report.py 文件源码

def merge_h5(in_filenames, out_filename):
    """ Merge a list of h5 files """
    out_h5 = h5.File(out_filename, 'a')
    for filename in in_filenames:
        if filename is None:
            continue
        in_h5 = h5.File(filename, 'r')
        for name in in_h5.keys():
            # If the dataset already exists,
            # They must be equal or one must be all-zero.
            if name in out_h5.keys():
                src_data, dest_data = in_h5[name][()], out_h5[name][()]
                if src_data.dtype.kind != 'S' and dest_data.dtype.kind != 'S':
                    # Both numeric
                    if not np.any(src_data):
                        # Source is all zero. Do nothing.
                        continue
                    elif not np.any(dest_data):
                        # Dest is all zero. Overwrite.
                        del out_h5[name]
                        h5.h5o.copy(in_h5.id, name, out_h5.id, name)
                    else:
                        # Both non-zero. Assert equality and do nothing.
                        assert np.array_equal(src_data, dest_data)
                else:
                    # Either are non-numeric. Assert equality and do nothing.
                    assert np.array_equal(src_data, dest_data)
            else:
                # Only exists in src. Copy to dest.
                h5.h5o.copy(in_h5.id, name, out_h5.id, name)

    out_h5.flush()
    out_h5.close()