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 - [x] Fix outdated example config.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
|
@ -79,13 +79,13 @@ func Code(ctx *context.Context) {
|
|||
if (len(repoIDs) > 0) || isAdmin {
|
||||
total, searchResults, searchResultLanguages, err = code_indexer.PerformSearch(ctx, repoIDs, language, keyword, page, setting.UI.RepoSearchPagingNum, isMatch)
|
||||
if err != nil {
|
||||
if code_indexer.IsAvailable() {
|
||||
if code_indexer.IsAvailable(ctx) {
|
||||
ctx.ServerError("SearchResults", err)
|
||||
return
|
||||
}
|
||||
ctx.Data["CodeIndexerUnavailable"] = true
|
||||
} else {
|
||||
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable()
|
||||
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable(ctx)
|
||||
}
|
||||
|
||||
loadRepoIDs := make([]int64, 0, len(searchResults))
|
||||
|
|
|
@ -191,7 +191,7 @@ func issues(ctx *context.Context, milestoneID, projectID int64, isPullOption uti
|
|||
if len(keyword) > 0 {
|
||||
issueIDs, err = issue_indexer.SearchIssuesByKeyword(ctx, []int64{repo.ID}, keyword)
|
||||
if err != nil {
|
||||
if issue_indexer.IsAvailable() {
|
||||
if issue_indexer.IsAvailable(ctx) {
|
||||
ctx.ServerError("issueIndexer.Search", err)
|
||||
return
|
||||
}
|
||||
|
|
|
@ -45,13 +45,13 @@ func Search(ctx *context.Context) {
|
|||
total, searchResults, searchResultLanguages, err := code_indexer.PerformSearch(ctx, []int64{ctx.Repo.Repository.ID},
|
||||
language, keyword, page, setting.UI.RepoSearchPagingNum, isMatch)
|
||||
if err != nil {
|
||||
if code_indexer.IsAvailable() {
|
||||
if code_indexer.IsAvailable(ctx) {
|
||||
ctx.ServerError("SearchResults", err)
|
||||
return
|
||||
}
|
||||
ctx.Data["CodeIndexerUnavailable"] = true
|
||||
} else {
|
||||
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable()
|
||||
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable(ctx)
|
||||
}
|
||||
|
||||
ctx.Data["SourcePath"] = ctx.Repo.Repository.Link()
|
||||
|
|
|
@ -71,13 +71,13 @@ func CodeSearch(ctx *context.Context) {
|
|||
if len(repoIDs) > 0 {
|
||||
total, searchResults, searchResultLanguages, err = code_indexer.PerformSearch(ctx, repoIDs, language, keyword, page, setting.UI.RepoSearchPagingNum, isMatch)
|
||||
if err != nil {
|
||||
if code_indexer.IsAvailable() {
|
||||
if code_indexer.IsAvailable(ctx) {
|
||||
ctx.ServerError("SearchResults", err)
|
||||
return
|
||||
}
|
||||
ctx.Data["CodeIndexerUnavailable"] = true
|
||||
} else {
|
||||
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable()
|
||||
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable(ctx)
|
||||
}
|
||||
|
||||
loadRepoIDs := make([]int64, 0, len(searchResults))
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue