lidavidm commented on code in PR #13709:
URL: https://github.com/apache/arrow/pull/13709#discussion_r931528356
##########
python/pyarrow/_dataset.pyx:
##########
@@ -1237,6 +1238,40 @@ cdef class CsvFileFormat(FileFormat):
return f"<CsvFileFormat parse_options={self.parse_options}>"
+# From io.pxi
+def py_buffer(object obj):
+ """
+ Construct an Arrow buffer from a Python bytes-like or buffer-like object
+
+ Parameters
+ ----------
+ obj : object
+ the object from which the buffer should be constructed.
+ """
+ cdef shared_ptr[CBuffer] buf
+ buf = GetResultValue(PyBuffer.FromPyObject(obj))
+ return pyarrow_wrap_buffer(buf)
+
+
+# From io.pxi
+cdef void _cb_transform(transform_func, const shared_ptr[CBuffer]& src,
+ shared_ptr[CBuffer]* dest) except *:
+ py_dest = transform_func(pyarrow_wrap_buffer(src))
+ dest[0] = pyarrow_unwrap_buffer(py_buffer(py_dest))
+
+
+# from io.pxi
+class Transcoder:
Review Comment:
We mostly discussed this in the JIRA - you'd have to pull in a library like
icu if you want to do it on the C++ side, and also Python (at least) has
'special' encodings like 'unicodereplace' that users may or may not expect to
be able to use
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
