Method parse

access_parser/access_parser.py:220–259

This is the main table parsing function. We go through all of the data pages linked to the table, separate each data page to rows(records) and parse each record. :return defaultdict(list) with the parsed data -- table[column][row_index]

(self)

        return parsed_table

    def parse(self):
        """
        This is the main table parsing function. We go through all of the data pages linked to the table, separate each
        data page to rows(records) and parse each record.
        :return defaultdict(list) with the parsed data -- table[column][row_index]
        """
        if not self.table.linked_pages:
            return self.create_empty_table()
        for data_chunk in self.table.linked_pages:
            original_data = data_chunk
            parsed_data = parse_data_page_header(original_data, version=self.version)

            last_offset = None
            for rec_offset in parsed_data.record_offsets:
                # Deleted row - Just skip it
                if rec_offset & 0x8000:
                    last_offset = rec_offset & 0xfff
                    continue
                # Overflow page
                if rec_offset & 0x4000:
                    # overflow ptr is 4 bits flags, 12 bits ptr
                    rec_ptr_offset = rec_offset & 0xfff
                    # update last pointer to pointer without flags
                    last_offset = rec_ptr_offset
                    # The ptr is the offset in the current data page. we get a 4 byte record_pointer from that
                    overflow_rec_ptr = original_data[rec_ptr_offset:rec_ptr_offset + 4]
                    overflow_rec_ptr = struct.unpack("<I", overflow_rec_ptr)[0]
                    record = self._get_overflow_record(overflow_rec_ptr)
                    if record:
                        self._parse_row(record)
                    continue
                # First record is actually the last one - from offset until the end of the data
                if not last_offset:
                    record = original_data[rec_offset:]
                else:
                    record = original_data[rec_offset:last_offset]
                last_offset = rec_offset
                if record:
                    self._parse_row(record)
        return self.parsed_table

    def _parse_row(self, record):
        """