netcdf-c/libnczarr/ztype.c
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

524 lines
15 KiB
C

/* Copyright 2005-2018, University Corporation for Atmospheric
* Research. See the COPYRIGHT file for copying and redistribution
* conditions. */
/**
* @file @internal This file is part of netcdf-4, a netCDF-like
* interface for NCZ, or a ZARR backend for netCDF, depending on your
* point of view.
*
* This file handles the nc4 user-defined type functions
* (i.e. compound and opaque types).
*
* @author Dennis Heimbigner, Ed Hartnett
*/
#include "zincludes.h"
/**
* @internal Determine if two types are equal.
*
* @param ncid1 First file/group ID.
* @param typeid1 First type ID.
* @param ncid2 Second file/group ID.
* @param typeid2 Second type ID.
* @param equalp Pointer that will get 1 if the two types are equal.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_EBADTYPE Type not found.
* @return ::NC_EINVAL Invalid type.
* @author Dennis Heimbigner, Ed Hartnett
*/
extern int
NCZ_inq_type_equal(int ncid1, nc_type typeid1, int ncid2,
nc_type typeid2, int *equalp)
{
NC_GRP_INFO_T *grpone, *grptwo;
NC_TYPE_INFO_T *type1, *type2;
int retval;
LOG((2, "nc_inq_type_equal: ncid1 0x%x typeid1 %d ncid2 0x%x typeid2 %d",
ncid1, typeid1, ncid2, typeid2));
/* Check input. */
if(equalp == NULL) return NC_NOERR;
if (typeid1 <= NC_NAT || typeid2 <= NC_NAT)
return NC_EINVAL;
/* If one is atomic, and the other user-defined, the types are not
* equal. */
if ((typeid1 <= NC_STRING && typeid2 > NC_STRING) ||
(typeid2 <= NC_STRING && typeid1 > NC_STRING))
{
*equalp = 0;
return NC_NOERR;
}
/* If both are atomic types, the answer is easy. */
if (typeid1 <= NUM_ATOMIC_TYPES)
{
if (typeid1 == typeid2)
*equalp = 1;
else
*equalp = 0;
return NC_NOERR;
}
/* Not atomic types - so find type1 and type2 information. */
if ((retval = nc4_find_nc4_grp(ncid1, &grpone)))
return retval;
if (!(type1 = nclistget(grpone->nc4_info->alltypes, typeid1)))
return NC_EBADTYPE;
if ((retval = nc4_find_nc4_grp(ncid2, &grptwo)))
return retval;
if (!(type2 = nclistget(grptwo->nc4_info->alltypes, typeid2)))
return NC_EBADTYPE;
#ifdef LOOK
/* Are the two types equal? */
{
hid_t hid1, hid2;
/* Get the ZARR types from the NCZ-specific type info. */
assert(type1->format_type_info && type2->format_type_info);
hid1 = ((NCZ_TYPE_INFO_T *)type1->format_type_info)->native_hdf_typeid;
hid2 = ((NCZ_TYPE_INFO_T *)type2->format_type_info)->native_hdf_typeid;
/* Ask ZARR if the types are equal. */
if ((retval = H5Tequal(hid1, hid2)) < 0)
return NC_EHDFERR;
*equalp = 1 ? retval : 0;
}
#else
*equalp = 0;
#endif
return NC_NOERR;
}
/**
* @internal Get the id of a type from the name.
*
* @param ncid File and group ID.
* @param name Name of type.
* @param typeidp Pointer that will get the type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_ENOMEM Out of memory.
* @return ::NC_EINVAL Bad size.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EBADTYPE Type not found.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_inq_typeid(int ncid, const char *name, nc_type *typeidp)
{
return NC4_inq_typeid(ncid,name,typeidp);
}
/**
* @internal Get the # and ids of user defined types
*
* @param ncid File and group ID.
* @param ntypes Pointer to store # user defined groups
* @param typeids Pointer to store ids of user defined groups
*
* @return ::NC_NOERR No error.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EBADTYPE Type not found.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_inq_typeids(int ncid, int *ntypes, int *typeids)
{
ZTRACE(0,"ncid=%d",ncid);
if(ntypes) *ntypes = 0;
return ZUNTRACEX(NC_NOERR,"ntypes=%d typeids=%p",(ntypes?-1:*ntypes),typeids);
}
#ifdef LOOK
/**
* @internal This internal function adds a new user defined type to
* the metadata of a group of an open file.
*
* @param ncid File and group ID.
* @param size Size in bytes of new type.
* @param name Name of new type.
* @param base_typeid Base type ID.
* @param type_class NC_VLEN, NC_ENUM
* @param typeidp Pointer that gets new type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EINVAL Bad size.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @return ::NC_ESTRICTNC3 Cannot define user types in classic model.
* @author Dennis Heimbigner, Ed Hartnett
*/
static int
add_user_type(int ncid, size_t size, const char *name, nc_type base_typeid,
nc_type type_class, nc_type *typeidp)
{
NC_FILE_INFO_T *h5;
NC_GRP_INFO_T *grp;
NC_TYPE_INFO_T *type;
NCZ_TYPE_INFO_T *ncz_type;
char norm_name[NC_MAX_NAME + 1];
int retval;
/* Check and normalize the name. */
if ((retval = ncz_check_name(name, norm_name)))
return retval;
LOG((2, "%s: ncid 0x%x size %d name %s base_typeid %d ",
__FUNCTION__, ncid, size, norm_name, base_typeid));
/* Find group metadata. */
if ((retval = ncz_find_grp_h5(ncid, &grp, &h5)))
return retval;
assert(h5 && grp);
/* User types cannot be defined with classic model flag. */
if (h5->cmode & NC_CLASSIC_MODEL)
return NC_ESTRICTNC3;
/* Turn on define mode if it is not on. */
if (!(h5->cmode & NC_INDEF))
if ((retval = NCZ_redef(ncid)))
return retval;
/* No size is provided for vlens; use the size of nc_vlen_t */
if (type_class == NC_VLEN)
size = sizeof(nc_vlen_t);
/* No size is provided for enums, get it from the base type. */
else if(type_class == NC_ENUM)
{
if ((retval = ncz_get_typelen_mem(grp->ncz_info, base_typeid, &size)))
return retval;
}
else if (size <= 0)
return NC_EINVAL;
/* Check that this name is not in use as a var, grp, or type. */
if ((retval = ncz_check_dup_name(grp, norm_name)))
return retval;
/* Add to our list of types. */
if ((retval = ncz_type_list_add(grp, size, norm_name, &type)))
return retval;
/* Allocate storage for NCZ-specific type info. */
if (!(ncz_type = calloc(1, sizeof(NCZ_TYPE_INFO_T))))
return NC_ENOMEM;
type->format_type_info = ncz_type;
ncz_type->common.file = h5;
/* Remember info about this type. */
type->nc_type_class = type_class;
if (type_class == NC_VLEN)
type->u.v.base_nc_typeid = base_typeid;
else if (type_class == NC_ENUM) {
type->u.e.base_nc_typeid = base_typeid;
type->u.e.enum_member = nclistnew();
} else if (type_class == NC_COMPOUND)
type->u.c.field = nclistnew();
/* Return the typeid to the user. */
if (typeidp)
*typeidp = type->hdr.id;
return NC_NOERR;
}
/**
* @internal Create a compound type.
*
* @param ncid File and group ID.
* @param size Gets size in bytes of one element of type.
* @param name Name of the type.
* @param typeidp Gets the type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EINVAL Bad size.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @return ::NC_ESTRICTNC3 Cannot define user types in classic model.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_def_compound(int ncid, size_t size, const char *name, nc_type *typeidp)
{
return add_user_type(ncid, size, name, 0, NC_COMPOUND, typeidp);
}
/**
* @internal Insert a named field into a compound type.
*
* @param ncid File and group ID.
* @param typeid1 Type ID.
* @param name Name of the type.
* @param offset Offset of field.
* @param field_typeid Field type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_insert_compound(int ncid, nc_type typeid1, const char *name, size_t offset,
nc_type field_typeid)
{
return nc_insert_array_compound(ncid, typeid1, name, offset,
field_typeid, 0, NULL);
}
/**
* @internal Insert a named array into a compound type.
*
* @param ncid File and group ID.
* @param typeid1 Type ID.
* @param name Name of the array field.
* @param offset Offset in bytes.
* @param field_typeid Type of field.
* @param ndims Number of dims for field.
* @param dim_sizesp Array of dim sizes.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @author Dennis Heimbigner, Ed Hartnett
*/
extern int
NCZ_insert_array_compound(int ncid, int typeid1, const char *name,
size_t offset, nc_type field_typeid,
int ndims, const int *dim_sizesp)
{
NC_GRP_INFO_T *grp;
NC_TYPE_INFO_T *type;
char norm_name[NC_MAX_NAME + 1];
int retval;
LOG((2, "nc_insert_array_compound: ncid 0x%x, typeid %d name %s "
"offset %d field_typeid %d ndims %d", ncid, typeid1,
name, offset, field_typeid, ndims));
/* Check and normalize the name. */
if ((retval = ncz_check_name(name, norm_name)))
return retval;
/* Find file metadata. */
if ((retval = ncz_find_ncz_grp(ncid, &grp)))
return retval;
/* Find type metadata. */
if ((retval = ncz_find_type(grp->ncz_info, typeid1, &type)))
return retval;
/* Did the user give us a good compound type typeid? */
if (!type || type->nc_type_class != NC_COMPOUND)
return NC_EBADTYPE;
/* If this type has already been written to the file, you can't
* change it. */
if (type->committed)
return NC_ETYPDEFINED;
/* Insert new field into this type's list of fields. */
if ((retval = ncz_field_list_add(type, norm_name, offset, field_typeid,
ndims, dim_sizesp)))
return retval;
return NC_NOERR;
}
/* Opaque type. */
/**
* @internal Create an opaque type. Provide a size and a name.
*
* @param ncid File and group ID.
* @param datum_size Size in bytes of a datum.
* @param name Name of new vlen type.
* @param typeidp Pointer that gets new type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EINVAL Bad size.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @return ::NC_ESTRICTNC3 Cannot define user types in classic model.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_def_opaque(int ncid, size_t datum_size, const char *name,
nc_type *typeidp)
{
return add_user_type(ncid, datum_size, name, 0, NC_OPAQUE, typeidp);
}
/**
* @internal Define a variable length type.
*
* @param ncid File and group ID.
* @param name Name of new vlen type.
* @param base_typeid Base type of vlen.
* @param typeidp Pointer that gets new type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @return ::NC_ESTRICTNC3 Cannot define user types in classic model.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_def_vlen(int ncid, const char *name, nc_type base_typeid,
nc_type *typeidp)
{
return add_user_type(ncid, 0, name, base_typeid, NC_VLEN, typeidp);
}
/**
* @internal Create an enum type. Provide a base type and a name. At
* the moment only ints are accepted as base types.
*
* @param ncid File and group ID.
* @param base_typeid Base type of vlen.
* @param name Name of new vlen type.
* @param typeidp Pointer that gets new type ID.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_ENOTNC4 User types in netCDF-4 files only.
* @return ::NC_EMAXNAME Name is too long.
* @return ::NC_EBADNAME Name breaks netCDF name rules.
* @return ::NC_ESTRICTNC3 Cannot define user types in classic model.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_def_enum(int ncid, nc_type base_typeid, const char *name,
nc_type *typeidp)
{
return add_user_type(ncid, 0, name, base_typeid, NC_ENUM, typeidp);
}
/**
* @internal Insert a identifier value into an enum type. The value
* must fit within the size of the enum type, the identifier size must
* be <= NC_MAX_NAME.
*
* @param ncid File and group ID.
* @param typeid1 Type ID.
* @param identifier Name of this enum value.
* @param value Value of enum.
*
* @return ::NC_NOERR No error.
* @return ::NC_EBADID Bad ncid.
* @return ::NC_EBADTYPE Type not found.
* @return ::NC_ETYPDEFINED Type already defined.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_insert_enum(int ncid, nc_type typeid1, const char *identifier,
const void *value)
{
NC_GRP_INFO_T *grp;
NC_TYPE_INFO_T *type;
char norm_name[NC_MAX_NAME + 1];
int retval;
LOG((2, "nc_insert_enum: ncid 0x%x, typeid %d identifier %s value %d", ncid,
typeid1, identifier, value));
/* Check and normalize the name. */
if ((retval = ncz_check_name(identifier, norm_name)))
return retval;
/* Find file metadata. */
if ((retval = ncz_find_ncz_grp(ncid, &grp)))
return retval;
/* Find type metadata. */
if ((retval = ncz_find_type(grp->ncz_info, typeid1, &type)))
return retval;
/* Did the user give us a good enum typeid? */
if (!type || type->nc_type_class != NC_ENUM)
return NC_EBADTYPE;
/* If this type has already been written to the file, you can't
* change it. */
if (type->committed)
return NC_ETYPDEFINED;
/* Insert new field into this type's list of fields. */
if ((retval = ncz_enum_member_add(type, type->size,
norm_name, value)))
return retval;
return NC_NOERR;
}
/**
* @internal Insert one element into an already allocated vlen array
* element.
*
* @param ncid File and group ID.
* @param typeid1 Type ID.
* @param vlen_element The VLEN element to insert.
* @param len Length of element in bytes.
* @param data Element data.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_put_vlen_element(int ncid, int typeid1, void *vlen_element,
size_t len, const void *data)
{
nc_vlen_t *tmp = (nc_vlen_t*)vlen_element;
tmp->len = len;
tmp->p = (void *)data;
return NC_NOERR;
}
/**
* @internal Insert one element into an already allocated vlen array
* element.
*
* @param ncid File and group ID.
* @param typeid1 Type ID.
* @param vlen_element The VLEN element to insert.
* @param len Length of element in bytes.
* @param data Element data.
*
* @return ::NC_NOERR No error.
* @author Dennis Heimbigner, Ed Hartnett
*/
int
NCZ_get_vlen_element(int ncid, int typeid1, const void *vlen_element,
size_t *len, void *data)
{
const nc_vlen_t *tmp = (nc_vlen_t*)vlen_element;
int type_size = 4;
*len = tmp->len;
memcpy(data, tmp->p, tmp->len * type_size);
return NC_NOERR;
}
#endif /*LOOK*/