rok commented on code in PR #14341:
URL: https://github.com/apache/arrow/pull/14341#discussion_r1269627474
##########
cpp/src/parquet/encoding_test.cc:
##########
@@ -1908,4 +1907,304 @@ TEST(DeltaLengthByteArrayEncodingAdHoc, ArrowDirectPut)
{
CheckDecode(encoded, ::arrow::ArrayFromJSON(::arrow::large_binary(),
values));
}
+// ----------------------------------------------------------------------
+// DELTA_BYTE_ARRAY encode/decode tests.
+
+template <typename Type>
+class TestDeltaByteArrayEncoding : public TestEncodingBase<Type> {
+ public:
+ using c_type = typename Type::c_type;
+ static constexpr int TYPE = Type::type_num;
+
+ void InitData(int nvalues, int repeats, double prefixed_probability) {
+ num_values_ = nvalues * repeats;
+ input_bytes_.resize(num_values_ * sizeof(c_type));
+ output_bytes_.resize(num_values_ * sizeof(c_type));
+ draws_ = reinterpret_cast<c_type*>(input_bytes_.data());
+ decode_buf_ = reinterpret_cast<c_type*>(output_bytes_.data());
+ GeneratePrefixedData<c_type>(nvalues, draws_, &data_buffer_,
prefixed_probability);
+
+ // add some repeated values
+ for (int j = 1; j < repeats; ++j) {
+ for (int i = 0; i < nvalues; ++i) {
+ draws_[nvalues * j + i] = draws_[i];
+ }
+ }
+ }
+
+ void Execute(int nvalues, int repeats, double prefixed_probability) {
+ InitData(nvalues, repeats, prefixed_probability);
+ CheckRoundtrip();
+ }
+
+ void ExecuteSpaced(int nvalues, int repeats, int64_t valid_bits_offset,
+ double null_probability, double prefixed_probability) {
+ InitData(nvalues, repeats, prefixed_probability);
+
+ int64_t size = num_values_ + valid_bits_offset;
+ auto rand = ::arrow::random::RandomArrayGenerator(1923);
+ const auto array = rand.UInt8(size, /*min=*/0, /*max=*/100,
null_probability);
+ const auto valid_bits = array->null_bitmap_data();
+ if (valid_bits) {
+ CheckRoundtripSpaced(valid_bits, valid_bits_offset);
+ }
+ }
+
+ void CheckRoundtrip() override {
Review Comment:
I'll abstract these soon and ping back.
--
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]
