mirror of
https://codeberg.org/forgejo/forgejo
synced 2024-11-27 20:26:09 +01:00
375fd15fbf
Refactor `modules/indexer` to make it more maintainable. And it can be easier to support more features. I'm trying to solve some of issue searching, this is a precursor to making functional changes. Current supported engines and the index versions: | engines | issues | code | | - | - | - | | db | Just a wrapper for database queries, doesn't need version | - | | bleve | The version of index is **2** | The version of index is **6** | | elasticsearch | The old index has no version, will be treated as version **0** in this PR | The version of index is **1** | | meilisearch | The old index has no version, will be treated as version **0** in this PR | - | ## Changes ### Split Splited it into mutiple packages ```text indexer ├── internal │ ├── bleve │ ├── db │ ├── elasticsearch │ └── meilisearch ├── code │ ├── bleve │ ├── elasticsearch │ └── internal └── issues ├── bleve ├── db ├── elasticsearch ├── internal └── meilisearch ``` - `indexer/interanal`: Internal shared package for indexer. - `indexer/interanal/[engine]`: Internal shared package for each engine (bleve/db/elasticsearch/meilisearch). - `indexer/code`: Implementations for code indexer. - `indexer/code/internal`: Internal shared package for code indexer. - `indexer/code/[engine]`: Implementation via each engine for code indexer. - `indexer/issues`: Implementations for issues indexer. ### Deduplication - Combine `Init/Ping/Close` for code indexer and issues indexer. - ~Combine `issues.indexerHolder` and `code.wrappedIndexer` to `internal.IndexHolder`.~ Remove it, use dummy indexer instead when the indexer is not ready. - Duplicate two copies of creating ES clients. - Duplicate two copies of `indexerID()`. ### Enhancement - [x] Support index version for elasticsearch issues indexer, the old index without version will be treated as version 0. - [x] Fix spell of `elastic_search/ElasticSearch`, it should be `Elasticsearch`. - [x] Improve versioning of ES index. We don't need `Aliases`: - Gitea does't need aliases for "Zero Downtime" because it never delete old indexes. - The old code of issues indexer uses the orignal name to create issue index, so it's tricky to convert it to an alias. - [x] Support index version for meilisearch issues indexer, the old index without version will be treated as version 0. - [x] Do "ping" only when `Ping` has been called, don't ping periodically and cache the status. - [x] Support the context parameter whenever possible. - [x] Fix outdated example config. - [x] Give up the requeue logic of issues indexer: When indexing fails, call Ping to check if it was caused by the engine being unavailable, and only requeue the task if the engine is unavailable. - It is fragile and tricky, could cause data losing (It did happen when I was doing some tests for this PR). And it works for ES only. - Just always requeue the failed task, if it caused by bad data, it's a bug of Gitea which should be fixed. --------- Co-authored-by: Giteabot <teabot@gitea.io>
133 lines
2.7 KiB
Go
133 lines
2.7 KiB
Go
// Copyright 2020 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package code
|
|
|
|
import (
|
|
"context"
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
|
|
"code.gitea.io/gitea/models/unittest"
|
|
"code.gitea.io/gitea/modules/git"
|
|
"code.gitea.io/gitea/modules/indexer/code/bleve"
|
|
"code.gitea.io/gitea/modules/indexer/code/elasticsearch"
|
|
"code.gitea.io/gitea/modules/indexer/code/internal"
|
|
|
|
_ "code.gitea.io/gitea/models"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
)
|
|
|
|
func TestMain(m *testing.M) {
|
|
unittest.MainTest(m, &unittest.TestOptions{
|
|
GiteaRootPath: filepath.Join("..", "..", ".."),
|
|
})
|
|
}
|
|
|
|
func testIndexer(name string, t *testing.T, indexer internal.Indexer) {
|
|
t.Run(name, func(t *testing.T) {
|
|
var repoID int64 = 1
|
|
err := index(git.DefaultContext, indexer, repoID)
|
|
assert.NoError(t, err)
|
|
keywords := []struct {
|
|
RepoIDs []int64
|
|
Keyword string
|
|
IDs []int64
|
|
Langs int
|
|
}{
|
|
{
|
|
RepoIDs: nil,
|
|
Keyword: "Description",
|
|
IDs: []int64{repoID},
|
|
Langs: 1,
|
|
},
|
|
{
|
|
RepoIDs: []int64{2},
|
|
Keyword: "Description",
|
|
IDs: []int64{},
|
|
Langs: 0,
|
|
},
|
|
{
|
|
RepoIDs: nil,
|
|
Keyword: "repo1",
|
|
IDs: []int64{repoID},
|
|
Langs: 1,
|
|
},
|
|
{
|
|
RepoIDs: []int64{2},
|
|
Keyword: "repo1",
|
|
IDs: []int64{},
|
|
Langs: 0,
|
|
},
|
|
{
|
|
RepoIDs: nil,
|
|
Keyword: "non-exist",
|
|
IDs: []int64{},
|
|
Langs: 0,
|
|
},
|
|
}
|
|
|
|
for _, kw := range keywords {
|
|
t.Run(kw.Keyword, func(t *testing.T) {
|
|
total, res, langs, err := indexer.Search(context.TODO(), kw.RepoIDs, "", kw.Keyword, 1, 10, false)
|
|
assert.NoError(t, err)
|
|
assert.Len(t, kw.IDs, int(total))
|
|
assert.Len(t, langs, kw.Langs)
|
|
|
|
ids := make([]int64, 0, len(res))
|
|
for _, hit := range res {
|
|
ids = append(ids, hit.RepoID)
|
|
assert.EqualValues(t, "# repo1\n\nDescription for repo1", hit.Content)
|
|
}
|
|
assert.EqualValues(t, kw.IDs, ids)
|
|
})
|
|
}
|
|
|
|
assert.NoError(t, indexer.Delete(context.Background(), repoID))
|
|
})
|
|
}
|
|
|
|
func TestBleveIndexAndSearch(t *testing.T) {
|
|
unittest.PrepareTestEnv(t)
|
|
|
|
dir := t.TempDir()
|
|
|
|
idx := bleve.NewIndexer(dir)
|
|
_, err := idx.Init(context.Background())
|
|
if err != nil {
|
|
assert.Fail(t, "Unable to create bleve indexer Error: %v", err)
|
|
if idx != nil {
|
|
idx.Close()
|
|
}
|
|
return
|
|
}
|
|
defer idx.Close()
|
|
|
|
testIndexer("beleve", t, idx)
|
|
}
|
|
|
|
func TestESIndexAndSearch(t *testing.T) {
|
|
unittest.PrepareTestEnv(t)
|
|
|
|
u := os.Getenv("TEST_INDEXER_CODE_ES_URL")
|
|
if u == "" {
|
|
t.SkipNow()
|
|
return
|
|
}
|
|
|
|
indexer := elasticsearch.NewIndexer(u, "gitea_codes")
|
|
if _, err := indexer.Init(context.Background()); err != nil {
|
|
assert.Fail(t, "Unable to init ES indexer Error: %v", err)
|
|
if indexer != nil {
|
|
indexer.Close()
|
|
}
|
|
return
|
|
}
|
|
|
|
defer indexer.Close()
|
|
|
|
testIndexer("elastic_search", t, indexer)
|
|
}
|