Skip to content

GH-47657: [C++][Parquet] Check for integer overflow when coercing timestamps #49615

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
ArnavBalyan wants to merge 4 commits into
base: main
Choose a base branch
from
+43 −1
Open

GH-47657: [C++][Parquet] Check for integer overflow when coercing timestamps #49615

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5a3f92e
update
ArnavBalyan Mar 29, 2026
c3075ce
comments
ArnavBalyan Mar 30, 2026
57096ac
lint
ArnavBalyan Mar 30, 2026
c551cf0
comments
ArnavBalyan Apr 2, 2026
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
35 changes: 35 additions & 0 deletions cpp/src/parquet/arrow/arrow_reader_writer_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2178,6 +2178,41 @@ TEST(TestArrowReadWrite, ImplicitSecondToMillisecondTimestampCoercion) {
ASSERT_NO_FATAL_FAILURE(::arrow::AssertTablesEqual(*tx, *to));
}

TEST(TestArrowReadWrite, TimestampCoercionOverflow) {
using ::arrow::ArrayFromVector;
using ::arrow::field;
using ::arrow::schema;
auto t_s = ::arrow::timestamp(TimeUnit::SECOND);
std::vector<int64_t> overflow_values = {9223372036854776LL};
std::vector<bool> is_valid = {true};
std::shared_ptr<Array> a_s;
ArrayFromVector<::arrow::TimestampType, int64_t>(t_s, is_valid, overflow_values, &a_s);

auto s = schema({field("timestamp", t_s)});
auto table = Table::Make(s, {a_s});

for (auto unit : {TimeUnit::SECOND, TimeUnit::MILLI, TimeUnit::MICRO, TimeUnit::NANO}) {
if (unit == TimeUnit::SECOND) {
ASSERT_RAISES(Invalid, WriteTable(*table, default_memory_pool(),
CreateOutputStream(), table->num_rows()));
} else {
auto coerce_props =
ArrowWriterProperties::Builder().coerce_timestamps(unit)->build();
ASSERT_RAISES(Invalid, WriteTable(*table, default_memory_pool(),
CreateOutputStream(), table->num_rows(),
default_writer_properties(), coerce_props));
}
}

std::vector<bool> null_valid = {false};
std::shared_ptr<Array> a_null;
ArrayFromVector<::arrow::TimestampType, int64_t>(t_s, null_valid, overflow_values,
&a_null);
auto null_table = Table::Make(s, {a_null});
ASSERT_OK_NO_THROW(WriteTable(*null_table, default_memory_pool(), CreateOutputStream(),
null_table->num_rows()));
}

TEST(TestArrowReadWrite, ParquetVersionTimestampDifferences) {
using ::arrow::ArrayFromVector;
using ::arrow::field;
Expand Down
9 changes: 8 additions & 1 deletion cpp/src/parquet/column_writer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
#include "arrow/util/crc32.h"
#include "arrow/util/endian.h"
#include "arrow/util/float16.h"
#include "arrow/util/int_util_overflow.h"
#include "arrow/util/key_value_metadata.h"
#include "arrow/util/logging_internal.h"
#include "arrow/util/rle_encoding_internal.h"
Expand Down Expand Up @@ -2352,7 +2353,13 @@ struct SerializeFunctor<Int64Type, ::arrow::TimestampType> {

auto MultiplyBy = [&](const int64_t factor) {
for (int64_t i = 0; i < array.length(); i++) {
out[i] = values[i] * factor;
if (array.IsValid(i) &&
ARROW_PREDICT_FALSE(::arrow::internal::MultiplyWithOverflowGeneric(
values[i], factor, &out[i]))) {
return Status::Invalid("Integer overflow when casting timestamp value ",
values[i], " from ", source_type.ToString(), " to ",
target_type->ToString());
}
}
return Status::OK();
};
Expand Down
Loading