mirror of
https://github.com/Unidata/netcdf-c.git
synced 2024-12-27 08:49:16 +08:00
bf2746b8ea
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 This PR also incorporates significantly changed model inference code (see the superceded PR https://github.com/Unidata/netcdf-c/pull/1259). 1.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.
129 lines
2.7 KiB
C
129 lines
2.7 KiB
C
/*********************************************************************
|
|
Copyright 2018, UCAR/Unidata See netcdf/COPYRIGHT file for
|
|
copying and redistribution conditions.
|
|
*********************************************************************/
|
|
|
|
#include "config.h"
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <assert.h>
|
|
#include "ncdispatch.h"
|
|
|
|
#define ID_SHIFT (16)
|
|
#define NCFILELISTLENGTH 0x10000
|
|
|
|
/* Version one just allocates the max space (sizeof(NC*)*2^16)*/
|
|
static NC** nc_filelist = NULL;
|
|
|
|
static int numfiles = 0;
|
|
|
|
/* Common */
|
|
int
|
|
count_NCList(void)
|
|
{
|
|
return numfiles;
|
|
}
|
|
|
|
|
|
void
|
|
free_NCList(void)
|
|
{
|
|
if(numfiles > 0) return; /* not empty */
|
|
if(nc_filelist != NULL) free(nc_filelist);
|
|
nc_filelist = NULL;
|
|
}
|
|
|
|
int
|
|
add_to_NCList(NC* ncp)
|
|
{
|
|
int i;
|
|
int new_id;
|
|
if(nc_filelist == NULL) {
|
|
if (!(nc_filelist = calloc(1, sizeof(NC*)*NCFILELISTLENGTH)))
|
|
return NC_ENOMEM;
|
|
numfiles = 0;
|
|
}
|
|
#ifdef USE_REFCOUNT
|
|
/* Check the refcount */
|
|
if(ncp->refcount > 0)
|
|
return NC_NOERR;
|
|
#endif
|
|
|
|
new_id = 0; /* id's begin at 1 */
|
|
for(i=1; i < NCFILELISTLENGTH; i++) {
|
|
if(nc_filelist[i] == NULL) {new_id = i; break;}
|
|
}
|
|
if(new_id == 0) return NC_ENOMEM; /* no more slots */
|
|
nc_filelist[new_id] = ncp;
|
|
numfiles++;
|
|
new_id = (new_id << ID_SHIFT);
|
|
ncp->ext_ncid = new_id;
|
|
return NC_NOERR;
|
|
}
|
|
|
|
void
|
|
del_from_NCList(NC* ncp)
|
|
{
|
|
unsigned int ncid = ((unsigned int)ncp->ext_ncid) >> ID_SHIFT;
|
|
if(numfiles == 0 || ncid == 0 || nc_filelist == NULL) return;
|
|
if(nc_filelist[ncid] != ncp) return;
|
|
#ifdef USE_REFCOUNT
|
|
/* Check the refcount */
|
|
if(ncp->refcount > 0)
|
|
return; /* assume caller has decrecmented */
|
|
#endif
|
|
|
|
nc_filelist[ncid] = NULL;
|
|
numfiles--;
|
|
|
|
/* If all files have been closed, release the filelist memory. */
|
|
if (numfiles == 0)
|
|
free_NCList();
|
|
}
|
|
|
|
NC *
|
|
find_in_NCList(int ext_ncid)
|
|
{
|
|
NC* f = NULL;
|
|
unsigned int ncid = ((unsigned int)ext_ncid) >> ID_SHIFT;
|
|
if(numfiles > 0 && nc_filelist != NULL && ncid < NCFILELISTLENGTH)
|
|
f = nc_filelist[ncid];
|
|
|
|
/* for classic files, ext_ncid must be a multiple of (1<<ID_SHIFT) */
|
|
if (f != NULL && f->model->impl == NC_FORMATX_NC3 && (ext_ncid % (1<<ID_SHIFT)))
|
|
return NULL;
|
|
|
|
return f;
|
|
}
|
|
|
|
/*
|
|
Added to support open by name
|
|
*/
|
|
NC*
|
|
find_in_NCList_by_name(const char* path)
|
|
{
|
|
int i;
|
|
NC* f = NULL;
|
|
if(nc_filelist == NULL)
|
|
return NULL;
|
|
for(i=1; i < NCFILELISTLENGTH; i++) {
|
|
if(nc_filelist[i] != NULL) {
|
|
if(strcmp(nc_filelist[i]->path,path)==0) {
|
|
f = nc_filelist[i];
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
return f;
|
|
}
|
|
|
|
int
|
|
iterate_NCList(int index, NC** ncp)
|
|
{
|
|
/* Walk from 0 ...; 0 return => stop */
|
|
if(index < 0 || index >= NCFILELISTLENGTH)
|
|
return NC_ERANGE;
|
|
if(ncp) *ncp = nc_filelist[index];
|
|
return NC_NOERR;
|
|
}
|