def unimarc_title(self, key, value):
"""Get title data.
field 200: non repetitive
$a : repetitive
$e : repetitive
$f : repetitive
$g : repetitive
$h : repetitive
$i : repetitive
field 510,512,514,515,516,517,518,519,532: repetitive
$a : non repetitive
$e : repetitive
$h : repetitive
$i : repetitive
"""
title_list = []
title = self.get('title', [])
# this function will be called for each fields 200, but as we already
# process all of them in the first run and the tittle is already build,
# there is nothing to do if the title has already been build.
if not title:
language = unimarc.lang_from_101
responsibilites = []
for tag in [
'200', '510', '512', '514', '515', '516', '517', '518', '519',
'532'
]:
for field in unimarc.get_alt_graphic_fields(tag=tag):
title_data = {}
part_list = TitlePartList(part_number_code='h',
part_name_code='i')
subfields_6 = unimarc.get_subfields(field, '6')
subfields_7 = unimarc.get_subfields(field, '7')
subfields_a = unimarc.get_subfields(field, 'a')
subfields_e = unimarc.get_subfields(field, 'e')
language_script_code = ''
if subfields_7:
language_script_code = \
unimarc.get_language_script(subfields_7[0])
title_type = 'bf:VariantTitle'
if tag == '200':
title_type = 'bf:Title'
elif tag == '510':
title_type = 'bf:ParallelTitle'
# build title parts
index = 1
link = ''
if subfields_6:
link = subfields_6[0]
items = get_field_items(field['subfields'])
for blob_key, blob_value in items:
if blob_key == 'a':
value_data = \
unimarc.build_value_with_alternate_graphic(
tag, blob_key, blob_value,
index, link, ',.', ':;/-=')
title_data['mainTitle'] = value_data
if blob_key == 'e':
value_data = \
unimarc.build_value_with_alternate_graphic(
tag, blob_key, blob_value,
index, link, ',.', ':;/-=')
title_data['subtitle'] = value_data
if blob_key in ['f', 'g'] and tag == '200':
value_data = \
unimarc.build_value_with_alternate_graphic(
tag, blob_key, blob_value,
index, link, ',.', ':;/-=')
responsibilites.append(value_data)
if blob_key in ['h', 'i']:
part_list.update_part([dict(value=blob_value)],
blob_key, blob_value)
if blob_key != '__order__':
index += 1
title_data['type'] = title_type
the_part_list = part_list.get_part_list()
if the_part_list:
title_data['part'] = the_part_list
if title_data:
title_list.append(title_data)
# extract responsibilities
if responsibilites:
new_responsibility = self.get('responsibilityStatement', [])
for resp in responsibilites:
new_responsibility.append(resp)
self['responsibilityStatement'] = new_responsibility
return title_list or None
field_245_a_end_with_colon = re.search(r'\s*:\s*$', subfield_245_a)
field_245_a_end_with_semicolon = re.search(r'\s*;\s*$', subfield_245_a)
field_245_b_contains_equal = re.search(r'=', subfield_245_b)
fields_246 = marc21.get_fields(tag='246')
subfield_246_a = ''
if fields_246:
if subfields_246_a := marc21.get_subfields(fields_246[0], 'a'):
subfield_246_a = subfields_246_a[0]
tag_link, link = get_field_link_data(value)
items = get_field_items(value)
index = 1
title_list = []
title_data = {}
part_list = TitlePartList(part_number_code='n', part_name_code='p')
parallel_titles = []
pararalel_title_data_list = []
pararalel_title_string_set = set()
responsibility = {}
subfield_selection = {'a', 'b', 'c', 'n', 'p'}
for blob_key, blob_value in items:
if blob_key in subfield_selection:
value_data = marc21.build_value_with_alternate_graphic(
'245', blob_key, blob_value, index, link, ',.', ':;/-=')
if blob_key in {'a', 'b', 'c'}:
subfield_selection.remove(blob_key)
if blob_key == 'a':
title_data['mainTitle'] = value_data
elif blob_key == 'b':
def marc21_to_title(self, key, value):
"""Get title data.
The title data are extracted from the following fields:
field 245:
$a : non repetitive
$b : non repetitive
$c : non repetitive
$n : repetitive
$p : repetitive
$6 : non repetitive
field 246:
$a : non repetitive
$n : repetitive
$p : repetitive
$6 : non repetitive
"""
# extraction and initialization of data for further processing
subfield_245_a = ''
subfield_245_b = ''
fields_245 = marc21.get_fields(tag='245')
if fields_245:
subfields_245_a = marc21.get_subfields(fields_245[0], 'a')
subfields_245_b = marc21.get_subfields(fields_245[0], 'b')
if subfields_245_a:
subfield_245_a = subfields_245_a[0]
if subfields_245_b:
subfield_245_b = subfields_245_b[0]
field_245_a_end_with_equal = re.search(r'\s*=\s*$', subfield_245_a)
field_245_a_end_with_colon = re.search(r'\s*:\s*$', subfield_245_a)
field_245_a_end_with_semicolon = re.search(r'\s*;\s*$', subfield_245_a)
field_245_b_contains_equal = re.search(r'=', subfield_245_b)
fields_246 = marc21.get_fields(tag='246')
subfield_246_a = ''
if fields_246:
subfields_246_a = marc21.get_subfields(fields_246[0], 'a')
if subfields_246_a:
subfield_246_a = subfields_246_a[0]
tag_link, link = get_field_link_data(value)
items = get_field_items(value)
index = 1
title_list = []
title_data = {}
part_list = TitlePartList(part_number_code='n', part_name_code='p')
parallel_titles = []
pararalel_title_data_list = []
pararalel_title_string_set = set()
responsibility = {}
# parse field 245 subfields for extracting:
# main title, subtitle, parallel titles and the title parts
subfield_selection = {'a', 'b', 'c', 'n', 'p'}
for blob_key, blob_value in items:
if blob_key in subfield_selection:
value_data = marc21.build_value_with_alternate_graphic(
'245', blob_key, blob_value, index, link, ',.', ':;/-=')
if blob_key in {'a', 'b', 'c'}:
subfield_selection.remove(blob_key)
if blob_key == 'a':
if value_data:
title_data['mainTitle'] = value_data
elif blob_key == 'b':
if subfield_246_a:
subtitle, parallel_titles, pararalel_title_string_set = \
extract_subtitle_and_parallel_titles_from_field_245_b(
value_data, field_245_a_end_with_equal)
if subtitle:
title_data['subtitle'] = subtitle
elif not subfield_246_a and value_data:
title_data['subtitle'] = value_data
elif blob_key == 'c':
responsibility = build_responsibility_data(value_data)
elif blob_key in ['n', 'p']:
part_list.update_part(value_data, blob_key, blob_value)
if blob_key != '__order__':
index += 1
title_data['type'] = 'bf:Title'
the_part_list = part_list.get_part_list()
if the_part_list:
title_data['part'] = the_part_list
if title_data:
title_list.append(title_data)
for parallel_title in parallel_titles:
title_list.append(parallel_title)
# extract variant titles
variant_title_list = \
marc21.build_variant_title_data(pararalel_title_string_set)
for variant_title_data in variant_title_list:
title_list.append(variant_title_data)
# extract responsibilities
if responsibility:
new_responsibility = self.get('responsibilityStatement', [])
for resp in responsibility:
new_responsibility.append(resp)
self['responsibilityStatement'] = new_responsibility
return title_list or None
def marc21_to_work_access_point(self, key, value):
"""Get work access point."""
"""
* "date_of_work": "[130$f|730$f]"
* "miscellaneous_information": "[130$g|130$s|730$g|730$s]"
* "language": "[130$l|730$l]"
* "form_subdivision": ["[130$k|730$k]"]
* "medium_of_performance_for_music": ["[130$m|730$m]"]
* "arranged_statement_for_music": "[130$o|730$o]"
* "key_for_music": "[130$r|730$r]"
[1] Nettoyer la chaîne: supprimer la ponctuation finale "/:;.,=",
supprimer en particulier la chaine ". - "
"""
work = {}
tag_key = key[:3]
part_list = TitlePartList(part_number_code='n', part_name_code='p')
part_selection = {'n', 'p'}
items = get_field_items(value)
if tag_key in ['130', '730']:
work_selection = {'a', 'f', 'k', 'l', 'm', 'o', 'r'}
miscellaneous_selection = {'g', 's'}
miscellaneous_parts = []
# _WORK_ACCESS_POINT.get(subfield_code)
for blob_key, blob_value in items:
if blob_key in work_selection:
if blob_key in {'k', 'm'}:
datas = work.get(_WORK_ACCESS_POINT.get(blob_key), [])
datas.append(blob_value)
work[_WORK_ACCESS_POINT.get(blob_key)] = datas
else:
work[_WORK_ACCESS_POINT.get(blob_key)] = blob_value
if blob_key in miscellaneous_selection:
miscellaneous_parts.append(blob_value)
if blob_key in part_selection:
part_list.update_part(blob_value, blob_key, blob_value)
if miscellaneous_parts:
work['miscellaneous_information'] = '. '.join(miscellaneous_parts)
if tag_key == '240':
for blob_key, blob_value in items:
if blob_key in {'a'}:
# work[_WORK_ACCESS_POINT.get('a')] = value.get('a')
work[_WORK_ACCESS_POINT.get(blob_key)] = blob_value
if blob_key in part_selection:
part_list.update_part(blob_value, blob_key, blob_value)
field_100 = marc21.get_fields('100')
if field_100:
agent = {}
for blob_key, blob_value in field_100[0].get('subfields').items():
agent['type'] = 'bf:Person'
if blob_key == 'a':
# numeration = not_repetitive(
# marc21.bib_id, marc21.bib_id, blob_key, blob_value, 'b')
agent['preferred_name'] = remove_trailing_punctuation(
blob_value)
if blob_key == 'b':
# numeration = not_repetitive(
# marc21.bib_id, marc21.bib_id, blob_key, blob_value, 'b')
agent['numeration'] = remove_trailing_punctuation(
blob_value)
if blob_key == 'c':
# qualifier = not_repetitive(
# marc21.bib_id, marc21.bib_id, blob_key, blob_value, 'c')
agent['qualifier'] = remove_trailing_punctuation(
blob_value)
if blob_key == 'd':
# date = not_repetitive(
# marc21.bib_id, marc21.bib_id, blob_key, blob_value, 'd')
date = blob_value.rstrip(',')
dates = remove_trailing_punctuation(date).split('-')
try:
date_of_birth = dates[0].strip()
if date_of_birth:
agent['date_of_birth'] = date_of_birth
except Exception:
pass
try:
date_of_death = dates[1].strip()
if date_of_death:
agent['date_of_death'] = date_of_death
except Exception:
pass
if blob_key == 'q':
# fuller_form_of_name = not_repetitive(
# marc21.bib_id, marc21.bib_id, blob_key, blob_value, 'q')
agent['fuller_form_of_name'] = remove_trailing_punctuation(
blob_value).lstrip('(').rstrip(')')
work['agent'] = agent
the_part_list = part_list.get_part_list()
if the_part_list:
work['part'] = the_part_list
if work:
work_access_points = self.get('work_access_point', [])
work_access_points.append(work)
self['work_access_point'] = work_access_points