def get_headers_for_document_id(document_id, document_text=None):
if document_text is None:
ecco_api_client = OctavoEccoClient()
document_data = ecco_api_client.get_text_for_document_id(document_id)
document_text = document_data.get('text')
headerdata = get_headers_from_document_text(document_text)
return headerdata
def set_octavo_indices(self):
ecco_api_client = OctavoEccoClient()
eebo_api_client = OctavoEeboClient()
for document_id, fragment_list in self.fragments_by_ecco_id.items():
# TODO: handle the notes somehow!
if "_note_" in str(document_id):
textdata = None
elif len(document_id) < 10:
textdata = eebo_api_client.get_text_for_document_id(
document_id).get('text')
else:
textdata = ecco_api_client.get_text_for_document_id(
document_id).get('text')
for fragment in fragment_list:
fragment.set_octavo_index(textdata)
from lib.octavo_api_client import (
OctavoEccoClient,
OctavoEccoClusterClient
)
from lib.fragmentlists import (
get_fragmentlist,
get_doctext_indexmap,
test_fragment_text)
from lib.utils_common import create_dir_if_not_exists
from lib.headerdata_dump_common import read_docid_asciimap_csv
ecco_api_client = OctavoEccoClient()
cluster_api_client = OctavoEccoClusterClient(timeout=600)
docids_asciimap = read_docid_asciimap_csv('data/eccoids/asciilines.csv')
fields_ecco = ["documentID", "content"]
field_eccocluster = ["documentID", "fragmentID", "text",
"startIndex", "endIndex"]
docid_to_process = "0162900301"
docid_clusterdata = (
cluster_api_client.get_cluster_data_for_document_id(
docid_to_process, fields=field_eccocluster))