Skip to content

MINOR: [C++][Gandiva] Fix output buffer size in mask() #53915

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
Nayana-Naik73 wants to merge 1 commit into
base: main
Choose a base branch
from
+32 −2
Open

MINOR: [C++][Gandiva] Fix output buffer size in mask() #53915

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
14 changes: 12 additions & 2 deletions cpp/src/gandiva/gdv_function_stubs.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@

#include <utf8proc.h>

#include <algorithm>
#include <boost/crc.hpp>
#include <cstdio>
#include <sstream>
Expand All @@ -28,6 +29,7 @@
#include "arrow/util/base64.h"
#include "arrow/util/bit_util.h"
#include "arrow/util/double_conversion_internal.h"
#include "arrow/util/int_util_overflow.h"
#include "arrow/util/value_parsing.h"

#include "gandiva/encrypt_utils.h"
Expand Down Expand Up @@ -663,8 +665,16 @@ const char* mask_utf8_utf8_utf8_utf8(int64_t context, const char* data, int32_t
return nullptr;
}

int32_t max_length =
std::max(upper_length, std::max(lower_length, num_length)) * data_len;
// Characters that are not replaced are copied as-is, so reserve at least one
// output byte per input byte even when all replacements are empty.
int32_t max_length;
if (ARROW_PREDICT_FALSE(arrow::internal::MultiplyWithOverflow(
std::max({upper_length, lower_length, num_length, 1}), data_len,
&max_length))) {
gdv_fn_context_set_error_msg(context, "Would overflow maximum output size");
*out_len = 0;
return nullptr;
}
char* out = reinterpret_cast<char*>(gdv_fn_context_arena_malloc(context, max_length));
if (out == nullptr) {
gdv_fn_context_set_error_msg(context, "Could not allocate memory for output string");
Expand Down
20 changes: 20 additions & 0 deletions cpp/src/gandiva/gdv_function_stubs_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1539,6 +1539,26 @@ TEST(TestGdvFnStubs, TestMask) {
result = mask_utf8_utf8_utf8_utf8(ctx_ptr, data.c_str(), data_len, "\?", 1, "*", 1, "#",
1, &out_len);
EXPECT_EQ(std::string(result, out_len), expected);

// With empty replacements the unmasked characters must still get their own
// output space, so a later allocation cannot overwrite them.
data = "QwErTy:4)";
expected = ":)";
data_len = static_cast<int32_t>(data.length());
result = mask_utf8_utf8_utf8_utf8(ctx_ptr, data.c_str(), data_len, "", 0, "", 0, "", 0,
&out_len);
int32_t other_len = 0;
mask_utf8_utf8_utf8_utf8(ctx_ptr, "#$", 2, "", 0, "", 0, "", 0, &other_len);
EXPECT_EQ(std::string(result, out_len), expected);

data = std::string(46341, 'A');
data_len = static_cast<int32_t>(data.length());
result = mask_utf8_utf8_utf8_utf8(ctx_ptr, data.c_str(), data_len, data.c_str(),
data_len, "x", 1, "n", 1, &out_len);
EXPECT_EQ(out_len, 0);
EXPECT_THAT(ctx.get_error(),
::testing::HasSubstr("Would overflow maximum output size"));
ctx.Reset();
}

TEST(TestGdvFnStubs, TestAesEncryptDecrypt16) {
Expand Down
Loading