|
268 | 268 | {"shape":"InternalServiceException"}, |
269 | 269 | {"shape":"ResourceNumberLimitExceededException"} |
270 | 270 | ], |
271 | | - "documentation":"<p>Annotate datapoints over time for a specific data quality statistic.</p>" |
| 271 | + "documentation":"<p>Annotate datapoints over time for a specific data quality statistic. The API requires both profileID and statisticID as part of the InclusionAnnotation input. The API only works for a single statisticId across multiple profiles.</p>" |
272 | 272 | }, |
273 | 273 | "BatchStopJobRun":{ |
274 | 274 | "name":"BatchStopJobRun", |
|
5599 | 5599 | "members":{ |
5600 | 5600 | "InclusionAnnotations":{ |
5601 | 5601 | "shape":"InclusionAnnotationList", |
5602 | | - "documentation":"<p>A list of <code>DatapointInclusionAnnotation</code>'s.</p>" |
| 5602 | + "documentation":"<p>A list of <code>DatapointInclusionAnnotation</code>'s. The InclusionAnnotations must contain a profileId and statisticId. If there are multiple InclusionAnnotations, the list must refer to a single statisticId across multiple profileIds.</p>" |
5603 | 5603 | }, |
5604 | 5604 | "ClientToken":{ |
5605 | 5605 | "shape":"HashString", |
|
10731 | 10731 | }, |
10732 | 10732 | "documentation":"<p>Additional run options you can specify for an evaluation run.</p>" |
10733 | 10733 | }, |
| 10734 | + "DataQualityGlueTable":{ |
| 10735 | + "type":"structure", |
| 10736 | + "required":[ |
| 10737 | + "DatabaseName", |
| 10738 | + "TableName" |
| 10739 | + ], |
| 10740 | + "members":{ |
| 10741 | + "DatabaseName":{ |
| 10742 | + "shape":"NameString", |
| 10743 | + "documentation":"<p>A database name in the Glue Data Catalog.</p>" |
| 10744 | + }, |
| 10745 | + "TableName":{ |
| 10746 | + "shape":"NameString", |
| 10747 | + "documentation":"<p>A table name in the Glue Data Catalog.</p>" |
| 10748 | + }, |
| 10749 | + "CatalogId":{ |
| 10750 | + "shape":"NameString", |
| 10751 | + "documentation":"<p>A unique identifier for the Glue Data Catalog.</p>" |
| 10752 | + }, |
| 10753 | + "ConnectionName":{ |
| 10754 | + "shape":"NameString", |
| 10755 | + "documentation":"<p>The name of the connection to the Glue Data Catalog.</p>" |
| 10756 | + }, |
| 10757 | + "AdditionalOptions":{ |
| 10758 | + "shape":"GlueTableAdditionalOptions", |
| 10759 | + "documentation":"<p>Additional options for the table. Currently there are two keys supported:</p> <ul> <li> <p> <code>pushDownPredicate</code>: to filter on partitions without having to list and read all the files in your dataset.</p> </li> <li> <p> <code>catalogPartitionPredicate</code>: to use server-side partition pruning using partition indexes in the Glue Data Catalog.</p> </li> </ul>" |
| 10760 | + }, |
| 10761 | + "PreProcessingQuery":{ |
| 10762 | + "shape":"PreProcessingQueryString", |
| 10763 | + "documentation":"<p>SQL Query of SparkSQL format that can be used to pre-process the data for the table in Glue Data Catalog, before running the Data Quality Operation.</p>" |
| 10764 | + } |
| 10765 | + }, |
| 10766 | + "documentation":"<p>The database and table in the Glue Data Catalog that is used for input or output data for Data Quality Operations.</p>" |
| 10767 | + }, |
10734 | 10768 | "DataQualityMetricValues":{ |
10735 | 10769 | "type":"structure", |
10736 | 10770 | "members":{ |
@@ -11172,11 +11206,14 @@ |
11172 | 11206 | }, |
11173 | 11207 | "DataSource":{ |
11174 | 11208 | "type":"structure", |
11175 | | - "required":["GlueTable"], |
11176 | 11209 | "members":{ |
11177 | 11210 | "GlueTable":{ |
11178 | 11211 | "shape":"GlueTable", |
11179 | 11212 | "documentation":"<p>An Glue table.</p>" |
| 11213 | + }, |
| 11214 | + "DataQualityGlueTable":{ |
| 11215 | + "shape":"DataQualityGlueTable", |
| 11216 | + "documentation":"<p>An Glue table for Data Quality Operations.</p>" |
11180 | 11217 | } |
11181 | 11218 | }, |
11182 | 11219 | "documentation":"<p>A data source (an Glue table) for which you want data quality results.</p>" |
|
21426 | 21463 | }, |
21427 | 21464 | "documentation":"<p>Specifies a target that uses Postgres SQL.</p>" |
21428 | 21465 | }, |
| 21466 | + "PreProcessingQueryString":{ |
| 21467 | + "type":"string", |
| 21468 | + "documentation":"<p>SQL Query of SparkSQL format that can be used to pre-process data before running Data Quality Operations.</p>", |
| 21469 | + "max":51200, |
| 21470 | + "min":0, |
| 21471 | + "pattern":"[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*" |
| 21472 | + }, |
21429 | 21473 | "Predecessor":{ |
21430 | 21474 | "type":"structure", |
21431 | 21475 | "members":{ |
|
0 commit comments