def parse_header(self, elem):
values = self._collect('header', elem)
# Handle a reference to a DataStructureDefinition
attrs = {}
for k in ['id', 'agencyid', 'version', 'urn']:
value = values.pop('structure_ref_' + k, None)
if not value:
continue
elif k == 'agencyid':
attrs['maintainer'] = Agency(id=value)
else:
attrs[k] = value
if set(attrs.keys()) == {'urn'}:
attrs['id'] = values['structure_id']
if 'id' in attrs:
# Create the DSD and DFD
dsd = self._maintained(DataStructureDefinition, **attrs)
dfd = DataflowDefinition(id=values.pop('structure_id'),
structure=dsd)
# Also store the dimension at observation
self._set_obs_dim(values.pop('dim_at_obs'))
extra = [dfd]
else:
extra = []
# Maybe return the DFD; see .initialize()
return [Header(**values)] + extra
class DataMessage(Message):
#: :class:`list` of :class:`pandasdmx.model.DataSet`
data: List[DataSet] = []
dataflow: DataflowDefinition = DataflowDefinition()
# TODO infer the observation dimension from the DSD, e.g.
# - If a *TimeSeriesDataSet, it's the TimeDimension,
# - etc.
observation_dimension: Union[_AllDimensions, List[Dimension]] = None
# Convenience access
@property
def structure(self):
"""The DataStructureDefinition used in the DataMessage.dataflow."""
return self.dataflow.structure
def __repr__(self):
"""String representation."""
lines = [super().__repr__()]
# DataMessage contents
if len(self.data):
lines.append('DataSet ({})'.format(len(self.data)))
lines.extend(_summarize(self, ('dataflow', 'observation_dimension')))
return '\n '.join(lines)
class DataMessage(Message):
"""Data Message.
.. note:: A DataMessage may contain zero or more :class:`.DataSet`, so
:attr:`data` is a list. To retrieve the first (and possibly only)
data set in the message, access the first element of the list:
``msg.data[0]``.
"""
#: :class:`list` of :class:`.DataSet`.
data: List[DataSet] = []
#: :class:`.DataflowDefinition` that contains the data.
dataflow: DataflowDefinition = DataflowDefinition()
# TODO infer the observation dimension from the DSD, e.g.
# - If a *TimeSeriesDataSet, it's the TimeDimension,
# - etc.
observation_dimension: Union[_AllDimensions, List[Dimension]] = None
# Convenience access
@property
def structure(self):
"""DataStructureDefinition used in the :attr:`dataflow`."""
return self.dataflow.structure
def __repr__(self):
"""String representation."""
lines = [super().__repr__()]
# DataMessage contents
if self.data:
lines.append('DataSet ({})'.format(len(self.data)))
lines.extend(_summarize(self, ('dataflow', 'observation_dimension')))
return '\n '.join(lines)
def parse_header(self, elem):
# Collect values from *elem* and its children using XPath
values = {}
for key, xpath in HEADER_XPATH.items():
matches = xpath(elem)
if len(matches) == 0:
continue
values[key] = matches[0] if len(matches) == 1 else matches
# Handle a reference to a DataStructureDefinition
attrs = {}
for k in ['id', 'agencyid', 'version', 'urn']:
value = values.pop('structure_ref_' + k, None)
if not value:
continue
elif k == 'agencyid':
attrs['maintainer'] = Agency(id=value)
else:
attrs[k] = value
if set(attrs.keys()) == {'urn'}:
attrs['id'] = values['structure_id']
extra = []
if 'id' in attrs:
# Create or retrieve the DSD. NB if the dsd argument was provided
# to read_message(), this should be the same DSD
dsd = self._maintained(DataStructureDefinition, **attrs)
if 'structure_id' in values:
# Add the DSD to the index a second time, using the message
# -specific structure ID (rather that the DSD's own ID).
key = ('DataStructureDefinition', values['structure_id'])
self._index[key] = dsd
# Create a DataflowDefinition
dfd = DataflowDefinition(id=values.pop('structure_id'),
structure=dsd)
extra.append(dfd)
# Store the observation at dimension level
dim_at_obs = values.pop('dim_at_obs')
if dim_at_obs == 'AllDimensions':
self._obs_dim = AllDimensions
else:
# Retrieve or create the Dimension
args = dict(id=dim_at_obs, order=1e9)
if 'TimeSeries' in self._stack[0]:
# {,StructureSpecific}TimeSeriesData message → the
# dimension at observation level is a TimeDimension
args['cls'] = TimeDimension
self._obs_dim = dsd.dimensions.get(**args)
# Maybe return the DFD; see .initialize()
return [Header(**values)] + extra
def test_contentconstraint():
crole = ConstraintRole(role=ConstraintRoleType['allowable'])
cr = ContentConstraint(role=crole)
cr.content = {DataflowDefinition()}
cr.data_content_region = CubeRegion(included=True, member={})