This is an automated email from the ASF dual-hosted git repository.
agrove pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-comet.git
The following commit(s) were added to refs/heads/main by this push:
new fa95f1b2 chore: Remove unsafe use of from_raw_parts in Parquet decoder
(#549)
fa95f1b2 is described below
commit fa95f1b253bf339e214b0ce642c68fb7007b5dc0
Author: Andy Grove <[email protected]>
AuthorDate: Tue Jun 11 07:17:04 2024 -0600
chore: Remove unsafe use of from_raw_parts in Parquet decoder (#549)
* refactor make_int_variant_impl to remove unsafe use of from_raw_parts
* fix
* refactor
* smaller change
* remove commented out code
* remove in_ptr
* simplify
---
core/src/parquet/read/values.rs | 36 ++++--------------------------------
1 file changed, 4 insertions(+), 32 deletions(-)
diff --git a/core/src/parquet/read/values.rs b/core/src/parquet/read/values.rs
index 9d9bbb3c..c2b1b6e6 100644
--- a/core/src/parquet/read/values.rs
+++ b/core/src/parquet/read/values.rs
@@ -443,49 +443,21 @@ macro_rules! make_int_variant_impl {
($ty: ident, $native_ty: ty, $type_size: expr) => {
impl PlainDecoding for $ty {
fn decode(src: &mut PlainDecoderInner, dst: &mut
ParquetMutableVector, num: usize) {
- let num_bytes = 4 * num; // Parquet stores Int8/Int16 using 4
bytes
-
let src_data = &src.data;
- let mut src_offset = src.offset;
let dst_slice = dst.value_buffer.as_slice_mut();
let mut dst_offset = dst.num_values * $type_size;
-
- let mut i = 0;
- let mut in_ptr = &src_data[src_offset..] as *const [u8] as
*const u8 as *const u32;
-
- while num - i >= 32 {
- unsafe {
- let in_slice = std::slice::from_raw_parts(in_ptr, 32);
-
- for n in 0..32 {
- copy_nonoverlapping(
- in_slice[n..].as_ptr() as *const $native_ty,
- &mut dst_slice[dst_offset] as *mut u8 as *mut
$native_ty,
- 1,
- );
- i += 1;
- dst_offset += $type_size;
- }
- in_ptr = in_ptr.offset(32);
- }
- }
-
- src_offset += i * 4;
-
- (0..(num - i)).for_each(|_| {
+ for _ in 0..num {
unsafe {
copy_nonoverlapping(
- &src_data[src_offset..] as *const [u8] as *const u8
+ &src_data[src.offset..] as *const [u8] as *const u8
as *const $native_ty,
&mut dst_slice[dst_offset] as *mut u8 as *mut
$native_ty,
1,
);
}
- src_offset += 4;
+ src.offset += 4; // Parquet stores Int8/Int16 using 4 bytes
dst_offset += $type_size;
- });
-
- src.offset += num_bytes;
+ }
}
fn skip(src: &mut PlainDecoderInner, num: usize) {
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
