netcdf-c/nczarr_test/z4dump.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

151 lines
3.2 KiB
C

/*
* Copyright 2018, University Corporation for Atmospheric Research
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*/
#include "ut_includes.h"
#define DATANAME "data"
#define OPT_NONE 0
#define OPT_OBJDUMP 1
#define OPT_TYPE 2
/* Command line options */
struct Options {
int debug;
int typetag;
int action;
char* infile;
} options;
/* Forward */
static int objdump(void);
#define NCCHECK(expr) nccheck((expr),__LINE__)
void nccheck(int stat, int line)
{
if(stat) {
fprintf(stderr,"%d: %s\n",line,nc_strerror(stat));
fflush(stderr);
exit(1);
}
}
static void
usage(void)
{
fprintf(stderr,"usage: z4dump <options> <file>\n");
exit(1);
}
int
main(int argc, char** argv)
{
int stat = NC_NOERR;
int c;
memset((void*)&options,0,sizeof(options));
/* Set defaults */
options.action = OPT_OBJDUMP;
while ((c = getopt(argc, argv, "dt")) != EOF) {
switch(c) {
case 'd':
options.debug = 1;
break;
case 't':
options.typetag = 1;
break;
case 'v':
usage();
goto done;
case '?':
fprintf(stderr,"unknown option\n");
goto fail;
}
}
/* get file argument */
argc -= optind;
argv += optind;
if (argc > 1) {
fprintf(stderr, "z4dump: only one input file argument permitted\n");
goto fail;
}
if (argc == 0) {
fprintf(stderr, "z4dump: no input file specified\n");
goto fail;
}
options.infile = strdup(argv[0]);
switch (options.action) {
case OPT_OBJDUMP:
if((stat = objdump())) goto done;
break;
default:
fprintf(stderr,"Unimplemented action\n");
goto fail;
}
done:
if(stat)
nc_strerror(stat);
return (stat ? 1 : 0);
fail:
stat = NC_EINVAL;
goto done;
}
static int
objdump(void)
{
int stat = NC_NOERR;
int i, ncid, grpid;
size_t len;
char* name = NULL;
NClist* stack = nclistnew(); /* stack for depth first walk */
int ngrps;
int* subgrps = NULL;
NCCHECK(nc_open(options.infile,NC_NETCDF4,&ncid));
/* Depth first walk all the groups */
nclistpush(stack,(void*)(uintptr_t)ncid);
while(nclistlength(stack) > 0) {
grpid = (uintptr_t)nclistget(stack,0); /* zero pos is always top of stack */
nclistremove(stack,0); /* pop stack */
NCCHECK(nc_inq_grpname_full(grpid,&len,NULL));
if((name = malloc(len+1)) == NULL)
{stat = NC_ENOMEM; goto done;}
NCCHECK(nc_inq_grpname_full(grpid,&len,name));
name[len] = '\0';
printf("%s",name);
if(options.typetag) {
int varid;
if((stat=nc_get_att_text(grpid,NC_GLOBAL,DATANAME,NULL)) == NC_NOERR) {
printf("(M)");
} else if((stat=nc_inq_varid(grpid,DATANAME,&varid)) == NC_NOERR) {
printf("(D)");
}
}
printf("\n");
nullfree(name); name = NULL; /* cleanup */
/* Get subgroups of grpid and push onto the stack in proper order */
NCCHECK(nc_inq_grps(grpid,&ngrps,NULL));
if(ngrps > 0) {
if((subgrps = malloc(sizeof(int)*ngrps)) == NULL)
{stat = NC_ENOMEM; goto done;}
NCCHECK(nc_inq_grps(grpid,&ngrps,subgrps));
for(i=(ngrps-1);i>=0;i--) {
nclistinsert(stack,0,(void*)(uintptr_t)subgrps[i]); /* push in order */
}
}
}
done:
return stat;
}