Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Fix ilike_utf8_scalar kernals #2545

Merged
merged 3 commits into from
Aug 23, 2022
Merged

Fix ilike_utf8_scalar kernals #2545

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dbdaa5d
fix ilike kernals
psvri Aug 21, 2022
11b8e04
minor refactor for perf improvements
psvri Aug 22, 2022
80c8417
Remove wrongly added file
psvri Aug 22, 2022
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
50 changes: 19 additions & 31 deletions arrow/src/compute/kernels/comparison.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -467,29 +467,24 @@ pub fn ilike_utf8_scalar<OffsetSize: OffsetSizeTrait>(

if !right.contains(is_like_pattern) {
// fast path, can use equals
let right_uppercase = right.to_uppercase();
for i in 0..left.len() {
result.append(left.value(i) == right);
result.append(left.value(i).to_uppercase() == right_uppercase);
}
} else if right.ends_with('%')
&& !right.ends_with("\\%")
&& !right[..right.len() - 1].contains(is_like_pattern)
{
// fast path, can use ends_with
// fast path, can use starts_with
let start_str = &right[..right.len() - 1].to_uppercase();
for i in 0..left.len() {
result.append(
left.value(i)
.to_uppercase()
.starts_with(&right[..right.len() - 1].to_uppercase()),
);
result.append(left.value(i).to_uppercase().starts_with(start_str));
}
} else if right.starts_with('%') && !right[1..].contains(is_like_pattern) {
// fast path, can use starts_with
// fast path, can use ends_with
let ends_str = &right[1..].to_uppercase();
for i in 0..left.len() {
result.append(
left.value(i)
.to_uppercase()
.ends_with(&right[1..].to_uppercase()),
);
result.append(left.value(i).to_uppercase().ends_with(ends_str));
}
} else {
let re_pattern = replace_like_wildcards(right)?;
Expand Down Expand Up @@ -550,31 +545,24 @@ pub fn nilike_utf8_scalar<OffsetSize: OffsetSizeTrait>(

if !right.contains(is_like_pattern) {
// fast path, can use equals
let right_uppercase = right.to_uppercase();
for i in 0..left.len() {
result.append(left.value(i) != right);
result.append(left.value(i).to_uppercase() != right_uppercase);
}
} else if right.ends_with('%')
&& !right.ends_with("\\%")
&& !right[..right.len() - 1].contains(is_like_pattern)
{
// fast path, can use ends_with
// fast path, can use starts_with
let start_str = &right[..right.len() - 1].to_uppercase();
for i in 0..left.len() {
result.append(
!left
.value(i)
.to_uppercase()
.starts_with(&right[..right.len() - 1].to_uppercase()),
);
result.append(!left.value(i).to_uppercase().starts_with(start_str));
}
} else if right.starts_with('%') && !right[1..].contains(is_like_pattern) {
// fast path, can use starts_with
// fast path, can use ends_with
let end_str = &right[1..].to_uppercase();
for i in 0..left.len() {
result.append(
!left
.value(i)
.to_uppercase()
.ends_with(&right[1..].to_uppercase()),
);
result.append(!left.value(i).to_uppercase().ends_with(end_str));
}
} else {
let re_pattern = replace_like_wildcards(right)?;
Expand Down Expand Up @@ -4181,7 +4169,7 @@ mod tests {
test_utf8_scalar!(
test_utf8_array_ilike_scalar_equals,
vec!["arrow", "parrow", "arrows", "arr"],
"arrow",
"Arrow",
ilike_utf8_scalar,
vec![true, false, false, false]
);
Expand Down Expand Up @@ -4234,8 +4222,8 @@ mod tests {

test_utf8_scalar!(
test_utf8_array_nilike_scalar_equals,
vec!["arrow", "parrow", "arrows", "arr"],
"arrow",
vec!["arRow", "parrow", "arrows", "arr"],
"Arrow",
nilike_utf8_scalar,
vec![false, true, true, true]
);
Expand Down