def marc21_to_subjects_imported(self, key, value):
"""Get subject and genreForm_imported imported from 919 (L53, L54)."""
specific_contains_regexp = \
re.compile(r'\[(carte postale|affiche|document photographique)\]')
contains_specific_voc_regexp = re.compile(
r'^(chrero|rerovoc|ram|rameau|gnd|rerovoc|gatbegr|gnd-content)$')
subfields_2 = utils.force_list(value.get('2'))
term_string = ''
data_imported = None
field_key = 'subjects_imported'
if subfields_2:
subfield_2 = subfields_2[0]
match = contains_specific_voc_regexp.search(subfield_2)
if match:
add_data_imported = False
if subfield_2 == 'chrero':
subfields_9 = utils.force_list(value.get('9'))
subfield_9 = subfields_9[0]
subfields_v = utils.force_list(value.get('v'))
if subfields_v:
subfield_v = subfields_v[0]
match = specific_contains_regexp.search(subfield_v)
if match:
contains_655_regexp = re.compile(r'655')
match = contains_655_regexp.search(subfield_9)
add_data_imported = True
if match:
field_key = 'genreForm_imported'
else:
add_data_imported = True
if subfield_2 == 'gatbegr' or subfield_2 == 'gnd-content':
field_key = 'genreForm_imported'
if add_data_imported:
term_string = build_string_from_subfields(
value, 'abcdefghijklmnopqrstuvwxyz', ' - ')
data_imported = {
'type': 'bf:Topic',
'source': subfield_2,
'term': term_string
}
else:
term_string = build_string_from_subfields(
value, 'abcdefghijklmnopqrstuvwxyz', ' - ')
if term_string:
data_imported = {'type': 'bf:Topic', 'term': term_string}
if data_imported:
subjects_or_genre_form_imported_imported = self.get(field_key, [])
subjects_or_genre_form_imported_imported.append(data_imported)
self[field_key] = subjects_or_genre_form_imported_imported
def marc21_to_subjects_imported(self, key, value):
"""Get subjects.
- create an object :
genreForm : for the field 655
subjects : for 6xx with $2 rero
subjects_imported : for 6xx having indicator 2 '0' or '2'
"""
def perform_subdivisions(field):
"""Perform subject subdivisions from MARC field."""
subdivisions = {
'v': 'genreForm_subdivisions',
'x': 'topic_subdivisions',
'y': 'temporal_subdivisions',
'z': 'place_subdivisions'
}
for code, subdivision in subdivisions.items():
for subfield_value in utils.force_list(value.get(code, [])):
field.setdefault(subdivision, []).append(subfield_value)
type_per_tag = {
'600': 'bf:Person',
'610': 'bf:Organisation',
'611': 'bf:Organisation',
'600t': 'bf:Work',
'610t': 'bf:Work',
'611t': 'bf:Work',
'630': 'bf:Work',
'650': 'bf:Topic', # or bf:Temporal, changed by code
'651': 'bf:Place',
'655': 'bf:Topic'
}
field_data_per_tag = {
'600': 'preferred_name',
'610': 'preferred_name',
'611': 'preferred_name',
'600t': 'title',
'610t': 'title',
'611t': 'title',
'630': 'title',
'650': 'term',
'651': 'preferred_name',
'655': 'term'
}
conference_per_tag = {'610': False, '611': True}
source_per_indicator_2 = {'7': 'LCSH', '2': 'MeSH'}
indicator_2 = key[4]
tag_key = key[:3]
subfields_2 = utils.force_list(value.get('2'))
subfield_2 = subfields_2[0] if subfields_2 else None
if subfield_2 == 'lcsh' or indicator_2 in ['0', '2', '7']:
term_string = build_string_from_subfields(value,
'abcdefghijklmnopqrstuw',
' - ')
if term_string:
source = 'LCSH' if subfield_2 == 'lcsh' else \
source_per_indicator_2[indicator_2]
subject_imported = {
'type': type_per_tag[tag_key],
'source': source,
field_data_per_tag[tag_key]: term_string.rstrip('.')
}
perform_subdivisions(subject_imported)
if tag_key in ['610', '611']:
subject_imported['conference'] = conference_per_tag[tag_key]
subjects_imported = self.get('subjects_imported', [])
if subject_imported:
subjects_imported.append(subject_imported)
self['subjects_imported'] = subjects_imported
def marc21_to_subjects(self, key, value):
"""Get subjects.
- create an object :
genreForm : for the field 655
subjects : for 6xx with $2 rero
subjects_imported : for 6xx having indicator 2 '0' or '2'
"""
type_per_tag = {
'600': 'bf:Person',
'610': 'bf:Organization',
'611': 'bf:Organization',
'600t': 'bf:Work',
'610t': 'bf:Work',
'611t': 'bf:Work',
'630': 'bf:Work',
'650': 'bf:Topic', # or bf:Temporal, changed by code
'651': 'bf:Place',
'655': 'bf:Topic'
}
ref_link_per_tag = {
'600': 'IdRef agent',
'610': 'IdRef agent',
'611': 'IdRef agent',
'600t': 'IdRef work',
'610t': 'IdRef work',
'611t': 'IdRef work',
'630': 'IdRef work',
'650': 'RERO RAMEAU concept',
'651': 'Idref place',
'655': 'RERO RAMEAU concept'
}
field_data_per_tag = {
'600': 'preferred_name',
'610': 'preferred_name',
'611': 'preferred_name',
'600t': 'title',
'610t': 'title',
'611t': 'title',
'630': 'title',
'650': 'term',
'651': 'preferred_name',
'655': 'term'
}
subfield_code_per_tag = {
'600': 'abcd',
'610': 'ab',
'611': 'acden',
'600t': 'tpn',
'610t': 'tpn',
'611t': 't',
'630': 'apn',
'650': 'a',
'651': 'a',
'655': 'a'
}
conference_per_tag = {'610': False, '611': True}
source_per_indicator_2 = {'0': 'LCSH', '2': 'MeSH'}
indicator_2 = key[4]
tag_key = key[:3]
subfields_2 = utils.force_list(value.get('2'))
subfield_2 = None
if subfields_2:
subfield_2 = subfields_2[0]
subfields_a = utils.force_list(value.get('a', []))
if subfield_2 == 'rero':
has_dollar_t = value.get('t')
if tag_key in ('600', '610', '611') and has_dollar_t:
tag_key += 't'
data_type = type_per_tag[tag_key]
start_with_digit = False
if tag_key == '650':
for subfield_a in subfields_a:
start_with_digit_regexp = re.compile(r'^\d')
match = start_with_digit_regexp.search(subfield_a)
if match:
data_type = 'bf:Temporal'
break
subject = {
'type': data_type,
}
string_build = build_string_from_subfields(
value, subfield_code_per_tag[tag_key])
if (tag_key == '655'):
# remove the square brackets
string_build = re.sub(r'^\[(.*)\]$', r'\1', string_build)
subject[field_data_per_tag[tag_key]] = string_build
if tag_key in ('610', '611'):
subject['conference'] = conference_per_tag[tag_key]
if tag_key in ('600t', '610t', '611t'):
creator_tag_key = tag_key[:3] # to keep only tag: 600, 610, 611
subject['creator'] = remove_trailing_punctuation(
build_string_from_subfields(
value, subfield_code_per_tag[creator_tag_key]), '.', '.')
field_key = 'subjects'
if tag_key == '655':
field_key = 'genreForm'
subfields_0 = utils.force_list(value.get('0'))
if data_type in ['bf:Person', 'bf:Organisation'] and subfields_0:
ref = get_contribution_link(marc21.bib_id, marc21.rero_id,
subfields_0[0], key)
if ref:
subject = {
'$ref': ref,
'type': data_type,
}
if not subject.get('$ref'):
identifier = build_identifier(value)
if identifier:
subject['identifiedBy'] = identifier
if subject.get('$ref') or subject.get(field_data_per_tag[tag_key]):
subjects = self.get(field_key, [])
subjects.append(subject)
self[field_key] = subjects
elif subfield_2 == 'rerovoc' or indicator_2 in ['0', '2']:
term_string = build_string_from_subfields(
value, 'abcdefghijklmnopqrstuvwxyz', ' - ')
if term_string:
if subfield_2 == 'rerovoc':
source = 'rerovoc'
else:
source = source_per_indicator_2[indicator_2]
subject_imported = {
'type': type_per_tag[tag_key],
'source': source
}
subject_imported[field_data_per_tag[tag_key]] = term_string
if tag_key in ('610', '611'):
subject_imported['conference'] = conference_per_tag[tag_key]
subjects_imported = self.get('subjects_imported', [])
if subject_imported:
subjects_imported.append(subject_imported)
self['subjects_imported'] = subjects_imported
def marc21_to_subjects_imported(self, key, value):
"""Get subjects.
- create an object :
genreForm : for the field 655
subjects : for 6xx with $2 rero
subjects_imported : for 6xx having indicator 2 '0' or '2'
"""
type_per_tag = {
'600': 'bf:Person',
'610': 'bf:Organization',
'611': 'bf:Organization',
'600t': 'bf:Work',
'610t': 'bf:Work',
'611t': 'bf:Work',
'630': 'bf:Work',
'650': 'bf:Topic', # or bf:Temporal, changed by code
'651': 'bf:Place',
'655': 'bf:Topic'
}
ref_link_per_tag = {
'600': 'IdRef agent',
'610': 'IdRef agent',
'611': 'IdRef agent',
'600t': 'IdRef work',
'610t': 'IdRef work',
'611t': 'IdRef work',
'630': 'IdRef work',
'650': 'RERO RAMEAU concept',
'651': 'Idref place',
'655': 'RERO RAMEAU concept'
}
field_data_per_tag = {
'600': 'preferred_name',
'610': 'preferred_name',
'611': 'preferred_name',
'600t': 'title',
'610t': 'title',
'611t': 'title',
'630': 'title',
'650': 'term',
'651': 'preferred_name',
'655': 'term'
}
subfield_code_per_tag = {
'600': 'abcd',
'610': 'ab',
'611': 'acden',
'600t': 'tpn',
'610t': 'tpn',
'611t': 't',
'630': 'apn',
'650': 'a',
'651': 'a',
'655': 'a'
}
conference_per_tag = {'610': False, '611': True}
source_per_indicator_2 = {'7': 'LCSH', '2': 'MeSH'}
indicator_2 = key[4]
tag_key = key[:3]
subfields_2 = utils.force_list(value.get('2'))
subfield_2 = None
if subfields_2:
subfield_2 = subfields_2[0]
subfields_a = utils.force_list(value.get('a', []))
if subfield_2 == 'lcsh' or indicator_2 in ['0', '2', '7']:
term_string = build_string_from_subfields(
value, 'abcdefghijklmnopqrstuvwxyz', ' - ')
if term_string:
if subfield_2 == 'lcsh':
source = 'LCSH'
else:
source = source_per_indicator_2[indicator_2]
subject_imported = {
'type': type_per_tag[tag_key],
'source': source
}
subject_imported[field_data_per_tag[tag_key]] = \
term_string.rstrip('.')
if tag_key in ('610', '611'):
subject_imported['conference'] = conference_per_tag[tag_key]
subjects_imported = self.get('subjects_imported', [])
if subject_imported:
subjects_imported.append(subject_imported)
self['subjects_imported'] = subjects_imported
def marc21_to_series(self, key, value):
"""Get series.
series.name: [490$a repetitive]
series.number: [490$v repetitive]
"""
if key[:3] == '490':
marc21.extract_series_statement_from_marc_field(key, value, self)
else:
# we have a 440 series statement
"""
440$a = seriesTitle
1. if $p:
440$n$p = subseriesTitle
440$v = subseriesEnumeration
2. if $v and $n but no $p:
440$n,$v = seriesEnumeration
3 if $n but no $p and no $v:
440$n = subseriesTitle
4. if no $p and no $n:
440$v = seriesEnumeration
remove final punctuation "." or "," or ";" in seriesTitle
"""
if value.get('a'):
series = {}
subseriesStatement = {}
subfield_a = remove_punctuation(utils.force_list(
value.get('a'))[0],
with_dot=True)
series['seriesTitle'] = [{'value': subfield_a}]
if value.get('p'):
"""
440$n$p = subseriesTitle
440$v = subseriesEnumeration
"""
string_build = build_string_from_subfields(value, 'np', ' ')
subseriesStatement['subseriesTitle'] = [{
'value':
remove_punctuation(string_build, with_dot=True).rstrip()
}]
if value.get('v'):
parts = []
for subfield_v in utils.force_list(value.get('v')):
parts.append(remove_punctuation(subfield_v))
subseriesStatement['subseriesEnumeration'] = [{
'value':
'/'.join(parts)
}]
series['subseriesStatement'] = [subseriesStatement]
else:
if value.get('n'):
if value.get('v'):
string_build = build_string_from_subfields(value, 'nv')
series['seriesEnumeration'] = [{
'value':
remove_punctuation(string_build,
with_dot=True).rstrip()
}]
else:
if value.get('n'):
subseriesStatement['subseriesTitle'] = [{
'value':
''.join(utils.force_list(value.get('n')))
}]
series['subseriesStatement'] = [subseriesStatement]
elif value.get('v'):
parts = []
for subfield_v in utils.force_list(value.get('v')):
parts.append(remove_punctuation(subfield_v))
series['seriesEnumeration'] = [{'value': '/'.join(parts)}]
# marc21.extract_series_statement_from_440_field(value, self)
self['seriesStatement'] = self.get('seriesStatement', [])
self['seriesStatement'].append(series)
return None
def marc21_to_subjects_6XX(self, key, value):
"""Get subjects.
- create an object :
genreForm : for the field 655
subjects : for 6xx with $2 rero
subjects_imported : for 6xx having indicator 2 '0' or '2'
"""
def perform_subdivisions(field):
"""Perform subject subdivisions from MARC field."""
subdivisions = {
'v': 'genreForm_subdivisions',
'x': 'topic_subdivisions',
'y': 'temporal_subdivisions',
'z': 'place_subdivisions'
}
for code, subdivision in subdivisions.items():
for subfield_value in utils.force_list(value.get(code, [])):
field.setdefault(subdivision, []).append(subfield_value)
type_per_tag = {
'600': DocumentSubjectType.PERSON,
'610': DocumentSubjectType.ORGANISATION,
'611': DocumentSubjectType.ORGANISATION,
'600t': DocumentSubjectType.WORK,
'610t': DocumentSubjectType.WORK,
'611t': DocumentSubjectType.WORK,
'630': DocumentSubjectType.WORK,
'650': DocumentSubjectType.TOPIC, # or bf:Temporal, changed by code
'651': DocumentSubjectType.PLACE,
'655': DocumentSubjectType.TOPIC
}
field_data_per_tag = {
'600': 'preferred_name',
'610': 'preferred_name',
'611': 'preferred_name',
'600t': 'title',
'610t': 'title',
'611t': 'title',
'630': 'title',
'650': 'term',
'651': 'preferred_name',
'655': 'term'
}
subfield_code_per_tag = {
'600': 'abcd',
'610': 'ab',
'611': 'acden',
'600t': 'tpn',
'610t': 'tpn',
'611t': 't',
'630': 'apn',
'650': 'a',
'651': 'a',
'655': 'a'
}
conference_per_tag = {
'610': False,
'611': True
}
source_per_indicator_2 = {
'0': 'LCSH',
'2': 'MeSH'
}
indicator_2 = key[4]
tag_key = key[:3]
subfields_2 = utils.force_list(value.get('2'))
subfield_2 = subfields_2[0] if subfields_2 else None
subfields_a = utils.force_list(value.get('a', []))
if subfield_2 in ['rero', 'gnd', 'idref']:
if tag_key in ['600', '610', '611'] and value.get('t'):
tag_key += 't'
data_type = type_per_tag[tag_key]
# `data_type` is Temporal if tag is 650 and a $a start with digit.
if tag_key == '650':
for subfield_a in subfields_a:
if subfield_a[0].isdigit():
data_type = 'bf:Temporal'
break
subject = {
'type': data_type,
}
string_build = build_string_from_subfields(
value, subfield_code_per_tag[tag_key])
if tag_key == '655':
# remove the square brackets
string_build = re.sub(r'^\[(.*)\]$', r'\1', string_build)
subject[field_data_per_tag[tag_key]] = string_build
if tag_key in ['610', '611']:
subject['conference'] = conference_per_tag[tag_key]
if tag_key in ['600t', '610t', '611t']:
creator_tag_key = tag_key[:3] # to keep only tag: 600, 610, 611
subject['creator'] = remove_trailing_punctuation(
build_string_from_subfields(
value, subfield_code_per_tag[creator_tag_key]), '.', '.')
field_key = 'genreForm' if tag_key == '655' else 'subjects'
subfields_0 = utils.force_list(value.get('0'))
if data_type in [DocumentSubjectType.PERSON,
DocumentSubjectType.ORGANISATION] and subfields_0:
ref = get_contribution_link(marc21.bib_id, marc21.rero_id,
subfields_0[0], key)
if ref:
subject = {
'$ref': ref,
'type': data_type,
}
if not subject.get('$ref'):
identifier = build_identifier(value)
if identifier:
subject['identifiedBy'] = identifier
perform_subdivisions(subject)
if subject.get('$ref') or subject.get(field_data_per_tag[tag_key]):
subjects = self.get(field_key, [])
subjects.append(subject)
self[field_key] = subjects
elif indicator_2 in ['0', '2']:
term_string = build_string_from_subfields(
value, 'abcdefghijklmnopqrstuw', ' - ')
if term_string:
subject_imported = {
'type': type_per_tag[tag_key],
'source': source_per_indicator_2[indicator_2],
field_data_per_tag[tag_key]: term_string.rstrip('.')
}
perform_subdivisions(subject_imported)
if tag_key in ['610', '611']:
subject_imported['conference'] = conference_per_tag[tag_key]
subjects_imported = self.get('subjects_imported', [])
if subject_imported:
subjects_imported.append(subject_imported)
self['subjects_imported'] = subjects_imported
def marc21_to_tableOfContents(self, key, value):
"""Get tableOfContents from repetitive field 464."""
table_of_contents = build_string_from_subfields(value, 't')
if table_of_contents:
self.setdefault('tableOfContents', []).append(table_of_contents)