Skip to content

fix(programs): identify the input file by identity on Windows #4861

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Huang-404-Q wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

fix(programs): identify the input file by identity on Windows #4861

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 30 additions & 10 deletions programs/util.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
#endif /* #ifdef __FreeBSD__ */

#if defined(_WIN32)
# include <windows.h> /* CreateFileA, GetFileInformationByHandle */
# include <sys/utime.h> /* utime */
# include <io.h> /* _chmod */
# define ZSTD_USE_UTIMENSAT 0
Expand Down Expand Up @@ -381,17 +382,34 @@ int UTIL_compareStr(const void *p1, const void *p2) {
return strcmp(* (char * const *) p1, * (char * const *) p2);
}

#if defined(_MSC_VER) || defined(_WIN32)
/* Windows has no inode: compare the volume serial and file index instead. */
static int UTIL_getFileIdentity(const char* fName, BY_HANDLE_FILE_INFORMATION* info)
{
HANDLE const h = CreateFileA(fName, FILE_READ_ATTRIBUTES,
FILE_SHARE_READ | FILE_SHARE_WRITE | FILE_SHARE_DELETE,
NULL, OPEN_EXISTING, FILE_ATTRIBUTE_NORMAL, NULL);
BOOL ok;
if (h == INVALID_HANDLE_VALUE) return 0;
ok = GetFileInformationByHandle(h, info);
CloseHandle(h);
return ok != 0;
}
#endif

int UTIL_isSameFile(const char* fName1, const char* fName2)
{
int ret;
assert(fName1 != NULL); assert(fName2 != NULL);
UTIL_TRACE_CALL("UTIL_isSameFile(%s, %s)", fName1, fName2);
#if defined(_MSC_VER) || defined(_WIN32)
/* note : Visual does not support file identification by inode.
* inode does not work on Windows, even with a posix layer, like msys2.
* The following work-around is limited to detecting exact name repetition only,
* aka `filename` is considered different from `subdir/../filename` */
ret = !strcmp(fName1, fName2);
{ BY_HANDLE_FILE_INFORMATION file1Info, file2Info;
ret = UTIL_getFileIdentity(fName1, &file1Info)
&& UTIL_getFileIdentity(fName2, &file2Info)
&& file1Info.dwVolumeSerialNumber == file2Info.dwVolumeSerialNumber
&& file1Info.nFileIndexHigh == file2Info.nFileIndexHigh
&& file1Info.nFileIndexLow == file2Info.nFileIndexLow;
}
#else
{ stat_t file1Stat;
stat_t file2Stat;
Expand All @@ -412,13 +430,15 @@ int UTIL_isSameFileStat(
assert(fName1 != NULL); assert(fName2 != NULL);
UTIL_TRACE_CALL("UTIL_isSameFileStat(%s, %s)", fName1, fName2);
#if defined(_MSC_VER) || defined(_WIN32)
/* note : Visual does not support file identification by inode.
* inode does not work on Windows, even with a posix layer, like msys2.
* The following work-around is limited to detecting exact name repetition only,
* aka `filename` is considered different from `subdir/../filename` */
(void)file1Stat;
(void)file2Stat;
ret = !strcmp(fName1, fName2);
{ BY_HANDLE_FILE_INFORMATION file1Info, file2Info;
ret = UTIL_getFileIdentity(fName1, &file1Info)
&& UTIL_getFileIdentity(fName2, &file2Info)
&& file1Info.dwVolumeSerialNumber == file2Info.dwVolumeSerialNumber
&& file1Info.nFileIndexHigh == file2Info.nFileIndexHigh
&& file1Info.nFileIndexLow == file2Info.nFileIndexLow;
}
#else
{
ret = (file1Stat->st_dev == file2Stat->st_dev)
Expand Down
14 changes: 14 additions & 0 deletions tests/cli-tests/file-stat/compress-file-to-itself.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
#!/bin/sh

set -e

datagen > file
cp file file.orig

# The same path spelled differently must still be detected as the input file.
# On Windows the old strcmp fallback treated "./file" as a different file and
# truncated the input before reading it.
println "+ zstd -q -f file -o ./file"
zstd -q -f file -o ./file && die "Should not overwrite the input file"

cmp file file.orig