def recreate_all_dictionary_data(connection, index_name, doc_type, logger, entity_data_directory_path=None,
csv_file_paths=None, **kwargs):
"""
Re-indexes all entity data from csv files stored at entity_data_directory_path, one file at a time
Args:
connection: Elasticsearch client object
index_name: The name of the index
doc_type: The type of the documents being indexed
logger: logging object to log at debug and exception level
entity_data_directory_path: Optional, Path of the directory containing the entity data csv files.
Default is None
csv_file_paths: Optional, list of file paths to csv files. Default is None
kwargs:
Refer http://elasticsearch-py.readthedocs.io/en/master/helpers.html#elasticsearch.helpers.bulk
"""
logger.debug('%s: +++ Started: recreate_all_dictionary_data() +++' % log_prefix)
if entity_data_directory_path:
logger.debug('%s: \t== Fetching from variants/ ==' % log_prefix)
csv_files = get_files_from_directory(entity_data_directory_path)
for csv_file in csv_files:
csv_file_path = os.path.join(entity_data_directory_path, csv_file)
create_dictionary_data_from_file(connection=connection, index_name=index_name, doc_type=doc_type,
csv_file_path=csv_file_path, update=True, logger=logger, **kwargs)
if csv_file_paths:
for csv_file_path in csv_file_paths:
if csv_file_path and csv_file_path.endswith('.csv'):
create_dictionary_data_from_file(connection=connection, index_name=index_name, doc_type=doc_type,
csv_file_path=csv_file_path, update=True, logger=logger, **kwargs)
logger.debug('%s: +++ Finished: recreate_all_dictionary_data() +++' % log_prefix)
评论列表
文章目录
