Issue 19 adopt dotnet format

.github/workflows/format.yml

@@ -0,0 +1,24 @@
+name: Check formatting
+
+on:
+  pull_request:
+  push:
+    branches: [ main ]
+
+jobs:
+  format:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup .NET
+        uses: actions/setup-dotnet@v3
+        with:
+          global-json-file: global.json
+
+      - name: Verify code formatting
+        run: |
+          dotnet format src/csharp/Microsoft.Spark.sln --verify-no-changes
+          dotnet format examples/Microsoft.Spark.Examples.sln --verify-no-changes
+          dotnet format benchmark/csharp/Microsoft.Spark.Benchmark.sln --verify-no-changes

benchmark/csharp/Tpch/VectorFunctions.intrinsics.cs

@@ -71,7 +71,7 @@ internal static unsafe DoubleArray ComputeDiscountPrice(DoubleArray price, Doubl
             fixed (double* pBuffer = buffer)
             {
                 Vector256<double> ones = Vector256.Create(1.0);
-                
+
                 int i = 0;
                 for (; i < vectorizationLength; i += 4)
                 {

examples/Microsoft.Spark.CSharp.Examples/Sql/Batch/Basic.cs

@@ -108,7 +108,7 @@ public void Run(string[] args)
 
             DataFrame joinedDf3 = df.Join(df, df["name"] == df["name"], "outer");
             joinedDf3.Show();
-            
+
             // Union of two data frames
             DataFrame unionDf = df.Union(df);
             unionDf.Show();

examples/Microsoft.Spark.CSharp.Examples/Sql/Batch/Datasource.cs

@@ -20,7 +20,7 @@ public void Run(string[] args)
             {
                 Console.Error.WriteLine(
                     "Usage: Datasource <path to SPARK_HOME/examples/src/main/resources/>");
-                
+
                 Environment.Exit(1);
             }
 
@@ -92,11 +92,11 @@ private void RunDatasourceExample(SparkSession spark)
         private void RunParquetExample(SparkSession spark, string json)
         {
             DataFrame peopleDf = spark.Read().Json(json);
-        
+
             peopleDf.Write().Mode(SaveMode.Overwrite).Parquet("people.parquet");
 
             DataFrame parquetFile = spark.Read().Parquet("people.parquet");
-            
+
             parquetFile.CreateTempView("parquet");
 
             DataFrame teenagers = spark.Sql(

examples/Microsoft.Spark.CSharp.Examples/Sql/Streaming/StructuredNetworkCharacterCount.cs

@@ -54,7 +54,7 @@ public void Run(string[] args)
                 .WriteStream()
                 .Format("console")
                 .Start();
-                
+
             query.AwaitTermination();
         }
     }

src/csharp/Extensions/Microsoft.Spark.Extensions.DotNet.Interactive.UnitTest/PackageResolverTests.cs

@@ -33,7 +33,7 @@ public void TestPackageResolver()
             using (File.Create(nugetFile.FullName))
             {
             }
-            
+
             var assemblyPaths = new string[]
             {
                 Path.Combine(packageFrameworkPath, "1.dll"),
@@ -51,7 +51,7 @@ public void TestPackageResolver()
                         packageVersion,
                         assemblyPaths,
                         packageRootPath,
-                        probingPaths) 
+                        probingPaths)
                 });
 
             var packageResolver = new PackageResolver(mockSupportNugetWrapper.Object);

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs

@@ -55,16 +55,16 @@ public void TestBucketizer()
             Assert.Equal(expectedInputCol, bucketizer.GetInputCol());
             Assert.Equal(expectedOutputCol, bucketizer.GetOutputCol());
             Assert.Equal(expectedSplits, bucketizer.GetSplits());
-            
+
             using (var tempDirectory = new TemporaryDirectory())
             {
                 string savePath = Path.Join(tempDirectory.Path, "bucket");
                 bucketizer.Save(savePath);
-                
+
                 Bucketizer loadedBucketizer = Bucketizer.Load(savePath);
                 Assert.Equal(bucketizer.Uid(), loadedBucketizer.Uid());
             }
-            
+
             TestFeatureBase(bucketizer, "handleInvalid", "keep");
         }
 

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs

@@ -31,12 +31,12 @@ public void TestCountVectorizerModel()
         {
             DataFrame input = _spark.Sql("SELECT array('hello', 'I', 'AM', 'a', 'string', 'TO', " +
                 "'TOKENIZE') as input from range(100)");
-            
+
             const string inputColumn = "input";
             const string outputColumn = "output";
             const double minTf = 10.0;
             const bool binary = false;
-            
+
             var vocabulary = new List<string>()
             {
                 "hello",
@@ -45,17 +45,17 @@ public void TestCountVectorizerModel()
                 "TO",
                 "TOKENIZE"
             };
-            
+
             var countVectorizerModel = new CountVectorizerModel(vocabulary);
-            
+
             Assert.IsType<CountVectorizerModel>(new CountVectorizerModel("my-uid", vocabulary));
-            
+
             countVectorizerModel = countVectorizerModel
                 .SetInputCol(inputColumn)
                 .SetOutputCol(outputColumn)
                 .SetMinTF(minTf)
                 .SetBinary(binary);
-            
+
             Assert.Equal(inputColumn, countVectorizerModel.GetInputCol());
             Assert.Equal(outputColumn, countVectorizerModel.GetOutputCol());
             Assert.Equal(minTf, countVectorizerModel.GetMinTF());
@@ -64,7 +64,7 @@ public void TestCountVectorizerModel()
             {
                 string savePath = Path.Join(tempDirectory.Path, "countVectorizerModel");
                 countVectorizerModel.Save(savePath);
-                
+
                 CountVectorizerModel loadedModel = CountVectorizerModel.Load(savePath);
                 Assert.Equal(countVectorizerModel.Uid(), loadedModel.Uid());
             }
@@ -75,8 +75,8 @@ public void TestCountVectorizerModel()
 
             Assert.IsType<StructType>(countVectorizerModel.TransformSchema(input.Schema()));
             Assert.IsType<DataFrame>(countVectorizerModel.Transform(input));
-            
+
             TestFeatureBase(countVectorizerModel, "minDF", 100);
-        } 
+        }
     }
 }

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs

@@ -38,16 +38,16 @@ public void TestCountVectorizer()
             const double minTf = 10;
             const int vocabSize = 10000;
             const bool binary = false;
-            
+
             var countVectorizer = new CountVectorizer();
-            
+
             countVectorizer
                 .SetInputCol(inputColumn)
                 .SetOutputCol(outputColumn)
                 .SetMinDF(minDf)
                 .SetMinTF(minTf)
                 .SetVocabSize(vocabSize);
-                
+
             Assert.IsType<CountVectorizerModel>(countVectorizer.Fit(input));
             Assert.Equal(inputColumn, countVectorizer.GetInputCol());
             Assert.Equal(outputColumn, countVectorizer.GetOutputCol());
@@ -60,17 +60,17 @@ public void TestCountVectorizer()
             {
                 string savePath = Path.Join(tempDirectory.Path, "countVectorizer");
                 countVectorizer.Save(savePath);
-                
+
                 CountVectorizer loadedVectorizer = CountVectorizer.Load(savePath);
                 Assert.Equal(countVectorizer.Uid(), loadedVectorizer.Uid());
             }
-            
+
             Assert.NotEmpty(countVectorizer.ExplainParams());
             Assert.NotEmpty(countVectorizer.ToString());
-            
+
             TestFeatureBase(countVectorizer, "minDF", 0.4);
         }
-        
+
         /// <summary>
         /// Test signatures for APIs introduced in Spark 2.4.*.
         /// </summary>

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs

@@ -17,20 +17,20 @@ protected FeatureBaseTests(SparkFixture fixture)
         {
             _spark = fixture.Spark;
         }
-        
+
         /// <summary>
         /// Tests the common functionality across all ML.Feature classes.
         /// </summary>
         /// <param name="testObject">The object that implemented FeatureBase</param>
         /// <param name="paramName">The name of a parameter that can be set on this object</param>
         /// <param name="paramValue">A parameter value that can be set on this object</param>
         public void TestFeatureBase(
-            Params testObject, 
-            string paramName, 
+            Params testObject,
+            string paramName,
             object paramValue)
         {
             Assert.NotEmpty(testObject.ExplainParams());
-            
+
             Param param = testObject.GetParam(paramName);
             Assert.NotEmpty(param.Doc);
             Assert.NotEmpty(param.Name);

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs

@@ -28,7 +28,7 @@ public void TestHashingTF()
             int expectedFeatures = 10;
 
             Assert.IsType<HashingTF>(new HashingTF());
-            
+
             HashingTF hashingTf = new HashingTF("my-unique-id")
                 .SetNumFeatures(expectedFeatures)
                 .SetInputCol(expectedInputCol)
@@ -43,21 +43,21 @@ public void TestHashingTF()
 
             DataFrame output = hashingTf.Transform(input);
             DataFrame outputVector = output.Select(expectedOutputCol);
-            
+
             Assert.Contains(expectedOutputCol, outputVector.Columns());
-       
+
             using (var tempDirectory = new TemporaryDirectory())
             {
                 string savePath = Path.Join(tempDirectory.Path, "hashingTF");
                 hashingTf.Save(savePath);
-                
+
                 HashingTF loadedHashingTf = HashingTF.Load(savePath);
                 Assert.Equal(hashingTf.Uid(), loadedHashingTf.Uid());
             }
 
             hashingTf.SetBinary(true);
             Assert.True(hashingTf.GetBinary());
-            
+
             TestFeatureBase(hashingTf, "numFeatures", 1000);
         }
     }

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs

@@ -26,14 +26,14 @@ public void TestIDFModel()
             int expectedDocFrequency = 1980;
             string expectedInputCol = "rawFeatures";
             string expectedOutputCol = "features";
-            
+
             DataFrame sentenceData =
                 _spark.Sql("SELECT 0.0 as label, 'Hi I heard about Spark' as sentence");
-            
+
             Tokenizer tokenizer = new Tokenizer()
                 .SetInputCol("sentence")
                 .SetOutputCol("words");
-            
+
             DataFrame wordsData = tokenizer.Transform(sentenceData);
 
             HashingTF hashingTF = new HashingTF()
@@ -42,21 +42,21 @@ public void TestIDFModel()
                 .SetNumFeatures(20);
 
             DataFrame featurizedData = hashingTF.Transform(wordsData);
-    
+
             IDF idf = new IDF()
                 .SetInputCol(expectedInputCol)
                 .SetOutputCol(expectedOutputCol)
                 .SetMinDocFreq(expectedDocFrequency);
-            
+
             IDFModel idfModel = idf.Fit(featurizedData);
 
             DataFrame rescaledData = idfModel.Transform(featurizedData);
             Assert.Contains(expectedOutputCol, rescaledData.Columns());
-            
+
             Assert.Equal(expectedInputCol, idfModel.GetInputCol());
             Assert.Equal(expectedOutputCol, idfModel.GetOutputCol());
             Assert.Equal(expectedDocFrequency, idfModel.GetMinDocFreq());
-            
+
             using (var tempDirectory = new TemporaryDirectory())
             {
                 string modelPath = Path.Join(tempDirectory.Path, "idfModel");
@@ -65,7 +65,7 @@ public void TestIDFModel()
                 IDFModel loadedModel = IDFModel.Load(modelPath);
                 Assert.Equal(idfModel.Uid(), loadedModel.Uid());
             }
-            
+
             TestFeatureBase(idfModel, "minDocFreq", 1000);
         }
     }

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs

@@ -26,25 +26,25 @@ public void TestIDFModel()
             string expectedInputCol = "rawFeatures";
             string expectedOutputCol = "features";
             int expectedDocFrequency = 100;
-            
+
             IDF idf = new IDF()
                 .SetInputCol(expectedInputCol)
                 .SetOutputCol(expectedOutputCol)
                 .SetMinDocFreq(expectedDocFrequency);
-            
+
             Assert.Equal(expectedInputCol, idf.GetInputCol());
             Assert.Equal(expectedOutputCol, idf.GetOutputCol());
             Assert.Equal(expectedDocFrequency, idf.GetMinDocFreq());
-            
+
             using (var tempDirectory = new TemporaryDirectory())
             {
                 string savePath = Path.Join(tempDirectory.Path, "IDF");
                 idf.Save(savePath);
-                
+
                 IDF loadedIdf = IDF.Load(savePath);
                 Assert.Equal(idf.Uid(), loadedIdf.Uid());
             }
-            
+
             TestFeatureBase(idf, "minDocFreq", 1000);
         }
     }

src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/PipelineModelTests.cs

@@ -5,8 +5,8 @@
 using System.IO;
 using Microsoft.Spark.ML.Feature;
 using Microsoft.Spark.Sql;
-using Microsoft.Spark.UnitTest.TestUtils;
 using Microsoft.Spark.Sql.Types;
+using Microsoft.Spark.UnitTest.TestUtils;
 using Xunit;
 
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
@@ -59,7 +59,7 @@ public void TestPipelineModelTransform()
 
             Assert.IsType<StructType>(pipelineModel.TransformSchema(input.Schema()));
             Assert.IsType<DataFrame>(output);
-            
+
             using (var tempDirectory = new TemporaryDirectory())
             {
                 string savePath = Path.Join(tempDirectory.Path, "pipelineModel");