1
0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-11-23 08:47:42 -05:00
forgejo/routers/web/user/code.go
Jason Song 375fd15fbf
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

114 lines
2.8 KiB
Go

// Copyright 2022 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package user
import (
"net/http"
repo_model "code.gitea.io/gitea/models/repo"
"code.gitea.io/gitea/modules/base"
"code.gitea.io/gitea/modules/context"
code_indexer "code.gitea.io/gitea/modules/indexer/code"
"code.gitea.io/gitea/modules/setting"
)
const (
tplUserCode base.TplName = "user/code"
)
// CodeSearch render user/organization code search page
func CodeSearch(ctx *context.Context) {
if !setting.Indexer.RepoIndexerEnabled {
ctx.Redirect(ctx.ContextUser.HomeLink())
return
}
ctx.Data["IsProjectEnabled"] = true
ctx.Data["IsPackageEnabled"] = setting.Packages.Enabled
ctx.Data["IsRepoIndexerEnabled"] = setting.Indexer.RepoIndexerEnabled
ctx.Data["Title"] = ctx.Tr("explore.code")
ctx.Data["ContextUser"] = ctx.ContextUser
language := ctx.FormTrim("l")
keyword := ctx.FormTrim("q")
queryType := ctx.FormTrim("t")
isMatch := queryType == "match"
ctx.Data["Keyword"] = keyword
ctx.Data["Language"] = language
ctx.Data["queryType"] = queryType
ctx.Data["IsCodePage"] = true
if keyword == "" {
ctx.HTML(http.StatusOK, tplUserCode)
return
}
var (
repoIDs []int64
err error
)
page := ctx.FormInt("page")
if page <= 0 {
page = 1
}
repoIDs, err = repo_model.FindUserCodeAccessibleOwnerRepoIDs(ctx, ctx.ContextUser.ID, ctx.Doer)
if err != nil {
ctx.ServerError("FindUserCodeAccessibleOwnerRepoIDs", err)
return
}
var (
total int
searchResults []*code_indexer.Result
searchResultLanguages []*code_indexer.SearchResultLanguages
)
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(ctx) {
ctx.ServerError("SearchResults", err)
return
}
ctx.Data["CodeIndexerUnavailable"] = true
} else {
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable(ctx)
}
loadRepoIDs := make([]int64, 0, len(searchResults))
for _, result := range searchResults {
var find bool
for _, id := range loadRepoIDs {
if id == result.RepoID {
find = true
break
}
}
if !find {
loadRepoIDs = append(loadRepoIDs, result.RepoID)
}
}
repoMaps, err := repo_model.GetRepositoriesMapByIDs(loadRepoIDs)
if err != nil {
ctx.ServerError("GetRepositoriesMapByIDs", err)
return
}
ctx.Data["RepoMaps"] = repoMaps
}
ctx.Data["SearchResults"] = searchResults
ctx.Data["SearchResultLanguages"] = searchResultLanguages
pager := context.NewPagination(total, setting.UI.RepoSearchPagingNum, page, 5)
pager.SetDefaultParams(ctx)
pager.AddParam(ctx, "l", "Language")
ctx.Data["Page"] = pager
ctx.HTML(http.StatusOK, tplUserCode)
}