netcdf-c/include/ncjson.h
Dennis Heimbigner 231ae96c4b Add support for Zarr string type to NCZarr
* re: https://github.com/Unidata/netcdf-c/pull/2278
* re: https://github.com/Unidata/netcdf-c/issues/2485
* re: https://github.com/Unidata/netcdf-c/issues/2474

This PR subsumes PR https://github.com/Unidata/netcdf-c/pull/2278.
Actually is a bit an omnibus covering several issues.

## PR https://github.com/Unidata/netcdf-c/pull/2278
Add support for the Zarr string type.
Zarr strings are restricted currently to be of fixed size.
The primary issue to be addressed is to provide a way for user to
specify the size of the fixed length strings. This is handled by providing
the following new attributes special:
1. **_nczarr_default_maxstrlen** —
This is an attribute of the root group. It specifies the default
maximum string length for string types. If not specified, then
it has the value of 64 characters.
2. **_nczarr_maxstrlen** —
This is a per-variable attribute. It specifies the maximum
string length for the string type associated with the variable.
If not specified, then it is assigned the value of
**_nczarr_default_maxstrlen**.

This PR also requires some hacking to handle the existing netcdf-c NC_CHAR
type, which does not exist in zarr. The goal was to choose numpy types for
both the netcdf-c NC_STRING type and the netcdf-c NC_CHAR type such that
if a pure zarr implementation read them, it would still work and an
NC_CHAR type would be handled by zarr as a string of length 1.

For writing variables and NCZarr attributes, the type mapping is as follows:
* "|S1" for NC_CHAR.
* ">S1" for NC_STRING && MAXSTRLEN==1
* ">Sn" for NC_STRING && MAXSTRLEN==n

Note that it is a bit of a hack to use endianness, but it should be ok since for
string/char, the endianness has no meaning.

For reading attributes with pure zarr (i.e. with no nczarr
atribute types defined), they will always be interpreted as of
type NC_CHAR.

## Issue: https://github.com/Unidata/netcdf-c/issues/2474
This PR partly fixes this issue because it provided more
comprehensive support for Zarr attributes that are JSON valued expressions.
This PR still does not address the problem in that issue where the
_ARRAY_DIMENSION attribute is incorrectly set. Than can only be
fixed by the creator of the datasets.

## Issue: https://github.com/Unidata/netcdf-c/issues/2485
This PR also fixes the scalar failure shown in this issue.
It generally cleans up scalar handling.
It also adds a note to the documentation describing that
NCZarr supports scalars while Zarr does not and also how
scalar interoperability is achieved.

## Misc. Other Changes
1. Convert the nczarr special attributes and keys to be all lower case. So "_NCZARR_ATTR" now used "_nczarr_attr. Support back compatibility for the upper case names.
2. Cleanup my too-clever-by-half handling of scalars in libnczarr.
2022-08-27 20:21:13 -06:00

148 lines
4.1 KiB
C

/* Copyright 2018, UCAR/Unidata.
See the COPYRIGHT file for more information.
*/
#ifndef NCJSON_H
#define NCJSON_H 1
/*
WARNING:
If you modify this file,
then you need to got to
the include/ directory
and do the command:
make makepluginjson
*/
/* Inside libnetcdf and for plugins, export the json symbols */
#ifndef DLLEXPORT
#ifdef _WIN32
#define DLLEXPORT __declspec(dllexport)
#else
#define DLLEXPORT
#endif
#endif
/* Override for plugins */
#ifdef NETCDF_JSON_H
#define OPTEXPORT static
#else
#define OPTEXPORT DLLEXPORT
#endif /*NETCDF_JSON_H*/
/**************************************************/
/* Json object sorts (note use of term sort rather than e.g. type or discriminant) */
#define NCJ_UNDEF 0
#define NCJ_STRING 1
#define NCJ_INT 2
#define NCJ_DOUBLE 3
#define NCJ_BOOLEAN 4
#define NCJ_DICT 5
#define NCJ_ARRAY 6
#define NCJ_NULL 7
#define NCJ_NSORTS 8
/* No flags are currently defined, but the argument is a placeholder */
/* Define a struct to store primitive values as unquoted
strings. The sort will provide more info. Do not bother with
a union since the amount of saved space is minimal.
*/
typedef struct NCjson {
int sort; /* of this object */
char* string; /* sort != DICT|ARRAY */
struct NCjlist {
int len;
struct NCjson** contents;
} list; /* sort == DICT|ARRAY */
} NCjson;
/* Structure to hold result of convertinf one json sort to value of another type;
don't use union so we can know when to reclaim sval
*/
struct NCJconst {int bval; long long ival; double dval; char* sval;};
#define NCJconst_empty {0,0,0.0,NULL}
/**************************************************/
/* Extended API */
/* Return 0 if ok else -1 */
#if defined(__cplusplus)
extern "C" {
#endif
/* Parse a string to NCjson*/
OPTEXPORT int NCJparse(const char* text, unsigned flags, NCjson** jsonp);
/* Parse a counted string to NCjson*/
OPTEXPORT int NCJparsen(size_t len, const char* text, unsigned flags, NCjson** jsonp);
/* Reclaim a JSON tree */
OPTEXPORT void NCJreclaim(NCjson* json);
/* Create a new JSON node of a given sort */
OPTEXPORT int NCJnew(int sort, NCjson** objectp);
/* Create new json object with given string content */
OPTEXPORT int NCJnewstring(int sort, const char* value, NCjson** jsonp);
/* Create new json object with given counted string content */
OPTEXPORT int NCJnewstringn(int sort, size_t len, const char* value, NCjson** jsonp);
/* Get dict key value by name */
OPTEXPORT int NCJdictget(const NCjson* dict, const char* key, NCjson** valuep);
/* Convert one json sort to value of another type; don't use union so we can know when to reclaim sval */
OPTEXPORT int NCJcvt(const NCjson* value, int outsort, struct NCJconst* output);
/* Insert an atomic value to an array or dict object. */
OPTEXPORT int NCJaddstring(NCjson* json, int sort, const char* s);
/* Append value to an array or dict object. */
OPTEXPORT int NCJappend(NCjson* object, NCjson* value);
/* Insert key-value pair into a dict object. key will be copied */
OPTEXPORT int NCJinsert(NCjson* object, char* key, NCjson* value);
/* Unparser to convert NCjson object to text in buffer */
OPTEXPORT int NCJunparse(const NCjson* json, unsigned flags, char** textp);
/* Deep clone a json object */
OPTEXPORT int NCJclone(const NCjson* json, NCjson** clonep);
#ifndef NETCDF_JSON_H
/* dump NCjson* object to output file */
OPTEXPORT void NCJdump(const NCjson* json, unsigned flags, FILE*);
/* convert NCjson* object to output string */
OPTEXPORT const char* NCJtotext(const NCjson* json);
#endif
#if defined(__cplusplus)
}
#endif
/* Getters */
#define NCJsort(x) ((x)->sort)
#define NCJstring(x) ((x)->string)
#define NCJlength(x) ((x)==NULL ? 0 : (x)->list.len)
#define NCJcontents(x) ((x)->list.contents)
#define NCJith(x,i) ((x)->list.contents[i])
/* Setters */
#define NCJsetsort(x,s) (x)->sort=(s)
#define NCJsetstring(x,y) (x)->string=(y)
#define NCJsetcontents(x,c) (x)->list.contents=(c)
#define NCJsetlength(x,l) (x)->list.len=(l)
/* Misc */
#define NCJisatomic(j) ((j)->sort != NCJ_ARRAY && (j)->sort != NCJ_DICT && (j)->sort != NCJ_NULL && (j)->sort != NCJ_UNDEF)
/**************************************************/
#endif /*NCJSON_H*/