *The time and date before which the transforms were created.
- * @public - */ - CreatedBefore?: Date; - - /** - *The time and date after which the transforms were created.
- * @public - */ - CreatedAfter?: Date; - - /** - *Filter on transforms last modified before this date.
- * @public - */ - LastModifiedBefore?: Date; - - /** - *Filter on transforms last modified after this date.
- * @public - */ - LastModifiedAfter?: Date; - - /** - *Filters on datasets with a specific schema. The Map
- * object is an array of key-value pairs representing the schema this transform accepts, where
- * Column is the name of a column, and Type is the type of the data
- * such as an integer or string. Has an upper bound of 100 columns.
The sorting criteria that are associated with the machine learning transform.
- * @public - */ -export interface TransformSortCriteria { - /** - *The column to be used in the sorting criteria that are associated with the machine - * learning transform.
- * @public - */ - Column: TransformSortColumnType | undefined; - - /** - *The sort direction to be used in the sorting criteria that are associated with the machine - * learning transform.
- * @public - */ - SortDirection: SortDirectionType | undefined; -} - /** * @internal */ diff --git a/clients/client-glue/src/models/models_2.ts b/clients/client-glue/src/models/models_2.ts index 102d8821334c..60417d6b5760 100644 --- a/clients/client-glue/src/models/models_2.ts +++ b/clients/client-glue/src/models/models_2.ts @@ -4,14 +4,11 @@ import { ExceptionOptionType as __ExceptionOptionType, SENSITIVE_STRING } from " import { GlueServiceException as __BaseException } from "./GlueServiceException"; import { - Action, AuditContext, CrawlerTargets, CustomEntityType, - DataFormat, DataSource, ErrorDetail, - EventBatchingCondition, ExecutionClass, GlueTable, InclusionAnnotationValue, @@ -21,7 +18,6 @@ import { Partition, PartitionInput, PartitionValueList, - Predicate, RecrawlPolicy, SchemaChangePolicy, SchemaId, @@ -29,10 +25,8 @@ import { SourceControlProvider, StatisticAnnotation, TableOptimizer, - TableOptimizerConfiguration, TableOptimizerRun, TableOptimizerType, - TaskStatusType, TimestampedInclusionAnnotation, Trigger, WorkerType, @@ -49,10 +43,10 @@ import { CsvSerdeOption, DatabaseInput, DataCatalogEncryptionSettings, + DataFormat, DataQualityEvaluationRunAdditionalRunOptions, DataQualityTargetTable, EncryptionConfiguration, - EvaluationMetrics, JobBookmarkEntry, Language, Location, @@ -64,20 +58,426 @@ import { RegistryStatus, ResourceShareType, ResourceUri, - SchemaColumn, SchemaStatus, SchemaVersionStatus, Session, + SortDirectionType, TableInput, + TaskStatusType, TransformEncryption, - TransformFilterCriteria, TransformParameters, - TransformSortCriteria, - TransformStatusType, - UserDefinedFunctionInput, + TransformType, ViewDialect, } from "./models_1"; +/** + * @public + */ +export interface GetMLTransformRequest { + /** + *The unique identifier of the transform, generated at the time that the transform was + * created.
+ * @public + */ + TransformId: string | undefined; +} + +/** + *A structure containing the column name and column importance score for a column.
+ *Column importance helps you understand how columns contribute to your model, by identifying which columns in your records are more important than others.
+ * @public + */ +export interface ColumnImportance { + /** + *The name of a column.
+ * @public + */ + ColumnName?: string; + + /** + *The column importance score for the column, as a decimal.
+ * @public + */ + Importance?: number; +} + +/** + *The confusion matrix shows you what your transform is predicting accurately and what types of errors it is making.
+ *For more information, see Confusion matrix in Wikipedia.
+ * @public + */ +export interface ConfusionMatrix { + /** + *The number of matches in the data that the transform correctly found, in the confusion matrix for your transform.
+ * @public + */ + NumTruePositives?: number; + + /** + *The number of nonmatches in the data that the transform incorrectly classified as a match, + * in the confusion matrix for your transform.
+ * @public + */ + NumFalsePositives?: number; + + /** + *The number of nonmatches in the data that the transform correctly rejected, in the + * confusion matrix for your transform.
+ * @public + */ + NumTrueNegatives?: number; + + /** + *The number of matches in the data that the transform didn't find, in the confusion matrix for your transform.
+ * @public + */ + NumFalseNegatives?: number; +} + +/** + *The evaluation metrics for the find matches algorithm. The quality of your machine + * learning transform is measured by getting your transform to predict some matches and comparing + * the results to known matches from the same dataset. The quality metrics are based on a subset + * of your data, so they are not precise.
+ * @public + */ +export interface FindMatchesMetrics { + /** + *The area under the precision/recall curve (AUPRC) is a single number measuring the overall + * quality of the transform, that is independent of the choice made for precision vs. recall. + * Higher values indicate that you have a more attractive precision vs. recall tradeoff.
+ *For more information, see Precision and recall in Wikipedia.
+ * @public + */ + AreaUnderPRCurve?: number; + + /** + *The precision metric indicates when often your transform is correct when it predicts a match. Specifically, it measures how well the transform finds true positives from the total true positives possible.
+ *For more information, see Precision and recall in Wikipedia.
+ * @public + */ + Precision?: number; + + /** + *The recall metric indicates that for an actual match, how often your transform predicts + * the match. Specifically, it measures how well the transform finds true positives from the + * total records in the source data.
+ *For more information, see Precision and recall in Wikipedia.
+ * @public + */ + Recall?: number; + + /** + *The maximum F1 metric indicates the transform's accuracy between 0 and 1, where 1 is the best accuracy.
+ *For more information, see F1 score in Wikipedia.
+ * @public + */ + F1?: number; + + /** + *The confusion matrix shows you what your transform is predicting accurately and what types of errors it is making.
+ *For more information, see Confusion matrix in Wikipedia.
+ * @public + */ + ConfusionMatrix?: ConfusionMatrix; + + /** + *A list of ColumnImportance structures containing column importance metrics, sorted in order of descending importance.
Evaluation metrics provide an estimate of the quality of your machine learning transform.
+ * @public + */ +export interface EvaluationMetrics { + /** + *The type of machine learning transform.
+ * @public + */ + TransformType: TransformType | undefined; + + /** + *The evaluation metrics for the find matches algorithm.
+ * @public + */ + FindMatchesMetrics?: FindMatchesMetrics; +} + +/** + *A key-value pair representing a column and data type that this transform can
+ * run against. The Schema parameter of the MLTransform may contain up to 100 of these structures.
The name of the column.
+ * @public + */ + Name?: string; + + /** + *The type of data in the column.
+ * @public + */ + DataType?: string; +} + +/** + * @public + * @enum + */ +export const TransformStatusType = { + DELETING: "DELETING", + NOT_READY: "NOT_READY", + READY: "READY", +} as const; + +/** + * @public + */ +export type TransformStatusType = (typeof TransformStatusType)[keyof typeof TransformStatusType]; + +/** + * @public + */ +export interface GetMLTransformResponse { + /** + *The unique identifier of the transform, generated at the time that the transform was + * created.
+ * @public + */ + TransformId?: string; + + /** + *The unique name given to the transform when it was created.
+ * @public + */ + Name?: string; + + /** + *A description of the transform.
+ * @public + */ + Description?: string; + + /** + *The last known status of the transform (to indicate whether it can be used or not). One of "NOT_READY", "READY", or "DELETING".
+ * @public + */ + Status?: TransformStatusType; + + /** + *The date and time when the transform was created.
+ * @public + */ + CreatedOn?: Date; + + /** + *The date and time when the transform was last modified.
+ * @public + */ + LastModifiedOn?: Date; + + /** + *A list of Glue table definitions used by the transform.
+ * @public + */ + InputRecordTables?: GlueTable[]; + + /** + *The configuration parameters that are specific to the algorithm used.
+ * @public + */ + Parameters?: TransformParameters; + + /** + *The latest evaluation metrics.
+ * @public + */ + EvaluationMetrics?: EvaluationMetrics; + + /** + *The number of labels available for this transform.
+ * @public + */ + LabelCount?: number; + + /** + *The Map object that represents the schema that this
+ * transform accepts. Has an upper bound of 100 columns.
The name or Amazon Resource Name (ARN) of the IAM role with the required + * permissions.
+ * @public + */ + Role?: string; + + /** + *This value determines which version of Glue this machine learning transform is compatible with. Glue 1.0 is recommended for most customers. If the value is not set, the Glue compatibility defaults to Glue 0.9. For more information, see Glue Versions in the developer guide.
+ * @public + */ + GlueVersion?: string; + + /** + *The number of Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. A DPU is a relative measure of + * processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more + * information, see the Glue pricing + * page.
+ *When the WorkerType field is set to a value other than Standard, the MaxCapacity field is set automatically and becomes read-only.
The type of predefined worker that is allocated when this task runs. Accepts a value of Standard, G.1X, or G.2X.
+ *For the Standard worker type, each worker provides 4 vCPU, 16 GB of memory and a 50GB disk, and 2 executors per worker.
For the G.1X worker type, each worker provides 4 vCPU, 16 GB of memory and a 64GB disk, and 1 executor per worker.
For the G.2X worker type, each worker provides 8 vCPU, 32 GB of memory and a 128GB disk, and 1 executor per worker.
The number of workers of a defined workerType that are allocated when this task runs.
The timeout for a task run for this transform in minutes. This is the maximum time that a task run for this transform can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours).
The maximum number of times to retry a task for this transform after a task run fails.
+ * @public + */ + MaxRetries?: number; + + /** + *The encryption-at-rest settings of the transform that apply to accessing user data. Machine learning transforms can access user data encrypted in Amazon S3 using KMS.
+ * @public + */ + TransformEncryption?: TransformEncryption; +} + +/** + *The criteria used to filter the machine learning transforms.
+ * @public + */ +export interface TransformFilterCriteria { + /** + *A unique transform name that is used to filter the machine learning transforms.
+ * @public + */ + Name?: string; + + /** + *The type of machine learning transform that is used to filter the machine learning + * transforms.
+ * @public + */ + TransformType?: TransformType; + + /** + *Filters the list of machine learning transforms by the last known status of the transforms (to indicate whether a transform can be used or not). One of "NOT_READY", "READY", or "DELETING".
+ * @public + */ + Status?: TransformStatusType; + + /** + *This value determines which version of Glue this machine learning transform is compatible with. Glue 1.0 is recommended for most customers. If the value is not set, the Glue compatibility defaults to Glue 0.9. For more information, see Glue Versions in the developer guide.
+ * @public + */ + GlueVersion?: string; + + /** + *The time and date before which the transforms were created.
+ * @public + */ + CreatedBefore?: Date; + + /** + *The time and date after which the transforms were created.
+ * @public + */ + CreatedAfter?: Date; + + /** + *Filter on transforms last modified before this date.
+ * @public + */ + LastModifiedBefore?: Date; + + /** + *Filter on transforms last modified after this date.
+ * @public + */ + LastModifiedAfter?: Date; + + /** + *Filters on datasets with a specific schema. The Map
+ * object is an array of key-value pairs representing the schema this transform accepts, where
+ * Column is the name of a column, and Type is the type of the data
+ * such as an integer or string. Has an upper bound of 100 columns.
The sorting criteria that are associated with the machine learning transform.
+ * @public + */ +export interface TransformSortCriteria { + /** + *The column to be used in the sorting criteria that are associated with the machine + * learning transform.
+ * @public + */ + Column: TransformSortColumnType | undefined; + + /** + *The sort direction to be used in the sorting criteria that are associated with the machine + * learning transform.
+ * @public + */ + SortDirection: SortDirectionType | undefined; +} + /** * @public */ @@ -7606,226 +8006,6 @@ export interface UpdateTableRequest { Force?: boolean; } -/** - * @public - */ -export interface UpdateTableResponse {} - -/** - * @public - */ -export interface UpdateTableOptimizerRequest { - /** - *The Catalog ID of the table.
- * @public - */ - CatalogId: string | undefined; - - /** - *The name of the database in the catalog in which the table resides.
- * @public - */ - DatabaseName: string | undefined; - - /** - *The name of the table.
- * @public - */ - TableName: string | undefined; - - /** - *The type of table optimizer. Currently, the only valid value is compaction.
A TableOptimizerConfiguration object representing the configuration of a table optimizer.
A structure used to provide information used to update a trigger. This object updates the - * previous trigger definition by overwriting it completely.
- * @public - */ -export interface TriggerUpdate { - /** - *Reserved for future use.
- * @public - */ - Name?: string; - - /** - *A description of this trigger.
- * @public - */ - Description?: string; - - /** - *A cron expression used to specify the schedule (see Time-Based
- * Schedules for Jobs and Crawlers. For example, to run
- * something every day at 12:15 UTC, you would specify:
- * cron(15 12 * * ? *).
The actions initiated by this trigger.
- * @public - */ - Actions?: Action[]; - - /** - *The predicate of this trigger, which defines when it will fire.
- * @public - */ - Predicate?: Predicate; - - /** - *Batch condition that must be met (specified number of events received or batch time window expired) - * before EventBridge event trigger fires.
- * @public - */ - EventBatchingCondition?: EventBatchingCondition; -} - -/** - * @public - */ -export interface UpdateTriggerRequest { - /** - *The name of the trigger to update.
- * @public - */ - Name: string | undefined; - - /** - *The new values with which to update the trigger.
- * @public - */ - TriggerUpdate: TriggerUpdate | undefined; -} - -/** - * @public - */ -export interface UpdateTriggerResponse { - /** - *The resulting trigger definition.
- * @public - */ - Trigger?: Trigger; -} - -/** - * @public - */ -export interface UpdateUsageProfileRequest { - /** - *The name of the usage profile.
- * @public - */ - Name: string | undefined; - - /** - *A description of the usage profile.
- * @public - */ - Description?: string; - - /** - *A ProfileConfiguration object specifying the job and session values for the profile.
The name of the usage profile that was updated.
- * @public - */ - Name?: string; -} - -/** - * @public - */ -export interface UpdateUserDefinedFunctionRequest { - /** - *The ID of the Data Catalog where the function to be updated is located. If none is - * provided, the Amazon Web Services account ID is used by default.
- * @public - */ - CatalogId?: string; - - /** - *The name of the catalog database where the function to be updated is - * located.
- * @public - */ - DatabaseName: string | undefined; - - /** - *The name of the function.
- * @public - */ - FunctionName: string | undefined; - - /** - *A FunctionInput object that redefines the function in the Data
- * Catalog.
Name of the workflow to be updated.
- * @public - */ - Name: string | undefined; - - /** - *The description of the workflow.
- * @public - */ - Description?: string; - - /** - *A collection of properties to be used as part of each execution of the workflow.
- * @public - */ - DefaultRunProperties?: RecordYou can use this parameter to prevent unwanted multiple updates to data, to control costs, or in some cases, to prevent exceeding the maximum number of concurrent runs of any of the component jobs. If you leave this parameter blank, there is no limit to the number of concurrent workflow runs.
- * @public - */ - MaxConcurrentRuns?: number; -} - /** * @internal */ diff --git a/clients/client-glue/src/models/models_3.ts b/clients/client-glue/src/models/models_3.ts index a6eeb1d16564..db9a1644402c 100644 --- a/clients/client-glue/src/models/models_3.ts +++ b/clients/client-glue/src/models/models_3.ts @@ -2,6 +2,7 @@ import { SENSITIVE_STRING } from "@smithy/smithy-client"; import { + Action, Aggregate, AmazonRedshiftSource, AmazonRedshiftTarget, @@ -28,6 +29,7 @@ import { ErrorDetail, EvaluateDataQuality, EvaluateDataQualityMultiFrame, + EventBatchingCondition, ExecutionClass, ExecutionProperty, FillMissingValues, @@ -50,6 +52,7 @@ import { PIIDetection, PostgreSQLCatalogSource, PostgreSQLCatalogTarget, + Predicate, Recipe, RedshiftSource, RedshiftTarget, @@ -81,11 +84,14 @@ import { Spigot, SplitFields, StorageDescriptor, + TableOptimizerConfiguration, + TableOptimizerType, + Trigger, Union, WorkerType, } from "./models_0"; -import { Permission, TableIdentifier } from "./models_1"; +import { Permission, ProfileConfiguration, TableIdentifier, UserDefinedFunctionInput } from "./models_1"; import { ColumnRowFilter, @@ -96,6 +102,226 @@ import { ViewValidation, } from "./models_2"; +/** + * @public + */ +export interface UpdateTableResponse {} + +/** + * @public + */ +export interface UpdateTableOptimizerRequest { + /** + *The Catalog ID of the table.
+ * @public + */ + CatalogId: string | undefined; + + /** + *The name of the database in the catalog in which the table resides.
+ * @public + */ + DatabaseName: string | undefined; + + /** + *The name of the table.
+ * @public + */ + TableName: string | undefined; + + /** + *The type of table optimizer. Currently, the only valid value is compaction.
A TableOptimizerConfiguration object representing the configuration of a table optimizer.
A structure used to provide information used to update a trigger. This object updates the + * previous trigger definition by overwriting it completely.
+ * @public + */ +export interface TriggerUpdate { + /** + *Reserved for future use.
+ * @public + */ + Name?: string; + + /** + *A description of this trigger.
+ * @public + */ + Description?: string; + + /** + *A cron expression used to specify the schedule (see Time-Based
+ * Schedules for Jobs and Crawlers. For example, to run
+ * something every day at 12:15 UTC, you would specify:
+ * cron(15 12 * * ? *).
The actions initiated by this trigger.
+ * @public + */ + Actions?: Action[]; + + /** + *The predicate of this trigger, which defines when it will fire.
+ * @public + */ + Predicate?: Predicate; + + /** + *Batch condition that must be met (specified number of events received or batch time window expired) + * before EventBridge event trigger fires.
+ * @public + */ + EventBatchingCondition?: EventBatchingCondition; +} + +/** + * @public + */ +export interface UpdateTriggerRequest { + /** + *The name of the trigger to update.
+ * @public + */ + Name: string | undefined; + + /** + *The new values with which to update the trigger.
+ * @public + */ + TriggerUpdate: TriggerUpdate | undefined; +} + +/** + * @public + */ +export interface UpdateTriggerResponse { + /** + *The resulting trigger definition.
+ * @public + */ + Trigger?: Trigger; +} + +/** + * @public + */ +export interface UpdateUsageProfileRequest { + /** + *The name of the usage profile.
+ * @public + */ + Name: string | undefined; + + /** + *A description of the usage profile.
+ * @public + */ + Description?: string; + + /** + *A ProfileConfiguration object specifying the job and session values for the profile.
The name of the usage profile that was updated.
+ * @public + */ + Name?: string; +} + +/** + * @public + */ +export interface UpdateUserDefinedFunctionRequest { + /** + *The ID of the Data Catalog where the function to be updated is located. If none is + * provided, the Amazon Web Services account ID is used by default.
+ * @public + */ + CatalogId?: string; + + /** + *The name of the catalog database where the function to be updated is + * located.
+ * @public + */ + DatabaseName: string | undefined; + + /** + *The name of the function.
+ * @public + */ + FunctionName: string | undefined; + + /** + *A FunctionInput object that redefines the function in the Data
+ * Catalog.
Name of the workflow to be updated.
+ * @public + */ + Name: string | undefined; + + /** + *The description of the workflow.
+ * @public + */ + Description?: string; + + /** + *A collection of properties to be used as part of each execution of the workflow.
+ * @public + */ + DefaultRunProperties?: RecordYou can use this parameter to prevent unwanted multiple updates to data, to control costs, or in some cases, to prevent exceeding the maximum number of concurrent runs of any of the component jobs. If you leave this parameter blank, there is no limit to the number of concurrent workflow runs.
+ * @public + */ + MaxConcurrentRuns?: number; +} + /** * @public */ diff --git a/clients/client-glue/src/protocols/Aws_json1_1.ts b/clients/client-glue/src/protocols/Aws_json1_1.ts index 71fbc0687ab1..8124b288ab55 100644 --- a/clients/client-glue/src/protocols/Aws_json1_1.ts +++ b/clients/client-glue/src/protocols/Aws_json1_1.ts @@ -564,9 +564,6 @@ import { BatchUpdatePartitionRequestEntry, Blueprint, CancelDataQualityRuleRecommendationRunRequest, - CancelDataQualityRulesetEvaluationRunRequest, - CancelMLTaskRunRequest, - CancelStatementRequest, CatalogDeltaSource, CatalogHudiSource, CatalogKafkaSource, @@ -574,8 +571,8 @@ import { CatalogSchemaChangePolicy, CatalogSource, CatalogTarget, - CheckSchemaVersionValidityInput, Column, + CompactionMetrics, Condition, ConditionExpression, ConnectionsList, @@ -627,8 +624,12 @@ import { GovernedCatalogSource, GovernedCatalogTarget, HudiTarget, + IcebergCompactionMetrics, + IcebergOrphanFileDeletionConfiguration, + IcebergOrphanFileDeletionMetrics, + IcebergRetentionConfiguration, + IcebergRetentionMetrics, IcebergTarget, - IllegalSessionStateException, InternalServiceException, InvalidInputException, InvalidStateException, @@ -667,6 +668,8 @@ import { OracleSQLCatalogSource, OracleSQLCatalogTarget, Order, + OrphanFileDeletionConfiguration, + OrphanFileDeletionMetrics, Partition, PartitionInput, PartitionValueList, @@ -685,6 +688,8 @@ import { RenameField, ResourceNotReadyException, ResourceNumberLimitExceededException, + RetentionConfiguration, + RetentionMetrics, S3CatalogDeltaSource, S3CatalogHudiSource, S3CatalogSource, @@ -726,6 +731,7 @@ import { TableOptimizer, TableOptimizerConfiguration, TableOptimizerRun, + ThrottlingException, TimestampedInclusionAnnotation, TransformConfigParameter, Union, @@ -738,14 +744,17 @@ import { BinaryColumnStatisticsData, BlueprintRun, BooleanColumnStatisticsData, + CancelDataQualityRulesetEvaluationRunRequest, + CancelMLTaskRunRequest, + CancelStatementRequest, CatalogEntry, CatalogImportStatus, + CheckSchemaVersionValidityInput, Classifier, CloudWatchEncryption, CodeGenEdge, CodeGenNode, CodeGenNodeArg, - ColumnImportance, ColumnStatistics, ColumnStatisticsData, ColumnStatisticsTaskRun, @@ -830,10 +839,8 @@ import { DoubleColumnStatisticsData, EncryptionAtRest, EncryptionConfiguration, - EvaluationMetrics, FederatedDatabase, FederatedResourceAlreadyExistsException, - FindMatchesMetrics, FindMatchesParameters, GetBlueprintRequest, GetBlueprintResponse, @@ -901,11 +908,10 @@ import { GetMLTaskRunResponse, GetMLTaskRunsRequest, GetMLTaskRunsResponse, - GetMLTransformRequest, - GetMLTransformResponse, GrokClassifier, IcebergInput, IdempotentParameterMismatchException, + IllegalSessionStateException, JobBookmarksEncryption, JsonClassifier, Location, @@ -923,7 +929,6 @@ import { ResourceUri, S3Encryption, SchedulerTransitioningException, - SchemaColumn, Session, SessionCommand, StatisticModelResult, @@ -934,9 +939,7 @@ import { TaskRunFilterCriteria, TaskRunSortCriteria, TransformEncryption, - TransformFilterCriteria, TransformParameters, - TransformSortCriteria, UserDefinedFunctionInput, ValidationException, ViewDefinitionInput, @@ -944,6 +947,7 @@ import { XMLClassifier, } from "../models/models_1"; import { + ColumnImportance, ColumnStatisticsError, ColumnStatisticsTaskNotRunningException, ColumnStatisticsTaskRunningException, @@ -962,6 +966,10 @@ import { DataQualityRulesetFilterCriteria, DataQualityRulesetListDetails, DevEndpointCustomLibraries, + EvaluationMetrics, + FindMatchesMetrics, + GetMLTransformRequest, + GetMLTransformResponse, GetMLTransformsRequest, GetMLTransformsResponse, GetPartitionIndexesRequest, @@ -1073,6 +1081,7 @@ import { RunStatementRequest, SchedulerNotRunningException, SchedulerRunningException, + SchemaColumn, SchemaVersionNumber, SearchTablesRequest, SecurityConfiguration, @@ -1103,7 +1112,8 @@ import { TableAttributes, TagResourceRequest, TimestampFilter, - TriggerUpdate, + TransformFilterCriteria, + TransformSortCriteria, UnfilteredPartition, UntagResourceRequest, UpdateBlueprintRequest, @@ -1127,12 +1137,7 @@ import { UpdateRegistryInput, UpdateSchemaInput, UpdateSourceControlFromJobRequest, - UpdateTableOptimizerRequest, UpdateTableRequest, - UpdateTriggerRequest, - UpdateUsageProfileRequest, - UpdateUserDefinedFunctionRequest, - UpdateWorkflowRequest, UpdateXMLClassifierRequest, UsageProfileDefinition, UserDefinedFunction, @@ -1159,7 +1164,13 @@ import { Table, TableStatus, TableVersion, + TriggerUpdate, UpdateJobRequest, + UpdateTableOptimizerRequest, + UpdateTriggerRequest, + UpdateUsageProfileRequest, + UpdateUserDefinedFunctionRequest, + UpdateWorkflowRequest, } from "../models/models_3"; /** @@ -8597,6 +8608,9 @@ const de_CommandError = async (output: __HttpResponse, context: __SerdeContext): case "InvalidStateException": case "com.amazonaws.glue#InvalidStateException": throw await de_InvalidStateExceptionRes(parsedOutput, context); + case "ThrottlingException": + case "com.amazonaws.glue#ThrottlingException": + throw await de_ThrottlingExceptionRes(parsedOutput, context); case "IllegalSessionStateException": case "com.amazonaws.glue#IllegalSessionStateException": throw await de_IllegalSessionStateExceptionRes(parsedOutput, context); @@ -9217,6 +9231,19 @@ const de_SchedulerTransitioningExceptionRes = async ( return __decorateServiceException(exception, body); }; +/** + * deserializeAws_json1_1ThrottlingExceptionRes + */ +const de_ThrottlingExceptionRes = async (parsedOutput: any, context: __SerdeContext): PromiseA TableOptimizer object that contains details on the configuration and last run of a table optimzer.
A TableOptimizer object that contains details on the configuration and last run of a table optimizer.
A structure containing the Iceberg compaction metrics for the optimizer run.
" + } + } + }, + "traits": { + "smithy.api#documentation": "A structure that contains compaction metrics for the optimizer run.
" + } + }, "com.amazonaws.glue#Comparator": { "type": "enum", "members": { @@ -10221,6 +10247,12 @@ }, { "target": "com.amazonaws.glue#InvalidInputException" + }, + { + "target": "com.amazonaws.glue#ThrottlingException" + }, + { + "target": "com.amazonaws.glue#ValidationException" } ], "traits": { @@ -13530,6 +13562,9 @@ }, { "target": "com.amazonaws.glue#InvalidInputException" + }, + { + "target": "com.amazonaws.glue#ThrottlingException" } ], "traits": { @@ -20055,6 +20090,9 @@ }, { "target": "com.amazonaws.glue#InvalidInputException" + }, + { + "target": "com.amazonaws.glue#ThrottlingException" } ], "traits": { @@ -22151,6 +22189,42 @@ "smithy.api#pattern": "^arn:aws(-(cn|us-gov|iso(-[bef])?))?:iam::[0-9]{12}:role/.+$" } }, + "com.amazonaws.glue#IcebergCompactionMetrics": { + "type": "structure", + "members": { + "NumberOfBytesCompacted": { + "target": "com.amazonaws.glue#metricCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of bytes removed by the compaction job run.
" + } + }, + "NumberOfFilesCompacted": { + "target": "com.amazonaws.glue#metricCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of files removed by the compaction job run.
" + } + }, + "NumberOfDpus": { + "target": "com.amazonaws.glue#dpuCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of DPU hours consumed by the job.
" + } + }, + "JobDurationInHour": { + "target": "com.amazonaws.glue#dpuDurationInHour", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The duration of the job in hours.
" + } + } + }, + "traits": { + "smithy.api#documentation": "Compaction metrics for Iceberg for the optimizer run.
" + } + }, "com.amazonaws.glue#IcebergInput": { "type": "structure", "members": { @@ -22172,6 +22246,124 @@ "smithy.api#documentation": "A structure that defines an Apache Iceberg metadata table to create in the catalog.
" } }, + "com.amazonaws.glue#IcebergOrphanFileDeletionConfiguration": { + "type": "structure", + "members": { + "orphanFileRetentionPeriodInDays": { + "target": "com.amazonaws.glue#NullableInteger", + "traits": { + "smithy.api#documentation": "The number of days that orphan files should be retained before file deletion. If an input is not provided, the default value 3 will be used.
" + } + }, + "location": { + "target": "com.amazonaws.glue#MessageString", + "traits": { + "smithy.api#documentation": "Specifies a directory in which to look for files (defaults to the table's location). You may choose a sub-directory rather than the top-level table location.
" + } + } + }, + "traits": { + "smithy.api#documentation": "The configuration for an Iceberg orphan file deletion optimizer.
" + } + }, + "com.amazonaws.glue#IcebergOrphanFileDeletionMetrics": { + "type": "structure", + "members": { + "NumberOfOrphanFilesDeleted": { + "target": "com.amazonaws.glue#metricCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of orphan files deleted by the orphan file deletion job run.
" + } + }, + "NumberOfDpus": { + "target": "com.amazonaws.glue#dpuCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of DPU hours consumed by the job.
" + } + }, + "JobDurationInHour": { + "target": "com.amazonaws.glue#dpuDurationInHour", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The duration of the job in hours.
" + } + } + }, + "traits": { + "smithy.api#documentation": "Orphan file deletion metrics for Iceberg for the optimizer run.
" + } + }, + "com.amazonaws.glue#IcebergRetentionConfiguration": { + "type": "structure", + "members": { + "snapshotRetentionPeriodInDays": { + "target": "com.amazonaws.glue#NullableInteger", + "traits": { + "smithy.api#documentation": "The number of days to retain the Iceberg snapshots. If an input is not provided, the corresponding Iceberg table configuration field will be used or if not present, the default value 5 will be used.
" + } + }, + "numberOfSnapshotsToRetain": { + "target": "com.amazonaws.glue#NullableInteger", + "traits": { + "smithy.api#documentation": "The number of Iceberg snapshots to retain within the retention period. If an input is not provided, the corresponding Iceberg table configuration field will be used or if not present, the default value 1 will be used.
" + } + }, + "cleanExpiredFiles": { + "target": "com.amazonaws.glue#NullableBoolean", + "traits": { + "smithy.api#documentation": "If set to false, snapshots are only deleted from table metadata, and the underlying data and metadata files are not deleted.
" + } + } + }, + "traits": { + "smithy.api#documentation": "The configuration for an Iceberg snapshot retention optimizer.
" + } + }, + "com.amazonaws.glue#IcebergRetentionMetrics": { + "type": "structure", + "members": { + "NumberOfDataFilesDeleted": { + "target": "com.amazonaws.glue#metricCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of data files deleted by the retention job run.
" + } + }, + "NumberOfManifestFilesDeleted": { + "target": "com.amazonaws.glue#metricCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of manifest files deleted by the retention job run.
" + } + }, + "NumberOfManifestListsDeleted": { + "target": "com.amazonaws.glue#metricCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of manifest lists deleted by the retention job run.
" + } + }, + "NumberOfDpus": { + "target": "com.amazonaws.glue#dpuCounts", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The number of DPU hours consumed by the job.
" + } + }, + "JobDurationInHour": { + "target": "com.amazonaws.glue#dpuDurationInHour", + "traits": { + "smithy.api#default": 0, + "smithy.api#documentation": "The duration of the job in hours.
" + } + } + }, + "traits": { + "smithy.api#documentation": "Snapshot retention metrics for Iceberg for the optimizer run.
" + } + }, "com.amazonaws.glue#IcebergTarget": { "type": "structure", "members": { @@ -25875,6 +26067,12 @@ }, { "target": "com.amazonaws.glue#InvalidInputException" + }, + { + "target": "com.amazonaws.glue#ThrottlingException" + }, + { + "target": "com.amazonaws.glue#ValidationException" } ], "traits": { @@ -25882,6 +26080,7 @@ "smithy.api#paginated": { "inputToken": "NextToken", "outputToken": "NextToken", + "items": "TableOptimizerRuns", "pageSize": "MaxResults" } } @@ -27736,6 +27935,34 @@ "target": "com.amazonaws.glue#Order" } }, + "com.amazonaws.glue#OrphanFileDeletionConfiguration": { + "type": "structure", + "members": { + "icebergConfiguration": { + "target": "com.amazonaws.glue#IcebergOrphanFileDeletionConfiguration", + "traits": { + "smithy.api#documentation": "The configuration for an Iceberg orphan file deletion optimizer.
" + } + } + }, + "traits": { + "smithy.api#documentation": "The configuration for an orphan file deletion optimizer.
" + } + }, + "com.amazonaws.glue#OrphanFileDeletionMetrics": { + "type": "structure", + "members": { + "IcebergMetrics": { + "target": "com.amazonaws.glue#IcebergOrphanFileDeletionMetrics", + "traits": { + "smithy.api#documentation": "A structure containing the Iceberg orphan file deletion metrics for the optimizer run.
" + } + } + }, + "traits": { + "smithy.api#documentation": "A structure that contains orphan file deletion metrics for the optimizer run.
" + } + }, "com.amazonaws.glue#OtherMetadataValueList": { "type": "list", "member": { @@ -30151,6 +30378,34 @@ "smithy.api#output": {} } }, + "com.amazonaws.glue#RetentionConfiguration": { + "type": "structure", + "members": { + "icebergConfiguration": { + "target": "com.amazonaws.glue#IcebergRetentionConfiguration", + "traits": { + "smithy.api#documentation": "The configuration for an Iceberg snapshot retention optimizer.
" + } + } + }, + "traits": { + "smithy.api#documentation": "The configuration for a snapshot retention optimizer.
" + } + }, + "com.amazonaws.glue#RetentionMetrics": { + "type": "structure", + "members": { + "IcebergMetrics": { + "target": "com.amazonaws.glue#IcebergRetentionMetrics", + "traits": { + "smithy.api#documentation": "A structure containing the Iceberg retention metrics for the optimizer run.
" + } + } + }, + "traits": { + "smithy.api#documentation": "A structure that contains retention metrics for the optimizer run.
" + } + }, "com.amazonaws.glue#Role": { "type": "string" }, @@ -30230,7 +30485,7 @@ } }, "traits": { - "smithy.api#documentation": "Metrics for the optimizer run.
" + "smithy.api#documentation": "Metrics for the optimizer run.
\nThis structure is deprecated. See the individual metric members for compaction, retention, and orphan file deletion.
" } }, "com.amazonaws.glue#RunStatement": { @@ -35248,7 +35503,7 @@ "type": { "target": "com.amazonaws.glue#TableOptimizerType", "traits": { - "smithy.api#documentation": "The type of table optimizer. Currently, the only valid value is compaction.
The type of table optimizer. The valid values are:
\n\n compaction: for managing compaction with a table optimizer.
\n retention: for managing the retention of snapshot with a table optimizer.
\n orphan_file_deletion: for managing the deletion of orphan files with a table optimizer.
Whether table optimization is enabled.
" + "smithy.api#documentation": "Whether table optimization is enabled.
" + } + }, + "retentionConfiguration": { + "target": "com.amazonaws.glue#RetentionConfiguration", + "traits": { + "smithy.api#documentation": "The configuration for a snapshot retention optimizer.
" + } + }, + "orphanFileDeletionConfiguration": { + "target": "com.amazonaws.glue#OrphanFileDeletionConfiguration", + "traits": { + "smithy.api#documentation": "The configuration for an orphan file deletion optimizer.
" } } }, @@ -35341,7 +35608,10 @@ "metrics": { "target": "com.amazonaws.glue#RunMetrics", "traits": { - "smithy.api#documentation": "A RunMetrics object containing metrics for the optimizer run.
A RunMetrics object containing metrics for the optimizer run.
This member is deprecated. See the individual metric members for compaction, retention, and orphan file deletion.
" } }, "error": { @@ -35349,6 +35619,24 @@ "traits": { "smithy.api#documentation": "An error that occured during the optimizer run.
" } + }, + "compactionMetrics": { + "target": "com.amazonaws.glue#CompactionMetrics", + "traits": { + "smithy.api#documentation": "A CompactionMetrics object containing metrics for the optimizer run.
A RetentionMetrics object containing metrics for the optimizer run.
An OrphanFileDeletionMetrics object containing metrics for the optimizer run.
A message describing the problem.
" + } + } + }, + "traits": { + "smithy.api#documentation": "The throttling threshhold was exceeded.
", + "smithy.api#error": "client" + } + }, "com.amazonaws.glue#Timeout": { "type": "integer", "traits": { @@ -38372,6 +38687,9 @@ { "target": "com.amazonaws.glue#AccessDeniedException" }, + { + "target": "com.amazonaws.glue#ConcurrentModificationException" + }, { "target": "com.amazonaws.glue#EntityNotFoundException" }, @@ -38380,6 +38698,12 @@ }, { "target": "com.amazonaws.glue#InvalidInputException" + }, + { + "target": "com.amazonaws.glue#ThrottlingException" + }, + { + "target": "com.amazonaws.glue#ValidationException" } ], "traits": { @@ -39779,6 +40103,24 @@ } } }, + "com.amazonaws.glue#dpuCounts": { + "type": "integer", + "traits": { + "smithy.api#default": 0 + } + }, + "com.amazonaws.glue#dpuDurationInHour": { + "type": "double", + "traits": { + "smithy.api#default": 0 + } + }, + "com.amazonaws.glue#metricCounts": { + "type": "long", + "traits": { + "smithy.api#default": 0 + } + }, "com.amazonaws.glue#tableNameString": { "type": "string", "traits": {