Skip to content

Adds is_null function to RowAccessor #9979

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
choubacha wants to merge 3 commits into
base: main
Choose a base branch
from
+91 −7
Open

Adds is_null function to RowAccessor #9979

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
24bda89
Adds is_null function to RowAccessor
choubacha May 15, 2026
e2ce6cc
Corrects implementation to return false when not Null
choubacha May 16, 2026
048aab1
Replaces unchecked index access with checked gets
choubacha May 21, 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
98 changes: 91 additions & 7 deletions parquet/src/record/api.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,8 @@ impl<'a> Iterator for RowColumnIter<'a> {

/// Trait for type-safe convenient access to fields within a Row.
pub trait RowAccessor {
/// Check if the field at the index is null.
fn is_null(&self, i: usize) -> Result<bool>;
/// Try to get a boolean value at the given index.
fn get_bool(&self, i: usize) -> Result<bool>;
/// Try to get a byte value at the given index.
Expand Down Expand Up @@ -210,11 +212,12 @@ pub trait RowFormatter {
macro_rules! row_primitive_accessor {
($METHOD:ident, $VARIANT:ident, $TY:ty) => {
fn $METHOD(&self, i: usize) -> Result<$TY> {
match self.fields[i].1 {
Field::$VARIANT(v) => Ok(v),
match self.fields.get(i) {
Some((_, Field::$VARIANT(v))) => Ok(*v),
None => Err(ParquetError::IndexOutOfBound(i, self.fields.len())),
_ => Err(general_err!(
"Cannot access {} as {}",
self.fields[i].1.get_type_name(),
self.fields[i].1.get_type_name(), // Safe access as None is
stringify!($VARIANT)
)),
}
Expand All @@ -227,11 +230,13 @@ macro_rules! row_primitive_accessor {
macro_rules! row_complex_accessor {
($METHOD:ident, $VARIANT:ident, $TY:ty) => {
fn $METHOD(&self, i: usize) -> Result<&$TY> {
match self.fields[i].1 {
Field::$VARIANT(ref v) => Ok(v),
match self.fields.get(i) {
Some((_, Field::$VARIANT(v))) => Ok(v),
None => Err(ParquetError::IndexOutOfBound(i, self.fields.len())),
_ => Err(general_err!(
"Cannot access {} as {}",
self.fields[i].1.get_type_name(),
self.fields[i].1.get_type_name(), // Safe access as None is
// just checked.
stringify!($VARIANT)
)),
}
Expand All @@ -242,11 +247,23 @@ macro_rules! row_complex_accessor {
impl RowFormatter for Row {
/// Get Display reference for a given field.
fn fmt(&self, i: usize) -> &dyn fmt::Display {
&self.fields[i].1
if let Some((_, v)) = self.fields.get(i) {
v
} else {
&"<IndexOutOfBound>"
Copy link
Copy Markdown
Author

@choubacha choubacha May 21, 2026

Choose a reason for hiding this comment

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

Unsure if this should be something different so if you have another recommendation feel free to weigh in.

Copy link
Copy Markdown
Contributor

@alamb alamb May 21, 2026

Choose a reason for hiding this comment

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

seems fine to me

}
}
}

impl RowAccessor for Row {
fn is_null(&self, i: usize) -> Result<bool> {
match self.fields.get(i) {
Some((_, Field::Null)) => Ok(true),
None => Err(ParquetError::IndexOutOfBound(i, self.len())),
_ => Ok(false),
}
}

row_primitive_accessor!(get_bool, Bool, bool);

row_primitive_accessor!(get_byte, Byte, i8);
Expand Down Expand Up @@ -1651,6 +1668,8 @@ mod tests {
("p".to_string(), Field::Float16(f16::from_f32(9.1))),
]);

assert!(row.is_null(0).unwrap());
assert!(!row.is_null(1).unwrap());
assert!(!row.get_bool(1).unwrap());
assert_eq!(3, row.get_byte(2).unwrap());
assert_eq!(4, row.get_short(3).unwrap());
Expand All @@ -1666,6 +1685,71 @@ mod tests {
assert_eq!(5, row.get_bytes(13).unwrap().len());
assert_eq!(7, row.get_decimal(14).unwrap().precision());
assert!((f16::from_f32(9.1) - row.get_float16(15).unwrap()).abs() < f16::EPSILON);

assert!(matches!(
row.is_null(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_bool(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_byte(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_short(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_int(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_long(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_ubyte(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_ushort(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_uint(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_ulong(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_float(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_double(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_string(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_bytes(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_decimal(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
assert!(matches!(
row.get_float16(16).unwrap_err(),
ParquetError::IndexOutOfBound(16, 16),
));
}

#[test]
Expand Down
Loading