Skip to content

Speedup character_length #15931

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 3, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
78 changes: 48 additions & 30 deletions datafusion/functions/src/unicode/character_length.rs
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

use crate::utils::{make_scalar_function, utf8_to_int_type};
use arrow::array::{
Array, ArrayRef, ArrowPrimitiveType, AsArray, OffsetSizeTrait, PrimitiveBuilder,
Array, ArrayRef, ArrowPrimitiveType, AsArray, OffsetSizeTrait, PrimitiveArray,
StringArrayType,
};
use arrow::datatypes::{ArrowNativeType, DataType, Int32Type, Int64Type};
Expand Down Expand Up @@ -131,46 +131,64 @@ where
T::Native: OffsetSizeTrait,
V: StringArrayType<'a>,
{
let mut builder = PrimitiveBuilder::<T>::with_capacity(array.len());

// String characters are variable length encoded in UTF-8, counting the
// number of chars requires expensive decoding, however checking if the
// string is ASCII only is relatively cheap.
// If strings are ASCII only, count bytes instead.
let is_array_ascii_only = array.is_ascii();
if array.null_count() == 0 {
let array = if array.null_count() == 0 {
if is_array_ascii_only {
for i in 0..array.len() {
let value = array.value(i);
builder.append_value(T::Native::usize_as(value.len()));
}
let values: Vec<_> = (0..array.len())
.map(|i| {
let value = array.value(i);
T::Native::usize_as(value.len())
})
.collect();
PrimitiveArray::<T>::new(values.into(), None)
} else {
for i in 0..array.len() {
let value = array.value(i);
builder.append_value(T::Native::usize_as(value.chars().count()));
}
let values: Vec<_> = (0..array.len())
.map(|i| {
let value = array.value(i);
if value.is_ascii() {
T::Native::usize_as(value.len())
} else {
T::Native::usize_as(value.chars().count())
}
})
.collect();
PrimitiveArray::<T>::new(values.into(), None)
}
} else if is_array_ascii_only {
for i in 0..array.len() {
if array.is_null(i) {
builder.append_null();
} else {
let value = array.value(i);
builder.append_value(T::Native::usize_as(value.len()));
}
}
let values: Vec<_> = (0..array.len())
.map(|i| {
if array.is_null(i) {
T::default_value()
} else {
let value = array.value(i);
T::Native::usize_as(value.len())
}
})
.collect();
PrimitiveArray::<T>::new(values.into(), array.nulls().cloned())
} else {
for i in 0..array.len() {
if array.is_null(i) {
builder.append_null();
} else {
let value = array.value(i);
builder.append_value(T::Native::usize_as(value.chars().count()));
}
}
}
let values: Vec<_> = (0..array.len())
.map(|i| {
if array.is_null(i) {
T::default_value()
} else {
let value = array.value(i);
if value.is_ascii() {
T::Native::usize_as(value.len())
} else {
T::Native::usize_as(value.chars().count())
}
}
})
.collect();
PrimitiveArray::<T>::new(values.into(), array.nulls().cloned())
};

Ok(Arc::new(builder.finish()) as ArrayRef)
Ok(Arc::new(array))
}

#[cfg(test)]
Expand Down