def _updateDataset_(self, parent, dataset_name, numpy_array, attributes,
**kwargs):
""" Update a dataset in the data file. If the dataset does not exist,
it is created. Returns a pointer to the dataset.
"""
dataset_key = safeDataKey(dataset_name)
if dataset_key not in parent.keys():
errmsg = "'%s' dataset is not in current data file."
raise IOError, errmsg % dataset_name
if len(numpy_array.shape) == 3:
parent[dataset_key][:, :, :] = numpy_array[:, :, :]
elif len(numpy_array.shape) == 2:
parent[dataset_key][:, :] = numpy_array[:, :]
elif len(numpy_array.shape) == 1:
parent[dataset_key][:] = numpy_array[:]
dataset = parent[dataset_key]
for attr_name, attr_value in attributes.items():
try:
dataset.attrs[safeDataKey(attr_name)] = safevalue(attr_value)
except Exception as e:
errmsg = "Could not set attribute '%s' to '%s' for dataset '%s'"
ds_name = dataset.name
if ds_name.startswith('/'): ds_name = ds_name[1:]
errmsg = errmsg % (attr_name, str(attr_value), ds_name)
e.args = (errmsg, ) + e.args
raise
return dataset
def __init__(self, name, access_key=None, **kwargs):
self.name = safeDataKey(name)
if access_key is None:
self.access_key = self.name
else:
self.access_key = safeDataKey(access_key)
for var_name in kwargs.keys():
setattr(self, var_name, kwargs[var_name])
def walkToObject(root_object, object_key):
if isinstance(object_key, basestring):
path = [safeDataKey(key) for key in object_key.split('.')]
else:
path = [safeDataKey(key) for key in object_key]
try:
_object = root_object[path[0]]
except KeyError:
raise KeyError, WALK_ERRMSG % (fullObjectPath(root_object), path[0])
if len(path) == 1: return _object
else:
return walkToObject(_object, path[1:])
def _getObjectAttribute_(self, _object, attr_name):
""" Returns a the value of a single attribute of an object
"""
try:
return _object.attrs[safeDataKey(attr_name)]
except Exception as e:
obj_name = fullObjectPath(_object)
if obj_name.startswith('/'): obj_name = obj_name[1:]
errmsg = "ERROR retrieving attribute '%s' from object '%s'"
e.args = (errmsg % (attr_name, obj_name), ) + e.args
raise e
def _setObjectAttribute_(self, _object, attr_name, attr_value):
""" Returns a dictionary of attr_name/attr_value pairs for all
setable attributes of the dataset indicates by dataset_key.
"""
try:
_object.attrs[safeDataKey(attr_name)] = safestring(attr_value)
except Exception as e:
errmsg = "Could not set attribute '%s' to '%s' for object '%s'"
obj_name = fullObjectPath(_object)
if obj_name.startswith('/'): obj_name = obj_name[1:]
errmsg = errmsg % (attr_name, str(attr_value), obj_name)
e.args = (errmsg, ) + e.args
def _deleteObjectAttribute_(self, _object, attr_name):
""" Deletes an attribute of an object.
"""
try:
del _object.attrs[safeDataKey(attr_name)]
except Exception as e:
errmsg = "Could not delete attribute '%s' of object '%s'"
obj_name = fullObjectPath(_object)
if obj_name.startswith('/'): obj_name = obj_name[1:]
errmsg = errmsg % (attr_name, obj_name)
e.args = (errmsg, ) + e.args
raise
def _getObject_(self, parent, object_key):
""" Returns the object indicated by object_key.
"""
try:
return parent[safeDataKey(object_key)]
except KeyError as e:
errmsg = "HDF5 file does not have a data object named '%s'"
e.args = (errmsg % object_key, ) + e.args
raise e
except Exception as e:
errmsg = "Error during attempt to access data object named '%s'"
e.args = (errmsg % object_key, ) + e.args
raise e
def _createGroup_(self, parent, group_name, **kwargs):
""" Creates a new group in the parent and returns a pointer to
it. Raises IOError exception if the group already exists.
"""
group_key = safeDataKey(group_name)
if group_key in parent.keys():
errmsg = "'%s' group already exists in %s"
raise IOError, errmsg % (group_name, fullObjectPath(parent))
group = parent.create_group(group_name)
if kwargs:
for attr_name, attr_value in kwargs.items():
self._setObjectAttribute_(group, attr_name, attr_value)
return group
def _createDataset_(self, parent, dataset_name, numpy_array, attributes,
**kwargs):
""" Creates a new dataset in the data file and returns a pointer to
it. Raises IOError exception if the dataset already exists.
"""
dataset_key = safeDataKey(dataset_name)
if dataset_key in parent.keys():
errmsg = "'%s' dataset already exists in current data file."
raise IOError, errmsg % dataset_name
create_args = {}
for arg_name in kwargs:
create_args[safe_name(arg_name)] = kwargs[arg_name]
if 'maxshape' in create_args:
if 'dtype' not in create_args:
raise IOError, "'dtype' is required for extendable datasets."
if len(numpy_array) != len(create_args['maxshape']):
errmg = '3rd argument must be the initial shape of the array.'
raise IOError, errmsg
initial_shape = numpy_array
dataset = parent.create_dataset(dataset_key, initial_shape,
**create_args)
else:
if 'dtype' not in create_args\
and numpy_array.dtype == N.dtype(object):
create_args['dtype'] = h5py.new_vlen(str)
dataset = parent.create_dataset(dataset_key,
data=numpy_array,
**create_args)
for attr_name, attr_value in attributes.items():
if attr_name != 'dtype' and attr_value is not None:
dataset.attrs[safeDataKey(attr_name)] = safevalue(attr_value)
return dataset
def getIndexedStations(self, metadata='all', criteria=None, sort_by=None):
manager = self.getFileManager('index', mode='r')
dataset_names = self._parseMetadata(metadata, manager)
_criteria = self._validCriteria(criteria, dataset_names)
datasets = manager.getDataWhere(dataset_names, _criteria)
manager.closeFile()
stations = []
for stn_indx in range(len(datasets[0])):
station = {}
for indx in range(len(dataset_names)):
station[safeDataKey(dataset_names[indx])] =\
safevalue(datasets[indx][stn_indx])
stations.append(station)
if sort_by is not None:
stations = self._sortStations(stations, sort_by)
return stations
def _deleteObject_(self, parent, object_key):
""" deletes the object indicated by object_key.
"""
key = safeDataKey(object_key)
if key in parent.keys(): del parent[key]
