mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2024-12-25 17:04:12 -05:00
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>
92 lines
1.8 KiB
Go
92 lines
1.8 KiB
Go
// Copyright 2023 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package elasticsearch
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"code.gitea.io/gitea/modules/indexer/internal"
|
|
|
|
"github.com/olivere/elastic/v7"
|
|
)
|
|
|
|
var _ internal.Indexer = &Indexer{}
|
|
|
|
// Indexer represents a basic elasticsearch indexer implementation
|
|
type Indexer struct {
|
|
Client *elastic.Client
|
|
|
|
url string
|
|
indexName string
|
|
version int
|
|
mapping string
|
|
}
|
|
|
|
func NewIndexer(url, indexName string, version int, mapping string) *Indexer {
|
|
return &Indexer{
|
|
url: url,
|
|
indexName: indexName,
|
|
version: version,
|
|
mapping: mapping,
|
|
}
|
|
}
|
|
|
|
// Init initializes the indexer
|
|
func (i *Indexer) Init(ctx 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")
|
|
}
|
|
|
|
client, err := i.initClient()
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
i.Client = client
|
|
|
|
exists, err := i.Client.IndexExists(i.VersionedIndexName()).Do(ctx)
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
if exists {
|
|
return true, nil
|
|
}
|
|
|
|
if err := i.createIndex(ctx); err != nil {
|
|
return false, err
|
|
}
|
|
|
|
return exists, nil
|
|
}
|
|
|
|
// 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.ClusterHealth().Do(ctx)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if resp.Status != "green" {
|
|
// see https://www.elastic.co/guide/en/elasticsearch/reference/current/cluster-health.html
|
|
return fmt.Errorf("status of elasticsearch cluster is %s", resp.Status)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// Close closes the indexer
|
|
func (i *Indexer) Close() {
|
|
if i == nil {
|
|
return
|
|
}
|
|
i.Client = nil
|
|
}
|