jhorstmann commented on a change in pull request #8262:
URL: https://github.com/apache/arrow/pull/8262#discussion_r501273876
##########
File path: rust/arrow/src/buffer.rs
##########
@@ -371,118 +388,165 @@ where
fn bitwise_bin_op_helper<F>(
left: &Buffer,
- left_offset: usize,
+ left_offset_in_bits: usize,
right: &Buffer,
- right_offset: usize,
- len: usize,
+ right_offset_in_bits: usize,
+ len_in_bits: usize,
op: F,
) -> Buffer
where
- F: Fn(u8, u8) -> u8,
+ F: Fn(u64, u64) -> u64,
{
- let mut result = MutableBuffer::new(len).with_bitset(len, false);
+ // reserve capacity and set length so we can get a typed view of u64 chunks
+ let mut result =
+ MutableBuffer::new(ceil(len_in_bits, 8)).with_bitset(len_in_bits / 64
* 8, false);
- result
- .data_mut()
- .iter_mut()
- .zip(
- left.data()[left_offset..]
- .iter()
- .zip(right.data()[right_offset..].iter()),
- )
+ let left_chunks = left.bit_chunks(left_offset_in_bits, len_in_bits);
+ let right_chunks = right.bit_chunks(right_offset_in_bits, len_in_bits);
+ let result_chunks = result.typed_data_mut::<u64>().iter_mut();
+
+ result_chunks
+ .zip(left_chunks.iter().zip(right_chunks.iter()))
.for_each(|(res, (left, right))| {
- *res = op(*left, *right);
+ *res = op(left, right);
});
+ let remainder_bytes = ceil(left_chunks.remainder_len(), 8);
+ let rem = op(left_chunks.remainder_bits(), right_chunks.remainder_bits());
+ let rem = &rem.to_le_bytes()[0..remainder_bytes];
+ result
+ .write_all(rem)
+ .expect("not enough capacity in buffer");
+
result.freeze()
}
fn bitwise_unary_op_helper<F>(
left: &Buffer,
- left_offset: usize,
- len: usize,
+ offset_in_bits: usize,
+ len_in_bits: usize,
op: F,
) -> Buffer
where
- F: Fn(u8) -> u8,
+ F: Fn(u64) -> u64,
{
- let mut result = MutableBuffer::new(len).with_bitset(len, false);
+ // reserve capacity and set length so we can get a typed view of u64 chunks
+ let mut result =
+ MutableBuffer::new(ceil(len_in_bits, 8)).with_bitset(len_in_bits / 64
* 8, false);
- result
- .data_mut()
- .iter_mut()
- .zip(left.data()[left_offset..].iter())
+ let left_chunks = left.bit_chunks(offset_in_bits, len_in_bits);
+ let result_chunks = result.typed_data_mut::<u64>().iter_mut();
+
+ result_chunks
+ .zip(left_chunks.iter())
.for_each(|(res, left)| {
- *res = op(*left);
+ *res = op(left);
});
+ let remainder_bytes = ceil(left_chunks.remainder_len(), 8);
+ let rem = op(left_chunks.remainder_bits());
+ let rem = &rem.to_le_bytes()[0..remainder_bytes];
Review comment:
@nevi-me Talking about endianness, I'm only about 85% sure that
`to_le_bytes` is correct here instead of `to_ne_bytes`
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
