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>

modules/indexer/internal/meilisearch/indexer.go

@@ -0,0 +1,92 @@
+// Copyright 2023 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package meilisearch
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/meilisearch/meilisearch-go"
+)
+
+// Indexer represents a basic meilisearch indexer implementation
+type Indexer struct {
+	Client *meilisearch.Client
+
+	url, apiKey string
+	indexName   string
+	version     int
+}
+
+func NewIndexer(url, apiKey, indexName string, version int) *Indexer {
+	return &Indexer{
+		url:       url,
+		apiKey:    apiKey,
+		indexName: indexName,
+		version:   version,
+	}
+}
+
+// Init initializes the indexer
+func (i *Indexer) Init(_ context.Context) (bool, error) {
+	if i == nil {
+		return false, fmt.Errorf("cannot init nil indexer")
+	}
+
+	if i.Client != nil {
+		return false, fmt.Errorf("indexer is already initialized")
+	}
+
+	i.Client = meilisearch.NewClient(meilisearch.ClientConfig{
+		Host:   i.url,
+		APIKey: i.apiKey,
+	})
+
+	_, err := i.Client.GetIndex(i.VersionedIndexName())
+	if err == nil {
+		return true, nil
+	}
+	_, err = i.Client.CreateIndex(&meilisearch.IndexConfig{
+		Uid:        i.VersionedIndexName(),
+		PrimaryKey: "id",
+	})
+	if err != nil {
+		return false, err
+	}
+
+	i.checkOldIndexes()
+
+	_, err = i.Client.Index(i.VersionedIndexName()).UpdateFilterableAttributes(&[]string{"repo_id"})
+	return false, err
+}
+
+// Ping checks if the indexer is available
+func (i *Indexer) Ping(ctx context.Context) error {
+	if i == nil {
+		return fmt.Errorf("cannot ping nil indexer")
+	}
+	if i.Client == nil {
+		return fmt.Errorf("indexer is not initialized")
+	}
+	resp, err := i.Client.Health()
+	if err != nil {
+		return err
+	}
+	if resp.Status != "available" {
+		// See https://docs.meilisearch.com/reference/api/health.html#status
+		return fmt.Errorf("status of meilisearch is not available: %s", resp.Status)
+	}
+	return nil
+}
+
+// Close closes the indexer
+func (i *Indexer) Close() {
+	if i == nil {
+		return
+	}
+	if i.Client == nil {
+		return
+	}
+	i.Client = nil
+}

modules/indexer/internal/meilisearch/util.go

@@ -0,0 +1,38 @@
+// Copyright 2023 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package meilisearch
+
+import (
+	"fmt"
+
+	"code.gitea.io/gitea/modules/log"
+)
+
+// VersionedIndexName returns the full index name with version
+func (i *Indexer) VersionedIndexName() string {
+	return versionedIndexName(i.indexName, i.version)
+}
+
+func versionedIndexName(indexName string, version int) string {
+	if version == 0 {
+		// Old index name without version
+		return indexName
+	}
+
+	// The format of the index name is <index_name>_v<version>, not <index_name>.v<version> like elasticsearch.
+	// Because meilisearch does not support "." in index name, it should contain only alphanumeric characters, hyphens (-) and underscores (_).
+	// See https://www.meilisearch.com/docs/learn/core_concepts/indexes#index-uid
+
+	return fmt.Sprintf("%s_v%d", indexName, version)
+}
+
+func (i *Indexer) checkOldIndexes() {
+	for v := 0; v < i.version; v++ {
+		indexName := versionedIndexName(i.indexName, v)
+		_, err := i.Client.GetIndex(indexName)
+		if err == nil {
+			log.Warn("Found older meilisearch index named %q, Gitea will keep the old NOT DELETED. You can delete the old version after the upgrade succeed.", indexName)
+		}
+	}
+}