2017-08-31 02:05:04 +08:00
|
|
|
/*
|
2018-12-07 05:29:57 +08:00
|
|
|
Copyright (c) 1998-2018 University Corporation for Atmospheric Research/Unidata
|
|
|
|
See COPYRIGHT for license information.
|
2017-08-31 02:05:04 +08:00
|
|
|
*/
|
2017-03-09 08:01:10 +08:00
|
|
|
|
|
|
|
#include "config.h"
|
|
|
|
#ifdef HAVE_UNISTD_H
|
|
|
|
#include <unistd.h>
|
|
|
|
#endif
|
|
|
|
#ifdef HAVE_STDARG_H
|
|
|
|
#include <stdarg.h>
|
|
|
|
#endif
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
2017-08-31 07:44:57 +08:00
|
|
|
#include "netcdf.h"
|
2017-03-09 08:01:10 +08:00
|
|
|
#include "ncbytes.h"
|
2017-08-31 07:44:57 +08:00
|
|
|
#include "ncuri.h"
|
2017-03-09 08:01:10 +08:00
|
|
|
#include "ncrc.h"
|
2017-08-31 07:44:57 +08:00
|
|
|
#include "nclog.h"
|
2020-10-14 09:12:15 +08:00
|
|
|
#include "ncpathmgr.h"
|
2017-08-31 07:44:57 +08:00
|
|
|
|
|
|
|
#define RCFILEENV "DAPRCFILE"
|
2017-03-09 08:01:10 +08:00
|
|
|
|
|
|
|
#define RTAG ']'
|
|
|
|
#define LTAG '['
|
|
|
|
|
|
|
|
#define TRIMCHARS " \t\r\n"
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
#undef MEMCHECK
|
|
|
|
#define MEMCHECK(x) if((x)==NULL) {goto nomem;} else {}
|
|
|
|
|
|
|
|
/* Forward */
|
|
|
|
static char* rcreadline(char** nextlinep);
|
|
|
|
static void rctrim(char* text);
|
2018-02-09 10:53:40 +08:00
|
|
|
static void rcorder(NClist* rc);
|
2017-08-31 07:44:57 +08:00
|
|
|
static int rccompile(const char* path);
|
|
|
|
static struct NCTriple* rclocate(const char* key, const char* hostport);
|
|
|
|
static int rcsearch(const char* prefix, const char* rcname, char** pathp);
|
2017-09-01 04:19:56 +08:00
|
|
|
static void rcfreetriples(NClist* rc);
|
2017-08-31 07:44:57 +08:00
|
|
|
#ifdef D4DEBUG
|
|
|
|
static void storedump(char* msg, NClist* triples);
|
|
|
|
#endif
|
2017-03-09 08:01:10 +08:00
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/* Define default rc files and aliases, also defines search order*/
|
2019-03-31 04:06:20 +08:00
|
|
|
static const char* rcfilenames[] = {".daprc",".dodsrc",".ncrc",NULL};
|
2017-03-09 08:01:10 +08:00
|
|
|
|
|
|
|
/**************************************************/
|
2017-08-31 07:44:57 +08:00
|
|
|
/* External Entry Points */
|
2017-03-09 08:01:10 +08:00
|
|
|
|
2019-03-31 04:06:20 +08:00
|
|
|
static NCRCglobalstate* ncrc_globalstate = NULL;
|
|
|
|
|
|
|
|
/* Get global state */
|
|
|
|
NCRCglobalstate*
|
|
|
|
ncrc_getglobalstate(void)
|
|
|
|
{
|
|
|
|
if(ncrc_globalstate == NULL) {
|
|
|
|
ncrc_globalstate = calloc(1,sizeof(NCRCglobalstate));
|
|
|
|
}
|
|
|
|
return ncrc_globalstate;
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
ncrc_freeglobalstate(void)
|
|
|
|
{
|
|
|
|
if(ncrc_globalstate != NULL) {
|
|
|
|
nullfree(ncrc_globalstate->tempdir);
|
|
|
|
nullfree(ncrc_globalstate->home);
|
|
|
|
NC_rcclear(&ncrc_globalstate->rcinfo);
|
|
|
|
free(ncrc_globalstate);
|
|
|
|
ncrc_globalstate = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
NC_rcclear(NCRCinfo* info)
|
|
|
|
{
|
|
|
|
if(info == NULL) return;
|
|
|
|
nullfree(info->rcfile);
|
|
|
|
rcfreetriples(info->triples);
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
rcfreetriples(NClist* rc)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
for(i=0;i<nclistlength(rc);i++) {
|
|
|
|
NCTriple* t = (NCTriple*)nclistget(rc,i);
|
|
|
|
nullfree(t->host);
|
|
|
|
nullfree(t->key);
|
|
|
|
nullfree(t->value);
|
|
|
|
free(t);
|
|
|
|
}
|
|
|
|
nclistfree(rc);
|
|
|
|
}
|
2017-03-09 08:01:10 +08:00
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/* locate, read and compile the rc file, if any */
|
2017-03-09 08:01:10 +08:00
|
|
|
int
|
2017-08-31 07:44:57 +08:00
|
|
|
NC_rcload(void)
|
2017-03-09 08:01:10 +08:00
|
|
|
{
|
2017-08-31 07:44:57 +08:00
|
|
|
int ret = NC_NOERR;
|
2017-03-09 08:01:10 +08:00
|
|
|
char* path = NULL;
|
2019-03-31 04:06:20 +08:00
|
|
|
NCRCglobalstate* globalstate = ncrc_getglobalstate();
|
2017-03-09 08:01:10 +08:00
|
|
|
|
2019-03-31 04:06:20 +08:00
|
|
|
if(globalstate->rcinfo.ignore) {
|
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
|
|
|
nclog(NCLOGDBG,"No .daprc|.dodsrc runtime configuration file specified; continuing");
|
2017-08-31 07:44:57 +08:00
|
|
|
return (NC_NOERR);
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
2019-03-31 04:06:20 +08:00
|
|
|
if(globalstate->rcinfo.loaded) return (NC_NOERR);
|
2017-03-09 08:01:10 +08:00
|
|
|
|
|
|
|
/* locate the configuration files in the following order:
|
2017-08-31 07:44:57 +08:00
|
|
|
1. specified by NC_set_rcfile
|
|
|
|
2. set by DAPRCFILE env variable
|
|
|
|
3. ./<rcfile> (current directory)
|
|
|
|
4. $HOME/<rcfile>
|
2017-03-09 08:01:10 +08:00
|
|
|
*/
|
2019-03-31 04:06:20 +08:00
|
|
|
if(globalstate->rcinfo.rcfile != NULL) { /* always use this */
|
|
|
|
path = strdup(globalstate->rcinfo.rcfile);
|
2017-08-31 07:44:57 +08:00
|
|
|
} else if(getenv(RCFILEENV) != NULL && strlen(getenv(RCFILEENV)) > 0) {
|
|
|
|
path = strdup(getenv(RCFILEENV));
|
|
|
|
} else {
|
2019-03-31 04:06:20 +08:00
|
|
|
const char** rcname;
|
2017-08-31 07:44:57 +08:00
|
|
|
int found = 0;
|
|
|
|
for(rcname=rcfilenames;!found && *rcname;rcname++) {
|
|
|
|
ret = rcsearch(".",*rcname,&path);
|
|
|
|
if(ret == NC_NOERR && path == NULL) /* try $HOME */
|
2019-03-31 04:06:20 +08:00
|
|
|
ret = rcsearch(globalstate->home,*rcname,&path);
|
2017-08-31 07:44:57 +08:00
|
|
|
if(ret != NC_NOERR)
|
|
|
|
goto done;
|
|
|
|
if(path != NULL)
|
|
|
|
found = 1;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
if(path == 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
|
|
|
nclog(NCLOGDBG,"No .daprc|.dodsrc runtime configuration file specified; continuing");
|
2017-08-31 07:44:57 +08:00
|
|
|
} else {
|
|
|
|
#ifdef D4DEBUG
|
|
|
|
fprintf(stderr, "RC file: %s\n", path);
|
|
|
|
#endif
|
|
|
|
if((ret=rccompile(path))) {
|
|
|
|
nclog(NCLOGERR, "Error parsing %s\n",path);
|
|
|
|
goto done;
|
|
|
|
}
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
done:
|
2019-03-31 04:06:20 +08:00
|
|
|
globalstate->rcinfo.loaded = 1; /* even if not exists */
|
2017-08-31 07:44:57 +08:00
|
|
|
nullfree(path);
|
|
|
|
return (ret);
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/**
|
|
|
|
* Locate a triple by property key and host+port (may be null|"")
|
|
|
|
* If duplicate keys, first takes precedence.
|
|
|
|
*/
|
|
|
|
char*
|
|
|
|
NC_rclookup(const char* key, const char* hostport)
|
|
|
|
{
|
|
|
|
struct NCTriple* triple = rclocate(key,hostport);
|
2017-03-09 08:01:10 +08:00
|
|
|
return (triple == NULL ? NULL : triple->value);
|
|
|
|
}
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/*!
|
|
|
|
Set the absolute path to use for the rc file.
|
|
|
|
WARNING: this MUST be called before any other
|
|
|
|
call in order for this to take effect.
|
2017-03-09 08:01:10 +08:00
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
\param[in] rcfile The path to use. If NULL, or "",
|
|
|
|
then do not use any rcfile.
|
|
|
|
|
|
|
|
\retval OC_NOERR if the request succeeded.
|
|
|
|
\retval OC_ERCFILE if the file failed to load
|
|
|
|
*/
|
|
|
|
|
|
|
|
int
|
|
|
|
NC_set_rcfile(const char* rcfile)
|
|
|
|
{
|
|
|
|
int stat = NC_NOERR;
|
|
|
|
FILE* f = NULL;
|
2019-03-31 04:06:20 +08:00
|
|
|
NCRCglobalstate* globalstate = ncrc_getglobalstate();
|
2017-08-31 07:44:57 +08:00
|
|
|
|
|
|
|
if(rcfile != NULL && strlen(rcfile) == 0)
|
|
|
|
rcfile = NULL;
|
|
|
|
f = NCfopen(rcfile,"r");
|
|
|
|
if(f == NULL) {
|
|
|
|
stat = NC_ERCFILE;
|
|
|
|
goto done;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
fclose(f);
|
2019-03-31 04:06:20 +08:00
|
|
|
nullfree(globalstate->rcinfo.rcfile);
|
|
|
|
globalstate->rcinfo.rcfile = strdup(rcfile);
|
|
|
|
/* Clear globalstate->rcinfo */
|
|
|
|
NC_rcclear(&globalstate->rcinfo);
|
2017-08-31 07:44:57 +08:00
|
|
|
/* (re) load the rcfile and esp the triplestore*/
|
|
|
|
stat = NC_rcload();
|
|
|
|
done:
|
|
|
|
return stat;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/**************************************************/
|
|
|
|
/* RC processing functions */
|
|
|
|
|
|
|
|
static char*
|
|
|
|
rcreadline(char** nextlinep)
|
2017-03-09 08:01:10 +08:00
|
|
|
{
|
2017-08-31 07:44:57 +08:00
|
|
|
char* line;
|
|
|
|
char* p;
|
|
|
|
|
|
|
|
line = (p = *nextlinep);
|
|
|
|
if(*p == '\0') return NULL; /*signal done*/
|
|
|
|
for(;*p;p++) {
|
|
|
|
if(*p == '\r' && p[1] == '\n') *p = '\0';
|
|
|
|
else if(*p == '\n') break;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
*p++ = '\0'; /* null terminate line; overwrite newline */
|
|
|
|
*nextlinep = p;
|
|
|
|
return line;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/* Trim TRIMCHARS from both ends of text; */
|
2017-03-09 08:01:10 +08:00
|
|
|
static void
|
2017-08-31 07:44:57 +08:00
|
|
|
rctrim(char* text)
|
2017-03-09 08:01:10 +08:00
|
|
|
{
|
2017-08-31 07:44:57 +08:00
|
|
|
char* p = text;
|
2018-06-08 06:17:32 +08:00
|
|
|
size_t len = 0;
|
2017-08-31 07:44:57 +08:00
|
|
|
int i;
|
|
|
|
|
|
|
|
/* locate first non-trimchar */
|
|
|
|
for(;*p;p++) {
|
|
|
|
if(strchr(TRIMCHARS,*p) == NULL) break; /* hit non-trim char */
|
|
|
|
}
|
|
|
|
memmove(text,p,strlen(p)+1);
|
|
|
|
len = strlen(text);
|
|
|
|
/* locate last non-trimchar */
|
|
|
|
if(len > 0) {
|
|
|
|
for(i=(len-1);i>=0;i--) {
|
|
|
|
if(strchr(TRIMCHARS,text[i]) == NULL) {
|
|
|
|
text[i+1] = '\0'; /* elide trailing trimchars */
|
|
|
|
break;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Order the triples: those with urls must be first,
|
|
|
|
but otherwise relative order does not matter.
|
|
|
|
*/
|
2018-02-09 10:53:40 +08:00
|
|
|
static void
|
2017-08-31 07:44:57 +08:00
|
|
|
rcorder(NClist* rc)
|
|
|
|
{
|
2017-11-09 21:24:18 +08:00
|
|
|
int i;
|
2017-08-31 07:44:57 +08:00
|
|
|
int len = nclistlength(rc);
|
2018-05-19 10:28:51 +08:00
|
|
|
NClist* tmprc = NULL;
|
2018-02-09 10:53:40 +08:00
|
|
|
if(rc == NULL || len == 0) return;
|
2018-05-19 10:28:51 +08:00
|
|
|
tmprc = nclistnew();
|
2018-02-09 10:53:40 +08:00
|
|
|
/* Copy rc into tmprc and clear rc */
|
2017-08-31 07:44:57 +08:00
|
|
|
for(i=0;i<len;i++) {
|
|
|
|
NCTriple* ti = nclistget(rc,i);
|
2018-02-09 10:53:40 +08:00
|
|
|
nclistpush(tmprc,ti);
|
|
|
|
}
|
|
|
|
nclistclear(rc);
|
|
|
|
/* Two passes: 1) pull triples with host */
|
|
|
|
for(i=0;i<len;i++) {
|
|
|
|
NCTriple* ti = nclistget(tmprc,i);
|
2017-08-31 07:44:57 +08:00
|
|
|
if(ti->host == NULL) continue;
|
2018-02-09 10:53:40 +08:00
|
|
|
nclistpush(rc,ti);
|
2017-08-31 07:44:57 +08:00
|
|
|
}
|
|
|
|
/* pass 2 pull triples without host*/
|
|
|
|
for(i=0;i<len;i++) {
|
2018-02-09 10:53:40 +08:00
|
|
|
NCTriple* ti = nclistget(tmprc,i);
|
2017-08-31 07:44:57 +08:00
|
|
|
if(ti->host != NULL) continue;
|
2018-02-09 10:53:40 +08:00
|
|
|
nclistpush(rc,ti);
|
2017-08-31 07:44:57 +08:00
|
|
|
}
|
|
|
|
#ifdef D4DEBUG
|
2018-02-09 10:53:40 +08:00
|
|
|
storedump("reorder:",rc);
|
2017-08-31 07:44:57 +08:00
|
|
|
#endif
|
2018-02-09 10:53:40 +08:00
|
|
|
nclistfree(tmprc);
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Create a triple store from a file */
|
|
|
|
static int
|
2017-08-31 07:44:57 +08:00
|
|
|
rccompile(const char* path)
|
2017-03-09 08:01:10 +08:00
|
|
|
{
|
2017-08-31 07:44:57 +08:00
|
|
|
int ret = NC_NOERR;
|
2018-02-09 10:53:40 +08:00
|
|
|
NClist* rc = NULL;
|
2017-08-31 07:44:57 +08:00
|
|
|
char* contents = NULL;
|
|
|
|
NCbytes* tmp = ncbytesnew();
|
|
|
|
NCURI* uri = NULL;
|
|
|
|
char* nextline = NULL;
|
2019-03-31 04:06:20 +08:00
|
|
|
NCRCglobalstate* globalstate = ncrc_getglobalstate();
|
2017-08-31 07:44:57 +08:00
|
|
|
|
|
|
|
if((ret=NC_readfile(path,tmp))) {
|
2018-06-08 06:17:32 +08:00
|
|
|
nclog(NCLOGERR, "Could not open configuration file: %s",path);
|
|
|
|
goto done;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
contents = ncbytesextract(tmp);
|
|
|
|
if(contents == NULL) contents = strdup("");
|
2018-02-09 10:53:40 +08:00
|
|
|
/* Either reuse or create new */
|
2019-03-31 04:06:20 +08:00
|
|
|
rc = globalstate->rcinfo.triples;
|
2018-02-09 10:53:40 +08:00
|
|
|
if(rc != NULL)
|
|
|
|
rcfreetriples(rc); /* clear out any old data */
|
|
|
|
else {
|
|
|
|
rc = nclistnew();
|
2019-03-31 04:06:20 +08:00
|
|
|
globalstate->rcinfo.triples = rc;
|
2018-02-09 10:53:40 +08:00
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
nextline = contents;
|
2017-03-09 08:01:10 +08:00
|
|
|
for(;;) {
|
|
|
|
char* line;
|
2017-08-31 07:44:57 +08:00
|
|
|
char* key;
|
|
|
|
char* value;
|
|
|
|
size_t llen;
|
|
|
|
NCTriple* triple;
|
|
|
|
|
|
|
|
line = rcreadline(&nextline);
|
|
|
|
if(line == NULL) break; /* done */
|
|
|
|
rctrim(line); /* trim leading and trailing blanks */
|
|
|
|
if(line[0] == '#') continue; /* comment */
|
|
|
|
if((llen=strlen(line)) == 0) continue; /* empty line */
|
|
|
|
triple = (NCTriple*)calloc(1,sizeof(NCTriple));
|
|
|
|
if(triple == NULL) {ret = NC_ENOMEM; goto done;}
|
2018-10-02 05:51:43 +08:00
|
|
|
if(line[0] == LTAG) {
|
|
|
|
char* url = ++line;
|
|
|
|
char* rtag = strchr(line,RTAG);
|
|
|
|
if(rtag == NULL) {
|
|
|
|
nclog(NCLOGERR, "Malformed [url] in %s entry: %s",path,line);
|
|
|
|
free(triple);
|
2017-08-31 07:44:57 +08:00
|
|
|
continue;
|
2018-10-02 05:51:43 +08:00
|
|
|
}
|
|
|
|
line = rtag + 1;
|
|
|
|
*rtag = '\0';
|
|
|
|
/* compile the url and pull out the host */
|
|
|
|
if(uri) ncurifree(uri);
|
2019-09-30 02:59:28 +08:00
|
|
|
if(ncuriparse(url,&uri)) {
|
2018-10-02 05:51:43 +08:00
|
|
|
nclog(NCLOGERR, "Malformed [url] in %s entry: %s",path,line);
|
|
|
|
free(triple);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
ncbytesclear(tmp);
|
|
|
|
ncbytescat(tmp,uri->host);
|
|
|
|
if(uri->port != NULL) {
|
2017-08-31 07:44:57 +08:00
|
|
|
ncbytesappend(tmp,':');
|
2018-10-02 05:51:43 +08:00
|
|
|
ncbytescat(tmp,uri->port);
|
|
|
|
}
|
|
|
|
ncbytesnull(tmp);
|
|
|
|
triple->host = ncbytesextract(tmp);
|
2018-02-28 05:22:04 +08:00
|
|
|
if(strlen(triple->host)==0)
|
|
|
|
{free(triple->host); triple->host = NULL;}
|
2018-10-02 05:51:43 +08:00
|
|
|
}
|
2017-03-09 08:01:10 +08:00
|
|
|
/* split off key and value */
|
2017-08-31 07:44:57 +08:00
|
|
|
key=line;
|
2017-03-09 08:01:10 +08:00
|
|
|
value = strchr(line, '=');
|
|
|
|
if(value == NULL)
|
|
|
|
value = line + strlen(line);
|
|
|
|
else {
|
|
|
|
*value = '\0';
|
|
|
|
value++;
|
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
triple->key = strdup(key);
|
|
|
|
triple->value = strdup(value);
|
|
|
|
rctrim(triple->key);
|
|
|
|
rctrim(triple->value);
|
|
|
|
#ifdef D4DEBUG
|
|
|
|
fprintf(stderr,"rc: host=%s key=%s value=%s\n",
|
2018-02-28 05:22:04 +08:00
|
|
|
(triple->host != NULL ? triple->host : "<null>"),
|
|
|
|
triple->key,triple->valu);
|
2017-08-31 07:44:57 +08:00
|
|
|
#endif
|
|
|
|
nclistpush(rc,triple);
|
|
|
|
triple = NULL;
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
rcorder(rc);
|
|
|
|
|
2017-03-09 08:01:10 +08:00
|
|
|
done:
|
2018-02-09 10:53:40 +08:00
|
|
|
if(contents) free(contents);
|
2017-08-31 07:44:57 +08:00
|
|
|
ncurifree(uri);
|
|
|
|
ncbytesfree(tmp);
|
|
|
|
return (ret);
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
/**
|
|
|
|
* (Internal) Locate a triple by property key and host+port (may be null or "").
|
|
|
|
* If duplicate keys, first takes precedence.
|
|
|
|
*/
|
|
|
|
static struct NCTriple*
|
|
|
|
rclocate(const char* key, const char* hostport)
|
|
|
|
{
|
2018-02-09 10:53:40 +08:00
|
|
|
int i,found;
|
2019-03-31 04:06:20 +08:00
|
|
|
NCRCglobalstate* globalstate = ncrc_getglobalstate();
|
|
|
|
NClist* rc = globalstate->rcinfo.triples;
|
2017-08-31 07:44:57 +08:00
|
|
|
NCTriple* triple = NULL;
|
|
|
|
|
2019-03-31 04:06:20 +08:00
|
|
|
if(globalstate->rcinfo.ignore)
|
2017-08-31 07:44:57 +08:00
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if(key == NULL || rc == NULL) return NULL;
|
|
|
|
if(hostport == NULL) hostport = "";
|
|
|
|
|
|
|
|
for(found=0,i=0;i<nclistlength(rc);i++) {
|
2018-11-09 03:37:03 +08:00
|
|
|
int t;
|
|
|
|
size_t hplen;
|
|
|
|
triple = (NCTriple*)nclistget(rc,i);
|
|
|
|
|
|
|
|
hplen = (triple->host == NULL ? 0 : strlen(triple->host));
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
if(strcmp(key,triple->key) != 0) continue; /* keys do not match */
|
|
|
|
/* If the triple entry has no url, then use it
|
|
|
|
(because we have checked all other cases)*/
|
|
|
|
if(hplen == 0) {found=1;break;}
|
|
|
|
/* do hostport match */
|
2018-02-28 05:22:04 +08:00
|
|
|
t = 0;
|
|
|
|
if(triple->host != NULL)
|
|
|
|
t = strcmp(hostport,triple->host);
|
2017-08-31 07:44:57 +08:00
|
|
|
if(t == 0) {found=1; break;}
|
|
|
|
}
|
|
|
|
return (found?triple:NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Locate rc file by searching in directory prefix.
|
|
|
|
*/
|
|
|
|
static
|
|
|
|
int
|
|
|
|
rcsearch(const char* prefix, const char* rcname, char** pathp)
|
2017-03-09 08:01:10 +08:00
|
|
|
{
|
|
|
|
char* path = NULL;
|
|
|
|
FILE* f = NULL;
|
2019-10-25 04:28:39 +08:00
|
|
|
size_t plen = (prefix?strlen(prefix):0);
|
2019-01-12 02:41:09 +08:00
|
|
|
size_t rclen = strlen(rcname);
|
2017-08-31 07:44:57 +08:00
|
|
|
int ret = NC_NOERR;
|
|
|
|
|
|
|
|
size_t pathlen = plen+rclen+1; /*+1 for '/' */
|
|
|
|
path = (char*)malloc(pathlen+1); /* +1 for nul*/
|
|
|
|
if(path == NULL) {ret = NC_ENOMEM; goto done;}
|
|
|
|
strncpy(path,prefix,pathlen);
|
|
|
|
strncat(path,"/",pathlen);
|
|
|
|
strncat(path,rcname,pathlen);
|
2017-03-09 08:01:10 +08:00
|
|
|
/* see if file is readable */
|
Codify cross-platform file paths
The netcdf-c code has to deal with a variety of platforms:
Windows, OSX, Linux, Cygwin, MSYS, etc. These platforms differ
significantly in the kind of file paths that they accept. So in
order to handle this, I have created a set of replacements for
the most common file system operations such as _open_ or _fopen_
or _access_ to manage the file path differences correctly.
A more limited version of this idea was already implemented via
the ncwinpath.h and dwinpath.c code. So this can be viewed as a
replacement for that code. And in path in many cases, the only
change that was required was to replace '#include <ncwinpath.h>'
with '#include <ncpathmgt.h>' and then replace file operation
calls with the NCxxx equivalent from ncpathmgr.h Note that
recently, the ncwinpath.h was renamed ncpathmgmt.h, so this pull
request should not require dealing with winpath.
The heart of the change is include/ncpathmgmt.h, which provides
alternate operations such as NCfopen or NCaccess and which properly
parse and rebuild path arguments to work for the platform on which
the code is executing. This mostly matters for Windows because of the
way that it uses backslash and drive letters, as compared to *nix*.
One important feature is that the user can do string manipulations
on a file path without having to worry too much about the platform
because the path management code will properly handle most mixed cases.
So one can for example concatenate a path suffix that uses forward
slashes to a Windows path and have it work correctly.
The conversion code is in libdispatch/dpathmgr.c, and the
important function there is NCpathcvt which does the proper
conversions to the local path format.
As a rule, most code should just replace their file operations with
the corresponding NCxxx ones defined in include/ncpathmgmt.h. These
NCxxx functions all call NCpathcvt on their path arguments before
executing the actual file operation.
In some rare cases, the client may need to directly use NCpathcvt,
but this should be avoided as much as possible. If there is a need
for supporting a new file operation not already in ncpathmgmt.h, then
use the code in dpathmgr.c as a template. Also please notify Unidata
so we can include it as a formal part or our supported operations.
Also, if you see an operation in the library that is not using the
NCxxx form, then please submit an issue so we can fix it.
Misc. Changes:
* Clean up the utf8 testing code; it is impossible to get some
tests to work under windows using shell scripts; the args do
not pass as utf8 but as some other encoding.
* Added an extra utf8 test case: test_unicode_path.sh
* Add a true test for HDF5 1.10.6 or later because as noted in
PR https://github.com/Unidata/netcdf-c/pull/1794,
HDF5 changed its Windows file path handling.
2021-03-05 04:41:31 +08:00
|
|
|
f = NCfopen(path,"r");
|
2017-03-09 08:01:10 +08:00
|
|
|
if(f != NULL)
|
|
|
|
nclog(NCLOGDBG, "Found rc file=%s",path);
|
|
|
|
done:
|
2017-08-31 07:44:57 +08:00
|
|
|
if(f == NULL || ret != NC_NOERR) {
|
|
|
|
nullfree(path);
|
2017-03-09 08:01:10 +08:00
|
|
|
path = NULL;
|
|
|
|
}
|
|
|
|
if(f != NULL)
|
2017-08-31 07:44:57 +08:00
|
|
|
fclose(f);
|
2017-03-09 08:01:10 +08:00
|
|
|
if(pathp != NULL)
|
2017-08-31 07:44:57 +08:00
|
|
|
*pathp = path;
|
|
|
|
else {
|
|
|
|
nullfree(path);
|
|
|
|
path = NULL;
|
|
|
|
}
|
|
|
|
return (ret);
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
|
|
|
|
2018-08-27 07:04:46 +08:00
|
|
|
int
|
|
|
|
NC_rcfile_insert(const char* key, const char* value, const char* hostport)
|
|
|
|
{
|
|
|
|
int ret = NC_NOERR;
|
|
|
|
/* See if this key already defined */
|
|
|
|
struct NCTriple* triple = NULL;
|
2019-03-31 04:06:20 +08:00
|
|
|
NCRCglobalstate* globalstate = ncrc_getglobalstate();
|
|
|
|
NClist* rc = globalstate->rcinfo.triples;
|
2018-08-27 07:04:46 +08:00
|
|
|
|
|
|
|
if(rc == NULL) {
|
|
|
|
rc = nclistnew();
|
|
|
|
if(rc == NULL) {ret = NC_ENOMEM; goto done;}
|
|
|
|
}
|
|
|
|
triple = rclocate(key,hostport);
|
|
|
|
if(triple == NULL) {
|
|
|
|
triple = (NCTriple*)calloc(1,sizeof(NCTriple));
|
|
|
|
if(triple == NULL) {ret = NC_ENOMEM; goto done;}
|
|
|
|
triple->key = strdup(key);
|
|
|
|
triple->value = NULL;
|
|
|
|
rctrim(triple->key);
|
|
|
|
triple->host = (hostport == NULL ? NULL : strdup(hostport));
|
|
|
|
nclistpush(rc,triple);
|
|
|
|
}
|
|
|
|
if(triple->value != NULL) free(triple->value);
|
|
|
|
triple->value = strdup(value);
|
|
|
|
rctrim(triple->value);
|
|
|
|
done:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
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.
2019-01-02 09:27:36 +08:00
|
|
|
/* Obtain the count of number of triples */
|
|
|
|
size_t
|
|
|
|
NC_rcfile_length(NCRCinfo* info)
|
|
|
|
{
|
|
|
|
return nclistlength(info->triples);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Obtain the ith triple; return NULL if out of range */
|
|
|
|
NCTriple*
|
|
|
|
NC_rcfile_ith(NCRCinfo* info, size_t i)
|
|
|
|
{
|
|
|
|
if(i >= nclistlength(info->triples))
|
|
|
|
return NULL;
|
|
|
|
return (NCTriple*)nclistget(info->triples,i);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2017-08-31 07:44:57 +08:00
|
|
|
#ifdef D4DEBUG
|
|
|
|
static void
|
|
|
|
storedump(char* msg, NClist* triples)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if(msg != NULL) fprintf(stderr,"%s\n",msg);
|
|
|
|
if(triples == NULL || nclistlength(triples)==0) {
|
|
|
|
fprintf(stderr,"<EMPTY>\n");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
for(i=0;i<nclistlength(triples);i++) {
|
|
|
|
NCTriple* t = (NCTriple*)nclistget(triples,i);
|
|
|
|
fprintf(stderr,"\t%s\t%s\t%s\n",
|
|
|
|
((t->host == NULL || strlen(t->host)==0)?"--":t->host),t->key,t->value);
|
|
|
|
}
|
|
|
|
fflush(stderr);
|
2017-03-09 08:01:10 +08:00
|
|
|
}
|
2017-08-31 07:44:57 +08:00
|
|
|
#endif
|