Method WriteTable

cpp/src/parquet/arrow/writer.cc:394–428

  std::shared_ptr<::arrow::Schema> schema() const override { return schema_; }

  Status WriteTable(const Table& table, int64_t chunk_size) override {
    RETURN_NOT_OK(CheckClosed());
    RETURN_NOT_OK(table.Validate());

    if (chunk_size <= 0 && table.num_rows() > 0) {
      return Status::Invalid("chunk size per row_group must be greater than 0");
    } else if (!table.schema()->Equals(*schema_, false)) {
      return Status::Invalid("table schema does not match this writer's. table:'",
                             table.schema()->ToString(), "' this:'", schema_->ToString(),
                             "'");
    } else if (chunk_size > this->properties().max_row_group_length()) {
      chunk_size = this->properties().max_row_group_length();
    }

    auto WriteRowGroup = [&](int64_t offset, int64_t size) {
      RETURN_NOT_OK(NewRowGroup());
      for (int i = 0; i < table.num_columns(); i++) {
        RETURN_NOT_OK(WriteColumnChunk(table.column(i), offset, size));
      }
      return Status::OK();
    };

    if (table.num_rows() == 0) {
      // Append a row group with 0 rows
      RETURN_NOT_OK(
          WriteRowGroup(0, 0).OrElse([&](auto&&) { PARQUET_IGNORE_NOT_OK(Close()); }));
    }

    for (int chunk = 0; chunk * chunk_size < table.num_rows(); chunk++) {
      int64_t offset = chunk * chunk_size;
      RETURN_NOT_OK(WriteRowGroup(offset, std::min(chunk_size, table.num_rows() - offset))
                        .OrElse([&](auto&&) { PARQUET_IGNORE_NOT_OK(Close()); }));
    }
    return Status::OK();
  }

  Status NewBufferedRowGroup() override {
    RETURN_NOT_OK(CheckClosed());