wgtmac commented on code in PR #37400:
URL: https://github.com/apache/arrow/pull/37400#discussion_r2593174390
##########
cpp/src/parquet/column_writer_test.cc:
##########
@@ -2380,5 +2382,86 @@ TYPED_TEST(TestColumnWriterMaxRowsPerPage,
RequiredLargeChunk) {
}
}
+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>> BuildWriter(
+ int64_t output_size, const ColumnProperties& column_properties) {
+ this->sink_ = CreateOutputStream();
+
+ WriterProperties::Builder properties_builder;
+ if (column_properties.encoding() == Encoding::PLAIN_DICTIONARY ||
+ column_properties.encoding() == Encoding::RLE_DICTIONARY) {
+ properties_builder.enable_dictionary();
+ } else {
+ properties_builder.disable_dictionary();
+ properties_builder.encoding(column_properties.encoding());
+ }
+ auto path = this->schema_.Column(0)->path();
+ if (column_properties.bloom_filter_enabled()) {
+
properties_builder.enable_bloom_filter(*column_properties.bloom_filter_options(),
+ path);
+ } else {
+ properties_builder.disable_bloom_filter(path);
+ }
+ this->writer_properties_ = properties_builder.build();
+
+ this->metadata_ =
+ ColumnChunkMetaDataBuilder::Make(this->writer_properties_,
this->descr_);
+ auto pager = PageWriter::Open(this->sink_, column_properties.compression(),
+ this->metadata_.get());
+
+ builder_ = BloomFilterBuilder::Make(&this->schema_,
this->writer_properties_.get());
+ builder_->AppendRowGroup();
+ bloom_filter_ = builder_->GetOrCreateBloomFilter(/*column_ordinal=*/0);
+
+ return std::static_pointer_cast<TypedColumnWriter<TestType>>(
+ ColumnWriter::Make(this->metadata_.get(), std::move(pager),
+ this->writer_properties_.get(), bloom_filter_));
+ }
+
+ std::unique_ptr<BloomFilterBuilder> builder_;
+ BloomFilter* bloom_filter_{nullptr};
Review Comment:
Yes, let me add a comment.
--
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]
