X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=BaseTools%2FTests%2FCheckUnicodeSourceFiles.py;h=6ae62f180a840090141d4fdf23aafe0e3a7e99c8;hb=156d6d65a5ac1e31d36381b7726c42066891a845;hp=ad5fd189639d620f78c58da0900a02ddfdea10c4;hpb=dadfab5b23c3f02ab8396a5487122de797188845;p=mirror_edk2.git

diff --git a/BaseTools/Tests/CheckUnicodeSourceFiles.py b/BaseTools/Tests/CheckUnicodeSourceFiles.py
index ad5fd18963..6ae62f180a 100644
--- a/BaseTools/Tests/CheckUnicodeSourceFiles.py
+++ b/BaseTools/Tests/CheckUnicodeSourceFiles.py
@@ -114,6 +114,66 @@ class Tests(TestTools.BaseToolsTest):
 
         self.CheckFile(encoding=None, shouldPass=False, string=data)
 
+    def testValidUtf8File(self):
+        self.CheckFile(encoding='utf_8', shouldPass=True)
+
+    def testValidUtf8FileWithBom(self):
+        #
+        # Same test as testValidUtf8File, but add the UTF-8 BOM
+        #
+        data = codecs.BOM_UTF8 + codecs.encode(self.SampleData, 'utf_8')
+
+        self.CheckFile(encoding=None, shouldPass=True, 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)
+
+    def testSurrogatePairUnicodeCharInUtf8File(self):
+        #
+        # Surrogate Pair code points are used in UTF-16 files to
+        # encode the Supplementary Plane characters. In UTF-8, it is
+        # trivial to encode these code points, but they are not valid
+        # code points for characters, since they are reserved for the
+        # UTF-16 Surrogate Pairs.
+        #
+        # This test makes sure that BaseTools rejects these characters
+        # if seen in a .uni file.
+        #
+        data = '\xed\xa0\x81'
+
+        self.CheckFile(encoding=None, shouldPass=False, string=data)
+
+    def testSurrogatePairUnicodeCharInUtf8FileWithBom(self):
+        #
+        # Same test as testSurrogatePairUnicodeCharInUtf8File, but add
+        # the UTF-8 BOM
+        #
+        data = codecs.BOM_UTF8 + '\xed\xa0\x81'
+
+        self.CheckFile(encoding=None, shouldPass=False, string=data)
+
 TheTestSuite = TestTools.MakeTheTestSuite(locals())
 
 if __name__ == '__main__':