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

Implement native support StringView for Ends With #11924

Merged
merged 1 commit into from
Aug 12, 2024
Merged

Implement native support StringView for Ends With #11924

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
33 changes: 15 additions & 18 deletions datafusion/functions/src/string/ends_with.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,12 +18,10 @@
use std::any::Any;
use std::sync::Arc;

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

use datafusion_common::cast::as_generic_string_array;
use datafusion_common::{exec_err, Result};
use datafusion_common::{internal_err, Result};
use datafusion_expr::TypeSignature::*;
use datafusion_expr::{ColumnarValue, Volatility};
use datafusion_expr::{ScalarUDFImpl, Signature};
Expand All @@ -43,14 +41,15 @@ impl Default for EndsWithFunc {

impl EndsWithFunc {
pub fn new() -> Self {
use DataType::*;
Self {
signature: Signature::one_of(
vec![
Exact(vec![Utf8, Utf8]),
Exact(vec![Utf8, LargeUtf8]),
Exact(vec![LargeUtf8, Utf8]),
Exact(vec![LargeUtf8, LargeUtf8]),
// Planner attempts coercion to the target type starting with the most preferred candidate.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️ for the comments

// For example, given input `(Utf8View, Utf8)`, it first tries coercing to `(Utf8View, Utf8View)`.
// If that fails, it proceeds to `(Utf8, Utf8)`.
Exact(vec![DataType::Utf8View, DataType::Utf8View]),
Exact(vec![DataType::Utf8, DataType::Utf8]),
Exact(vec![DataType::LargeUtf8, DataType::LargeUtf8]),
],
Volatility::Immutable,
),
Expand All @@ -72,27 +71,25 @@ impl ScalarUDFImpl for EndsWithFunc {
}

fn return_type(&self, _arg_types: &[DataType]) -> Result<DataType> {
Ok(Boolean)
Ok(DataType::Boolean)
}

fn invoke(&self, args: &[ColumnarValue]) -> Result<ColumnarValue> {
match args[0].data_type() {
DataType::Utf8 => make_scalar_function(ends_with::<i32>, vec![])(args),
DataType::LargeUtf8 => make_scalar_function(ends_with::<i64>, vec![])(args),
DataType::Utf8View | DataType::Utf8 | DataType::LargeUtf8 => {
make_scalar_function(ends_with, vec![])(args)
}
other => {
exec_err!("Unsupported data type {other:?} for function ends_with")
internal_err!("Unsupported data type {other:?} for function ends_with. Expected Utf8, LargeUtf8 or Utf8View")?
}
}
}
}

/// Returns true if string ends with suffix.
/// ends_with('alphabet', 'abet') = 't'
pub fn ends_with<T: OffsetSizeTrait>(args: &[ArrayRef]) -> Result<ArrayRef> {
let left = as_generic_string_array::<T>(&args[0])?;
let right = as_generic_string_array::<T>(&args[1])?;

let result = arrow::compute::kernels::comparison::ends_with(left, right)?;
pub fn ends_with(args: &[ArrayRef]) -> Result<ArrayRef> {
let result = arrow::compute::kernels::comparison::ends_with(&args[0], &args[1])?;

Ok(Arc::new(result) as ArrayRef)
}
Expand Down
6 changes: 2 additions & 4 deletions datafusion/sqllogictest/test_files/string_view.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -574,17 +574,15 @@ logical_plan
03)----TableScan: test projection=[column1_utf8view, column2_utf8view]

## Ensure no casts for ENDS_WITH
## TODO https://github.com/apache/datafusion/issues/11852
query TT
EXPLAIN SELECT
ENDS_WITH(column1_utf8view, 'foo') as c1,
ENDS_WITH(column2_utf8view, column2_utf8view) as c2
FROM test;
----
logical_plan
01)Projection: ends_with(CAST(test.column1_utf8view AS Utf8), Utf8("foo")) AS c1, ends_with(__common_expr_1, __common_expr_1) AS c2
02)--Projection: CAST(test.column2_utf8view AS Utf8) AS __common_expr_1, test.column1_utf8view
03)----TableScan: test projection=[column1_utf8view, column2_utf8view]
01)Projection: ends_with(test.column1_utf8view, Utf8View("foo")) AS c1, ends_with(test.column2_utf8view, test.column2_utf8view) AS c2
02)--TableScan: test projection=[column1_utf8view, column2_utf8view]


## Ensure no casts for INITCAP
Expand Down