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

Minor: improve performance of ScalarValue::Binary* debug #12323

Merged
merged 6 commits into from
Sep 6, 2024
Merged

Minor: improve performance of ScalarValue::Binary* debug #12323

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d92897d
Minor: improve performance of ScalarValue debug
alamb Sep 4, 2024
3ed5981
reduce allocations
alamb Sep 4, 2024
99a57e7
simplify loop
alamb Sep 5, 2024
3df0e84
Merge remote-tracking branch 'apache/main' into alamb/less_debug_copy
alamb Sep 5, 2024
7017d52
Add test for single list
alamb Sep 5, 2024
a7e3f2a
Add another test for display
alamb Sep 5, 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
80 changes: 69 additions & 11 deletions datafusion/common/src/scalar/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3661,18 +3661,20 @@ fn fmt_list(arr: ArrayRef, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{value_formatter}")
}

/// writes a byte array to formatter. `[1, 2, 3]` ==> `"1,2,3"`
fn fmt_binary(data: &[u8], f: &mut fmt::Formatter) -> fmt::Result {
let mut iter = data.iter();
if let Some(b) = iter.next() {
write!(f, "{b}")?;
}
for b in iter {
write!(f, ",{b}")?;
}
Ok(())
}

impl fmt::Debug for ScalarValue {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
fn fmt_binary(data: &[u8], f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"{}",
data.iter()
.map(|v| format!("{v}"))
.collect::<Vec<_>>()
.join(",")
)
}
match self {
ScalarValue::Decimal128(_, _, _) => write!(f, "Decimal128({self})"),
ScalarValue::Decimal256(_, _, _) => write!(f, "Decimal256({self})"),
Expand Down Expand Up @@ -3722,7 +3724,7 @@ impl fmt::Debug for ScalarValue {
write!(f, "FixedSizeBinary({size}, {self})")
}
ScalarValue::FixedSizeBinary(size, Some(b)) => {
write!(f, "Binary({size}, \"")?;
write!(f, "FixedSizeBinary({size}, \"")?;
Copy link
Contributor Author

Choose a reason for hiding this comment

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

this is a bug (likely copy/paste error) found with the tests

fmt_binary(b.as_slice(), f)?;
write!(f, "\")")
}
Expand Down Expand Up @@ -6667,6 +6669,8 @@ mod tests {
fn test_binary_display() {
let no_binary_value = ScalarValue::Binary(None);
assert_eq!(format!("{no_binary_value}"), "NULL");
let single_binary_value = ScalarValue::Binary(Some(vec![42u8]));
assert_eq!(format!("{single_binary_value}"), "2A");
let small_binary_value = ScalarValue::Binary(Some(vec![1u8, 2, 3]));
assert_eq!(format!("{small_binary_value}"), "010203");
let large_binary_value =
Expand Down Expand Up @@ -6700,6 +6704,60 @@ mod tests {
assert_eq!(format!("{large_binary_value}"), "0102030405060708090A...");
}

#[test]
fn test_binary_debug() {
let no_binary_value = ScalarValue::Binary(None);
assert_eq!(format!("{no_binary_value:?}"), "Binary(NULL)");
let single_binary_value = ScalarValue::Binary(Some(vec![42u8]));
assert_eq!(format!("{single_binary_value:?}"), "Binary(\"42\")");
let small_binary_value = ScalarValue::Binary(Some(vec![1u8, 2, 3]));
assert_eq!(format!("{small_binary_value:?}"), "Binary(\"1,2,3\")");
let large_binary_value =
ScalarValue::Binary(Some(vec![1u8, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]));
assert_eq!(
format!("{large_binary_value:?}"),
"Binary(\"1,2,3,4,5,6,7,8,9,10,11\")"
);

let no_binary_value = ScalarValue::BinaryView(None);
assert_eq!(format!("{no_binary_value:?}"), "BinaryView(NULL)");
let small_binary_value = ScalarValue::BinaryView(Some(vec![1u8, 2, 3]));
assert_eq!(format!("{small_binary_value:?}"), "BinaryView(\"1,2,3\")");
let large_binary_value =
ScalarValue::BinaryView(Some(vec![1u8, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]));
assert_eq!(
format!("{large_binary_value:?}"),
"BinaryView(\"1,2,3,4,5,6,7,8,9,10,11\")"
);

let no_binary_value = ScalarValue::LargeBinary(None);
assert_eq!(format!("{no_binary_value:?}"), "LargeBinary(NULL)");
let small_binary_value = ScalarValue::LargeBinary(Some(vec![1u8, 2, 3]));
assert_eq!(format!("{small_binary_value:?}"), "LargeBinary(\"1,2,3\")");
let large_binary_value =
ScalarValue::LargeBinary(Some(vec![1u8, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]));
assert_eq!(
format!("{large_binary_value:?}"),
"LargeBinary(\"1,2,3,4,5,6,7,8,9,10,11\")"
);

let no_binary_value = ScalarValue::FixedSizeBinary(3, None);
assert_eq!(format!("{no_binary_value:?}"), "FixedSizeBinary(3, NULL)");
let small_binary_value = ScalarValue::FixedSizeBinary(3, Some(vec![1u8, 2, 3]));
assert_eq!(
format!("{small_binary_value:?}"),
"FixedSizeBinary(3, \"1,2,3\")"
);
let large_binary_value = ScalarValue::FixedSizeBinary(
11,
Some(vec![1u8, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]),
);
assert_eq!(
format!("{large_binary_value:?}"),
"FixedSizeBinary(11, \"1,2,3,4,5,6,7,8,9,10,11\")"
);
}

#[test]
fn test_build_timestamp_millisecond_list() {
let values = vec![ScalarValue::TimestampMillisecond(Some(1), None)];
Expand Down