[mono] Fix assembly name parser to accommodate non-ASCII UTF8 strings (#103363)

Fixes #103276

Added an automated test that the testcase failed in the above issue. It now passes with this change.

Ideally, Mono should share the same assembly name parsing logic as CoreCLR, which is `AssemblyNameParser.TryParse`.

Author: fanyang-mono

src/libraries/System.Runtime/tests/System.Reflection.Tests/GetTypeTests.cs

@@ -300,6 +300,14 @@ public void TestTypeIdentifierAttribute()
             Assert.Equal(42, mi.Invoke(null, args));
         }
 
+        [Fact]
+        public void TestAssemblyNameWithInternationalChar()
+        {
+            Type testObj = typeof(Hello工程123.Program);
+            var t = Type.GetType(testObj.AssemblyQualifiedName);
+            Assert.NotNull(t);
+        }
+
         [Fact]
         public void IgnoreLeadingDotForTypeNamesWithoutNamespace()
         {

src/libraries/System.Runtime/tests/System.Reflection.Tests/Hello工程123/Hello工程123.cs

@@ -0,0 +1,8 @@
+using System;
+
+namespace System.Reflection.Hello工程123
+{
+    public class Program
+    {
+    }
+}

src/libraries/System.Runtime/tests/System.Reflection.Tests/Hello工程123/Hello工程123.csproj

@@ -0,0 +1,8 @@
+<Project Sdk="Microsoft.NET.Sdk">
+    <PropertyGroup>
+        <TargetFramework>$(NetCoreAppCurrent)</TargetFramework>
+    </PropertyGroup>
+    <ItemGroup>
+        <Compile Include="Hello工程123.cs" />
+    </ItemGroup>
+</Project>

src/libraries/System.Runtime/tests/System.Reflection.Tests/System.Reflection.Tests.csproj

@@ -77,6 +77,7 @@
     <ProjectReference Include="UnloadableAssembly\UnloadableAssembly.csproj" />
     <ProjectReference Include="TestExe\System.Reflection.TestExe.csproj" />
     <ProjectReference Include="TestAssembly\TestAssembly.csproj" />
+    <ProjectReference Include="Hello工程123\Hello工程123.csproj" />
   </ItemGroup>
     <ItemGroup Condition="'$(TargetOS)' == 'browser'">
     <WasmFilesToIncludeFromPublishDir Include="$(AssemblyName).dll" />
@@ -87,5 +88,6 @@
 
     <!-- Assemblies that should be excluded from the bundle -->
     <__ExcludeFromBundle Include="TestAssembly.dll" />
+    <__ExcludeFromBundle Include="Hello工程123.dll" />
   </ItemGroup>
 </Project>

src/mono/mono/eglib/eglib-remap.h

@@ -219,6 +219,7 @@
 #define g_wtf8_to_utf16 monoeg_g_wtf8_to_utf16
 #define g_utf8_to_utf16_custom_alloc monoeg_g_utf8_to_utf16_custom_alloc
 #define g_utf8_to_utf16le_custom_alloc monoeg_g_utf8_to_utf16le_custom_alloc
+#define g_utf8_validate_part monoeg_g_utf8_validate_part
 #define g_utf8_validate monoeg_g_utf8_validate
 #define g_vasprintf monoeg_g_vasprintf
 #define g_assertion_disable_global monoeg_assertion_disable_global

src/mono/mono/eglib/glib.h

@@ -1067,6 +1067,7 @@ g_async_safe_printf (gchar const *format, ...)
  */
 extern const guchar g_utf8_jump_table[256];
 
+gboolean  g_utf8_validate_part (const unsigned char *inptr, size_t len);
 gboolean  g_utf8_validate      (const gchar *str, gssize max_len, const gchar **end);
 glong     g_utf8_strlen        (const gchar *str, gssize max);
 

src/mono/mono/eglib/gutf8.c

@@ -30,8 +30,8 @@ const guchar g_utf8_jump_table[256] = {
 	3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3, 4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
 };
 
-static gboolean
-utf8_validate (const unsigned char *inptr, size_t len)
+gboolean
+g_utf8_validate_part (const unsigned char *inptr, size_t len)
 {
 	const unsigned char *ptr = inptr + len;
 	unsigned char c;
@@ -105,7 +105,7 @@ g_utf8_validate (const gchar *str, gssize max_len, const gchar **end)
 	if (max_len < 0) {
 		while (*inptr != 0) {
 			length = g_utf8_jump_table[*inptr];
-			if (!utf8_validate (inptr, length)) {
+			if (!g_utf8_validate_part (inptr, length)) {
 				valid = FALSE;
 				break;
 			}
@@ -124,7 +124,7 @@ g_utf8_validate (const gchar *str, gssize max_len, const gchar **end)
 			length = g_utf8_jump_table[*inptr];
 			min = MIN (length, GSSIZE_TO_UINT (max_len - n));
 
-			if (!utf8_validate (inptr, min)) {
+			if (!g_utf8_validate_part (inptr, min)) {
 				valid = FALSE;
 				break;
 			}

src/mono/mono/metadata/reflection.c

@@ -1548,8 +1548,17 @@ assembly_name_to_aname (MonoAssemblyName *assembly, char *p)
 	}
 	assembly->name = p;
 	s = p;
-	while (*p && (isalnum (*p) || *p == '.' || *p == '-' || *p == '_' || *p == '$' || *p == '@' || g_ascii_isspace (*p)))
-		p++;
+	guchar *inptr = (guchar *) p;
+	while (*p && (*p != ',') && (*p != '\0')) {
+		if (quoted && (*p == '"'))
+			break;
+		guint length = g_utf8_jump_table[*inptr];
+		if (!g_utf8_validate_part (inptr, length)) {
+			return 0;
+		}
+		p += length;
+		inptr += length;
+	}
 	if (quoted) {
 		if (*p != '"')
 			return 1;
@@ -1648,7 +1657,7 @@ assembly_name_to_aname (MonoAssemblyName *assembly, char *p)
 			found_sep = 1;
 			continue;
 		}
-		/* failed */
+		/* Done processing */
 		if (!found_sep)
 			return 1;
 	}