mapleFU commented on code in PR #35758:
URL: https://github.com/apache/arrow/pull/35758#discussion_r1211698378
##########
cpp/src/parquet/metadata.cc:
##########
@@ -1462,40 +1462,42 @@ 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;
+ auto add_encoding = [&thrift_encodings](format::Encoding::type value) {
+ auto it = std::find(thrift_encodings.begin(), thrift_encodings.end(),
value);
+ if (it == thrift_encodings.end()) {
+ thrift_encodings.push_back(value);
+ }
+ };
+ // 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);
+ // Dictionary Encoding would be PLAIN_DICTIONARY in v1 and
+ // PLAIN in v2.
+ 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);
+ add_encoding(dict_encoding);
}
- } else { // Dictionary not enabled
-
thrift_encodings.push_back(ToThrift(properties_->encoding(column_->path())));
}
+ // Force add encoding for RL/DL.
+ // TODO(mwish): BIT_PACKED encoding is supported, but it will not be
+ // added here. And when RL/DL is empty, it will not be added.
Review Comment:
Thats a good question:
```
void LevelEncoder::Init(Encoding::type encoding, int16_t max_level,
int num_buffered_values, uint8_t* data, int
data_size) {
bit_width_ = bit_util::Log2(max_level + 1);
encoding_ = encoding;
switch (encoding) {
case Encoding::RLE: {
rle_encoder_ = std::make_unique<RleEncoder>(data, data_size,
bit_width_);
break;
}
case Encoding::BIT_PACKED: {
int num_bytes =
static_cast<int>(bit_util::BytesForBits(num_buffered_values *
bit_width_));
bit_packed_encoder_ = std::make_unique<BitWriter>(data, num_bytes);
break;
}
default:
throw ParquetException("Unknown encoding type for levels.");
}
}
```
I guess we have `LevelEncoder` that can use `BIT_PACKED`. But actually it's
never used in our code now except for testing
--
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]
