def make_new_dset(parent, shape=None, dtype=None, data=None,
                 chunks=None, compression=None, shuffle=None,
                    fletcher32=None, maxshape=None, compression_opts=None,
                  fillvalue=None, scaleoffset=None, track_times=None):
    """ Return a new low-level dataset identifier

    Only creates anonymous datasets.
    """

    # Convert data to a C-contiguous ndarray
    if data is not None:
        import base
        data = numpy.asarray(data, order="C", dtype=base.guess_dtype(data))

    # Validate shape
    if shape is None:
        if data is None:
            raise TypeError("Either data or shape must be specified")
        shape = data.shape
    else:
        shape = tuple(shape)
        if data is not None and (numpy.product(shape) != numpy.product(data.shape)):
            raise ValueError("Shape tuple is incompatible with data")

    tmp_shape = maxshape if maxshape is not None else shape
    # Validate chunk shape
    if isinstance(chunks, tuple) and (-numpy.array([ i>=j for i,j in zip(tmp_shape,chunks) if i is not None])).any():
        errmsg = "Chunk shape must not be greater than data shape in any dimension. "\
                 "{} is not compatible with {}".format(chunks, shape)
        raise ValueError(errmsg)

    if isinstance(dtype, h5py.Datatype):
        # Named types are used as-is
        tid = dtype.id
        dtype = tid.dtype  # Following code needs this
    else:
        # Validate dtype
        if dtype is None and data is None:
            dtype = numpy.dtype("=f4")
        elif dtype is None and data is not None:
            dtype = data.dtype
        else:
            dtype = numpy.dtype(dtype)
        tid = h5t.py_create(dtype, logical=1)

    # Legacy
    if any((compression, shuffle, fletcher32, maxshape,scaleoffset)) and chunks is False:
        raise ValueError("Chunked format required for given storage options")

    # Legacy
    if compression is True:
        if compression_opts is None:
            compression_opts = 4
        compression = 'gzip'

    # Legacy
    if compression in _LEGACY_GZIP_COMPRESSION_VALS:
        if compression_opts is not None:
            raise TypeError("Conflict in compression options")
        compression_opts = compression
        compression = 'gzip'

    dcpl = filters.generate_dcpl(shape, dtype, chunks, compression, compression_opts,
                  shuffle, fletcher32, maxshape, scaleoffset)

    if fillvalue is not None:
        fillvalue = numpy.array(fillvalue)
        dcpl.set_fill_value(fillvalue)

    if track_times in (True, False):
        dcpl.set_obj_track_times(track_times)
    elif track_times is not None:
        raise TypeError("track_times must be either True or False")

    if maxshape is not None:
        maxshape = tuple(m if m is not None else h5s.UNLIMITED for m in maxshape)
    sid = h5s.create_simple(shape, maxshape)


    dset_id = h5d.create(parent.id, None, tid, sid, dcpl=dcpl)

    if data is not None:
        dset_id.write(h5s.ALL, h5s.ALL, data)

    return dset_id
Beispiel #2
0
def make_new_dset(parent, shape=None, dtype=None, data=None,
                 chunks=None, compression=None, shuffle=None,
                    fletcher32=None, maxshape=None, compression_opts=None,
                  fillvalue=None, scaleoffset=None, track_times=None):
    """ Return a new low-level dataset identifier

    Only creates anonymous datasets.
    """

    # Convert data to a C-contiguous ndarray
    if data is not None:
        import base
        data = numpy.asarray(data, order="C", dtype=base.guess_dtype(data))

    # Validate shape
    if shape is None:
        if data is None:
            raise TypeError("Either data or shape must be specified")
        shape = data.shape
    else:
        shape = tuple(shape)
        if data is not None and (numpy.product(shape) != numpy.product(data.shape)):
            raise ValueError("Shape tuple is incompatible with data")

    # Validate dtype
    if dtype is None and data is None:
        dtype = numpy.dtype("=f4")
    elif dtype is None and data is not None:
        dtype = data.dtype
    else:
        dtype = numpy.dtype(dtype)

    # Legacy
    if any((compression, shuffle, fletcher32, maxshape,scaleoffset)) and chunks is False:
        raise ValueError("Chunked format required for given storage options")

    # Legacy
    if compression is True:
        if compression_opts is None:
            compression_opts = 4
        compression = 'gzip'

    # Legacy
    if compression in range(10):
        if compression_opts is not None:
            raise TypeError("Conflict in compression options")
        compression_opts = compression
        compression = 'gzip'

    dcpl = filters.generate_dcpl(shape, dtype, chunks, compression, compression_opts,
                  shuffle, fletcher32, maxshape, scaleoffset)

    if fillvalue is not None:
        fillvalue = numpy.array(fillvalue)
        dcpl.set_fill_value(fillvalue)

    if track_times in (True, False):
        dcpl.set_obj_track_times(track_times)
    elif track_times is not None:
        raise TypeError("track_times must be either True or False")

    if maxshape is not None:
        maxshape = tuple(m if m is not None else h5s.UNLIMITED for m in maxshape)
    sid = h5s.create_simple(shape, maxshape)
    tid = h5t.py_create(dtype, logical=1)

    dset_id = h5d.create(parent.id, None, tid, sid, dcpl=dcpl)

    if data is not None:
        dset_id.write(h5s.ALL, h5s.ALL, data)

    return dset_id
Beispiel #3
0
def make_new_dset(parent,
                  shape=None,
                  dtype=None,
                  data=None,
                  chunks=None,
                  compression=None,
                  shuffle=None,
                  fletcher32=None,
                  maxshape=None,
                  compression_opts=None,
                  fillvalue=None,
                  scaleoffset=None,
                  track_times=None):
    """ Return a new low-level dataset identifier

    Only creates anonymous datasets.
    """

    # Convert data to a C-contiguous ndarray
    if data is not None:
        import base
        data = numpy.asarray(data, order="C", dtype=base.guess_dtype(data))

    # Validate shape
    if shape is None:
        if data is None:
            raise TypeError("Either data or shape must be specified")
        shape = data.shape
    else:
        shape = tuple(shape)
        if data is not None and (numpy.product(shape) != numpy.product(
                data.shape)):
            raise ValueError("Shape tuple is incompatible with data")

    tmp_shape = maxshape if maxshape is not None else shape
    # Validate chunk shape
    if isinstance(chunks, tuple) and (-numpy.array(
        [i >= j for i, j in zip(tmp_shape, chunks) if i is not None])).any():
        errmsg = "Chunk shape must not be greater than data shape in any dimension. "\
                 "{} is not compatible with {}".format(chunks, shape)
        raise ValueError(errmsg)

    if isinstance(dtype, h5py.Datatype):
        # Named types are used as-is
        tid = dtype.id
        dtype = tid.dtype  # Following code needs this
    else:
        # Validate dtype
        if dtype is None and data is None:
            dtype = numpy.dtype("=f4")
        elif dtype is None and data is not None:
            dtype = data.dtype
        else:
            dtype = numpy.dtype(dtype)
        tid = h5t.py_create(dtype, logical=1)

    # Legacy
    if any((compression, shuffle, fletcher32, maxshape,
            scaleoffset)) and chunks is False:
        raise ValueError("Chunked format required for given storage options")

    # Legacy
    if compression is True:
        if compression_opts is None:
            compression_opts = 4
        compression = 'gzip'

    # Legacy
    if compression in _LEGACY_GZIP_COMPRESSION_VALS:
        if compression_opts is not None:
            raise TypeError("Conflict in compression options")
        compression_opts = compression
        compression = 'gzip'

    dcpl = filters.generate_dcpl(shape, dtype, chunks, compression,
                                 compression_opts, shuffle, fletcher32,
                                 maxshape, scaleoffset)

    if fillvalue is not None:
        fillvalue = numpy.array(fillvalue)
        dcpl.set_fill_value(fillvalue)

    if track_times in (True, False):
        dcpl.set_obj_track_times(track_times)
    elif track_times is not None:
        raise TypeError("track_times must be either True or False")

    if maxshape is not None:
        maxshape = tuple(m if m is not None else h5s.UNLIMITED
                         for m in maxshape)
    sid = h5s.create_simple(shape, maxshape)

    dset_id = h5d.create(parent.id, None, tid, sid, dcpl=dcpl)

    if data is not None:
        dset_id.write(h5s.ALL, h5s.ALL, data)

    return dset_id