netcdf-c/ncgen/cdata.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

220 lines
5.2 KiB
C

/*********************************************************************
* Copyright 2018, UCAR/Unidata
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*********************************************************************/
#include "includes.h"
#ifdef ENABLE_C
#include <math.h>
#ifndef isnan
extern int isnan(double);
#endif
static int c_uid = 0;
static int
c_charconstant(Generator* generator, Symbol* sym, Bytebuffer* codebuf, ...)
{
/* Escapes and quoting will be handled in genc_write */
/* Just transfer charbuf to codebuf */
Bytebuffer* charbuf;
va_list ap;
va_start(ap,codebuf);
charbuf = va_arg(ap, Bytebuffer*);
va_end(ap);
bbNull(charbuf);
bbCatbuf(codebuf,charbuf);
return 1;
}
static int
c_constant(Generator* generator, Symbol* sym, NCConstant* con, Bytebuffer* buf,...)
{
Bytebuffer* codetmp = bbNew();
char* special = NULL;
switch (con->nctype) {
case NC_CHAR:
if(con->value.charv == '\'')
bbprintf(codetmp,"'\\''");
else
bbprintf(codetmp,"'%s'",cescapifychar(con->value.charv,'\''));
break;
case NC_BYTE:
bbprintf(codetmp,"%hhd",con->value.int8v);
break;
case NC_SHORT:
bbprintf(codetmp,"%hd",con->value.int16v);
break;
case NC_INT:
bbprintf(codetmp,"%d",con->value.int32v);
break;
case NC_FLOAT:
/* Special case for nanf */
if(isnan(con->value.floatv))
bbprintf(codetmp,"nanf");
else
bbprintf(codetmp,"%f",con->value.floatv);
break;
case NC_DOUBLE:
/* Special case for nan */
if(isnan(con->value.doublev))
bbprintf(codetmp,"nan");
else
bbprintf(codetmp,"%lf",con->value.doublev);
break;
case NC_UBYTE:
bbprintf(codetmp,"%hhuU",con->value.uint8v);
break;
case NC_USHORT:
bbprintf(codetmp,"%huU",con->value.uint16v);
break;
case NC_UINT:
bbprintf(codetmp,"%uU",con->value.uint32v);
break;
case NC_INT64:
bbprintf(codetmp,"%lldLL",con->value.int64v);
break;
case NC_UINT64:
bbprintf(codetmp,"%lluULL",con->value.uint64v);
break;
case NC_ECONST:
bbprintf(codetmp,"%s",cname(con->value.enumv));
break;
case NC_NIL:
case NC_STRING: { /* handle separately */
if(con->value.stringv.len == 0 && con->value.stringv.stringv == NULL) {
bbprintf(codetmp,"NULL");
} else {
char* escaped = escapify(con->value.stringv.stringv,
'"',con->value.stringv.len);
special = poolalloc(1+2+strlen(escaped));
strcpy(special,"\"");
strcat(special,escaped);
strcat(special,"\"");
}
} break;
case NC_OPAQUE: {
char* p;
int bslen;
bslen=(4*con->value.opaquev.len);
special = poolalloc(bslen+2+1);
strcpy(special,"\"");
p = con->value.opaquev.stringv;
while(*p) {
strcat(special,"\\x");
strncat(special,p,2);
p += 2;
}
strcat(special,"\"");
} break;
default: PANIC1("ncstype: bad type code: %d",con->nctype);
}
if(special == NULL)
bbCatbuf(buf,codetmp);
else
bbCat(buf,special);
bbFree(codetmp);
return 1;
}
static int
c_listbegin(Generator* generator, Symbol* sym, void* liststate, ListClass lc, size_t size, Bytebuffer* codebuf, int* uidp, ...)
{
if(uidp) *uidp = ++c_uid;
switch (lc) {
case LISTVLEN:
case LISTATTR:
case LISTDATA:
break;
case LISTFIELDARRAY:
case LISTCOMPOUND:
bbAppend(codebuf,'{');
break;
}
return 1;
}
static int
c_list(Generator* generator, Symbol* sym, void* liststate, ListClass lc, int uid, size_t count, Bytebuffer* codebuf, ...)
{
switch (lc) {
case LISTVLEN:
case LISTATTR:
if(count > 0) bbCat(codebuf,", ");
break;
case LISTDATA:
case LISTCOMPOUND:
case LISTFIELDARRAY:
bbAppend(codebuf,' ');
break;
}
return 1;
}
static int
c_listend(Generator* generator, Symbol* sym, void* liststate, ListClass lc, int uid, size_t count, Bytebuffer* buf, ...)
{
switch (lc) {
case LISTCOMPOUND:
case LISTFIELDARRAY:
bbAppend(buf,'}');
break;
case LISTDATA:
case LISTVLEN:
case LISTATTR:
break;
}
return 1;
}
static int
c_vlendecl(Generator* generator, Symbol* tsym, Bytebuffer* codebuf, int uid, size_t count, ...)
{
/* Build a bytebuffer to capture the vlen decl */
List* declstack = (List*)generator->globalstate;
Bytebuffer* decl = bbNew();
Bytebuffer* vlenbuf;
va_list ap;
va_start(ap,count);
vlenbuf = va_arg(ap, Bytebuffer*);
va_end(ap);
bbprintf0(decl,"static const %s vlen_%u[] = {",
ctypename(tsym->typ.basetype),
uid);
commify(vlenbuf);
bbCatbuf(decl,vlenbuf);
bbCat(decl,"} ;");
listpush(declstack,(void*)decl);
/* Now generate the reference to buffer */
bbprintf(codebuf,"{%u,(void*)vlen_%u}",count,uid);
return 1;
}
static int
c_vlenstring(Generator* generator, Symbol* sym, Bytebuffer* vlenmem, int* uidp, size_t* countp,...)
{
if(uidp) *uidp = ++c_uid;
if(countp) *countp = bbLength(vlenmem);
return 1;
}
/* Define the single static bin data generator */
static Generator c_generator_singleton = {
NULL,
c_charconstant,
c_constant,
c_listbegin,
c_list,
c_listend,
c_vlendecl,
c_vlenstring
};
Generator* c_generator = &c_generator_singleton;
#endif /*ENABLE_C*/