add test for AutoML inferColumn API

src/Microsoft.ML.AutoML/ColumnInference/ColumnInferenceApi.cs

@@ -55,6 +55,7 @@ public static ColumnInferenceResults InferColumns(MLContext context, string path
                 Separators = new[] { splitInference.Separator.Value },
                 AllowSparse = splitInference.AllowSparse,
                 AllowQuoting = splitInference.AllowQuote,
+                ReadMultilines = splitInference.ReadMultilines,
                 HasHeader = hasHeader,
                 TrimWhitespace = trimWhitespace
             };
@@ -91,6 +92,7 @@ public static ColumnInferenceResults InferColumns(MLContext context, string path
                 AllowQuoting = splitInference.AllowQuote,
                 AllowSparse = splitInference.AllowSparse,
                 Separators = new char[] { splitInference.Separator.Value },
+                ReadMultilines = splitInference.ReadMultilines,
                 HasHeader = hasHeader,
                 TrimWhitespace = trimWhitespace
             };
@@ -139,6 +141,7 @@ private static ColumnTypeInference.InferenceResult InferColumnTypes(MLContext co
                     Separator = splitInference.Separator.Value,
                     AllowSparse = splitInference.AllowSparse,
                     AllowQuote = splitInference.AllowQuote,
+                    ReadMultilines = splitInference.ReadMultilines,
                     HasHeader = hasHeader,
                     LabelColumnIndex = labelColumnIndex,
                     Label = label

src/Microsoft.ML.AutoML/ColumnInference/ColumnTypeInference.cs

@@ -32,6 +32,7 @@ internal sealed class Arguments
             public int MaxRowsToRead;
             public uint? LabelColumnIndex;
             public string Label;
+            public bool ReadMultilines;
 
             public Arguments()
             {
@@ -262,6 +263,7 @@ private static InferenceResult InferTextFileColumnTypesCore(MLContext context, I
                 Separators = new[] { args.Separator },
                 AllowSparse = args.AllowSparse,
                 AllowQuoting = args.AllowQuote,
+                ReadMultilines = args.ReadMultilines,
             };
             var textLoader = context.Data.CreateTextLoader(textLoaderOptions);
             var idv = textLoader.Load(fileSource);

src/Microsoft.ML.AutoML/ColumnInference/TextFileContents.cs

@@ -23,14 +23,16 @@ public class ColumnSplitResult
 
             public bool AllowQuote { get; set; }
             public bool AllowSparse { get; set; }
+            public bool  ReadMultilines { get; set; }
 
-            public ColumnSplitResult(bool isSuccess, char? separator, bool allowQuote, bool allowSparse, int columnCount)
+            public ColumnSplitResult(bool isSuccess, char? separator, bool allowQuote, bool readMultilines, bool allowSparse, int columnCount)
             {
                 IsSuccess = isSuccess;
                 Separator = separator;
                 AllowQuote = allowQuote;
                 AllowSparse = allowSparse;
                 ColumnCount = columnCount;
+                ReadMultilines = readMultilines;
             }
         }
 
@@ -78,7 +80,7 @@ from _tryMultiline in tryMultiline
                     break;
                 }
             }
-            return foundAny ? result : new ColumnSplitResult(false, null, true, true, 0);
+            return foundAny ? result : new ColumnSplitResult(false, null, true, true, true, 0);
         }
 
         private static bool TryParseFile(MLContext context, TextLoader.Options options, IMultiStreamSource source,
@@ -114,7 +116,7 @@ private static bool TryParseFile(MLContext context, TextLoader.Options options,
                 // disallow single-column case
                 if (mostCommon.Key <= 1) { return false; }
 
-                result = new ColumnSplitResult(true, options.Separators.First(), options.AllowQuoting, options.AllowSparse, mostCommon.Key);
+                result = new ColumnSplitResult(true, options.Separators.First(), options.AllowQuoting, options.ReadMultilines, options.AllowSparse, mostCommon.Key);
                 return true;
             }
             // fail gracefully if unable to instantiate data view with swept arguments

test/Microsoft.ML.AutoML.Tests/ColumnInferenceTests.cs

@@ -200,5 +200,26 @@ public void TrySplitColumns_should_split_on_dataset_with_newline_between_double_
             result.Separator.Should().Be(',');
             result.IsSuccess.Should().BeTrue();
         }
+
+        [Fact]
+        public void InferColumnsFromMultilineInputFile()
+        {
+            // Check if we can infer the column information
+            // from and input file which has escaped newlines inside quotes
+            var dataPath = GetDataPath("multiline.csv");
+            MLContext mlContext = new MLContext();
+            var inputColumnInformation = new ColumnInformation();
+            inputColumnInformation.LabelColumnName = @"id";
+            var result = mlContext.Auto().InferColumns(dataPath, inputColumnInformation);
+
+            // File only have 3 columns: "id", "description" and "animal"
+            Assert.NotNull(result.ColumnInformation.LabelColumnName);
+            Assert.Equal(1, result.ColumnInformation.TextColumnNames.Count);
+            Assert.Equal(1, result.ColumnInformation.CategoricalColumnNames.Count);
+
+            Assert.Equal("id", result.ColumnInformation.LabelColumnName);
+            Assert.Equal("description", result.ColumnInformation.TextColumnNames.First());
+            Assert.Equal("animal", result.ColumnInformation.CategoricalColumnNames.First());
+        }
     }
 }