netcdf-c/libnczarr/zclose.c

292 lines
7.4 KiB
C
Raw Normal View History

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.
2020-06-29 08:02:47 +08:00
/*********************************************************************
* Copyright 1993, UCAR/Unidata
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*********************************************************************/
#include "zincludes.h"
/* Forward */
static int zclose_group(NC_GRP_INFO_T*);
static int zclose_gatts(NC_GRP_INFO_T*);
static int zclose_vars(NC_GRP_INFO_T*);
static int zclose_dims(NC_GRP_INFO_T*);
static int zclose_types(NC_GRP_INFO_T*);
static int zclose_type(NC_TYPE_INFO_T* type);
static int zwrite_vars(NC_GRP_INFO_T *grp);
/**************************************************/
/**
* @internal This function will recurse through an open ZARR file and
* release resources. All ZARR annotations reclaimed
*
* @param file Pointer to ZARR file info struct.
* @param abort True if this is an abort.
*
* @return ::NC_NOERR No error.
* @return ::NC_ENCZARR could not close the file.
* @author Dennis Heimbigner
*/
int
ncz_close_file(NC_FILE_INFO_T* file, int abort)
{
int stat = NC_NOERR;
NCZ_FILE_INFO_T* zinfo = NULL;
if(!abort) {
/* Flush | create all chunks for all vars */
if((stat=zwrite_vars(file->root_grp))) goto done;
}
/* Internal close to reclaim zarr annotations */
if((stat = zclose_group(file->root_grp)))
goto done;
zinfo = file->format_file_info;
if((stat = nczmap_close(zinfo->map,(abort && zinfo->created)?1:0)))
goto done;
NCZ_freestringvec(0,zinfo->controls);
NC_authfree(zinfo->auth);
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.
2020-06-29 08:02:47 +08:00
nullfree(zinfo);
done:
return stat;
}
/**************************************************/
/**
* @internal Recursively free zarr annotations for a group (and everything
* it contains).
*
* @param grp Pointer to group info struct.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zclose_group(NC_GRP_INFO_T *grp)
{
int stat = NC_NOERR;
NCZ_GRP_INFO_T* zgrp;
int i;
assert(grp && grp->format_grp_info != NULL);
LOG((3, "%s: grp->name %s", __func__, grp->hdr.name));
/* Recursively call this function for each child, if any, stopping
* if there is an error. */
for(i=0; i<ncindexsize(grp->children); i++) {
if ((stat = zclose_group((NC_GRP_INFO_T*)ncindexith(grp->children,i))))
goto done;
}
/* Close resources associated with global attributes. */
if ((stat = zclose_gatts(grp)))
goto done;
/* Close resources associated with vars. */
if ((stat = zclose_vars(grp)))
goto done;
/* Close resources associated with dims. */
if ((stat = zclose_dims(grp)))
goto done;
/* Close resources associated with types. */
if ((stat = zclose_types(grp)))
goto done;
/* Close the zgroup. */
zgrp = grp->format_grp_info;
LOG((4, "%s: closing group %s", __func__, grp->hdr.name));
nullfree(zgrp);
grp->format_grp_info = NULL; /* avoid memory errors */
done:
return stat;
}
/**
* @internal Close resources for global atts in a group.
*
* @param grp Pointer to group info struct.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zclose_gatts(NC_GRP_INFO_T* grp)
{
int stat = NC_NOERR;
NC_ATT_INFO_T *att;
int a;
for(a = 0; a < ncindexsize(grp->att); a++) {
NCZ_ATT_INFO_T* zatt = NULL;
att = (NC_ATT_INFO_T* )ncindexith(grp->att, a);
assert(att && att->format_att_info != NULL);
zatt = att->format_att_info;
nullfree(zatt);
att->format_att_info = NULL; /* avoid memory errors */
}
return stat;
}
/**
* @internal Close resources for vars in a group.
*
* @param grp Pointer to group info struct.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zclose_vars(NC_GRP_INFO_T* grp)
{
int stat = NC_NOERR;
NC_VAR_INFO_T* var;
NCZ_VAR_INFO_T* zvar;
NC_ATT_INFO_T* att;
int a, i;
for(i = 0; i < ncindexsize(grp->vars); i++) {
var = (NC_VAR_INFO_T*)ncindexith(grp->vars, i);
assert(var && var->format_var_info);
zvar = var->format_var_info;;
for(a = 0; a < ncindexsize(var->att); a++) {
NCZ_ATT_INFO_T* zatt;
att = (NC_ATT_INFO_T*)ncindexith(var->att, a);
assert(att && att->format_att_info);
zatt = att->format_att_info;
nullfree(zatt);
att->format_att_info = NULL; /* avoid memory errors */
}
Mostly revert the filter code to reduce its complexity of use. re: https://github.com/Unidata/netcdf-c/issues/1836 Revert the internal filter code to simplify it. From the user's point of view, the only visible changes should be: 1. The functions that convert text to filter specs have had their signature reverted and have been moved to netcdf_aux.h 2. Some filter API functions now return NC_ENOFILTER when inquiry is made about some filter. Internally,the dispatch table has been modified to get rid of the filter_actions entry and associated complex structures. It has been replaced with inq_var_filter_ids and inq_var_filter_info entries and the dispatch table version has been bumped to 3. Corresponding NOOP and NOTNC4 functions were added to libdispatch/dnotnc4.c. Also, the filter_action entries in dispatch tables were replaced for all dispatch code bases (HDF5, DAP2, etc). This should only impact UDF users. In the process, it became clear that the form of the filters field in NC_VAR_INFO_T was format dependent, so I converted it to be of type void* and pushed its management into the various dispatch code bases. Specifically libhdf5 and libnczarr now manage the filters field in their own way. The auxilliary functions for parsing textual filter specifications were moved to netcdf_aux.h and were renamed to the following: * ncaux_h5filterspec_parse * ncaux_h5filterspec_parselist * ncaux_h5filterspec_free * ncaux_h5filter_fix8 Misc. Other Changes: 1. Document NUG/filters.md updated to reflect the changes above. 2. All the old data types (structs and enums) used by filter_actions actions were deleted. The exception is the NC_H5_Filterspec because it is needed by ncaux_h5filterspec_parselist. 3. Clientside filters were removed -- another enhancement for which no-one ever asked. 4. The ability to remove filters was itself removed. 5. Some functionality needed by nczarr was moved from libhdf5 to libsrc4 e.g. nc4_find_default_chunksizes 6. All the filterx code was removed 7. ncfilter.h and nc4filter.c no longer used Misc. Unrelated Changes: 1. The nczarr_test makefile clean was leaving some directories; so add clean-local to take care of them.
2020-09-28 02:43:46 +08:00
/* Reclaim filters */
if(var->filters != NULL) {
(void)NCZ_filter_freelist(var);
}
var->filters = NULL;
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.
2020-06-29 08:02:47 +08:00
/* Reclaim the type */
(void)zclose_type(var->type_info);
NCZ_free_chunk_cache(zvar->cache);
nullfree(zvar);
var->format_var_info = NULL; /* avoid memory errors */
}
return stat;
}
/**
* @internal Close resources for dims in a group.
*
* @param grp Pointer to group info struct.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zclose_dims(NC_GRP_INFO_T* grp)
{
int stat = NC_NOERR;
NC_DIM_INFO_T* dim;
int i;
for(i = 0; i < ncindexsize(grp->dim); i++) {
NCZ_DIM_INFO_T* zdim;
dim = (NC_DIM_INFO_T*)ncindexith(grp->dim, i);
assert(dim && dim->format_dim_info);
zdim = dim->format_dim_info;
nullfree(zdim);
dim->format_dim_info = NULL; /* avoid memory errors */
}
return stat;
}
/**
* @internal Close resources for a single type. Set values to
* 0 after closing types. Because of type reference counters, these
* closes can be called multiple times.
*
* @param type Pointer to type struct.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zclose_type(NC_TYPE_INFO_T* type)
{
int stat = NC_NOERR;
NCZ_TYPE_INFO_T* ztype;
assert(type && type->format_type_info != NULL);
/* Get Zarr-specific type info. */
ztype = type->format_type_info;
nullfree(ztype);
type->format_type_info = NULL; /* avoid memory errors */
return stat;
}
/**
* @internal Close resources for types in a group. Set values to
* 0 after closing types. Because of type reference counters, these
* closes can be called multiple times.
* Warning: note that atomic types are not covered here; this
* is only for user-defined types.
*
* @param grp Pointer to group info struct.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zclose_types(NC_GRP_INFO_T* grp)
{
int stat = NC_NOERR;
int i;
NC_TYPE_INFO_T* type;
for(i = 0; i < ncindexsize(grp->type); i++)
{
type = (NC_TYPE_INFO_T*)ncindexith(grp->type, i);
if((stat = zclose_type(type))) goto done;
}
done:
return stat;
}
/**
* @internal Recursively flush/create all data for all vars.
*
* @param grp Pointer to group info struct whose vars need to be written
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner
*/
static int
zwrite_vars(NC_GRP_INFO_T *grp)
{
int stat = NC_NOERR;
int i;
assert(grp && grp->format_grp_info != NULL);
LOG((3, "%s: grp->name %s", __func__, grp->hdr.name));
/* Write all vars for this group breadth first */
for(i = 0; i < ncindexsize(grp->vars); i++) {
NC_VAR_INFO_T* var = (NC_VAR_INFO_T*)ncindexith(grp->vars, i);
if((stat = ncz_write_var(var))) goto done;
}
/* Recursively call this function for each child group, if any, stopping
* if there is an error. */
for(i=0; i<ncindexsize(grp->children); i++) {
if ((stat = zwrite_vars((NC_GRP_INFO_T*)ncindexith(grp->children,i))))
goto done;
}
done:
return stat;
}