Last active
December 13, 2018 21:51
-
-
Save suvayu/aa2d38cee82b97be76186ec00073fe10 to your computer and use it in GitHub Desktop.
Gandiva filtering MWE for SO (https://stackoverflow.com/q/53750405/289784)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CC := $(shell which gcc) | |
CXX := $(shell which g++) | |
PKGCONFIG := $(shell which pkg-config) | |
CXXSTD := -std=c++17 | |
OPTS := -g -Wall -m64 $(CXXSTD) | |
CXXFLAGS := $(OPTS) -pthread -fPIC $(shell $(PKGCONFIG) --cflags gandiva) | |
LDFLAGS := $(shell $(PKGCONFIG) --libs gandiva) | |
%: %.cc | |
$(CXX) $(CXXFLAGS) $< -o $@ $(LDFLAGS) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <memory> | |
#include <iostream> | |
#include <arrow/memory_pool.h> | |
#include <arrow/array.h> | |
#include <arrow/builder.h> | |
#include <gandiva/arrow.h> | |
#include <gandiva/filter.h> | |
#include <gandiva/tree_expr_builder.h> | |
#include <arrow/status.h> | |
#define EXPECT_OK(expr) \ | |
do { \ | |
::arrow::Status s = (expr); \ | |
} while (false) | |
using namespace arrow; | |
using namespace gandiva; | |
int main() | |
{ | |
arrow::MemoryPool* pool_ = arrow::default_memory_pool(); | |
int num_records = 5; | |
arrow::Int64Builder i64builder; | |
ArrayPtr array0; | |
EXPECT_OK(i64builder.AppendValues({1, 3, 2, 4, 5})); | |
EXPECT_OK(i64builder.Finish(&array0)); | |
std::cout << array0->ToString() << std::endl; | |
// schema for input fields | |
auto field0 = field("f0", arrow::int64()); | |
auto schema = arrow::schema({field0}); | |
// even: f0 % 2 == 0 | |
auto field0_node = TreeExprBuilder::MakeField(field0); | |
auto lit_2 = TreeExprBuilder::MakeLiteral(int64_t(2)); | |
auto remainder = TreeExprBuilder::MakeFunction("mod", {field0_node, lit_2}, int64()); | |
auto lit_0 = TreeExprBuilder::MakeLiteral(int64_t(0)); | |
auto even = TreeExprBuilder::MakeFunction("equal", {remainder, lit_0}, boolean()); | |
auto condition = TreeExprBuilder::MakeCondition(even); | |
// input record batch | |
auto in_batch = arrow::RecordBatch::Make(schema, num_records, {array0}); | |
// filter | |
std::shared_ptr<Filter> filter; | |
EXPECT_OK(Filter::Make(schema, condition, &filter)); | |
std::shared_ptr<SelectionVector> selected; | |
EXPECT_OK(SelectionVector::MakeInt16(num_records, pool_, &selected)); | |
EXPECT_OK(filter->Evaluate(*in_batch, selected)); | |
auto idx_arr = selected->ToArray(); | |
std::cout << idx_arr->ToString() << "\n" | |
<< "length of idx_arr: " << idx_arr->length() << std::endl; | |
// std::cout << "array0[0]: " << array0->Value(0); // doesn't compile | |
// error: ‘using element_type = class arrow::Array’ {aka ‘class | |
// arrow::Array’} has no member named ‘Value’ | |
// downcast it to the correct derived class | |
auto array0_cast = std::dynamic_pointer_cast<NumericArray<Int64Type>>(array0); | |
std::cout << "array0[0]: " << array0_cast->Value(0) << std::endl; | |
auto idx_arr_cast = std::dynamic_pointer_cast<NumericArray<Int16Type>>(idx_arr); | |
if (idx_arr_cast) { | |
std::cout << "idx_arr[0]: " << idx_arr_cast->Value(0) << std::endl; | |
} else { | |
std::cerr << "idx_arr_cast is a nullptr!" << std::endl; | |
} | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment