mapleFU commented on code in PR #35758:
URL: https://github.com/apache/arrow/pull/35758#discussion_r1205673126
##########
cpp/src/parquet/metadata.cc:
##########
@@ -1462,40 +1462,48 @@ class
ColumnChunkMetaDataBuilder::ColumnChunkMetaDataBuilderImpl {
column_chunk_->meta_data.__set_total_compressed_size(compressed_size);
std::vector<format::Encoding::type> thrift_encodings;
+ std::vector<format::PageEncodingStats> thrift_encoding_stats;
+ // Add dictionary page encoding stats
if (has_dictionary) {
-
thrift_encodings.push_back(ToThrift(properties_->dictionary_index_encoding()));
- if (properties_->version() == ParquetVersion::PARQUET_1_0) {
- thrift_encodings.push_back(ToThrift(Encoding::PLAIN));
- } else {
-
thrift_encodings.push_back(ToThrift(properties_->dictionary_page_encoding()));
+ for (const auto& entry : dict_encoding_stats) {
+ format::PageEncodingStats dict_enc_stat;
+ dict_enc_stat.__set_page_type(format::PageType::DICTIONARY_PAGE);
+ format::Encoding::type dict_encoding = ToThrift(entry.first);
+ dict_enc_stat.__set_encoding(dict_encoding);
+ dict_enc_stat.__set_count(entry.second);
+ thrift_encoding_stats.push_back(dict_enc_stat);
+ auto iter =
+ std::find(thrift_encodings.begin(), thrift_encodings.end(),
dict_encoding);
+ if (iter == thrift_encodings.end()) {
+ thrift_encodings.push_back(dict_encoding);
+ }
}
- } else { // Dictionary not enabled
-
thrift_encodings.push_back(ToThrift(properties_->encoding(column_->path())));
+ // Dictionary Data Page Encoding.
+
thrift_encodings.push_back(ToThrift(properties_->dictionary_page_encoding()));
}
+ // Force add encoding for RL/DL.
Review Comment:
This follows the previous logic. I can adding checks for it now
--
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]
