Throw exception when reaching EOF without ending quote on a given field.

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoaderCursor.cs

@@ -472,7 +472,7 @@ private static class MultiLineReader
                     // When reading lines that contain quoted fields, the quoted fields can contain
                     // '\n' so we we'll need to read multiple lines (multilines) to get all the fields
                     // of a given row.
-                    public static string ReadMultiLine(TextReader sr, StringBuilder sb, bool ignoreHashLine)
+                    public static string ReadMultiLine(TextReader sr, StringBuilder sb, long lineNum, bool ignoreHashLine)
                     {
                         string line;
                         line = sr.ReadLine();
@@ -503,7 +503,7 @@ public static string ReadMultiLine(TextReader sr, StringBuilder sb, bool ignoreH
                             line = sr.ReadLine();
 
                             if (line == null) // If we've reached the end of the file
-                                break; // MYTODO: This could happen if we have an invalid open quote which never closes so we reach the end of the file without properly closing the field, should we throw instead in this case?
+                                throw new EndOfStreamException($"A quote opened on a field on line {lineNum} was never closed, and we've read to the last line in the file without finding the closing quote");
 
                             sb.Append("\n");
                             sb.Append(line);
@@ -549,7 +549,7 @@ private void ThreadProc()
                                     // introducing a CharSpan type (similar to ReadOnlyMemory but based on char[] or StringBuilder)
                                     // and implementing all the necessary conversion functionality on it. See task 3871.
                                     if (_readMultilines)
-                                        text = MultiLineReader.ReadMultiLine(rdr, multilineSB, true);
+                                        text = MultiLineReader.ReadMultiLine(rdr, multilineSB, line, true);
                                     else
                                         text = rdr.ReadLine();
 
@@ -580,7 +580,7 @@ private void ThreadProc()
                                         return;
 
                                     if (_readMultilines)
-                                        text = MultiLineReader.ReadMultiLine(rdr, multilineSB, true);
+                                        text = MultiLineReader.ReadMultiLine(rdr, multilineSB, line, false);
                                     else
                                         text = rdr.ReadLine();
 

test/Microsoft.ML.Tests/TextLoaderTests.cs

@@ -1013,5 +1013,54 @@ public void TestLoadTextWithEscapedNewLines(bool useSaved)
                 }
             }
         }
+
+        [Fact]
+        public void TestInvalidMultilineCSVQuote()
+        {
+            var mlContext = new MLContext(seed: 1);
+
+            string badInputCsv =
+                "id,description,animal\n" +
+                "9,\"this is a quoted field correctly formatted\",cat\n" +
+                "10,\"this is a quoted field\nwithout closing quote,cat\n" +
+                "11,this field isn't quoted,dog\n" +
+                "12,this will reach the end of the file without finding a closing quote so it will throw,frog\n"
+                ;
+
+            var filePath = GetOutputPath("multiline-invalid.csv");
+            File.WriteAllText(filePath, badInputCsv);
+
+            bool threwException = false;
+            try
+            {
+                var options = new TextLoader.Options()
+                {
+                    HasHeader = true,
+                    Separator = ",",
+                    AllowQuoting = true,
+                    ReadMultilines = true,
+                    Columns = new[]
+                    {
+                    new TextLoader.Column("id", DataKind.Int32, 0),
+                    new TextLoader.Column("description", DataKind.String, 1),
+                    new TextLoader.Column("animal", DataKind.String, 2),
+                },
+                };
+
+                var data = mlContext.Data.LoadFromTextFile(filePath, options);
+
+                data.Preview();
+            }
+            catch(EndOfStreamException)
+            {
+                threwException = true;
+            }
+            catch(FormatException)
+            {
+                threwException = true;
+            }
+
+            Assert.True(threwException, "Invalid file should have thrown an exception");
+        }
     }
 }