dongjoon-hyun commented on a change in pull request #934: URL: https://github.com/apache/orc/pull/934#discussion_r727798871
########## File path: c++/test/TestReader.cc ########## @@ -101,4 +101,41 @@ namespace orc { 900, rowsInCurrentStripe, rowIndexStride, includedRowGroups)); } + void CheckFileWithSargs(const char* fileName, const char* softwareVersion) { + std::stringstream ss; + if(const char* example_dir = std::getenv("ORC_EXAMPLE_DIR")) { + ss << example_dir; + } else { + ss << "../../../examples"; + } + // Read a file with bloom filters written by CPP writer in version 1.6.11. + ss << "/" << fileName; + ReaderOptions readerOpts; + std::unique_ptr<Reader> reader = + createReader(readLocalFile(ss.str().c_str()), readerOpts); + EXPECT_EQ(WriterId::ORC_CPP_WRITER, reader->getWriterId()); + EXPECT_EQ(softwareVersion, reader->getSoftwareVersion()); + + // Create SearchArgument with a EQUALS predicate which can leverage the bloom filters. + RowReaderOptions rowReaderOpts; + std::unique_ptr<SearchArgumentBuilder> sarg = SearchArgumentFactory::newBuilder(); + // Integer value 18000000000 has an inconsistent hash before the fix of ORC-1024. + sarg->equals(1, PredicateDataType::LONG,Literal(static_cast<int64_t>(18000000000L))); + std::unique_ptr<SearchArgument> final_sarg = sarg->build(); + rowReaderOpts.searchArgument(std::move(final_sarg)); + std::unique_ptr<RowReader> rowReader = reader->createRowReader(rowReaderOpts); + + // Make sure bad bloom filters won't affect the results. + std::unique_ptr<ColumnVectorBatch> batch = + rowReader->createRowBatch(1024); + EXPECT_TRUE(rowReader->next(*batch)); + EXPECT_EQ(5, batch->numElements); + EXPECT_FALSE(rowReader->next(*batch)); + } + + TEST(TestRowReader, testSkipBadBloomFilters) { + CheckFileWithSargs("bad_bloom_filter_1.6.11.orc", "ORC C++ 1.6.11"); + CheckFileWithSargs("bad_bloom_filter_1.6.0.orc", "ORC C++"); + CheckFileWithSargs("bad_bloom_filter_1.6.11-SNAPSHOT.orc", "ORC C++ 1.6.11-SNAPSHOT"); Review comment: Shall we remove this because we have `bad_bloom_filter_1.6.11.orc`? -- 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: dev-unsubscr...@orc.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org