Skip to content

ARROW-16977: [R] Update dataset row counting so no integer overflow on large datasets #13514

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

Merged
nealrichardson merged 11 commits into from
Jul 14, 2022
Merged

ARROW-16977: [R] Update dataset row counting so no integer overflow on large datasets #13514

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
dbdacb7
Add in r_vec_size for dataset scanner row counting
thisisnic Jul 5, 2022
545e7e9
Update generated file
thisisnic Jul 7, 2022
fc061bc
Swap out int64 for r_vec_size
thisisnic Jul 7, 2022
34e9062
Add tests for Tables and RecordBatches
thisisnic Jul 8, 2022
21337ea
Add test for buffer size method
thisisnic Jul 8, 2022
63c5acc
Remove RecordBatch test
thisisnic Jul 12, 2022
2e19218
Use r_vec_size for more return types
thisisnic Jul 12, 2022
dc92b50
Use map_dbl not map_int for utility functions which use lengths
thisisnic Jul 12, 2022
e8c441a
Test more fields
thisisnic Jul 12, 2022
c71c5e1
Add test for buffers too
thisisnic Jul 13, 2022
c12da57
Remove redundant buffer test
thisisnic Jul 13, 2022
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
24 changes: 12 additions & 12 deletions r/src/array.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,15 +244,15 @@ int32_t ListArray__value_length(const std::shared_ptr<arrow::ListArray>& array,
}

// [[arrow::export]]
int64_t LargeListArray__value_length(const std::shared_ptr<arrow::LargeListArray>& array,
int64_t i) {
return array->value_length(i);
r_vec_size LargeListArray__value_length(
const std::shared_ptr<arrow::LargeListArray>& array, int64_t i) {
return r_vec_size(array->value_length(i));
}

// [[arrow::export]]
int64_t FixedSizeListArray__value_length(
r_vec_size FixedSizeListArray__value_length(
const std::shared_ptr<arrow::FixedSizeListArray>& array, int64_t i) {
return array->value_length(i);
return r_vec_size(array->value_length(i));
}

// [[arrow::export]]
Expand All @@ -262,15 +262,15 @@ int32_t ListArray__value_offset(const std::shared_ptr<arrow::ListArray>& array,
}

// [[arrow::export]]
int64_t LargeListArray__value_offset(const std::shared_ptr<arrow::LargeListArray>& array,
int64_t i) {
return array->value_offset(i);
r_vec_size LargeListArray__value_offset(
const std::shared_ptr<arrow::LargeListArray>& array, int64_t i) {
return r_vec_size(array->value_offset(i));
}

// [[arrow::export]]
int64_t FixedSizeListArray__value_offset(
r_vec_size FixedSizeListArray__value_offset(
const std::shared_ptr<arrow::FixedSizeListArray>& array, int64_t i) {
return array->value_offset(i);
return r_vec_size(array->value_offset(i));
}

// [[arrow::export]]
Expand Down Expand Up @@ -319,8 +319,8 @@ bool Array__Same(const std::shared_ptr<arrow::Array>& x,
}

// [[arrow::export]]
int64_t Array__ReferencedBufferSize(const std::shared_ptr<arrow::Array>& x) {
return ValueOrStop(arrow::util::ReferencedBufferSize(*x));
r_vec_size Array__ReferencedBufferSize(const std::shared_ptr<arrow::Array>& x) {
return r_vec_size(ValueOrStop(arrow::util::ReferencedBufferSize(*x)));
}

// [[arrow::export]]
Expand Down
44 changes: 22 additions & 22 deletions r/src/arrowExports.cpp
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 4 additions & 4 deletions r/src/buffer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,13 +28,13 @@ void Buffer__ZeroPadding(const std::shared_ptr<arrow::Buffer>& buffer) {
}

// [[arrow::export]]
int64_t Buffer__capacity(const std::shared_ptr<arrow::Buffer>& buffer) {
return buffer->capacity();
r_vec_size Buffer__capacity(const std::shared_ptr<arrow::Buffer>& buffer) {
return r_vec_size(buffer->capacity());
}

// [[arrow::export]]
int64_t Buffer__size(const std::shared_ptr<arrow::Buffer>& buffer) {
return buffer->size();
r_vec_size Buffer__size(const std::shared_ptr<arrow::Buffer>& buffer) {
return r_vec_size(buffer->size());
}

// [[arrow::export]]
Expand Down
4 changes: 2 additions & 2 deletions r/src/chunkedarray.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ std::shared_ptr<arrow::ChunkedArray> ChunkedArray__from_list(cpp11::list chunks,
}

// [[arrow::export]]
int64_t ChunkedArray__ReferencedBufferSize(
r_vec_size ChunkedArray__ReferencedBufferSize(
const std::shared_ptr<arrow::ChunkedArray>& chunked_array) {
return ValueOrStop(arrow::util::ReferencedBufferSize(*chunked_array));
return r_vec_size(ValueOrStop(arrow::util::ReferencedBufferSize(*chunked_array)));
}
4 changes: 2 additions & 2 deletions r/src/dataset.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,8 +511,8 @@ std::shared_ptr<arrow::Table> dataset___Scanner__TakeRows(
}

// [[dataset::export]]
int64_t dataset___Scanner__CountRows(const std::shared_ptr<ds::Scanner>& scanner) {
return ValueOrStop(scanner->CountRows());
r_vec_size dataset___Scanner__CountRows(const std::shared_ptr<ds::Scanner>& scanner) {
return r_vec_size(ValueOrStop(scanner->CountRows()));
Comment thread
thisisnic marked this conversation as resolved.
}

#endif
4 changes: 3 additions & 1 deletion r/src/filesystem.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,9 @@ void fs___FileInfo__set_path(const std::shared_ptr<fs::FileInfo>& x,
}

// [[arrow::export]]
int64_t fs___FileInfo__size(const std::shared_ptr<fs::FileInfo>& x) { return x->size(); }
r_vec_size fs___FileInfo__size(const std::shared_ptr<fs::FileInfo>& x) {
return r_vec_size(x->size());
}

// [[arrow::export]]
void fs___FileInfo__set_size(const std::shared_ptr<fs::FileInfo>& x, int64_t size) {
Expand Down
21 changes: 11 additions & 10 deletions r/src/io.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,9 +51,9 @@ void io___OutputStream__Close(const std::shared_ptr<arrow::io::OutputStream>& x)
// ------ arrow::io::RandomAccessFile

// [[arrow::export]]
int64_t io___RandomAccessFile__GetSize(
r_vec_size io___RandomAccessFile__GetSize(
const std::shared_ptr<arrow::io::RandomAccessFile>& x) {
return ValueOrStop(x->GetSize());
return r_vec_size(ValueOrStop(x->GetSize()));
}

// [[arrow::export]]
Expand All @@ -69,9 +69,9 @@ void io___RandomAccessFile__Seek(const std::shared_ptr<arrow::io::RandomAccessFi
}

// [[arrow::export]]
int64_t io___RandomAccessFile__Tell(
r_vec_size io___RandomAccessFile__Tell(
const std::shared_ptr<arrow::io::RandomAccessFile>& x) {
return ValueOrStop(x->Tell());
return r_vec_size(ValueOrStop(x->Tell()));
}

// [[arrow::export]]
Expand Down Expand Up @@ -161,8 +161,9 @@ void io___Writable__write(const std::shared_ptr<arrow::io::Writable>& stream,
// ------- arrow::io::OutputStream

// [[arrow::export]]
int64_t io___OutputStream__Tell(const std::shared_ptr<arrow::io::OutputStream>& stream) {
return ValueOrStop(stream->Tell());
r_vec_size io___OutputStream__Tell(
const std::shared_ptr<arrow::io::OutputStream>& stream) {
return r_vec_size(ValueOrStop(stream->Tell()));
}

// ------ arrow::io::FileOutputStream
Expand All @@ -183,9 +184,9 @@ std::shared_ptr<arrow::io::BufferOutputStream> io___BufferOutputStream__Create(
}

// [[arrow::export]]
int64_t io___BufferOutputStream__capacity(
r_vec_size io___BufferOutputStream__capacity(
const std::shared_ptr<arrow::io::BufferOutputStream>& stream) {
return stream->capacity();
return r_vec_size(stream->capacity());
}

// [[arrow::export]]
Expand All @@ -195,9 +196,9 @@ std::shared_ptr<arrow::Buffer> io___BufferOutputStream__Finish(
}

// [[arrow::export]]
int64_t io___BufferOutputStream__Tell(
r_vec_size io___BufferOutputStream__Tell(
const std::shared_ptr<arrow::io::BufferOutputStream>& stream) {
return ValueOrStop(stream->Tell());
return r_vec_size(ValueOrStop(stream->Tell()));
}

// [[arrow::export]]
Expand Down
9 changes: 5 additions & 4 deletions r/src/message.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,9 @@
#include <arrow/ipc/writer.h>

// [[arrow::export]]
int64_t ipc___Message__body_length(const std::unique_ptr<arrow::ipc::Message>& message) {
return message->body_length();
r_vec_size ipc___Message__body_length(
const std::unique_ptr<arrow::ipc::Message>& message) {
return r_vec_size(message->body_length());
}

// [[arrow::export]]
Expand All @@ -38,8 +39,8 @@ std::shared_ptr<arrow::Buffer> ipc___Message__body(
}

// [[arrow::export]]
int64_t ipc___Message__Verify(const std::unique_ptr<arrow::ipc::Message>& message) {
return message->Verify();
r_vec_size ipc___Message__Verify(const std::unique_ptr<arrow::ipc::Message>& message) {
return r_vec_size(message->Verify());
}

// [[arrow::export]]
Expand Down
4 changes: 2 additions & 2 deletions r/src/parquet.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,9 +148,9 @@ std::shared_ptr<arrow::Table> parquet___arrow___FileReader__ReadRowGroups2(
}

// [[parquet::export]]
int64_t parquet___arrow___FileReader__num_rows(
r_vec_size parquet___arrow___FileReader__num_rows(
const std::shared_ptr<parquet::arrow::FileReader>& reader) {
return reader->parquet_reader()->metadata()->num_rows();
return r_vec_size(reader->parquet_reader()->metadata()->num_rows());
}

// [[parquet::export]]
Expand Down
Loading