Method BuildBufferInternal

cpp/src/parquet/decoder.cc:2013–2047

 protected:
  template <bool is_first_run>
  static void BuildBufferInternal(const int32_t* prefix_len_ptr, int i, ByteArray* buffer,
                                  std::string_view* prefix, uint8_t** data_ptr) {
    if (ARROW_PREDICT_FALSE(static_cast<size_t>(prefix_len_ptr[i]) > prefix->length())) {
      throw ParquetException("prefix length too large in DELTA_BYTE_ARRAY");
    }
    // For now, `buffer` points to string suffixes, and the suffix decoder
    // ensures that the suffix data has sufficient lifetime.
    if (prefix_len_ptr[i] == 0) {
      // prefix is empty: buffer[i] already points to the suffix.
      *prefix = std::string_view{buffer[i]};
      return;
    }
    DCHECK_EQ(is_first_run, i == 0);
    if constexpr (!is_first_run) {
      if (buffer[i].len == 0) {
        // suffix is empty: buffer[i] can simply point to the prefix.
        // This is not possible for the first run since the prefix
        // would point to the mutable `last_value_`.
        *prefix = prefix->substr(0, prefix_len_ptr[i]);
        buffer[i] = ByteArray(*prefix);
        return;
      }
    }
    // Both prefix and suffix are non-empty, so we need to decode the string
    // into `data_ptr`.
    // 1. Copy the prefix
    memcpy(*data_ptr, prefix->data(), prefix_len_ptr[i]);
    // 2. Copy the suffix.
    memcpy(*data_ptr + prefix_len_ptr[i], buffer[i].ptr, buffer[i].len);
    // 3. Point buffer[i] to the decoded string.
    buffer[i].ptr = *data_ptr;
    buffer[i].len += prefix_len_ptr[i];
    *data_ptr += buffer[i].len;
    *prefix = std::string_view{buffer[i]};
  }

  int GetInternal(ByteArray* buffer, int max_values) {
    // Decode up to `max_values` strings into an internal buffer