+ def testSupplementaryPlaneUnicodeCharInUtf16File(self):\r
+ #\r
+ # Supplementary Plane characters can exist in UTF-16 files,\r
+ # but they are not valid UCS-2 characters.\r
+ #\r
+ # This test makes sure that BaseTools rejects these characters\r
+ # if seen in a .uni file.\r
+ #\r
+ data = u'''\r
+ #langdef en-US "English"\r
+ #string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF"\r
+ '''\r
+\r
+ self.CheckFile('utf_16', shouldPass=False, string=data)\r
+\r
+ def testSurrogatePairUnicodeCharInUtf16File(self):\r
+ #\r
+ # Surrogate Pair code points are used in UTF-16 files to\r
+ # encode the Supplementary Plane characters. But, a Surrogate\r
+ # Pair code point which is not followed by another Surrogate\r
+ # Pair code point might be interpreted as a single code point\r
+ # with the Surrogate Pair code point.\r
+ #\r
+ # This test makes sure that BaseTools rejects these characters\r
+ # if seen in a .uni file.\r
+ #\r
+ data = codecs.BOM_UTF16_LE + '//\x01\xd8 '\r
+\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
+ #string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF"\r
+ '''\r
+\r
+ self.CheckFile('utf_16', shouldPass=False, string=data)\r
+\r
+ def test32bitUnicodeCharInUtf8File(self):\r
+ data = u'''\r
+ #langdef en-US "English"\r
+ #string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF"\r
+ '''\r
+\r
+ self.CheckFile('utf_8', shouldPass=False, string=data)\r
+\r
+ def test32bitUnicodeCharInUtf8Comment(self):\r
+ data = u'''\r
+ // Even in comments, we reject non-UCS-2 chars: \U00010300\r
+ #langdef en-US "English"\r
+ #string STR_A #language en-US "A"\r
+ '''\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