populate.py 文件源码

def create_dictionary_data_from_file(connection, index_name, doc_type, csv_file_path, update, logger, **kwargs):
    """
    Indexes all entity data from the csv file at path csv_file_path
    Args:
        connection: Elasticsearch client object
        index_name: The name of the index
        doc_type:  The type of the documents being indexed
        csv_file_path: absolute file path of the csv file to populate entity data from
        update: boolean, True if this is a update type operation, False if create/index type operation
        logger: logging object to log at debug and exception level
        kwargs:
            Refer http://elasticsearch-py.readthedocs.io/en/master/helpers.html#elasticsearch.helpers.bulk
    """

    base_file_name = os.path.basename(csv_file_path)
    dictionary_key = os.path.splitext(base_file_name)[0]

    if update:
        delete_entity_by_name(connection=connection, index_name=index_name, doc_type=doc_type,
                              entity_name=dictionary_key, logger=logger, **kwargs)
    dictionary_value = get_variants_dictionary_value_from_key(csv_file_path=csv_file_path,
                                                              dictionary_key=dictionary_key, logger=logger,
                                                              **kwargs)
    if dictionary_value:
        add_data_elastic_search(connection=connection, index_name=index_name, doc_type=doc_type,
                                dictionary_key=dictionary_key,
                                dictionary_value=remove_duplicate_data(dictionary_value), logger=logger, **kwargs)
    if os.path.exists(csv_file_path) and os.path.splitext(csv_file_path)[1] == '.csv':
        os.path.basename(csv_file_path)