Rich-T-kid commented on code in PR #10813:
URL: https://github.com/apache/arrow-rs/pull/10813#discussion_r3890072373
##########
arrow-select/src/take.rs:
##########
@@ -456,43 +456,229 @@ fn take_native<T: ArrowNativeType, I:
ArrowPrimitiveType>(
}
}
+/// Read the bit at `src_bit_idx` from `src` and, if it is set, write a `1` to
`dst_bit_idx`
+/// in `dst`. Leaves `dst_bit_idx` unchanged (zero) when the source bit is
unset.
+///
+/// ```text
+/// src = 0b00100000 (bit 5 is set)
+/// copy_bit_if_set(src, 5, dst, 2) → dst bit 2 becomes 1
+/// ```
+///
+/// # Safety
+/// - `src` must be valid for reads up to byte `src_bit_idx / 8`.
+/// - `dst` must be valid for writes up to byte `dst_bit_idx / 8`.
+#[inline(always)]
+unsafe fn copy_bit_if_set(src: *const u8, src_bit_idx: usize, dst: *mut u8,
dst_bit_idx: usize) {
+ unsafe {
+ if bit_util::get_bit_raw(src, src_bit_idx) {
+ bit_util::set_bit_raw(dst, dst_bit_idx);
+ }
+ }
+}
+
+/// Read the bit at `bit_idx` from `src` and return it shifted to `out_pos`,
ready to be
+/// OR'd into an output byte accumulator.
+///
+/// ```text
+/// src = 0b10100000 (bit 5 is set)
+/// pack_bit(src, 5, 2) → 0b00000100 (bit from position 5, placed at
position 2)
+/// ```
+///
+/// # Safety
+/// `src` must be valid for reads up to byte `bit_idx / 8`.
+#[inline(always)]
+unsafe fn pack_bit(src: *const u8, bit_idx: usize, out_pos: usize) -> u8 {
+ let byte = unsafe { *src.add(bit_idx >> 3) }; // byte containing bit
`bit_idx`
+ ((byte >> (bit_idx & 7)) & 1) << out_pos // extract the bit, shift to
output position
+}
+
#[inline(never)]
fn take_bits<I: ArrowPrimitiveType, const CHECKED: bool>(
values: &BooleanBuffer,
indices: &PrimitiveArray<I>,
) -> BooleanBuffer {
let len = indices.len();
+ let src_offset = values.offset();
+ let src_ptr = values.values().as_ptr();
+ let out_bytes = len.div_ceil(8);
+
+ match indices.nulls().filter(|nulls| nulls.null_count() > 0) {
+ Some(index_nulls) => {
+ let mut output = vec![0u8; out_bytes];
+ let out_ptr = output.as_mut_ptr();
+ index_nulls.valid_indices().for_each(|valid_idx| {
+ let src_idx = if CHECKED {
+ indices.value(valid_idx).as_usize()
+ } else {
+ // SAFETY: valid_idx < len (validity bitmap); caller
guarantees index values are in bounds when CHECKED=false
+ unsafe { indices.value_unchecked(valid_idx) }.as_usize()
+ } + src_offset;
+ // SAFETY: src_idx bounded by take's prior bounds check
Review Comment:
the comment is referring to the two branches above
```
let src_idx = if CHECKED {
indices.value(base + bit).as_usize()
} else {
// SAFETY: base + bit < len (loop bound); caller
guarantees index values are in bounds when CHECKED=false
unsafe { indices.value_unchecked(base + bit)
}.as_usize()
} + src_offset;
```
CHECKED=true ; indces.value() will panic before hitting the ` byte |= unsafe
{ pack_bit(src_ptr, src_idx, bit) };` if its out of bounds
CHECKED=FALSE; it is up to the caller to guarantee that the indices are
correct. if not this will be a UB but the caller had to explicitly call this
function with `unsafe{}` so Its their resposnsibility.
##########
arrow-select/src/take.rs:
##########
@@ -456,43 +456,229 @@ fn take_native<T: ArrowNativeType, I:
ArrowPrimitiveType>(
}
}
+/// Read the bit at `src_bit_idx` from `src` and, if it is set, write a `1` to
`dst_bit_idx`
+/// in `dst`. Leaves `dst_bit_idx` unchanged (zero) when the source bit is
unset.
+///
+/// ```text
+/// src = 0b00100000 (bit 5 is set)
+/// copy_bit_if_set(src, 5, dst, 2) → dst bit 2 becomes 1
+/// ```
+///
+/// # Safety
+/// - `src` must be valid for reads up to byte `src_bit_idx / 8`.
+/// - `dst` must be valid for writes up to byte `dst_bit_idx / 8`.
+#[inline(always)]
+unsafe fn copy_bit_if_set(src: *const u8, src_bit_idx: usize, dst: *mut u8,
dst_bit_idx: usize) {
+ unsafe {
+ if bit_util::get_bit_raw(src, src_bit_idx) {
+ bit_util::set_bit_raw(dst, dst_bit_idx);
+ }
+ }
+}
+
+/// Read the bit at `bit_idx` from `src` and return it shifted to `out_pos`,
ready to be
+/// OR'd into an output byte accumulator.
+///
+/// ```text
+/// src = 0b10100000 (bit 5 is set)
+/// pack_bit(src, 5, 2) → 0b00000100 (bit from position 5, placed at
position 2)
+/// ```
+///
+/// # Safety
+/// `src` must be valid for reads up to byte `bit_idx / 8`.
+#[inline(always)]
+unsafe fn pack_bit(src: *const u8, bit_idx: usize, out_pos: usize) -> u8 {
+ let byte = unsafe { *src.add(bit_idx >> 3) }; // byte containing bit
`bit_idx`
+ ((byte >> (bit_idx & 7)) & 1) << out_pos // extract the bit, shift to
output position
+}
+
#[inline(never)]
fn take_bits<I: ArrowPrimitiveType, const CHECKED: bool>(
values: &BooleanBuffer,
indices: &PrimitiveArray<I>,
) -> BooleanBuffer {
let len = indices.len();
+ let src_offset = values.offset();
+ let src_ptr = values.values().as_ptr();
+ let out_bytes = len.div_ceil(8);
+
+ match indices.nulls().filter(|nulls| nulls.null_count() > 0) {
+ Some(index_nulls) => {
+ let mut output = vec![0u8; out_bytes];
+ let out_ptr = output.as_mut_ptr();
+ index_nulls.valid_indices().for_each(|valid_idx| {
+ let src_idx = if CHECKED {
+ indices.value(valid_idx).as_usize()
+ } else {
+ // SAFETY: valid_idx < len (validity bitmap); caller
guarantees index values are in bounds when CHECKED=false
+ unsafe { indices.value_unchecked(valid_idx) }.as_usize()
+ } + src_offset;
+ // SAFETY: src_idx bounded by take's prior bounds check
Review Comment:
will update the comment to be more clear
--
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]
