mirror of
1
Fork 0
forgejo/modules/indexer/issues/indexer_test.go

92 lines
2.5 KiB
Go
Raw Normal View History

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package issues
import (
"context"
"path"
"path/filepath"
"testing"
"time"
"code.gitea.io/gitea/models/unittest"
Refactor indexer (#25174) 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>
2023-06-23 14:37:56 +02:00
"code.gitea.io/gitea/modules/indexer/issues/bleve"
"code.gitea.io/gitea/modules/setting"
_ "code.gitea.io/gitea/models"
"github.com/stretchr/testify/assert"
)
func TestMain(m *testing.M) {
unittest.MainTest(m, &unittest.TestOptions{
GiteaRootPath: filepath.Join("..", "..", ".."),
})
}
func TestBleveSearchIssues(t *testing.T) {
assert.NoError(t, unittest.PrepareTestDatabase())
setting.CfgProvider, _ = setting.NewConfigProviderFromData("")
tmpIndexerDir := t.TempDir()
setting.CfgProvider.Section("queue.issue_indexer").Key("DATADIR").MustString(path.Join(tmpIndexerDir, "issues.queue"))
oldIssuePath := setting.Indexer.IssuePath
setting.Indexer.IssuePath = path.Join(tmpIndexerDir, "issues.queue")
defer func() {
setting.Indexer.IssuePath = oldIssuePath
}()
setting.Indexer.IssueType = "bleve"
setting.LoadQueueSettings()
InitIssueIndexer(true)
defer func() {
Refactor indexer (#25174) 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>
2023-06-23 14:37:56 +02:00
if bleveIndexer, ok := (*globalIndexer.Load()).(*bleve.Indexer); ok {
bleveIndexer.Close()
}
}()
time.Sleep(5 * time.Second)
ids, err := SearchIssuesByKeyword(context.TODO(), []int64{1}, "issue2", "")
assert.NoError(t, err)
assert.EqualValues(t, []int64{2}, ids)
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "first", "")
assert.NoError(t, err)
assert.EqualValues(t, []int64{1}, ids)
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "for", "")
assert.NoError(t, err)
assert.ElementsMatch(t, []int64{1, 2, 3, 5, 11}, ids)
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "good", "")
assert.NoError(t, err)
assert.EqualValues(t, []int64{1}, ids)
}
func TestDBSearchIssues(t *testing.T) {
assert.NoError(t, unittest.PrepareTestDatabase())
setting.Indexer.IssueType = "db"
InitIssueIndexer(true)
ids, err := SearchIssuesByKeyword(context.TODO(), []int64{1}, "issue2", "")
assert.NoError(t, err)
assert.EqualValues(t, []int64{2}, ids)
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "first", "")
assert.NoError(t, err)
assert.EqualValues(t, []int64{1}, ids)
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "for", "")
assert.NoError(t, err)
assert.ElementsMatch(t, []int64{1, 2, 3, 5, 11}, ids)
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "good", "")
assert.NoError(t, err)
assert.EqualValues(t, []int64{1}, ids)
}