Skip to content

Optimize performance of substr_index and add tests #9973

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

Merged
merged 9 commits into from
Apr 8, 2024
Merged

Optimize performance of substr_index and add tests #9973

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
ef36090
Optimize performance of substr_index
kevinmingtarja Apr 6, 2024
94b8de2
Add tests for substr_index
kevinmingtarja Apr 6, 2024
cd4cbbc
cargo clippy
kevinmingtarja Apr 6, 2024
abbbea2
Use StringBuilder to avoid String creation in the iterator
kevinmingtarja Apr 6, 2024
89261d7
Add more tests
kevinmingtarja Apr 6, 2024
06e8ace
cargo clippy
kevinmingtarja Apr 6, 2024
14e91bf
Append null if builder is empty
kevinmingtarja Apr 6, 2024
8bdfb36
Fix handling of non matching rows
kevinmingtarja Apr 7, 2024
421f6d9
Refactor test
kevinmingtarja Apr 7, 2024
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
153 changes: 133 additions & 20 deletions datafusion/functions/src/unicode/substrindex.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
use std::any::Any;
use std::sync::Arc;

use arrow::array::{ArrayRef, GenericStringArray, OffsetSizeTrait};
use arrow::array::{ArrayRef, OffsetSizeTrait, StringBuilder};
use arrow::datatypes::DataType;

use datafusion_common::cast::{as_generic_string_array, as_int64_array};
Expand Down Expand Up @@ -101,38 +101,151 @@ pub fn substr_index<T: OffsetSizeTrait>(args: &[ArrayRef]) -> Result<ArrayRef> {
let delimiter_array = as_generic_string_array::<T>(&args[1])?;
let count_array = as_int64_array(&args[2])?;

let result = string_array
let mut builder = StringBuilder::new();
string_array
.iter()
.zip(delimiter_array.iter())
.zip(count_array.iter())
.map(|((string, delimiter), n)| match (string, delimiter, n) {
.for_each(|((string, delimiter), n)| match (string, delimiter, n) {
(Some(string), Some(delimiter), Some(n)) => {
// In MySQL, these cases will return an empty string.
if n == 0 || string.is_empty() || delimiter.is_empty() {
return Some(String::new());
builder.append_value("");
return;
}

let splitted: Box<dyn Iterator<Item = _>> = if n > 0 {
Box::new(string.split(delimiter))
let occurrences = usize::try_from(n.unsigned_abs()).unwrap_or(usize::MAX);
let length = if n > 0 {
let splitted = string.split(delimiter);
splitted
.take(occurrences)
.map(|s| s.len() + delimiter.len())
.sum::<usize>()
- delimiter.len()
} else {
Box::new(string.rsplit(delimiter))
let splitted = string.rsplit(delimiter);
splitted
.take(occurrences)
.map(|s| s.len() + delimiter.len())
.sum::<usize>()
- delimiter.len()
};
let occurrences = usize::try_from(n.unsigned_abs()).unwrap_or(usize::MAX);
// The length of the substring covered by substr_index.
let length = splitted
.take(occurrences) // at least 1 element, since n != 0
.map(|s| s.len() + delimiter.len())
.sum::<usize>()
- delimiter.len();
if n > 0 {
Some(string[..length].to_owned())
match string.get(..length) {
Some(substring) => builder.append_value(substring),
None => builder.append_null(),
}
} else {
Some(string[string.len() - length..].to_owned())
match string.get(string.len().saturating_sub(length)..) {
Some(substring) => builder.append_value(substring),
None => builder.append_null(),
}
}
}
_ => None,
})
.collect::<GenericStringArray<T>>();
_ => builder.append_null(),
});

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

Ok(Arc::new(result) as ArrayRef)
#[cfg(test)]
mod tests {
use arrow::array::{Array, StringArray};
use arrow::datatypes::DataType::Utf8;

use datafusion_common::{Result, ScalarValue};
use datafusion_expr::{ColumnarValue, ScalarUDFImpl};

use crate::unicode::substrindex::SubstrIndexFunc;
use crate::utils::test::test_function;

#[test]
fn test_functions() -> Result<()> {
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("www.apache.org")),
ColumnarValue::Scalar(ScalarValue::from(".")),
ColumnarValue::Scalar(ScalarValue::from(1i64)),
],
Ok(Some("www")),
&str,
Utf8,
StringArray
);
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("www.apache.org")),
ColumnarValue::Scalar(ScalarValue::from(".")),
ColumnarValue::Scalar(ScalarValue::from(2i64)),
],
Ok(Some("www.apache")),
&str,
Utf8,
StringArray
);
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("www.apache.org")),
ColumnarValue::Scalar(ScalarValue::from(".")),
ColumnarValue::Scalar(ScalarValue::from(-2i64)),
],
Ok(Some("apache.org")),
&str,
Utf8,
StringArray
);
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("www.apache.org")),
ColumnarValue::Scalar(ScalarValue::from(".")),
ColumnarValue::Scalar(ScalarValue::from(-1i64)),
],
Ok(Some("org")),
&str,
Utf8,
StringArray
);
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("www.apache.org")),
ColumnarValue::Scalar(ScalarValue::from(".")),
ColumnarValue::Scalar(ScalarValue::from(0i64)),
],
Ok(Some("")),
&str,
Utf8,
StringArray
);
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("")),
ColumnarValue::Scalar(ScalarValue::from(".")),
ColumnarValue::Scalar(ScalarValue::from(1i64)),
],
Ok(Some("")),
&str,
Utf8,
StringArray
);
test_function!(
SubstrIndexFunc::new(),
&[
ColumnarValue::Scalar(ScalarValue::from("www.apache.org")),
ColumnarValue::Scalar(ScalarValue::from("")),
ColumnarValue::Scalar(ScalarValue::from(1i64)),
],
Ok(Some("")),
&str,
Utf8,
StringArray
);

Ok(())
}
}
11 changes: 10 additions & 1 deletion datafusion/sqllogictest/test_files/functions.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -940,7 +940,8 @@ SELECT str, n, substring_index(str, '.', n) AS c FROM
(VALUES
ROW('arrow.apache.org'),
ROW('.'),
ROW('...')
ROW('...'),
ROW(NULL)
) AS strings(str),
(VALUES
ROW(1),
Expand All @@ -954,6 +955,14 @@ SELECT str, n, substring_index(str, '.', n) AS c FROM
) AS occurrences(n)
ORDER BY str DESC, n;
----
NULL -100 NULL
NULL -3 NULL
NULL -2 NULL
NULL -1 NULL
NULL 1 NULL
NULL 2 NULL
NULL 3 NULL
NULL 100 NULL
arrow.apache.org -100 arrow.apache.org
arrow.apache.org -3 arrow.apache.org
arrow.apache.org -2 apache.org
Expand Down