Function ConvertCategoricals

python/pyarrow/src/arrow/python/arrow_to_pandas.cc:2516–2554

};

Status ConvertCategoricals(const PandasOptions& options, ChunkedArrayVector* arrays,
                           FieldVector* fields) {
  std::vector<int> columns_to_encode;

  // For Categorical conversions
  auto EncodeColumn = [&](int j) {
    int i = columns_to_encode[j];
    if (options.zero_copy_only) {
      return Status::Invalid("Need to dictionary encode a column, but ",
                             "only zero-copy conversions allowed");
    }
    compute::ExecContext ctx(options.pool);
    ARROW_ASSIGN_OR_RAISE(
        Datum out, DictionaryEncode((*arrays)[i],
                                    compute::DictionaryEncodeOptions::Defaults(), &ctx));
    (*arrays)[i] = out.chunked_array();
    (*fields)[i] = (*fields)[i]->WithType((*arrays)[i]->type());
    return Status::OK();
  };

  if (options.HasCategoricalColumns()) {
    for (int i = 0; i < static_cast<int>(arrays->size()); i++) {
      if ((*arrays)[i]->type()->id() != Type::DICTIONARY &&
          options.IsCategoricalColumn((*fields)[i]->name())) {
        columns_to_encode.push_back(i);
      }
    }
  }
  if (options.strings_to_categorical) {
    for (int i = 0; i < static_cast<int>(arrays->size()); i++) {
      if (is_base_binary_like((*arrays)[i]->type()->id()) ||
          is_binary_view_like((*arrays)[i]->type()->id())) {
        columns_to_encode.push_back(i);
      }
    }
  }
  return OptionalParallelFor(options.use_threads,
                             static_cast<int>(columns_to_encode.size()), EncodeColumn);
}

}  // namespace