\r
self.CheckFile(encoding=None, shouldPass=False, string=data)\r
\r
+ def testValidUtf8File(self):\r
+ self.CheckFile(encoding='utf_8', shouldPass=True)\r
+\r
+ def testValidUtf8FileWithBom(self):\r
+ #\r
+ # Same test as testValidUtf8File, but add the UTF-8 BOM\r
+ #\r
+ data = codecs.BOM_UTF8 + codecs.encode(self.SampleData, 'utf_8')\r
+\r
+ self.CheckFile(encoding=None, shouldPass=True, string=data)\r
+\r
def test32bitUnicodeCharInUtf8File(self):\r
data = u'''\r
#langdef en-US "English"\r
\r
self.CheckFile('utf_8', shouldPass=False, string=data)\r
\r
+ def testSurrogatePairUnicodeCharInUtf8File(self):\r
+ #\r
+ # Surrogate Pair code points are used in UTF-16 files to\r
+ # encode the Supplementary Plane characters. In UTF-8, it is\r
+ # trivial to encode these code points, but they are not valid\r
+ # code points for characters, since they are reserved for the\r
+ # UTF-16 Surrogate Pairs.\r
+ #\r
+ # This test makes sure that BaseTools rejects these characters\r
+ # if seen in a .uni file.\r
+ #\r
+ data = '\xed\xa0\x81'\r
+\r
+ self.CheckFile(encoding=None, shouldPass=False, string=data)\r
+\r
+ def testSurrogatePairUnicodeCharInUtf8FileWithBom(self):\r
+ #\r
+ # Same test as testSurrogatePairUnicodeCharInUtf8File, but add\r
+ # the UTF-8 BOM\r
+ #\r
+ data = codecs.BOM_UTF8 + '\xed\xa0\x81'\r
+\r
+ self.CheckFile(encoding=None, shouldPass=False, string=data)\r
+\r
TheTestSuite = TestTools.MakeTheTestSuite(locals())\r
\r
if __name__ == '__main__':\r