forgejo/modules/indexer/issues/meilisearch/meilisearch.go

99 lines
2.6 KiB
Go
Raw Normal View History

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 12:37:56 +00:00
// Copyright 2023 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package meilisearch
import (
"context"
"strconv"
"strings"
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
inner_meilisearch "code.gitea.io/gitea/modules/indexer/internal/meilisearch"
"code.gitea.io/gitea/modules/indexer/issues/internal"
"github.com/meilisearch/meilisearch-go"
)
const (
issueIndexerLatestVersion = 0
)
var _ internal.Indexer = &Indexer{}
// Indexer implements Indexer interface
type Indexer struct {
inner *inner_meilisearch.Indexer
indexer_internal.Indexer // do not composite inner_meilisearch.Indexer directly to avoid exposing too much
}
// NewIndexer creates a new meilisearch indexer
func NewIndexer(url, apiKey, indexerName string) *Indexer {
inner := inner_meilisearch.NewIndexer(url, apiKey, indexerName, issueIndexerLatestVersion)
indexer := &Indexer{
inner: inner,
Indexer: inner,
}
return indexer
}
// Index will save the index data
func (b *Indexer) Index(_ context.Context, issues []*internal.IndexerData) error {
if len(issues) == 0 {
return nil
}
for _, issue := range issues {
_, err := b.inner.Client.Index(b.inner.VersionedIndexName()).AddDocuments(issue)
if err != nil {
return err
}
}
// TODO: bulk send index data
return nil
}
// Delete deletes indexes by ids
func (b *Indexer) Delete(_ context.Context, ids ...int64) error {
if len(ids) == 0 {
return nil
}
for _, id := range ids {
_, err := b.inner.Client.Index(b.inner.VersionedIndexName()).DeleteDocument(strconv.FormatInt(id, 10))
if err != nil {
return err
}
}
// TODO: bulk send deletes
return nil
}
// Search searches for issues by given conditions.
// Returns the matching issue IDs
func (b *Indexer) Search(ctx context.Context, keyword string, repoIDs []int64, limit, start int) (*internal.SearchResult, error) {
repoFilters := make([]string, 0, len(repoIDs))
for _, repoID := range repoIDs {
repoFilters = append(repoFilters, "repo_id = "+strconv.FormatInt(repoID, 10))
}
filter := strings.Join(repoFilters, " OR ")
searchRes, err := b.inner.Client.Index(b.inner.VersionedIndexName()).Search(keyword, &meilisearch.SearchRequest{
Filter: filter,
Limit: int64(limit),
Offset: int64(start),
})
if err != nil {
return nil, err
}
hits := make([]internal.Match, 0, len(searchRes.Hits))
for _, hit := range searchRes.Hits {
hits = append(hits, internal.Match{
ID: int64(hit.(map[string]any)["id"].(float64)),
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 12:37:56 +00:00
})
}
return &internal.SearchResult{
Total: searchRes.TotalHits,
Hits: hits,
}, nil
}