def init_indexes():
indexes = Vocabulary()
indexes.identifier = IrokoVocabularyIdentifiers.INDEXES.value
indexes.human_name = 'Indices, Bases de Datos'
db.session.add(indexes)
db.session.commit()
work_dir = current_app.config['HARVESTER_SECONDARY_DIRECTORY']
miar_harvester = MiarHarvester(work_dir)
miar_harvester.syncronize_miar_databases()
def sync_databases(cls, recheck=True):
work_dir = current_app.config['IROKO_DATA_DIRECTORY']
indexes = Vocabulary.query.filter_by(
identifier=IrokoVocabularyIdentifiers.INDEXES.value).first()
if not indexes:
indexes = Vocabulary()
indexes.identifier = IrokoVocabularyIdentifiers.INDEXES.value
indexes.human_name = 'Indices, Bases de Datos'
db.session.add(indexes)
db.session.commit()
miar_harvester = MiarHarvester(work_dir)
miar_harvester.syncronize_miar_databases()
def init_cuntries(path):
vocab = Vocabulary()
vocab.identifier = IrokoVocabularyIdentifiers.COUNTRIES.value
vocab.human_name = 'Paises'
db.session.add(vocab)
db.session.commit()
with open(path) as f:
countries = json.load(f)
for country in countries:
nterm = Term()
nterm.identifier = country['key']
nterm.description = country['text']
nterm.vocabulary_id = vocab.identifier
db.session.add(nterm)
db.session.commit()
def add_vocabulary():
"""The create view."""
form = VocabularyForm()
# if the form is submitted and valid
if form.validate_on_submit():
new_vocab = Vocabulary()
if form.name.data:
new_vocab.identifier = form.name.data
if form.description.data:
new_vocab.description = form.description.data
db.session.add(new_vocab)
db.session.commit()
flash(_('Vocabulary added'), 'info')
return redirect(url_for('iroko_curator.add_vocabulary'))
return render_template('add_vocabulary.html', form=form)
def init_unesco(path):
subjects = Vocabulary()
subjects.identifier = IrokoVocabularyIdentifiers.SUBJECTS.value
subjects.human_name = 'Cobertura tematica'
db.session.add(subjects)
db.session.commit()
groups = [
{
'name': 'http://vocabularies.unesco.org/thesaurus/domain1',
'description': 'Educación'
}, {
'name': 'http://vocabularies.unesco.org/thesaurus/domain2',
'description': 'Ciencia'
}, {
'name': 'http://vocabularies.unesco.org/thesaurus/domain3',
'description': 'Cultura'
}, {
'name': 'http://vocabularies.unesco.org/thesaurus/domain4',
'description': 'Ciencias sociales y humanas'
}, {
'name': 'http://vocabularies.unesco.org/thesaurus/domain5',
'description': 'Información y comunicación'
}, {
'name': 'http://vocabularies.unesco.org/thesaurus/domain6',
'description': 'Política, derecho y economía'
}
]
graph = Graph()
graph.load(path)
for t in groups:
term = Term()
term.identifier = t['name']
term.description = t['description']
term.vocabulary_id = subjects.identifier
db.session.add(term)
db.session.commit()
_add_group_terms(graph, t['name'], term, subjects)
db.session.commit()
def new_vocabulary(cls, input_data) -> Dict[str, Vocabulary]:
msg = ''
try:
data = vocabulary_schema.load(input_data)
vocab = Vocabulary.query.filter_by(identifier=data['name']).first()
if not vocab:
vocab = Vocabulary()
vocab.identifier = string_as_identifier(data['name'])
vocab.human_name = data['human_name']
vocab.description = data['description']
vocab.data = data['data']
db.session.add(vocab)
db.session.commit()
msg = 'New Vocabulary CREATED name={0}'.format(
vocab.identifier)
else:
msg = 'Vocabulary already exist name={0}'.format(
vocab.identifier)
vocab = None
except Exception as err:
msg = 'ERROR {0} - {1}'.format(err, data)
vocab = None
finally:
return msg, vocab
def init_taxonomy():
"""Init vocabularies"""
delete_all_vocabs()
# print('delete all vocabs and terms')
# tax_path = '../../data/taxonomy.json' .
datadir = current_app.config['IROKO_DATA_DIRECTORY']
init_cuntries(os.path.join(datadir, 'countries.json'))
init_unesco(os.path.join(datadir, 'unesco-thesaurus.rdf'))
init_indexes()
path = os.path.join(datadir, 'vocabularies.json')
with open(path) as f:
tax = json.load(f)
institutions = Vocabulary()
institutions.identifier = IrokoVocabularyIdentifiers.CUBAN_INTITUTIONS.value
institutions.human_name = 'Instituciones Cubanas'
db.session.add(institutions)
extra_institutions = Vocabulary()
extra_institutions.identifier = IrokoVocabularyIdentifiers.EXTRA_INSTITUTIONS.value
extra_institutions.human_name = 'Instituciones sin REUP'
db.session.add(extra_institutions)
provinces = Vocabulary()
provinces.identifier = IrokoVocabularyIdentifiers.CUBAN_PROVINCES.value
provinces.human_name = 'Provincias Cubanas'
db.session.add(provinces)
grupo_mes = Vocabulary()
grupo_mes.identifier = IrokoVocabularyIdentifiers.INDEXES_CLASIFICATION.value
grupo_mes.human_name = 'Clasificaciones de Bases de Datos e Indizadores'
db.session.add(grupo_mes)
licences = Vocabulary()
licences.identifier = IrokoVocabularyIdentifiers.LICENCES.value
licences.human_name = 'Licencias'
db.session.add(licences)
record_sets = Vocabulary()
record_sets.identifier = IrokoVocabularyIdentifiers.RECOD_SETS.value
record_sets.human_name = 'Conjuntos de Articulos'
db.session.add(record_sets)
# record_set is clasified as record_type
record_types = Vocabulary()
record_types.identifier = IrokoVocabularyIdentifiers.RECORD_TYPES.value
record_types.human_name = 'Tipos de Articulos'
db.session.add(record_types)
db.session.commit()
init_vocabulary(tax, 'institutions', institutions)
init_vocabulary(tax, 'provinces', provinces)
init_vocabulary(tax, 'grupo_mes', grupo_mes)
init_vocabulary(tax, 'licences', licences)