Skip to content

Make SearchMode have default value and add comments #33863

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.

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 5 commits into from
Mar 14, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
9 changes: 7 additions & 2 deletions modules/indexer/code/bleve/bleve.go
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import (
"code.gitea.io/gitea/modules/setting"
"code.gitea.io/gitea/modules/timeutil"
"code.gitea.io/gitea/modules/typesniffer"
"code.gitea.io/gitea/modules/util"

"github.com/blevesearch/bleve/v2"
analyzer_custom "github.com/blevesearch/bleve/v2/analysis/analyzer/custom"
Expand Down Expand Up @@ -272,14 +273,18 @@ func (b *Indexer) Search(ctx context.Context, opts *internal.SearchOptions) (int
pathQuery.FieldVal = "Filename"
pathQuery.SetBoost(10)

if opts.SearchMode == indexer.SearchModeExact {
searchMode := util.IfZero(opts.SearchMode, b.SupportedSearchModes()[0].ModeValue)
if searchMode == indexer.SearchModeExact {
// 1.21 used NewPrefixQuery, but it seems not working well, and later releases changed to NewMatchPhraseQuery
q := bleve.NewMatchPhraseQuery(opts.Keyword)
q.Analyzer = repoIndexerAnalyzer
q.FieldVal = "Content"
contentQuery = q
} else /* words */ {
q := bleve.NewMatchQuery(opts.Keyword)
q.FieldVal = "Content"
if opts.SearchMode == indexer.SearchModeFuzzy {
q.Analyzer = repoIndexerAnalyzer
if searchMode == indexer.SearchModeFuzzy {
// this logic doesn't seem right, it is only used to pass the test-case `Keyword: "dESCRIPTION"`, which doesn't seem to be a real-life use-case.
q.Fuzziness = inner_bleve.GuessFuzzinessByKeyword(opts.Keyword)
} else {
Expand Down
5 changes: 4 additions & 1 deletion modules/indexer/code/elasticsearch/elasticsearch.go
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import (
"code.gitea.io/gitea/modules/setting"
"code.gitea.io/gitea/modules/timeutil"
"code.gitea.io/gitea/modules/typesniffer"
"code.gitea.io/gitea/modules/util"

"github.com/go-enry/go-enry/v2"
"github.com/olivere/elastic/v7"
Expand Down Expand Up @@ -365,7 +366,9 @@ func extractAggs(searchResult *elastic.SearchResult) []*internal.SearchResultLan
// Search searches for codes and language stats by given conditions.
func (b *Indexer) Search(ctx context.Context, opts *internal.SearchOptions) (int64, []*internal.SearchResult, []*internal.SearchResultLanguages, error) {
var contentQuery elastic.Query
if opts.SearchMode == indexer.SearchModeExact {
searchMode := util.IfZero(opts.SearchMode, b.SupportedSearchModes()[0].ModeValue)
if searchMode == indexer.SearchModeExact {
// 1.21 used NewMultiMatchQuery().Type(esMultiMatchTypePhrasePrefix), but later releases changed to NewMatchPhraseQuery
contentQuery = elastic.NewMatchPhraseQuery("content", opts.Keyword)
} else /* words */ {
contentQuery = elastic.NewMultiMatchQuery("content", opts.Keyword).Type(esMultiMatchTypeBestFields).Operator("and")
Expand Down
3 changes: 2 additions & 1 deletion modules/indexer/code/indexer_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@ import (
"code.gitea.io/gitea/modules/indexer/code/internal"
"code.gitea.io/gitea/modules/setting"
"code.gitea.io/gitea/modules/test"
"code.gitea.io/gitea/modules/util"

_ "code.gitea.io/gitea/models"
_ "code.gitea.io/gitea/models/actions"
Expand Down Expand Up @@ -240,7 +241,7 @@ func testIndexer(name string, t *testing.T, indexer internal.Indexer) {
total, res, langs, err := indexer.Search(t.Context(), &internal.SearchOptions{
RepoIDs: kw.RepoIDs,
Keyword: kw.Keyword,
SearchMode: kw.SearchMode,
SearchMode: util.IfZero(kw.SearchMode, indexer_module.SearchModeWords),
Paginator: &db.ListOptions{
Page: 1,
PageSize: 10,
Expand Down
6 changes: 4 additions & 2 deletions modules/indexer/issues/bleve/bleve.go
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ import (
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
inner_bleve "code.gitea.io/gitea/modules/indexer/internal/bleve"
"code.gitea.io/gitea/modules/indexer/issues/internal"
"code.gitea.io/gitea/modules/util"

"github.com/blevesearch/bleve/v2"
"github.com/blevesearch/bleve/v2/analysis/analyzer/custom"
Expand Down Expand Up @@ -162,9 +163,10 @@ func (b *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (
var queries []query.Query

if options.Keyword != "" {
if options.SearchMode == indexer.SearchModeWords || options.SearchMode == indexer.SearchModeFuzzy {
searchMode := util.IfZero(options.SearchMode, b.SupportedSearchModes()[0].ModeValue)
if searchMode == indexer.SearchModeWords || searchMode == indexer.SearchModeFuzzy {
fuzziness := 0
if options.SearchMode == indexer.SearchModeFuzzy {
if searchMode == indexer.SearchModeFuzzy {
fuzziness = inner_bleve.GuessFuzzinessByKeyword(options.Keyword)
}
queries = append(queries, bleve.NewDisjunctionQuery([]query.Query{
Expand Down
11 changes: 6 additions & 5 deletions modules/indexer/issues/db/db.go
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ import (
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
inner_db "code.gitea.io/gitea/modules/indexer/internal/db"
"code.gitea.io/gitea/modules/indexer/issues/internal"
"code.gitea.io/gitea/modules/util"

"xorm.io/builder"
)
Expand Down Expand Up @@ -46,7 +47,7 @@ func (i *Indexer) Delete(_ context.Context, _ ...int64) error {

func buildMatchQuery(mode indexer.SearchModeType, colName, keyword string) builder.Cond {
if mode == indexer.SearchModeExact {
return db.BuildCaseInsensitiveLike("issue.name", keyword)
return db.BuildCaseInsensitiveLike(colName, keyword)
}

// match words
Expand Down Expand Up @@ -84,16 +85,16 @@ func (i *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (
repoCond = builder.Eq{"repo_id": options.RepoIDs[0]}
}
subQuery := builder.Select("id").From("issue").Where(repoCond)

searchMode := util.IfZero(options.SearchMode, i.SupportedSearchModes()[0].ModeValue)
cond = builder.Or(
buildMatchQuery(options.SearchMode, "issue.name", options.Keyword),
buildMatchQuery(options.SearchMode, "issue.content", options.Keyword),
buildMatchQuery(searchMode, "issue.name", options.Keyword),
buildMatchQuery(searchMode, "issue.content", options.Keyword),
builder.In("issue.id", builder.Select("issue_id").
From("comment").
Where(builder.And(
builder.Eq{"type": issue_model.CommentTypeComment},
builder.In("issue_id", subQuery),
buildMatchQuery(options.SearchMode, "content", options.Keyword),
buildMatchQuery(searchMode, "content", options.Keyword),
)),
),
)
Expand Down
4 changes: 3 additions & 1 deletion modules/indexer/issues/elasticsearch/elasticsearch.go
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ import (
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
inner_elasticsearch "code.gitea.io/gitea/modules/indexer/internal/elasticsearch"
"code.gitea.io/gitea/modules/indexer/issues/internal"
"code.gitea.io/gitea/modules/util"

"github.com/olivere/elastic/v7"
)
Expand Down Expand Up @@ -152,7 +153,8 @@ func (b *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (
query := elastic.NewBoolQuery()

if options.Keyword != "" {
if options.SearchMode == indexer.SearchModeExact {
searchMode := util.IfZero(options.SearchMode, b.SupportedSearchModes()[0].ModeValue)
if searchMode == indexer.SearchModeExact {
query.Must(elastic.NewMultiMatchQuery(options.Keyword, "title", "content", "comments").Type(esMultiMatchTypePhrasePrefix))
} else /* words */ {
query.Must(elastic.NewMultiMatchQuery(options.Keyword, "title", "content", "comments").Type(esMultiMatchTypeBestFields).Operator("and"))
Expand Down
7 changes: 3 additions & 4 deletions modules/indexer/issues/indexer.go
Original file line number Diff line number Diff line change
Expand Up @@ -282,7 +282,7 @@ const (

// SearchIssues search issues by options.
func SearchIssues(ctx context.Context, opts *SearchOptions) ([]int64, int64, error) {
indexer := *globalIndexer.Load()
ix := *globalIndexer.Load()

if opts.Keyword == "" || opts.IsKeywordNumeric() {
// This is a conservative shortcut.
Expand All @@ -291,10 +291,9 @@ func SearchIssues(ctx context.Context, opts *SearchOptions) ([]int64, int64, err
// So if the user creates an issue and list issues immediately, the issue may not be listed because the indexer needs time to index the issue.
// Even worse, the external indexer like elastic search may not be available for a while,
// and the user may not be able to list issues completely until it is available again.
indexer = db.NewIndexer()
ix = db.NewIndexer()
}

result, err := indexer.Search(ctx, opts)
result, err := ix.Search(ctx, opts)
if err != nil {
return nil, 0, err
}
Expand Down
8 changes: 5 additions & 3 deletions modules/indexer/issues/indexer_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -82,9 +82,11 @@ func searchIssueWithKeyword(t *testing.T) {
}

for _, test := range tests {
issueIDs, _, err := SearchIssues(t.Context(), &test.opts)
require.NoError(t, err)
assert.Equal(t, test.expectedIDs, issueIDs)
t.Run(test.opts.Keyword, func(t *testing.T) {
issueIDs, _, err := SearchIssues(t.Context(), &test.opts)
require.NoError(t, err)
assert.Equal(t, test.expectedIDs, issueIDs)
})
}
}

Expand Down