wgtmac commented on code in PR #35825:
URL: https://github.com/apache/arrow/pull/35825#discussion_r1253953070
##########
cpp/src/parquet/arrow/arrow_reader_writer_test.cc:
##########
@@ -1342,6 +1354,23 @@ TEST_F(TestUInt32ParquetIO, Parquet_1_0_Compatibility) {
using TestStringParquetIO = TestParquetIO<::arrow::StringType>;
+#if defined(_WIN64) || defined(__x86_64__)
Review Comment:
Is `#if defined(_WIN64) || defined(__LP64__)` enough?
##########
cpp/src/parquet/encoding.cc:
##########
@@ -1484,6 +1521,41 @@ class DictDecoderImpl : public DecoderImpl, virtual
public DictDecoder<Type> {
// Perform type-specific initiatialization
void SetDict(TypedDecoder<Type>* dictionary) override;
+ template <typename T = Type,
+ typename = std::enable_if_t<std::is_same_v<T, ByteArrayType> ||
+ std::is_same_v<T, LargeByteArrayType>>>
+ void SetByteArrayDict(TypedDecoder<Type>* dictionary) {
+ DecodeDict(dictionary);
+
+ auto dict_values =
reinterpret_cast<ByteArray*>(dictionary_->mutable_data());
+
+ using offset_type = typename EncodingTraits<Type>::ArrowType::offset_type;
+
+ offset_type total_size = 0;
+ for (int i = 0; i < dictionary_length_; ++i) {
+ if (AddWithOverflow(total_size, dict_values[i].len, &total_size)) {
+ throw ParquetException("String/Binary length to large");
Review Comment:
```suggestion
throw ParquetException("String/Binary length too large");
```
--
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]
