cpplint_unittest.py 文件源码

def testInvalidUtf8(self):
    def DoTest(self, raw_bytes, has_invalid_utf8):
      error_collector = ErrorCollector(self.assert_)
      cpplint.ProcessFileData(
          'foo.cc', 'cc',
          unicode(raw_bytes, 'utf8', 'replace').split('\n'),
          error_collector)
      # The warning appears only once.
      self.assertEquals(
          int(has_invalid_utf8),
          error_collector.Results().count(
              'Line contains invalid UTF-8'
              ' (or Unicode replacement character).'
              '  [readability/utf8] [5]'))

    DoTest(self, 'Hello world\n', False)
    DoTest(self, '\xe9\x8e\xbd\n', False)
    DoTest(self, '\xe9x\x8e\xbd\n', True)
    # This is the encoding of the replacement character itself (which
    # you can see by evaluating codecs.getencoder('utf8')(u'\ufffd')).
    DoTest(self, '\xef\xbf\xbd\n', True)