BaseTools/Tests: Verify 32-bit UTF-8 chars are rejected

Since UTF-8 .uni unicode files might contain strings with unicode code
points larger than 16-bits, and UEFI only supports UCS-2 characters,
we need to make sure that BaseTools rejects these characters in UTF-8
.uni source files.

Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Michael D Kinney <michael.d.kinney@intel.com>
Reviewed-by: Yingke Liu <yingke.d.liu@intel.com>

git-svn-id: https://svn.code.sf.net/p/edk2/code/trunk/edk2@17697 6f19259b-4bc3-4df7-8a09-765794883524

BaseTools/Tests/CheckUnicodeSourceFiles.py

@@ -114,6 +114,31 @@ class Tests(TestTools.BaseToolsTest):
 
         self.CheckFile(encoding=None, shouldPass=False, string=data)
 
+    def test32bitUnicodeCharInUtf8File(self):
+        data = u'''
+            #langdef en-US "English"
+            #string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF"
+        '''
+
+        self.CheckFile('utf_16', shouldPass=False, string=data)
+
+    def test32bitUnicodeCharInUtf8File(self):
+        data = u'''
+            #langdef en-US "English"
+            #string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF"
+        '''
+
+        self.CheckFile('utf_8', shouldPass=False, string=data)
+
+    def test32bitUnicodeCharInUtf8Comment(self):
+        data = u'''
+            // Even in comments, we reject non-UCS-2 chars: \U00010300
+            #langdef en-US "English"
+            #string STR_A #language en-US "A"
+        '''
+
+        self.CheckFile('utf_8', shouldPass=False, string=data)
+
 TheTestSuite = TestTools.MakeTheTestSuite(locals())
 
 if __name__ == '__main__':