Skip to content

DPL Analysis: add initial support for boolean columns #3131

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
ktf merged 1 commit into from
Mar 13, 2020
Merged

DPL Analysis: add initial support for boolean columns #3131

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
12 changes: 8 additions & 4 deletions Framework/Core/include/Framework/ASoA.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,10 @@ template <typename T>
struct arrow_array_for {
};
template <>
struct arrow_array_for<bool> {
using type = arrow::Int8Array;
};
template <>
struct arrow_array_for<int8_t> {
using type = arrow::Int8Array;
};
Expand Down Expand Up @@ -165,7 +169,7 @@ class ColumnIterator : ChunkingPolicy
{
auto chunks = mColumn->data();
auto array = std::static_pointer_cast<arrow_array_for_t<T>>(chunks->chunk(mCurrentChunk));
mCurrent = array->raw_values();
mCurrent = reinterpret_cast<T const*>(array->raw_values());
mLast = mCurrent + array->length();
}

Expand All @@ -184,7 +188,7 @@ class ColumnIterator : ChunkingPolicy
mFirstIndex += previousArray->length();
mCurrentChunk++;
auto array = std::static_pointer_cast<arrow_array_for_t<T>>(chunks->chunk(mCurrentChunk));
mCurrent = array->raw_values() - mFirstIndex;
mCurrent = reinterpret_cast<T const*>(array->raw_values() - mFirstIndex);
mLast = mCurrent + array->length() + mFirstIndex;
}

Expand All @@ -195,7 +199,7 @@ class ColumnIterator : ChunkingPolicy
mFirstIndex -= previousArray->length();
mCurrentChunk--;
auto array = std::static_pointer_cast<arrow_array_for_t<T>>(chunks->chunk(mCurrentChunk));
mCurrent = array->raw_values() - mFirstIndex;
mCurrent = reinterpret_cast<T const*>(array->raw_values() - mFirstIndex);
mLast = mCurrent + array->length() + mFirstIndex;
}

Expand All @@ -220,7 +224,7 @@ class ColumnIterator : ChunkingPolicy
auto array = std::static_pointer_cast<arrow_array_for_t<T>>(chunks->chunk(mCurrentChunk));
assert(array.get());
mFirstIndex = mColumn->length() - array->length();
mCurrent = array->raw_values() - mFirstIndex;
mCurrent = reinterpret_cast<T const*>(array->raw_values() - mFirstIndex);
mLast = mCurrent + array->length() + mFirstIndex;
}

Expand Down
3 changes: 2 additions & 1 deletion Framework/Core/include/Framework/TableBuilder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,8 @@ struct ConversionTraits {
using ArrowType = ::arrow::ArrowType_; \
};

O2_ARROW_STL_CONVERSION(bool, BooleanType)
// FIXME: for now we use Int8 to store booleans
O2_ARROW_STL_CONVERSION(bool, Int8Type)
O2_ARROW_STL_CONVERSION(int8_t, Int8Type)
O2_ARROW_STL_CONVERSION(int16_t, Int16Type)
O2_ARROW_STL_CONVERSION(int32_t, Int32Type)
Expand Down
15 changes: 11 additions & 4 deletions Framework/Core/test/test_ASoA.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,10 +36,11 @@ DECLARE_SOA_TABLE(Points, "TST", "POINTS", test::X, test::Y);

namespace test
{
DECLARE_SOA_COLUMN(SomeBool, someBool, bool, "someBool");
DECLARE_SOA_COLUMN(Color, color, int32_t, "color");
} // namespace test

DECLARE_SOA_TABLE(Infos, "TST", "INFOS", test::Color);
DECLARE_SOA_TABLE(Infos, "TST", "INFOS", test::Color, test::SomeBool);

namespace test
{
Expand Down Expand Up @@ -456,11 +457,15 @@ BOOST_AUTO_TEST_CASE(TestDereference)

TableBuilder builderA2;
auto infoWriter = builderA2.cursor<Infos>();
infoWriter(0, 0);
infoWriter(0, 1);
infoWriter(0, 4);
infoWriter(0, 0, 1);
infoWriter(0, 1, 0);
infoWriter(0, 4, 1);
auto infosT = builderA2.finalize();
Infos infos{infosT};
BOOST_REQUIRE_EQUAL(infos.begin().someBool(), true);
BOOST_REQUIRE_EQUAL((infos.begin() + 1).someBool(), false);
BOOST_REQUIRE_EQUAL((infos.begin() + 2).someBool(), true);
BOOST_REQUIRE_EQUAL((infos.begin() + 2).color(), 4);
BOOST_REQUIRE_EQUAL(infosT->num_rows(), 3);

TableBuilder builderB;
Expand All @@ -485,6 +490,7 @@ BOOST_AUTO_TEST_CASE(TestDereference)
i.bindExternalIndices(&points, &infos);
BOOST_CHECK_EQUAL(i.n(), 10);
BOOST_CHECK_EQUAL(i.info().color(), 4);
BOOST_CHECK_EQUAL(i.info().someBool(), true);
BOOST_CHECK_EQUAL(i.pointA().x(), 0);
BOOST_CHECK_EQUAL(i.pointA().y(), 0);
BOOST_CHECK_EQUAL(i.pointB().x(), 3);
Expand All @@ -494,6 +500,7 @@ BOOST_AUTO_TEST_CASE(TestDereference)
auto j = segments.begin();
BOOST_CHECK_EQUAL(j.n(), 10);
BOOST_CHECK_EQUAL(j.info().color(), 4);
BOOST_CHECK_EQUAL(j.info().someBool(), true);
BOOST_CHECK_EQUAL(j.pointA().x(), 0);
BOOST_CHECK_EQUAL(j.pointA().y(), 0);
BOOST_CHECK_EQUAL(j.pointB().x(), 3);
Expand Down
2 changes: 1 addition & 1 deletion Framework/Core/test/test_TableBuilder.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ BOOST_AUTO_TEST_CASE(TestTableBuilderMore)
BOOST_REQUIRE_EQUAL(table->column(0)->type()->id(), arrow::int32()->id());
BOOST_REQUIRE_EQUAL(table->column(1)->type()->id(), arrow::float32()->id());
BOOST_REQUIRE_EQUAL(table->column(2)->type()->id(), arrow::utf8()->id());
BOOST_REQUIRE_EQUAL(table->column(3)->type()->id(), arrow::boolean()->id());
BOOST_REQUIRE_EQUAL(table->column(3)->type()->id(), arrow::int8()->id());
}

// Use RDataFrame to build the table
Expand Down