wgtmac commented on code in PR #15244:
URL: https://github.com/apache/arrow/pull/15244#discussion_r1065954327
##########
cpp/src/parquet/arrow/arrow_reader_writer_test.cc:
##########
@@ -4727,5 +4726,74 @@ std::vector<NestedFilterTestCase>
GenerateMapFilteredTestCases() {
INSTANTIATE_TEST_SUITE_P(MapFilteredReads, TestNestedSchemaFilteredReader,
::testing::ValuesIn(GenerateMapFilteredTestCases()));
+template <typename TestType>
+class TestIntegerAnnotateDecimalTypeParquetIO : public TestParquetIO<TestType>
{
+ public:
+ template <typename ArrayType>
+ void WriteColumn(const std::shared_ptr<ArrayType>& values) {
+ auto arrow_schema = ::arrow::schema({::arrow::field("a", values->type())});
+
+ parquet::WriterProperties::Builder builder;
+ // Enforce integer type to annotate decimal type
+ auto writer_properties =
builder.enable_integer_annotate_decimal()->build();
+ std::shared_ptr<SchemaDescriptor> parquet_schema;
+ ASSERT_OK_NO_THROW(ToParquetSchema(arrow_schema.get(), *writer_properties,
+ *default_arrow_writer_properties(),
+ &parquet_schema));
+
+ this->sink_ = CreateOutputStream();
+ auto schema_node =
std::static_pointer_cast<GroupNode>(parquet_schema->schema_root());
+
+ std::unique_ptr<FileWriter> writer;
+ ASSERT_OK_NO_THROW(FileWriter::Make(
+ ::arrow::default_memory_pool(),
+ ParquetFileWriter::Open(this->sink_, schema_node, writer_properties),
+ arrow_schema, default_arrow_writer_properties(), &writer));
+ ASSERT_OK_NO_THROW(writer->NewRowGroup(values->length()));
+ ASSERT_OK_NO_THROW(writer->WriteColumnChunk(*values));
+ ASSERT_OK_NO_THROW(writer->Close());
+ }
+
+ void ReadAndCheckSingleDecimalColumnFile(const Array& values) {
+ std::shared_ptr<Array> out;
+ std::unique_ptr<FileReader> reader;
+ this->ReaderFromSink(&reader);
+ this->ReadSingleColumnFile(std::move(reader), &out);
+
+ // Reader always read values as DECIMAL128 type
+ ASSERT_EQ(out->type()->id(), ::arrow::Type::DECIMAL128);
+
+ if (values.type()->id() == ::arrow::Type::DECIMAL128) {
+ AssertArraysEqual(values, *out);
+ } else {
+ auto& expected_values = dynamic_cast<const
::arrow::Decimal256Array&>(values);
+ auto& read_values = dynamic_cast<const ::arrow::Decimal128Array&>(*out);
+ ASSERT_EQ(expected_values.null_count(), read_values.null_count());
+ ASSERT_EQ(0, read_values.null_count());
+ ASSERT_EQ(expected_values.length(), read_values.length());
+ for (int64_t i = 0; i < expected_values.length(); ++i) {
+ ASSERT_EQ(::arrow::Decimal256(expected_values.Value(i)).ToString(0),
+ ::arrow::Decimal128(read_values.Value(i)).ToString(0));
+ }
+ }
+ }
+};
+
+typedef ::testing::Types<
+ DecimalWithPrecisionAndScale<1>, DecimalWithPrecisionAndScale<5>,
+ DecimalWithPrecisionAndScale<10>, DecimalWithPrecisionAndScale<18>,
+ Decimal256WithPrecisionAndScale<1>, Decimal256WithPrecisionAndScale<5>,
+ Decimal256WithPrecisionAndScale<10>, Decimal256WithPrecisionAndScale<18>>
+ DecimalTestTypes;
+
+TYPED_TEST_SUITE(TestIntegerAnnotateDecimalTypeParquetIO, DecimalTestTypes);
+
+TYPED_TEST(TestIntegerAnnotateDecimalTypeParquetIO, SingleDecimalColumn) {
Review Comment:
Thanks for your review!
I have added the test with null values. It seems that the unsuccessful CI
checks are unrelavant to my commit. Please take a look again. Thanks!
@wjones127
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
