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- [x] Fix outdated example config.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
|
|
|
// Copyright 2023 The Gitea Authors. All rights reserved.
|
|
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
|
|
|
|
package bleve
|
|
|
|
|
|
|
|
import (
|
|
|
|
"context"
|
|
|
|
"fmt"
|
|
|
|
|
|
|
|
"code.gitea.io/gitea/modules/indexer/internal"
|
|
|
|
"code.gitea.io/gitea/modules/log"
|
|
|
|
|
|
|
|
"github.com/blevesearch/bleve/v2"
|
|
|
|
"github.com/blevesearch/bleve/v2/mapping"
|
|
|
|
"github.com/ethantkoenig/rupture"
|
|
|
|
)
|
|
|
|
|
|
|
|
var _ internal.Indexer = &Indexer{}
|
|
|
|
|
|
|
|
// Indexer represents a basic bleve indexer implementation
|
|
|
|
type Indexer struct {
|
|
|
|
Indexer bleve.Index
|
|
|
|
|
|
|
|
indexDir string
|
|
|
|
version int
|
|
|
|
mappingGetter MappingGetter
|
|
|
|
}
|
|
|
|
|
|
|
|
type MappingGetter func() (mapping.IndexMapping, error)
|
|
|
|
|
|
|
|
func NewIndexer(indexDir string, version int, mappingGetter func() (mapping.IndexMapping, error)) *Indexer {
|
|
|
|
return &Indexer{
|
|
|
|
indexDir: indexDir,
|
|
|
|
version: version,
|
|
|
|
mappingGetter: mappingGetter,
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// 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.Indexer != nil {
|
|
|
|
return false, fmt.Errorf("indexer is already initialized")
|
|
|
|
}
|
|
|
|
|
|
|
|
indexer, version, err := openIndexer(i.indexDir, i.version)
|
|
|
|
if err != nil {
|
|
|
|
return false, err
|
|
|
|
}
|
|
|
|
if indexer != nil {
|
|
|
|
i.Indexer = indexer
|
|
|
|
return true, nil
|
|
|
|
}
|
|
|
|
|
|
|
|
if version != 0 {
|
|
|
|
log.Warn("Found older bleve index with version %d, Gitea will remove it and rebuild", version)
|
|
|
|
}
|
|
|
|
|
|
|
|
indexMapping, err := i.mappingGetter()
|
|
|
|
if err != nil {
|
|
|
|
return false, err
|
|
|
|
}
|
|
|
|
|
|
|
|
indexer, err = bleve.New(i.indexDir, indexMapping)
|
|
|
|
if err != nil {
|
|
|
|
return false, err
|
|
|
|
}
|
|
|
|
|
|
|
|
if err = rupture.WriteIndexMetadata(i.indexDir, &rupture.IndexMetadata{
|
|
|
|
Version: i.version,
|
|
|
|
}); err != nil {
|
|
|
|
return false, err
|
|
|
|
}
|
|
|
|
|
|
|
|
i.Indexer = indexer
|
|
|
|
|
|
|
|
return false, nil
|
|
|
|
}
|
|
|
|
|
|
|
|
// Ping checks if the indexer is available
|
|
|
|
func (i *Indexer) Ping(_ context.Context) error {
|
|
|
|
if i == nil {
|
|
|
|
return fmt.Errorf("cannot ping nil indexer")
|
|
|
|
}
|
|
|
|
if i.Indexer == nil {
|
|
|
|
return fmt.Errorf("indexer is not initialized")
|
|
|
|
}
|
|
|
|
return nil
|
|
|
|
}
|
|
|
|
|
|
|
|
func (i *Indexer) Close() {
|
2024-02-25 14:05:23 +01:00
|
|
|
if i == nil || i.Indexer == nil {
|
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
|
|
|
return
|
|
|
|
}
|
|
|
|
|
|
|
|
if err := i.Indexer.Close(); err != nil {
|
|
|
|
log.Error("Failed to close bleve indexer in %q: %v", i.indexDir, err)
|
|
|
|
}
|
|
|
|
i.Indexer = nil
|
|
|
|
}
|