def get_doc_id()

in filtering/deduplication/add_dedup_info.py [0:0]


def get_doc_id(pos, pos2id, pos2id_list):
    """
    Gets id of the datapoint at position.
    """
    pos = bisect_right(pos2id_list, pos)
    doc_id = pos2id[pos2id_list[pos - 1]]
    return doc_id