library(nanoarrow)

ascii_bytes <- vapply(letters, charToRaw, raw(1), USE.NAMES = FALSE)

random_string_array <- function(n = 1, n_chars = 16) {
  data_buffer <- sample(ascii_bytes, n_chars * n, replace = TRUE)
  offsets_buffer <- as.integer(seq(0, n * n_chars, length.out = n + 1))
  nanoarrow_array_modify(
    nanoarrow_array_init(na_string()),
    list(
      length = n,
      null_count = 0,
      buffers = list(NULL, offsets_buffer, data_buffer)
    )
  )
}

random_string_struct <- function(n_rows = 1024, n_cols = 1, n_chars = 16) {
  col_names <- sprintf("col%03d", seq_len(n_cols))
  col_types <- rep(list(na_string()), n_cols)
  names(col_types) <- col_names
  schema <- na_struct(col_types)
  
  columns <- lapply(
    col_names,
    function(...) random_string_array(n_rows, n_chars = n_chars)
  )
  
  nanoarrow_array_modify(
    nanoarrow_array_init(schema),
    list(
      length = n_rows,
      null_count = 0,
      children = columns
    )
  )  
}

random_string_batches <- function(n_batches = 1, n_rows = 1, n_cols = 1, n_chars = 16) {
  lapply(
    seq_len(n_batches),
    function(...) random_string_struct(n_rows, n_cols, n_chars)
  )
}

batches <- random_string_batches(n_batches = 100, n_cols = 160)
stream <- basic_array_stream(batches)
write_nanoarrow(stream, "many_strings.arrows")