feat: add document search query

This commit is contained in:
Vincent Koc 2026-04-26 23:32:06 -07:00
parent d4138a0e2c
commit 05ede2e7cb
No known key found for this signature in database
2 changed files with 93 additions and 0 deletions

53
internal/store/search.go Normal file
View File

@ -0,0 +1,53 @@
package store
import (
"context"
"database/sql"
"fmt"
)
type SearchHit struct {
ThreadID int64 `json:"thread_id"`
Number int `json:"number"`
Kind string `json:"kind"`
State string `json:"state"`
Title string `json:"title"`
HTMLURL string `json:"html_url"`
AuthorLogin string `json:"author_login,omitempty"`
Snippet string `json:"snippet"`
}
func (s *Store) SearchDocuments(ctx context.Context, repoID int64, query string, limit int) ([]SearchHit, error) {
if limit <= 0 {
limit = 20
}
rows, err := s.db.QueryContext(ctx, `
select t.id, t.number, t.kind, t.state, t.title, t.html_url, t.author_login,
snippet(documents_fts, 3, '[', ']', '...', 18)
from documents_fts
join documents d on d.id = documents_fts.rowid
join threads t on t.id = d.thread_id
where t.repo_id = ? and documents_fts match ?
order by bm25(documents_fts)
limit ?
`, repoID, query, limit)
if err != nil {
return nil, fmt.Errorf("search documents: %w", err)
}
defer rows.Close()
var out []SearchHit
for rows.Next() {
var hit SearchHit
var author sql.NullString
if err := rows.Scan(&hit.ThreadID, &hit.Number, &hit.Kind, &hit.State, &hit.Title, &hit.HTMLURL, &author, &hit.Snippet); err != nil {
return nil, fmt.Errorf("scan search hit: %w", err)
}
hit.AuthorLogin = author.String
out = append(out, hit)
}
if err := rows.Err(); err != nil {
return nil, fmt.Errorf("iterate search hits: %w", err)
}
return out, nil
}

View File

@ -0,0 +1,40 @@
package store
import (
"context"
"path/filepath"
"testing"
)
func TestSearchDocuments(t *testing.T) {
ctx := context.Background()
st, err := Open(ctx, filepath.Join(t.TempDir(), "gitcrawl.db"))
if err != nil {
t.Fatalf("open store: %v", err)
}
defer st.Close()
repoID, err := st.UpsertRepository(ctx, Repository{Owner: "openclaw", Name: "gitcrawl", FullName: "openclaw/gitcrawl", RawJSON: "{}", UpdatedAt: "2026-04-26T00:00:00Z"})
if err != nil {
t.Fatalf("repo: %v", err)
}
threadID, err := st.UpsertThread(ctx, Thread{
RepoID: repoID, GitHubID: "1", Number: 1, Kind: "issue", State: "open",
Title: "download stalls", HTMLURL: "https://github.com/openclaw/gitcrawl/issues/1",
LabelsJSON: "[]", AssigneesJSON: "[]", RawJSON: "{}", ContentHash: "hash", UpdatedAt: "2026-04-26T00:00:00Z",
})
if err != nil {
t.Fatalf("thread: %v", err)
}
if _, err := st.UpsertDocument(ctx, Document{ThreadID: threadID, Title: "download stalls", RawText: "artifact download stalls", DedupeText: "artifact download stalls", UpdatedAt: "2026-04-26T00:00:00Z"}); err != nil {
t.Fatalf("document: %v", err)
}
hits, err := st.SearchDocuments(ctx, repoID, "artifact", 10)
if err != nil {
t.Fatalf("search: %v", err)
}
if len(hits) != 1 || hits[0].Number != 1 {
t.Fatalf("unexpected hits: %#v", hits)
}
}