def add_metadata(self, good_metadata, author_metadata):
if self.ecco_id in good_metadata.keys():
self.location = get_location_from_estc(
self.ecco_id, good_metadata)
self.country = get_country_from_estc(
self.ecco_id, good_metadata)
self.author = get_author_from_estc(
self.ecco_id, good_metadata)
self.estc_id = get_estcid_from_estc(
self.ecco_id, good_metadata)
self.year = get_year_from_estc(
self.ecco_id, good_metadata)
self.title = get_title_from_estc(
self.ecco_id, good_metadata)
bd = get_author_bd_from_estc(self.ecco_id, good_metadata)
self.author_birth = bd.get('birth')
self.author_death = bd.get('death')
self.first_ed_year_guess = get_first_ed_year_guess_from_estc(
self.ecco_id, good_metadata)
if self.first_ed_year_guess is None:
self.first_ed_year_guess = (
self.__get_guessed_first_ed_year())
self.author_politics = (
self.get_author_political_affiliation(author_metadata))
else:
print(str(self.ecco_id) + " not in good metadata.")
def enrich_reuse_summary(reuse_summary, metadata):
for row in reuse_summary:
row['title'] = get_title_from_estc(row['document_id'], metadata)
row['year'] = get_year_from_estc(row['document_id'], metadata)
row['author'] = get_author_from_estc(row['document_id'], metadata)
row['location'] = get_location_from_estc(row['document_id'], metadata)
row['estcid'] = get_estcid_from_estc(row['document_id'], metadata)
def get_cluster_data_for_document_id_from_api_filters(document_id,
good_metadata,
not_author=True,
originals_only=True,
years_min=-1000,
years_max=1000,
testing_amount=-1):
# data = get_wide_cluster_data_for_document_id_from_api(document_id,
# testing_amount)
api_client = OctavoEccoClusterClient(limit=testing_amount)
data = api_client.get_wide_cluster_data_for_document_id(document_id)
print("Orig data length:" + str(len(data)))
document_id = str(document_id)
orig_author = get_author_from_estc(document_id, good_metadata)
orig_year = get_year_from_estc(document_id, good_metadata)
enriched_cluster_data = enrich_cluster_data(data, good_metadata)
interesting_clusters = (get_cluster_ids_where_book_id_first(
enriched_cluster_data, document_id))
returndata = []
for item in enriched_cluster_data:
author = item.get('author')
year = item.get('year')
if not_author:
if (orig_author == author
and item.get('document_id') != document_id):
continue
if originals_only:
if (item.get('cluster_id') not in interesting_clusters):
continue
if years_max != 1000:
if not (year <= (orig_year + years_max)):
continue
if years_min != -1000:
if not (year >= (orig_year + years_min)):
continue
returndata.append(item)
print("Filtered data length:" + str(len(returndata)))
return returndata
def enrich_cluster_data(cluster_data, good_metadata):
returndata = []
for item in cluster_data:
item_document_id = str(item.get('documentID'))
author = get_author_from_estc(item_document_id, good_metadata)
year = get_year_from_estc(item_document_id, good_metadata)
estcid = get_estcid_from_estc(item_document_id, good_metadata)
new_item = {
'document_id': str(item_document_id),
'cluster_id': str(item.get('fragmentID')),
'title': item.get('title'),
'author': author,
'year': year,
'startIndex': item.get('startIndex'),
'endIndex': item.get('endIndex'),
'text': item.get('text'),
'estc_id': estcid
}
returndata.append(new_item)
print("return data length:" + str(len(returndata)))
return returndata