def conf_corpus(corpus, corpus_conf_dir_name):
if not corpus:
logging.error("Error: empty corpus")
else:
logging.info("init corpus: {}".format(corpus))
if not corpus_conf_dir_name:
corpus_conf_dir_name = corpus
date_begin = datetime.datetime.now()
# types
results_types_common = conf_types(corpus, "common")
results_types_corpus = conf_types(corpus, corpus_conf_dir_name)
date_types = datetime.datetime.now()
total_count = 0
logging.info("# Import common types:")
if results_types_common:
for entry in results_types_common:
total_count += 1
logging.info("type_id: {}, _id: {}".format(
entry["type_id"], entry["_id"]))
else:
logging.debug("Empty common types")
logging.info("# Import {} types:".format(corpus))
if results_types_corpus:
for entry in results_types_corpus:
total_count += 1
logging.info("type_id: {}, _id: {}".format(
entry["type_id"], entry["_id"]))
else:
logging.info("Empty {} types".format(corpus))
chrono.chrono_trace("conf_types", date_begin, date_types, total_count)
# datafields
results_fields_common = conf_fields(corpus, "common")
results_fields_corpus = conf_fields(corpus, corpus)
date_fields = datetime.datetime.now()
total_count = 0
logging.info("# Import common fields:")
if results_fields_common:
for entry in results_fields_common:
total_count += 1
logging.info("rec_type: {}, _id: {}".format(
entry["rec_type"], entry["_id"]))
else:
logging.info("Empty common fields")
logging.info("# Import {} fields:".format(corpus))
if results_fields_corpus:
for entry in results_fields_corpus:
total_count += 1
logging.info("rec_type: {}, _id: {}".format(
entry["rec_type"], entry["_id"]))
else:
logging.info("Empty {} fields".format(corpus))
chrono.chrono_trace("conf_fields", date_types, date_fields,
total_count)
def conf_corpus(corpus, corpus_conf_dir_name):
if not corpus:
logging.error("Error: empty corpus")
else:
logging.info("init corpus: {}".format(corpus))
if not corpus_conf_dir_name:
corpus_conf_dir_name = corpus
date_begin = datetime.datetime.now()
# types
results_types_common = conf_types(corpus, "common")
results_types_corpus = conf_types(corpus, corpus_conf_dir_name)
date_types = datetime.datetime.now()
total_count = 0
logging.info("# Import common types:")
if results_types_common:
for entry in results_types_common:
total_count += 1
logging.info("type_id: {}, _id: {}".format(entry["type_id"], entry["_id"]))
else:
logging.debug("Empty common types")
logging.info("# Import {} types:".format(corpus))
if results_types_corpus:
for entry in results_types_corpus:
total_count += 1
logging.info("type_id: {}, _id: {}".format(entry["type_id"], entry["_id"]))
else:
logging.info("Empty {} types".format(corpus))
chrono.chrono_trace("conf_types", date_begin, date_types, total_count)
# datafields
results_fields_common = conf_fields(corpus, "common")
results_fields_corpus = conf_fields(corpus, corpus)
date_fields = datetime.datetime.now()
total_count = 0
logging.info("# Import common fields:")
if results_fields_common:
for entry in results_fields_common:
total_count += 1
logging.info("rec_type: {}, _id: {}".format(entry["rec_type"], entry["_id"]))
else:
logging.info("Empty common fields")
logging.info("# Import {} fields:".format(corpus))
if results_fields_corpus:
for entry in results_fields_corpus:
total_count += 1
logging.info("rec_type: {}, _id: {}".format(entry["rec_type"], entry["_id"]))
else:
logging.info("Empty {} fields".format(corpus))
chrono.chrono_trace("conf_fields", date_types, date_fields, total_count)
def harvest_by_set(corpus, target, target_set):
logging.info("harvest_by_set: {}".format(target_set))
date_begin = datetime.datetime.now()
# harvest
metajson_list = oaipmh_harvester.list_records(target, None, None, target_set)
date_harvest = datetime.datetime.now()
chrono.chrono_trace("harvest spire and convert to metajson", date_begin, date_harvest, len(ids))
# import
result_import = corpus_service.import_metajson_list(corpus, metajson_list, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("harvest spire, convert metadata and save to MongoDB", date_harvest, date_import, len(result_import[0]))
def clean_corpus(corpus):
if not corpus:
logging.error("Error: empty corpus")
else:
logging.info("clean corpus: {}".format(corpus))
date_begin = datetime.datetime.now()
repository_service.create_corpus(corpus)
repository_service.empty_corpus(corpus)
repository_service.init_corpus_indexes(corpus)
date_end = datetime.datetime.now()
chrono.chrono_trace("clean_corpus", date_begin, date_end, None)
def clean_corpus(corpus):
if not corpus:
logging.error("Error: empty corpus")
else:
logging.info("clean corpus: {}".format(corpus))
date_begin = datetime.datetime.now()
repository_service.create_corpus(corpus)
repository_service.empty_corpus(corpus)
repository_service.init_corpus_indexes(corpus)
date_end = datetime.datetime.now()
chrono.chrono_trace("clean_corpus", date_begin, date_end, None)
def harvest_by_ids(corpus, target, ids):
logging.info("harvest_by_ids: {}".format(ids))
date_begin = datetime.datetime.now()
# harvest
metajson_list = []
for identifier in ids:
metajson_list.append(oaipmh_harvester.get_record(target, identifier))
date_harvest = datetime.datetime.now()
chrono.chrono_trace("harvest spire and convert to metajson", date_begin, date_harvest, len(ids))
# import
result_import = corpus_service.import_metajson_list(corpus, metajson_list, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("import", date_harvest, date_import, len(result_import))
def harvest_by_set(corpus, target, target_set):
logging.info("harvest_by_set: {}".format(target_set))
date_begin = datetime.datetime.now()
# harvest
metajson_list = oaipmh_harvester.list_records(target, None, None,
target_set)
date_harvest = datetime.datetime.now()
chrono.chrono_trace("harvest spire and convert to metajson", date_begin,
date_harvest, len(ids))
# import
result_import = corpus_service.import_metajson_list(
corpus, metajson_list, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("harvest spire, convert metadata and save to MongoDB",
date_harvest, date_import, len(result_import[0]))
def harvest_by_ids(corpus, target, ids):
logging.info("harvest_by_ids: {}".format(ids))
date_begin = datetime.datetime.now()
# harvest
metajson_list = []
for identifier in ids:
metajson_list.append(oaipmh_harvester.get_record(target, identifier))
date_harvest = datetime.datetime.now()
chrono.chrono_trace("harvest spire and convert to metajson", date_begin,
date_harvest, len(ids))
# import
result_import = corpus_service.import_metajson_list(
corpus, metajson_list, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("import", date_harvest, date_import,
len(result_import))
chrono.chrono_trace("harvest spire and convert to metajson", date_begin, date_harvest, len(ids))
# import
result_import = corpus_service.import_metajson_list(corpus, metajson_list, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("import", date_harvest, date_import, len(result_import))
if __name__ == "__main__":
date_begin = datetime.datetime.now()
# conf corpus
corpus = "spire"
corpus_service.clean_corpus(corpus)
date_clean = datetime.datetime.now()
chrono.chrono_trace("Initialize corpus", date_begin, date_clean, None)
target = Target()
target['identifier'] = 'spire'
target['title'] = 'Sciences Po Institutional Repository'
target['type'] = 'oaipmh'
target['url'] = 'http://spire.sciencespo.fr/dissemination/oaipmh2-no-prefix-publications.xml'
target['metadata_prefix'] = 'didl'
ids = [
"oai:spire.sciencespo.fr:2441/dambferfb7dfprc9m26c8c8o3",
"oai:spire.sciencespo.fr:2441/eo6779thqgm5r489makgoai85",
"oai:spire.sciencespo.fr:2441/5l6uh8ogmqildh09h6m8hj429",
"oai:spire.sciencespo.fr:2441/3fm4jv3k2s99lms9jb5i5asil",
"oai:spire.sciencespo.fr:2441/f4rshpf3v1umfa09lb0joe5g5",
"oai:spire.sciencespo.fr:2441/dambferfb7dfprc9m2h2og5ig",
source = "FNSP"
rec_id_prefix = "sc_"
input_dir_path = os.path.join("data", "num", "input")
input_format = constants.FORMAT_UNIMARC
output_dir_path = os.path.join("data", "num", "output")
if not os.path.exists(output_dir_path):
os.mkdir(output_dir_path)
error_file_name = "".join(["validation-", corpus, ".txt"])
error_file_path = os.path.join(output_dir_path, error_file_name)
#logging.debug("error_file_path: {}".format(error_file_path))
# 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
input_file_paths = io_service.get_relevant_file_list_by_format(
input_dir_path, input_format)
results = corpus_service.import_metadata_files(corpus, input_file_paths,
input_format, source,
rec_id_prefix, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("Import corpus", date_clean, date_import, None)
# Validate
corpus_service.validate_corpus(corpus, error_file_path)
date_validate = datetime.datetime.now()
chrono.chrono_trace("Validate corpus", 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)
source = "FNSP"
rec_id_prefix = "sc"
input_dir_path = os.path.join("data", "num", "input")
input_format = constants.FORMAT_UNIMARC
output_dir_path = os.path.join("data", "num", "output")
if not os.path.exists(output_dir_path):
os.mkdir(output_dir_path)
error_file_name = "".join(["validation-", corpus, ".txt"])
error_file_path = os.path.join(output_dir_path, error_file_name)
#logging.debug("error_file_path: {}".format(error_file_path))
# 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
input_file_paths = io_service.get_relevant_file_list_by_format(input_dir_path, input_format)
results = corpus_service.import_metadata_files(corpus, input_file_paths, input_format, source, rec_id_prefix, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("Import corpus", date_clean, date_import, None)
# Validate
corpus_service.validate_corpus(corpus, error_file_path)
date_validate = datetime.datetime.now()
chrono.chrono_trace("Validate corpus", date_import, date_validate, None)
# Export mods
corpus_service.export_corpus(corpus, output_dir_path, constants.FORMAT_MODS, False, True)
date_export_mods = datetime.datetime.now()
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)
# import
result_import = corpus_service.import_metajson_list(
corpus, metajson_list, True, None)
date_import = datetime.datetime.now()
chrono.chrono_trace("import", date_harvest, date_import,
len(result_import))
if __name__ == "__main__":
date_begin = datetime.datetime.now()
# conf corpus
corpus = "spire"
corpus_service.clean_corpus(corpus)
date_clean = datetime.datetime.now()
chrono.chrono_trace("Initialize corpus", date_begin, date_clean, None)
target = Target()
target['identifier'] = 'spire'
target['title'] = 'Sciences Po Institutional Repository'
target['type'] = 'oaipmh'
target[
'url'] = 'http://spire.sciencespo.fr/dissemination/oaipmh2-no-prefix-publications.xml'
target['metadata_prefix'] = 'didl'
ids = [
"oai:spire.sciencespo.fr:2441/dambferfb7dfprc9m26c8c8o3",
"oai:spire.sciencespo.fr:2441/eo6779thqgm5r489makgoai85",
"oai:spire.sciencespo.fr:2441/5l6uh8ogmqildh09h6m8hj429",
"oai:spire.sciencespo.fr:2441/3fm4jv3k2s99lms9jb5i5asil",
"oai:spire.sciencespo.fr:2441/f4rshpf3v1umfa09lb0joe5g5",