Fix windows-1252 encoding not working on net6.0 and 8.0

src/UglyToad.PdfPig.Tests/Integration/EncodingsTests.cs

@@ -5,6 +5,22 @@
 
     public class EncodingsTests
     {
+        [Fact]
+        public void Windows1252Encoding()
+        {
+            string path = IntegrationHelpers.GetDocumentPath("GHOSTSCRIPT-698363-0.pdf");
+            using (var document = PdfDocument.Open(path))
+            {
+                var page = document.GetPage(1);
+                string actual = string.Concat(page.Letters.Select(l => l.Value));
+
+                // The expected string value is just here to make sure we have the same results across net versions.
+                // Feel free to correct/update it if chars are not actually correct.
+                string expected = "ҘҹЧѥЧКጹѝঐܮ̂ҥ҇ҁӃ࿋\u0c0dҀғҊ˺෨ཌආр෨ཌ̂ҘҹЧѥЧКጹѝঐܮ̂ҥ҇ҁӃ࿋\u0c0dҀғҊ˺෨ཌආр෨ཌ̂ݰႺംࢥ༢࣭\u089aѽ̔ҫһҐ̔ݰႺംࢥ༢࣭\u089aѽ̔ҫһҐ̔";
+                Assert.Equal(expected, actual);
+            }
+        }
+
         [Fact]
         public void Issue688()
         {

src/UglyToad.PdfPig.Tests/Integration/IntegrationDocumentTests.cs

@@ -3,10 +3,11 @@
     public class IntegrationDocumentTests
     {
         private static readonly Lazy<string> DocumentFolder = new Lazy<string>(() => Path.GetFullPath(Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "..", "..", "..", "Integration", "Documents")));
-        private static readonly HashSet<string> _documentsToIgnore = new HashSet<string>()
-        {
-            "issue_671.pdf"
-        };
+        private static readonly HashSet<string> _documentsToIgnore =
+        [
+            "issue_671.pdf",
+            "GHOSTSCRIPT-698363-0.pdf"
+        ];
 
         [Theory]
         [MemberData(nameof(GetAllDocuments))]

src/UglyToad.PdfPig.Tokenization/NameTokenizer.cs

@@ -11,6 +11,13 @@
 
     internal class NameTokenizer : ITokenizer
     {
+        static NameTokenizer()
+        {
+#if NET6_0_OR_GREATER
+            Encoding.RegisterProvider(CodePagesEncodingProvider.Instance);
+#endif
+        }
+
         public bool ReadsNextByte { get; } = true;
 
         public bool TryTokenize(byte currentByte, IInputBytes inputBytes, out IToken token)