Method InitializeDataDecoder

cpp/src/parquet/column_reader.cc:854–897

Get a decoder object for this page or create a new decoder if this is the first page with this encoding.

  // Get a decoder object for this page or create a new decoder if this is the
  // first page with this encoding.
  void InitializeDataDecoder(const DataPage& page, int64_t levels_byte_size) {
    const uint8_t* buffer = page.data() + levels_byte_size;
    const int64_t data_size = page.size() - levels_byte_size;

    if (data_size < 0) {
      throw ParquetException("Page smaller than size of encoded levels");
    }

    Encoding::type encoding = page.encoding();
    if (IsDictionaryIndexEncoding(encoding)) {
      // Normalizing the PLAIN_DICTIONARY to RLE_DICTIONARY encoding
      // in decoder.
      encoding = Encoding::RLE_DICTIONARY;
    }

    auto it = decoders_.find(static_cast<int>(encoding));
    if (it != decoders_.end()) {
      ARROW_DCHECK(it->second.get() != nullptr);
      current_decoder_ = it->second.get();
    } else {
      switch (encoding) {
        case Encoding::PLAIN:
        case Encoding::BYTE_STREAM_SPLIT:
        case Encoding::RLE:
        case Encoding::DELTA_BINARY_PACKED:
        case Encoding::DELTA_BYTE_ARRAY:
        case Encoding::DELTA_LENGTH_BYTE_ARRAY: {
          auto decoder = MakeTypedDecoder<DType>(encoding, descr_, pool_);
          current_decoder_ = decoder.get();
          decoders_[static_cast<int>(encoding)] = std::move(decoder);
          break;
        }

        case Encoding::RLE_DICTIONARY:
          throw ParquetException("Dictionary page must be before data page.");

        default:
          throw ParquetException("Unknown encoding type.");
      }
    }
    current_encoding_ = encoding;
    current_decoder_->SetData(static_cast<int>(num_buffered_values_), buffer,
                              static_cast<int>(data_size));
  }

  // Available values in the current data page, value includes repeated values
  // and nulls.