reader.py 文件源码

def determine_encoding(self):
        # type: () -> None
        while not self.eof and (self.raw_buffer is None or
                                len(self.raw_buffer) < 2):
            self.update_raw()
        if isinstance(self.raw_buffer, binary_type):
            if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
                self.raw_decode = codecs.utf_16_le_decode  # type: ignore
                self.encoding = 'utf-16-le'
            elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
                self.raw_decode = codecs.utf_16_be_decode  # type: ignore
                self.encoding = 'utf-16-be'
            else:
                self.raw_decode = codecs.utf_8_decode  # type: ignore
                self.encoding = 'utf-8'
        self.update(1)

    # 4 if 32 bit unicode supported, 2 e.g. on MacOS (issue 56)