Apache DataFusion SQL Query Engine
chore: use new `OffsetBuffer::subtract` helper (#23424)
Raz Luvaton13a6e3003f6f
diff --git a/datafusion/common/src/utils/mod.rs b/datafusion/common/src/utils/mod.rsindex f71cf23d53..94bbb91a7f 100644--- a/datafusion/common/src/utils/mod.rs+++ b/datafusion/common/src/utils/mod.rs@@ -1236,16 +1236,7 @@ pub fn adjust_offsets_for_slice<O: OffsetSizeTrait>() -> OffsetBuffer<O> {let offsets = list.offsets();- if let (Some(first), Some(last)) = (offsets.first(), offsets.last())- && (!first.is_zero() || last.as_usize() != list.values().len())- {- let offsets = offsets.iter().map(|offset| *offset - *first).collect();-- //todo: use unsafe Offset::new_unchecked?- return OffsetBuffer::new(offsets);- }-- offsets.clone()+ offsets.clone().subtract(offsets[0])}/// For lists and large lists, truncates the sublist of null valuesdiff --git a/datafusion/functions-nested/src/sort.rs b/datafusion/functions-nested/src/sort.rsindex 0a34cce6b9..ca9267bb88 100644--- a/datafusion/functions-nested/src/sort.rs+++ b/datafusion/functions-nested/src/sort.rs@@ -471,12 +471,7 @@ fn take_by_indices<OffsetSize: OffsetSizeTrait>(fn rebase_offsets<OffsetSize: OffsetSizeTrait>(offsets: &OffsetBuffer<OffsetSize>,) -> OffsetBuffer<OffsetSize> {- if offsets[0].as_usize() == 0 {- offsets.clone()- } else {- let rebased: Vec<OffsetSize> = offsets.iter().map(|o| *o - offsets[0]).collect();- OffsetBuffer::new(rebased.into())- }+ offsets.clone().subtract(offsets[0])}fn order_desc(modifier: &str) -> Result<bool> {diff --git a/datafusion/functions/src/string/common.rs b/datafusion/functions/src/string/common.rsindex b51b92e9df..7a5d2573ec 100644--- a/datafusion/functions/src/string/common.rs+++ b/datafusion/functions/src/string/common.rs@@ -27,7 +27,7 @@ use arrow::array::{Array, ArrayRef, AsArray, GenericStringArray, NullBufferBuilder, OffsetSizeTrait,StringViewArray, new_null_array,};-use arrow::buffer::{Buffer, OffsetBuffer, ScalarBuffer};+use arrow::buffer::{Buffer, ScalarBuffer};use arrow::datatypes::DataType;use datafusion_common::Result;use datafusion_common::cast::{as_generic_string_array, as_string_view_array};@@ -636,15 +636,10 @@ fn case_conversion_ascii_array<O: OffsetSizeTrait>(let values = Buffer::from_vec(converted);// Shift offsets from `start`-based to 0-based so they index into `values`.- let offsets = if start == 0 {- string_array.offsets().clone()- } else {- let s = O::usize_as(start);- let rebased: Vec<O> = value_offsets.iter().map(|&o| o - s).collect();- // SAFETY: subtracting a constant from monotonic offsets preserves- // monotonicity, and `start` is the minimum offset, so no underflow.- unsafe { OffsetBuffer::new_unchecked(ScalarBuffer::from(rebased)) }- };+ let offsets = string_array+ .offsets()+ .clone()+ .subtract(string_array.offsets()[0]);let nulls = string_array.nulls().cloned();// SAFETY: offsets are monotonic and in-bounds for `values`; nullsdiff --git a/datafusion/functions/src/unicode/initcap.rs b/datafusion/functions/src/unicode/initcap.rsindex 9192f23844..8981d59aec 100644--- a/datafusion/functions/src/unicode/initcap.rs+++ b/datafusion/functions/src/unicode/initcap.rs@@ -18,7 +18,7 @@use std::sync::Arc;use arrow::array::{Array, ArrayRef, GenericStringArray, OffsetSizeTrait};-use arrow::buffer::{Buffer, OffsetBuffer};+use arrow::buffer::Buffer;use arrow::datatypes::DataType;use crate::strings::{GenericStringArrayBuilder, StringViewArrayBuilder};@@ -217,17 +217,10 @@ fn initcap_ascii_array<T: OffsetSizeTrait>(}let values = Buffer::from_vec(out);- let out_offsets = if first_offset == 0 {- offsets.clone()- } else {- // For sliced arrays, we need to rebase the offsets to reflect that the- // output only contains the bytes in the visible slice.- let rebased_offsets = offsets- .iter()- .map(|offset| T::usize_as(offset.as_usize() - first_offset))- .collect::<Vec<_>>();- OffsetBuffer::<T>::new(rebased_offsets.into())- };++ // Rebase offsets for sliced arrays to reflect that the+ // output only contains the bytes in the visible slice.+ let out_offsets = offsets.clone().subtract(offsets[0]);// SAFETY: ASCII case conversion preserves byte length, so the original// string boundaries are preserved. `out_offsets` is either identical to