mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2025-05-14 05:52:43 +00:00
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>
This commit is contained in:
parent
b0215c40cd
commit
375fd15fbf
43 changed files with 1374 additions and 1426 deletions
|
@ -9,6 +9,7 @@ import (
|
|||
"strings"
|
||||
|
||||
"code.gitea.io/gitea/modules/highlight"
|
||||
"code.gitea.io/gitea/modules/indexer/code/internal"
|
||||
"code.gitea.io/gitea/modules/timeutil"
|
||||
"code.gitea.io/gitea/modules/util"
|
||||
)
|
||||
|
@ -25,6 +26,8 @@ type Result struct {
|
|||
FormattedLines string
|
||||
}
|
||||
|
||||
type SearchResultLanguages = internal.SearchResultLanguages
|
||||
|
||||
func indices(content string, selectionStartIndex, selectionEndIndex int) (int, int) {
|
||||
startIndex := selectionStartIndex
|
||||
numLinesBefore := 0
|
||||
|
@ -61,7 +64,7 @@ func writeStrings(buf *bytes.Buffer, strs ...string) error {
|
|||
return nil
|
||||
}
|
||||
|
||||
func searchResult(result *SearchResult, startIndex, endIndex int) (*Result, error) {
|
||||
func searchResult(result *internal.SearchResult, startIndex, endIndex int) (*Result, error) {
|
||||
startLineNum := 1 + strings.Count(result.Content[:startIndex], "\n")
|
||||
|
||||
var formattedLinesBuffer bytes.Buffer
|
||||
|
@ -109,12 +112,12 @@ func searchResult(result *SearchResult, startIndex, endIndex int) (*Result, erro
|
|||
}
|
||||
|
||||
// PerformSearch perform a search on a repository
|
||||
func PerformSearch(ctx context.Context, repoIDs []int64, language, keyword string, page, pageSize int, isMatch bool) (int, []*Result, []*SearchResultLanguages, error) {
|
||||
func PerformSearch(ctx context.Context, repoIDs []int64, language, keyword string, page, pageSize int, isMatch bool) (int, []*Result, []*internal.SearchResultLanguages, error) {
|
||||
if len(keyword) == 0 {
|
||||
return 0, nil, nil, nil
|
||||
}
|
||||
|
||||
total, results, resultLanguages, err := indexer.Search(ctx, repoIDs, language, keyword, page, pageSize, isMatch)
|
||||
total, results, resultLanguages, err := (*globalIndexer.Load()).Search(ctx, repoIDs, language, keyword, page, pageSize, isMatch)
|
||||
if err != nil {
|
||||
return 0, nil, nil, err
|
||||
}
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue