Skip to content
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

Fixes out-of-bounds access for small files in unzip #8498

Merged
merged 9 commits into from
Jun 17, 2021
Merged

Fixes out-of-bounds access for small files in unzip #8498

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
fd1e7c6
fixed OOB access for small files in unzip
elstehle Jun 11, 2021
ca1c679
fixing style
elstehle Jun 11, 2021
36e1c89
added unit test for reading zip-compressed CSV
elstehle Jun 15, 2021
e4db732
replaced underflow handling
elstehle Jun 15, 2021
d4a3a78
add python test for small zip files
elstehle Jun 16, 2021
0c67f2e
Merge branch 'branch-21.08' into fix/unzip-segfault-for-small-files
elstehle Jun 16, 2021
3c9e6df
reverted c++ test in favor of python test
elstehle Jun 16, 2021
8479017
remove redundant code block
elstehle Jun 16, 2021
e408fad
revert unrelated changes
elstehle Jun 17, 2021
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
8 changes: 5 additions & 3 deletions cpp/src/io/comp/uncomp.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,16 +193,18 @@ bool OpenZipArchive(zip_archive_s *dst, const uint8_t *raw, size_t len)
memset(dst, 0, sizeof(zip_archive_s));
// Find the end of central directory
if (len >= sizeof(zip_eocd_s) + 2) {
for (size_t i = len - sizeof(zip_eocd_s) - 2; i + sizeof(zip_eocd_s) + 2 + 0xffff >= len; i--) {
for (ptrdiff_t i = len - sizeof(zip_eocd_s) - 2;
i + sizeof(zip_eocd_s) + 2 + 0xffff >= len && i >= 0;
i--) {
const zip_eocd_s *eocd = reinterpret_cast<zip_eocd_s const *>(raw + i);
if (eocd->sig == 0x06054b50 &&
eocd->disk_id == eocd->start_disk // multi-file archives not supported
&& eocd->num_entries == eocd->total_entries &&
eocd->cdir_size >= sizeof(zip_cdfh_s) * eocd->num_entries && eocd->cdir_offset < len &&
i + *reinterpret_cast<const uint16_t *>(eocd + 1) <= len) {
i + *reinterpret_cast<const uint16_t *>(eocd + 1) <= static_cast<ptrdiff_t>(len)) {
const zip_cdfh_s *cdfh = reinterpret_cast<const zip_cdfh_s *>(raw + eocd->cdir_offset);
dst->eocd = eocd;
if (i >= sizeof(zip64_eocdl)) {
if (i >= static_cast<ptrdiff_t>(sizeof(zip64_eocdl))) {
const zip64_eocdl *eocdl =
reinterpret_cast<const zip64_eocdl *>(raw + i - sizeof(zip64_eocdl));
if (eocdl->sig == 0x07064b50) { dst->eocdl = eocdl; }
Expand Down
16 changes: 16 additions & 0 deletions python/cudf/cudf/tests/test_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -979,6 +979,22 @@ def test_csv_reader_filepath_or_buffer(tmpdir, path_or_buf, src):
assert_eq(expect, got)


def test_small_zip(tmpdir):
df = pd.DataFrame(
{
"a": [1997] * 2,
"b": ["Ford"] * 2,
"c": ["Super, luxurious truck"] * 2,
}
)

fname = tmpdir.join("small_zip_file.zip")
df.to_csv(fname, index=False)

got = cudf.read_csv(fname)
assert_eq(df, got)


def test_csv_reader_carriage_return(tmpdir):
rows = 1000
names = ["int_row", "int_double_row"]
Expand Down