def import_metadatas(args): corpus = args.corpus if not corpus: corpus = default_corpus logging.info("corpus: {}".format(corpus)) input_format = args.input_format logging.info("input_format: {}".format(input_format)) input_file_path = args.input_file_path logging.info("input_file_path: {}".format(input_file_path)) source = args.source logging.info("source: {}".format(source)) rec_id_prefix = args.rec_id_prefix logging.info("rec_id_prefix: {}".format(rec_id_prefix)) corpus_service.import_metadata_file(corpus, input_file_path, input_format, source, rec_id_prefix, True, None)
def import_metadatas(args): corpus = args.corpus if not corpus: corpus = default_corpus logging.info("corpus: {}".format(corpus)) input_format = args.input_format logging.info("input_format: {}".format(input_format)) input_file_path = args.input_file_path logging.info("input_file_path: {}".format(input_file_path)) source = args.source logging.info("source: {}".format(source)) rec_id_prefix = args.rec_id_prefix logging.info("rec_id_prefix: {}".format(rec_id_prefix)) corpus_service.import_metadata_file(corpus, input_file_path, input_format, source, rec_id_prefix, True, None)
if __name__ == "__main__": date_begin = datetime.datetime.now() # conf params corpus = "perio" source = "Sciences Po | la bibliothèque" rec_id_prefix = "" input_file_path = os.path.join("data", "unimarc", "periouni.mrc") input_format = constants.FORMAT_UNIMARC csv_file_name = "".join(["validation-", corpus, ".csv"]) csv_file_path = os.path.join("data", "result", csv_file_name) # conf corpus corpus_service.clean_corpus(corpus) corpus_service.conf_corpus(corpus, "aime") date_clean = datetime.datetime.now() chrono.chrono_trace("Clean and conf corpus", date_begin, date_clean, None) # import corpus_service.import_metadata_file(corpus, input_file_path, input_format, source, rec_id_prefix, True, None) date_import = datetime.datetime.now() chrono.chrono_trace("Import corpus", date_clean, date_import, None) # Validate perio documents = repository_service.get_documents(corpus) validate_perios(documents, csv_file_path) date_validate = datetime.datetime.now() chrono.chrono_trace("Validate perio", date_import, date_validate, None)
if __name__ == "__main__": date_begin = datetime.datetime.now() # conf params corpus = "perio" source = "Sciences Po | la bibliothèque" rec_id_prefix = "" input_file_path = os.path.join("data", "unimarc", "periouni.mrc") input_format = constants.FORMAT_UNIMARC csv_file_name = "".join(["validation-", corpus, ".csv"]) csv_file_path = os.path.join("data", "result", csv_file_name) # conf corpus corpus_service.clean_corpus(corpus) corpus_service.conf_corpus(corpus, "aime") date_clean = datetime.datetime.now() chrono.chrono_trace("Clean and conf corpus", date_begin, date_clean, None) # import corpus_service.import_metadata_file(corpus, input_file_path, input_format, source, rec_id_prefix, True, None) date_import = datetime.datetime.now() chrono.chrono_trace("Import corpus", date_clean, date_import, None) # Validate perio documents = repository_service.get_documents(corpus) validate_perios(documents, csv_file_path) date_validate = datetime.datetime.now() chrono.chrono_trace("Validate perio", date_import, date_validate, None)