readmdict.py 文件源码

def _split_key_block(self, key_block):
        key_list = []
        key_start_index = 0
        while key_start_index < len(key_block):
            temp = key_block[key_start_index:key_start_index + self._number_width]
            # the corresponding record's offset in record block
            key_id = unpack(self._number_format, key_block[key_start_index:key_start_index + self._number_width])[0]
            # key text ends with '\x00'
            if self._encoding == 'UTF-16':
                delimiter = b'\x00\x00'
                width = 2
            else:
                delimiter = b'\x00'
                width = 1
            i = key_start_index + self._number_width
            while i < len(key_block):
                if key_block[i:i + width] == delimiter:
                    key_end_index = i
                    break
                i += width
            key_text = key_block[key_start_index + self._number_width:key_end_index]\
                .decode(self._encoding, errors='ignore').encode('utf-8').strip()
            key_start_index = key_end_index + width
            key_list += [(key_id, key_text)]
        return key_list