commit	9935713a4a853e8cdcd32ec42b983df04093ae23	[log] [tgz]
author	Max Conradt <43765720+mhconradt@users.noreply.github.com>	Wed Apr 03 05:41:15 2024 -0700
committer	GitHub <noreply@github.com>	Wed Apr 03 09:41:15 2024 -0300
tree	837542f6bc8b12ba98b3fa9aed74606aaa61ca26
parent	a9ef7459dec2da8a28b4e00fd9cec5b825905432 [diff]

tree: 837542f6bc8b12ba98b3fa9aed74606aaa61ca26

README.md

nanoarrow

The nanoarrow library is a set of helper functions to interpret and generate Arrow C Data Interface and Arrow C Stream Interface structures. The library is in active early development and users should update regularly from the main branch of this repository.

Whereas the current suite of Arrow implementations provide the basis for a comprehensive data analysis toolkit, this library is intended to support clients that wish to produce or interpret Arrow C Data and/or Arrow C Stream structures where linking to a higher level Arrow binding is difficult or impossible.

Using the C library

The nanoarrow C library is intended to be copied and vendored. This can be done using CMake or by using the bundled nanoarrow.h/nanoarrow.c distribution available in the dist/ directory in this repository. Examples of both can be found in the examples/ directory in this repository.

A simple producer example:

#include "nanoarrow.h"

int make_simple_array(struct ArrowArray* array_out, struct ArrowSchema* schema_out) {
  struct ArrowError error;
  array_out->release = NULL;
  schema_out->release = NULL;

  NANOARROW_RETURN_NOT_OK(ArrowArrayInitFromType(array_out, NANOARROW_TYPE_INT32));

  NANOARROW_RETURN_NOT_OK(ArrowArrayStartAppending(array_out));
  NANOARROW_RETURN_NOT_OK(ArrowArrayAppendInt(array_out, 1));
  NANOARROW_RETURN_NOT_OK(ArrowArrayAppendInt(array_out, 2));
  NANOARROW_RETURN_NOT_OK(ArrowArrayAppendInt(array_out, 3));
  NANOARROW_RETURN_NOT_OK(ArrowArrayFinishBuildingDefault(array_out, &error));

  NANOARROW_RETURN_NOT_OK(ArrowSchemaInitFromType(schema_out, NANOARROW_TYPE_INT32));

  return NANOARROW_OK;
}

A simple consumer example:

#include <stdio.h>

#include "nanoarrow.h"

int print_simple_array(struct ArrowArray* array, struct ArrowSchema* schema) {
  struct ArrowError error;
  struct ArrowArrayView array_view;
  NANOARROW_RETURN_NOT_OK(ArrowArrayViewInitFromSchema(&array_view, schema, &error));

  if (array_view.storage_type != NANOARROW_TYPE_INT32) {
    printf("Array has storage that is not int32\n");
  }

  int result = ArrowArrayViewSetArray(&array_view, array, &error);
  if (result != NANOARROW_OK) {
    ArrowArrayViewReset(&array_view);
    return result;
  }

  for (int64_t i = 0; i < array->length; i++) {
    printf("%d\n", (int)ArrowArrayViewGetIntUnsafe(&array_view, i));
  }

  ArrowArrayViewReset(&array_view);
  return NANOARROW_OK;
}