def extract_csv_line(args_array, line):
#print(line)
# Declare a processed array to append to
processed_array = {
"table_name": set_table_name_from_type(args_array['extraction_type']),
"FileName": args_array['file_name'],
"extraction_type": args_array['extraction_type']
}
# Handle a correspondance items
if args_array['extraction_type'] == "correspondence":
processed_array['ApplicationID'] = USPTOSanitizer.strip_leading_zeros(
USPTOSanitizer.clean_PAIR_csv_item(line[0]))
processed_array['Name1'] = USPTOSanitizer.clean_PAIR_csv_item(line[1])
processed_array['Name2'] = USPTOSanitizer.clean_PAIR_csv_item(line[2])
processed_array['Address'] = USPTOSanitizer.clean_PAIR_csv_item(
line[3]) + " " + USPTOSanitizer.clean_PAIR_csv_item(line[4])
processed_array['City'] = USPTOSanitizer.clean_PAIR_csv_item(line[5])
processed_array['PostalCode'] = USPTOSanitizer.clean_PAIR_csv_item(
line[6])
processed_array['RegionCode'] = USPTOSanitizer.clean_PAIR_csv_item(
line[7])
processed_array['RegionName'] = USPTOSanitizer.clean_PAIR_csv_item(
line[8])
processed_array['CountryCode'] = USPTOSanitizer.clean_PAIR_csv_item(
line[9])
processed_array['CountryName'] = USPTOSanitizer.clean_PAIR_csv_item(
line[10])
processed_array['CustomerNum'] = USPTOSanitizer.clean_PAIR_csv_item(
line[11])
elif args_array['extraction_type'] == "continuityparent":
processed_array['ApplicationID'] = USPTOSanitizer.strip_leading_zeros(
USPTOSanitizer.clean_PAIR_csv_item(line[0]))
processed_array[
'ParentApplicationID'] = USPTOSanitizer.strip_leading_zeros(
USPTOSanitizer.clean_PAIR_csv_item(line[1]))
processed_array['FileDate'] = USPTOSanitizer.clean_PAIR_csv_item(
line[2])
processed_array[
'ContinuationType'] = USPTOSanitizer.clean_PAIR_csv_item(line[3])
elif args_array['extraction_type'] == "continuitychild":
processed_array['ApplicationID'] = USPTOSanitizer.strip_leading_zeros(
USPTOSanitizer.clean_PAIR_csv_item(line[0]))
processed_array[
'ChildApplicationID'] = USPTOSanitizer.strip_leading_zeros(
USPTOSanitizer.clean_PAIR_csv_item(line[1]))
processed_array['FileDate'] = USPTOSanitizer.clean_PAIR_csv_item(
line[2])
processed_array[
'ContinuationType'] = USPTOSanitizer.clean_PAIR_csv_item(line[3])
# Return the array for storage
return processed_array
def extract_csv_line(args_array, line):
#print(line)
# Declare a processed array to append to
processed_array = {
"table_name": set_table_name_from_type(args_array['extraction_type']),
"FileName": args_array['file_name'],
"extraction_type": args_array['extraction_type']
}
# Handle a correspondance items
if args_array['extraction_type'] == "cases":
processed_array['CaseID'] = USPTOSanitizer.clean_PAIR_csv_item(line[1])
processed_array['PacerID'] = USPTOSanitizer.clean_PAIR_csv_item(
line[2])
processed_array['CourtTitle'] = USPTOSanitizer.clean_PAIR_csv_item(
line[3])
processed_array['DistrictID'] = USPTOSanitizer.clean_PAIR_csv_item(
line[4])
processed_array['CaseTitle'] = USPTOSanitizer.clean_PAIR_csv_item(
line[5])
processed_array['AssignedTo'] = USPTOSanitizer.clean_PAIR_csv_item(
line[6])
processed_array['ReferredTo'] = USPTOSanitizer.clean_PAIR_csv_item(
line[7])
processed_array['Cause'] = USPTOSanitizer.clean_PAIR_csv_item(line[8])
processed_array[
'JurisdictionBasis'] = USPTOSanitizer.clean_PAIR_csv_item(line[9])
processed_array['FileDate'] = USPTOSanitizer.clean_PAIR_csv_item(
line[10])
processed_array['CloseDate'] = USPTOSanitizer.clean_PAIR_csv_item(
line[11])
processed_array['LastFileDate'] = USPTOSanitizer.clean_PAIR_csv_item(
line[12])
processed_array['JuryDemand'] = USPTOSanitizer.clean_PAIR_csv_item(
line[13])
processed_array['Demand'] = USPTOSanitizer.clean_PAIR_csv_item(
line[14])
processed_array['LeadCase'] = USPTOSanitizer.clean_PAIR_csv_item(
line[15])
processed_array['RelatedCase'] = USPTOSanitizer.clean_PAIR_csv_item(
line[16])
processed_array['Settlement'] = USPTOSanitizer.clean_PAIR_csv_item(
line[17])
processed_array['CaseIDRaw'] = USPTOSanitizer.clean_PAIR_csv_item(
line[18])
processed_array['CaseType1'] = USPTOSanitizer.clean_PAIR_csv_item(
line[19])
processed_array['CaseType2'] = USPTOSanitizer.clean_PAIR_csv_item(
line[20])
processed_array['CaseType3'] = USPTOSanitizer.clean_PAIR_csv_item(
line[21])
processed_array['CaseTypeNote'] = USPTOSanitizer.clean_PAIR_csv_item(
line[22])
elif args_array['extraction_type'] == "pacercases":
processed_array['ApplicationID'] = USPTOSanitizer.clean_PAIR_csv_item(
line[0])
processed_array[
'ParentApplicationID'] = USPTOSanitizer.clean_PAIR_csv_item(
line[1])
processed_array['FileDate'] = USPTOSanitizer.clean_PAIR_csv_item(
line[2])
processed_array[
'ContinuationType'] = USPTOSanitizer.clean_PAIR_csv_item(line[3])
elif args_array['extraction_type'] == "names":
processed_array['CaseID'] = USPTOSanitizer.clean_PAIR_csv_item(line[1])
processed_array['PartyType'] = USPTOSanitizer.clean_PAIR_csv_item(
line[3])
processed_array['Name'] = USPTOSanitizer.clean_PAIR_csv_item(line[5])
elif args_array['extraction_type'] == "attorneys":
processed_array['CaseID'] = USPTOSanitizer.clean_PAIR_csv_item(line[1])
processed_array['CaseIDRaw'] = USPTOSanitizer.clean_PAIR_csv_item(
line[2])
processed_array['PartyType'] = USPTOSanitizer.clean_PAIR_csv_item(
line[4])
processed_array['Name'] = USPTOSanitizer.clean_PAIR_csv_item(line[6])
processed_array['ContactInfo'] = USPTOSanitizer.clean_PAIR_csv_item(
line[7])
processed_array['Position'] = USPTOSanitizer.clean_PAIR_csv_item(
line[8])
elif args_array['extraction_type'] == "patents":
processed_array['CaseID'] = USPTOSanitizer.clean_PAIR_csv_item(line[2])
processed_array['PacerID'] = USPTOSanitizer.clean_PAIR_csv_item(
line[1])
processed_array['NOS'] = USPTOSanitizer.clean_PAIR_csv_item(line[4])
processed_array['PatentID'] = USPTOSanitizer.strip_leading_zeros(
USPTOSanitizer.clean_PAIR_csv_item(line[11]))
processed_array['PatentDocType'] = USPTOSanitizer.clean_PAIR_csv_item(
line[12])
# Return the array for storage
return processed_array