netcdf-c/libdispatch/ncbytes.c

212 lines
4.5 KiB
C
Raw Normal View History

/* Copyright 2018, UCAR/Unidata and OPeNDAP, Inc.
2010-06-03 21:24:43 +08:00
See the COPYRIGHT file for more information. */
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include "ncbytes.h"
#ifndef TRUE
#define TRUE 1
#endif
#ifndef FALSE
#define FALSE 0
#endif
#define DEFAULTALLOC 1024
#define ALLOCINCR 1024
#define NCBYTESDEBUG 1
2010-06-03 21:24:43 +08:00
static int
2010-06-03 21:24:43 +08:00
ncbytesfail(void)
{
fflush(stdout);
fprintf(stderr,"bytebuffer failure\n");
fflush(stderr);
#ifdef NCBYTESDEBUG
abort();
#endif
2010-06-03 21:24:43 +08:00
return FALSE;
}
NCbytes*
ncbytesnew(void)
{
NCbytes* bb = (NCbytes*)malloc(sizeof(NCbytes));
if(bb == NULL) return (ncbytesfail(),NULL);
2010-06-03 21:24:43 +08:00
bb->alloc=0;
bb->length=0;
bb->content=NULL;
bb->nonextendible = 0;
return bb;
}
int
ncbytessetalloc(NCbytes* bb, unsigned long sz)
2010-06-03 21:24:43 +08:00
{
char* newcontent;
if(bb == NULL) return ncbytesfail();
if(sz == 0) {sz = (bb->alloc?2*bb->alloc:DEFAULTALLOC);}
2010-06-03 21:24:43 +08:00
if(bb->alloc >= sz) return TRUE;
if(bb->nonextendible) return ncbytesfail();
newcontent=(char*)calloc(sz,sizeof(char));
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
if(newcontent == NULL) ncbytesfail();
2010-06-03 21:24:43 +08:00
if(bb->alloc > 0 && bb->length > 0 && bb->content != NULL) {
memcpy((void*)newcontent,(void*)bb->content,sizeof(char)*bb->length);
}
if(bb->content != NULL) free(bb->content);
bb->content=newcontent;
bb->alloc=sz;
return TRUE;
}
2020-09-16 04:56:12 +08:00
EXTERNL void
2010-06-03 21:24:43 +08:00
ncbytesfree(NCbytes* bb)
{
if(bb == NULL) return;
if(!bb->nonextendible && bb->content != NULL) free(bb->content);
free(bb);
}
int
ncbytessetlength(NCbytes* bb, unsigned long sz)
2010-06-03 21:24:43 +08:00
{
if(bb == NULL) return ncbytesfail();
if(bb->length < sz) {
if(sz > bb->alloc) {if(!ncbytessetalloc(bb,sz)) return ncbytesfail();}
}
2010-06-03 21:24:43 +08:00
bb->length = sz;
return TRUE;
}
int
ncbytesfill(NCbytes* bb, char fill)
{
unsigned long i;
2010-06-03 21:24:43 +08:00
if(bb == NULL) return ncbytesfail();
for(i=0;i<bb->length;i++) bb->content[i] = fill;
return TRUE;
}
int
ncbytesget(NCbytes* bb, unsigned long index)
2010-06-03 21:24:43 +08:00
{
if(bb == NULL) return -1;
if(index >= bb->length) return -1;
return bb->content[index];
}
int
ncbytesset(NCbytes* bb, unsigned long index, char elem)
2010-06-03 21:24:43 +08:00
{
if(bb == NULL) return ncbytesfail();
if(index >= bb->length) return ncbytesfail();
bb->content[index] = elem;
return TRUE;
}
int
ncbytesappend(NCbytes* bb, char elem)
2010-06-03 21:24:43 +08:00
{
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
char s[2];
2010-06-03 21:24:43 +08:00
if(bb == NULL) return ncbytesfail();
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
s[0] = elem;
s[1] = '\0';
ncbytesappendn(bb,s,1);
2010-06-03 21:24:43 +08:00
return TRUE;
}
/* This assumes s is a null terminated string*/
int
ncbytescat(NCbytes* bb, const char* s)
2010-06-03 21:24:43 +08:00
{
2023-04-28 05:12:26 +08:00
if(bb == NULL) return ncbytesfail();
if(s == NULL) return 1;
ncbytesappendn(bb,(void*)s,strlen(s)+1); /* include trailing null*/
/* back up over the trailing null*/
if(bb->length == 0) return ncbytesfail();
bb->length--;
return 1;
2010-06-03 21:24:43 +08:00
}
int
ncbytesappendn(NCbytes* bb, const void* elem, unsigned long n)
2010-06-03 21:24:43 +08:00
{
if(bb == NULL || elem == NULL) return ncbytesfail();
if(n == 0) {n = strlen((char*)elem);}
Improve S3 Documentation and Support ## Improvements to S3 Documentation * Create a new document *quickstart_paths.md* that give a summary of the legal path formats used by netcdf-c. This includes both file paths and URL paths. * Modify *nczarr.md* to remove most of the S3 related text. * Move the S3 text from *nczarr.md* to a new document *cloud.md*. * Add some S3-related text to the *byterange.md* document. Hopefully, this will make it easier for users to find the information they want. ## Rebuild NCZarr Testing In order to avoid problems with running make check in parallel, two changes were made: 1. The *nczarr_test* test system was rebuilt. Now, for each test. any generated files are kept in a test-specific directory, isolated from all other test executions. 2. Similarly, since the S3 test bucket is shared, any generated S3 objects are isolated using a test-specific key path. ## Other S3 Related Changes * Add code to ensure that files created on S3 are reclaimed at end of testing. * Used the bash "trap" command to ensure S3 cleanup even if the test fails. * Cleanup the S3 related configure.ac flag set since S3 is used in several places. So now one should use the option *--enable-s3* instead of *--enable-nczarr-s3*, although the latter is still kept as a deprecated alias for the former. * Get some of the github actions yml to work with S3; required fixing various test scripts adding a secret to access the Unidata S3 bucket. * Cleanup S3 portion of libnetcdf.settings.in and netcdf_meta.h.in and test_common.in. * Merge partial S3 support into dhttp.c. * Create an experimental s3 access library especially for use with Windows. It is enabled by using the options *--enable-s3-internal* (automake) or *-DENABLE_S3_INTERNAL=ON* (CMake). Also add a unit-test for it. * Move some definitions from ncrc.h to ncs3sdk.h ## Other Changes * Provide a default implementation of strlcpy and move this and similar defaults into *dmissing.c*.
2023-04-26 07:15:06 +08:00
ncbytessetalloc(bb,bb->length+n);
2010-06-03 21:24:43 +08:00
memcpy((void*)&bb->content[bb->length],(void*)elem,n);
bb->length += n;
return TRUE;
}
int
ncbytesprepend(NCbytes* bb, char elem)
{
int i; /* do not make unsigned */
if(bb == NULL) return ncbytesfail();
if(bb->length >= bb->alloc) if(!ncbytessetalloc(bb,0)) return ncbytesfail();
/* could we trust memcpy? instead */
for(i=(int)bb->alloc;i>=1;i--) {bb->content[i]=bb->content[i-1];}
2010-06-03 21:24:43 +08:00
bb->content[0] = elem;
bb->length++;
return TRUE;
}
char*
ncbytesdup(NCbytes* bb)
{
char* result = (char*)malloc(bb->length+1);
memcpy((void*)result,(const void*)bb->content,bb->length);
result[bb->length] = '\0'; /* just in case it is a string*/
return result;
}
char*
ncbytesextract(NCbytes* bb)
{
char* result = bb->content;
bb->alloc = 0;
bb->length = 0;
bb->content = NULL;
return result;
}
int
ncbytessetcontents(NCbytes* bb, void* contents, unsigned long alloc)
2010-06-03 21:24:43 +08:00
{
if(bb == NULL) return ncbytesfail();
ncbytesclear(bb);
if(!bb->nonextendible && bb->content != NULL) free(bb->content);
bb->content = (char*)contents;
bb->length = alloc;
2010-06-03 21:24:43 +08:00
bb->alloc = alloc;
bb->nonextendible = 1;
return 1;
}
/* Null terminate the byte string without extending its length */
int
ncbytesnull(NCbytes* bb)
{
ncbytesappend(bb,'\0');
bb->length--;
return 1;
}
Primary change: add dap4 support Specific changes: 1. Add dap4 code: libdap4 and dap4_test. Note that until the d4ts server problem is solved, dap4 is turned off. 2. Modify various files to support dap4 flags: configure.ac, Makefile.am, CMakeLists.txt, etc. 3. Add nc_test/test_common.sh. This centralizes the handling of the locations of various things in the build tree: e.g. where is ncgen.exe located. See nc_test/test_common.sh for details. 4. Modify .sh files to use test_common.sh 5. Obsolete separate oc2 by moving it to be part of netcdf-c. This means replacing code with netcdf-c equivalents. 5. Add --with-testserver to configure.ac to allow override of the servers to be used for --enable-dap-remote-tests. 6. There were multiple versions of nctypealignment code. Try to centralize in libdispatch/doffset.c and include/ncoffsets.h 7. Add a unit test for the ncuri code because of its complexity. 8. Move the findserver code out of libdispatch and into a separate, self contained program in ncdap_test and dap4_test. 9. Move the dispatch header files (nc{3,4}dispatch.h) to .../include because they are now shared by modules. 10. Revamp the handling of TOPSRCDIR and TOPBUILDDIR for shell scripts. 11. Make use of MREMAP if available 12. Misc. minor changes e.g. - #include <config.h> -> #include "config.h" - Add some no-install headers to /include - extern -> EXTERNL and vice versa as needed - misc header cleanup - clean up checking for misc. unix vs microsoft functions 13. Change copyright decls in some files to point to LICENSE file. 14. Add notes to RELEASENOTES.md
2017-03-09 08:01:10 +08:00
/* Remove char at position i */
int
ncbytesremove(NCbytes* bb, unsigned long pos)
{
if(bb == NULL) return ncbytesfail();
if(bb->length <= pos) return ncbytesfail();
if(pos < (bb->length - 1)) {
int copylen = (bb->length - pos) - 1;
memmove(bb->content+pos,bb->content+pos+1,copylen);
}
bb->length--;
return TRUE;
}