GameCult/Huginn
Watch
9
0
Fork
You've already forked Huginn
 0
Code Issues Pull requests 2 Projects Releases Packages Wiki Activity Actions

recall cited(): skip non-standing positions before scanning the word run, so one long run costs O(n) not O(n^2); a 1 MiB run test

Browse source 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
Meta Vens 2026-11-07 11:57:40 +00:00
commit c8b338598c
1 changed files with 16 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

18
crates/eureka-state/src/bin/huginn/recall.rs
View file

@ -204,10 +204,13 @@ fn cited(text: &str) -> Vec<String> {
continue;
}
let standing = at == 0 || !(word(bytes[at - 1]) || matches!(bytes[at - 1], b'.' | b':'));
if !standing {
continue;
}
let mut end = run(at);
// Dotted campaign slugs: each pass takes a dot and the word after it.
for _ in 0..bytes.len() {
if !(standing && end > at && bytes.get(end) == Some(&b'.') && run(end + 1) > end + 1) {
if !(end > at && bytes.get(end) == Some(&b'.') && run(end + 1) > end + 1) {
break;
}
end = run(end + 1);
@ -216,7 +219,7 @@ fn cited(text: &str) -> Vec<String> {
bytes.get(end) == Some(&b':') && bytes[end + 1..].starts_with(kind.as_bytes()) && bytes.get(end + 1 + kind.len()) == Some(&b':')
});
match kind {
Some(kind) if standing && end > at => {
Some(kind) if end > at => {
let label = end + kind.len() + 2;
let stop = run(label);
if stop > label {
@ -328,6 +331,17 @@ mod tests {
assert_eq!(cited("a.b.c:ruling:d t:ruling:e"), ["a.b.c:ruling:d", "t:ruling:e"]);
}
#[test]
fn a_megabyte_word_run_is_scanned_in_linear_time() {
for unit in ["a", "a.", "a-1_"] {
let text = format!("{} t:ruling:x", unit.repeat((1 << 20) / unit.len()));
let began = std::time::Instant::now();
let found = cited(&text);
assert!(began.elapsed() < std::time::Duration::from_millis(500), "{unit}: {:?}", began.elapsed());
assert_eq!(found, ["t:ruling:x"]);
}
}
#[test]
fn inert_writes_the_framing_characters_as_escapes() {
assert_eq!(inert("a \"b\" \\ <c>\n\u{202e}\u{a0}\u{7f}é"), r#""a \"b\" \\ \u003cc\u003e\n\u202e\u00a0\u007fé""#);