TheCloud/dwarfs
1
0
Fork 0
mirror of https://github.com/mhx/dwarfs.git synced 2025-09-09 12:28:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

Visit entries in inode order during extraction

Browse Source
This commit is contained in:
Marcus Holland-Moritz 2021-03-05 00:39:22 +01:00
parent ad901ee092
commit ea6369cf8b
1 changed files with 21 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/dwarfsextract.cpp
View File

@ -19,9 +19,12 @@
* along with dwarfs. If not, see <https://www.gnu.org/licenses/>.
*/
#include <algorithm>
#include <cstring>
#include <exception>
#include <vector>
#include <sys/statvfs.h>
#include <unistd.h>
#include <boost/program_options.hpp>
@ -141,6 +144,22 @@ int dwarfsextract(int argc, char** argv) {
: nullptr));
}
// TODO: This can surely be implemented more efficiently inside libdwarfs
// using entry indices / inode numbers, which should reduce the
// amount of memory needed by roughly a factor of 8.
std::vector<std::pair<entry_view, directory_view>> entries;
fs.walk([&](auto entry, auto parent) {
if (!S_ISDIR(entry.mode())) {
entries.emplace_back(entry, parent);
}
});
std::sort(entries.begin(), entries.end(), [](auto& a, auto& b) {
return a.first.inode() < b.first.inode();
});
auto lr = ::archive_entry_linkresolver_new();
::archive_entry_linkresolver_set_strategy(lr, ::archive_format(a));
@ -159,11 +178,7 @@ int dwarfsextract(int argc, char** argv) {
}
};
fs.walk([&](auto entry, auto parent) {
if (entry.inode() == 0) {
return;
}
for (auto& [entry, parent] : entries) {
auto ae = ::archive_entry_new();
struct ::stat stbuf;
@ -206,7 +221,7 @@ int dwarfsextract(int argc, char** argv) {
do_archive(spare, *ev);
::archive_entry_free(spare);
}
});
}
// As we're visiting *all* hardlinks, we should never see any deferred
// entries.