netcdf-c/liblib/nc_initialize.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(see the superceded PR https://github.com/Unidata/netcdf-c/pull/1259).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

157 lines
3.2 KiB
C

/*********************************************************************
* Copyright 2018, UCAR/Unidata
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*********************************************************************/
#include "config.h"
#ifdef USE_PARALLEL
#include <mpi.h>
#endif
#include "ncdispatch.h"
extern int NC3_initialize(void);
extern int NC3_finalize(void);
#ifdef USE_NETCDF4
#include "nc4internal.h"
#include "hdf5internal.h"
extern int NC4_initialize(void);
extern int NC4_finalize(void);
#endif
#ifdef USE_HDF5
extern int NC_HDF5_initialize(void);
extern int NC_HDF5_finalize(void);
#endif
#ifdef ENABLE_DAP2
extern int NCD2_initialize(void);
extern int NCD2_finalize(void);
#endif
#ifdef ENABLE_DAP4
extern int NCD4_initialize(void);
extern int NCD4_finalize(void);
#endif
#ifdef USE_PNETCDF
extern int NCP_initialize(void);
extern int NCP_finalize(void);
#endif
#ifdef USE_HDF4
extern int NC_HDF4_initialize(void);
extern int NC_HDF4_finalize(void);
#endif
#ifdef _MSC_VER
#include <io.h>
#include <fcntl.h>
#endif
int NC_argc = 1;
char* NC_argv[] = {"nc_initialize",NULL};
int NC_initialized = 0;
int NC_finalized = 1;
/**
This procedure invokes all defined
initializers, and there is an initializer
for every known dispatch table.
So if you modify the format of NC_Dispatch,
then you need to fix it everywhere.
It also initializes appropriate external libraries.
*/
int
nc_initialize()
{
int stat = NC_NOERR;
if(NC_initialized) return NC_NOERR;
NC_initialized = 1;
NC_finalized = 0;
/* Do general initialization */
if((stat = NCDISPATCH_initialize())) goto done;
/* Initialize each active protocol */
if((stat = NC3_initialize())) goto done;
#ifdef ENABLE_DAP
if((stat = NCD2_initialize())) goto done;
#endif
#ifdef ENABLE_DAP4
if((stat = NCD4_initialize())) goto done;
#endif
#ifdef USE_PNETCDF
if((stat = NCP_initialize())) goto done;
#endif
#ifdef USE_NETCDF4
if((stat = NC4_initialize())) goto done;
#endif /* USE_NETCDF4 */
#ifdef USE_HDF5
if((stat = NC_HDF5_initialize())) goto done;
#endif
#ifdef USE_HDF4
if((stat = NC_HDF4_initialize())) goto done;
#endif
done:
return stat;
}
/**
This procedure invokes all defined
finalizers, and there should be one
for every known dispatch table.
So if you modify the format of NC_Dispatch,
then you need to fix it everywhere.
It also finalizes appropriate external libraries.
*/
int
nc_finalize(void)
{
int stat = NC_NOERR;
if(NC_finalized) return NC_NOERR;
NC_initialized = 0;
NC_finalized = 1;
/* Finalize each active protocol */
#ifdef ENABLE_DAP2
if((stat = NCD2_finalize())) return stat;
#endif
#ifdef ENABLE_DAP4
if((stat = NCD4_finalize())) return stat;
#endif
#ifdef USE_PNETCDF
if((stat = NCP_finalize())) return stat;
#endif
#ifdef USE_HDF4
if((stat = NC_HDF4_finalize())) return stat;
#endif /* USE_HDF4 */
#ifdef USE_NETCDF4
if((stat = NC4_finalize())) return stat;
#endif /* USE_NETCDF4 */
#ifdef USE_HDF5
if((stat = NC_HDF5_finalize())) return stat;
#endif
if((stat = NC3_finalize())) return stat;
/* Do general finalization */
if((stat = NCDISPATCH_finalize())) return stat;
return NC_NOERR;
}