1
1
mirror of https://github.com/go-gitea/gitea synced 2024-12-27 02:54:27 +00:00
gitea/modules/indexer/issues/db/db.go
Jason Song 1e76a824bc
Refactor and enhance issue indexer to support both searching, filtering and paging (#26012)
Fix #24662.

Replace #24822 and #25708 (although it has been merged)


## Background

In the past, Gitea supported issue searching with a keyword and
conditions in a less efficient way. It worked by searching for issues
with the keyword and obtaining limited IDs (as it is heavy to get all)
on the indexer (bleve/elasticsearch/meilisearch), and then querying with
conditions on the database to find a subset of the found IDs. This is
why the results could be incomplete.

To solve this issue, we need to store all fields that could be used as
conditions in the indexer and support both keyword and additional
conditions when searching with the indexer.

## Major changes

- Redefine `IndexerData` to include all fields that could be used as
filter conditions.
- Refactor `Search(ctx context.Context, kw string, repoIDs []int64,
limit, start int, state string)` to `Search(ctx context.Context, options
*SearchOptions)`, so it supports more conditions now.
- Change the data type stored in `issueIndexerQueue`. Use
`IndexerMetadata` instead of `IndexerData` in case the data has been
updated while it is in the queue. This also reduces the storage size of
the queue.
- Enhance searching with Bleve/Elasticsearch/Meilisearch, make them
fully support `SearchOptions`. Also, update the data versions.
- Keep most logic of database indexer, but remove
`issues.SearchIssueIDsByKeyword` in `models` to avoid confusion where is
the entry point to search issues.
- Start a Meilisearch instance to test it in unit tests.
- Add unit tests with almost full coverage to test
Bleve/Elasticsearch/Meilisearch indexer.

---------

Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
2023-07-31 06:28:53 +00:00

97 lines
2.9 KiB
Go

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package db
import (
"context"
"code.gitea.io/gitea/models/db"
issue_model "code.gitea.io/gitea/models/issues"
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
inner_db "code.gitea.io/gitea/modules/indexer/internal/db"
"code.gitea.io/gitea/modules/indexer/issues/internal"
"xorm.io/builder"
)
var _ internal.Indexer = &Indexer{}
// Indexer implements Indexer interface to use database's like search
type Indexer struct {
indexer_internal.Indexer
}
func NewIndexer() *Indexer {
return &Indexer{
Indexer: &inner_db.Indexer{},
}
}
// Index dummy function
func (i *Indexer) Index(_ context.Context, _ ...*internal.IndexerData) error {
return nil
}
// Delete dummy function
func (i *Indexer) Delete(_ context.Context, _ ...int64) error {
return nil
}
// Search searches for issues
func (i *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (*internal.SearchResult, error) {
// FIXME: I tried to avoid importing models here, but it seems to be impossible.
// We can provide a function to register the search function, so models/issues can register it.
// So models/issues will import modules/indexer/issues, it's OK because it's by design.
// But modules/indexer/issues has already imported models/issues to do UpdateRepoIndexer and UpdateIssueIndexer.
// And to avoid circular import, we have to move the functions to another package.
// I believe it should be services/indexer, sounds great!
// But the two functions are used in modules/notification/indexer, that means we will import services/indexer in modules/notification/indexer.
// So that's the root problem:
// The notification is defined in modules, but it's using lots of things should be in services.
cond := builder.NewCond()
if options.Keyword != "" {
repoCond := builder.In("repo_id", options.RepoIDs)
if len(options.RepoIDs) == 1 {
repoCond = builder.Eq{"repo_id": options.RepoIDs[0]}
}
subQuery := builder.Select("id").From("issue").Where(repoCond)
cond = builder.Or(
db.BuildCaseInsensitiveLike("issue.name", options.Keyword),
db.BuildCaseInsensitiveLike("issue.content", options.Keyword),
builder.In("issue.id", builder.Select("issue_id").
From("comment").
Where(builder.And(
builder.Eq{"type": issue_model.CommentTypeComment},
builder.In("issue_id", subQuery),
db.BuildCaseInsensitiveLike("content", options.Keyword),
)),
),
)
}
opt, err := ToDBOptions(ctx, options)
if err != nil {
return nil, err
}
ids, total, err := issue_model.IssueIDs(ctx, opt, cond)
if err != nil {
return nil, err
}
hits := make([]internal.Match, 0, len(ids))
for _, id := range ids {
hits = append(hits, internal.Match{
ID: id,
})
}
return &internal.SearchResult{
Total: total,
Hits: hits,
}, nil
}