def __getitem__(self, name):
""" Open an object in the file """
if isinstance(name, h5r.Reference):
oid = h5r.dereference(name, self.id)
if oid is None:
raise ValueError("Invalid HDF5 object reference")
else:
oid = h5o.open(self.id, self._e(name), lapl=self._shared.lapl)
otype = h5i.get_type(oid)
if otype == h5i.GROUP:
return Group(oid)
elif otype == h5i.DATASET:
return dataset.Dataset(oid)
elif otype == h5i.DATATYPE:
return datatype.Datatype(oid)
else:
raise TypeError("Unknown object type")
def __getitem__(self, name):
""" Open an object in the file """
if isinstance(name, h5r.Reference):
oid = h5r.dereference(name, self.id)
if oid is None:
raise ValueError("Invalid HDF5 object reference")
else:
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
otype = h5i.get_type(oid)
if otype == h5i.GROUP:
return Group(oid)
elif otype == h5i.DATASET:
return dataset.Dataset(oid)
elif otype == h5i.DATATYPE:
return datatype.Datatype(oid)
else:
raise TypeError("Unknown object type")
def __getitem__(self, args):
""" Read a slice from the HDF5 dataset.
Takes slices and recarray-style field names (more than one is
allowed!) in any order. Obeys basic NumPy rules, including
broadcasting.
Also supports:
* Boolean "mask" array indexing
"""
args = args if isinstance(args, tuple) else (args, )
# Sort field indices from the rest of the args.
names = tuple(x for x in args if isinstance(x, str))
args = tuple(x for x in args if not isinstance(x, str))
def strip_fields(basetype):
""" Strip extra dtype information from special types """
if basetype.kind == 'O':
return numpy.dtype('O')
if basetype.fields is not None:
if basetype.kind in ('i', 'u'):
return basetype.fields['enum'][0]
fields = []
for name in basetype.names:
fff = basetype.fields[name]
if len(fff) == 3:
(subtype, offset, meta) = fff
else:
subtype, meta = fff
offset = 0
subtype = strip_fields(subtype)
fields.append((name, subtype))
return numpy.dtype(fields)
return basetype
def readtime_dtype(basetype, names):
""" Make a NumPy dtype appropriate for reading """
basetype = strip_fields(basetype)
if len(names) == 0: # Not compound, or we want all fields
return basetype
if basetype.names is None: # Names provided, but not compound
raise ValueError("Field names only allowed for compound types")
for name in names: # Check all names are legal
if not name in basetype.names:
raise ValueError("Field %s does not appear in this type." %
name)
return numpy.dtype([(name, basetype.fields[name][0])
for name in names])
if self._local.astype is not None:
new_dtype = readtime_dtype(self._local.astype, names)
else:
# This is necessary because in the case of array types, NumPy
# discards the array information at the top level.
new_dtype = readtime_dtype(self.id.dtype, names)
mtype = h5t.py_create(new_dtype)
# === Special-case region references ====
if len(args) == 1 and isinstance(args[0], h5r.RegionReference):
obj = h5r.dereference(args[0], self.id)
if obj != self.id:
raise ValueError("Region reference must point to this dataset")
sid = h5r.get_region(args[0], self.id)
mshape = sel.guess_shape(sid)
if mshape is None:
return numpy.array((0, ), dtype=new_dtype)
if numpy.product(mshape) == 0:
return numpy.array(mshape, dtype=new_dtype)
out = numpy.empty(mshape, dtype=new_dtype)
sid_out = h5s.create_simple(mshape)
sid_out.select_all()
self.id.read(sid_out, sid, out, mtype)
return out
# === Check for zero-sized datasets =====
if numpy.product(self.shape) == 0:
# These are the only access methods NumPy allows for such objects
if args == (Ellipsis, ) or args == tuple():
return numpy.empty(self.shape, dtype=new_dtype)
# === Scalar dataspaces =================
if self.shape == ():
fspace = self.id.get_space()
selection = sel2.select_read(fspace, args)
arr = numpy.ndarray(selection.mshape, dtype=new_dtype)
for mspace, fspace in selection:
self.id.read(mspace, fspace, arr, mtype)
if len(names) == 1:
arr = arr[names[0]]
if selection.mshape is None:
return arr[()]
return arr
# === Everything else ===================
# Perform the dataspace selection.
selection = sel.select(self.shape, args, dsid=self.id)
if selection.nselect == 0:
return numpy.ndarray(selection.mshape, dtype=new_dtype)
# Up-converting to (1,) so that numpy.ndarray correctly creates
# np.void rows in case of multi-field dtype. (issue 135)
single_element = selection.mshape == ()
mshape = (1, ) if single_element else selection.mshape
arr = numpy.ndarray(mshape, new_dtype, order='C')
# HDF5 has a bug where if the memory shape has a different rank
# than the dataset, the read is very slow
if len(mshape) < len(self.shape):
# pad with ones
mshape = (1, ) * (len(self.shape) - len(mshape)) + mshape
# Perfom the actual read
mspace = h5s.create_simple(mshape)
fspace = selection._id
self.id.read(mspace, fspace, arr, mtype)
# Patch up the output for NumPy
if len(names) == 1:
arr = arr[names[0]] # Single-field recarray convention
if arr.shape == ():
arr = numpy.asscalar(arr)
if single_element:
arr = arr[0]
return arr
def __getitem__(self, args):
""" Read a slice from the HDF5 dataset.
Takes slices and recarray-style field names (more than one is
allowed!) in any order. Obeys basic NumPy rules, including
broadcasting.
Also supports:
* Boolean "mask" array indexing
"""
args = args if isinstance(args, tuple) else (args,)
# Sort field indices from the rest of the args.
names = tuple(x for x in args if isinstance(x, str))
args = tuple(x for x in args if not isinstance(x, str))
def strip_fields(basetype):
""" Strip extra dtype information from special types """
if basetype.kind == 'O':
return numpy.dtype('O')
if basetype.fields is not None:
if basetype.kind in ('i','u'):
return basetype.fields['enum'][0]
fields = []
for name in basetype.names:
fff = basetype.fields[name]
if len(fff) == 3:
(subtype, offset, meta) = fff
else:
subtype, meta = fff
offset = 0
subtype = strip_fields(subtype)
fields.append((name, subtype))
return numpy.dtype(fields)
return basetype
def readtime_dtype(basetype, names):
""" Make a NumPy dtype appropriate for reading """
basetype = strip_fields(basetype)
if len(names) == 0: # Not compound, or we want all fields
return basetype
if basetype.names is None: # Names provided, but not compound
raise ValueError("Field names only allowed for compound types")
for name in names: # Check all names are legal
if not name in basetype.names:
raise ValueError("Field %s does not appear in this type." % name)
return numpy.dtype([(name, basetype.fields[name][0]) for name in names])
if self._local.astype is not None:
new_dtype = readtime_dtype(self._local.astype, names)
else:
# This is necessary because in the case of array types, NumPy
# discards the array information at the top level.
new_dtype = readtime_dtype(self.id.dtype, names)
mtype = h5t.py_create(new_dtype)
# === Special-case region references ====
if len(args) == 1 and isinstance(args[0], h5r.RegionReference):
obj = h5r.dereference(args[0], self.id)
if obj != self.id:
raise ValueError("Region reference must point to this dataset")
sid = h5r.get_region(args[0], self.id)
mshape = sel.guess_shape(sid)
if mshape is None:
return np.array((0,), dtype=new_dtype)
if numpy.product(mshape) == 0:
return np.array(mshape, dtype=new_dtype)
out = numpy.empty(mshape, dtype=new_dtype)
sid_out = h5s.create_simple(mshape)
sid_out.select_all()
self.id.read(sid_out, sid, out, mtype)
return out
# === Check for zero-sized datasets =====
if numpy.product(self.shape) == 0:
# These are the only access methods NumPy allows for such objects
if args == (Ellipsis,) or args == tuple():
return numpy.empty(self.shape, dtype=new_dtype)
# === Scalar dataspaces =================
if self.shape == ():
fspace = self.id.get_space()
selection = sel2.select_read(fspace, args)
arr = numpy.ndarray(selection.mshape, dtype=new_dtype)
for mspace, fspace in selection:
self.id.read(mspace, fspace, arr, mtype)
if len(names) == 1:
arr = arr[names[0]]
if selection.mshape is None:
return arr[()]
return arr
# === Everything else ===================
# Perform the dataspace selection.
selection = sel.select(self.shape, args, dsid=self.id)
if selection.nselect == 0:
return numpy.ndarray(selection.mshape, dtype=new_dtype)
# Up-converting to (1,) so that numpy.ndarray correctly creates
# np.void rows in case of multi-field dtype. (issue 135)
single_element = selection.mshape == ()
mshape = (1,) if single_element else selection.mshape
arr = numpy.ndarray(mshape, new_dtype, order='C')
# HDF5 has a bug where if the memory shape has a different rank
# than the dataset, the read is very slow
if len(mshape) < len(self.shape):
# pad with ones
mshape = (1,)*(len(self.shape)-len(mshape)) + mshape
# Perfom the actual read
mspace = h5s.create_simple(mshape)
fspace = selection._id
self.id.read(mspace, fspace, arr, mtype)
# Patch up the output for NumPy
if len(names) == 1:
arr = arr[names[0]] # Single-field recarray convention
if arr.shape == ():
arr = numpy.asscalar(arr)
if single_element:
arr = arr[0]
return arr
def __getitem__(self, args, new_dtype=None):
""" Read a slice from the HDF5 dataset.
Takes slices and recarray-style field names (more than one is
allowed!) in any order. Obeys basic NumPy rules, including
broadcasting.
"""
# This boilerplate code is based on h5py.Dataset.__getitem__
args = args if isinstance(args, tuple) else (args, )
if new_dtype is None:
new_dtype = getattr(self._local, 'astype', None)
# Sort field names from the rest of the args.
names = tuple(x for x in args if isinstance(x, str))
if names:
# Read a subset of the fields in this structured dtype
if len(names) == 1:
names = names[0] # Read with simpler dtype of this field
args = tuple(x for x in args if not isinstance(x, str))
return self.fields(names, _prior_dtype=new_dtype)[args]
if new_dtype is None:
new_dtype = self.dtype
mtype = h5t.py_create(new_dtype)
# === Special-case region references ====
if len(args) == 1 and isinstance(args[0], h5r.RegionReference):
obj = h5r.dereference(args[0], self.id)
if obj != self.id:
raise ValueError("Region reference must point to this dataset")
sid = h5r.get_region(args[0], self.id)
mshape = guess_shape(sid)
if mshape is None:
# 0D with no data (NULL or deselected SCALAR)
return Empty(new_dtype)
out = np.empty(mshape, dtype=new_dtype)
if out.size == 0:
return out
sid_out = h5s.create_simple(mshape)
sid_out.select_all()
self.id.read(sid_out, sid, out, mtype)
return out
# === END CODE FROM h5py.Dataset.__getitem__ ===
idx = ndindex(args).reduce(self.shape)
arr = np.ndarray(idx.newshape(self.shape), new_dtype, order='C')
for c, index in as_subchunks(idx, self.shape, self.chunks):
if isinstance(self.id.data_dict[c], (slice, Slice, tuple, Tuple)):
raw_idx = Tuple(self.id.data_dict[c],
*[slice(0, len(i)) for i in c.args[1:]]).raw
a = self.id._read_chunk(raw_idx)
self.id.data_dict[c] = a
if self.id.data_dict[c].size != 0:
arr_idx = c.as_subindex(idx)
arr[arr_idx.raw] = self.id.data_dict[c][index.raw]
return arr
