mapleFU commented on code in PR #37400:
URL: https://github.com/apache/arrow/pull/37400#discussion_r1313776556
##########
cpp/src/parquet/column_writer_test.cc:
##########
@@ -1591,5 +1592,88 @@ TEST(TestColumnWriter, WriteDataPageV2HeaderNullCount) {
}
}
+template <typename TestType>
+class TestBloomFilterWriter : public TestPrimitiveWriter<TestType> {
+ public:
+ void SetUp() override {
+ TestPrimitiveWriter<TestType>::SetUp();
+ builder_ = nullptr;
+ bloom_filter_ = nullptr;
+ }
+
+ std::shared_ptr<TypedColumnWriter<TestType>> BuildWriterWithBloomFilter(
+ int64_t output_size = SMALL_SIZE,
+ const ColumnProperties& column_properties = ColumnProperties());
+
+ std::unique_ptr<BloomFilterBuilder> builder_;
+ BloomFilter* bloom_filter_;
+};
+
+template <typename TestType>
+std::shared_ptr<TypedColumnWriter<TestType>>
+TestBloomFilterWriter<TestType>::BuildWriterWithBloomFilter(
+ int64_t output_size, const ColumnProperties& column_properties) {
+ this->sink_ = CreateOutputStream();
+ WriterProperties::Builder wp_builder;
+ if (column_properties.encoding() == Encoding::PLAIN_DICTIONARY ||
+ column_properties.encoding() == Encoding::RLE_DICTIONARY) {
+ wp_builder.enable_dictionary();
+ wp_builder.dictionary_pagesize_limit(DICTIONARY_PAGE_SIZE);
+ } else {
+ wp_builder.disable_dictionary();
+ wp_builder.encoding(column_properties.encoding());
+ }
+ wp_builder.max_statistics_size(column_properties.max_statistics_size());
+ this->writer_properties_ = wp_builder.build();
+
+ this->metadata_ =
+ ColumnChunkMetaDataBuilder::Make(this->writer_properties_, this->descr_);
+ std::unique_ptr<PageWriter> pager = PageWriter::Open(
+ this->sink_, column_properties.compression(), this->metadata_.get());
+ builder_ = BloomFilterBuilder::Make(&this->schema_,
*this->writer_properties_);
+ // Initial RowGroup
+ builder_->AppendRowGroup();
+ BloomFilterOptions options;
+ options.ndv = static_cast<int32_t>(output_size);
+ bloom_filter_ = builder_->GetOrCreateBloomFilter(0, options);
+ std::shared_ptr<ColumnWriter> writer =
+ ColumnWriter::Make(this->metadata_.get(), std::move(pager),
+ this->writer_properties_.get(), bloom_filter_);
+ return std::static_pointer_cast<TypedColumnWriter<TestType>>(writer);
+}
+
+// Note: BooleanType is Excluded.
+using TestBloomFilterTypes = ::testing::Types<Int32Type, Int64Type, Int96Type,
FloatType,
+ DoubleType, ByteArrayType,
FLBAType>;
+
+TYPED_TEST_SUITE(TestBloomFilterWriter, TestBloomFilterTypes);
+
+TYPED_TEST(TestBloomFilterWriter, Basic) {
+ this->GenerateData(SMALL_SIZE);
+ ColumnProperties column_properties;
+ column_properties.set_bloom_filter_enabled(true);
+
+ auto writer = this->BuildWriterWithBloomFilter(SMALL_SIZE,
column_properties);
+ writer->WriteBatch(this->values_.size(), nullptr, nullptr,
this->values_ptr_);
+ writer->Close();
+
+ // Read all rows so we are sure that also the non-dictionary pages are read
correctly
+ this->SetupValuesOut(SMALL_SIZE);
+ this->ReadColumnFully();
+ ASSERT_EQ(SMALL_SIZE, this->values_read_);
+ this->values_.resize(SMALL_SIZE);
Review Comment:
Removed
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
