mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2024-12-26 10:06:24 +00:00
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>
90 lines
1.7 KiB
Go
90 lines
1.7 KiB
Go
// Copyright 2018 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package bleve
|
|
|
|
import (
|
|
"context"
|
|
"testing"
|
|
|
|
"code.gitea.io/gitea/modules/indexer/issues/internal"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
)
|
|
|
|
func TestBleveIndexAndSearch(t *testing.T) {
|
|
dir := t.TempDir()
|
|
indexer := NewIndexer(dir)
|
|
defer indexer.Close()
|
|
|
|
if _, err := indexer.Init(context.Background()); err != nil {
|
|
assert.Fail(t, "Unable to initialize bleve indexer: %v", err)
|
|
return
|
|
}
|
|
|
|
err := indexer.Index(context.Background(), []*internal.IndexerData{
|
|
{
|
|
ID: 1,
|
|
RepoID: 2,
|
|
Title: "Issue search should support Chinese",
|
|
Content: "As title",
|
|
Comments: []string{
|
|
"test1",
|
|
"test2",
|
|
},
|
|
},
|
|
{
|
|
ID: 2,
|
|
RepoID: 2,
|
|
Title: "CJK support could be optional",
|
|
Content: "Chinese Korean and Japanese should be supported but I would like it's not enabled by default",
|
|
Comments: []string{
|
|
"LGTM",
|
|
"Good idea",
|
|
},
|
|
},
|
|
})
|
|
assert.NoError(t, err)
|
|
|
|
keywords := []struct {
|
|
Keyword string
|
|
IDs []int64
|
|
}{
|
|
{
|
|
Keyword: "search",
|
|
IDs: []int64{1},
|
|
},
|
|
{
|
|
Keyword: "test1",
|
|
IDs: []int64{1},
|
|
},
|
|
{
|
|
Keyword: "test2",
|
|
IDs: []int64{1},
|
|
},
|
|
{
|
|
Keyword: "support",
|
|
IDs: []int64{1, 2},
|
|
},
|
|
{
|
|
Keyword: "chinese",
|
|
IDs: []int64{1, 2},
|
|
},
|
|
{
|
|
Keyword: "help",
|
|
IDs: []int64{},
|
|
},
|
|
}
|
|
|
|
for _, kw := range keywords {
|
|
res, err := indexer.Search(context.TODO(), kw.Keyword, []int64{2}, 10, 0)
|
|
assert.NoError(t, err)
|
|
|
|
ids := make([]int64, 0, len(res.Hits))
|
|
for _, hit := range res.Hits {
|
|
ids = append(ids, hit.ID)
|
|
}
|
|
assert.ElementsMatch(t, kw.IDs, ids)
|
|
}
|
|
}
|