Merge pull request #8 from riv/master

[NEW FEATURE] MSGHT Non-Incremental Pipeline Setup

.gitignore

@@ -251,3 +251,4 @@ paket-files/
 .idea/
 *.sln.iml
 
+/ghinsights/DataFactory/ProductionEnvironment.json

ghinsights/DataFactory/MSEventDetail.json

@@ -0,0 +1,43 @@
+{
+  "$schema": "http://datafactories.schema.management.azure.com/schemas/2015-08-01/Microsoft.DataFactory.Table.json",
+  "name": "MSEventDetail",
+  "properties": {
+    "type": "AzureBlob",
+    "linkedServiceName": "MSPrestagedEventsAzureStorage",
+    "typeProperties": {
+      "folderPath": "raw/{EventName}/v1/{Year}/{Month}",
+      "fileName": "{EventName}_{Year}_{Month}_{Day}.json.gz",
+      "partitionedBy": [
+        {
+          "name": "Year",
+          "value": {
+            "type": "DateTime",
+            "date": "SliceStart",
+            "format": "yyyy"
+          }
+        },
+        {
+          "name": "Month",
+          "value": {
+            "type": "DateTime",
+            "date": "SliceStart",
+            "format": "MM"
+          }
+        },
+        {
+          "name": "Day",
+          "value": {
+            "type": "DateTime",
+            "date": "SliceStart",
+            "format": "dd"
+          }
+        }
+      ]
+    },
+    "external": false,
+    "availability": {
+      "frequency": "Day",
+      "interval": 1
+    }
+  }
+}

ghinsights/DataFactory/MSGHTEventDetailPipeline.json

@@ -0,0 +1,39 @@
+{
+  "$schema": "http://datafactories.schema.management.azure.com/schemas/2015-08-01/Microsoft.DataFactory.Pipeline.json",
+  "name": "MSGHTEventDetailPipeline",
+  "properties": {
+    "description": "Custom DotNetActivity pipeline to gather microsoft github mongodb backups and unpack the seperate events into a new container.",
+    "activities": [
+      {
+        "name": "MongoDbDumpTransformActivity",
+        "type": "DotNetActivity",
+        "inputs": [ { "name": "MSMongoDbDump" } ],
+        "outputs": [ { "name": "MSEventDetail" } ],
+        "typeProperties": {
+          "assemblyName": "GHInsights.DataFactory.dll",
+          "entryPoint": "GHInsights.DataFactory.MongoDbDumpTransformActivity",
+          "packageLinkedService": "GHInsightsAzureStorage",
+          "packageFile": "datafactory/GHInsights.DataFactory.zip",
+          "extendedProperties": {
+            "Year": "$$Text.Format('{0:yyyy}',SliceStart)",
+            "Month": "$$Text.Format('{0:MM}',SliceStart)",
+            "Day": "$$Text.Format('{0:dd}',SliceStart)"
+          }
+        },
+        "linkedServiceName": "BatchProcessor",
+        "policy": {
+          "concurrency": 6,
+          "executionPriorityOrder": "NewestFirst",
+          "retry": 0,
+          "timeout": "04:00:00"
+        },
+        "scheduler": {
+          "frequency": "Day",
+          "interval": 1
+        }
+      }
+    ],
+    "start": "2016-06-13T00:00:00Z",
+    "end": "9999-09-09T00:00:00Z"
+  }
+}

ghinsights/DataFactory/MSGHTorrentAzureStorage.json

@@ -0,0 +1,11 @@
+{
+  "$schema": "http://datafactories.schema.management.azure.com/schemas/2015-10-01/Microsoft.DataFactory.LinkedService.json",
+
+  "name": "MSGHTorrentAzureStorage",
+  "properties": {
+    "type": "AzureStorageSas",
+    "typeProperties": {
+      "sasUri": ""
+    }
+  }
+}

ghinsights/DataFactory/MSMongoDbDump.json

@@ -0,0 +1,61 @@
+{
+  "$schema": "http://datafactories.schema.management.azure.com/schemas/2015-08-01/Microsoft.DataFactory.Table.json",
+  "name": "MSMongoDbDump",
+  "properties": {
+    "type": "AzureBlob",
+    "linkedServiceName": "MSGHTorrentAzureStorage",
+    // "structure": [],
+    "typeProperties": {
+      "folderPath": "msght-azure-storage/downloads/",
+      "fileName": "mongo-dump-{Year}-{Month}-{Day}.tar.gz",
+      "partitionedBy": [
+        {
+          "name": "Year",
+          "value": {
+            "type": "DateTime",
+            "date": "SliceStart",
+            "format": "yyyy"
+          }
+        },
+        {
+          "name": "Month",
+          "value": {
+            "type": "DateTime",
+            "date": "SliceStart",
+            "format": "MM"
+          }
+        },
+        {
+          "name": "Day",
+          "value": {
+            "type": "DateTime",
+            "date": "SliceStart",
+            "format": "dd"
+          }
+        }
+      ]
+      //,"format": {
+      //      "type": "<Two formats are supported: TextFormat, AvroFormat. If the type is 'TextFormat', you can specify the following properties. The type 'Avro' does not require any additional properties>",
+      //      "columnDelimiter": "<The character used as a column separator in a file.This property is optional. The default value is comma (,)>",
+      //      "rowDelimiter": "<The character used as a row separator in a file. This property is optional. The default value is any of the following: (” \n”)>",
+      //      "EscapeChar": "<The character used to escape any special character in the blob content. This property is optional. No default value>",
+      //      "NullValue": "<The character used to represent null value in the blob content. This property is optional. The default value is ” \n”>"
+      //  }
+    },
+    "external": true,
+    "availability": {
+      "frequency": "Day",
+      "interval": 1
+    },
+    "policy": {
+      "validation": {
+        "minimumSizeMB": 0.1
+      },
+      "externalData": {
+        "retryInterval": "01:00:00",
+        "retryTimeout": "00:10:00",
+        "maximumRetry": 10
+      }
+    }
+  }
+}

ghinsights/DataFactory/MSPrestagedEventsAzureStorage.json

@@ -0,0 +1,10 @@
+{
+  "$schema": "http://datafactories.schema.management.azure.com/schemas/2015-08-01/Microsoft.DataFactory.LinkedService.json",
+  "name": "MSPrestagedEventsAzureStorage",
+  "properties": {
+    "type": "AzureStorage",
+    "typeProperties": {
+      "connectionString": ""
+    }
+  }
+}

ghinsights/DataFactory/MongoDbDump.json

@@ -54,7 +54,7 @@
         "externalData": {
           "retryInterval": "01:00:00",
           "retryTimeout": "00:10:00",
-          "maximumRetry": 24
+          "maximumRetry": 10
         }
       }
     }

ghinsights/USQL/ProcessPullRequest.usql

@@ -55,7 +55,7 @@ SELECT	 GHInsights.USql.Utility.GetString(Data, "repo") AS Repo
 		,GHInsights.USql.Utility.GetString(Data, "base.user.login") AS BaseUserLogin
 		,GHInsights.USql.Utility.GetBoolean(Data, "base.user.site_admin") AS BaseUserSiteAdmin
 		,GHInsights.USql.Utility.GetString(Data, "base.user.type") AS BaseUserType
-		,GHInsights.USql.Utility.GetUsqlString(Data, "body") AS Body
+		,GHInsights.USql.Utility.GetUSqlString(Data, "body") AS Body
 		,GHInsights.USql.Utility.GetInteger(Data, "changed_files") AS ChangedFiles
 		,GHInsights.USql.Utility.GetDateTime(Data, "closed_at") AS ClosedAt
 		,GHInsights.USql.Utility.GetInteger(Data, "comments") AS Comments