2021-06-08 23:33:54 +00:00
|
|
|
// Copyright 2021 The Gitea Authors. All rights reserved.
|
2022-11-27 18:20:29 +00:00
|
|
|
// SPDX-License-Identifier: MIT
|
2021-06-08 23:33:54 +00:00
|
|
|
|
|
|
|
package explore
|
|
|
|
|
|
|
|
import (
|
|
|
|
"net/http"
|
|
|
|
|
2024-03-16 10:32:45 +00:00
|
|
|
"code.gitea.io/gitea/models/db"
|
2021-12-10 01:27:50 +00:00
|
|
|
repo_model "code.gitea.io/gitea/models/repo"
|
2021-06-08 23:33:54 +00:00
|
|
|
"code.gitea.io/gitea/modules/base"
|
|
|
|
code_indexer "code.gitea.io/gitea/modules/indexer/code"
|
|
|
|
"code.gitea.io/gitea/modules/setting"
|
2024-02-27 07:12:22 +00:00
|
|
|
"code.gitea.io/gitea/services/context"
|
2021-06-08 23:33:54 +00:00
|
|
|
)
|
|
|
|
|
|
|
|
const (
|
|
|
|
// tplExploreCode explore code page template
|
|
|
|
tplExploreCode base.TplName = "explore/code"
|
|
|
|
)
|
|
|
|
|
|
|
|
// Code render explore code page
|
|
|
|
func Code(ctx *context.Context) {
|
|
|
|
if !setting.Indexer.RepoIndexerEnabled {
|
2022-03-23 04:54:07 +00:00
|
|
|
ctx.Redirect(setting.AppSubURL + "/explore")
|
2021-06-08 23:33:54 +00:00
|
|
|
return
|
|
|
|
}
|
|
|
|
|
|
|
|
ctx.Data["UsersIsDisabled"] = setting.Service.Explore.DisableUsersPage
|
|
|
|
ctx.Data["IsRepoIndexerEnabled"] = setting.Indexer.RepoIndexerEnabled
|
|
|
|
ctx.Data["Title"] = ctx.Tr("explore")
|
|
|
|
ctx.Data["PageIsExplore"] = true
|
|
|
|
ctx.Data["PageIsExploreCode"] = true
|
|
|
|
|
2021-08-11 15:08:52 +00:00
|
|
|
language := ctx.FormTrim("l")
|
|
|
|
keyword := ctx.FormTrim("q")
|
2022-10-10 23:12:03 +00:00
|
|
|
|
2024-08-27 15:23:02 +00:00
|
|
|
isFuzzy := ctx.FormOptionalBool("fuzzy").ValueOrDefault(true)
|
2024-08-16 13:23:25 +00:00
|
|
|
if mode := ctx.FormTrim("mode"); len(mode) > 0 {
|
|
|
|
isFuzzy = mode == "fuzzy"
|
|
|
|
}
|
2022-10-10 23:12:03 +00:00
|
|
|
|
|
|
|
ctx.Data["Keyword"] = keyword
|
|
|
|
ctx.Data["Language"] = language
|
2024-08-16 13:23:25 +00:00
|
|
|
ctx.Data["CodeSearchOptions"] = []string{"exact", "fuzzy"}
|
|
|
|
if isFuzzy {
|
|
|
|
ctx.Data["CodeSearchMode"] = "fuzzy"
|
|
|
|
} else {
|
|
|
|
ctx.Data["CodeSearchMode"] = "exact"
|
|
|
|
}
|
2022-10-10 23:12:03 +00:00
|
|
|
ctx.Data["PageIsViewCode"] = true
|
|
|
|
|
|
|
|
if keyword == "" {
|
|
|
|
ctx.HTML(http.StatusOK, tplExploreCode)
|
|
|
|
return
|
|
|
|
}
|
|
|
|
|
2021-07-29 01:42:15 +00:00
|
|
|
page := ctx.FormInt("page")
|
2021-06-08 23:33:54 +00:00
|
|
|
if page <= 0 {
|
|
|
|
page = 1
|
|
|
|
}
|
|
|
|
|
2022-10-10 23:12:03 +00:00
|
|
|
var (
|
|
|
|
repoIDs []int64
|
|
|
|
err error
|
|
|
|
isAdmin bool
|
|
|
|
)
|
|
|
|
if ctx.Doer != nil {
|
|
|
|
isAdmin = ctx.Doer.IsAdmin
|
|
|
|
}
|
2021-06-08 23:33:54 +00:00
|
|
|
|
2022-10-10 23:12:03 +00:00
|
|
|
// guest user or non-admin user
|
|
|
|
if ctx.Doer == nil || !isAdmin {
|
|
|
|
repoIDs, err = repo_model.FindUserCodeAccessibleRepoIDs(ctx, ctx.Doer)
|
|
|
|
if err != nil {
|
|
|
|
ctx.ServerError("FindUserCodeAccessibleRepoIDs", err)
|
|
|
|
return
|
2021-06-08 23:33:54 +00:00
|
|
|
}
|
2022-10-10 23:12:03 +00:00
|
|
|
}
|
2021-06-08 23:33:54 +00:00
|
|
|
|
2022-10-10 23:12:03 +00:00
|
|
|
var (
|
|
|
|
total int
|
|
|
|
searchResults []*code_indexer.Result
|
|
|
|
searchResultLanguages []*code_indexer.SearchResultLanguages
|
|
|
|
)
|
|
|
|
|
|
|
|
if (len(repoIDs) > 0) || isAdmin {
|
2024-03-16 10:32:45 +00:00
|
|
|
total, searchResults, searchResultLanguages, err = code_indexer.PerformSearch(ctx, &code_indexer.SearchOptions{
|
|
|
|
RepoIDs: repoIDs,
|
|
|
|
Keyword: keyword,
|
|
|
|
IsKeywordFuzzy: isFuzzy,
|
|
|
|
Language: language,
|
|
|
|
Paginator: &db.ListOptions{
|
|
|
|
Page: page,
|
|
|
|
PageSize: setting.UI.RepoSearchPagingNum,
|
|
|
|
},
|
|
|
|
})
|
2022-10-10 23:12:03 +00:00
|
|
|
if err != 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 12:37:56 +00:00
|
|
|
if code_indexer.IsAvailable(ctx) {
|
2022-01-27 08:30:51 +00:00
|
|
|
ctx.ServerError("SearchResults", err)
|
|
|
|
return
|
|
|
|
}
|
2022-10-10 23:12:03 +00:00
|
|
|
ctx.Data["CodeIndexerUnavailable"] = true
|
|
|
|
} else {
|
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
|
|
|
ctx.Data["CodeIndexerUnavailable"] = !code_indexer.IsAvailable(ctx)
|
2021-06-08 23:33:54 +00:00
|
|
|
}
|
2022-06-15 23:24:10 +00:00
|
|
|
|
2022-10-10 23:12:03 +00:00
|
|
|
loadRepoIDs := make([]int64, 0, len(searchResults))
|
|
|
|
for _, result := range searchResults {
|
|
|
|
var find bool
|
|
|
|
for _, id := range loadRepoIDs {
|
|
|
|
if id == result.RepoID {
|
|
|
|
find = true
|
|
|
|
break
|
2022-06-15 23:24:10 +00:00
|
|
|
}
|
2022-01-27 08:30:51 +00:00
|
|
|
}
|
2022-10-10 23:12:03 +00:00
|
|
|
if !find {
|
|
|
|
loadRepoIDs = append(loadRepoIDs, result.RepoID)
|
2021-06-08 23:33:54 +00:00
|
|
|
}
|
2022-10-10 23:12:03 +00:00
|
|
|
}
|
2021-06-08 23:33:54 +00:00
|
|
|
|
2023-10-11 04:24:07 +00:00
|
|
|
repoMaps, err := repo_model.GetRepositoriesMapByIDs(ctx, loadRepoIDs)
|
2022-10-10 23:12:03 +00:00
|
|
|
if err != nil {
|
|
|
|
ctx.ServerError("GetRepositoriesMapByIDs", err)
|
|
|
|
return
|
2021-06-08 23:33:54 +00:00
|
|
|
}
|
|
|
|
|
2022-10-10 23:12:03 +00:00
|
|
|
ctx.Data["RepoMaps"] = repoMaps
|
2022-10-22 09:23:20 +00:00
|
|
|
|
|
|
|
if len(loadRepoIDs) != len(repoMaps) {
|
|
|
|
// Remove deleted repos from search results
|
|
|
|
cleanedSearchResults := make([]*code_indexer.Result, 0, len(repoMaps))
|
|
|
|
for _, sr := range searchResults {
|
|
|
|
if _, found := repoMaps[sr.RepoID]; found {
|
|
|
|
cleanedSearchResults = append(cleanedSearchResults, sr)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
searchResults = cleanedSearchResults
|
|
|
|
}
|
2021-06-08 23:33:54 +00:00
|
|
|
}
|
|
|
|
|
2022-10-10 23:12:03 +00:00
|
|
|
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
|
|
|
|
|
2021-06-08 23:33:54 +00:00
|
|
|
ctx.HTML(http.StatusOK, tplExploreCode)
|
|
|
|
}
|