netcdf-c/libnczarr/zarr.h

69 lines
3.2 KiB
C
Raw Normal View History

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
/*********************************************************************
* Copyright 2018, UCAR/Unidata
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*********************************************************************/
/**
* Provide the zarr specific code to implement the netcdf-4 code.
*
* @author Dennis Heimbigner
*/
#ifndef ZARR_H
#define ZARR_H
/* zarr.c */
extern int ncz_create_dataset(NC_FILE_INFO_T*, NC_GRP_INFO_T*, const char** controls);
extern int ncz_open_dataset(NC_FILE_INFO_T*, const char** controls);
extern int ncz_del_attr(NC_FILE_INFO_T* file, NC_OBJ* container, const char* name);
extern int NCZ_isnetcdf4(struct NC_FILE_INFO*);
extern int NCZ_get_libversion(unsigned long* majorp, unsigned long* minorp,unsigned long* releasep);
extern int NCZ_get_superblock(NC_FILE_INFO_T* file, int* superblockp);
extern int ncz_unload_jatts(NCZ_FILE_INFO_T*, NC_OBJ* container, NCjson* jattrs, NCjson* jtypes);
/* zclose.c */
extern int ncz_close_file(NC_FILE_INFO_T* file, int abort);
/* zcvt.c */
extern int NCZ_convert1(NCjson* jsrc, nc_type, char* memory0);
extern int NCZ_stringconvert1(nc_type typid, char* src, char** strp);
extern int NCZ_stringconvert(nc_type typid, size_t len, void* data0, NCjson** jdatap);
/* zsync.c */
extern int ncz_sync_file(NC_FILE_INFO_T* file);
extern int ncz_sync_grp(NC_FILE_INFO_T* file, NC_GRP_INFO_T* grp);
extern int ncz_sync_atts(NC_FILE_INFO_T*, NC_OBJ* container, NCindex* attlist);
extern int ncz_read_grp(NC_FILE_INFO_T* file, NC_GRP_INFO_T* grp);
extern int ncz_read_atts(NC_FILE_INFO_T* file, NC_OBJ* container);
extern int ncz_read_vars(NC_FILE_INFO_T* file, NC_GRP_INFO_T* grp);
extern int ncz_read_file(NC_FILE_INFO_T* file);
extern int ncz_write_var(NC_VAR_INFO_T* var);
extern int ncz_create_superblock(NCZ_FILE_INFO_T* zinfo);
/* zutil.c */
extern int NCZ_grpkey(const NC_GRP_INFO_T* grp, char** pathp);
extern int NCZ_varkey(const NC_VAR_INFO_T* var, char** pathp);
extern int NCZ_dimkey(const NC_DIM_INFO_T* dim, char** pathp);
extern int ncz_splitkey(const char* path, NClist* segments);
extern int NCZ_readdict(NCZMAP* zmap, const char* key, NCjson** jsonp);
extern int NCZ_readarray(NCZMAP* zmap, const char* key, NCjson** jsonp);
extern int ncz_zarr_type_name(nc_type nctype, int little, const char** znamep);
extern int ncz_dtype2typeinfo(const char* dtype, nc_type* nctypep, int* endianness);
extern int ncz_fill_value_sort(nc_type nctype, int*);
extern int NCZ_createobject(NCZMAP* zmap, const char* key, size64_t size);
extern int NCZ_uploadjson(NCZMAP* zmap, const char* key, NCjson* json);
extern int NCZ_downloadjson(NCZMAP* zmap, const char* key, NCjson** jsonp);
extern int NCZ_isLittleEndian(void);
extern int NCZ_subobjects(NCZMAP* map, const char* prefix, const char* tag, NClist* objlist);
extern int NCZ_grpname_full(int gid, char** pathp);
extern int ncz_get_var_meta(NC_FILE_INFO_T* file, NC_VAR_INFO_T* var);
extern int NCZ_comma_parse(const char* s, NClist* list);
extern int NCZ_swapatomicdata(size_t datalen, void* data, int typesize);
extern char** NCZ_clonestringvec(size_t len, const char** vec);
extern void NCZ_freestringvec(size_t len, char** vec);
extern int NCZ_create_fill_chunk(size64_t chunksize, size_t typesize, void* fill, void** fillchunkp);
#endif /*ZARR_H*/