Expose offset on TomlException

Author: xoofx

src/Tomlyn.Tests/NewApiExceptionLocationTests.cs

@@ -1,4 +1,5 @@
 using NUnit.Framework;
+using Tomlyn.Parsing;
 using Tomlyn.Serialization;
 
 namespace Tomlyn.Tests;
@@ -38,4 +39,27 @@ public void Parse_SyntaxError_IncludesLocation()
         Assert.That(ex.Column, Is.GreaterThan(0));
         Assert.That(ex.Message, Does.Contain("test.toml("));
     }
+
+    [Test]
+    public void Parse_InvalidUtf8_IncludesByteOffset()
+    {
+        // "a = " followed by an invalid UTF-8 sequence: 0xC3 0x28
+        var bytes = new byte[] { (byte)'a', (byte)' ', (byte)'=', (byte)' ', 0xC3, 0x28, (byte)'\n' };
+        var options = new TomlSerializerOptions { SourceName = "utf8.toml" };
+
+        var parser = TomlParser.Create(bytes, options);
+        var ex = Assert.Throws<TomlException>(() =>
+        {
+            while (parser.MoveNext())
+            {
+            }
+        });
+
+        Assert.That(ex, Is.Not.Null);
+        Assert.That(ex!.Span.HasValue, Is.True);
+        Assert.That(ex.Offset, Is.EqualTo(4));
+        Assert.That(ex.Line, Is.EqualTo(1));
+        Assert.That(ex.Column, Is.EqualTo(5));
+        Assert.That(ex.Message, Does.Contain("utf8.toml("));
+    }
 }

src/Tomlyn/TomlException.cs

@@ -72,6 +72,14 @@ public TomlException(TomlSourceSpan span, string message, Exception? innerExcept
     /// </summary>
     public int Column => Span?.Start.Column + 1 ?? 0;
 
+    /// <summary>
+    /// Gets the 0-based offset associated with this exception, or 0 when unknown.
+    /// </summary>
+    /// <remarks>
+    /// When parsing UTF-8 inputs, this offset represents a byte offset. When parsing string inputs, this offset represents a character offset.
+    /// </remarks>
+    public int Offset => Span?.Offset ?? 0;
+
     private static string Format(TomlSourceSpan span, string message)
     {
         return $"{span.ToStringSimple()} : error : {message}";