Method test_ucs4

Lib/test/test_capi/test_unicode.py:1938–1975

(self)

                         "latin1=\xE9-euro=\u20AC-max=\U0010ffff-zeroes=\0\0\0.")

    def test_ucs4(self):
        encoding = 'utf-32le' if sys.byteorder == 'little' else 'utf-32be'

        writer = self.create_writer(0)
        writer.write_ucs4("ascii IGNORED".encode(encoding), 5)
        writer.write_char(ord("-"))
        writer.write_ucs4("latin1=\xe9".encode(encoding))
        writer.write_char(ord("-"))
        writer.write_ucs4("euro=\u20ac".encode(encoding))
        writer.write_char(ord("-"))
        writer.write_ucs4("max=\U0010ffff".encode(encoding))
        writer.write_char(ord("."))
        self.assertEqual(writer.finish(),
                         "ascii-latin1=\xE9-euro=\u20AC-max=\U0010ffff.")

        # Test some special characters
        writer = self.create_writer(0)
        # Lone surrogate character
        writer.write_ucs4("lone\uDC80".encode(encoding, 'surrogatepass'))
        writer.write_char(ord("-"))
        # Surrogate pair
        writer.write_ucs4("pair\uD83D\uDC0D".encode(encoding, 'surrogatepass'))
        writer.write_char(ord("-"))
        writer.write_ucs4("null[\0]".encode(encoding), 7)
        invalid = (b'\x00\x00\x11\x00' if sys.byteorder == 'little' else
                   b'\x00\x11\x00\x00')
        # CRASHES writer.write_ucs4("invalid".encode(encoding) + invalid)
        writer.write_ucs4(NULL, 0)
        # CRASHES writer.write_ucs4(NULL, 1)
        self.assertEqual(writer.finish(),
                         "lone\udc80-pair\ud83d\udc0d-null[\x00]")

        # invalid size
        writer = self.create_writer(0)
        with self.assertRaises(ValueError):
            writer.write_ucs4("text".encode(encoding), -1)
        self.assertRaises(ValueError, writer.write_ucs4, b'', -1)
        self.assertRaises(ValueError, writer.write_ucs4, NULL, -1)

    def test_substring_empty(self):
        writer = self.create_writer(0)