Various updates

This commit is contained in:
Paul Andrew
2022-02-28 07:37:47 +00:00
parent 5868d4ed76
commit 3439868f62
40 changed files with 2249 additions and 0 deletions

View File

@@ -0,0 +1,64 @@
{
"name": "BuildProductDimension",
"properties": {
"folder": {
"name": "Lab4"
},
"type": "MappingDataFlow",
"typeProperties": {
"sources": [
{
"dataset": {
"referenceName": "ADLS_Product",
"type": "DatasetReference"
},
"name": "Product"
},
{
"dataset": {
"referenceName": "ADLS_ProductCategory",
"type": "DatasetReference"
},
"name": "ProductCategory"
},
{
"dataset": {
"referenceName": "ADLS_ProductModel",
"type": "DatasetReference"
},
"name": "ProductModel"
}
],
"sinks": [
{
"dataset": {
"referenceName": "ADLS_DimProduct",
"type": "DatasetReference"
},
"name": "DimProduct"
}
],
"transformations": [
{
"name": "SelectProductColumns"
},
{
"name": "SelectProductCategoryColumns"
},
{
"name": "SelectProductModelColumns"
},
{
"name": "LookupProductCategory"
},
{
"name": "LookupProductModelID"
},
{
"name": "RemoveDuplicateColumns"
}
],
"script": "source(output(\n\t\tProductID as short,\n\t\tName as string,\n\t\tProductNumber as string,\n\t\tColor as string,\n\t\tStandardCost as double,\n\t\tListPrice as double,\n\t\tSize as string,\n\t\tWeight as double,\n\t\tProductCategoryID as short,\n\t\tProductModelID as short,\n\t\tSellStartDate as string,\n\t\tSellEndDate as string,\n\t\tDiscontinuedDate as string,\n\t\tThumbNailPhoto as string,\n\t\tThumbnailPhotoFileName as string,\n\t\trowguid as string,\n\t\tModifiedDate as string\n\t),\n\tallowSchemaDrift: true,\n\tvalidateSchema: false,\n\tignoreNoFilesFound: false) ~> Product\nsource(output(\n\t\tProductCategoryID as short,\n\t\tParentProductCategoryID as string,\n\t\tName as string,\n\t\trowguid as string,\n\t\tModifiedDate as string\n\t),\n\tallowSchemaDrift: true,\n\tvalidateSchema: false,\n\tignoreNoFilesFound: false) ~> ProductCategory\nsource(output(\n\t\tProductModelID as short,\n\t\tName as string,\n\t\tCatalogDescription as string,\n\t\trowguid as string,\n\t\tModifiedDate as string\n\t),\n\tallowSchemaDrift: true,\n\tvalidateSchema: false,\n\tignoreNoFilesFound: false) ~> ProductModel\nProduct select(mapColumn(\n\t\tProductID,\n\t\tProduct = Name,\n\t\tProductCategoryID,\n\t\tProductModelID\n\t),\n\tskipDuplicateMapInputs: true,\n\tskipDuplicateMapOutputs: true) ~> SelectProductColumns\nProductCategory select(mapColumn(\n\t\tProductCategoryID,\n\t\tProductCategory = Name\n\t),\n\tskipDuplicateMapInputs: true,\n\tskipDuplicateMapOutputs: true) ~> SelectProductCategoryColumns\nProductModel select(mapColumn(\n\t\tProductModelID,\n\t\tProductModel = Name\n\t),\n\tskipDuplicateMapInputs: true,\n\tskipDuplicateMapOutputs: true) ~> SelectProductModelColumns\nSelectProductColumns, SelectProductCategoryColumns lookup(SelectProductColumns@ProductCategoryID == SelectProductCategoryColumns@ProductCategoryID,\n\tmultiple: false,\n\tpickup: 'any',\n\tbroadcast: 'auto')~> LookupProductCategory\nLookupProductCategory, SelectProductModelColumns lookup(SelectProductColumns@ProductModelID == SelectProductModelColumns@ProductModelID,\n\tmultiple: false,\n\tpickup: 'any',\n\tbroadcast: 'auto')~> LookupProductModelID\nLookupProductModelID select(mapColumn(\n\t\tProductID,\n\t\tProduct,\n\t\tProductCategoryID = {SelectProductColumns@ProductCategoryID},\n\t\tProductModelID = {SelectProductColumns@ProductModelID},\n\t\tProductCategory,\n\t\tProductModel\n\t),\n\tskipDuplicateMapInputs: true,\n\tskipDuplicateMapOutputs: true) ~> RemoveDuplicateColumns\nRemoveDuplicateColumns sink(allowSchemaDrift: true,\n\tvalidateSchema: false,\n\tformat: 'parquet',\n\tskipDuplicateMapInputs: true,\n\tskipDuplicateMapOutputs: true) ~> DimProduct"
}
}
}

View File

@@ -0,0 +1,24 @@
{
"name": "ADLS_DimProduct",
"properties": {
"linkedServiceName": {
"referenceName": "AzureDataLakeStorage1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab4"
},
"annotations": [],
"type": "Parquet",
"typeProperties": {
"location": {
"type": "AzureBlobFSLocation",
"folderPath": "Cleaned/DimProduct",
"fileSystem": "lakeroot"
},
"compressionCodec": "snappy"
},
"schema": []
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,28 @@
{
"name": "ADLS_Product",
"properties": {
"linkedServiceName": {
"referenceName": "AzureDataLakeStorage1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab4"
},
"annotations": [],
"type": "DelimitedText",
"typeProperties": {
"location": {
"type": "AzureBlobFSLocation",
"fileName": "SalesLT.Product.txt",
"folderPath": "Raw",
"fileSystem": "lakeroot"
},
"columnDelimiter": ",",
"escapeChar": "\\",
"firstRowAsHeader": true,
"quoteChar": "\""
},
"schema": []
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,28 @@
{
"name": "ADLS_ProductCategory",
"properties": {
"linkedServiceName": {
"referenceName": "AzureDataLakeStorage1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab4"
},
"annotations": [],
"type": "DelimitedText",
"typeProperties": {
"location": {
"type": "AzureBlobFSLocation",
"fileName": "SalesLT.ProductCategory.txt",
"folderPath": "Raw",
"fileSystem": "lakeroot"
},
"columnDelimiter": ",",
"escapeChar": "\\",
"firstRowAsHeader": true,
"quoteChar": "\""
},
"schema": []
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,28 @@
{
"name": "ADLS_ProductModel",
"properties": {
"linkedServiceName": {
"referenceName": "AzureDataLakeStorage1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab4"
},
"annotations": [],
"type": "DelimitedText",
"typeProperties": {
"location": {
"type": "AzureBlobFSLocation",
"fileName": "SalesLT.ProductModel.txt",
"folderPath": "Raw",
"fileSystem": "lakeroot"
},
"columnDelimiter": ",",
"escapeChar": "\\",
"firstRowAsHeader": true,
"quoteChar": "\""
},
"schema": []
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,27 @@
{
"name": "ADLS_Raw",
"properties": {
"linkedServiceName": {
"referenceName": "AzureDataLakeStorage1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab2"
},
"annotations": [],
"type": "DelimitedText",
"typeProperties": {
"location": {
"type": "AzureBlobFSLocation",
"folderPath": "Raw",
"fileSystem": "lakeroot"
},
"columnDelimiter": ",",
"escapeChar": "\\",
"firstRowAsHeader": true,
"quoteChar": "\""
},
"schema": []
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,36 @@
{
"name": "ADLS_Raw_Generic",
"properties": {
"linkedServiceName": {
"referenceName": "AzureDataLakeStorage1",
"type": "LinkedServiceReference"
},
"parameters": {
"File": {
"type": "string"
}
},
"folder": {
"name": "Lab5"
},
"annotations": [],
"type": "DelimitedText",
"typeProperties": {
"location": {
"type": "AzureBlobFSLocation",
"fileName": {
"value": "@dataset().File",
"type": "Expression"
},
"folderPath": "Raw",
"fileSystem": "lakeroot"
},
"columnDelimiter": ",",
"escapeChar": "\\",
"firstRowAsHeader": true,
"quoteChar": "\""
},
"schema": []
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,34 @@
{
"name": "ASQL_AdventureWorks_Generic",
"properties": {
"linkedServiceName": {
"referenceName": "AzureSqlDatabase1",
"type": "LinkedServiceReference"
},
"parameters": {
"TableSchema": {
"type": "string"
},
"TableName": {
"type": "string"
}
},
"folder": {
"name": "Lab5"
},
"annotations": [],
"type": "AzureSqlTable",
"schema": [],
"typeProperties": {
"schema": {
"value": "@dataset().TableSchema",
"type": "Expression"
},
"table": {
"value": "@dataset().TableName",
"type": "Expression"
}
}
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,106 @@
{
"name": "ASQL_Product",
"properties": {
"linkedServiceName": {
"referenceName": "AzureSqlDatabase1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab2"
},
"annotations": [],
"type": "AzureSqlTable",
"schema": [
{
"name": "ProductID",
"type": "int",
"precision": 10
},
{
"name": "Name",
"type": "nvarchar"
},
{
"name": "ProductNumber",
"type": "nvarchar"
},
{
"name": "Color",
"type": "nvarchar"
},
{
"name": "StandardCost",
"type": "money",
"precision": 19,
"scale": 4
},
{
"name": "ListPrice",
"type": "money",
"precision": 19,
"scale": 4
},
{
"name": "Size",
"type": "nvarchar"
},
{
"name": "Weight",
"type": "decimal",
"precision": 8,
"scale": 2
},
{
"name": "ProductCategoryID",
"type": "int",
"precision": 10
},
{
"name": "ProductModelID",
"type": "int",
"precision": 10
},
{
"name": "SellStartDate",
"type": "datetime",
"precision": 23,
"scale": 3
},
{
"name": "SellEndDate",
"type": "datetime",
"precision": 23,
"scale": 3
},
{
"name": "DiscontinuedDate",
"type": "datetime",
"precision": 23,
"scale": 3
},
{
"name": "ThumbNailPhoto",
"type": "varbinary"
},
{
"name": "ThumbnailPhotoFileName",
"type": "nvarchar"
},
{
"name": "rowguid",
"type": "uniqueidentifier"
},
{
"name": "ModifiedDate",
"type": "datetime",
"precision": 23,
"scale": 3
}
],
"typeProperties": {
"schema": "SalesLT",
"table": "Product"
}
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,106 @@
{
"name": "ASQL_ProductModel",
"properties": {
"linkedServiceName": {
"referenceName": "AzureSqlDatabase1",
"type": "LinkedServiceReference"
},
"folder": {
"name": "Lab4"
},
"annotations": [],
"type": "AzureSqlTable",
"schema": [
{
"name": "ProductID",
"type": "int",
"precision": 10
},
{
"name": "Name",
"type": "nvarchar"
},
{
"name": "ProductNumber",
"type": "nvarchar"
},
{
"name": "Color",
"type": "nvarchar"
},
{
"name": "StandardCost",
"type": "money",
"precision": 19,
"scale": 4
},
{
"name": "ListPrice",
"type": "money",
"precision": 19,
"scale": 4
},
{
"name": "Size",
"type": "nvarchar"
},
{
"name": "Weight",
"type": "decimal",
"precision": 8,
"scale": 2
},
{
"name": "ProductCategoryID",
"type": "int",
"precision": 10
},
{
"name": "ProductModelID",
"type": "int",
"precision": 10
},
{
"name": "SellStartDate",
"type": "datetime",
"precision": 23,
"scale": 3
},
{
"name": "SellEndDate",
"type": "datetime",
"precision": 23,
"scale": 3
},
{
"name": "DiscontinuedDate",
"type": "datetime",
"precision": 23,
"scale": 3
},
{
"name": "ThumbNailPhoto",
"type": "varbinary"
},
{
"name": "ThumbnailPhotoFileName",
"type": "nvarchar"
},
{
"name": "rowguid",
"type": "uniqueidentifier"
},
{
"name": "ModifiedDate",
"type": "datetime",
"precision": 23,
"scale": 3
}
],
"typeProperties": {
"schema": "SalesLT",
"table": "ProductModel"
}
},
"type": "Microsoft.DataFactory/factories/datasets"
}

View File

@@ -0,0 +1,4 @@
{
"name": "adayfullofadf-adf",
"location": "uksouth"
}

View File

@@ -0,0 +1,27 @@
{
"name": "SSISIntegrationRuntime",
"properties": {
"type": "Managed",
"typeProperties": {
"computeProperties": {
"location": "UK South",
"nodeSize": "Standard_D2_v3",
"numberOfNodes": 1,
"maxParallelExecutionsPerNode": 2
},
"ssisProperties": {
"catalogInfo": {
"catalogServerEndpoint": "adayfullofadf-sql.database.windows.net",
"catalogAdminUserName": "sql-admin",
"catalogAdminPassword": {
"type": "SecureString",
"value": "**********"
},
"catalogPricingTier": "S1"
},
"edition": "Standard",
"licenseType": "LicenseIncluded"
}
}
}
}

View File

@@ -0,0 +1,11 @@
{
"name": "AzureDataLakeStorage1",
"type": "Microsoft.DataFactory/factories/linkedservices",
"properties": {
"annotations": [],
"type": "AzureBlobFS",
"typeProperties": {
"url": "https://adayfullofadfsa.dfs.core.windows.net"
}
}
}

View File

@@ -0,0 +1,12 @@
{
"name": "AzureSqlDatabase1",
"type": "Microsoft.DataFactory/factories/linkedservices",
"properties": {
"annotations": [],
"type": "AzureSqlDatabase",
"typeProperties": {
"connectionString": "integrated security=False;encrypt=True;connection timeout=30;data source=adayfullofadf-sql.database.windows.net;initial catalog=AdventureWorks;user id=sql-admin",
"encryptedCredential": "ew0KICAiVmVyc2lvbiI6ICIyMDE3LTExLTMwIiwNCiAgIlByb3RlY3Rpb25Nb2RlIjogIktleSIsDQogICJTZWNyZXRDb250ZW50VHlwZSI6ICJQbGFpbnRleHQiLA0KICAiQ3JlZGVudGlhbElkIjogIkFEQVlGVUxMT0ZBREYtQURGXzA3MGU1MDIyLWEzYjMtNDFmMS1hOTk3LWU2ODE3Y2VhNjdhYyINCn0="
}
}
}

View File

@@ -0,0 +1,36 @@
{
"name": "BuildProductDimension",
"properties": {
"activities": [
{
"name": "BuildProductDimension",
"type": "ExecuteDataFlow",
"dependsOn": [],
"policy": {
"timeout": "7.00:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"dataflow": {
"referenceName": "BuildProductDimension",
"type": "DataFlowReference"
},
"compute": {
"coreCount": 8,
"computeType": "General"
}
}
}
],
"folder": {
"name": "Lab4"
},
"annotations": [],
"lastPublishTime": "2020-09-26T17:05:06Z"
},
"type": "Microsoft.DataFactory/factories/pipelines"
}

View File

@@ -0,0 +1,83 @@
{
"name": "CopyAdventureWorks",
"properties": {
"activities": [
{
"name": "Get table list",
"type": "Lookup",
"dependsOn": [],
"policy": {
"timeout": "7.00:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"source": {
"type": "AzureSqlSource",
"sqlReaderQuery": "SELECT TABLE_SCHEMA, TABLE_NAME \nFROM INFORMATION_SCHEMA.TABLES\nWHERE TABLE_TYPE = 'BASE TABLE'\nAND TABLE_SCHEMA = 'SalesLT'\n",
"queryTimeout": "02:00:00",
"partitionOption": "None"
},
"dataset": {
"referenceName": "ASQL_Product",
"type": "DatasetReference"
},
"firstRowOnly": false
}
},
{
"name": "ForEach1",
"type": "ForEach",
"dependsOn": [
{
"activity": "Get table list",
"dependencyConditions": [
"Succeeded"
]
}
],
"userProperties": [],
"typeProperties": {
"items": {
"value": "@activity('Get table list').output.value",
"type": "Expression"
},
"activities": [
{
"name": "Execute Pipeline1",
"type": "ExecutePipeline",
"dependsOn": [],
"userProperties": [],
"typeProperties": {
"pipeline": {
"referenceName": "CopyAnyTable",
"type": "PipelineReference"
},
"waitOnCompletion": true,
"parameters": {
"TableSchema": {
"value": "@item().TABLE_SCHEMA",
"type": "Expression"
},
"TableName": {
"value": "@item().TABLE_NAME",
"type": "Expression"
}
}
}
}
]
}
}
],
"folder": {
"name": "Lab5"
},
"annotations": [],
"lastPublishTime": "2020-09-26T17:11:52Z"
},
"type": "Microsoft.DataFactory/factories/pipelines"
}

View File

@@ -0,0 +1,89 @@
{
"name": "CopyAnyTable",
"properties": {
"activities": [
{
"name": "Copy table",
"type": "Copy",
"dependsOn": [],
"policy": {
"timeout": "7.00:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"source": {
"type": "AzureSqlSource",
"queryTimeout": "02:00:00",
"partitionOption": "None"
},
"sink": {
"type": "DelimitedTextSink",
"storeSettings": {
"type": "AzureBlobFSWriteSettings"
},
"formatSettings": {
"type": "DelimitedTextWriteSettings",
"quoteAllText": true,
"fileExtension": ".txt"
}
},
"enableStaging": false,
"translator": {
"type": "TabularTranslator",
"typeConversion": true,
"typeConversionSettings": {
"allowDataTruncation": true,
"treatBooleanAsNumber": false
}
}
},
"inputs": [
{
"referenceName": "ASQL_AdventureWorks_Generic",
"type": "DatasetReference",
"parameters": {
"TableSchema": {
"value": "@pipeline().parameters.TableSchema",
"type": "Expression"
},
"TableName": {
"value": "@pipeline().parameters.TableName",
"type": "Expression"
}
}
}
],
"outputs": [
{
"referenceName": "ADLS_Raw_Generic",
"type": "DatasetReference",
"parameters": {
"File": {
"value": "@{pipeline().parameters.TableSchema}.@{pipeline().parameters.TableName}.txt",
"type": "Expression"
}
}
}
]
}
],
"parameters": {
"TableSchema": {
"type": "string"
},
"TableName": {
"type": "string"
}
},
"folder": {
"name": "Lab5"
},
"annotations": [],
"lastPublishTime": "2020-09-26T17:11:52Z"
},
"type": "Microsoft.DataFactory/factories/pipelines"
}

View File

@@ -0,0 +1,65 @@
{
"name": "CopyProduct",
"properties": {
"activities": [
{
"name": "Copy data to lake",
"type": "Copy",
"dependsOn": [],
"policy": {
"timeout": "7.00:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"source": {
"type": "AzureSqlSource",
"queryTimeout": "02:00:00",
"partitionOption": "None"
},
"sink": {
"type": "DelimitedTextSink",
"storeSettings": {
"type": "AzureBlobFSWriteSettings"
},
"formatSettings": {
"type": "DelimitedTextWriteSettings",
"quoteAllText": true,
"fileExtension": ".txt"
}
},
"enableStaging": false,
"translator": {
"type": "TabularTranslator",
"typeConversion": true,
"typeConversionSettings": {
"allowDataTruncation": true,
"treatBooleanAsNumber": false
}
}
},
"inputs": [
{
"referenceName": "ASQL_Product",
"type": "DatasetReference"
}
],
"outputs": [
{
"referenceName": "ADLS_Raw",
"type": "DatasetReference"
}
]
}
],
"folder": {
"name": "Lab2"
},
"annotations": [],
"lastPublishTime": "2020-09-26T14:33:50Z"
},
"type": "Microsoft.DataFactory/factories/pipelines"
}

View File

@@ -0,0 +1,38 @@
{
"name": "CopyProductCategory",
"properties": {
"activities": [
{
"name": "Execute CopyProductCategory",
"type": "ExecuteSSISPackage",
"dependsOn": [],
"policy": {
"timeout": "7.00:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"packageLocation": {
"packagePath": "ADayFullOfAdf/SsisPackages/CopyProductCategory.dtsx",
"type": "SSISDB"
},
"environmentPath": null,
"connectVia": {
"referenceName": "SSISIntegrationRuntime",
"type": "IntegrationRuntimeReference"
},
"loggingLevel": "Basic"
}
}
],
"folder": {
"name": "Lab3"
},
"annotations": [],
"lastPublishTime": "2020-09-26T15:27:22Z"
},
"type": "Microsoft.DataFactory/factories/pipelines"
}

View File

@@ -0,0 +1,65 @@
{
"name": "CopyProductModel",
"properties": {
"activities": [
{
"name": "Copy data1",
"type": "Copy",
"dependsOn": [],
"policy": {
"timeout": "7.00:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"source": {
"type": "AzureSqlSource",
"queryTimeout": "02:00:00",
"partitionOption": "None"
},
"sink": {
"type": "DelimitedTextSink",
"storeSettings": {
"type": "AzureBlobFSWriteSettings"
},
"formatSettings": {
"type": "DelimitedTextWriteSettings",
"quoteAllText": true,
"fileExtension": ".txt"
}
},
"enableStaging": false,
"translator": {
"type": "TabularTranslator",
"typeConversion": true,
"typeConversionSettings": {
"allowDataTruncation": true,
"treatBooleanAsNumber": false
}
}
},
"inputs": [
{
"referenceName": "ASQL_ProductModel",
"type": "DatasetReference"
}
],
"outputs": [
{
"referenceName": "ADLS_Raw",
"type": "DatasetReference"
}
]
}
],
"folder": {
"name": "Lab4"
},
"annotations": [],
"lastPublishTime": "2020-09-26T16:27:34Z"
},
"type": "Microsoft.DataFactory/factories/pipelines"
}