def build_registration(rows, name_type, name_data):
# logging.debug('Head Entry:')
# logging.debug(json.dumps(rows))
coc = class_without_brackets(rows['class_type'])
if coc in ['PAB', 'WOB']:
eo_type = "Debtor"
occupation = rows['occupation']
else:
eo_type = "Estate Owner"
occupation = ''
county_text = rows['property_county'].strip()
logging.info(' County_text is "%s"', county_text)
banks_county = ''
if county_text in ['BANKS', ''] and coc in ['PA', 'WO', 'DA']: # Special case for <1% of the data...
banks_county = rows['counties']
logging.info(' BANKS county of "%s"', county_text)
if county_text in ['NO COUNTY', 'NO COUNTIES', 'BANKS']:
county_text = ''
pty_desc = rows['property']
parish_district = rows['parish_district']
registration = {
"class_of_charge": coc,
"registration": {
"date": rows['registration_date'],
"registration_no": re.sub("[^0-9]", "", str(rows['registration_no']))
},
"parties": [{
"type": eo_type,
}],
"applicant": {
'name': '',
'address': '',
'key_number': '',
'reference': ''
},
"additional_information": "",
"migration_data": {
'unconverted_reg_no': rows['registration_no'],
'amend_info': rows['amendment_info'],
'flags': [],
'bankruptcy_county': banks_county
}
}
amend = parse_amend_info(rows['amendment_info'])
registration['additional_information'] = amend['additional_information']
if coc in ['PAB', 'WOB']:
registration['parties'][0]['occupation'] = occupation
registration['parties'][0]['trading_name'] = ''
registration['parties'][0]['residence_withheld'] = False
registration['parties'][0]['case_reference'] = amend['reference']
registration['parties'][0]['addresses'] = []
address_strings = rows['address'].split(' ')
for address in address_strings:
addr_obj = {
'type': 'Residence',
'address_string': address
}
registration['parties'][0]['addresses'].append(addr_obj)
if amend['court'] is not None:
registration['parties'].append({
'type': 'Court',
'names': [{
'type': 'Other',
'other': amend['court']
}]
})
else:
if rows['address'] is not None and rows['address'] != '':
# Some old registers have addresses on non-PAB/WOB regns
registration['parties'][0]['addresses'] = []
address_strings = rows['address'].split(' ')
for address in address_strings:
addr_obj = {
'type': 'Residence',
'address_string': address
}
registration['parties'][0]['addresses'].append(addr_obj)
registration['particulars'] = {
'counties': [reformat_county(county_text)],
'district': parish_district,
'description': pty_desc
}
registration['parties'][0]['names'] = [name_data]
registration['parties'][0]['names'][0]['type'] = name_type
return registration
def build_registration(rows, name_type, name_data):
# logging.debug('Head Entry:')
# logging.debug(json.dumps(rows))
coc = class_without_brackets(rows['class_type'])
if coc in ['PAB', 'WOB']:
eo_type = "Debtor"
occupation = rows['occupation']
else:
eo_type = "Estate Owner"
occupation = ''
county_text = rows['property_county'].strip()
logging.info(' County_text is "%s"', county_text)
banks_county = ''
if county_text in ['BANKS', ''] and coc in [
'PA', 'WO', 'DA'
]: # Special case for <1% of the data...
banks_county = rows['counties']
logging.info(' BANKS county of "%s"', county_text)
if county_text in ['NO COUNTY', 'NO COUNTIES', 'BANKS']:
county_text = ''
pty_desc = rows['property']
parish_district = rows['parish_district']
registration = {
"class_of_charge": coc,
"registration": {
"date": rows['registration_date'],
"registration_no": re.sub("[^0-9]", "",
str(rows['registration_no']))
},
"parties": [{
"type": eo_type,
}],
"applicant": {
'name': '',
'address': '',
'key_number': '',
'reference': ''
},
"additional_information": "",
"migration_data": {
'unconverted_reg_no': rows['registration_no'],
'amend_info': rows['amendment_info'],
'flags': [],
'bankruptcy_county': banks_county
}
}
amend = parse_amend_info(rows['amendment_info'])
registration['additional_information'] = amend['additional_information']
if coc in ['PAB', 'WOB']:
registration['parties'][0]['occupation'] = occupation
registration['parties'][0]['trading_name'] = ''
registration['parties'][0]['residence_withheld'] = False
registration['parties'][0]['case_reference'] = amend['reference']
registration['parties'][0]['addresses'] = []
address_strings = rows['address'].split(' ')
for address in address_strings:
addr_obj = {'type': 'Residence', 'address_string': address}
registration['parties'][0]['addresses'].append(addr_obj)
if amend['court'] is not None:
registration['parties'].append({
'type':
'Court',
'names': [{
'type': 'Other',
'other': amend['court']
}]
})
else:
if rows['address'] is not None and rows['address'] != '':
# Some old registers have addresses on non-PAB/WOB regns
registration['parties'][0]['addresses'] = []
address_strings = rows['address'].split(' ')
for address in address_strings:
addr_obj = {'type': 'Residence', 'address_string': address}
registration['parties'][0]['addresses'].append(addr_obj)
registration['particulars'] = {
'counties': [reformat_county(county_text)],
'district': parish_district,
'description': pty_desc
}
registration['parties'][0]['names'] = [name_data]
registration['parties'][0]['names'][0]['type'] = name_type
return registration
def handle_additional_rows(registration, rows, app_type):
# It's possible for the data to turn up some interesting variants where we have multiple index entries for
# a registration. This is uncommon (about 1.3% of the entries), but 1.3% of several million is still a good
# number of rows.
# Identified cases:
# Additional county add extra county to existing row
# Additional name add extra names
# Additional class of charge add new registration
add_regs = []
#"migration_data": {
#registration['migration_data']['additional_data'] = []
additional_data = {}
for row in rows[1:]:
changes = whats_different(row, rows[0])
if "class_type" in changes:
add_regs.append(extract_data([row], app_type))
else:
# Lovely unrolled loop... well, it's a one-off
if "amendment_info" in changes:
if 'amendment_info' not in additional_data:
additional_data['amendment_info'] = []
additional_data['amendment_info'].append(row['amendment_info'])
if "priority_notice" in changes:
if 'priority_notice' not in additional_data:
additional_data['priority_notice'] = []
additional_data['priority_notice'].append(row['priority_notice'])
if "parish_district" in changes:
if 'parish_district' not in additional_data:
additional_data['parish_district'] = []
additional_data['parish_district'].append(row['parish_district'])
if "address" in changes:
if 'address' not in additional_data:
additional_data['address'] = []
additional_data['address'].append(row['address'])
if "property" in changes:
if 'property' not in additional_data:
additional_data['property'] = []
additional_data['property'].append(row['property'])
if "name" in changes:
if 'name' not in additional_data:
additional_data['name'] = []
additional_data['name'].append(row['name'])
if "occupation" in changes:
if 'occupation' not in additional_data:
additional_data['occupation'] = []
additional_data['occupation'].append(row['occupation'])
if "priority_notice_ref" in changes:
if 'priority_notice_ref' not in additional_data:
additional_data['priority_notice_ref'] = []
additional_data['priority_notice_ref'].append(row['priority_notice_ref'])
if "counties" in changes:
if 'counties' not in additional_data:
additional_data['counties'] = []
additional_data['counties'].append(row['counties'])
if "reverse_name" in changes or "remainder_name" in changes or "punctuation_code" in changes:
alt_regn = extract_data([row], app_type)[0]
if len(alt_regn['parties']) > 0:
# logging.debug('Copying names...')
for name in alt_regn['parties'][0]['names']:
registration['parties'][0]['names'].append(name)
if "property_county" in changes and 'particulars' in registration:
if row['property_county'] not in ['BANKS', 'NO COUNTY', 'NO COUNTIES'] and row['property_county'] not in registration['particulars']['counties']:
registration['particulars']['counties'].append(reformat_county(row['property_county']))
registration['migration_data']['additional_rows'] = additional_data
return add_regs
def handle_additional_rows(registration, rows, app_type):
# It's possible for the data to turn up some interesting variants where we have multiple index entries for
# a registration. This is uncommon (about 1.3% of the entries), but 1.3% of several million is still a good
# number of rows.
# Identified cases:
# Additional county add extra county to existing row
# Additional name add extra names
# Additional class of charge add new registration
add_regs = []
#"migration_data": {
#registration['migration_data']['additional_data'] = []
additional_data = {}
for row in rows[1:]:
changes = whats_different(row, rows[0])
if "class_type" in changes:
add_regs.append(extract_data([row], app_type))
else:
# Lovely unrolled loop... well, it's a one-off
if "amendment_info" in changes:
if 'amendment_info' not in additional_data:
additional_data['amendment_info'] = []
additional_data['amendment_info'].append(row['amendment_info'])
if "priority_notice" in changes:
if 'priority_notice' not in additional_data:
additional_data['priority_notice'] = []
additional_data['priority_notice'].append(
row['priority_notice'])
if "parish_district" in changes:
if 'parish_district' not in additional_data:
additional_data['parish_district'] = []
additional_data['parish_district'].append(
row['parish_district'])
if "address" in changes:
if 'address' not in additional_data:
additional_data['address'] = []
additional_data['address'].append(row['address'])
if "property" in changes:
if 'property' not in additional_data:
additional_data['property'] = []
additional_data['property'].append(row['property'])
if "name" in changes:
if 'name' not in additional_data:
additional_data['name'] = []
additional_data['name'].append(row['name'])
if "occupation" in changes:
if 'occupation' not in additional_data:
additional_data['occupation'] = []
additional_data['occupation'].append(row['occupation'])
if "priority_notice_ref" in changes:
if 'priority_notice_ref' not in additional_data:
additional_data['priority_notice_ref'] = []
additional_data['priority_notice_ref'].append(
row['priority_notice_ref'])
if "counties" in changes:
if 'counties' not in additional_data:
additional_data['counties'] = []
additional_data['counties'].append(row['counties'])
if "reverse_name" in changes or "remainder_name" in changes or "punctuation_code" in changes:
alt_regn = extract_data([row], app_type)[0]
if len(alt_regn['parties']) > 0:
# logging.debug('Copying names...')
for name in alt_regn['parties'][0]['names']:
registration['parties'][0]['names'].append(name)
if "property_county" in changes and 'particulars' in registration:
if row['property_county'] not in [
'BANKS', 'NO COUNTY', 'NO COUNTIES'
] and row['property_county'] not in registration[
'particulars']['counties']:
registration['particulars']['counties'].append(
reformat_county(row['property_county']))
registration['migration_data']['additional_rows'] = additional_data
return add_regs