AWS Glue DataBrew Update: This SDK release adds two new dataset features: 1) support for specifying the file format for a dataset, and 2) support for specifying whether the first row of a CSV or Excel file contains a header.

Author: AWS

.changes/next-release/feature-AWSGlueDataBrew-9f246d6.json

@@ -0,0 +1,6 @@
+{
+    "type": "feature",
+    "category": "AWS Glue DataBrew",
+    "contributor": "",
+    "description": "This SDK release adds two new dataset features: 1) support for specifying the file format for a dataset, and 2) support for specifying whether the first row of a CSV or Excel file contains a header."
+}

services/databrew/src/main/resources/codegen-resources/service-2.json

@@ -739,6 +739,10 @@
           "shape":"DatasetName",
           "documentation":"<p>The name of the dataset to be created. Valid characters are alphanumeric (A-Z, a-z, 0-9), hyphen (-), period (.), and space.</p>"
         },
+        "Format":{
+          "shape":"InputFormat",
+          "documentation":"<p>Specifies the file format of a dataset created from an S3 file or folder.</p>"
+        },
         "FormatOptions":{"shape":"FormatOptions"},
         "Input":{"shape":"Input"},
         "Tags":{
@@ -1016,6 +1020,10 @@
         "Delimiter":{
           "shape":"Delimiter",
           "documentation":"<p>A single character that specifies the delimiter being used in the Csv file.</p>"
+        },
+        "HeaderRow":{
+          "shape":"HeaderRow",
+          "documentation":"<p>A variable that specifies whether the first row in the file will be parsed as the header. If false, column names will be auto-generated.</p>"
         }
       },
       "documentation":"<p>Options that define how DataBrew will read a Csv file when creating a dataset from that file.</p>"
@@ -1084,6 +1092,10 @@
           "shape":"DatasetName",
           "documentation":"<p>The unique name of the dataset.</p>"
         },
+        "Format":{
+          "shape":"InputFormat",
+          "documentation":"<p>Specifies the file format of a dataset created from an S3 file or folder.</p>"
+        },
         "FormatOptions":{
           "shape":"FormatOptions",
           "documentation":"<p>Options that define how DataBrew interprets the data in the dataset.</p>"
@@ -1287,6 +1299,10 @@
           "shape":"DatasetName",
           "documentation":"<p>The name of the dataset.</p>"
         },
+        "Format":{
+          "shape":"InputFormat",
+          "documentation":"<p>Specifies the file format of a dataset created from an S3 file or folder.</p>"
+        },
         "FormatOptions":{"shape":"FormatOptions"},
         "Input":{"shape":"Input"},
         "LastModifiedDate":{
@@ -1717,6 +1733,10 @@
         "SheetIndexes":{
           "shape":"SheetIndexList",
           "documentation":"<p>Specifies one or more sheet numbers in the Excel file, which will be included in the dataset.</p>"
+        },
+        "HeaderRow":{
+          "shape":"HeaderRow",
+          "documentation":"<p>A variable that specifies whether the first row in the file will be parsed as the header. If false, column names will be auto-generated.</p>"
         }
       },
       "documentation":"<p>Options that define how DataBrew will interpret a Microsoft Excel file, when creating a dataset from that file.</p>"
@@ -1740,6 +1760,7 @@
       },
       "documentation":"<p>Options that define the structure of either Csv, Excel, or JSON input.</p>"
     },
+    "HeaderRow":{"type":"boolean"},
     "HiddenColumnList":{
       "type":"list",
       "member":{"shape":"ColumnName"}
@@ -1758,6 +1779,15 @@
       },
       "documentation":"<p>Information on how DataBrew can find data, in either the AWS Glue Data Catalog or Amazon S3.</p>"
     },
+    "InputFormat":{
+      "type":"string",
+      "enum":[
+        "CSV",
+        "JSON",
+        "PARQUET",
+        "EXCEL"
+      ]
+    },
     "InternalServerException":{
       "type":"structure",
       "members":{
@@ -3047,6 +3077,10 @@
           "location":"uri",
           "locationName":"name"
         },
+        "Format":{
+          "shape":"InputFormat",
+          "documentation":"<p>Specifies the file format of a dataset created from an S3 file or folder.</p>"
+        },
         "FormatOptions":{"shape":"FormatOptions"},
         "Input":{"shape":"Input"}
       }