netcdf-c/libdispatch/dutil.c

368 lines
7.6 KiB
C
Raw Normal View History

2017-09-01 04:36:54 +08:00
/*********************************************************************
* Copyright 2018, UCAR/Unidata
2017-09-01 04:36:54 +08:00
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*********************************************************************/
#include "config.h"
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_SYS_STAT_H
#include <sys/stat.h>
#endif
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif
#ifdef _MSC_VER
#include <io.h>
#endif
#include "netcdf.h"
#include "ncuri.h"
#include "ncbytes.h"
#include "nclist.h"
2017-09-01 04:36:54 +08:00
#include "nclog.h"
#include "ncpathmgr.h"
2017-09-01 04:36:54 +08:00
#define NC_MAX_PATH 4096
#define LBRACKET '['
#define RBRACKET ']'
/**************************************************/
/**
* Provide a hidden interface to allow utilities
* to check if a given path name is really an ncdap4 url.
* If no, return null, else return basename of the url
* minus any extension.
*/
int
NC__testurl(const char* path, char** basenamep)
{
NCURI* uri;
int ok = NC_NOERR;
if(ncuriparse(path,&uri))
2017-09-01 04:36:54 +08:00
ok = NC_EURL;
else {
char* slash = (uri->path == NULL ? NULL : strrchr(uri->path, '/'));
char* dot;
if(slash == NULL) slash = (char*)path; else slash++;
slash = nulldup(slash);
if(slash == NULL)
dot = NULL;
else
dot = strrchr(slash, '.');
if(dot != NULL && dot != slash) *dot = '\0';
if(basenamep)
*basenamep=slash;
else if(slash)
free(slash);
}
ncurifree(uri);
return ok;
}
/* Return 1 if this machine is little endian */
int
NC_isLittleEndian(void)
{
union {
unsigned char bytes[SIZEOF_INT];
int i;
} u;
u.i = 1;
return (u.bytes[0] == 1 ? 1 : 0);
}
char*
NC_backslashEscape(const char* s)
{
const char* p;
char* q;
size_t len;
char* escaped = NULL;
len = strlen(s);
escaped = (char*)malloc(1+(2*len)); /* max is everychar is escaped */
if(escaped == NULL) return NULL;
for(p=s,q=escaped;*p;p++) {
char c = *p;
switch (c) {
case '\\':
case '/':
case '.':
case '@':
*q++ = '\\'; *q++ = '\\';
break;
default: *q++ = c; break;
}
}
*q = '\0';
return escaped;
}
char*
NC_backslashUnescape(const char* esc)
{
size_t len;
char* s;
const char* p;
char* q;
if(esc == NULL) return NULL;
len = strlen(esc);
s = (char*)malloc(len+1);
if(s == NULL) return NULL;
for(p=esc,q=s;*p;) {
switch (*p) {
case '\\':
p++;
/* fall thru */
default: *q++ = *p++; break;
}
}
*q = '\0';
return s;
}
char*
NC_entityescape(const char* s)
{
const char* p;
char* q;
size_t len;
char* escaped = NULL;
const char* entity;
len = strlen(s);
escaped = (char*)malloc(1+(6*len)); /* 6 = |&apos;| */
if(escaped == NULL) return NULL;
for(p=s,q=escaped;*p;p++) {
char c = *p;
switch (c) {
case '&': entity = "&amp;"; break;
case '<': entity = "&lt;"; break;
case '>': entity = "&gt;"; break;
case '"': entity = "&quot;"; break;
case '\'': entity = "&apos;"; break;
default : entity = NULL; break;
}
if(entity == NULL)
*q++ = c;
else {
len = strlen(entity);
memcpy(q,entity,len);
q+=len;
}
}
*q = '\0';
return escaped;
}
char*
/*
Depending on the platform, the shell will sometimes
pass an escaped octotherpe character without removing
the backslash. So this function is appropriate to be called
on possible url paths to unescape such cases. See e.g. ncgen.
*/
NC_shellUnescape(const char* esc)
{
size_t len;
char* s;
const char* p;
char* q;
if(esc == NULL) return NULL;
len = strlen(esc);
s = (char*)malloc(len+1);
if(s == NULL) return NULL;
for(p=esc,q=s;*p;) {
switch (*p) {
case '\\':
if(p[1] == '#')
p++;
/* fall thru */
default: *q++ = *p++; break;
}
}
*q = '\0';
return s;
}
2017-09-01 04:36:54 +08:00
/**
Wrap mktmp and return the generated path,
or null if failed.
Base is the base file path. XXXXX is appended
to allow mktmp add its unique id.
Return the generated path.
2017-09-01 04:36:54 +08:00
*/
char*
NC_mktmp(const char* base)
2017-09-01 04:36:54 +08:00
{
int fd = -1;
char* tmp = NULL;
size_t len;
len = strlen(base)+6+1;
if((tmp = (char*)malloc(len))==NULL)
goto done;
strncpy(tmp,base,len);
strlcat(tmp, "XXXXXX", len);
fd = NCmkstemp(tmp);
2017-09-01 04:36:54 +08:00
if(fd < 0) {
nclog(NCLOGERR, "Could not create temp file: %s",tmp);
goto done;
}
done:
if(fd >= 0) close(fd);
return tmp;
2017-09-01 04:36:54 +08:00
}
Revert/Improve nc_create + NC_DISKLESS behavior re: https://github.com/Unidata/netcdf-c/issues/1154 Inadvertently, the behavior of NC_DISKLESS with nc_create() was changed in release 4.6.1. Previously, the NC_WRITE flag needed to be explicitly used with NC_DISKLESS in order to cause the created file to be persisted to disk. Additional analyis indicated that the current NC_DISKLESS implementation was seriously flawed. This PR attempts to clean up and regularize the situation with respect to NC_DISKLESS control. One important aspect of diskless operation is that there are two different notions of write. 1. The file is read-write vs read-only when using the netcdf API. 2. The file is persisted or not to disk at nc_close(). Previously, these two were conflated. The rules now are as follows. 1. NC_DISKLESS + NC_WRITE means that the file is read/write using the netcdf API 2. NC_DISKLESS + NC_PERSIST means that the file is persisted to a disk file at nc_close. 3. NC_DISKLESS + NC_PERSIST + NC_WRITE means both 1 and 2. The NC_PERSIST flag is new and takes over the obsolete NC_MPIPOSIX flag. NC_MPIPOSIX is still defined, but is now an alias for the NC_MPIIO flag. It is also now the case that for netcdf-4, NC_DISKLESS is independent of NC_INMEMORY and in fact it is an error to specify both flags simultaneously. Finally, the MMAP code was fixed to use NC_PERSIST as well. Also marked MMAP as deprecated. Also added a test case to test various combinations of NC_DISKLESS, NC_PERSIST, and NC_WRITE. This PR affects a number of files and especially test cases that used NC_DISKLESS. Misc. Unrelated fixes 1. fixed some warnings in ncdump/dumplib.c
2018-10-11 03:32:17 +08:00
int
NC_readfile(const char* filename, NCbytes* content)
{
int ret = NC_NOERR;
FILE* stream = NULL;
char part[1024];
#ifdef _WIN32
stream = NCfopen(filename,"rb");
#else
stream = NCfopen(filename,"r");
#endif
if(stream == NULL) {ret=errno; goto done;}
for(;;) {
size_t count = fread(part, 1, sizeof(part), stream);
if(count <= 0) break;
ncbytesappendn(content,part,count);
if(ferror(stream)) {ret = NC_EIO; goto done;}
if(feof(stream)) break;
}
ncbytesnull(content);
done:
if(stream) fclose(stream);
return ret;
}
int
NC_writefile(const char* filename, size_t size, void* content)
{
int ret = NC_NOERR;
FILE* stream = NULL;
void* p;
size_t remain;
#ifdef _WIN32
stream = NCfopen(filename,"wb");
#else
stream = NCfopen(filename,"w");
#endif
if(stream == NULL) {ret=errno; goto done;}
p = content;
remain = size;
while(remain > 0) {
size_t written = fwrite(p, 1, remain, stream);
if(ferror(stream)) {ret = NC_EIO; goto done;}
if(feof(stream)) break;
remain -= written;
}
done:
if(stream) fclose(stream);
return ret;
}
/*
Parse a path as a url and extract the modelist.
If the path is not a URL, then return a NULL list.
If a URL, but modelist is empty or does not exist,
then return empty list.
*/
int
NC_getmodelist(const char* path, NClist** modelistp)
{
int stat=NC_NOERR;
NClist* modelist = NULL;
NCURI* uri = NULL;
const char* modestr = NULL;
const char* p = NULL;
const char* endp = NULL;
ncuriparse(path,&uri);
if(uri == NULL) goto done; /* not a uri */
/* Get the mode= arg from the fragment */
modelist = nclistnew();
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
modestr = ncurifragmentlookup(uri,"mode");
if(modestr == NULL || strlen(modestr) == 0) goto done;
/* Parse the mode string at the commas or EOL */
p = modestr;
for(;;) {
char* s;
ptrdiff_t slen;
endp = strchr(p,',');
if(endp == NULL) endp = p + strlen(p);
slen = (endp - p);
if((s = malloc(slen+1)) == NULL) {stat = NC_ENOMEM; goto done;}
memcpy(s,p,slen);
s[slen] = '\0';
nclistpush(modelist,s);
if(*endp == '\0') break;
p = endp+1;
}
done:
if(stat == NC_NOERR) {
if(modelistp) {*modelistp = modelist; modelist = NULL;}
}
ncurifree(uri);
nclistfree(modelist);
return stat;
}
/*
Check "mode=" list for a path and return 1 if present, 0 otherwise.
*/
int
NC_testmode(const char* path, const char* tag)
{
int stat = NC_NOERR;
int found = 0;
int i;
NClist* modelist = NULL;
if((stat = NC_getmodelist(path, &modelist))) goto done;
for(i=0;i<nclistlength(modelist);i++) {
const char* value = nclistget(modelist,i);
if(strcasecmp(tag,value)==0) {found = 1; break;}
}
done:
Add support for multiple filters per variable. re: https://github.com/Unidata/netcdf-c/issues/1584 Support has been added for multiple filters per variable. This affects a number of components in netcdf. The new APIs are documented in NUG/filters.md. The primary changes are: * A set of new functions are provided (see __include/netcdf_filter.h__). - Obtain a list of the filters associated with a variable - Obtain the parameters for a specific filter. * The existing __nc_inq_var_filter__ function now returns info about the first defined filter. * The utilities (ncgen, ncdump, and nccopy) now support an extended format for specifying a sequence of filters. The general form is __<filter>|<filter>..._. * The ncdump **_Filter** attribute now dumps a list of all the filters associated with a variable using the above new format. * Filter specifications can now use a filter name instead of number for filters known to the netcdf library, which in turn is taken from the HDF5 filter registration page. * New errors are defined: NC_EFILTER and NC_ENOFILTER. The latter is returned if an attempt is made to access an unknown filter. * Internally, the dispatch table has been extended to add a function to handle all of the filter functions. * New, filter-related, tests were added to nc_test4. * A new plugin was added to the plugins directory to help with testing. Notes: 1. The shuffle and fletcher32 filters are not part of the multifilter system. Misc. changes: 1. A debug module was added to libhdf5 to help catch error locations.
2020-02-17 03:59:33 +08:00
nclistfreeall(modelist);
return found;
}
#ifdef __APPLE__
int isinf(double x)
{
union { unsigned long long u; double f; } ieee754;
ieee754.f = x;
return ( (unsigned)(ieee754.u >> 32) & 0x7fffffff ) == 0x7ff00000 &&
( (unsigned)ieee754.u == 0 );
}
int isnan(double x)
{
union { unsigned long long u; double f; } ieee754;
ieee754.f = x;
return ( (unsigned)(ieee754.u >> 32) & 0x7fffffff ) +
( (unsigned)ieee754.u != 0 ) > 0x7ff00000;
}
#endif /*APPLE*/