Tuesday, October 17, 2017

ADLA Powershell upload files

Import-AzureRmDataLakeStoreItem
-Account wingspandevadla
-Destination /output/temp/srccust.tsv
-Path C:\Users\nitin24g\Downloads\CustomerDIM.csv

Submit ADLA job in ADF with Parameters



Linked Service:
 
AzureDataLakeAnalyticsLinkedService:
{
    "name": "AzureDataLakeAnalyticsLinkedService",
    "properties": {
        "hubName": "devadf_hub",
        "type": "AzureDataLakeAnalytics",
        "typeProperties": {
            "accountName": "devadla",
            "dataLakeAnalyticsUri": "azuredatalakeanalytics.net",
            "authorization": "**********",
            "sessionId": "**********",
            "subscriptionId": "42195f5d-f64b-45d3-a497-b4f61559c464",
            "resourceGroupName": "RGdev"
        }
    }
}


Source-BlobStorageLS:
{
    "name": "Source-BlobStorageLS",
    "properties": {
        "hubName": "devadf_hub",
        "type": "AzureStorage",
        "typeProperties": {
            "connectionString": "DefaultEndpointsProtocol=https;AccountName=blobAccount;AccountKey=**********"
        }
    }
}


Destination-DataLakeStore : 
{
    "name": "Destination-DataLakeStore",
    "properties": {
        "hubName": "devadf_hub",
        "type": "AzureDataLakeStore",
        "typeProperties": {
            "dataLakeStoreUri": "https://***.azuredatalakestore.net/webhdfs/v1",
            "servicePrincipalId": "5db67c2***************",
            "servicePrincipalKey": "*******",
            "tenant": "***.onmicrosoft.com",
            "subscriptionId": "42195f*********",
            "resourceGroupName": "RGdev"
        }
    }
}



 Data set:
DummyTab1:

{
    "name": "DummyTab1",
    "properties": {
        "published": false,
        "type": "AzureDataLakeStore",
        "linkedServiceName": "Destination-DataLakeStore",
        "typeProperties": {
            "fileName": "s.txt",
            "folderPath": "output/",
            "format": {
                "type": "TextFormat",
                "rowDelimiter": "\n",
                "columnDelimiter": "\t"
            }
        },
        "availability": {
            "frequency": "Hour",
            "interval": 1
        },
        "external": true,
        "policy": {}
    }
}


 DummyDataSet 2:
{
    "name": "DummyTab2",
    "properties": {
        "published": false,
        "type": "AzureDataLakeStore",
        "linkedServiceName": "Destination-DataLakeStore",
        "typeProperties": {
            "folderPath": "output"
        },
        "availability": {
            "frequency": "Hour",
            "interval": 1
        }
    }
}

 
Pipeline:

{
    "name": "MyADLAParam",
    "properties": {
        "description": "This is a pipeline to compute events for en-gb locale and date less than 2012/02/19.",
        "activities": [
            {
                "type": "DataLakeAnalyticsU-SQL",
                "typeProperties": {
                    "scriptPath": "sprint-release/Sprint6/DimCustomer_split.usql",
                    "scriptLinkedService": "Source-BlobStorageLS",
                    "degreeOfParallelism": 3,
                    "priority": 100,
                    "parameters": {
                        "paramMod": "1"
                    }
                },
                "inputs": [
                    {
                        "name": "DummyTab1"
                    }
                ],
                "outputs": [
                    {
                        "name": "DummyTab2"
                    }
                ],
                "policy": {
                    "timeout": "06:00:00",
                    "concurrency": 1,
                    "executionPriorityOrder": "NewestFirst",
                    "retry": 1
                },
                "scheduler": {
                    "frequency": "Hour",
                    "interval": 1
                },
                "name": "DimCustomerByMod",
                "linkedServiceName": "AzureDataLakeAnalyticsLinkedService"
            }
        ],
        "start": "2017-10-16T22:00:00Z",
        "end": "2017-10-17T12:00:00Z",
        "isPaused": false,
        "hubName": "devadf_hub",
        "pipelineMode": "Scheduled"
    }
}