Skip to content

[ENH] Optimize FTS #5592

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

Merged
merged 1 commit into from
Oct 15, 2025
Merged

[ENH] Optimize FTS #5592

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
12 changes: 6 additions & 6 deletions rust/index/src/fulltext/types.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,7 +325,7 @@ impl<'me> FullTextIndexReader<'me> {
.then(|token| async move {
let positional_posting_list = self
.posting_lists_blockfile_reader
.get_range(token.text.as_str()..=token.text.as_str(), ..)
.get_prefix(token.text.as_str())
.await?
.collect::<Vec<_>>();
Ok::<_, FullTextIndexError>(positional_posting_list)
Expand All @@ -346,7 +346,7 @@ impl<'me> FullTextIndexReader<'me> {
.enumerate()
.map(|(i, posting_list)| {
if pointers[i] < posting_list.len() {
Some(posting_list[pointers[i]].1)
Some(posting_list[pointers[i]].0)
} else {
None
}
Expand All @@ -372,15 +372,15 @@ impl<'me> FullTextIndexReader<'me> {

// Seed with the positions of the first token.
let mut adjusted = posting_lists[0][pointers[0]]
.2
.1
.iter()
.copied()
.collect::<HashSet<_>>();

for i in 1..num_tokens {
let byte_delta_from_first_token =
tokens[i].offset_from as u32 - tokens[0].offset_from as u32;
let positions = &posting_lists[i][pointers[i]].2;
let positions = &posting_lists[i][pointers[i]].1;

let shifted = positions
.iter()
Expand Down Expand Up @@ -424,10 +424,10 @@ impl<'me> FullTextIndexReader<'me> {
) -> Result<Vec<(u32, Vec<u32>)>, FullTextIndexError> {
let positional_posting_list = self
.posting_lists_blockfile_reader
.get_range(token..=token, ..)
.get_prefix(token)
.await?;
let mut results = vec![];
for (_, doc_id, positions) in positional_posting_list {
for (doc_id, positions) in positional_posting_list {
results.push((doc_id, positions.to_vec()));
}
Ok(results)
Expand Down
Loading