Skip to content

Feat/regexp extract #20985

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

Open
olsemeno wants to merge 2 commits into
base: main
Choose a base branch
from
+462 −0
Open

Feat/regexp extract #20985

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
32c7644
feat: implement regexp_extract scalar function (Spark compatible)
olsemeno Mar 17, 2026
15f7020
Add expr_fn
olsemeno Mar 17, 2026
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
82 changes: 82 additions & 0 deletions datafusion-examples/examples/builtin_functions/regexp.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -340,5 +340,87 @@ pub async fn regexp() -> Result<()> {
&result
);

//
//
// regexp_extract examples
//
//
// regexp_extract format is regexp_extract(str, regexp, idx)
// idx=0 returns the entire matched string, idx=N returns the Nth capture group
// if the regex did not match, or the group did not match, an empty string is returned
//

// extract year from date string (group 1)
let result = ctx
.sql("SELECT regexp_extract('2024-03-16', '(\\d{4})-(\\d{2})-(\\d{2})', 1)")
.await?
.collect()
.await?;

assert_batches_eq!(
&[
"+-----------------------------------------------------------------------------+",
r#"| regexp_extract(Utf8("2024-03-16"),Utf8("(\d{4})-(\d{2})-(\d{2})"),Int64(1)) |"#,
"+-----------------------------------------------------------------------------+",
"| 2024 |",
"+-----------------------------------------------------------------------------+",
],
&result
);

// idx=0 returns the entire matched string
let result = ctx
.sql("SELECT regexp_extract('2024-03-16', '(\\d{4})-(\\d{2})-(\\d{2})', 0)")
.await?
.collect()
.await?;

assert_batches_eq!(
&[
"+-----------------------------------------------------------------------------+",
r#"| regexp_extract(Utf8("2024-03-16"),Utf8("(\d{4})-(\d{2})-(\d{2})"),Int64(0)) |"#,
"+-----------------------------------------------------------------------------+",
"| 2024-03-16 |",
"+-----------------------------------------------------------------------------+",
],
&result
);

// no match returns empty string (not NULL)
let result = ctx
.sql("SELECT regexp_extract('no digits here', '(\\d+)', 1)")
.await?
.collect()
.await?;

assert_batches_eq!(
&[
"+---------------------------------------------------------------+",
r#"| regexp_extract(Utf8("no digits here"),Utf8("(\d+)"),Int64(1)) |"#,
"+---------------------------------------------------------------+",
"| |",
"+---------------------------------------------------------------+",
],
&result
);

// NULL input returns NULL
let result = ctx
.sql("SELECT regexp_extract(NULL, '(\\d+)', 1)")
.await?
.collect()
.await?;

assert_batches_eq!(
&[
"+---------------------------------------------+",
r#"| regexp_extract(NULL,Utf8("(\d+)"),Int64(1)) |"#,
"+---------------------------------------------+",
"| |",
"+---------------------------------------------+",
],
&result
);

Ok(())
}
8 changes: 8 additions & 0 deletions datafusion/functions/src/regex/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,13 +23,15 @@ use std::collections::HashMap;
use std::collections::hash_map::Entry;
use std::sync::Arc;
pub mod regexpcount;
pub mod regexpextract;
pub mod regexpinstr;
pub mod regexplike;
pub mod regexpmatch;
pub mod regexpreplace;

// create UDFs
make_udf_function!(regexpcount::RegexpCountFunc, regexp_count);
make_udf_function!(regexpextract::RegexpExtractFunc, regexp_extract);
make_udf_function!(regexpinstr::RegexpInstrFunc, regexp_instr);
make_udf_function!(regexpmatch::RegexpMatchFunc, regexp_match);
make_udf_function!(regexplike::RegexpLikeFunc, regexp_like);
Expand Down Expand Up @@ -102,6 +104,11 @@ pub mod expr_fn {
super::regexp_like().call(args)
}

/// Extracts the first match of a regular expression capture group from a string.
pub fn regexp_extract(str: Expr, regexp: Expr, idx: Expr) -> Expr {
super::regexp_extract().call(vec![str, regexp, idx])
}

/// Replaces substrings in a string that match.
pub fn regexp_replace(
string: Expr,
Expand All @@ -121,6 +128,7 @@ pub mod expr_fn {
pub fn functions() -> Vec<Arc<datafusion_expr::ScalarUDF>> {
vec![
regexp_count(),
regexp_extract(),
regexp_match(),
regexp_instr(),
regexp_like(),
Expand Down
Loading