1
1
mirror of https://github.com/go-gitea/gitea synced 2025-07-03 09:07:19 +00:00

Allow code search by filename (#32210)

This is a large and complex PR, so let me explain in detail its changes.

First, I had to create new index mappings for Bleve and ElasticSerach as
the current ones do not support search by filename. This requires Gitea
to recreate the code search indexes (I do not know if this is a breaking
change, but I feel it deserves a heads-up).

I've used [this
approach](https://www.elastic.co/guide/en/elasticsearch/reference/7.17/analysis-pathhierarchy-tokenizer.html)
to model the filename index. It allows us to efficiently search for both
the full path and the name of a file. Bleve, however, does not support
this out-of-box, so I had to code a brand new [token
filter](https://blevesearch.com/docs/Token-Filters/) to generate the
search terms.

I also did an overhaul in the `indexer_test.go` file. It now asserts the
order of the expected results (this is important since matches based on
the name of a file are more relevant than those based on its content).
I've added new test scenarios that deal with searching by filename. They
use a new repo included in the Gitea fixture.

The screenshot below depicts how Gitea shows the search results. It
shows results based on content in the same way as the current version
does. In matches based on the filename, the first seven lines of the
file contents are shown (BTW, this is how GitHub does it).


![image](https://github.com/user-attachments/assets/9d938d86-1a8d-4f89-8644-1921a473e858)

Resolves #32096

---------

Signed-off-by: Bruno Sofiato <bruno.sofiato@gmail.com>
This commit is contained in:
Bruno Sofiato
2024-10-11 20:35:04 -03:00
committed by GitHub
parent 0fe5e2b08c
commit 900ac62251
38 changed files with 721 additions and 50 deletions

View File

@ -712,3 +712,24 @@
type: 3
config: "{\"IgnoreWhitespaceConflicts\":false,\"AllowMerge\":true,\"AllowRebase\":true,\"AllowRebaseMerge\":true,\"AllowSquash\":true}"
created_unix: 946684810
-
id: 108
repo_id: 62
type: 1
config: "{}"
created_unix: 946684810
-
id: 109
repo_id: 62
type: 2
config: "{\"EnableTimetracker\":true,\"AllowOnlyContributorsToTrackTime\":true}"
created_unix: 946684810
-
id: 110
repo_id: 62
type: 3
config: "{\"IgnoreWhitespaceConflicts\":false,\"AllowMerge\":true,\"AllowRebase\":true,\"AllowRebaseMerge\":true,\"AllowSquash\":true}"
created_unix: 946684810

View File

@ -1768,3 +1768,34 @@
size: 0
is_fsck_enabled: true
close_issues_via_commit_in_any_branch: false
-
id: 62
owner_id: 42
owner_name: org42
lower_name: search-by-path
name: search-by-path
default_branch: master
num_watches: 0
num_stars: 0
num_forks: 0
num_issues: 0
num_closed_issues: 0
num_pulls: 0
num_closed_pulls: 0
num_milestones: 0
num_closed_milestones: 0
num_projects: 0
num_closed_projects: 0
is_private: false
is_empty: false
is_archived: false
is_mirror: false
status: 0
is_fork: false
fork_id: 0
is_template: false
template_id: 0
size: 0
is_fsck_enabled: true
close_issues_via_commit_in_any_branch: false

View File

@ -1517,3 +1517,40 @@
repo_admin_change_team_access: false
theme: ""
keep_activity_private: false
-
id: 42
lower_name: org42
name: org42
full_name: Org42
email: org42@example.com
keep_email_private: false
email_notifications_preference: onmention
passwd: ZogKvWdyEx:password
passwd_hash_algo: dummy
must_change_password: false
login_source: 0
login_name: org42
type: 1
salt: ZogKvWdyEx
max_repo_creation: -1
is_active: false
is_admin: false
is_restricted: false
allow_git_hook: false
allow_import_local: false
allow_create_organization: true
prohibit_login: false
avatar: avatar42
avatar_email: org42@example.com
use_custom_avatar: false
num_followers: 0
num_following: 0
num_stars: 0
num_repos: 1
num_teams: 0
num_members: 0
visibility: 0
repo_admin_change_team_access: false
theme: ""
keep_activity_private: false

View File

@ -138,12 +138,12 @@ func getTestCases() []struct {
{
name: "AllPublic/PublicRepositoriesOfUserIncludingCollaborative",
opts: &repo_model.SearchRepoOptions{ListOptions: db.ListOptions{Page: 1, PageSize: 10}, OwnerID: 15, AllPublic: true, Template: optional.Some(false)},
count: 33,
count: 34,
},
{
name: "AllPublic/PublicAndPrivateRepositoriesOfUserIncludingCollaborative",
opts: &repo_model.SearchRepoOptions{ListOptions: db.ListOptions{Page: 1, PageSize: 10}, OwnerID: 15, Private: true, AllPublic: true, AllLimited: true, Template: optional.Some(false)},
count: 38,
count: 39,
},
{
name: "AllPublic/PublicAndPrivateRepositoriesOfUserIncludingCollaborativeByName",
@ -158,7 +158,7 @@ func getTestCases() []struct {
{
name: "AllPublic/PublicRepositoriesOfOrganization",
opts: &repo_model.SearchRepoOptions{ListOptions: db.ListOptions{Page: 1, PageSize: 10}, OwnerID: 17, AllPublic: true, Collaborate: optional.Some(false), Template: optional.Some(false)},
count: 33,
count: 34,
},
{
name: "AllTemplates",

View File

@ -92,7 +92,10 @@ func TestSearchUsers(t *testing.T) {
testOrgSuccess(&user_model.SearchUserOptions{OrderBy: "id ASC", ListOptions: db.ListOptions{Page: 4, PageSize: 2}},
[]int64{26, 41})
testOrgSuccess(&user_model.SearchUserOptions{ListOptions: db.ListOptions{Page: 5, PageSize: 2}},
testOrgSuccess(&user_model.SearchUserOptions{OrderBy: "id ASC", ListOptions: db.ListOptions{Page: 5, PageSize: 2}},
[]int64{42})
testOrgSuccess(&user_model.SearchUserOptions{ListOptions: db.ListOptions{Page: 6, PageSize: 2}},
[]int64{})
// test users