netcdf-c/libsrc/ncFile.c

223 lines
5.2 KiB
C
Raw Normal View History

/*
* Copyright 2018, University Corporation for Atmospheric Research
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*/
#include <stdlib.h>
#include <stdio.h>
#include <errno.h>
Codify cross-platform file paths The netcdf-c code has to deal with a variety of platforms: Windows, OSX, Linux, Cygwin, MSYS, etc. These platforms differ significantly in the kind of file paths that they accept. So in order to handle this, I have created a set of replacements for the most common file system operations such as _open_ or _fopen_ or _access_ to manage the file path differences correctly. A more limited version of this idea was already implemented via the ncwinpath.h and dwinpath.c code. So this can be viewed as a replacement for that code. And in path in many cases, the only change that was required was to replace '#include <ncwinpath.h>' with '#include <ncpathmgt.h>' and then replace file operation calls with the NCxxx equivalent from ncpathmgr.h Note that recently, the ncwinpath.h was renamed ncpathmgmt.h, so this pull request should not require dealing with winpath. The heart of the change is include/ncpathmgmt.h, which provides alternate operations such as NCfopen or NCaccess and which properly parse and rebuild path arguments to work for the platform on which the code is executing. This mostly matters for Windows because of the way that it uses backslash and drive letters, as compared to *nix*. One important feature is that the user can do string manipulations on a file path without having to worry too much about the platform because the path management code will properly handle most mixed cases. So one can for example concatenate a path suffix that uses forward slashes to a Windows path and have it work correctly. The conversion code is in libdispatch/dpathmgr.c, and the important function there is NCpathcvt which does the proper conversions to the local path format. As a rule, most code should just replace their file operations with the corresponding NCxxx ones defined in include/ncpathmgmt.h. These NCxxx functions all call NCpathcvt on their path arguments before executing the actual file operation. In some rare cases, the client may need to directly use NCpathcvt, but this should be avoided as much as possible. If there is a need for supporting a new file operation not already in ncpathmgmt.h, then use the code in dpathmgr.c as a template. Also please notify Unidata so we can include it as a formal part or our supported operations. Also, if you see an operation in the library that is not using the NCxxx form, then please submit an issue so we can fix it. Misc. Changes: * Clean up the utf8 testing code; it is impossible to get some tests to work under windows using shell scripts; the args do not pass as utf8 but as some other encoding. * Added an extra utf8 test case: test_unicode_path.sh * Add a true test for HDF5 1.10.6 or later because as noted in PR https://github.com/Unidata/netcdf-c/pull/1794, HDF5 changed its Windows file path handling.
2021-03-05 04:41:31 +08:00
#include "ncpathmgr.h"
/*
Implement the ncstdio.h interface using unix stdio.h
*/
/* Forward */
static int NCFile_read(ncstdio*,void*,const size_t,size_t*);
static int NCFile_write(ncstdio*,const void*,const size_t,size_t*);
static int NCFile_free(ncstdio*);
static int NCFile_close(ncstdio*,int);
static int NCFile_flush(ncstdio*)
static int NCFile_seek(ncstdio*,off_t);
static int NCFile_sync(ncstdio*,off_t);
static int NCFile_uid(ncstdio*,int*);
/* Define the stdio.h base operators */
struct NCFile_ops NCFile_ops = {
NCFile_read,
NCFile_write,
NCFile_free,
NCFile_close,
NCFile_flush,
NCFile_seek,
NCFile_sync,
NCFile_uid
};
/* In order to implement the close with delete, we
need the file path.
*/
struct ncFileState {
char* path;
File* file;
};
static struct ncFileState
getState(ncstdio* iop)
{
if(iop != NULL) {
if(iop->state != NULL) {
return (struct ncFileState*)iop->state;
}
}
return NULL;
}
int
ncFile_create(const char *path, int ioflags, ncstdio** filepp)
{
ncstdio* filep;
File* f;
struct ncFileState* state;
Improve UTF8 Support On Windows re: Issue https://github.com/Unidata/netcdf-c/issues/2190 The primary purpose of this PR is to improve the utf8 support for windows. This is persuant to a change in Windows that supports utf8 natively (almost). The almost means that it is still utf16 internally and the set of characters representable by utf8 is larger than those representable by utf16. This leaves open the question in the Issue about handling the Windows 1252 character set. This required the following changes: 1. Test the Windows build and major version in order to see if native utf8 is supported. 2. If native utf8 is supported, Modify dpathmgr.c to call the 8-bit version of the windows fopen() and open() functions. 3. In support of this, programs that use XGetOpt (Windows versions) need to get the command line as utf8 and then parse to arc+argv as utf8. This requires using a homegrown command line parser named XCommandLineToArgvA. 4. Add a utility program called "acpget" that prints out the current Windows code page and locale. Additionally, some technical debt was cleaned up as follows: 1. Unify all the places which attempt to read all or a part of a file into the dutil.c#NC_readfile code. 2. Similary unify all the code that creates temp files into dutil.c#NC_mktmp code. 3. Convert almost all remaining calls to fopen() and open() to NCfopen() and NCopen3(). This is to ensure that path management is used consistently. This touches a number of files. 4. extern->EXTERNL as needed to get it to work under Windows.
2022-02-09 11:53:30 +08:00
f = NCfopen(path,"w+");
if(f == NULL)
return errno;
filep = (ncstdio*)calloc(sizeof(ncstdio),1);
if(filep == NULL) {fclose(f); return NC_ENOMEM;}
state = (ncstdio*)calloc(sizeof(ncFileState),1);
if(state == NULL) {fclose(f); free(filep); return NC_ENOMEM;}
filep->ops = &NCFILE_ops;
filep->ioflags = ioflags;
filep->state = (void*)state;
state->path = strdup(path);
state->file = f;
if(filepp) *filepp = filep;
return NC_NOERR;
}
int
ncFile_open(const char *path, int ioflags, ncstdio** filepp)
{
ncstdio* filep;
File* f;
if(fIsSet(ioflags,NC_NOCLOBBER))
Codify cross-platform file paths The netcdf-c code has to deal with a variety of platforms: Windows, OSX, Linux, Cygwin, MSYS, etc. These platforms differ significantly in the kind of file paths that they accept. So in order to handle this, I have created a set of replacements for the most common file system operations such as _open_ or _fopen_ or _access_ to manage the file path differences correctly. A more limited version of this idea was already implemented via the ncwinpath.h and dwinpath.c code. So this can be viewed as a replacement for that code. And in path in many cases, the only change that was required was to replace '#include <ncwinpath.h>' with '#include <ncpathmgt.h>' and then replace file operation calls with the NCxxx equivalent from ncpathmgr.h Note that recently, the ncwinpath.h was renamed ncpathmgmt.h, so this pull request should not require dealing with winpath. The heart of the change is include/ncpathmgmt.h, which provides alternate operations such as NCfopen or NCaccess and which properly parse and rebuild path arguments to work for the platform on which the code is executing. This mostly matters for Windows because of the way that it uses backslash and drive letters, as compared to *nix*. One important feature is that the user can do string manipulations on a file path without having to worry too much about the platform because the path management code will properly handle most mixed cases. So one can for example concatenate a path suffix that uses forward slashes to a Windows path and have it work correctly. The conversion code is in libdispatch/dpathmgr.c, and the important function there is NCpathcvt which does the proper conversions to the local path format. As a rule, most code should just replace their file operations with the corresponding NCxxx ones defined in include/ncpathmgmt.h. These NCxxx functions all call NCpathcvt on their path arguments before executing the actual file operation. In some rare cases, the client may need to directly use NCpathcvt, but this should be avoided as much as possible. If there is a need for supporting a new file operation not already in ncpathmgmt.h, then use the code in dpathmgr.c as a template. Also please notify Unidata so we can include it as a formal part or our supported operations. Also, if you see an operation in the library that is not using the NCxxx form, then please submit an issue so we can fix it. Misc. Changes: * Clean up the utf8 testing code; it is impossible to get some tests to work under windows using shell scripts; the args do not pass as utf8 but as some other encoding. * Added an extra utf8 test case: test_unicode_path.sh * Add a true test for HDF5 1.10.6 or later because as noted in PR https://github.com/Unidata/netcdf-c/pull/1794, HDF5 changed its Windows file path handling.
2021-03-05 04:41:31 +08:00
f = NCfopen(path,"r");
else
Codify cross-platform file paths The netcdf-c code has to deal with a variety of platforms: Windows, OSX, Linux, Cygwin, MSYS, etc. These platforms differ significantly in the kind of file paths that they accept. So in order to handle this, I have created a set of replacements for the most common file system operations such as _open_ or _fopen_ or _access_ to manage the file path differences correctly. A more limited version of this idea was already implemented via the ncwinpath.h and dwinpath.c code. So this can be viewed as a replacement for that code. And in path in many cases, the only change that was required was to replace '#include <ncwinpath.h>' with '#include <ncpathmgt.h>' and then replace file operation calls with the NCxxx equivalent from ncpathmgr.h Note that recently, the ncwinpath.h was renamed ncpathmgmt.h, so this pull request should not require dealing with winpath. The heart of the change is include/ncpathmgmt.h, which provides alternate operations such as NCfopen or NCaccess and which properly parse and rebuild path arguments to work for the platform on which the code is executing. This mostly matters for Windows because of the way that it uses backslash and drive letters, as compared to *nix*. One important feature is that the user can do string manipulations on a file path without having to worry too much about the platform because the path management code will properly handle most mixed cases. So one can for example concatenate a path suffix that uses forward slashes to a Windows path and have it work correctly. The conversion code is in libdispatch/dpathmgr.c, and the important function there is NCpathcvt which does the proper conversions to the local path format. As a rule, most code should just replace their file operations with the corresponding NCxxx ones defined in include/ncpathmgmt.h. These NCxxx functions all call NCpathcvt on their path arguments before executing the actual file operation. In some rare cases, the client may need to directly use NCpathcvt, but this should be avoided as much as possible. If there is a need for supporting a new file operation not already in ncpathmgmt.h, then use the code in dpathmgr.c as a template. Also please notify Unidata so we can include it as a formal part or our supported operations. Also, if you see an operation in the library that is not using the NCxxx form, then please submit an issue so we can fix it. Misc. Changes: * Clean up the utf8 testing code; it is impossible to get some tests to work under windows using shell scripts; the args do not pass as utf8 but as some other encoding. * Added an extra utf8 test case: test_unicode_path.sh * Add a true test for HDF5 1.10.6 or later because as noted in PR https://github.com/Unidata/netcdf-c/pull/1794, HDF5 changed its Windows file path handling.
2021-03-05 04:41:31 +08:00
f = NCfopen(path,"w+");
if(f == NULL)
return errno;
filep = (ncstdio*)calloc(sizeof(ncstdio),1);
if(filep == NULL) {fclose(f); return NC_ENOMEM;}
state = (ncstdio*)calloc(sizeof(ncFileState),1);
if(state == NULL) {fclose(f); free(filep); return NC_ENOMEM;}
filep->ops = &NCFILE_ops;
filep->ioflags = ioflags;
filep->state = (void*)state;
state->path = strdup(path);
state->file = f;
if(filepp) *filepp = filep;
return NC_NOERR;
}
static int
NCFile_close(ncstdio* filep, int delfile)
{
struct ncFileState* state;
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL || state->file == NULL) return NC_NOERR;
fclose(state->file);
state->file = NULL;
if(delfile)
unlink(state->path);
return NC_NOERR;
}
static int
NCFile_free(ncstdio* filep)
{
struct ncFileState* state;
if(filep == NULL) return NC_NOERR;
state = (struct ncFileState*)filep->state;
if(state != NULL) {
if(state->file != NULL) return NC_EINVAL;
if(state->path != NULL)
free(state->path);
free(state);
}
free(filep);
return NC_NOERR;
}
static int
NCFile_flush(ncstdio* filep);
{
File* state;
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL) return NC_EINVAL;
if(state->file == NULL) return NC_EINVAL;
fflush(state->file);
return NC_NOERR;
}
static int
NCFile_sync(ncstdio* filep);
{
File* state;
#ifdef USE_FSYNC
int fd;
#endif
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL) return NC_EINVAL;
if(state->file == NULL) return NC_EINVAL;
#ifdef HAVE_FSYNC
#ifdef USE_FSYNC
fd = fileno(state->file);
#ifndef _WIN32
fsync(fd);
#else
_commit(fd);
#endif /* _WIN32 */
#endif
#endif
return NC_NOERR;
}
static int
NCFile_seek(ncstdio* filep, off_t pos);
{
struct ncFileState* state;
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL) return NC_EINVAL;
if(state->file == NULL) return NC_EINVAL;
if(!fseek(state->file,pos)) return (errno > 0 ?errno : EINVAL);
return NC_NOERR;
}
static int
NCFile_read(ncstdio* filep, void* memory, const size_t size, size_t* actualp);
{
struct ncFileState* state;
size_t actual;
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL || state->file == NULL) return NC_EINVAL;
actual = fread(memory,1,size,state->file);
if(actualp) *actualp = actual;
return (actual < size ? NC_EIO : NC_NOERR);
}
static int
NCFile_write(ncstdio* filep, const void* memory, const size_t size, size_t* actual);
{
struct ncFileState* state;
size_t actual;
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL || state->file == NULL) return NC_EINVAL;
actual = fwrite(memory,1,size,state->file);
if(actualp) *actualp = actual;
return (actual < size ? NC_EIO : NC_NOERR);
}
static int
NCFile_uid(ncstdio* filep, int* idp)
{
struct ncFileState* state;
if(filep == NULL) return NC_EINVAL;
state = (struct ncFileState*)filep->state;
if(state == NULL || state->file == NULL) return NC_EINVAL;
if(idp) *idp = fileno(state->file);
return NC_NOERR;
}