Merged
Conversation
Walkthrough폴더 응답 DTO에 Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant FolderService
participant FolderItemRepository
participant FolderResponse as FolderResponse Factory
Client->>FolderService: getFolders()
FolderService->>FolderService: 폴더 목록 조회
loop 각 폴더별
FolderService->>FolderItemRepository: countByFolderFolderId(folderId)
FolderItemRepository-->>FolderService: itemCount (Long)
FolderService->>FolderResponse: from(folder, itemCount)
FolderResponse-->>FolderService: FolderResponse with itemCount
end
FolderService-->>Client: List<FolderResponse> (itemCount 포함)
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes 📋 리뷰 의견좋은 점:
주의할 점:
전체적으로는 간단하고 명확한 변경으로, 리뷰 부담이 적습니다! 👍 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In
`@src/main/java/com/finsight/finsight/domain/storage/domain/service/FolderService.java`:
- Around line 35-43: getFolders in FolderService triggers an N+1 by calling
FolderItemRepository.countByFolderFolderId for each FolderEntity; add a bulk
counting query to FolderItemRepository (e.g. a method like countByFolderIds that
returns folderId->count for a list of IDs) and change FolderService.getFolders
to: fetch folders, collect their folderIds, call the new bulk count method once,
map counts into a lookup, then stream folders and call
FolderResponse.from(folder, itemCountLookup.get(folder.getFolderId())); this
reduces queries to two and avoids the per-folder count calls.
Comment on lines
35
to
43
| public List<FolderResponse> getFolders(Long userId, FolderType folderType) { | ||
| List<FolderEntity> folders = folderRepository.findByUserUserIdAndFolderTypeOrderBySortOrderAsc(userId, folderType); | ||
| return folders.stream() | ||
| .map(FolderResponse::from) | ||
| .map(folder -> { | ||
| long itemCount = folderItemRepository.countByFolderFolderId(folder.getFolderId()); | ||
| return FolderResponse.from(folder, itemCount); | ||
| }) | ||
| .toList(); | ||
| } |
There was a problem hiding this comment.
현재 getFolders에서 폴더 리스트를 조회한 후, 각 폴더마다 countByFolderFolderId를 개별 호출하고 있습니다. 사용자가 폴더를 10개 가지고 있다면, 폴더 목록 조회 1회 + 카운트 조회 10회 = 총 11번의 쿼리가 실행됩니다. updateFolderOrder (Line 141)도 getFolders를 호출하므로 동일한 문제가 전파됩니다.
권장 해결 방법: 한 번의 쿼리로 모든 폴더의 아이템 개수를 한꺼번에 가져오는 방식으로 개선할 수 있습니다.
🔧 제안하는 수정 방법
1단계: FolderItemRepository에 벌크 카운트 쿼리 추가
`@Query`("SELECT fi.folder.folderId, COUNT(fi) FROM FolderItemEntity fi WHERE fi.folder.folderId IN :folderIds GROUP BY fi.folder.folderId")
List<Object[]> countByFolderIds(`@Param`("folderIds") List<Long> folderIds);2단계: FolderService.getFolders 수정
public List<FolderResponse> getFolders(Long userId, FolderType folderType) {
List<FolderEntity> folders = folderRepository.findByUserUserIdAndFolderTypeOrderBySortOrderAsc(userId, folderType);
+
+ List<Long> folderIds = folders.stream()
+ .map(FolderEntity::getFolderId)
+ .toList();
+
+ Map<Long, Long> itemCountMap = folderItemRepository.countByFolderIds(folderIds).stream()
+ .collect(Collectors.toMap(
+ row -> (Long) row[0],
+ row -> (Long) row[1]
+ ));
+
return folders.stream()
- .map(folder -> {
- long itemCount = folderItemRepository.countByFolderFolderId(folder.getFolderId());
- return FolderResponse.from(folder, itemCount);
- })
+ .map(folder -> FolderResponse.from(folder, itemCountMap.getOrDefault(folder.getFolderId(), 0L)))
.toList();
}이렇게 하면 폴더 개수와 관계없이 항상 2번의 쿼리로 처리됩니다.
As per coding guidelines, "JPA 사용 시 N+1 문제나 불필요한 쿼리가 발생하지 않는지 체크한다."
🤖 Prompt for AI Agents
In
`@src/main/java/com/finsight/finsight/domain/storage/domain/service/FolderService.java`
around lines 35 - 43, getFolders in FolderService triggers an N+1 by calling
FolderItemRepository.countByFolderFolderId for each FolderEntity; add a bulk
counting query to FolderItemRepository (e.g. a method like countByFolderIds that
returns folderId->count for a list of IDs) and change FolderService.getFolders
to: fetch folders, collect their folderIds, call the new bulk count method once,
map counts into a lookup, then stream folders and call
FolderResponse.from(folder, itemCountLookup.get(folder.getFolderId())); this
reduces queries to two and avoids the per-folder count calls.
9 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
📍 PR 타입 (하나 이상 선택)
❗️ 관련 이슈 링크
Close #72
📌 개요
사용자 폴더 조회 응답에 저장된 뉴스, 단어 개수 추가
🔁 변경 사항
Folder Response itemCount 필드 추가
Folder Repository 메서드 ( countByFolderFolderId ) 추가
Folder Service 응답 코드 수정
📸 스크린샷
👀 기타 더 이야기해볼 점
✅ 체크 리스트
Summary by CodeRabbit
릴리스 노트