netcdf-c/libnczarr/zgrp.c
Dennis Heimbigner 59e04ae071 This PR adds EXPERIMENTAL support for accessing data in the
cloud using a variant of the Zarr protocol and storage
format. This enhancement is generically referred to as "NCZarr".

The data model supported by NCZarr is netcdf-4 minus the user-defined
types and the String type. In this sense it is similar to the CDF-5
data model.

More detailed information about enabling and using NCZarr is
described in the document NUG/nczarr.md and in a
[Unidata Developer's blog entry](https://www.unidata.ucar.edu/blogs/developer/en/entry/overview-of-zarr-support-in).

WARNING: this code has had limited testing, so do use this version
for production work. Also, performance improvements are ongoing.
Note especially the following platform matrix of successful tests:

Platform | Build System | S3 support
------------------------------------
Linux+gcc      | Automake     | yes
Linux+gcc      | CMake        | yes
Visual Studio  | CMake        | no

Additionally, and as a consequence of the addition of NCZarr,
major changes have been made to the Filter API. NOTE: NCZarr
does not yet support filters, but these changes are enablers for
that support in the future.  Note that it is possible
(probable?) that there will be some accidental reversions if the
changes here did not correctly mimic the existing filter testing.

In any case, previously filter ids and parameters were of type
unsigned int. In order to support the more general zarr filter
model, this was all converted to char*.  The old HDF5-specific,
unsigned int operations are still supported but they are
wrappers around the new, char* based nc_filterx_XXX functions.
This entailed at least the following changes:
1. Added the files libdispatch/dfilterx.c and include/ncfilter.h
2. Some filterx utilities have been moved to libdispatch/daux.c
3. A new entry, "filter_actions" was added to the NCDispatch table
   and the version bumped.
4. An overly complex set of structs was created to support funnelling
   all of the filterx operations thru a single dispatch
   "filter_actions" entry.
5. Move common code to from libhdf5 to libsrc4 so that it is accessible
   to nczarr.

Changes directly related to Zarr:
1. Modified CMakeList.txt and configure.ac to support both C and C++
   -- this is in support of S3 support via the awd-sdk libraries.
2. Define a size64_t type to support nczarr.
3. More reworking of libdispatch/dinfermodel.c to
   support zarr and to regularize the structure of the fragments
   section of a URL.

Changes not directly related to Zarr:
1. Make client-side filter registration be conditional, with default off.
2. Hack include/nc4internal.h to make some flags added by Ed be unique:
   e.g. NC_CREAT, NC_INDEF, etc.
3. cleanup include/nchttp.h and libdispatch/dhttp.c.
4. Misc. changes to support compiling under Visual Studio including:
   * Better testing under windows for dirent.h and opendir and closedir.
5. Misc. changes to the oc2 code to support various libcurl CURLOPT flags
   and to centralize error reporting.
6. By default, suppress the vlen tests that have unfixed memory leaks; add option to enable them.
7. Make part of the nc_test/test_byterange.sh test be contingent on remotetest.unidata.ucar.edu being accessible.

Changes Left TO-DO:
1. fix provenance code, it is too HDF5 specific.
2020-06-28 18:02:47 -06:00

175 lines
5.2 KiB
C

/* Copyright 2005-2018, University Corporation for Atmospheric
* Research. See COPYRIGHT file for copying and redistribution
* conditions. */
/**
* @file @internal This file is part of netcdf-4, a netCDF-like
* interface for NCZ, or a ZARR backend for netCDF, depending on your
* point of view.
*
* This file handles ZARR groups.
*
* @author Dennis Heimbigner, Ed Hartnett
*/
#include "zincludes.h"
/**
* @internal Create a group. Its ncid is returned in the new_ncid
* pointer.
*
* @param parent_ncid Parent group.
* @param name Name of new group.
* @param new_ncid Pointer that gets ncid for new group.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ESTRICTNC3 Classic model in use for this file.
* @return ::NC_ENOTNC4 Not a netCDF-4 file.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_def_grp(int parent_ncid, const char *name, int *new_ncid)
{
NC_GRP_INFO_T *grp, *g;
NC_FILE_INFO_T *h5;
char norm_name[NC_MAX_NAME + 1];
int stat;
LOG((2, "%s: parent_ncid 0x%x name %s", __func__, parent_ncid, name));
/* Find info for this file and group, and set pointer to each. */
if ((stat = nc4_find_grp_h5(parent_ncid, &grp, &h5)))
return stat;
assert(h5);
/* Check and normalize the name. */
if ((stat = nc4_check_name(name, norm_name)))
return stat;
/* Check that this name is not in use as a var, grp, or type. */
if ((stat = nc4_check_dup_name(grp, norm_name)))
return stat;
/* No groups in netcdf-3! */
if (h5->cmode & NC_CLASSIC_MODEL)
return NC_ESTRICTNC3;
/* If it's not in define mode, switch to define mode. */
if (!(h5->flags & NC_INDEF))
if ((stat = NCZ_redef(parent_ncid)))
return stat;
/* Update internal lists to reflect new group. The actual NCZ
* group creation will be done when metadata is written by a
* sync. */
if ((stat = nc4_grp_list_add(h5, grp, norm_name, &g)))
return stat;
if (!(g->format_grp_info = calloc(1, sizeof(NCZ_GRP_INFO_T))))
return NC_ENOMEM;
((NCZ_GRP_INFO_T*)g->format_grp_info)->common.file = h5;
/* For new groups, there are no atts to read from file. */
g->atts_read = 1;
/* Return the ncid to the user. */
if (new_ncid)
*new_ncid = grp->nc4_info->controller->ext_ncid | g->hdr.id;
return NC_NOERR;
}
/**
* @internal Rename a group.
*
* @param grpid Group ID.
* @param name New name for group.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ENOTNC4 Not a netCDF-4 file.
* @return ::NC_EPERM File opened read-only.
* @return ::NC_EBADGRPID Renaming root forbidden.
* @return ::NC_EHDFERR ZARR function returned error.
* @return ::NC_ENOMEM Out of memory.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_rename_grp(int grpid, const char *name)
{
NC_GRP_INFO_T *grp;
NC_FILE_INFO_T *h5;
char norm_name[NC_MAX_NAME + 1];
int stat;
LOG((2, "nc_rename_grp: grpid 0x%x name %s", grpid, name));
/* Find info for this file and group, and set pointer to each. */
if ((stat = nc4_find_grp_h5(grpid, &grp, &h5)))
return stat;
assert(h5 && grp && grp->format_grp_info);
if (h5->no_write)
return NC_EPERM; /* attempt to write to a read-only file */
/* Do not allow renaming the root group */
if (grp->parent == NULL)
return NC_EBADGRPID;
/* Check and normalize the name. */
if ((stat = nc4_check_name(name, norm_name)))
return stat;
/* Check that this name is not in use as a var, grp, or type in the
* parent group (i.e. the group that grp is in). */
if ((stat = nc4_check_dup_name(grp->parent, norm_name)))
return stat;
/* If it's not in define mode, switch to define mode. */
if (!(h5->flags & NC_INDEF))
if ((stat = NCZ_redef(grpid)))
return stat;
#ifdef LOOK
/* Rename the group, if it exists in the file */
if (zgrp->hdf_grpid)
{
ZGRP_INFO_T *parent_zgrp;
parent_zgrp = (ZGRP_INFO_T *)grp->parent->format_grp_info;
/* Close the group */
if (H5Gclose(zgrp->hdf_grpid) < 0)
return NC_EHDFERR;
zgrp->hdf_grpid = 0;
/* Attempt to rename & re-open the group, if the parent group is open */
if (parent_zgrp->hdf_grpid)
{
/* Rename the group. */
if (H5Lmove(parent_zgrp->hdf_grpid, grp->hdr.name,
parent_zgrp->hdf_grpid, name, H5P_DEFAULT,
H5P_DEFAULT) < 0)
return NC_EHDFERR;
/* Reopen the group, with the new name. */
if ((zgrp->hdf_grpid = H5Gopen2(parent_zgrp->hdf_grpid, name,
H5P_DEFAULT)) < 0)
return NC_EHDFERR;
}
}
#endif
/* Give the group its new name in metadata. UTF8 normalization
* has been done. */
free(grp->hdr.name);
if (!(grp->hdr.name = strdup(norm_name)))
return NC_ENOMEM;
/* Update the hash and rebuild index. */
grp->hdr.hashkey = NC_hashmapkey(grp->hdr.name,strlen(grp->hdr.name));
if(!ncindexrebuild(grp->parent->children))
return NC_EINTERNAL;
return NC_NOERR;
}