Skip to content

Fix bleve fuzziness (#30799) #30804

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
May 1, 2024
Merged

Fix bleve fuzziness (#30799) #30804

Show file tree
Hide file tree
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
4 changes: 1 addition & 3 deletions modules/indexer/code/bleve/bleve.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,6 @@ import (
const (
unicodeNormalizeName = "unicodeNormalize"
maxBatchSize = 16
// fuzzyDenominator determines the levenshtein distance per each character of a keyword
fuzzyDenominator = 4
)

func addUnicodeNormalizeTokenFilter(m *mapping.IndexMappingImpl) error {
Expand Down Expand Up @@ -245,7 +243,7 @@ func (b *Indexer) Search(ctx context.Context, opts *internal.SearchOptions) (int
phraseQuery.Analyzer = repoIndexerAnalyzer
keywordQuery = phraseQuery
if opts.IsKeywordFuzzy {
phraseQuery.Fuzziness = len(opts.Keyword) / fuzzyDenominator
phraseQuery.Fuzziness = inner_bleve.GuessFuzzinessByKeyword(opts.Keyword)
}

if len(opts.RepoIDs) > 0 {
Expand Down
12 changes: 12 additions & 0 deletions modules/indexer/internal/bleve/util.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,3 +47,15 @@ func openIndexer(path string, latestVersion int) (bleve.Index, int, error) {

return index, 0, nil
}

func GuessFuzzinessByKeyword(s string) int {
// according to https://github.com/blevesearch/bleve/issues/1563, the supported max fuzziness is 2
// magic number 4 was chosen to determine the levenshtein distance per each character of a keyword
// BUT, when using CJK (eg: `갃갃갃` `啊啊啊`), it mismatches a lot.
for _, r := range s {
if r >= 128 {
return 0
}
}
return min(2, len(s)/4)
}
8 changes: 2 additions & 6 deletions modules/indexer/issues/bleve/bleve.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,11 +35,7 @@ func addUnicodeNormalizeTokenFilter(m *mapping.IndexMappingImpl) error {
})
}

const (
maxBatchSize = 16
// fuzzyDenominator determines the levenshtein distance per each character of a keyword
fuzzyDenominator = 4
)
const maxBatchSize = 16

// IndexerData an update to the issue indexer
type IndexerData internal.IndexerData
Expand Down Expand Up @@ -162,7 +158,7 @@ func (b *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (
if options.Keyword != "" {
fuzziness := 0
if options.IsFuzzyKeyword {
fuzziness = len(options.Keyword) / fuzzyDenominator
fuzziness = inner_bleve.GuessFuzzinessByKeyword(options.Keyword)
}

queries = append(queries, bleve.NewDisjunctionQuery([]query.Query{
Expand Down
2 changes: 1 addition & 1 deletion routers/web/repo/search.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ func Search(ctx *context.Context) {
ctx.Data["Language"] = language
ctx.Data["IsFuzzy"] = isFuzzy
ctx.Data["PageIsViewCode"] = true
ctx.Data["IsRepoIndexerEnabled"] = setting.Indexer.RepoIndexerEnabled

if keyword == "" {
ctx.HTML(http.StatusOK, tplSearch)
Expand Down Expand Up @@ -86,7 +87,6 @@ func Search(ctx *context.Context) {
}
}

ctx.Data["IsRepoIndexerEnabled"] = setting.Indexer.RepoIndexerEnabled
ctx.Data["Repo"] = ctx.Repo.Repository
ctx.Data["SearchResults"] = searchResults
ctx.Data["SearchResultLanguages"] = searchResultLanguages
Expand Down