"""Generate shared_fill_value.h5: datasets whose Fill Value message is
*shared*, in the two ways libhdf5 can share one.

- /sohm_a, /sohm_b: the file has a shared-object-header-message (SOHM) index
  for fill values, so libhdf5 stores the fill value (-7, int32) in the SOHM
  heap and /sohm_b's header holds only a reference to it. Chunked, with only
  the first chunk written, so the rest reads as the fill value.
- /unwritten_a, /unwritten_b: the same, never written: no storage at all,
  read entirely as the fill value.

h5py has no API for SOHM indexes, so the file creation property list is
configured by calling the libhdf5 bundled in the h5py wheel through ctypes.
Written with h5py 3.16.0 / HDF5 2.0.0. Re-run only to regenerate:

    python gen_shared_fill.py shared_fill_value.h5
"""
import ctypes
import glob
import os
import sys

import h5py
import numpy as np

libdir = os.path.join(os.path.dirname(os.path.dirname(h5py.__file__)), "h5py.libs")
libs = [p for p in glob.glob(os.path.join(libdir, "libhdf5*.so*")) if "_hl" not in os.path.basename(p)]
lib = ctypes.CDLL(libs[0])
lib.H5open()

H5O_SHMESG_FILL_FLAG = 1 << 0x0005

fcpl = h5py.h5p.create(h5py.h5p.FILE_CREATE)
lib.H5Pset_shared_mesg_nindexes.argtypes = [ctypes.c_int64, ctypes.c_uint]
lib.H5Pset_shared_mesg_index.argtypes = [ctypes.c_int64, ctypes.c_uint, ctypes.c_uint, ctypes.c_uint]
assert lib.H5Pset_shared_mesg_nindexes(fcpl.id, 1) >= 0
assert lib.H5Pset_shared_mesg_index(fcpl.id, 0, H5O_SHMESG_FILL_FLAG, 0) >= 0

fapl = h5py.h5p.create(h5py.h5p.FILE_ACCESS)
fapl.set_libver_bounds(h5py.h5f.LIBVER_LATEST, h5py.h5f.LIBVER_LATEST)
fid = h5py.h5f.create(sys.argv[1].encode(), h5py.h5f.ACC_TRUNC, fcpl=fcpl, fapl=fapl)
with h5py.File(fid) as f:
    # Chunked, with only the first chunk written: the rest reads as fill.
    # libhdf5 keeps the first copy of a message in its own header; the second
    # identical one (the `_b` datasets) is the SOHM reference.
    for name in ("sohm_a", "sohm_b"):
        d = f.create_dataset(name, shape=(8,), chunks=(4,), dtype="<i4", fillvalue=-7)
        d[:4] = np.arange(4)
    for name in ("unwritten_a", "unwritten_b"):
        f.create_dataset(name, shape=(3,), dtype="<i4", fillvalue=-7)