2019-02-21 06:24:05 +05:30
|
|
|
// Copyright 2019 The Gitea Authors. All rights reserved.
|
2022-11-27 23:50:29 +05:30
|
|
|
// SPDX-License-Identifier: MIT
|
2019-02-21 06:24:05 +05:30
|
|
|
|
|
|
|
package issues
|
|
|
|
|
|
|
|
import (
|
2022-01-27 14:00:51 +05:30
|
|
|
"context"
|
2019-12-28 07:38:05 +05:30
|
|
|
"path"
|
2019-02-21 06:24:05 +05:30
|
|
|
"path/filepath"
|
|
|
|
"testing"
|
|
|
|
"time"
|
|
|
|
|
2021-11-12 20:06:47 +05:30
|
|
|
"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 18:07:56 +05:30
|
|
|
"code.gitea.io/gitea/modules/indexer/issues/bleve"
|
2019-02-21 06:24:05 +05:30
|
|
|
"code.gitea.io/gitea/modules/setting"
|
|
|
|
|
2021-12-15 11:09:34 +05:30
|
|
|
_ "code.gitea.io/gitea/models"
|
|
|
|
|
2019-02-21 06:24:05 +05:30
|
|
|
"github.com/stretchr/testify/assert"
|
|
|
|
)
|
|
|
|
|
|
|
|
func TestMain(m *testing.M) {
|
2022-04-14 19:28:21 +05:30
|
|
|
unittest.MainTest(m, &unittest.TestOptions{
|
|
|
|
GiteaRootPath: filepath.Join("..", "..", ".."),
|
|
|
|
})
|
2019-02-21 06:24:05 +05:30
|
|
|
}
|
|
|
|
|
2019-02-24 21:46:20 +05:30
|
|
|
func TestBleveSearchIssues(t *testing.T) {
|
2021-11-12 20:06:47 +05:30
|
|
|
assert.NoError(t, unittest.PrepareTestDatabase())
|
2023-05-10 10:27:06 +05:30
|
|
|
setting.CfgProvider, _ = setting.NewConfigProviderFromData("")
|
2019-02-21 06:24:05 +05:30
|
|
|
|
2022-09-04 20:44:53 +05:30
|
|
|
tmpIndexerDir := t.TempDir()
|
2022-01-20 22:30:38 +05:30
|
|
|
|
2023-02-19 21:42:01 +05:30
|
|
|
setting.CfgProvider.Section("queue.issue_indexer").Key("DATADIR").MustString(path.Join(tmpIndexerDir, "issues.queue"))
|
2022-01-20 22:30:38 +05:30
|
|
|
|
2019-12-28 07:38:05 +05:30
|
|
|
oldIssuePath := setting.Indexer.IssuePath
|
|
|
|
setting.Indexer.IssuePath = path.Join(tmpIndexerDir, "issues.queue")
|
|
|
|
defer func() {
|
|
|
|
setting.Indexer.IssuePath = oldIssuePath
|
|
|
|
}()
|
|
|
|
|
2019-02-24 21:46:20 +05:30
|
|
|
setting.Indexer.IssueType = "bleve"
|
2023-02-19 21:42:01 +05:30
|
|
|
setting.LoadQueueSettings()
|
2019-10-15 19:09:51 +05:30
|
|
|
InitIssueIndexer(true)
|
2019-12-28 07:38:05 +05:30
|
|
|
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 18:07:56 +05:30
|
|
|
if bleveIndexer, ok := (*globalIndexer.Load()).(*bleve.Indexer); ok {
|
2019-12-28 07:38:05 +05:30
|
|
|
bleveIndexer.Close()
|
|
|
|
}
|
|
|
|
}()
|
2019-02-21 06:24:05 +05:30
|
|
|
|
2019-02-24 21:46:20 +05:30
|
|
|
time.Sleep(5 * time.Second)
|
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err := SearchIssuesByKeyword(context.TODO(), []int64{1}, "issue2")
|
2019-02-24 21:46:20 +05:30
|
|
|
assert.NoError(t, err)
|
|
|
|
assert.EqualValues(t, []int64{2}, ids)
|
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "first")
|
2019-02-24 21:46:20 +05:30
|
|
|
assert.NoError(t, err)
|
|
|
|
assert.EqualValues(t, []int64{1}, ids)
|
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "for")
|
2019-02-24 21:46:20 +05:30
|
|
|
assert.NoError(t, err)
|
2021-01-16 10:25:17 +05:30
|
|
|
assert.ElementsMatch(t, []int64{1, 2, 3, 5, 11}, ids)
|
2019-02-24 21:46:20 +05:30
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "good")
|
2019-02-24 21:46:20 +05:30
|
|
|
assert.NoError(t, err)
|
|
|
|
assert.EqualValues(t, []int64{1}, ids)
|
|
|
|
}
|
|
|
|
|
|
|
|
func TestDBSearchIssues(t *testing.T) {
|
2021-11-12 20:06:47 +05:30
|
|
|
assert.NoError(t, unittest.PrepareTestDatabase())
|
2019-02-24 21:46:20 +05:30
|
|
|
|
|
|
|
setting.Indexer.IssueType = "db"
|
2019-10-15 19:09:51 +05:30
|
|
|
InitIssueIndexer(true)
|
2019-02-21 06:24:05 +05:30
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err := SearchIssuesByKeyword(context.TODO(), []int64{1}, "issue2")
|
2019-02-21 06:24:05 +05:30
|
|
|
assert.NoError(t, err)
|
|
|
|
assert.EqualValues(t, []int64{2}, ids)
|
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "first")
|
2019-02-21 06:24:05 +05:30
|
|
|
assert.NoError(t, err)
|
|
|
|
assert.EqualValues(t, []int64{1}, ids)
|
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "for")
|
2019-02-21 06:24:05 +05:30
|
|
|
assert.NoError(t, err)
|
2021-01-16 10:25:17 +05:30
|
|
|
assert.ElementsMatch(t, []int64{1, 2, 3, 5, 11}, ids)
|
2019-02-21 10:31:28 +05:30
|
|
|
|
2022-01-27 14:00:51 +05:30
|
|
|
ids, err = SearchIssuesByKeyword(context.TODO(), []int64{1}, "good")
|
2019-02-21 10:31:28 +05:30
|
|
|
assert.NoError(t, err)
|
|
|
|
assert.EqualValues(t, []int64{1}, ids)
|
2019-02-21 06:24:05 +05:30
|
|
|
}
|