Skip to content

fix: trim before parsing numbers #9537

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
aryan-212 wants to merge 1 commit into
base: main
Choose a base branch
from
+32 −3
Open

fix: trim before parsing numbers #9537

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
35 changes: 32 additions & 3 deletions arrow-cast/src/parse.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -445,28 +445,29 @@ pub trait Parser: ArrowPrimitiveType {

impl Parser for Float16Type {
fn parse(string: &str) -> Option<f16> {
lexical_core::parse(string.as_bytes())
lexical_core::parse(string.trim().as_bytes())
Copy link
Contributor

@alamb alamb Mar 17, 2026

Choose a reason for hiding this comment

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

I wonder if there will be any performance implications 🤔

.ok()
.map(f16::from_f32)
}
}

impl Parser for Float32Type {
fn parse(string: &str) -> Option<f32> {
lexical_core::parse(string.as_bytes()).ok()
lexical_core::parse(string.trim().as_bytes()).ok()
}
}

impl Parser for Float64Type {
fn parse(string: &str) -> Option<f64> {
lexical_core::parse(string.as_bytes()).ok()
lexical_core::parse(string.trim().as_bytes()).ok()
}
}

macro_rules! parser_primitive {
($t:ty) => {
impl Parser for $t {
fn parse(string: &str) -> Option<Self::Native> {
let string = string.trim();
if !string.as_bytes().last().is_some_and(|x| x.is_ascii_digit()) {
return None;
}
Expand Down Expand Up @@ -2803,6 +2804,34 @@ mod tests {
assert_eq!(Date32Type::parse(""), None);
}

#[test]
fn test_parse_trimmed_whitespace() {
// Float types
assert_eq!(Float16Type::parse(" 1.5 "), Some(f16::from_f32(1.5)));
Copy link
Contributor

@alamb alamb Mar 17, 2026

Choose a reason for hiding this comment

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

Cn you please add some tests with only leading whitespace and some tests with only trailing whitespace?

assert_eq!(Float32Type::parse(" 1.5 "), Some(1.5_f32));
assert_eq!(Float64Type::parse(" 1.5 "), Some(1.5_f64));
assert_eq!(Float32Type::parse("\t2.0\n"), Some(2.0_f32));
assert_eq!(Float64Type::parse("\t2.0\n"), Some(2.0_f64));

// Integer types
assert_eq!(Int8Type::parse(" 42 "), Some(42_i8));
assert_eq!(Int16Type::parse(" 42 "), Some(42_i16));
assert_eq!(Int32Type::parse(" 42 "), Some(42_i32));
assert_eq!(Int64Type::parse(" 42 "), Some(42_i64));
assert_eq!(UInt8Type::parse(" 42 "), Some(42_u8));
assert_eq!(UInt16Type::parse(" 42 "), Some(42_u16));
assert_eq!(UInt32Type::parse(" 42 "), Some(42_u32));
assert_eq!(UInt64Type::parse(" 42 "), Some(42_u64));

// Negative integers with whitespace
assert_eq!(Int32Type::parse(" -1 "), Some(-1_i32));
assert_eq!(Int64Type::parse("\t-100\n"), Some(-100_i64));

// Whitespace-only strings should return None
assert_eq!(Int32Type::parse(" "), None);
assert_eq!(Float32Type::parse(" "), None);
}

#[test]
fn test_parse_interval_month_day_nano_config() {
let interval = parse_interval_month_day_nano_config(
Expand Down
Loading