def to_dict(self):
from nomenklatura.model.entity import Entity
num_aliases = Entity.all(self).filter(
Entity.canonical_id != None).count()
num_review = Entity.all(self).filter_by(reviewed=False).count()
num_entities = Entity.all(self).count()
num_invalid = Entity.all(self).filter_by(invalid=True).count()
return {
'id': self.id,
'name': self.name,
'label': self.label,
'owner': self.owner.to_dict(),
'stats': {
'num_aliases': num_aliases,
'num_entities': num_entities,
'num_review': num_review,
'num_invalid': num_invalid
},
'ignore_case': self.ignore_case,
'match_aliases': self.match_aliases,
'public_edit': self.public_edit,
'normalize_text': self.normalize_text,
'enable_invalid': self.enable_invalid,
'created_at': self.created_at,
'updated_at': self.updated_at
}
def suggest(dataset):
"""
Suggest API, emulates Google Refine API. See:
http://code.google.com/p/google-refine/wiki/SuggestApi
"""
dataset = Dataset.by_name(dataset)
entities = Entity.all().filter(Entity.invalid!=True)
query = request.args.get('prefix', '').strip()
entities = entities.filter(Entity.name.ilike('%s%%' % query))
entities = entities.offset(get_offset(field='start'))
entities = entities.limit(get_limit(default=20))
matches = []
for entity in entities:
matches.append({
'name': entity.name,
'n:type': {
'id': '/' + dataset.name,
'name': dataset.label
},
'id': entity.id
})
return jsonify({
"code" : "/api/status/ok",
"status" : "200 OK",
"prefix" : query,
"result" : matches
})
def review(dataset):
entities = Entity.all()
dataset = Dataset.find(dataset)
entities = entities.filter_by(dataset=dataset)
entities = entities.filter(Entity.reviewed==False)
entities = entities.offset(randint(0, entities.count()-1))
return jsonify(entities.first())
def index(dataset, format='json'):
dataset = Dataset.find(dataset)
q = Entity.all(dataset, eager=True)
if format == 'csv':
fn = csv_filename(dataset, 'entities')
headers = {'Content-Disposition': 'attachment; filename=' + fn}
return csvify(q, headers=headers)
return jsonify(q)
def _get_candidates(dataset):
for entity in Entity.all(dataset, eager_aliases=dataset.match_aliases):
candidate = normalize(entity.name, dataset)
yield candidate, entity.id
if dataset.match_aliases:
for link in entity.aliases_static:
candidate = normalize(link.name, dataset)
yield candidate, entity.id
def review(dataset):
entities = Entity.all()
dataset = Dataset.find(dataset)
entities = entities.filter_by(dataset=dataset)
entities = entities.filter(Entity.reviewed == False)
review_count = entities.count()
if review_count == 0:
return jsonify(None)
entities = entities.offset(randint(0, review_count - 1))
return jsonify(entities.first())
def index(dataset, format='json'):
dataset = Dataset.find(dataset)
q = Entity.all(dataset, eager=True)
if format == 'csv':
fn = csv_filename(dataset, 'entities')
headers = {
'Content-Disposition': 'attachment; filename=' + fn
}
return csvify(q, headers=headers)
return jsonify(q)
def review(dataset):
entities = Entity.all()
dataset = Dataset.find(dataset)
entities = entities.filter_by(dataset=dataset)
entities = entities.filter(Entity.reviewed == False) # noqa
review_count = entities.count()
if review_count == 0:
return jsonify(None)
entities = entities.offset(randint(0, review_count - 1))
return jsonify(entities.first())
def view(dataset):
dataset = Dataset.find(dataset)
format = response_format()
if format == 'json':
return jsonify(dataset)
unmatched = Alias.all_unmatched(dataset).count()
entities = Entity.all(dataset, query=request.args.get('query'))
pager = Pager(entities, '.view', dataset=dataset.name, limit=10)
return render_template('dataset/view.html',
entities=pager,
num_entities=len(pager),
num_aliases=Alias.all(dataset).count(),
invalid=Alias.all_invalid(dataset).count(),
query=request.args.get('query', ''),
dataset=dataset,
unmatched=unmatched)
def view(dataset):
dataset = Dataset.find(dataset)
format = response_format()
if format == 'json':
return jsonify(dataset)
unmatched = Alias.all_unmatched(dataset).count()
entities = Entity.all(dataset, query=request.args.get('query'))
pager = Pager(entities, '.view', dataset=dataset.name,
limit=10)
return render_template('dataset/view.html',
entities=pager,
num_entities=len(pager),
num_aliases=Alias.all(dataset).count(),
invalid=Alias.all_invalid(dataset).count(),
query=request.args.get('query', ''),
dataset=dataset, unmatched=unmatched)
def view(dataset):
dataset = Dataset.find(dataset)
format = response_format()
headers = {
'X-Dataset': dataset.name,
'Last-Modified': http_date(dataset.last_modified)
}
if format == 'json':
return jsonify(dataset, headers=headers)
unmatched = Alias.all_unmatched(dataset).count()
entities = Entity.all(dataset, query=request.args.get('query'))
pager = Pager(entities, '.view', dataset=dataset.name,
limit=10)
html = render_template('dataset/view.html',
entities=pager,
num_entities=len(pager),
num_aliases=Alias.all(dataset).count(),
invalid=Alias.all_invalid(dataset).count(),
query=request.args.get('query', ''),
dataset=dataset, unmatched=unmatched)
return Response(html, headers=headers)
def index():
entities = Entity.all()
dataset_arg = request.args.get('dataset')
if dataset_arg is not None:
dataset = Dataset.find(dataset_arg)
entities = entities.filter_by(dataset=dataset)
filter_name = request.args.get('filter_name', '')
if len(filter_name):
query = '%' + filter_name + '%'
entities = entities.filter(Entity.name.ilike(query))
# TODO, other filters.
format = request.args.get('format', 'json').lower().strip()
if format == 'csv':
res = csvify(entities)
else:
res = query_pager(entities)
if arg_bool('download'):
fn = dataset_filename(dataset, format)
res.headers['Content-Disposition'] = 'attachment; filename=' + fn
return res
def index():
entities = Entity.all()
dataset_arg = request.args.get('dataset')
if dataset_arg is not None:
dataset = Dataset.find(dataset_arg)
entities = entities.filter_by(dataset=dataset)
filter_name = request.args.get('filter_name', '')
if len(filter_name):
query = '%' + filter_name + '%'
entities = entities.filter(Entity.name.ilike(query))
# TODO, other filters.
format = request.args.get('format', 'json').lower().strip()
if format == 'csv':
res = csvify(entities)
else:
res = query_pager(entities)
if arg_bool('download'):
fn = dataset_filename(dataset, format)
res.headers['Content-Disposition'] = 'attachment; filename=' + fn
return res
def index():
entities = Entity.all()
dataset_arg = request.args.get("dataset")
if dataset_arg is not None:
dataset = Dataset.find(dataset_arg)
entities = entities.filter_by(dataset=dataset)
filter_name = request.args.get("filter_name", "")
if len(filter_name):
query = "%" + filter_name + "%"
entities = entities.filter(Entity.name.ilike(query))
# TODO, other filters.
format = request.args.get("format", "json").lower().strip()
if format == "csv":
res = csvify(entities)
else:
pager = Pager(entities)
res = jsonify(pager.to_dict())
if arg_bool("download"):
fn = dataset_filename(dataset, format)
res.headers["Content-Disposition"] = "attachment; filename=" + fn
return res
