Supplementary Plane characters can exist in UTF-16 files, but they are not valid UCS-2 characters.
For example, this python interpreter code: >>> import codecs >>> codecs.encode(u'\U00010300', 'utf-16') '\xff\xfe\x00\xd8\x00\xdf' Therefore the UCS-4 0x00010300 character is encoded as two 16-bit numbers (0xd800 0xdf00) in a little endian UTF-16 file. For more information, see: http://en.wikipedia.org/wiki/UTF-16#U.2B10000_to_U.2B10FFFF This test checks to make sure that BaseTools will reject these characters in UTF-16 files. The range of 0xd800 - 0xdfff should also be rejected as unicode code points because they are reserved for the surrogate pair usage in UTF-16 files. This test was fixed by the previous commit: "BaseTools/UniClassObject: Verify valid UCS-2 chars in UTF-16 .uni files" Contributed-under: TianoCore Contribution Agreement 1.0 Signed-off-by: Jordan Justen <jordan.l.jus...@intel.com> Cc: Yingke D Liu <yingke.d....@intel.com> Cc: Michael D Kinney <michael.d.kin...@intel.com> Cc: Laszlo Ersek <ler...@redhat.com> --- BaseTools/Tests/CheckUnicodeSourceFiles.py | 35 +++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) diff --git a/BaseTools/Tests/CheckUnicodeSourceFiles.py b/BaseTools/Tests/CheckUnicodeSourceFiles.py index 0083ad8..ad5fd18 100644 --- a/BaseTools/Tests/CheckUnicodeSourceFiles.py +++ b/BaseTools/Tests/CheckUnicodeSourceFiles.py @@ -38,7 +38,10 @@ class Tests(TestTools.BaseToolsTest): def EncodeToFile(self, encoding, string=None): if string is None: string = self.SampleData - data = codecs.encode(string, encoding) + if encoding is not None: + data = codecs.encode(string, encoding) + else: + data = string path = 'input.uni' self.WriteTmpFile(path, data) return PathClass(self.GetTmpFilePath(path)) @@ -81,6 +84,36 @@ class Tests(TestTools.BaseToolsTest): def testUtf16InUniFile(self): self.CheckFile('utf_16', shouldPass=True) + def testSupplementaryPlaneUnicodeCharInUtf16File(self): + # + # Supplementary Plane characters can exist in UTF-16 files, + # but they are not valid UCS-2 characters. + # + # This test makes sure that BaseTools rejects these characters + # if seen in a .uni file. + # + data = u''' + #langdef en-US "English" + #string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF" + ''' + + self.CheckFile('utf_16', shouldPass=False, string=data) + + def testSurrogatePairUnicodeCharInUtf16File(self): + # + # Surrogate Pair code points are used in UTF-16 files to + # encode the Supplementary Plane characters. But, a Surrogate + # Pair code point which is not followed by another Surrogate + # Pair code point might be interpreted as a single code point + # with the Surrogate Pair code point. + # + # This test makes sure that BaseTools rejects these characters + # if seen in a .uni file. + # + data = codecs.BOM_UTF16_LE + '//\x01\xd8 ' + + self.CheckFile(encoding=None, shouldPass=False, string=data) + TheTestSuite = TestTools.MakeTheTestSuite(locals()) if __name__ == '__main__': -- 2.1.4 ------------------------------------------------------------------------------ _______________________________________________ edk2-devel mailing list edk2-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/edk2-devel
