netcdf-c/libdispatch/dutil.c
Dennis Heimbigner 44d0dcaad2 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.
2020-02-16 12:59:33 -07:00

354 lines
7.6 KiB
C

/*********************************************************************
* Copyright 2018, UCAR/Unidata
* 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"
#include "nclog.h"
#include "ncwinpath.h"
extern int mkstemp(char *template);
#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))
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;
}
/**
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.
*/
char*
NC_mktmp(const char* base)
{
int fd;
char* cvtpath = NULL;
char tmp[NC_MAX_PATH];
#ifdef HAVE_MKSTEMP
mode_t mask;
#endif
/* Make sure that this path conversion has been applied */
cvtpath = NCpathcvt(base);
strncpy(tmp,cvtpath,sizeof(tmp));
nullfree(cvtpath);
strncat(tmp, "XXXXXX", sizeof(tmp) - strlen(tmp) - 1);
#ifdef HAVE_MKSTEMP
/* Note Potential problem: old versions of this function
leave the file in mode 0666 instead of 0600 */
mask=umask(0077);
fd = mkstemp(tmp);
(void)umask(mask);
#else /* !HAVE_MKSTEMP */
{
#ifdef HAVE_MKTEMP
#ifdef _MSC_VER
/* Use _mktemp_s */
_mktemp_s(tmp,sizeof(tmp)-1);
#else /*!_MSC_VER*/
mktemp(tmp);
tmo[sizeof[tmp]-1] = '\0';
#endif
#else /* !HAVE_MKTEMP */
/* Need to simulate by using some kind of pseudo-random number */
{
int rno = rand();
char spid[7];
if(rno < 0) rno = -rno;
snprintf(spid,sizeof(spid),"%06d",rno);
strncat(tmp,spid,sizeof(tmp) - strlen(tmp) - 1);
}
#endif /* HAVE_MKTEMP */
#ifdef _MSC_VER
fd=NCopen3(tmp,O_RDWR|O_BINARY|O_CREAT, _S_IREAD|_S_IWRITE);
#else
fd=NCopen3(tmp,O_RDWR|O_CREAT|O_EXCL, S_IRWXU);
#endif
}
#endif /* !HAVE_MKSTEMP */
if(fd < 0) {
nclog(NCLOGERR, "Could not create temp file: %s",tmp);
return NULL;
} else
close(fd);
return strdup(tmp);
}
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();
modestr = ncurilookup(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:
nclistfreeall(modelist);
return found;
}