wgtmac commented on code in PR #50157:
URL: https://github.com/apache/arrow/pull/50157#discussion_r3417928990
##########
cpp/src/parquet/column_reader.cc:
##########
@@ -591,14 +595,25 @@ std::shared_ptr<Buffer>
SerializedPageReader::DecompressIfNeeded(
} // namespace
+std::unique_ptr<PageReader> PageReader::Open(
+ std::shared_ptr<ArrowInputStream> stream, int64_t total_num_values,
+ Compression::type codec, const ReaderProperties& properties,
+ const ColumnDescriptor& descr, bool always_compressed, const
CryptoContext* ctx) {
+ const auto stats_min_max_field = GetStatisticsMinMaxField(descr);
+ return std::unique_ptr<PageReader>(
+ new SerializedPageReader(std::move(stream), total_num_values, codec,
properties,
+ ctx, always_compressed, stats_min_max_field));
+}
+
std::unique_ptr<PageReader> PageReader::Open(std::shared_ptr<ArrowInputStream>
stream,
int64_t total_num_values,
Compression::type codec,
const ReaderProperties&
properties,
bool always_compressed,
const CryptoContext* ctx) {
return std::unique_ptr<PageReader>(new SerializedPageReader(
- std::move(stream), total_num_values, codec, properties, ctx,
always_compressed));
+ std::move(stream), total_num_values, codec, properties, ctx,
always_compressed,
+ StatisticsMinMaxField::kMinValueMaxValue));
Review Comment:
This might be slightly a breaking change because
`StatisticsMinMaxField::kMinValueMaxValue` only looks for `min_value/max_value`
and does not try `min/max` anymore. But since all production code has been
migrated to the new `PageReeder::Open`, it should be acceptable. @pitrou
--
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]
