Skip to content
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

ARROW-87: [C++] Add all four possible ways to encode Decimals in Parquet to schema conversion #48

Closed
wants to merge 2 commits into from
Closed

ARROW-87: [C++] Add all four possible ways to encode Decimals in Parquet to schema conversion #48

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6bafc5f
ARROW-87: [C++] Add all four possible ways to encode Decimals in Parq…
xhochy Mar 28, 2016
05ca3be
Use parquet:: namespace instead of parquet_cpp
xhochy Mar 28, 2016
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
36 changes: 36 additions & 0 deletions cpp/src/arrow/parquet/parquet-schema-test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@

#include "arrow/test-util.h"
#include "arrow/type.h"
#include "arrow/types/decimal.h"
#include "arrow/util/status.h"

#include "arrow/parquet/schema.h"
Expand All @@ -46,6 +47,7 @@ const auto DOUBLE = std::make_shared<DoubleType>();
const auto UTF8 = std::make_shared<StringType>();
const auto BINARY = std::make_shared<ListType>(
std::make_shared<Field>("", UINT8));
const auto DECIMAL_8_4 = std::make_shared<DecimalType>(8, 4);

class TestConvertParquetSchema : public ::testing::Test {
public:
Expand Down Expand Up @@ -119,6 +121,40 @@ TEST_F(TestConvertParquetSchema, ParquetFlatPrimitives) {
CheckFlatSchema(arrow_schema);
}

TEST_F(TestConvertParquetSchema, ParquetFlatDecimals) {
std::vector<NodePtr> parquet_fields;
std::vector<std::shared_ptr<Field>> arrow_fields;

parquet_fields.push_back(
PrimitiveNode::Make("flba-decimal", Repetition::OPTIONAL,
ParquetType::FIXED_LEN_BYTE_ARRAY,
LogicalType::DECIMAL, 4, 8, 4));
arrow_fields.push_back(std::make_shared<Field>("flba-decimal", DECIMAL_8_4));

parquet_fields.push_back(
PrimitiveNode::Make("binary-decimal", Repetition::OPTIONAL,
ParquetType::BYTE_ARRAY,
LogicalType::DECIMAL, -1, 8, 4));
arrow_fields.push_back(std::make_shared<Field>("binary-decimal", DECIMAL_8_4));

parquet_fields.push_back(
PrimitiveNode::Make("int32-decimal", Repetition::OPTIONAL,
ParquetType::INT32,
LogicalType::DECIMAL, -1, 8, 4));
arrow_fields.push_back(std::make_shared<Field>("int32-decimal", DECIMAL_8_4));

parquet_fields.push_back(
PrimitiveNode::Make("int64-decimal", Repetition::OPTIONAL,
ParquetType::INT64,
LogicalType::DECIMAL, -1, 8, 4));
arrow_fields.push_back(std::make_shared<Field>("int64-decimal", DECIMAL_8_4));

auto arrow_schema = std::make_shared<Schema>(arrow_fields);
ASSERT_OK(ConvertSchema(parquet_fields));

CheckFlatSchema(arrow_schema);
}

TEST_F(TestConvertParquetSchema, UnsupportedThings) {
std::vector<NodePtr> unsupported_nodes;

Expand Down
9 changes: 9 additions & 0 deletions cpp/src/arrow/parquet/schema.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,9 @@ static Status FromByteArray(const PrimitiveNode* node, TypePtr* out) {
case LogicalType::UTF8:
*out = UTF8;
break;
case LogicalType::DECIMAL:
*out = MakeDecimalType(node);
break;
default:
// BINARY
*out = BINARY;
Expand Down Expand Up @@ -86,6 +89,9 @@ static Status FromInt32(const PrimitiveNode* node, TypePtr* out) {
case LogicalType::NONE:
*out = INT32;
break;
case LogicalType::DECIMAL:
*out = MakeDecimalType(node);
break;
default:
return Status::NotImplemented("Unhandled logical type for int32");
break;
Expand All @@ -98,6 +104,9 @@ static Status FromInt64(const PrimitiveNode* node, TypePtr* out) {
case LogicalType::NONE:
*out = INT64;
break;
case LogicalType::DECIMAL:
*out = MakeDecimalType(node);
break;
default:
return Status::NotImplemented("Unhandled logical type for int64");
break;
Expand Down