netcdf-c/libdispatch/nc.c
Dennis Heimbigner bf2746b8ea Provide byte-range reading of remote datasets
re: issue https://github.com/Unidata/netcdf-c/issues/1251

Assume that you have the URL to a remote dataset
which is a normal netcdf-3 or netcdf-4 file.

This PR allows the netcdf-c to read that dataset's
contents as a netcdf file using HTTP byte ranges
if the remote server supports byte-range access.

Originally, this PR was set up to access Amazon S3 objects,
but it can also access other remote datasets such as those
provided by a Thredds server via the HTTPServer access protocol.
It may also work for other kinds of servers.

Note that this is not intended as a true production
capability because, as is known, this kind of access to
can be quite slow. In addition, the byte-range IO drivers
do not currently do any sort of optimization or caching.

An additional goal here is to gain some experience with
the Amazon S3 REST protocol.

This architecture and its use documented in
the file docs/byterange.dox.

There are currently two test cases:

1. nc_test/tst_s3raw.c - this does a simple open, check format, close cycle
   for a remote netcdf-3 file and a remote netcdf-4 file.
2. nc_test/test_s3raw.sh - this uses ncdump to investigate some remote
   datasets.

This PR also incorporates significantly changed model inference code
(see the superceded PR https://github.com/Unidata/netcdf-c/pull/1259).

1. It centralizes the code that infers the dispatcher.
2. It adds support for byte-range URLs

Other changes:

1. NC_HDF5_finalize was not being properly called by nc_finalize().
2. Fix minor bug in ncgen3.l
3. fix memory leak in nc4info.c
4. add code to walk the .daprc triples and to replace protocol=
   fragment tag with a more general mode= tag.

Final Note:
Th inference code is still way too complicated. We need to move
to the validfile() model used by netcdf Java, where each
dispatcher is asked if it can process the file. This decentralizes
the inference code. This will be done after all the major new
dispatchers (PIO, Zarr, etc) have been implemented.
2019-01-01 18:27:36 -07:00

118 lines
2.8 KiB
C

/*
* Copyright 2018, University Corporation for Atmospheric Research
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*/
#include "config.h"
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#if defined(LOCKNUMREC) /* && _CRAYMPP */
# include <mpp/shmem.h>
# include <intrinsics.h>
#endif
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#include "ncdispatch.h"
int ncdebug = 0;
/* This is the default create format for nc_create and nc__create. */
static int default_create_format = NC_FORMAT_CLASSIC;
/* These have to do with version numbers. */
#define MAGIC_NUM_LEN 4
#define VER_CLASSIC 1
#define VER_64BIT_OFFSET 2
#define VER_HDF5 3
int
NC_check_id(int ncid, NC** ncpp)
{
NC* nc = find_in_NCList(ncid);
if(nc == NULL) return NC_EBADID;
if(ncpp) *ncpp = nc;
return NC_NOERR;
}
void
free_NC(NC *ncp)
{
if(ncp == NULL)
return;
if(ncp->path)
free(ncp->path);
if(ncp->model)
free(ncp->model);
/* We assume caller has already cleaned up ncp->dispatchdata */
#if _CRAYMPP && defined(LOCKNUMREC)
shfree(ncp);
#else
free(ncp);
#endif /* _CRAYMPP && LOCKNUMREC */
}
int
new_NC(NC_Dispatch* dispatcher, const char* path, int mode, NCmodel* model, NC** ncpp)
{
NC *ncp = (NC*)calloc(1,sizeof(NC));
if(ncp == NULL) return NC_ENOMEM;
ncp->dispatch = dispatcher;
ncp->path = nulldup(path);
ncp->mode = mode;
if((ncp->model = malloc(sizeof(NCmodel)))==NULL)
return NC_ENOMEM;
*ncp->model = *model; /* Make a copy */
if(ncp->path == NULL) { /* fail */
free_NC(ncp);
return NC_ENOMEM;
}
if(ncpp) {
*ncpp = ncp;
} else {
free_NC(ncp);
}
return NC_NOERR;
}
/* This function sets a default create flag that will be logically
or'd to whatever flags are passed into nc_create for all future
calls to nc_create.
Valid default create flags are NC_64BIT_OFFSET, NC_CLOBBER,
NC_LOCK, NC_SHARE. */
int
nc_set_default_format(int format, int *old_formatp)
{
/* Return existing format if desired. */
if (old_formatp)
*old_formatp = default_create_format;
/* Make sure only valid format is set. */
#ifndef ENABLE_CDF5
if (format == NC_FORMAT_CDF5)
return NC_ENOTBUILT;
#endif
#ifdef USE_HDF5
if (format != NC_FORMAT_CLASSIC && format != NC_FORMAT_64BIT_OFFSET &&
format != NC_FORMAT_NETCDF4 && format != NC_FORMAT_NETCDF4_CLASSIC &&
format != NC_FORMAT_CDF5)
return NC_EINVAL;
#else
if (format == NC_FORMAT_NETCDF4 || format == NC_FORMAT_NETCDF4_CLASSIC)
return NC_ENOTBUILT;
if (format != NC_FORMAT_CLASSIC && format != NC_FORMAT_64BIT_OFFSET &&
format != NC_FORMAT_CDF5)
return NC_EINVAL;
#endif
default_create_format = format;
return NC_NOERR;
}
int
nc_get_default_format(void)
{
return default_create_format;
}