wgtmac commented on code in PR #43945:
URL: https://github.com/apache/arrow/pull/43945#discussion_r1744847842
##########
cpp/src/parquet/arrow/reader_internal.cc:
##########
@@ -319,26 +319,59 @@ void ReconstructChunksWithoutNulls(::arrow::ArrayVector*
chunks) {
}
template <typename ArrowType, typename ParquetType>
-Status TransferInt(RecordReader* reader, MemoryPool* pool,
- const std::shared_ptr<Field>& field, Datum* out) {
+Status TransferInt(RecordReader* reader,
+ std::unique_ptr<::parquet::ColumnChunkMetaData> metadata,
+ const ReaderContext* ctx, const std::shared_ptr<Field>&
field,
+ Datum* out) {
using ArrowCType = typename ArrowType::c_type;
using ParquetCType = typename ParquetType::c_type;
int64_t length = reader->values_written();
ARROW_ASSIGN_OR_RAISE(auto data,
- ::arrow::AllocateBuffer(length * sizeof(ArrowCType),
pool));
+ ::arrow::AllocateBuffer(length * sizeof(ArrowCType),
ctx->pool));
auto values = reinterpret_cast<const ParquetCType*>(reader->values());
auto out_ptr = reinterpret_cast<ArrowCType*>(data->mutable_data());
std::copy(values, values + length, out_ptr);
+ int64_t null_count = 0;
+ std::vector<std::shared_ptr<Buffer>> buffers = {nullptr, std::move(data)};
if (field->nullable()) {
- *out = std::make_shared<ArrayType<ArrowType>>(field->type(), length,
std::move(data),
- reader->ReleaseIsValid(),
- reader->null_count());
- } else {
- *out =
- std::make_shared<ArrayType<ArrowType>>(field->type(), length,
std::move(data),
- /*null_bitmap=*/nullptr,
/*null_count=*/0);
+ null_count = reader->null_count();
+ buffers[0] = reader->ReleaseIsValid();
+ }
+ auto array_data =
+ ::arrow::ArrayData::Make(field->type(), length, std::move(buffers),
null_count);
+ auto array_statistics = std::make_shared<::arrow::ArrayStatistics>();
+ array_statistics->null_count = null_count;
+ auto statistics = metadata->statistics().get();
+ if (statistics) {
+ if (statistics->HasDistinctCount()) {
Review Comment:
Do we need a separate function for the stats conversion?
--
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]
