def resolve_record(marc_record, descr_index):
for marc_field_and_subfields in FIELDS_TO_CHECK:
fld, subflds = marc_field_and_subfields[0], marc_field_and_subfields[1]
if fld in marc_record:
raw_objects_flds_list = marc_record.get_fields(fld)
for raw_fld in raw_objects_flds_list:
name_for_prepare = ' '.join(
subfld for subfld in raw_fld.get_subfields(*subflds))
if name_for_prepare:
term_to_search = prepare_name_for_indexing(
name_for_prepare)
else:
raise DescriptorNotResolved
if term_to_search in descr_index:
descr = descr_index.get(term_to_search)
identifier = f'{descr[0]}^^{descr[1]}^^{descr[2]}'
marc_record.remove_field(raw_fld)
raw_fld.add_subfield('0', identifier)
marc_record.add_ordered_field(raw_fld)
else:
#print(term_to_search)
raise DescriptorNotResolved
return marc_record
def index_descriptors(path_dir):
descriptors_dict = {}
for filename in os.listdir(path_dir):
path_file = os.sep.join([path_dir, filename])
with open(path_file, 'r', encoding='utf-8') as fp:
for line in tqdm(fp):
line_as_dict = ujson.loads(line)
index = line_as_dict.get('_index')
es_id = line_as_dict.get('_id')
name = line_as_dict.get('_source')['descr_name']
indexing_name = prepare_name_for_indexing(name)
descriptors_dict.setdefault(indexing_name,
(es_id, index, name))
return descriptors_dict
def resolve_field_value(field_value_list, descr_index):
if field_value_list:
list_to_return = []
for val in field_value_list:
if val:
term_to_search = prepare_name_for_indexing(val)
if term_to_search in descr_index:
descr = descr_index.get(term_to_search)
val_with_id = f'{descr[0]}^^{descr[1]}^^{descr[2]}'
list_to_return.append(val_with_id)
return list_to_return
else:
return field_value_list
def test_4_1(self):
data = 'Tytuł$ nie tylko z literami i cyframi. cz. 1? \n $%'
result = cn.prepare_name_for_indexing(data)
self.assertEqual('TYTUŁ NIE TYLKO Z LITERAMI I CYFRAMI CZ 1', result)
def test_4_4(self):
data = 'Wszystko podniesione do WIeLKIch liter'
result = cn.prepare_name_for_indexing(data)
self.assertEqual('WSZYSTKO PODNIESIONE DO WIELKICH LITER', result)
def test_4_3(self):
data = ' Białe znaki z początku i końca są usuwane \n'
result = cn.prepare_name_for_indexing(data)
self.assertEqual('BIAŁE ZNAKI Z POCZĄTKU I KOŃCA SĄ USUWANE', result)
def test_4_2(self):
data = 'Wielokrotne białe znaki są redukowane \n do jednej \t spacji.'
result = cn.prepare_name_for_indexing(data)
self.assertEqual(
'WIELOKROTNE BIAŁE ZNAKI SĄ REDUKOWANE DO JEDNEJ SPACJI', result)