mapleFU commented on code in PR #35825:
URL: https://github.com/apache/arrow/pull/35825#discussion_r1229589409
##########
cpp/src/parquet/encoding.cc:
##########
@@ -1484,6 +1521,39 @@ 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());
+
+ int 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");
+ }
+ }
+ PARQUET_THROW_NOT_OK(byte_array_data_->Resize(total_size,
+ /*shrink_to_fit=*/false));
+ PARQUET_THROW_NOT_OK(
+ byte_array_offsets_->Resize((dictionary_length_ + 1) * sizeof(int32_t),
Review Comment:
Ok I got it. This patch uses `int32_t` as offset, and maximum will not
beyond `numeric_limit<int32_t>::max`. So it's also ok to use `int32_t` as
offset.
--
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]
