feat: implement branch-aware context switching and integrate tantivy fuzzy search index
This commit is contained in:
1 parent
e4ff476b6d
commit
3239e32866
6 files changed
+797
-2
No files matched your search
@@ -0,0 +1,91 @@
|
||||
use tantivy::schema::*;
|
||||
use tantivy::{doc, Index, IndexWriter, IndexReader, ReloadPolicy};
|
||||
use std::sync::Mutex;
|
||||
use crate::models::{Entity, Task, StickyNote, Adr, Snippet};
|
||||
|
||||
pub struct MemoryIndex {
|
||||
index: Index,
|
||||
reader: IndexReader,
|
||||
writer: Mutex<IndexWriter>,
|
||||
|
||||
// Schema fields
|
||||
pub id_field: Field,
|
||||
pub title_field: Field,
|
||||
pub body_field: Field,
|
||||
pub type_field: Field,
|
||||
pub namespace_field: Field,
|
||||
}
|
||||
|
||||
impl MemoryIndex {
|
||||
pub fn new() -> tantivy::Result<Self> {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let id_field = schema_builder.add_text_field("id", STRING | STORED);
|
||||
let title_field = schema_builder.add_text_field("title", TEXT | STORED);
|
||||
let body_field = schema_builder.add_text_field("body", TEXT | STORED);
|
||||
let type_field = schema_builder.add_text_field("type", STRING | STORED);
|
||||
let namespace_field = schema_builder.add_text_field("namespace", STRING | STORED);
|
||||
let schema = schema_builder.build();
|
||||
|
||||
let index = Index::create_in_ram(schema.clone());
|
||||
let writer = index.writer(50_000_000)?;
|
||||
let reader = index
|
||||
.reader_builder()
|
||||
.reload_policy(ReloadPolicy::OnCommitWithDelay)
|
||||
.try_into()?;
|
||||
|
||||
Ok(Self {
|
||||
index,
|
||||
reader,
|
||||
writer: Mutex::new(writer),
|
||||
id_field,
|
||||
title_field,
|
||||
body_field,
|
||||
type_field,
|
||||
namespace_field,
|
||||
})
|
||||
}
|
||||
|
||||
pub fn index_entity(&self, e: &Entity) -> tantivy::Result<()> {
|
||||
let mut writer = self.writer.lock().unwrap();
|
||||
writer.add_document(doc!(
|
||||
self.id_field => e.name.clone(),
|
||||
self.title_field => e.name.clone(),
|
||||
self.body_field => e.observations.join(" "),
|
||||
self.type_field => "entity",
|
||||
self.namespace_field => e.namespace.clone()
|
||||
))?;
|
||||
writer.commit()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn index_task(&self, t: &Task) -> tantivy::Result<()> {
|
||||
let mut writer = self.writer.lock().unwrap();
|
||||
writer.add_document(doc!(
|
||||
self.id_field => t.id.clone(),
|
||||
self.title_field => t.title.clone(),
|
||||
self.body_field => t.description.clone(),
|
||||
self.type_field => "task",
|
||||
self.namespace_field => "global"
|
||||
))?;
|
||||
writer.commit()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn search(&self, query: &str, namespace: Option<&str>) -> tantivy::Result<Vec<String>> {
|
||||
let searcher = self.reader.searcher();
|
||||
let query_parser = tantivy::query::QueryParser::for_index(&self.index, vec![self.title_field, self.body_field]);
|
||||
let q = query_parser.parse_query(query)?;
|
||||
|
||||
let top_docs = searcher.search(&q, &tantivy::collector::TopDocs::with_limit(50))?;
|
||||
let mut results = Vec::new();
|
||||
for (_score, doc_address) in top_docs {
|
||||
let retrieved_doc = searcher.doc::<tantivy::TantivyDocument>(doc_address)?;
|
||||
if let Some(val) = retrieved_doc.get_first(self.title_field) {
|
||||
if let Some(t) = val.as_str() {
|
||||
results.push(t.to_string());
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(results)
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user