netcdf-c/ncgen/data.h
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

125 lines
4.1 KiB
C

/*********************************************************************
* Copyright 2018, UCAR/Unidata
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*********************************************************************/
#ifndef DATA_H
#define DATA_H 1
#ifndef NO_STDARG
# include <stdarg.h>
#else
# include <varargs.h>
#endif
/* nmemonics*/
#define TOPLEVEL 1
#define DEEP 0
/* Forward types */
struct Datalist;
struct Symbol;
struct Dimset;
/* any one possible value*/
typedef union Constvalue {
struct Datalist* compoundv; /* NC_COMPOUND*/
char charv; /* NC_CHAR*/
signed char int8v; /* NC_BYTE*/
unsigned char uint8v; /* NC_UBYTE*/
short int16v; /* NC_SHORT*/
unsigned short uint16v; /* NC_USHORT*/
int int32v; /* NC_INT*/
unsigned int uint32v; /* NC_UINT*/
long long int64v; /* NC_INT64*/
unsigned long long uint64v; /* NC_UINT64*/
float floatv; /* NC_FLOAT*/
double doublev; /* NC_DOUBLE*/
struct Stringv { /* NC_STRING*/
int len;
char* stringv;
} stringv;
struct Opaquev { /* NC_OPAQUE*/
int len; /* length as originally written (rounded to even number)*/
char* stringv; /*as constant was written*/
/* (padded to even # chars >= 16)*/
/* without leading 0x*/
} opaquev;
struct Symbol* enumv; /* NC_ECONST*/
} Constvalue;
typedef struct NCConstant {
nc_type nctype; /* NC_INT,... */
nc_type subtype; /* NC_DIM | NC_NAT */
int lineno;
Constvalue value;
int filled; /* was this originally NC_FILLVALUE? */
} NCConstant;
typedef struct Datalist {
int readonly; /* data field is shared with another Datalist*/
size_t length; /* |data| */
size_t alloc; /* track total allocated space for data field*/
NCConstant** data; /* actual list of constants constituting the datalist*/
/* Track various values associated with the datalist*/
/* (used to be in Constvalue.compoundv)*/
} Datalist;
extern List* alldatalists;
/* from: data.c */
extern Datalist* builddatalist(int initialize);
extern void capture(Datalist* dl);
extern void dlappend(Datalist*, NCConstant*);
extern void dlinsert(Datalist* dl, size_t pos, Datalist* insertion);
extern void dlset(Datalist*, size_t, NCConstant*);
extern NCConstant* dlremove(Datalist*, size_t);
extern NCConstant* builddatasublist(Datalist* dl);
extern Datalist* builddatasubset(Datalist* dl, size_t start, size_t count);
extern void dlextend(Datalist* dl);
extern void dlsetalloc(Datalist* dl,size_t);
extern Datalist* clonedatalist(Datalist* dl);
extern void reclaimalldatalists(void);
extern void reclaimdatalist(Datalist*);
extern void reclaimconstant(NCConstant*);
extern void freedatalist(Datalist* list);
extern Datalist* flatten(Datalist* list,int rank);
int datalistline(Datalist*);
#define datalistith(dl,i) ((dl)==NULL?NULL:((i) >= (dl)->length?NULL:(dl)->data[i]))
#define datalistlen(dl) ((dl)==NULL?0:(dl)->length)
#define datalistclear(dl) {if((dl)!=NULL) {dl->length=0;}}
NCConstant* list2const(Datalist*);
Datalist* const2list(NCConstant* con);
int isstringable(nc_type nctype);
#define islistconst(con) ((con)!=NULL && ((con)->nctype == NC_COMPOUND))
#define isfillconst(con) ((con)!=NULL && (con)->nctype == NC_FILLVALUE)
#define constline(con) (con==NULL?0:(con)->lineno)
#define consttype(con) (con==NULL?NC_NAT:(con)->nctype)
#define isnilconst(con) ((con)!=NULL && (con)->nctype == NC_NIL)
#define compoundfor(con) ((con)==NULL?NULL:(con)->value.compoundv)
#define setsubtype(con,type) {if((con)!=NULL){(con)->subtype=(type);}}
NCConstant* emptycompoundconst(int lineno);
NCConstant* emptystringconst(int);
NCConstant* cloneconstant(NCConstant* con); /* deep clone*/
void clearconstant(NCConstant* con); /* deep clear*/
#define freeconst(con) freeconstant(con,DEEP);
void freeconstant(NCConstant* con, int shallow);
extern NCConstant* nullconst(void);
extern NCConstant nullconstant;
extern NCConstant fillconstant;
extern NCConstant nilconstant;
extern Datalist* filldatalist;
#endif /*DATA_H*/