rok commented on code in PR #34668:
URL: https://github.com/apache/arrow/pull/34668#discussion_r1144118212
##########
cpp/src/parquet/encoding.cc:
##########
@@ -2708,7 +2708,14 @@ class DeltaLengthByteArrayDecoder : public DecoderImpl,
void SetData(int num_values, const uint8_t* data, int len) override {
num_values_ = num_values;
- if (len == 0) return;
+ if (len == 0) {
+ if (num_values > 0) {
+ throw ParquetException(
+ "Delta length byte array page was empty, but expected {num_values}
values.");
Review Comment:
Does this print `num_values`? Perhaps we can check the message with
`EXPECT_THROW_THAT`
##########
cpp/src/parquet/encoding_test.cc:
##########
@@ -1759,12 +1832,10 @@ TEST(DeltaLengthByteArrayEncodingAdHoc, ArrowDirectPut)
{
CheckEncode(::arrow::ArrayFromJSON(::arrow::binary(), values), lengths);
CheckEncode(::arrow::ArrayFromJSON(::arrow::large_binary(), values),
lengths);
- const uint8_t data[] = {
- 0x80, 0x01, 0x04, 0x04, 0x0a, 0x00, 0x01, 0x00, 0x00, 0x00, 0x02, 0x00,
- 0x00, 0x00, 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x57, 0x6f, 0x72, 0x6c, 0x64,
- 0x46, 0x6f, 0x6f, 0x62, 0x61, 0x72, 0x41, 0x44, 0x42, 0x43, 0x45, 0x46,
- };
- auto encoded = Buffer::Wrap(data, sizeof(data));
+ auto encoded =
+ ::arrow::ConcatenateBuffers(
+ {DeltaEncode({5, 5, 6, 6}),
std::make_shared<Buffer>("HelloWorldFoobarADBCEF")})
+ .ValueOrDie();
Review Comment:
Much more readable now :D
--
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]
