Files
oak-gpui/crates/language/src/diagnostic_set.rs
T
Lukas Wirth e1b57f00a0 sum_tree: Reduce Cursor size for contextless summary types (#38776)
This reduces the size of cursor by a usize when the summary does not
require a context making Cursor usages and constructions slightly more
efficient.

This change is a bit annoying though, as Rust has no means of
specializing, so this uses a `ContextlessSummary` trait with a blanket
impl while turning the `Context` into a GAT `Context<'a>`. This means
`Summary` implies are a bit more verbose now while contextless ones are
slimmer. It does come with the downside that the lifetime in the GAT is
always considered invariant, so some lifetime splitting occurred due to
that.


 ```
push/4096               time:   [352.65 µs 360.87 µs 367.80 µs]
                        thrpt:  [10.621 MiB/s 10.825 MiB/s 11.077 MiB/s]
                 change:
time: [-2.6633% -1.3640% -0.0561%] (p = 0.05 < 0.05)
                        thrpt:  [+0.0561% +1.3828% +2.7361%]
                        Change within noise threshold.
Found 16 outliers among 100 measurements (16.00%)
  7 (7.00%) low severe
  3 (3.00%) low mild
  2 (2.00%) high mild
  4 (4.00%) high severe
push/65536              time:   [1.2917 ms 1.2949 ms 1.2979 ms]
                        thrpt:  [48.156 MiB/s 48.267 MiB/s 48.387 MiB/s]
                 change:
time: [+1.4428% +1.9844% +2.5299%] (p = 0.00 < 0.05)
                        thrpt:  [-2.4675% -1.9458% -1.4223%]
                        Performance has regressed.
Found 3 outliers among 100 measurements (3.00%)
  1 (1.00%) low severe
  1 (1.00%) low mild
  1 (1.00%) high severe

append/4096             time:   [677.87 ns 678.87 ns 679.83 ns]
                        thrpt:  [5.6112 GiB/s 5.6192 GiB/s 5.6274 GiB/s]
                 change:
time: [-0.8924% -0.5017% -0.1705%] (p = 0.00 < 0.05)
                        thrpt:  [+0.1708% +0.5043% +0.9004%]
                        Change within noise threshold.
Found 2 outliers among 100 measurements (2.00%)
  1 (1.00%) low mild
  1 (1.00%) high mild
append/65536            time:   [9.3275 µs 9.3406 µs 9.3536 µs]
                        thrpt:  [6.5253 GiB/s 6.5344 GiB/s 6.5435 GiB/s]
                 change:
time: [+0.5409% +0.7215% +0.9054%] (p = 0.00 < 0.05)
                        thrpt:  [-0.8973% -0.7163% -0.5380%]
                        Change within noise threshold.

slice/4096              time:   [27.673 µs 27.791 µs 27.907 µs]
                        thrpt:  [139.97 MiB/s 140.56 MiB/s 141.16 MiB/s]
                 change:
time: [-1.1065% -0.6725% -0.2429%] (p = 0.00 < 0.05)
                        thrpt:  [+0.2435% +0.6770% +1.1189%]
                        Change within noise threshold.
Found 5 outliers among 100 measurements (5.00%)
  4 (4.00%) low mild
  1 (1.00%) high mild
slice/65536             time:   [507.55 µs 517.40 µs 535.60 µs]
                        thrpt:  [116.69 MiB/s 120.80 MiB/s 123.14 MiB/s]
                 change:
time: [-1.3489% +0.0599% +2.2591%] (p = 0.96 > 0.05)
                        thrpt:  [-2.2092% -0.0598% +1.3674%]
                        No change in performance detected.
Found 8 outliers among 100 measurements (8.00%)
  5 (5.00%) low mild
  2 (2.00%) high mild
  1 (1.00%) high severe

bytes_in_range/4096     time:   [3.3917 µs 3.4108 µs 3.4313 µs]
                        thrpt:  [1.1117 GiB/s 1.1184 GiB/s 1.1247 GiB/s]
                 change:
time: [-5.3466% -4.7193% -4.1262%] (p = 0.00 < 0.05)
                        thrpt:  [+4.3038% +4.9531% +5.6487%]
                        Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
  1 (1.00%) low mild
  5 (5.00%) high mild
bytes_in_range/65536    time:   [88.175 µs 88.613 µs 89.111 µs]
                        thrpt:  [701.37 MiB/s 705.31 MiB/s 708.82 MiB/s]
                 change:
time: [-0.6935% +0.3769% +1.4655%] (p = 0.50 > 0.05)
                        thrpt:  [-1.4443% -0.3755% +0.6984%]
                        No change in performance detected.
Found 2 outliers among 100 measurements (2.00%)
  2 (2.00%) high mild

chars/4096              time:   [678.70 ns 680.38 ns 682.08 ns]
                        thrpt:  [5.5927 GiB/s 5.6067 GiB/s 5.6206 GiB/s]
                 change:
time: [-0.6969% -0.2755% +0.1485%] (p = 0.20 > 0.05)
                        thrpt:  [-0.1483% +0.2763% +0.7018%]
                        No change in performance detected.
Found 9 outliers among 100 measurements (9.00%)
  5 (5.00%) low mild
  4 (4.00%) high mild
chars/65536             time:   [12.720 µs 12.775 µs 12.830 µs]
                        thrpt:  [4.7573 GiB/s 4.7778 GiB/s 4.7983 GiB/s]
                 change:
time: [-0.6172% -0.1110% +0.4179%] (p = 0.68 > 0.05)
                        thrpt:  [-0.4162% +0.1112% +0.6211%]
                        No change in performance detected.
Found 2 outliers among 100 measurements (2.00%)
  1 (1.00%) low mild
  1 (1.00%) high mild

clip_point/4096         time:   [33.240 µs 33.310 µs 33.394 µs]
                        thrpt:  [116.98 MiB/s 117.27 MiB/s 117.52 MiB/s]
                 change:
time: [-2.8892% -2.6305% -2.3438%] (p = 0.00 < 0.05)
                        thrpt:  [+2.4000% +2.7015% +2.9751%]
                        Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
  1 (1.00%) low mild
  4 (4.00%) high mild
  7 (7.00%) high severe
clip_point/65536        time:   [1.6531 ms 1.6586 ms 1.6640 ms]
                        thrpt:  [37.560 MiB/s 37.683 MiB/s 37.808 MiB/s]
                 change:
time: [-6.6381% -5.9395% -5.2680%] (p = 0.00 < 0.05)
                        thrpt:  [+5.5610% +6.3146% +7.1100%]
                        Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
  1 (1.00%) low mild
  2 (2.00%) high mild
  4 (4.00%) high severe

point_to_offset/4096    time:   [11.586 µs 11.603 µs 11.621 µs]
                        thrpt:  [336.15 MiB/s 336.67 MiB/s 337.16 MiB/s]
                 change:
time: [-14.289% -14.111% -13.939%] (p = 0.00 < 0.05)
                        thrpt:  [+16.197% +16.429% +16.672%]
                        Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
  3 (3.00%) low severe
  5 (5.00%) low mild
  4 (4.00%) high mild
point_to_offset/65536   time:   [527.74 µs 532.08 µs 536.51 µs]
                        thrpt:  [116.49 MiB/s 117.46 MiB/s 118.43 MiB/s]
                 change:
time: [-6.7825% -4.6235% -2.3533%] (p = 0.00 < 0.05)
                        thrpt:  [+2.4100% +4.8477% +7.2760%]
                        Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
  4 (4.00%) high mild
  4 (4.00%) high severe

cursor/4096             time:   [16.154 µs 16.192 µs 16.232 µs]
                        thrpt:  [240.66 MiB/s 241.24 MiB/s 241.81 MiB/s]
                 change:
time: [-3.2536% -2.9145% -2.5526%] (p = 0.00 < 0.05)
                        thrpt:  [+2.6194% +3.0019% +3.3630%]
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  1 (1.00%) low mild
  2 (2.00%) high mild
  2 (2.00%) high severe
cursor/65536            time:   [509.60 µs 511.24 µs 512.93 µs]
                        thrpt:  [121.85 MiB/s 122.25 MiB/s 122.65 MiB/s]
                 change:
time: [-7.3677% -6.6017% -5.7840%] (p = 0.00 < 0.05)
                        thrpt:  [+6.1391% +7.0683% +7.9537%]
                        Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
  3 (3.00%) high mild
  3 (3.00%) high severe
```
Release Notes:

- N/A *or* Added/Fixed/Improved ...
2025-09-24 14:35:38 +02:00

290 lines
9.2 KiB
Rust

use crate::{Diagnostic, range_to_lsp};
use anyhow::Result;
use collections::HashMap;
use lsp::LanguageServerId;
use serde::Serialize;
use std::{
cmp::{Ordering, Reverse},
iter,
ops::Range,
};
use sum_tree::{self, Bias, SumTree};
use text::{Anchor, FromAnchor, PointUtf16, ToOffset};
/// A set of diagnostics associated with a given buffer, provided
/// by a single language server.
///
/// The diagnostics are stored in a [`SumTree`], which allows this struct
/// to be cheaply copied, and allows for efficient retrieval of the
/// diagnostics that intersect a given range of the buffer.
#[derive(Clone, Debug)]
pub struct DiagnosticSet {
diagnostics: SumTree<DiagnosticEntry<Anchor>>,
}
/// A single diagnostic in a set. Generic over its range type, because
/// the diagnostics are stored internally as [`Anchor`]s, but can be
/// resolved to different coordinates types like [`usize`] byte offsets or
/// [`Point`](gpui::Point)s.
#[derive(Clone, Debug, PartialEq, Eq, Serialize)]
pub struct DiagnosticEntry<T> {
/// The range of the buffer where the diagnostic applies.
pub range: Range<T>,
/// The information about the diagnostic.
pub diagnostic: Diagnostic,
}
/// A group of related diagnostics, ordered by their start position
/// in the buffer.
#[derive(Debug, Serialize)]
pub struct DiagnosticGroup<T> {
/// The diagnostics.
pub entries: Vec<DiagnosticEntry<T>>,
/// The index into `entries` where the primary diagnostic is stored.
pub primary_ix: usize,
}
impl DiagnosticGroup<Anchor> {
/// Converts the entries in this [`DiagnosticGroup`] to a different buffer coordinate type.
pub fn resolve<O: FromAnchor>(&self, buffer: &text::BufferSnapshot) -> DiagnosticGroup<O> {
DiagnosticGroup {
entries: self
.entries
.iter()
.map(|entry| entry.resolve(buffer))
.collect(),
primary_ix: self.primary_ix,
}
}
}
#[derive(Clone, Debug)]
pub struct Summary {
start: Anchor,
end: Anchor,
min_start: Anchor,
max_end: Anchor,
count: usize,
}
impl DiagnosticEntry<PointUtf16> {
/// Returns a raw LSP diagnostic used to provide diagnostic context to LSP
/// codeAction request
pub fn to_lsp_diagnostic_stub(&self) -> Result<lsp::Diagnostic> {
let range = range_to_lsp(self.range.clone())?;
Ok(lsp::Diagnostic {
range,
code: self.diagnostic.code.clone(),
severity: Some(self.diagnostic.severity),
source: self.diagnostic.source.clone(),
message: self.diagnostic.message.clone(),
data: self.diagnostic.data.clone(),
..Default::default()
})
}
}
impl DiagnosticSet {
/// Constructs a [DiagnosticSet] from a sequence of entries, ordered by
/// their position in the buffer.
pub fn from_sorted_entries<I>(iter: I, buffer: &text::BufferSnapshot) -> Self
where
I: IntoIterator<Item = DiagnosticEntry<Anchor>>,
{
Self {
diagnostics: SumTree::from_iter(iter, buffer),
}
}
/// Constructs a [DiagnosticSet] from a sequence of entries in an arbitrary order.
pub fn new<I>(iter: I, buffer: &text::BufferSnapshot) -> Self
where
I: IntoIterator<Item = DiagnosticEntry<PointUtf16>>,
{
let mut entries = iter.into_iter().collect::<Vec<_>>();
entries.sort_unstable_by_key(|entry| (entry.range.start, Reverse(entry.range.end)));
Self {
diagnostics: SumTree::from_iter(
entries.into_iter().map(|entry| DiagnosticEntry {
range: buffer.anchor_before(entry.range.start)
..buffer.anchor_before(entry.range.end),
diagnostic: entry.diagnostic,
}),
buffer,
),
}
}
/// Returns the number of diagnostics in the set.
pub fn len(&self) -> usize {
self.diagnostics.summary().count
}
/// Returns true when there are no diagnostics in this diagnostic set
pub fn is_empty(&self) -> bool {
self.len() == 0
}
/// Returns an iterator over the diagnostic entries in the set.
pub fn iter(&self) -> impl Iterator<Item = &DiagnosticEntry<Anchor>> {
self.diagnostics.iter()
}
/// Returns an iterator over the diagnostic entries that intersect the
/// given range of the buffer.
pub fn range<'a, T, O>(
&'a self,
range: Range<T>,
buffer: &'a text::BufferSnapshot,
inclusive: bool,
reversed: bool,
) -> impl 'a + Iterator<Item = DiagnosticEntry<O>>
where
T: 'a + ToOffset,
O: FromAnchor,
{
let end_bias = if inclusive { Bias::Right } else { Bias::Left };
let range = buffer.anchor_before(range.start)..buffer.anchor_at(range.end, end_bias);
let mut cursor = self.diagnostics.filter::<_, ()>(buffer, {
move |summary: &Summary| {
let start_cmp = range.start.cmp(&summary.max_end, buffer);
let end_cmp = range.end.cmp(&summary.min_start, buffer);
if inclusive {
start_cmp <= Ordering::Equal && end_cmp >= Ordering::Equal
} else {
start_cmp == Ordering::Less && end_cmp == Ordering::Greater
}
}
});
if reversed {
cursor.prev();
} else {
cursor.next();
}
iter::from_fn({
move || {
if let Some(diagnostic) = cursor.item() {
if reversed {
cursor.prev();
} else {
cursor.next();
}
Some(diagnostic.resolve(buffer))
} else {
None
}
}
})
}
/// Adds all of this set's diagnostic groups to the given output vector.
pub fn groups(
&self,
language_server_id: LanguageServerId,
output: &mut Vec<(LanguageServerId, DiagnosticGroup<Anchor>)>,
buffer: &text::BufferSnapshot,
) {
let mut groups = HashMap::default();
for entry in self.diagnostics.iter() {
groups
.entry(entry.diagnostic.group_id)
.or_insert(Vec::new())
.push(entry.clone());
}
let start_ix = output.len();
output.extend(groups.into_values().filter_map(|mut entries| {
entries.sort_unstable_by(|a, b| a.range.start.cmp(&b.range.start, buffer));
entries
.iter()
.position(|entry| entry.diagnostic.is_primary)
.map(|primary_ix| {
(
language_server_id,
DiagnosticGroup {
entries,
primary_ix,
},
)
})
}));
output[start_ix..].sort_unstable_by(|(id_a, group_a), (id_b, group_b)| {
group_a.entries[group_a.primary_ix]
.range
.start
.cmp(&group_b.entries[group_b.primary_ix].range.start, buffer)
.then_with(|| id_a.cmp(id_b))
});
}
/// Returns all of the diagnostics in a particular diagnostic group,
/// in order of their position in the buffer.
pub fn group<'a, O: FromAnchor>(
&'a self,
group_id: usize,
buffer: &'a text::BufferSnapshot,
) -> impl 'a + Iterator<Item = DiagnosticEntry<O>> {
self.iter()
.filter(move |entry| entry.diagnostic.group_id == group_id)
.map(|entry| entry.resolve(buffer))
}
}
impl sum_tree::Item for DiagnosticEntry<Anchor> {
type Summary = Summary;
fn summary(&self, _cx: &text::BufferSnapshot) -> Self::Summary {
Summary {
start: self.range.start,
end: self.range.end,
min_start: self.range.start,
max_end: self.range.end,
count: 1,
}
}
}
impl DiagnosticEntry<Anchor> {
/// Converts the [DiagnosticEntry] to a different buffer coordinate type.
pub fn resolve<O: FromAnchor>(&self, buffer: &text::BufferSnapshot) -> DiagnosticEntry<O> {
DiagnosticEntry {
range: O::from_anchor(&self.range.start, buffer)
..O::from_anchor(&self.range.end, buffer),
diagnostic: self.diagnostic.clone(),
}
}
}
impl Default for Summary {
fn default() -> Self {
Self {
start: Anchor::MIN,
end: Anchor::MAX,
min_start: Anchor::MAX,
max_end: Anchor::MIN,
count: 0,
}
}
}
impl sum_tree::Summary for Summary {
type Context<'a> = &'a text::BufferSnapshot;
fn zero(_cx: Self::Context<'_>) -> Self {
Default::default()
}
fn add_summary(&mut self, other: &Self, buffer: Self::Context<'_>) {
if other.min_start.cmp(&self.min_start, buffer).is_lt() {
self.min_start = other.min_start;
}
if other.max_end.cmp(&self.max_end, buffer).is_gt() {
self.max_end = other.max_end;
}
self.start = other.start;
self.end = other.end;
self.count += other.count;
}
}