paleolimbot commented on code in PR #464:
URL: https://github.com/apache/arrow-nanoarrow/pull/464#discussion_r1603605009
##########
python/src/nanoarrow/visitor.py:
##########
@@ -15,68 +15,186 @@
# specific language governing permissions and limitations
# under the License.
-from typing import Any, List, Sequence, Tuple, Union
+from typing import Any, Callable, List, Sequence, Tuple, Union
-from nanoarrow._lib import CArrayView
+from nanoarrow._lib import CArrayView, CArrowType, CBuffer, CBufferBuilder
from nanoarrow.c_array_stream import c_array_stream
+from nanoarrow.c_schema import c_schema_view
from nanoarrow.iterator import ArrayViewBaseIterator, PyIterator
from nanoarrow.schema import Type
-def to_pylist(obj, schema=None) -> List:
- """Convert ``obj`` to a ``list()` of Python objects
+class ArrayViewVisitable:
+ """Mixin class providing conversion methods based on visitors
+
+ Can be used with classes that implement ``__arrow_c_stream__()``
+ or ``__arrow_c_array__()``.
+ """
+
+ def to_pylist(self) -> List:
+ """Convert to a ``list()`` of Python objects
+
+ Computes an identical value to ``list(iter_py())`` but can be much
+ faster.
+
+ Examples
+ --------
+
+ >>> import nanoarrow as na
+ >>> from nanoarrow import visitor
+ >>> array = na.Array([1, 2, 3], na.int32())
+ >>> array.to_pylist()
+ [1, 2, 3]
+ """
+ return ListBuilder.visit(self)
+
+ def to_column_list(self, handle_nulls=None) -> Tuple[List[str],
List[Sequence]]:
+ """Convert to a ``list()` of contiguous sequences
+
+ Converts a stream of struct arrays into its column-wise representation
+ according to :meth:`to_column`.
+
+ Paramters
+ ---------
+ handle_nulls : callable
+ A function returning a sequence based on a validity bytemap and a
+ contiguous buffer of values (e.g., the callable returned by
+ :meth:`nulls_as_sentinel`).
+
+ Examples
+ --------
+
+ >>> import nanoarrow as na
+ >>> import pyarrow as pa
+ >>> batch = pa.record_batch({"col1": [1, 2, 3], "col2": ["a", "b",
"c"]})
+ >>> names, columns = na.Array(batch).to_column_list()
+ >>> names
+ ['col1', 'col2']
+ >>> columns
+ [nanoarrow.c_lib.CBuffer(int64[24 b] 1 2 3), ['a', 'b', 'c']]
+ """
+ return ColumnsBuilder.visit(self, handle_nulls=handle_nulls)
+
+ def to_column(self, handle_nulls=None) -> Sequence:
+ """Convert to a contiguous sequence
+
+ Converts a stream of arrays into a columnar representation
+ such that each column is either a contiguous buffer or a ``list()``.
+ Integer, float, and interval arrays are currently converted to their
+ contiguous buffer representation; other types are returned as a list
+ of Python objects. The sequences returned by :meth:`to_column` are
+ designed to work as input to ``pandas.Series`` and/or
``numpy.array()``.
+
+ Parameters
+ ---------
+ obj : array stream-like
+ An array-like or array stream-like object as sanitized by
+ :func:`c_array_stream`.
+ schema : schema-like, optional
+ An optional schema, passed to :func:`c_array_stream`.
+ handle_nulls : callable
Review Comment:
Yes, and only for explicitly nullable fields. Maybe there should be a
`handle_valid` and `handle_nulls`? Or maybe just a `handle_result()`?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
