zanmato1984 commented on code in PR #44470:
URL: https://github.com/apache/arrow/pull/44470#discussion_r1988456268
##########
cpp/src/arrow/dataset/file_test.cc:
##########
@@ -353,6 +356,89 @@ TEST_F(TestFileSystemDataset, WriteProjected) {
}
}
+// this kernel delays execution for some specific scalar values
+Status delay(compute::KernelContext* ctx, const compute::ExecSpan& batch,
+ compute::ExecResult* out) {
+ const ArraySpan& input = batch[0].array;
+ const uint32_t* input_values = input.GetValues<uint32_t>(1);
+ uint8_t* output_values = out->array_span()->buffers[1].data;
+
+ // Boolean data is stored in 1 bit per value
+ for (int64_t i = 0; i < input.length; ++i) {
+ if (input_values[i] % 16 == 0) {
+ std::this_thread::sleep_for(std::chrono::milliseconds(10));
+ }
+ bit_util::SetBitTo(output_values, i, true);
+ }
+
+ return Status::OK();
+}
+
+TEST_F(TestFileSystemDataset, WritePersistOrder) {
+ // Test for ARROW-26818
+ auto format = std::make_shared<IpcFileFormat>();
+ FileSystemDatasetWriteOptions write_options;
+ write_options.file_write_options = format->DefaultWriteOptions();
+ write_options.base_dir = "root";
+ write_options.partitioning = std::make_shared<HivePartitioning>(schema({}));
+ write_options.basename_template = "{i}.feather";
+
+ auto table = gen::Gen({gen::Step()})->FailOnError()->Table(2, 1024);
+ auto dataset = std::make_shared<InMemoryDataset>(table);
+
+ // register the scalar function that delays execution for some rows
+ // this guarantees the writing phase sees out-of-order exec batches
+ auto delay_func = std::make_shared<compute::ScalarFunction>("delay",
compute::Arity(1),
+
compute::FunctionDoc());
+ compute::ScalarKernel delay_kernel;
+ delay_kernel.exec = delay;
+ delay_kernel.signature = compute::KernelSignature::Make({uint32()},
boolean());
+ ARROW_CHECK_OK(delay_func->AddKernel(delay_kernel));
+ ARROW_CHECK_OK(compute::GetFunctionRegistry()->AddFunction(delay_func));
Review Comment:
IIUC `ARROW_CHECK/DCHECK_*` series are used to assert some invariants in
non-testing code (i.e., aborts the execution when fired), whereas
`ASSERT/EXPECT_*` is purely for tests (fails the test with nice error message
if possible).
--
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]
