Skip to content

cli: detect output filename collisions before processing to prevent data loss #4870

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
siddiqueirshad wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

cli: detect output filename collisions before processing to prevent data loss #4870

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
66 changes: 42 additions & 24 deletions programs/fileio.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1141,12 +1141,29 @@ static void FIO_initDict(FIO_Dict_t* dict, const char* fileName, FIO_prefs_t* co
}


static const char*
extractFilename(const char* path, char separator)
{
const char* search = strrchr(path, separator);
if (search == NULL) return path;
return search+1;
}

static int FIO_compareFilename(const void *p1, const void *p2) {
#if defined(_MSC_VER) || defined(__MINGW32__) || defined(_WIN32)
return _stricmp(* (char * const *) p1, * (char * const *) p2);
#else
return strcmp(* (char * const *) p1, * (char * const *) p2);
#endif
}

/* FIO_checkFilenameCollisions() :
* Checks for and warns if there are any files that would have the same output path
* Checks for and errors if there are any files that would have the same output path
*/
int FIO_checkFilenameCollisions(const char** filenameTable, unsigned nbFiles) {
const char **filenameTableSorted, *prevElem, *filename;
unsigned u;
int hasCollision = 0;

filenameTableSorted = (const char**) malloc(sizeof(char*) * nbFiles);
if (!filenameTableSorted) {
Expand All @@ -1155,33 +1172,25 @@ int FIO_checkFilenameCollisions(const char** filenameTable, unsigned nbFiles) {
}

for (u = 0; u < nbFiles; ++u) {
filename = strrchr(filenameTable[u], PATH_SEP);
if (filename == NULL) {
filenameTableSorted[u] = filenameTable[u];
} else {
filenameTableSorted[u] = filename+1;
}
filename = extractFilename(filenameTable[u], PATH_SEP);
#if defined(_MSC_VER) || defined(__MINGW32__) || defined(_WIN32)
filename = extractFilename(filename, '/');
#endif
filenameTableSorted[u] = filename;
}

qsort((void*)filenameTableSorted, nbFiles, sizeof(char*), UTIL_compareStr);
qsort((void*)filenameTableSorted, nbFiles, sizeof(char*), FIO_compareFilename);
prevElem = filenameTableSorted[0];
for (u = 1; u < nbFiles; ++u) {
if (strcmp(prevElem, filenameTableSorted[u]) == 0) {
DISPLAYLEVEL(2, "WARNING: Two files have same filename: %s\n", prevElem);
if (FIO_compareFilename(&prevElem, &filenameTableSorted[u]) == 0) {
DISPLAYLEVEL(1, "zstd: error: Two files have the same output filename: %s\n", prevElem);
hasCollision = 1;
}
prevElem = filenameTableSorted[u];
}

free((void*)filenameTableSorted);
return 0;
}

static const char*
extractFilename(const char* path, char separator)
{
const char* search = strrchr(path, separator);
if (search == NULL) return path;
return search+1;
return hasCollision;
}

/* FIO_createFilename_fromOutDir() :
Expand Down Expand Up @@ -2512,6 +2521,13 @@ int FIO_compressMultipleFilenames(FIO_ctx_t* const fCtx,
if (outMirroredRootDirName)
UTIL_mirrorSourceFilesDirectories(inFileNamesTable, (unsigned)fCtx->nbFilesTotal, outMirroredRootDirName);

if (outDirName) {
if (FIO_checkFilenameCollisions(inFileNamesTable, (unsigned)fCtx->nbFilesTotal)) {
FIO_freeCResources(&ress);
return 1;
}
}

for (; fCtx->currFileIdx < fCtx->nbFilesTotal; ++fCtx->currFileIdx) {
const char* const srcFileName = inFileNamesTable[fCtx->currFileIdx];
const char* dstFileName = NULL;
Expand All @@ -2532,9 +2548,6 @@ int FIO_compressMultipleFilenames(FIO_ctx_t* const fCtx,
if (!status) fCtx->nbFilesProcessed++;
error |= status;
}

if (outDirName)
FIO_checkFilenameCollisions(inFileNamesTable , (unsigned)fCtx->nbFilesTotal);
}

if (FIO_shouldDisplayMultipleFileSummary(fCtx)) {
Expand Down Expand Up @@ -3367,6 +3380,13 @@ FIO_decompressMultipleFilenames(FIO_ctx_t* const fCtx,
if (outMirroredRootDirName)
UTIL_mirrorSourceFilesDirectories(srcNamesTable, (unsigned)fCtx->nbFilesTotal, outMirroredRootDirName);

if (outDirName) {
if (FIO_checkFilenameCollisions(srcNamesTable, (unsigned)fCtx->nbFilesTotal)) {
FIO_freeDResources(ress);
return 1;
}
}

for (; fCtx->currFileIdx < fCtx->nbFilesTotal; fCtx->currFileIdx++) { /* create dstFileName */
const char* const srcFileName = srcNamesTable[fCtx->currFileIdx];
const char* dstFileName = NULL;
Expand All @@ -3386,8 +3406,6 @@ FIO_decompressMultipleFilenames(FIO_ctx_t* const fCtx,
if (!status) fCtx->nbFilesProcessed++;
error |= status;
}
if (outDirName)
FIO_checkFilenameCollisions(srcNamesTable , (unsigned)fCtx->nbFilesTotal);
}

if (FIO_shouldDisplayMultipleFileSummary(fCtx)) {
Expand Down