jorisvandenbossche commented on code in PR #14613:
URL: https://github.com/apache/arrow/pull/14613#discussion_r1017658822
##########
python/pyarrow/interchange/column.py:
##########
@@ -0,0 +1,358 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+from __future__ import annotations
+
+from typing import (
+ Any,
+ Dict,
+ Iterable,
+ Optional,
+ Tuple,
+)
+
+import pyarrow as pa
+from pyarrow.interchange.buffer import PyArrowBuffer
+from pyarrow.interchange.dataframe_protocol import (Column, ColumnBuffers,
+ ColumnNullType, DtypeKind,
+ CategoricalDescription)
+
+_PYARROW_KINDS = {
+ pa.int8(): (DtypeKind.INT, "c"),
+ pa.int16(): (DtypeKind.INT, "s"),
+ pa.int32(): (DtypeKind.INT, "i"),
+ pa.int64(): (DtypeKind.INT, "l"),
+ pa.uint8(): (DtypeKind.UINT, "C"),
+ pa.uint16(): (DtypeKind.UINT, "S"),
+ pa.uint32(): (DtypeKind.UINT, "I"),
+ pa.uint64(): (DtypeKind.UINT, "L"),
+ pa.float16(): (DtypeKind.FLOAT, "e"),
+ pa.float32(): (DtypeKind.FLOAT, "f"),
+ pa.float64(): (DtypeKind.FLOAT, "g"),
+ pa.bool_(): (DtypeKind.BOOL, "b"),
+ pa.string(): (DtypeKind.STRING, "u"), # utf-8
+ pa.large_string(): (DtypeKind.STRING, "U"),
+}
+
+
+class Endianness:
+ """Enum indicating the byte-order of a data-type."""
+
+ LITTLE = "<"
+ BIG = ">"
+ NATIVE = "="
+ NA = "|"
+
+
+class NoBufferPresent(Exception):
+ """Exception to signal that there is no requested buffer."""
+
+
+class PyArrowColumn(Column):
+ """
+ A column object, with only the methods and properties required by the
+ interchange protocol defined.
+ A column can contain one or more chunks. Each chunk can contain up to three
+ buffers - a data buffer, a mask buffer (depending on null representation),
+ and an offsets buffer (if variable-size binary; e.g., variable-length
+ strings).
+ Note: this Column object can only be produced by ``__dataframe__``, so
+ doesn't need its own version or ``__column__`` protocol.
+ """
+
+ def __init__(
+ self, column: pa.Array | pa.ChunkedArray, allow_copy: bool = True
+ ) -> None:
+ """
+ Handles PyArrow Arrays and ChunkedArrays.
+ """
+ # Store the column as a private attribute
+ self._col = column
+ self._allow_copy = allow_copy
+
+ def size(self) -> int:
+ """
+ Size of the column, in elements.
+ """
+ if isinstance(self._col, pa.Array):
+ len = self._col.to_numpy(zero_copy_only=False).size
Review Comment:
I think `len(self._col)` should work (in contrast to Table, the Array doesn't have a explicit attribute for it)
--
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-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org