def main():
h1, c1 = u.opencsv(
'/Users/amd243/Downloads/glad_aos_still_need_dates_boxes.csv')
h2, c2 = u.opencsv('/Users/amd243/Desktop/glad_top_containers_created.csv')
fileobject, csvoutfile = u.opencsvout(
'/Users/amd243/Desktop/matched_top_containers.csv')
match_ao_uris_w_tc_uris(c1, c2, fileobject, csvoutfile)
def __init__(self):
self.cnfg = u.get_config(cfg='/Users/aliciadetelich/as_tools_config.yml')
self.header_row, self.csvfile = u.opencsv(self.cnfg['input_csv'])
self.rowcount = row_count = sum(1 for line in open(self.cnfg['input_csv']).readlines()) - 1
self.api_url = 'http://api.snaccooperative.org/'
self.headers = {'Content-type': 'application/json','Accept': 'text/plain'}
self.q = {'command': 'read','sameas': 'lcnaf_uri'}
def main():
#1: Get a list of distinct creators for each collection, write output to file
#cfg_fp = input('Please enter path to config file: ')
list_of_parent_ids = input('Please enter path to list of parent IDs: ')
try:
header_row, parent_id_list = u.opencsv(list_of_parent_ids)
#need to do this to re-use the list
parent_id_list = [row for row in parent_id_list]
#set the configuration file here??
dbconn = dbssh.DBConn()
print('Running queries')
creator_data = aspace_run.run_db_queries(dbconn, parent_id_list,
queries.get_distinct_creators)
composition_data = aspace_run.run_db_queries(dbconn, parent_id_list,
queries.get_music_data)
outfile_path = input('Please enter path to outfile: ')
fileobject, csvoutfile = u.opencsvout(outfile_path)
write_outfile(creator_data, csvoutfile)
fileobject.close()
#2: Review manually and remediate any issues with agent records or duplicate agents
to_continue = input(
'After reviewing file please enter CONTINUE to continue: ')
if to_continue == 'CONTINUE':
#3: Create subseries for each agent record, save new URI
agent_data = u.opencsvdict(outfile_path)
#do the config here - need to fix utilities again
api_url, headers = u.login()
print('Creating subseries')
rows_w_uris = aspace_run.call_api(api_url,
headers,
agent_data,
crud=c.create_data,
json_data=jd.create_subseries)
#but if I'm just going to put it in a list anyway?? I guess for other implementations it makes more sense?
#Match new subseries URIs with all children
combined_data = match_uris(composition_data, rows_w_uris)
#5: Run data munging functions to get appropriate position
enumerated_data = add_positions(combined_data)
#NOW need to flatten this data as I did before...
flattened_data = flatten_data(enumerated_data)
#6: Use update ao position action to make change
dirpath = u.setdirectory()
aspace_run.call_api(api_url,
headers,
flattened_data,
dirpath=dirpath,
crud=c.update_parent)
except Exception as exc:
print('Error: ')
print(traceback.format_exc())
finally:
dbconn.close_conn()
def main():
mysql_instance = mysql.connector.connect(user='******',
password='******',
host='127.0.0.1',
use_pure=True)
db_cursor = mysql_instance.cursor()
db_tables = database_tables()
db_name = 'aspace_preservica_db'
header_row, csvfile = u.opencsv(
'/Users/aliciadetelich/Dropbox/git/mssa_digital_data_projects/database/db_data/tables_ingested/deliverable_unit_table_53615_2020-12-04-16-08_with_root.csv'
)
try:
#initialize_database(db_cursor, db_name, db_tables)
use_database(db_cursor, db_name)
drop_table(db_cursor, 'deliverable_unit')
create_table(db_cursor, 'deliverable_unit')
update_database(db_cursor, 'deliverable_unit', csvfile)
except Exception:
print(traceback.format_exc())
finally:
mysql_instance.commit()
db_cursor.close()
mysql_instance.close()
# csv_row['tc_uri']: The URI of the top container.
# csv_row['old_position']: The current position of the instance
# csv_row['new_position']: The desired position of the instance.
#
# Returns:
# dict: The JSON structure.
# '''
# new_instance_list = []
# for position, instance in enumerate(record_json['instances']):
# if instance['sub_container']['top_container']['ref'] == csv_row['tc_uri']:
#
#
# record_json['instances'] = new_instance_list
# return record_json
h1, c1 = u.opencsv(
'/Users/aliciadetelich/Desktop/glad_ao_multiple_instance_counts_out.csv')
csvlist = [row for row in c1]
case_dict = defaultdict(list)
for row in csvlist:
uri = row[0]
tc_uri = row[2]
tc_indicator = row[3]
current_position = row[4]
case_dict[uri].append([tc_uri, tc_indicator, current_position])
for key, value in case_dict.items():
for position, v in enumerate(value):
value[position].append(position)
def row_count(self):
'''Returns a count of rows in a CSV file, minus the header row'''
return len([row for row in u.opencsv(self.input_csv)[1]])
def main():
header_row, csvfile = u.opencsv()
#fileobject, csvoutfile = u.opencsvout()
#csvoutfile.writerow(['identifier', 'ratio', 'name'])
matcher(csvfile)
#/usr/bin/python3
from collections import Counter
from tqdm import tqdm
from utilities import utilities as u
header_row, csvfile = u.opencsv()
fileobject, csvoutfile = u.opencsvout()
headers = header_row + ['count']
csvoutfile.writerow(headers)
record_links = [row for row in csvfile]
agent_uris = [row[2] for row in record_links]
agent_uri_count = Counter(agent_uris)
output = [
row + [agent_uri_count[row[2]]] for row in tqdm(record_links)
if row[2] in agent_uri_count
]
csvoutfile.writerows(output)
fileobject.close()