def import_upload(dataset_name, id, account_id,
entity_col, alias_col):
dataset = Dataset.find(dataset_name)
account = Account.by_id(account_id)
metadata, row_set = parse_upload(dataset, id)
headers = detect_headers(row_set)
for row in row_set:
data = dict([(c.column, c.value) for c in row])
entity = data.pop(entity_col) if entity_col else None
alias = data.pop(alias_col) if alias_col else None
if alias_col and alias is not None and len(alias) and alias != entity:
d = {'name': alias, 'data': data}
alias_obj = Alias.lookup(dataset, d, account,
match_entity=False)
data = {}
if entity_col and entity is not None and len(entity):
d = {'name': entity, 'data': data}
entity_obj = Entity.by_name(dataset, entity)
if entity_obj is None:
entity_obj = Entity.create(dataset, d, account)
entity_obj.data = data
if alias_col and entity_col:
alias_obj.match(dataset, {'choice': entity_obj.id}, account)
db.session.commit()
flush_cache(dataset)
def update(self, data, account):
state = EntityState(self.dataset, self)
data = EntitySchema().to_python(data, state)
self.creator = account
self.name = data['name']
self.data = data['data']
flush_cache(self.dataset)
db.session.add(self)
def update(self, data, account):
state = EntityState(self.dataset, self)
data = EntitySchema().to_python(data, state)
self.creator = account
self.name = data['name']
self.data = data['data']
flush_cache(self.dataset)
db.session.add(self)
def create(cls, data, account):
data = DatasetNewSchema().to_python(data)
dataset = cls()
dataset.owner = account
dataset.name = data['name']
dataset.label = data['label']
db.session.add(dataset)
db.session.flush()
flush_cache(dataset)
return dataset
def create(cls, data, account):
data = DatasetNewSchema().to_python(data)
dataset = cls()
dataset.owner = account
dataset.name = data['name']
dataset.label = data['label']
db.session.add(dataset)
db.session.flush()
flush_cache(dataset)
return dataset
def update(self, data):
data = DatasetEditSchema().to_python(data)
self.label = data['label']
self.normalize_text = data['normalize_text']
self.ignore_case = data['ignore_case']
self.public_edit = data['public_edit']
self.match_aliases = data['match_aliases']
self.enable_invalid = data['enable_invalid']
self.algorithm = data['algorithm']
db.session.add(self)
db.session.flush()
flush_cache(self)
def update(dataset):
dataset = Dataset.find(dataset)
authz.require(authz.dataset_manage(dataset))
data = request_content()
try:
flush_cache(dataset)
dataset.update(data)
db.session.commit()
flash("Updated %s" % dataset.label, 'success')
return redirect(url_for('.view', dataset=dataset.name))
except Invalid, inv:
return handle_invalid(inv, edit, args=[dataset.name], data=data)
def update(self, data):
data = DatasetEditSchema().to_python(data)
self.label = data['label']
self.normalize_text = data['normalize_text']
self.ignore_case = data['ignore_case']
self.public_edit = data['public_edit']
self.match_aliases = data['match_aliases']
self.enable_invalid = data['enable_invalid']
self.algorithm = data['algorithm']
db.session.add(self)
db.session.flush()
flush_cache(self)
def update(dataset):
dataset = Dataset.find(dataset)
authz.require(authz.dataset_manage(dataset))
data = request_content()
try:
flush_cache(dataset)
dataset.update(data)
db.session.commit()
flash("Updated %s" % dataset.label, 'success')
return redirect(url_for('.view', dataset=dataset.name))
except Invalid, inv:
return handle_invalid(inv, edit,
args=[dataset.name], data=data)
def merge(dataset, value):
dataset = Dataset.find(dataset)
authz.require(authz.dataset_edit(dataset))
value = Value.find(dataset, value)
data = request_content()
try:
target = value.merge_into(data, request.account)
flush_cache(dataset)
db.session.commit()
flash("Merged %s" % value.value, 'success')
return redirect(url_for('.view', dataset=dataset.name,
value=target.id))
except Invalid, inv:
print inv
return handle_invalid(inv, view, data=data,
args=[dataset.name, value.id])
def merge_into(self, data, account):
from nomenklatura.model.alias import Alias
state = EntityState(self.dataset, self)
data = EntityMergeSchema().to_python(data, state)
target = data.get('target')
for alias in self.aliases:
alias.entity = target
alias = Alias()
alias.name = self.name
alias.creator = self.creator
alias.matcher = account
alias.entity = target
alias.dataset = self.dataset
alias.is_matched = True
db.session.delete(self)
db.session.add(alias)
db.session.commit()
flush_cache(self.dataset)
return target
def merge_into(self, data, account):
from nomenklatura.model.alias import Alias
state = EntityState(self.dataset, self)
data = EntityMergeSchema().to_python(data, state)
target = data.get('target')
for alias in self.aliases:
alias.value = target
alias = Alias()
alias.name = self.name
alias.creator = self.creator
alias.matcher = account
alias.entity = target
alias.dataset = self.dataset
alias.is_matched = True
db.session.delete(self)
db.session.add(alias)
db.session.commit()
flush_cache(self.dataset)
return target
def import_upload(dataset_name, sig, account_id, entity_col, alias_col):
dataset = Dataset.find(dataset_name)
account = Account.by_id(account_id)
metadata, row_set = parse_upload(dataset, sig)
headers = detect_headers(row_set)
for row in row_set:
data = dict([(c.column, c.value) for c in row])
entity = data.pop(entity_col) if entity_col else None
alias = data.pop(alias_col) if alias_col else None
if alias_col and alias is not None and len(alias) and alias != entity:
d = {'name': alias, 'data': data}
alias_obj = Alias.lookup(dataset, d, account, match_entity=False)
data = {}
if entity_col and entity is not None and len(entity):
d = {'name': entity, 'data': data}
entity_obj = Entity.by_name(dataset, entity)
if entity_obj is None:
entity_obj = Entity.create(dataset, d, account)
entity_obj.data = data
if alias_col and entity_col:
alias_obj.match(dataset, {'choice': entity_obj.id}, account)
db.session.commit()
flush_cache()