Sync main, develop branch history

.github/workflows/ci-java.yml

@@ -15,21 +15,47 @@ on:
       - ".github/workflows/ci-java.yml"
 
 permissions:
-  contents: read
+  contents: write   # Dependency graph 생성용
   packages: write
   security-events: write
   checks: write
   pull-requests: write
   pages: write      # GitHub Pages 배포
   id-token: write   # GitHub Pages 배포
+  actions: write
 
 jobs:
+  dependency-submission:
+    if: github.event_name != 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout sources
+        uses: actions/checkout@v4
+
+      - name: Setup Java
+        uses: actions/setup-java@v4
+        with:
+          distribution: 'temurin'
+          java-version: '21'
+
+      - name: Generate and submit dependency graph
+        uses: gradle/actions/dependency-submission@v4
+        with:
+          build-root-directory: apps/user-service
+
   spotless-check:
     if: github.event.pull_request.draft == false
     name: Lint Check
     runs-on: ubuntu-latest
 
     steps:
+      - name: Debug cache settings
+        run: |
+          echo "Event name: ${{ github.event_name }}"
+          echo "Event type: ${{ github.event.action }}"
+          echo "Cache read-only condition: ${{ github.event_name == 'pull_request' }}"
+          echo "GitHub ref: ${{ github.ref }}"
+
       - name: Checkout repository
         uses: actions/checkout@v4
 
@@ -44,6 +70,11 @@ jobs:
         uses: gradle/actions/setup-gradle@v3
         with:
           cache-read-only: ${{ github.event_name == 'pull_request' }}
+          gradle-home-cache-cleanup: false
+          gradle-home-cache-includes: |
+            caches
+            notifications
+            wrapper
 
       - name: Grant execute permission for Gradle wrapper
         run: chmod +x ./gradlew
@@ -73,7 +104,7 @@ jobs:
           distribution: 'temurin'
 
       - name: Setup Gradle
-        uses: gradle/actions/setup-gradle@v3
+        uses: gradle/actions/setup-gradle@v4
         with:
           cache-read-only: ${{ github.event_name == 'pull_request' }}
 

.github/workflows/deploy-java.yml

@@ -79,7 +79,7 @@ jobs:
           source: "docker/production/promtail-config.yml"
           target: "~/app"
 
-      - name: Copy promtail-config to EC2
+      - name: Copy agent-config to EC2
         uses: appleboy/[email protected]
         with:
           host: ${{ secrets.SERVER_HOST }}
@@ -89,6 +89,26 @@ jobs:
           target: "~/app"
           overwrite: true
 
+      - name: Copy application-production.yml to EC2
+        uses: appleboy/[email protected]
+        with:
+          host: ${{ secrets.SERVER_HOST }}
+          username: ubuntu
+          key: ${{ secrets.SERVER_SSH_KEY }}
+          source: "apps/user-service/src/main/resources/application-production.yml"
+          target: "~/app/docker/production/config/application-production.yml"
+          overwrite: true
+
+      - name: Copy log4j2-production.yml to EC2
+        uses: appleboy/[email protected]
+        with:
+          host: ${{ secrets.SERVER_HOST }}
+          username: ubuntu
+          key: ${{ secrets.SERVER_SSH_KEY }}
+          source: "apps/user-service/src/main/resources/log4j2-production.yml"
+          target: "~/app/docker/production/config/log4j2-production.yml"
+          overwrite: true
+
       - name: Deploy on EC2
         uses: appleboy/[email protected]
         with:

apps/pre-processing-service/Dockerfile

@@ -2,13 +2,11 @@
 FROM python:3.11-slim AS builder
 WORKDIR /app
 
-# 필수 OS 패키지 (기존 + Chrome 설치용 패키지 추가)
+# 필수 OS 패키지 설치
 RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
-    wget \
-    unzip \
-    gnupg \
     ca-certificates \
+    build-essential \
   && rm -rf /var/lib/apt/lists/*
 
 # Poetry 설치
@@ -20,16 +18,15 @@ RUN poetry self add "poetry-plugin-export>=1.7.0"
 RUN python -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
-# 의존성 해결 → requirements로 export → pip로 설치(= 반드시 /opt/venv에 설치됨)
+# poetry → requirements로 export → pip로 설치
 COPY pyproject.toml poetry.lock ./
 RUN poetry export --without dev -f requirements.txt -o requirements.txt \
  && pip install --no-cache-dir -r requirements.txt
-
 # ---- runtime ----
 FROM python:3.11-slim AS final
 WORKDIR /app
 
-# Chrome과 ChromeDriver 설치를 위한 패키지 설치
+# Chrome과 ChromeDriver 설치를 위한 패키지 설치 (삭제 예정 - 마운트 방식)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     wget \
     unzip \
@@ -38,22 +35,22 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     ca-certificates \
     && rm -rf /var/lib/apt/lists/*
 
-# Chrome 설치 (블로그 방식 - 직접 .deb 파일 다운로드)
+# Chrome 설치 (삭제 예정 - 마운트 방식)
 RUN wget -q https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb \
     && apt-get update \
     && apt-get install -y ./google-chrome-stable_current_amd64.deb \
     && rm ./google-chrome-stable_current_amd64.deb \
     && rm -rf /var/lib/apt/lists/*
 
-# MeCab & 사전 설치 (형태소 분석 의존)
+# MeCab & 사전 설치 (삭제 예정 - 마운트 방식)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     mecab \
     libmecab-dev \
     wget \
     build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# 한국어 사전 수동 설치
+# 한국어 사전 수동 설치 (삭제 예정 - 마운트 방식)
 RUN cd /tmp && \
     wget https://bitbucket.org/eunjeon/mecab-ko-dic/downloads/mecab-ko-dic-2.1.1-20180720.tar.gz && \
     tar -zxf mecab-ko-dic-2.1.1-20180720.tar.gz && \
@@ -70,5 +67,5 @@ ENV PATH="/opt/venv/bin:$PATH"
 # 앱 소스
 COPY . .
 
-# (권장 대안) 코드에서 uvicorn import 안 하고 프로세스 매니저로 실행하려면:
-ENTRYPOINT ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "app.main:app", "-b", "0.0.0.0:8000", "--timeout", "120"]
+# gunicorn으로 FastAPI 앱 실행 - 타임아웃 240초 설정
+ENTRYPOINT ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "app.main:app", "-b", "0.0.0.0:8000", "--timeout", "240"]

apps/pre-processing-service/app/api/endpoints/blog.py

@@ -10,10 +10,27 @@
 from app.utils.response import Response
 from app.service.blog.blog_create_service import BlogContentService
 from app.service.blog.blog_publish_service import BlogPublishService
+from app.service.ocr.S3OCRProcessor import S3OCRProcessor
 
 router = APIRouter()
 
 
+@router.post(
+    "/ocr/extract",
+    response_model=ResponseImageTextExtract,
+    summary="S3 이미지에서 텍스트 추출 및 번역",
+)
+async def ocr_extract(request: RequestImageTextExtract):
+    """
+    S3 이미지에서 텍스트 추출 및 번역
+    """
+    processor = S3OCRProcessor(request.keyword)
+
+    result = processor.process_images()
+
+    return Response.ok(result)
+
+
 @router.post(
     "/rag/create",
     response_model=ResponseBlogCreate,

apps/pre-processing-service/app/core/config.py

@@ -106,6 +106,9 @@ class BaseSettingsConfig(BaseSettings):
     # 테스트/추가용 필드
     OPENAI_API_KEY: Optional[str] = None  # << 이 부분 추가
 
+    # OCR 번역기 설정
+    google_application_credentials: Optional[str] = None
+
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 

apps/pre-processing-service/app/model/schemas.py

@@ -186,6 +186,13 @@ class S3ImageInfo(BaseModel):
         ..., title="원본 URL", description="크롤링된 원본 이미지 URL"
     )
     s3_url: str = Field(..., title="S3 URL", description="S3에서 접근 가능한 URL")
+    # 새로 추가: 파일 크기 정보 (이미지 선별용)
+    file_size_kb: Optional[float] = Field(
+        None, title="파일 크기(KB)", description="이미지 파일 크기"
+    )
+    file_name: Optional[str] = Field(
+        None, title="파일명", description="S3에 저장된 파일명"
+    )
 
 
 # 상품별 S3 업로드 결과
@@ -274,14 +281,18 @@ class RequestBlogCreate(RequestBase):
     keyword: Optional[str] = Field(
         None, title="키워드", description="콘텐츠 생성용 키워드"
     )
+    translation_language: Optional[str] = Field(
+        None,
+        title="번역한 언어",
+        description="이미지에서 중국어를 한국어로 번역한 언어",
+    )
     product_info: Optional[Dict] = Field(
         None, title="상품 정보", description="블로그 콘텐츠에 포함할 상품 정보"
     )
-    content_type: Optional[str] = Field(
-        None, title="콘텐츠 타입", description="생성할 콘텐츠 유형"
-    )
-    target_length: Optional[int] = Field(
-        None, title="목표 글자 수", description="생성할 콘텐츠의 목표 길이"
+    uploaded_images: Optional[List[Dict]] = Field(
+        None,
+        title="업로드된 이미지",
+        description="S3에 업로드된 이미지 목록 (크기 정보 포함)",
     )
 
 
@@ -301,6 +312,29 @@ class ResponseBlogCreate(ResponseBase[BlogCreateData]):
     pass
 
 
+# ================== 이미지에서 텍스트 추출 및 번역 ==================
+class RequestImageTextExtract(RequestBase):
+    keyword: Optional[str] = Field(
+        ..., title="키워드", description="텍스트 추출용 키워드"
+    )
+
+
+class ImageTextExtract(BaseModel):
+    keyword: Optional[str] = Field(
+        ..., title="키워드", description="텍스트 추출용 키워드"
+    )
+    extraction_language: str = Field(
+        ..., title="추출된 텍스트", description="이미지에서 추출된 텍스트"
+    )
+    translation_language: str = Field(
+        ..., title="번역된 텍스트", description="추출된 텍스트의 번역본"
+    )
+
+
+class ResponseImageTextExtract(ResponseBase[ImageTextExtract]):
+    pass
+
+
 # ============== 블로그 배포 ==============