From 0aa937b91a7d9be8f72110b8dd10507b4c045c82 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Wed, 25 Mar 2026 18:42:37 +0900
Subject: [PATCH 1/8] =?UTF-8?q?develop=20=EB=B8=8C=EB=9E=9C=EC=B9=98?=
 =?UTF-8?q?=EC=99=80=20=ED=86=B5=ED=95=A9=20=EB=B0=8F=20=EC=A0=95=EB=A6=AC?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 최근 develop 브랜치 내용과 통합
- docsinfos 테이블 연동 서버 독립 (포트 8002)
---
 EasyDOC-frontend/easydoc-parser/main.py       |  44 ++++++++-
 .../easydoc-parser/requirements.txt           |   5 +
 EasyDOC-frontend/package-lock.json            |   9 ++
 EasyDOC-frontend/src/pages/Viewer.jsx         |  87 +++++++++++++-----
 backend-OCR/ocr_server.py                     |  57 ++++++++++--
 backend-OCR/requirements.txt                  | Bin 186 -> 256 bytes
 database_document/__init__.py                 |   0
 .../__pycache__/__init__.cpython-310.pyc      | Bin 0 -> 162 bytes
 .../__pycache__/__init__.cpython-314.pyc      | Bin 0 -> 168 bytes
 .../__pycache__/database.cpython-310.pyc      | Bin 0 -> 1973 bytes
 .../__pycache__/database.cpython-314.pyc      | Bin 0 -> 2917 bytes
 .../__pycache__/document_api.cpython-314.pyc  | Bin 0 -> 4807 bytes
 database_document/database.py                 |  56 +++++++++++
 database_document/document_api.py             |  78 ++++++++++++++++
 database_document/requirements.txt            |   8 ++
 database_document/schema.sql                  |  13 +++
 16 files changed, 318 insertions(+), 39 deletions(-)
 create mode 100644 database_document/__init__.py
 create mode 100644 database_document/__pycache__/__init__.cpython-310.pyc
 create mode 100644 database_document/__pycache__/__init__.cpython-314.pyc
 create mode 100644 database_document/__pycache__/database.cpython-310.pyc
 create mode 100644 database_document/__pycache__/database.cpython-314.pyc
 create mode 100644 database_document/__pycache__/document_api.cpython-314.pyc
 create mode 100644 database_document/database.py
 create mode 100644 database_document/document_api.py
 create mode 100644 database_document/requirements.txt
 create mode 100644 database_document/schema.sql

diff --git a/EasyDOC-frontend/easydoc-parser/main.py b/EasyDOC-frontend/easydoc-parser/main.py
index b2f0805..922a539 100644
--- a/EasyDOC-frontend/easydoc-parser/main.py
+++ b/EasyDOC-frontend/easydoc-parser/main.py
@@ -1,4 +1,6 @@
-from fastapi import FastAPI, UploadFile, File
+from fastapi import FastAPI, UploadFile, File, Depends
+from sqlalchemy.orm import Session
+import sys
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 from typing import List, Optional
@@ -31,6 +33,16 @@
 if _env_files:
     print(f"✓ .env 로드 완료: {[str(f) for f in _env_files]}")
 
+# --- DB 공유를 위한 경로 설정 ---
+current_file_path = Path(__file__).resolve()
+root_dir = current_file_path.parent.parent.parent
+
+if str(root_dir) not in sys.path:
+    sys.path.append(str(root_dir))
+
+from database_document.database import get_db, Document
+# -----------------------------
+
 app = FastAPI()
 
 app.add_middleware(
@@ -191,8 +203,8 @@ async def parse_hwp(file: UploadFile = File(...)):
 
 
 @app.get("/parse/s3/{file_key:path}")
-async def parse_from_s3(file_key: str):
-    """S3에서 파일 가져와서 파싱"""
+async def parse_from_s3(file_key: str, db: Session = Depends(get_db)):
+    """S3에서 파일 가져와서 파싱 및 DB 저장"""
     print(f"[DEBUG] 파싱 요청 받음 - 파일 키: {file_key}")
     print(f"[DEBUG] 버킷: {BUCKET_NAME}")
     try:
@@ -212,7 +224,6 @@ async def parse_from_s3(file_key: str):
                     page_text = page.extract_text()
                     if page_text:
                         text += page_text + "\n"
-            return {"filename": filename, "text": text}
         
         elif ext == "hwp":
             ole = olefile.OleFileIO(io.BytesIO(contents))
@@ -222,10 +233,33 @@ async def parse_from_s3(file_key: str):
             else:
                 text = "텍스트를 추출할 수 없습니다."
             ole.close()
-            return {"filename": filename, "text": text.strip()}
+            text = text.strip()
         
         else:
             return {"error": "지원하지 않는 파일 형식입니다."}
+
+        # ================= [새로 추가] DB 저장 로직 =================
+        # S3 URL 조립
+        s3_url = f"https://{BUCKET_NAME}.s3.{os.getenv('AWS_DEFAULT_REGION')}.amazonaws.com/{file_key}"
+
+        # DB 모델 생성
+        new_doc = Document(
+            file_name=filename,
+            file_type=ext,
+            s3_url=s3_url,
+            extracted_text=text
+        )
+
+        # DB에 추가 및 커밋
+        db.add(new_doc)
+        db.commit()
+        db.refresh(new_doc)
+
+        print(f"[DEBUG] DB 저장 성공! (문서 번호: {new_doc.id})")
+        # ========================================================
+
+        # 저장된 ID와 함께 프론트엔드로 응답
+        return {"id": new_doc.id, "filename": filename, "text": text}
     
     except Exception as e:
         return {"error": str(e)}
diff --git a/EasyDOC-frontend/easydoc-parser/requirements.txt b/EasyDOC-frontend/easydoc-parser/requirements.txt
index 3435f10..7186df7 100644
--- a/EasyDOC-frontend/easydoc-parser/requirements.txt
+++ b/EasyDOC-frontend/easydoc-parser/requirements.txt
@@ -6,3 +6,8 @@ python-dotenv==1.0.0
 boto3==1.34.34
 google-generativeai==0.8.3
 pandas==2.2.0
+sqlalchemy
+pymysql
+cryptography
+google-cloud-aiplatform
+python-multipart
\ No newline at end of file
diff --git a/EasyDOC-frontend/package-lock.json b/EasyDOC-frontend/package-lock.json
index 08d9e63..abc4204 100644
--- a/EasyDOC-frontend/package-lock.json
+++ b/EasyDOC-frontend/package-lock.json
@@ -58,6 +58,7 @@
       "integrity": "sha512-e7jT4DxYvIDLk1ZHmU/m/mB19rex9sv0c2ftBtjSBv+kVM/902eh0fINUzD7UwLLNR+jU585GxUJ8/EBfAM5fw==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "@babel/code-frame": "^7.27.1",
         "@babel/generator": "^7.28.5",
@@ -1704,6 +1705,7 @@
       "integrity": "sha512-MWtvHrGZLFttgeEj28VXHxpmwYbor/ATPYbBfSFZEIRK0ecCFLl2Qo55z52Hss+UV9CRN7trSeq1zbgx7YDWWg==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "csstype": "^3.2.2"
       }
@@ -1752,6 +1754,7 @@
       "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "bin": {
         "acorn": "bin/acorn"
       },
@@ -1884,6 +1887,7 @@
         }
       ],
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "baseline-browser-mapping": "^2.9.0",
         "caniuse-lite": "^1.0.30001759",
@@ -2253,6 +2257,7 @@
       "integrity": "sha512-LEyamqS7W5HB3ujJyvi0HQK/dtVINZvd5mAAp9eT5S/ujByGjiZLCzPcHVzuXbpJDJF/cxwHlfceVUDZ2lnSTw==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "@eslint-community/eslint-utils": "^4.8.0",
         "@eslint-community/regexpp": "^4.12.1",
@@ -3198,6 +3203,7 @@
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -3275,6 +3281,7 @@
       "resolved": "https://registry.npmjs.org/react/-/react-19.2.3.tgz",
       "integrity": "sha512-Ku/hhYbVjOQnXDZFv2+RibmLFGwFdeeKHFcOTlrt7xplBnya5OGn/hIRDsqDiSUcfORsDC7MPxwork8jBwsIWA==",
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=0.10.0"
       }
@@ -3565,6 +3572,7 @@
       "integrity": "sha512-w+N7Hifpc3gRjZ63vYBXA56dvvRlNWRczTdmCBBa+CotUzAPf5b7YMdMR/8CQoeYE5LX3W4wj6RYTgonm1b9DA==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "esbuild": "^0.27.0",
         "fdir": "^6.5.0",
@@ -3686,6 +3694,7 @@
       "integrity": "sha512-k7Nwx6vuWx1IJ9Bjuf4Zt1PEllcwe7cls3VNzm4CQ1/hgtFUK2bRNG3rvnpPUhFjmqJKAKtjV576KnUkHocg/g==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "funding": {
         "url": "https://github.com/sponsors/colinhacks"
       }
diff --git a/EasyDOC-frontend/src/pages/Viewer.jsx b/EasyDOC-frontend/src/pages/Viewer.jsx
index add2068..03268bc 100644
--- a/EasyDOC-frontend/src/pages/Viewer.jsx
+++ b/EasyDOC-frontend/src/pages/Viewer.jsx
@@ -74,12 +74,8 @@ export default function Viewer({ parsedData, ocrData, pdfFileUrl }) {
     const [isPdf, setIsPdf] = useState(false);
 
     // 최근 문서 목록 상태
-    const [recentDocs, setRecentDocs] = useState([
-        {id: 1, title: '행정기본법.pdf', date: '2024.11.14'},
-        {id: 2, title: '조세특례제한법.pdf', date: '2024.11.13'},
-        {id: 3, title: '도시및주거환경지정비법.pdf', date: '2024.11.13'},
-        {id: 4, title: '건축법시행령.pdf', date: '2024.11.12'},
-    ]);
+    const [recentDocs, setRecentDocs] = useState([]);
+    const [selectedDoc, setSelectedDoc] = useState(null); // 현재 선택된 문서 상세 정보
 
     // 파일 선택을 위한 ref
     const fileInputRef = useRef(null);
@@ -126,8 +122,60 @@ export default function Viewer({ parsedData, ocrData, pdfFileUrl }) {
       setPendingSelectedText(null);
     };
 
+    // docsinfos DB에서 최근 문서 목록 가져오기
+    useEffect(() => {
+      fetchDocuments();
+    }, []);
+
+    const fetchDocuments = async () => {
+        try {
+            const response = await axios.get('http://localhost:8002/api/documents');
+            setRecentDocs(response.data);
+        } catch (error) {
+            console.error("문서 목록 로딩 실패:", error);
+        }
+    };
+
+    // 사이드바에서 문서 클릭 시 상세 내용 가져오기
+    const handleDocClick = async (id) => {
+        try {
+            setIsLoading(true);
+            const response = await axios.get(`http://localhost:8002/api/documents/${id}`);
+
+            const docData = response.data;
+
+            setSelectedDoc(docData); // 선택된 문서 상태 업데이트
+            //setPdfUrl(null); // PDF 뷰어에서 텍스트 모드로 전환
+            setDocumentName(docData.file_name); // AgentChat용 문서 이름 업데이트
+
+            // 가져온 텍스트를 뷰어 상태에 반영
+            setParsedText(docData.text || "");
+            setOcrText("");
+
+            if (docData.s3_url) {
+              setPdfUrl(docData.s3_url);
+              const isPdfFile = docData.file_type?.toLowerCase() === 'pdf' ||
+                docData.file_name?.toLowerCase().endsWith('.pdf');
+                setIsPdf(isPdfFile);
+            }
+        } catch (error) {
+            console.error("문서 상세 로딩 실패:", error);
+            alert("문서 내용을 불러올 수 없습니다.");
+        } finally {
+            setIsLoading(false);
+        }
+    };
+
+    // 날짜 형식 변환 함수 (2024-11-14 -> 2024.11.14)
+    const formatDate = (dateString) => {
+      if (!dateString) return "";
+      return dateString.substring(0, 10).replace(/-/g, '.');
+    };
+
     // props로 받은 데이터를 상태에 반영 (Upload에서 넘어올 때)
     useEffect(() => {
+      if (selectedDoc) return;
+
         if (parsedData) {
             console.log("Viewer가 받은 parsedData:", parsedData);
             setParsedText(parsedData.text || "");
@@ -143,7 +191,7 @@ export default function Viewer({ parsedData, ocrData, pdfFileUrl }) {
             setPdfUrl(pdfFileUrl);
             setIsPdf(true);
         }
-    }, [parsedData, ocrData, pdfFileUrl]);
+    }, [parsedData, ocrData, pdfFileUrl, selectedDoc]);
 
     // 버튼 클릭 시 숨겨진 input 실행
     const handleUploadBtnClick = () => {
@@ -231,20 +279,7 @@ const handleFileChange = async (e) => {
     }
 
     // 최근 문서 목록 업데이트
-    const newDoc = {
-      id: Date.now(),
-      title: file.name,
-      date: new Date().toLocaleDateString("ko-KR", {
-        year: "numeric",
-        month:"2-digit",
-        day: "2-digit",
-      })
-      .replace(/\. /g, ".")
-      .replace(".", "")
-    };
-
-    const filteredDocs = recentDocs.filter((doc) => doc.title != file.name);
-    setRecentDocs([newDoc, ...filteredDocs].slice(0, 10));
+   await fetchDocuments();
 
   } catch (error) {
     console.error("파일 처리 오류:", error);
@@ -290,14 +325,18 @@ const handleFileChange = async (e) => {
           </div>
           <ul className="doc-list">
             {recentDocs.map((doc) => (
-              <li key={doc.id} className="doc-item">
+              <li 
+                key={doc.id} 
+                className={`doc-item ${selectedDoc && selectedDoc.id === doc.id ? "active" : ""}`}
+                onClick={() => handleDocClick(doc.id)}
+              >
                 <div className="doc-info">
                   <div className="doc-icon-box">
                     <FileText size={18} />
                   </div>
                   <div className="doc-text">
-                    <span className="doc-title">{doc.title}</span>
-                    <span className="doc-date">{doc.date}</span>
+                    <span className="doc-title">{doc.file_name}</span>
+                    <span className="doc-date">{formatDate(doc.created_at)}</span>
                   </div>
                 </div>
                 <ChevronRight size={16} color="#9ca3af" />
diff --git a/backend-OCR/ocr_server.py b/backend-OCR/ocr_server.py
index c8da17f..95adb61 100644
--- a/backend-OCR/ocr_server.py
+++ b/backend-OCR/ocr_server.py
@@ -1,18 +1,28 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, Depends
 from fastapi.middleware.cors import CORSMiddleware
 import boto3
 import os
+import sys
 from urllib.parse import unquote
 from ocr_logic import EasyDocOCR
 from dotenv import load_dotenv
+from sqlalchemy.orm import Session
+from pathlib import Path  # 추가됨
+
+# --- DB 공유를 위한 경로 설정 ---
+current_file_path = Path(__file__).resolve()
+root_dir = current_file_path.parent.parent
+
+if str(root_dir) not in sys.path:
+    sys.path.append(str(root_dir))
+# ---------------------------------------------
+
+from database_document.database import get_db, Document  
 
 load_dotenv()
 
 app = FastAPI()
 
-# Google Cloud 인증 키 위치 지정
-os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "google-key.json"
-
 # CORS 설정
 app.add_middleware(
     CORSMiddleware,
@@ -22,7 +32,8 @@
     allow_headers=["*"],
 )
 
-# OCR 엔진 로딩
+# 설정 및 연결
+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "google-key.json" # Google Cloud 인증 키 위치 지정   
 ocr_engine = EasyDocOCR()
 
 # .env 파일에서 AWS 설정값 불러오기
@@ -39,10 +50,10 @@
     region_name=AWS_REGION
 )
 
-# 프론트엔드 요청에 맞게 GET 방식으로 주소 변경
+# db: Session = Depends(get_db)를 추가하여 API가 호출될 때마다 DB와 통신할 수 있는 세션 할당
 @app.get("/ocr/s3/{filename}")
-def run_ocr(filename: str):
-    #URL에 포함된 암호화된 파일명(예: %ED%95...)을 정상적인 글자로 변환
+def run_ocr(filename: str, db: Session = Depends(get_db)):
+    # URL에 포함된 암호화된 파일명(예: %ED%95...)을 정상적인 글자로 변환
     decoded_filename = unquote(filename)
 
     # 로컬에 다운로드할 임시 경로
@@ -58,8 +69,34 @@ def run_ocr(filename: str):
         text_result = ocr_engine.extract_text(local_path)
         print(f"분석 완료: {text_result[:30]}...")
 
-        #프론트엔드에서 ocrResponse.data.text로 받을 수 있도록 반환형식 수정
-        return {"text": text_result}
+        # ================= DB 저장 로직 =================
+        # 1. S3 URL 주소 조립
+        s3_url = f"https://{BUCKET_NAME}.s3.{AWS_REGION}.amazonaws.com/{filename}"
+
+        # 2. 파일명에서 확장자(예: png, jpg) 추출
+        file_extension = decoded_filename.split('.')[-1] if '.' in decoded_filename else "unknown"
+
+        # 3. DB에 넣을 데이터 포장 (INSERT 문과 동일한 역할)
+        new_doc = Document(
+            file_name = decoded_filename,
+            file_type = file_extension,
+            s3_url = s3_url,
+            extracted_text=text_result
+        )
+
+        # 4. DB에 추가하고 저장
+        db.add(new_doc)
+        db.commit()
+        db.refresh(new_doc) #MySQL이 방금 발급해준 고유 ID 번호를 가져온다
+
+        print(f"DB 저장 성공! (문서 번호: {new_doc.id})")
+        # ===================================================
+
+        # 프론트엔드에 추출 텍스트와 함께 부여된 문서 번호 반환
+        return {
+            "id": new_doc.id,
+            "text": text_result
+        }
 
     except Exception as e:
         print(f"에러 발생: {e}")
diff --git a/backend-OCR/requirements.txt b/backend-OCR/requirements.txt
index 3ecdd39bdd58d092ac423e97eec576c670ad489b..c00b79edcafe5a18169084aa92603d43ba49f0ca 100644
GIT binary patch
delta 77
zcmdnR*uXSlmm4nw7eg^aAwv#BA`mAtWH6*M<T6w;fW!-cG>8q62Z<yz6ao1K3?&Tt
O4Cz32B9NT{6afH#R}YZ@

delta 6
NcmZo*+Qm3w7XSy<0*C+r

diff --git a/database_document/__init__.py b/database_document/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/database_document/__pycache__/__init__.cpython-310.pyc b/database_document/__pycache__/__init__.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..9a4c6669fcaa13f6fea4f218781cc183ab613cf3
GIT binary patch
literal 162
zcmd1j<>g`kg3`{7nIQTxh(HF6K#l_t7qb9~6oz01O-8?!3`HPe1o6w&*(xTqIJKxa
zrZ}rO%OJ)jKe;qFHLs*N#yzvdqckbTHL<wT#osw5C9xziDX};;J_V{GCO$qhFS8^*
aUaz3?7Kcr4eoARhsvXGqVkRKL!T<nCZ6~Jy

literal 0
HcmV?d00001

diff --git a/database_document/__pycache__/__init__.cpython-314.pyc b/database_document/__pycache__/__init__.cpython-314.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..0d82d438f15b9733088672872c0cc3de7cb16b81
GIT binary patch
literal 168
zcmdPq<K<!ig3`{7nIQTxh=2h`DC095kkP;p#GuTe$>_I|p@<2{{|u76<?3t|6Iz^F
zR2);BRh(rI<C33Tnwy$eQXJ!+S>jQe6yus$T<PNP9Fvk*l9-fOoEo13RS^>(pP83g
m5+AQuP<e~PCO1E&G$+-rh!tom$lhWQ;}bI@BV!RWkOcrn2`RMz

literal 0
HcmV?d00001

diff --git a/database_document/__pycache__/database.cpython-310.pyc b/database_document/__pycache__/database.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..47b1a0f5bd82edf2b058bd8dfa753b4dfa72f4ef
GIT binary patch
literal 1973
zcmY*ZTW=Fb6rR~#ukH0E#)O0<1Pla-ixg04B@|IgNKBy0t+6R|6tr6JjFSy}ac0&b
zjzDVVJeG%wr>dYP>QjG5|HVAEFOBFg$V+=>%_Zz;&U|O)oSCy{zBy5$U?KRXfBVzB
zoJQzxr5yiqpxl8jLW~ea6#FQ^1P2<?0-flAL5v_pQh`a#AWhO(*=T+y$dYVe5i8Mk
zKNsXlKEZ}x2nwW-;FMn^MX)#hfuKZ6$z0k$5tK<8BUWN3dw75F0BxQkL+gkPv(q%w
z!*l3KnT)U@njJ%Al#T9>9U#8ShWF2~(E|*AL&|<@mJNethK#c^8>be{z0@$;dd!A-
zo1LY3TA;-}q-=WlS40Qi=so3I+&@Q42bfe6bOO-%1eF0@NYF_@7ZWrHXo8+%74RQo
z=Rpp$3kkjm@-&+OIr1h)E-}n5^)R{2EILX@*=0KRQYTkfwui{%Jfdgl_#UF;Y_g}5
zDm_cj?IH3RP1RAga;R>inwABZGbd&?3)j7nNpm*xJ3%PZ55kzOGcL_~%)M}38V$A+
z%WUJpVy)hoSzM9EH}&PEswPX6xxT}l*xP1y(-BPO1rx%H!oYdTcooac!t&C5qxQI=
zFonZnFJMcc7%NV^0b|aO9BR`jX5sc>3gX%|rT{iz_gsJ0ZiA)FMB9vWkFw4sF#7BD
zs|xJqs57V9-RX+*sk}XS{r1)C%D=ztz5V^C%A^a_`tWIh4Cu4a#UO}v^c+1gU*H%$
z$36VBwx!k49|$7SMa<!JZR)zjEnWuGL>$#-r`H||#>JZ06r0!A<|4NfurL;D^Im+v
z(_E`LqC2-dyY@aX_^ZCfhZzV}TDN>p#BLO{Z=X`JsK5phABN!wS7mzcuKloHTa`Hg
zD>L=_qvh4PWcL1Yy^(;G<<&k|npv#vmV&O>@~^hL$vA!O+7X^U!gr4FwcXO!?uNq!
zi@)l`t(!sfi+fdFT23d9;P}9UD^<AVcf^J?nqEj<2;!4ZUC15if`VX(V2X%FG0~a9
zQdEPc1L;iA($wf-nxf`Qjbsu%-GjW6Y=Yr|0k#0=V9di<fUyYU04r^tpjq%LQwzwM
zlbQF4C0R(I@WNIk5<0ZG7dX6YKV@B+f@s;!;eQa;Jw>gs<NHq2XNRA|jQ5WY{Khg(
zS<C78@ly4q%-DA51kARjW!phSJHEns+urIp{=1ceZ3Crz)>k=fg1F+0)I7>nDrC0h
zfuCA`2jgxV9*($Sceu}0QG=h_iMiv(jM}k+8Ra)Xy;jR}Ar|{t#Hrv=6A{m=C9@N|
zVf2hx{l`dcC;mvfJ{nTS6CkcY7mAS?WZ<G!!g**JXl0zNe{z3{{pxTvDJDVuh+@=3
zFVL>_9DRo{dIT?EA0GgssQv*zgUqS7ov-&_@<QY~zD&7(BpBpWqs?RCsmP?c&SIN3
zZ>V!r)z^M7u?9g6Y5XRr)vMA1hC05x!GbPVeE*o*B(2<3b4f~)Y!yG6PenZ7S+%To
zCL_mIsOR|1jm1<#{3QAPjB1gPX;n0QugMGGCe3~&;YFnY6OvoBWtuY)`P*=TZHL24
zmT6lshr1iV5vV7LnUE>&gzHRV#T?fOsi(@AG}#V3V<Ana-DV+`y3JZL1r&vCR6@X?
zkEpmul^9dvj1uD@$Z-AJg_(uf`?baI?YWu8%-xxK&3?GL0J|oon12aY(zpxNExFeu
zkH^xU6s08hnOl7>-&VIRra?@g_q0&tC~C$#idc#$S`i!CD7JJ9_uGV?(Tmu`B|V@2
EALLXEf&c&j

literal 0
HcmV?d00001

diff --git a/database_document/__pycache__/database.cpython-314.pyc b/database_document/__pycache__/database.cpython-314.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..be6e399be7cdedd87fe90f9ed699b8976c3b9fd9
GIT binary patch
literal 2917
zcmahLTTC3+_0GO#clOD10UHAbY_FZ-*bqCAqz+*4uFYdTyVQ=vcslG1F!AhzJ9jZS
zKdUIJ9H+ID@<Sy{P1SyouhO3=pSJSj&!tcSx3$u=KaJcEySCI+s??r4%PdY+x3ija
z&+DFh?s?6g2n7WM&%n>W)Q|88{h1N=<KIJ`ed|D|gsvfxOQ1MMxVVEj;!fg>yNE09
zChoY0c;Y<a+nA0c;f?!<FD?+lqMZqUJU{{#?n(sXK@zlZcOpbWpzle9;}H_EczmKJ
zUQ24*kQC`aQe7Wc@gNzqUD{v!_R!?<eV&bx#vVkXQd0-I=C*A_(C9gYNVC)^dS9_`
z1{+9=)RH`F@7!N)`$zX!YAr$skrYk#@9Wr@)MB3ko;Ut?k1h=&<U@zR0(cUHb6cfa
zxMQp66NR%7U-q=2OJQ59dTyt6?x7AO`q|zoRCM&fI|_FwAgQeb{Q%jgPdF}tWp+x@
zQ9uDC22ML|8F&^-zHJ@z9RPNNwhrldsZOY>bNHn?;i^vOOLZbuovxSa)Kqo4#agKY
z?olTl23Rk3T6h=02B{lh<7q!RB5@GMBh@`eB?0af6{FHovFWU{a#?ar@^v6PrzF;Z
zK&Ls1#1<*mXX_jn4@40;A-X#uer;9^brd`J4KoqrX)uE|g=n&to6~a|^$h2YVm3$l
zM2={48m68U!Fq0vy3*Pbp}urtd?b|~98Xf$#nj|P%t0fnmN68p5PeaTXB1PT0aG(g
zJ)g@e*EJmDsCR5~;zD}lYMS9H97go4HUWeysgQYC{YG9<Wi?N<+~Q4F55P1S_E#8k
z0hFjWzo=oXt6H%e{QlFum3A<su;Y3P%LDCfPy6Fv+<Uxoul=t-`{3~}f82hIaxu!E
zACjk1BO>(!k{nE>u1t#OEpB`=m9~)Nq*y^F2FFKkMzYK1f^nj-Y^?()Pf~7xa&J@a
z<ju&r%)Ek4jl5MPv#)1o`bJ|;Dkw#g&*ZaN9fHH~S)*vqQ`d~1Q!|w;RiI~&cvc3a
zgd{{b5fR6=qr@q4#3i{Q-5${aKW8<)yv6lG!~e@J1kokB?ZzU$s{FJqw^t(AGSOr6
z?3MT}S)fV>EqcEh!WJEoYLZ<qUZH}EeD(Y~(M#$@UnhzQ)O$XkDQ2}Cgh9<`Og%T7
zH?1rdu%1=$vV2`zrf!IewlvD>AXhXDWya9-zd)e^gIBd#rD%}P&_t|(dSyAMWHni)
zf-GnAYSCbLK$aJZim@jN%kr#_O=3XZ=JFs8$}*IMp;hGA1^!|;0P4_H%;HadvpN`J
z@;#I+7og_NUb%=39AGLTD08f2h^ESfp+3e8tNQG$o&opd8+ojn*b7_?QwdQ|kz{iD
z8&s(Dkt!>MHpsF`pdm6qK=;fPiDt?&W|jL4UPMQR2d1Y?4V%;EyXL#EPTR3Fr!VLv
zUYwa8QOxD@lf%<?kwbG-qFd!a+2b~_WdSx;O%=e8&`y0@Y5Z$n_+$Rl^m_f4?@VcE
zH`4gY;%a8)y|t;WNN*`op=VZZZbl9R6|DPYbhU3~Y%|zV8r^L;uo~ZN=q^p{HXd9}
zuNbAt-J0mCZ|(J8pZo0GR?Qn9T*PePSjT>+z*)FE;eECU;4n=65}Mxo(xK{%Dxd=}
z*_Tj>YlAfjssGQ%o@Q-G1as{u{eQG{^oFw)>D+5hor`g7AO%vD@iUgsC<b+BjJ&Bq
zfjQI}lljw*Ujs-za~hG=89V?)FTCb40N;SqfABSYbf`4+#Nl+;?Svw?y?^uycfB8a
z?+D-Caxmm4!avP=P=4Rv&)so#p`X_FbHA!R<NVy&&&6J$0?ZG^$jocmWz6okUx!u=
zV)#FTD)nQPR%l<nCy%q3{c*wUOHP|#kf^$1Xc=PmSYyem)Jpj|@+Rfkgf#RS9Aeu%
zm9dH8n~PW<StT!19&2XaScGaXD44Y=FPoZzGxN}4Fgz_ale)2zo6{)A`Yxm7RGp1$
z>d}^TlbF<_6bf2SrA}F!rEX|!Fyk}{d?X;4U<B7O=UHrU0|Si=L;=uf>hjp&*l>Jg
z{2lrHV0v(9Ff}4iiDO{e`tD%%Uxm7cV4hd1nxzGj#?4wed$p1?@0*oT@O_*DF-xX-
z9pDou$8lew^fpRwp!8R${}JkWgj#=(e2-AmBXsC%A#`i$qn>S{eM4y96b^3-u?-<s
z;&+1KlCbLw-CDTQR2tl=X<9w=yPA&D#T~w8n{V3So3{Cu-|{Ux-r8+%^M<#1_4t;z
zdneRzH}_%g{R>ZhNT_`lK!L{6@UAPoI=t4k?K=6?35>sckSnz7@|6Rp9t>=ro_H|u
zh4P!;^@Y#RJQ&zGJyAY2`Ea2uT;6htPdvyUyc@e6`#7;F90Hd@k-PeBeKoilI#TlQ
z2!R)6|APWMt>0U_vX)rCy#C&L_Wr5+SMDbsUVeDvp<cdnwfxQx%U6}MvQTcpWfXnt
zK|-_~?b-C5EO~ar2R<!+;l4k*6~0so?DEk~zPaRj?(uPN-XhNtEYF+VT-`tZ_7>`$
P<V-e3zx33MoE82Jw2{BZ

literal 0
HcmV?d00001

diff --git a/database_document/__pycache__/document_api.cpython-314.pyc b/database_document/__pycache__/document_api.cpython-314.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3f56aedd3a9ee1a92707922abb8dd088bc2f2430
GIT binary patch
literal 4807
zcmd5=U2Gf25#IaZzer26CF(EMuN6~C$e?oKzr;x;+aaOaX3w@_H=?g6@+4hCk<8vQ
ziBvR@6ScBq6tNK_R*M8}Q5Us=0Cf?k@Iz5F=tE!nK!O4&Z)zk(AA(dWK-X!~0)6Q0
zl1Iss>=furSK!|M%+Ait&Nn-&hkRZ)g7V(mzc+sELg+87V-;tmafgZs&7f0A5h5ro
z5FsoQF)R_OosEeRIcy^~-j*Wvu!A^wTaGxxF5=>CTf|M=Kx>b9!ZoC(9mQ%oQOvtT
zDDMz`z}j-<yQ9)1n_`=y9V_EjYojqz7pn)pbr#>4JKAf}uY7mIu8A&$+R(=H(ZC9=
z)w-Ln#h>fuh%|&7Nn_Yg{NX0j6mBNXpkH&;Qov#X-{{U&ok}y-q&Rn0>;UV8PNcXL
zw>3iAVr|jA8?3S^o}i%A@S3%}J8fmEcGQ4?htH3cO)=LFsXR)y0-vYW^HFLoU1Abg
zuF>lC3rZbusQ05}ZBnpQAszSNve{a<j>{I{(y)e0CvZ8ifh^VC*KzR!m!>sbx??>`
z^R5$cmTl}T!MkjcZDd<)Tl5?2d4q0kN{iB}wC$`|q#fwH`7iLmXKX=0qK<=_NxmM9
zP;dCyvFL$U;(CS{=@fPB*E4!5VFm>18$6;MJ!B*jN&RIF>sJNpII5c_P{E{YKr{72
z>4cs<3_Urjk%@pz?c+L86Qk6*KON6b>M26)dTQKA=~QO)jB?aSC8q1G`HuYq9Y=Ni
zl8#}{MhueFsnB-}Sb4Q%GX1ie#s;i6X<fM+$9e+T8d}n{C?<6>kxo>*6S|hru^C@&
z7{D|ycOHh12KbI4A}EN6r#gw$h|*{nffop1btjP(k=TY2u`5zH0y(zqH^#<{cs5C%
zP2+@lJd@Cf9%o)$@nj@Jn_2n}1K<<F3~)Oo?wW<ug3&hgO<_U^p`*fcXs@UUj0X6M
zpD~%}ri8^@eVK7*21*(x35e7_md2ABp<Y#uCpFVd7;&PiCR^4uLnDKGMvj}H=ZN{d
z`TV0JmOagpXABa~j*cAA%&GlH21h_zZ4^weCMqW~Vl`APV+1o(v_@66R4PqCEmftR
z8>t&yP0|Sxn6*&-a}K?RZZ<UM<>tRjND%J87`loM2OQL?swr)f@pG%{WIB;evNr7W
zVpdC5W;Utnn1M}_1oud#VY+VBE@RnL9EKV|V-U=Us~REL7|jyhEK^o(64#SSRSgK3
z1y+-t$<uf%)YxxTTwn+EK;Stvi!dAD)6>2X7$Ia?#JuZRnWg!$_CRB!Lsf(km?@W#
zzz!8RLywAyQOvdjnE<Y3nYzj{wL>4Xin)Qg8LAodC9(_kw^{YhgZ#tg<D$SkFK}Cx
zMHvJAm?%-E=bAENc{z&8Yo?&PYSw<=S?eZTMPx<RsAtt+rMZgl2D?VR>sMG2){3Li
zP4}kB2*W}xIxc3#Aj*md;kL?%3K|wS(ohj#d;{GS5ym&rDkL2ihaN)6g|?!Mlo5vk
z?^&@Oei_kVAyPCF)HP;+>oSj}ZiqdAkp#G6z)5W{W_3J;Ye07V2&;mu3PDAkfMgx3
zqf=B)=w_Ts5V`^~hOH2cq~j))pr&@Ln-En@X13mrjt=f2w2nv63RYDX3oyG$x53Yx
zg=z+U;_<$@>+G(J;Y&johAuZ1JNxsU{nt+v9}DLn3l}_*kG&0NPh6b1^umP~ijBSb
z#@<5X_JTL?vA6c@(R0U3He_?%cA~g2E)=}u`O&f5bEnRb^G7cYUl^W$?n?JBAG!L-
zjke#Je|Yu7R|~#jAecFr^Nufi>Shl83vlk65KLy}5BG)!g7UQgZUlwC1FES;;=6Z2
ziK)n;^eES0eSBOEB}H8EsgMY;lFG2MmpOAgLVT2r6v6CR?*}uspV`7U{StWu`)yWT
zmP+jNo}c&1XscoeXsc-JE2B-gKiaB(T**p+L$$1EvXN&Fqg`Qys_WUlYl?*x@J{i;
z%G|h*-6|thEGm$zD&o$H1`~oJ-2(?Qj5B{-QxqGF1JAWZvBNlv^J~gpp(+W#-`Y_S
zg=9D<$7dJ8VE^a>`la`7EYH5P^z+|zEMNQW^1HJg%V*|0mM?vO`Hc^j&Yf90cR6@f
zq#hR9v!)t{EP~n-I?;^e3YMr$^j8RGhZk^Rc90xwa4#B3qGL`-ZTtqo%)dAQsgJGE
z;tZxM%O$*<5ikJa$DlHqFZT9U5V!d*#8t##IU57BISmzH&Rz57_OshB?kc$3itg^b
zyZdtZ7ehZCy7qX!XLrH9r|5n<?|!=A9+(;Y)Z_b;ul0(Q+i_yScQWTZS+XOS_e}iF
zv9n`~&dmU{*oD}l(|2Af)^_D<yB3|z^ZmuvV7@h2Y~7J--Epm}<g(S+OUP!kbLX6X
z;2szY@tol<q%mZ2q&>mq{_l~dNF&UOyo7k>!%@dA2T=>Mh%)dbya#B?m+M!dk0s$I
za|d?GxrC=~v+8nxiG3D=1N{3(2Olk?kV$S8h9<7bzo7wlp7?)&LTOm4`u<m-a9G#~
zYr|5idP9Lm_qq8XXO|S2rxiBL4ii7gs(nyV$0VfT+PI$Wf!^}l*Oz{BdHF}zJC@E}
zfeygzdrLpKw*2n(zrAszV|n&he|`UhfO7>vc!2TYSJohFu~X+LqxN`ua?&7hRdKjH
z!zNZR!{~aeplQtVJXl?mzv3aFVltW<RR0@pK55xnYzgLDf-{2)vVT#w&qYp0W`{nh
zX~_AX%z5_Z<bB+0Sh6{(87Wnrc03y7f5rghSa3(k6KRuBIg`dD@E~=J!IKB_J<Qyy
ztT%Hq>aUCkC#!FrU_6aY%#Mos%omedGCrYCP6Z(&=T{DOW~LGvJVWA`1#K#sQzms}
z;0=^CMlt&@0~3m;4k~rPJ)cg#q|>^17Grq4lqVQ9wP)aA1+OG0PN(7FWME)LFi6ZN
zwG4ZT(Ux^Ne9#)f>=q~|AuQ9vER0hpyofYLVWli8Bp{H5WHQvJB@*h2njFSdf&j>q
z49ub)l`>hv&k=XCt|R-B0oF)S31?H7p_yB~oUJ&YC@1&(@EA<6q||&C>XIY~!pEpT
zkNR(+uiZjjx6sy)koy*Dx@|`d&GSuf9WHL^%Wvr`Y<W0`>J~k1MNfC$(_QrR<vo2f
z&Ob}`nO9zaa$fqe^M}p_sbf)g%!N;f=Z>5{a$#`Z`PQKYx$9GOpnwjPoJg?Ec~5(b
zs40({=EriVX#s76Z5+PbmhB7nz>EX|SdfdTK9A}b<@&|Vjpw&5Hnx<%tW)wJVe{vZ
zfQz5k3PQ{L?$6;d(*m4D+noQjKj&&L2rV~z9=dYyXGgwZdHNj*iLE6OTBZ6bQCC6e
zzS+O$#^dil^#w~W7*S72gjT7oO0>No1a2xPbKm-QLD9ZoagdSql|*Qj8j)OcW_m$t
d{s^R$J##~^4V{<f16O*Aa_F`V$t~RQ{{abx=tlqm

literal 0
HcmV?d00001

diff --git a/database_document/database.py b/database_document/database.py
new file mode 100644
index 0000000..6c549cf
--- /dev/null
+++ b/database_document/database.py
@@ -0,0 +1,56 @@
+from sqlalchemy import create_engine, Column, Integer, String, Text, TIMESTAMP, JSON
+from sqlalchemy.orm import declarative_base, sessionmaker
+from sqlalchemy.dialects.mysql import LONGTEXT
+from datetime import datetime
+import os
+from pathlib import Path
+from dotenv import load_dotenv
+
+_search = Path(__file__).resolve().parent
+_env_files = []
+for _ in range(5):  # 최대 5단계 상위 폴더까지 탐색
+    _candidate = _search / ".env"
+    if _candidate.exists():
+        _env_files.append(_candidate)
+    _search = _search.parent
+
+for _ef in _env_files:
+    load_dotenv(dotenv_path=_ef, override=True)
+
+if _env_files:
+    print(f"✓ database.py: .env 로드 완료 ({[str(f) for f in _env_files]})")
+
+# 환경변수에서 DB 정보 가져오기
+DB_USER = os.getenv("DB_USER")
+DB_PASSWORD = os.getenv("DB_PASSWORD")
+DB_HOST = os.getenv("DB_HOST")
+DB_PORT = os.getenv("DB_PORT")
+DB_NAME = os.getenv("DB_NAME")
+
+# MySQL 연결 주소 만들기 (pymysql)
+SQLALCHEMY_DATABASE_URL = f"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}?charset=utf8mb4"
+
+# DB 엔진 및 세션 생성
+engine = create_engine(SQLALCHEMY_DATABASE_URL)
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+Base = declarative_base()
+
+# 테이블 구조 정의 (MySQL과 1:1 매칭)
+class Document(Base):
+    __tablename__ = "docsinfos"
+
+    id = Column(Integer, primary_key=True, index=True)
+    file_name = Column(String(255), nullable=False)
+    file_type = Column(String(50))
+    s3_url = Column(String(1000))
+    extracted_text = Column(LONGTEXT)
+    difficult_words = Column(JSON)
+    created_at = Column(TIMESTAMP, default=datetime.utcnow)
+
+# DB 연결 세션을 가져오는 함수 (FastAPI에서 사용)
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()
\ No newline at end of file
diff --git a/database_document/document_api.py b/database_document/document_api.py
new file mode 100644
index 0000000..af61130
--- /dev/null
+++ b/database_document/document_api.py
@@ -0,0 +1,78 @@
+from fastapi import FastAPI, HTTPException, Depends
+from fastapi.middleware.cors import CORSMiddleware
+from sqlalchemy.orm import Session
+from pydantic import BaseModel
+import sys
+from pathlib import Path
+
+# --- DB 공유를 위한 경로 설정 ---
+current_file_path = Path(__file__).resolve()
+root_dir = current_file_path.parent.parent 
+
+if str(root_dir) not in sys.path:
+    sys.path.append(str(root_dir))
+
+from database_document.database import get_db, Document, engine, Base
+# ---------------------------------------------
+
+# 정의된 모델을 바탕으로 docsinfos 테이블이 없으면 자동으로 생성
+Base.metadata.create_all(bind=engine)
+
+# 독립적인 FastAPI 앱 생성
+app = FastAPI(title="Document DB Server")
+
+# CORS 설정 (프론트엔드 통신 허용)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+class DifficultWordsUpdate(BaseModel):
+    difficult_words: list
+
+# 전체 문서 목록 조회
+@app.get("/api/documents")
+def get_document_list(db: Session = Depends(get_db)):
+    docs = db.query(Document.id, Document.file_name, Document.created_at)\
+            .order_by(Document.id.desc())\
+            .all()
+
+    result = [{"id": doc.id, "file_name": doc.file_name, "created_at": doc.created_at} for doc in docs]
+    return result
+
+# 특정 문서 상세 조회
+@app.get("/api/documents/{doc_id}")
+def get_document_detail(doc_id: int, db: Session = Depends(get_db)):
+    doc = db.query(Document).filter(Document.id == doc_id).first()
+
+    if not doc:
+        raise HTTPException(status_code=404, detail="문서를 찾을 수 없습니다.")
+
+    return {
+        "id": doc.id,
+        "file_name": doc.file_name,
+        "text": doc.extracted_text,
+        "s3_url": doc.s3_url,        # 원본 PDF 조회를 위해 추가
+        "file_type": doc.file_type,  # PDF 여부 판단을 위해 추가
+        "difficult_words": doc.difficult_words or [] 
+    }
+
+# 어려운 단어 DB에 저장
+@app.put("/api/documents/{doc_id}/words")
+def update_difficult_words(doc_id: int, data: DifficultWordsUpdate, db: Session = Depends(get_db)):
+    doc = db.query(Document).filter(Document.id == doc_id).first()
+
+    if not doc:
+        raise HTTPException(status_code=404, detail="문서를 찾을 수 없습니다.")
+
+    doc.difficult_words = data.difficult_words
+    db.commit()
+
+    return {"message": "어려운 단어 업데이트 성공"}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8002)
\ No newline at end of file
diff --git a/database_document/requirements.txt b/database_document/requirements.txt
new file mode 100644
index 0000000..c542dfb
--- /dev/null
+++ b/database_document/requirements.txt
@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+sqlalchemy
+pymysql
+python-dotenv
+pydantic
+cryptography
+boto3
\ No newline at end of file
diff --git a/database_document/schema.sql b/database_document/schema.sql
new file mode 100644
index 0000000..b87a29b
--- /dev/null
+++ b/database_document/schema.sql
@@ -0,0 +1,13 @@
+-- 1. easydoc 데이터베이스 사용 선언
+USE easydoc;
+
+-- 2. 통합된 문서를 담을 docsinfos 테이블 생성
+CREATE TABLE IF NOT EXISTS docsinfos (
+    id INT AUTO_INCREMENT PRIMARY KEY,				-- 고유 번호 (자동 증가)
+    file_name VARCHAR(255) NOT NULL, 				-- 파일명 (예: 행정기본법.pdf)
+    file_type VARCHAR(50),							-- 확장자 (예: pdf, png)
+    s3_url VARCHAR(1000),							-- S3에 저장된 경로
+    extracted_text LONGTEXT,						-- 추출된 아주 긴 텍스트
+    difficult_words JSON,                           -- 어려운 단어 목록 (JSON 형식)        
+    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP	-- 업로드된 시간 (자동 기록)
+);
\ No newline at end of file

From d0a7d51fac5beb8585522679d64640bd26f7c032 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Fri, 27 Mar 2026 01:46:30 +0900
Subject: [PATCH 2/8] =?UTF-8?q?Upload=20=ED=8E=98=EC=9D=B4=EC=A7=80?=
 =?UTF-8?q?=EC=97=90=20=EC=B5=9C=EA=B7=BC=20=EB=AC=B8=EC=84=9C=20=EB=AA=A9?=
 =?UTF-8?q?=EB=A1=9D=20=EA=B8=B0=EB=8A=A5=20=EC=B6=94=EA=B0=80?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 업로드 페이지에 최근 문서 목록 추가
- 업로드 페이지에서 최근 문서 목록에서 문서를 누르면 바로 Viewer 페이지로 넘어가서 해당 문서 보여주는 기능 추가

- 업로드 페이지의 최근 문서 목록 사이드바에 스크롤 기능 추가
---
 EasyDOC-frontend/src/pages/Upload.css | 26 +++++++-
 EasyDOC-frontend/src/pages/Upload.jsx | 91 +++++++++++++++++++++------
 2 files changed, 95 insertions(+), 22 deletions(-)

diff --git a/EasyDOC-frontend/src/pages/Upload.css b/EasyDOC-frontend/src/pages/Upload.css
index 146a47e..89dbab6 100644
--- a/EasyDOC-frontend/src/pages/Upload.css
+++ b/EasyDOC-frontend/src/pages/Upload.css
@@ -3,7 +3,8 @@
    =============================== */
 .upload-page {
   width: 100vw;
-  min-height: 100vh;
+  height: 100vh;
+  overflow: hidden;
   background: #eef2f7;
   display: flex;
   flex-direction: column;
@@ -79,12 +80,14 @@
   flex-direction: column;
   padding: 24px;
   box-shadow: 2px 0 4px rgba(0, 0, 0, 0.05);
-  overflow-y: auto;
 }
 
 .sidebar-recent {
   display: flex;
   flex-direction: column;
+  flex: 1;
+  overflow: hidden;
+  min-height: 0;
 }
 
 .recent-header {
@@ -101,6 +104,25 @@
   display: flex;
   flex-direction: column;
   gap: 8px;
+  /* 세로 스크롤 추가 */
+  flex: 1;
+  overflow-y: auto;
+  padding-right: 4px;
+}
+
+/* 스크롤바 디자인 추가 */
+.recent-list::-webkit-scrollbar {
+  width: 6px;
+}
+.recent-list::-webkit-scrollbar-track {
+  background: transparent; 
+}
+.recent-list::-webkit-scrollbar-thumb {
+  background: #d1d5db;
+  border-radius: 10px;
+}
+.recent-list::-webkit-scrollbar-thumb:hover {
+  background: #9ca3af;
 }
 
 .recent-item {
diff --git a/EasyDOC-frontend/src/pages/Upload.jsx b/EasyDOC-frontend/src/pages/Upload.jsx
index 44a922a..5d54b43 100644
--- a/EasyDOC-frontend/src/pages/Upload.jsx
+++ b/EasyDOC-frontend/src/pages/Upload.jsx
@@ -1,4 +1,4 @@
-import React, { useState, useRef } from "react";
+import React, { useState, useRef, useEffect } from "react";
 import axios from "axios"; // 통신 라이브러리
 import Viewer from "./Viewer";
 import Loading from "./Loading";
@@ -18,6 +18,69 @@ export default function Upload({onNavigateToMyPage}) {
   // AWS API Gateway 주소
   const API_GATEWAY_URL = "https://28d37e8xg3.execute-api.ap-northeast-2.amazonaws.com/upload-url";
 
+  // 최근 문서 목록 가져오기
+  const fetchRecentDocs = async () => {
+    try {
+      const response = await axios.get('http://localhost:8002/api/documents');
+      
+      // DB 데이터를 화면에 맞게 변환
+      const formattedDocs = response.data.map(doc => {
+        const dateObj = new Date(doc.created_at);
+        return {
+          id: doc.id,
+          name: doc.file_name,
+          date: dateObj.toLocaleDateString("ko-KR", {
+            year: "numeric",
+            month: "2-digit",
+            day: "2-digit",
+          }).replace(/\./g, ".")
+        };
+      });
+      setRecentDocs(formattedDocs);
+    } catch (error) {
+      console.error("최근 문서 목록 로딩 실패:", error);
+    }
+  };
+
+  // 페이지가 처음 열릴 때 목록 가져오기
+  useEffect(() => {
+    fetchRecentDocs();
+  }, []);
+
+  // 최근 문서 목록에서 문서 클릭 시 뷰어 페이지로 이동
+  const handleRecentDocClick = async (docId) => {
+    if (!docId) return; // id가 없으면 무시
+
+    try {
+      setShowLoading(true);
+      const response = await axios.get(`http://localhost:8002/api/documents/${docId}`);
+      const docData = response.data;
+
+      // Viewer.jsx가 알아들을 수 있는 형태로 데이터 세팅
+      setParseResult({
+        id: docData.id,
+        filename: docData.file_name,
+        text: docData.text,
+        difficult_words: docData.difficult_words
+      });
+      setOcrResult(null);
+
+      // S3 주소가 있으면 PDF 원본 주소로 세팅
+      if (docData.s3_url) {
+        setPdfFileUrl(docData.s3_url);
+      } else {
+        setPdfFileUrl(null);
+      }
+
+      setShowLoading(false);
+      setShowViewer(true); // 뷰어 화면으로 전환!
+    } catch (error) {
+      console.error("문서 상세 불러오기 실패:", error);
+      alert("문서를 불러올 수 없습니다.");
+      setShowLoading(false);
+    }
+  };
+
   const handleFileSelect = (e) => {
     const file = e.target.files[0];
     if (file) {
@@ -116,24 +179,7 @@ export default function Upload({onNavigateToMyPage}) {
       // console.log("파싱 결과:", parseResponse.data.text);
 
       // UPDATE: UI 업데이트 (최근 문서 목록에 추가)
-      const fileInfo = {
-        name: selectedFile.name,
-        date: new Date()
-          .toLocaleDateString("ko-KR", {
-            year: "numeric",
-            month: "2-digit",
-            day: "2-digit",
-          })
-          .replace(/\./g, "."),
-      };
-
-      const filteredDocs = recentDocs.filter(
-        (doc) => doc.name !== selectedFile.name
-      );
-      setRecentDocs([fileInfo, ...filteredDocs.slice(0, 9)]);
-
-      // 파일 저장 (나중에 백엔드 API로 대체)
-      //console.log("업로드 성공", selectedFile.name);
+      await fetchRecentDocs();
 
       // 초기화
       setSelectedFile(null);
@@ -203,7 +249,12 @@ export default function Upload({onNavigateToMyPage}) {
             </div>
             <div className="recent-list">
               {recentDocs.map((doc, index) => (
-                <div key={index} className="recent-item">
+                <div 
+                  key={doc.id || index} 
+                  className="recent-item"
+                  onClick={() => handleRecentDocClick(doc.id)}
+                  style={{ cursor: "pointer" }}
+                >
                   <div className="recent-item-icon">
                     {getFileIcon(doc.name) === "pdf" && <PDFIcon />}
                     {getFileIcon(doc.name) === "hwp" && <HWPIcon />}

From 1eec5ef1bdac5c6cf4ba8147c651c6d61bf17133 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Fri, 27 Mar 2026 21:40:17 +0900
Subject: [PATCH 3/8] =?UTF-8?q?MyPage=20=ED=8E=98=EC=9D=B4=EC=A7=80?=
 =?UTF-8?q?=EC=97=90=20=EC=B5=9C=EA=B7=BC=20=EB=AC=B8=EC=84=9C=20=EB=AA=A9?=
 =?UTF-8?q?=EB=A1=9D=20=EC=97=B0=EB=8F=99=20=EC=B6=94=EA=B0=80?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 마이페이지: 변환 이력 화면에 최근 문서 목록 연동 추가
- 문서 칸 자체를 누르거나 눈알 버튼을 누르면 Viewer 페이지로 넘어가서 해당 문서 보여줌
- 다운로드 버튼을 누르면 문서 다운로드
- 프로필 정보에서 변환한 문서 수, 변환한 페이지 수 계산 추가

- docsinfos 테이블 설계에 총 페이지 수, 파일 용량 컬럼 추가
(마이페이지의 목록에서 해당 정보들을 표시하게 되있어서 추가)
- 기존 마이페이지 디자인에서는 파일 용량 표시 단위가 MB였는데 KB로 하향 (파일 크기가 너무 작아서 MB로 하면 0.0으로 표시됨)
---
 EasyDOC-frontend/easydoc-parser/main.py       |  23 ++-
 EasyDOC-frontend/src/pages/MyPage.jsx         | 154 +++++++++++++++++-
 backend-OCR/ocr_server.py                     |  13 +-
 .../__pycache__/database.cpython-310.pyc      | Bin 1973 -> 2029 bytes
 .../__pycache__/database.cpython-314.pyc      | Bin 2917 -> 3015 bytes
 database_document/database.py                 |   2 +
 database_document/document_api.py             |  19 ++-
 database_document/schema.sql                  |   2 +
 8 files changed, 196 insertions(+), 17 deletions(-)

diff --git a/EasyDOC-frontend/easydoc-parser/main.py b/EasyDOC-frontend/easydoc-parser/main.py
index 922a539..c1aa5a9 100644
--- a/EasyDOC-frontend/easydoc-parser/main.py
+++ b/EasyDOC-frontend/easydoc-parser/main.py
@@ -238,7 +238,20 @@ async def parse_from_s3(file_key: str, db: Session = Depends(get_db)):
         else:
             return {"error": "지원하지 않는 파일 형식입니다."}
 
-        # ================= [새로 추가] DB 저장 로직 =================
+        # ================= DB 저장 로직 =================
+        # 파일 크기 계산
+        size_kb = len(contents) / 1024
+        file_size_str = f"{size_kb:.1f} KB"
+
+        # 페이지 수 계산
+        total_pages = 1
+        if ext == "pdf":
+            try:
+                with pdfplumber.open(io.BytesIO(contents)) as pdf:
+                    total_pages = len(pdf.pages)
+            except:
+                total_pages = 1
+        
         # S3 URL 조립
         s3_url = f"https://{BUCKET_NAME}.s3.{os.getenv('AWS_DEFAULT_REGION')}.amazonaws.com/{file_key}"
 
@@ -247,15 +260,17 @@ async def parse_from_s3(file_key: str, db: Session = Depends(get_db)):
             file_name=filename,
             file_type=ext,
             s3_url=s3_url,
-            extracted_text=text
+            extracted_text=text,
+            file_size=file_size_str,
+            page_count=total_pages
         )
-
+        
         # DB에 추가 및 커밋
         db.add(new_doc)
         db.commit()
         db.refresh(new_doc)
 
-        print(f"[DEBUG] DB 저장 성공! (문서 번호: {new_doc.id})")
+        print(f"[DEBUG] DB 저장 성공! (문서 번호: {new_doc.id}, 크기: {file_size_str}, 페이지: {total_pages})")
         # ========================================================
 
         # 저장된 ID와 함께 프론트엔드로 응답
diff --git a/EasyDOC-frontend/src/pages/MyPage.jsx b/EasyDOC-frontend/src/pages/MyPage.jsx
index 5b049e0..955e503 100644
--- a/EasyDOC-frontend/src/pages/MyPage.jsx
+++ b/EasyDOC-frontend/src/pages/MyPage.jsx
@@ -15,7 +15,10 @@
  * 
  */
 
-import React, { useState } from "react";
+import React, { useState, useEffect } from "react"; 
+import axios from "axios"; 
+import Viewer from "./Viewer";
+import Loading from "./Loading";
 import "./mypage.css";
 
 /**
@@ -403,16 +406,77 @@ function LanguageSettingsContent() {
  *  그 정도 생각할 수 있을 듯.
  */
 
-function HistoryContent() {
+function HistoryContent({ onDocumentClick }) {
   // 문서 검색어 상태
   const [searchQuery, setSearchQuery] = useState("");
+  const [documents, setDocuments] = useState([]);
+
+  useEffect(() => {
+    const fetchHistory = async () => {
+      try {
+        const response = await axios.get('http://localhost:8002/api/documents');
+
+        const formattedDocs = response.data.map(doc => {
+          const d = new Date(doc.created_at);
+          const dateStr = `${d.getFullYear()}년 ${d.getMonth() + 1}월 ${d.getDate()}일 ${String(d.getHours()).padStart(2, '0')}:${String(d.getMinutes()).padStart(2, '0')}`;
+
+          return {
+            id: doc.id,
+            name: doc.file_name,
+            level: 3, // DB에 난이도 컬럼이 없으므로 디폴트 3 지정
+            category: "문서", // 기본 카테고리
+            date: dateStr,
+            pages: doc.page_count || "-",  // (DB에 값이 없으면 "-" 출력)
+            size: doc.file_size || "-",    
+          };
+        });
+        setDocuments(formattedDocs);
+      } catch (error) {
+        console.error("이력 로딩 실패: ", error);
+      }
+    };
+    fetchHistory();
+  }, []);
+  
+  // 파일 다운로드 처리 함수
+  const handleDownload = async (e, docId, fileName) => {
+    e.stopPropagation();
+
+    try{
+      const response = await axios.get(`http://localhost:8002/api/documents/${docId}`);
+      const s3Url = response.data.s3_url;
+
+      if (!s3Url) {
+        alert("다운로드할 원본 파일이 존재하지 않습니다.");
+        return;
+      }
+
+      // S3에서 파일을 받아와 내 컴퓨터에 저장
+      const fileResponse = await fetch(s3Url);
+      const blob = await fileResponse.blob();
+      const downloadUrl = window.URL.createObjectURL(blob);
+
+      const link = document.createElement("a");
+      link.href = downloadUrl;
+      link.download = fileName;
+      document.body.appendChild(link);
+      link.click();
+
+      link.remove();
+      window.URL.revokeObjectURL(downloadUrl);
+
+    } catch (error) {
+      console.error("다운로드 실패:", error);
+      alert("파일 다운로드 중 오류가 발생했습니다.");
+    }
+  };
 
   // ===== 더미 문서 데이터 =====
   // 실제 운영에서는 백엔드 API에서 fetch
   // 형식: { id, name, level, category, date, pages, size }
   // ISO 날짜 형식으로 바꿔야 하는데, 어떻게 하는지 모름
 
-  const documents = [
+  /*const documents = [
     {
       id: 1,
       name: "행정기본법.pdf",
@@ -590,13 +654,21 @@ function HistoryContent() {
               </div>
 
               <div className="document-actions">
-                <button className="action-btn" title="보기">
+                <button 
+                  className="action-btn" 
+                  title="보기" 
+                  onClick={() => onDocumentClick(doc.id)}
+                >
                   <svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
                     <path d="M1 12s4-8 11-8 11 8 11 8-4 8-11 8-11-8-11-8z" />
                     <circle cx="12" cy="12" r="3" />
                   </svg>
                 </button>
-                <button className="action-btn" title="다운로드">
+                <button 
+                  className="action-btn" 
+                  title="다운로드"
+                  onClick={(e) => handleDownload(e, doc.id, doc.name)}
+                >
                   <svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
                     <path d="M21 15v4a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-4" />
                     <polyline points="7 10 12 15 17 10" />
@@ -814,6 +886,36 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
   // 현재 활성화된 메뉴 상태 (기본값: 프로필)
   const [activeMenu, setActiveMenu] = useState("profile");
   
+  const [showViewer, setShowViewer] = useState(false);
+  const [showLoading, setShowLoading] = useState(false);
+  const [viewerData, setViewerData] = useState({ parseResult: null, ocrResult: null, pdfFileUrl: null });
+
+  const handleDocumentClick = async (docId) => {
+    try {
+      setShowLoading(true);
+      const response = await axios.get(`http://localhost:8002/api/documents/${docId}`);
+      const docData = response.data;
+
+      setViewerData({
+        parseResult: {
+          id: docData.id,
+          filename: docData.file_name,
+          text: docData.text,
+          difficult_words: docData.difficult_words
+        },
+        ocrResult: null,
+        pdfFileUrl: docData.s3_url || null
+      });
+
+      setShowLoading(false);
+      setShowViewer(true);
+    } catch (error) {
+      console.error("문서 상세 로딩 실패:", error);
+      alert("문서를 불러올 수 없습니다.");
+      setShowLoading(false);
+    }
+  };
+
   // ===== 더미 사용자 데이터 =====
   const [userData,setUserData]=useState({
     name: " ",
@@ -861,6 +963,31 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
         .catch(err => {
           console.error("정보 로딩 실패:", err);
         });
+
+      // 문서 DB에서 데이터 가져와서 통계 (문서 수, 페이지 수) 계산하기
+      axios.get('http://localhost:8002/api/documents')
+        .then(response => {
+          const docs = response.data;
+
+          // 총 문서 개수
+          const totalDocs = docs.length;
+
+          // 총 페이지 수 합산 (값이 비어있으면 1장으로 계산)
+          const totalPages = docs.reduce((sum, doc) => sum + (doc.page_count || 1), 0);
+
+          // 계산된 결과를 userData.stats에 반영
+          setUserData(prev => ({
+            ...prev,
+            stats: {
+              ...prev.stats,
+              documents: totalDocs,
+              pages: totalPages
+            }
+          }));
+        })
+        .catch(error => {
+          console.error("통계 정보 로딩 실패:", error);
+        });
     }
   }, [userEmail]);
 
@@ -884,7 +1011,7 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
       case "language":
         return <LanguageSettingsContent />;
       case "history":
-        return <HistoryContent />;
+        return <HistoryContent onDocumentClick={handleDocumentClick} />;
       case "settings":
         return <SettingsContent userEmail={userEmail} onLogout={onLogout}/>;
       default:
@@ -892,6 +1019,21 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
     }
   };
 
+  // 로딩 & 뷰어 화면 렌더링 추가
+  if (showLoading) {
+    return <Loading title="문서 불러오는 중" subtitle="잠시만 기다려주세요" />;
+  }
+
+  if (showViewer) {
+    return (
+      <Viewer 
+        parsedData={viewerData.parseResult} 
+        ocrData={viewerData.ocrResult} 
+        pdfFileUrl={viewerData.pdfFileUrl} 
+      />
+    );
+  }
+
 return (
     <div className="mypage">
       {/* ===== 사이드바 영역 ===== */}
diff --git a/backend-OCR/ocr_server.py b/backend-OCR/ocr_server.py
index 95adb61..81d74e3 100644
--- a/backend-OCR/ocr_server.py
+++ b/backend-OCR/ocr_server.py
@@ -70,6 +70,13 @@ def run_ocr(filename: str, db: Session = Depends(get_db)):
         print(f"분석 완료: {text_result[:30]}...")
 
         # ================= DB 저장 로직 =================
+        file_size_bytes = os.path.getsize(local_path)
+        size_kb = file_size_bytes / 1024
+        file_size_str = f"{size_kb:.1f} KB"
+
+        total_pages = 1 
+        # OCR은 촬영하거나 기기에 있는 이미지 하나를 업로드 하므로 총 페이지 수를 계산할 필요 없이 1로 고정
+
         # 1. S3 URL 주소 조립
         s3_url = f"https://{BUCKET_NAME}.s3.{AWS_REGION}.amazonaws.com/{filename}"
 
@@ -81,7 +88,9 @@ def run_ocr(filename: str, db: Session = Depends(get_db)):
             file_name = decoded_filename,
             file_type = file_extension,
             s3_url = s3_url,
-            extracted_text=text_result
+            extracted_text=text_result,
+            file_size = file_size_str,
+            page_count = total_pages
         )
 
         # 4. DB에 추가하고 저장
@@ -89,7 +98,7 @@ def run_ocr(filename: str, db: Session = Depends(get_db)):
         db.commit()
         db.refresh(new_doc) #MySQL이 방금 발급해준 고유 ID 번호를 가져온다
 
-        print(f"DB 저장 성공! (문서 번호: {new_doc.id})")
+        print(f"DB 저장 성공! (문서 번호: {new_doc.id}, 크기: {file_size_str}, 페이지: {total_pages})")
         # ===================================================
 
         # 프론트엔드에 추출 텍스트와 함께 부여된 문서 번호 반환
diff --git a/database_document/__pycache__/database.cpython-310.pyc b/database_document/__pycache__/database.cpython-310.pyc
index 47b1a0f5bd82edf2b058bd8dfa753b4dfa72f4ef..ca6b20625aae94cf2792364ce7f6faa9b89a1301 100644
GIT binary patch
delta 191
zcmdnW|CXOOpO=@50SG#6j%Ai^<UPX7STp$&bFy42ODby$R|;n@Q<N}}&7Q*E%-GBr
zC6dA&%%I6L*_tJoqlgix&refy@<f(Q##@trvp9?2;wnf?PmNE`FU>2t#hI3wlNw)~
zS(Q53j#W-l45*refrXKeNq~_D2swa|4@e74E@W*MH3iBRgIvPYz{bb~loDeqvfj+e
dX3i*R0TjK(;*?mNTBHJG7FkaYWKU+~0|4I`D#!o;

delta 146
zcmaFMzm=aipO=@50SK(-AI?<U$a{pDF=g^4=47@Mu3!dD?#aO{!OVV|!jsprWHLrg
zmSA<3FA@T(Mk2&OTooXp4#dSmlP9tYGYU;!$=WPx3=#kt&eXuh$i&FOD8^J|vDuN$
aoKeseD0+*<DX};ethLBuawmH-BM$%#106~L

diff --git a/database_document/__pycache__/database.cpython-314.pyc b/database_document/__pycache__/database.cpython-314.pyc
index be6e399be7cdedd87fe90f9ed699b8976c3b9fd9..c95711a228fb52725a30c6a31a05bd4b0898579e 100644
GIT binary patch
delta 260
zcmaDVc3hlSn~#@^0SG#6j%Ai^<ek96#K1UtKFcYQSXM=bShhHZAa-*mkOBsV5|PO-
zS)^G-gE&gWCg-vSGm1|>$hu#Qs~|BwH9k4NG_T|qXIf@XYJ72KRqEt=wsOY0$=}&h
z<r=(h3X0EQUm<u!P#ee=5Sv&wBWZHgWdWrY&myzQ3GDlY%z?(=VoOggiBCx?vH@~T
zHyd&^F<M%J#95pYi&Kl_flRQJCgUx}v|>ge*PsZjkHaQ6KczG$)vhQMC<u}$&e{Bi
oGlEfxn^C!=<O>6k`Xa;1DE#x2BO`;cKVvZ)P|aaBL05Aw08yJq761SM

delta 184
zcmX>u{#1-tn~#@^0SK(-AI?<U$UA|B=>o&#`7Ebcf;dV<CeLLJW)z+Lk#+y%<7{P&
zDU<EkQ(0QPicBUSWZy4j3e<LsEj_g)J|(Hh3dk|uJc*-;(b60w&f=6<oLVFgWP+tM
z8E-MB6*B_421Q_f95%W6DWy57c16KJL6Ago_GVwM2u4LtMw^b3FAPBHiv%m9@Xt@S
S495P9#cV(&huH*O&A9-szA%CS

diff --git a/database_document/database.py b/database_document/database.py
index 6c549cf..c9f3755 100644
--- a/database_document/database.py
+++ b/database_document/database.py
@@ -46,6 +46,8 @@ class Document(Base):
     extracted_text = Column(LONGTEXT)
     difficult_words = Column(JSON)
     created_at = Column(TIMESTAMP, default=datetime.utcnow)
+    page_count = Column(Integer, default=0)
+    file_size = Column(String(50))
 
 # DB 연결 세션을 가져오는 함수 (FastAPI에서 사용)
 def get_db():
diff --git a/database_document/document_api.py b/database_document/document_api.py
index af61130..ae4ca01 100644
--- a/database_document/document_api.py
+++ b/database_document/document_api.py
@@ -36,11 +36,20 @@ class DifficultWordsUpdate(BaseModel):
 # 전체 문서 목록 조회
 @app.get("/api/documents")
 def get_document_list(db: Session = Depends(get_db)):
-    docs = db.query(Document.id, Document.file_name, Document.created_at)\
-            .order_by(Document.id.desc())\
-            .all()
-
-    result = [{"id": doc.id, "file_name": doc.file_name, "created_at": doc.created_at} for doc in docs]
+    docs = db.query(Document.id, Document.file_name, Document.created_at, Document.page_count, Document.file_size)\
+             .order_by(Document.id.desc())\
+             .all()
+
+    result = [
+        {
+            "id": doc.id, 
+            "file_name": doc.file_name, 
+            "created_at": doc.created_at,
+            "page_count": doc.page_count,  
+            "file_size": doc.file_size    
+        } 
+        for doc in docs
+    ]
     return result
 
 # 특정 문서 상세 조회
diff --git a/database_document/schema.sql b/database_document/schema.sql
index b87a29b..765d9dd 100644
--- a/database_document/schema.sql
+++ b/database_document/schema.sql
@@ -10,4 +10,6 @@ CREATE TABLE IF NOT EXISTS docsinfos (
     extracted_text LONGTEXT,						-- 추출된 아주 긴 텍스트
     difficult_words JSON,                           -- 어려운 단어 목록 (JSON 형식)        
     created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP	-- 업로드된 시간 (자동 기록)
+    page_count INT DEFAULT 0;                       -- 문서 총 페이지 수
+    file_size VARCHAR(50);                          -- 문서 파일 용량
 );
\ No newline at end of file

From d5e347cd1fbcf018e7981a6f0f6b510232f2e781 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Sat, 28 Mar 2026 02:55:51 +0900
Subject: [PATCH 4/8] =?UTF-8?q?=EC=82=AC=EC=9A=A9=EC=9E=90=EB=B3=84=20?=
 =?UTF-8?q?=EC=B5=9C=EA=B7=BC=20=EB=AC=B8=EC=84=9C=20=EB=AA=A9=EB=A1=9D=20?=
 =?UTF-8?q?=EA=B0=9C=EC=9D=B8=ED=99=94=20=EA=B8=B0=EB=8A=A5=20=EA=B5=AC?=
 =?UTF-8?q?=ED=98=84?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 사용자마다 각자 업로드한 최근 문서 목록이 보이도록 구현

- docsinfos 테이블 설계에 사용자 이메일 컬럼 추가 (사용자 구분 용)
---
 EasyDOC-frontend/easydoc-parser/main.py       |   5 +++--
 EasyDOC-frontend/src/pages/Login.jsx          |   1 +
 EasyDOC-frontend/src/pages/MyPage.jsx         |   9 +++++----
 EasyDOC-frontend/src/pages/Upload.jsx         |  10 +++++-----
 EasyDOC-frontend/src/pages/Viewer.jsx         |   8 ++++----
 backend-OCR/ocr_server.py                     |   5 +++--
 .../__pycache__/database.cpython-310.pyc      | Bin 2029 -> 1607 bytes
 .../__pycache__/database.cpython-314.pyc      | Bin 3015 -> 2184 bytes
 database_document/database.py                 |  17 +++++++++--------
 database_document/document_api.py             |   7 ++++---
 database_document/schema.sql                  |   5 +++--
 11 files changed, 37 insertions(+), 30 deletions(-)

diff --git a/EasyDOC-frontend/easydoc-parser/main.py b/EasyDOC-frontend/easydoc-parser/main.py
index c1aa5a9..e1dcbfb 100644
--- a/EasyDOC-frontend/easydoc-parser/main.py
+++ b/EasyDOC-frontend/easydoc-parser/main.py
@@ -203,7 +203,7 @@ async def parse_hwp(file: UploadFile = File(...)):
 
 
 @app.get("/parse/s3/{file_key:path}")
-async def parse_from_s3(file_key: str, db: Session = Depends(get_db)):
+async def parse_from_s3(file_key: str, user_email: str = "", db: Session = Depends(get_db)):
     """S3에서 파일 가져와서 파싱 및 DB 저장"""
     print(f"[DEBUG] 파싱 요청 받음 - 파일 키: {file_key}")
     print(f"[DEBUG] 버킷: {BUCKET_NAME}")
@@ -262,7 +262,8 @@ async def parse_from_s3(file_key: str, db: Session = Depends(get_db)):
             s3_url=s3_url,
             extracted_text=text,
             file_size=file_size_str,
-            page_count=total_pages
+            page_count=total_pages,
+            user_email=user_email
         )
         
         # DB에 추가 및 커밋
diff --git a/EasyDOC-frontend/src/pages/Login.jsx b/EasyDOC-frontend/src/pages/Login.jsx
index da61338..18bacdb 100644
--- a/EasyDOC-frontend/src/pages/Login.jsx
+++ b/EasyDOC-frontend/src/pages/Login.jsx
@@ -22,6 +22,7 @@ export default function Login() {
         return (
           <Upload 
             onNavigateToMyPage={() => setCurrentView("mypage")} 
+            userEmail={userEmail}
           />
         );
       case "mypage":
diff --git a/EasyDOC-frontend/src/pages/MyPage.jsx b/EasyDOC-frontend/src/pages/MyPage.jsx
index 955e503..d6866aa 100644
--- a/EasyDOC-frontend/src/pages/MyPage.jsx
+++ b/EasyDOC-frontend/src/pages/MyPage.jsx
@@ -406,7 +406,7 @@ function LanguageSettingsContent() {
  *  그 정도 생각할 수 있을 듯.
  */
 
-function HistoryContent({ onDocumentClick }) {
+function HistoryContent({ onDocumentClick, userEmail }) {
   // 문서 검색어 상태
   const [searchQuery, setSearchQuery] = useState("");
   const [documents, setDocuments] = useState([]);
@@ -414,7 +414,7 @@ function HistoryContent({ onDocumentClick }) {
   useEffect(() => {
     const fetchHistory = async () => {
       try {
-        const response = await axios.get('http://localhost:8002/api/documents');
+        const response = await axios.get(`http://localhost:8002/api/documents?user_email=${userEmail}`);
 
         const formattedDocs = response.data.map(doc => {
           const d = new Date(doc.created_at);
@@ -965,7 +965,7 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
         });
 
       // 문서 DB에서 데이터 가져와서 통계 (문서 수, 페이지 수) 계산하기
-      axios.get('http://localhost:8002/api/documents')
+      axios.get(`http://localhost:8002/api/documents?user_email=${userEmail}`)
         .then(response => {
           const docs = response.data;
 
@@ -1011,7 +1011,7 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
       case "language":
         return <LanguageSettingsContent />;
       case "history":
-        return <HistoryContent onDocumentClick={handleDocumentClick} />;
+        return <HistoryContent onDocumentClick={handleDocumentClick} userEmail={userEmail} />;
       case "settings":
         return <SettingsContent userEmail={userEmail} onLogout={onLogout}/>;
       default:
@@ -1030,6 +1030,7 @@ export default function MyPage({userEmail,onLogout,onNavigateToUpload}) {
         parsedData={viewerData.parseResult} 
         ocrData={viewerData.ocrResult} 
         pdfFileUrl={viewerData.pdfFileUrl} 
+        userEmail={userEmail}
       />
     );
   }
diff --git a/EasyDOC-frontend/src/pages/Upload.jsx b/EasyDOC-frontend/src/pages/Upload.jsx
index 5d54b43..1bdccd2 100644
--- a/EasyDOC-frontend/src/pages/Upload.jsx
+++ b/EasyDOC-frontend/src/pages/Upload.jsx
@@ -4,7 +4,7 @@ import Viewer from "./Viewer";
 import Loading from "./Loading";
 import "./Upload.css";
 
-export default function Upload({onNavigateToMyPage}) {
+export default function Upload({onNavigateToMyPage, userEmail}) {
   const [selectedFile, setSelectedFile] = useState(null);
   const [recentDocs, setRecentDocs] = useState([]);
   const [showViewer, setShowViewer] = useState(false);
@@ -21,7 +21,7 @@ export default function Upload({onNavigateToMyPage}) {
   // 최근 문서 목록 가져오기
   const fetchRecentDocs = async () => {
     try {
-      const response = await axios.get('http://localhost:8002/api/documents');
+      const response = await axios.get(`http://localhost:8002/api/documents?user_email=${userEmail}`);
       
       // DB 데이터를 화면에 맞게 변환
       const formattedDocs = response.data.map(doc => {
@@ -149,7 +149,7 @@ export default function Upload({onNavigateToMyPage}) {
         // 파일이 이미지일 때 -> OCR 서버 (8001번) 요청
         console.log("6. OCR 서버에 분석 요청...");
         const ocrResponse = await axios.get(
-          `http://localhost:8001/ocr/s3/${encodeURIComponent(s3Key)}`
+          `http://localhost:8001/ocr/s3/${encodeURIComponent(s3Key)}?user_email=${userEmail}`
         );
         console.log("7. OCR 결과 도착!", ocrResponse.data);
         setOcrResult(ocrResponse.data); // 결과 저장
@@ -159,7 +159,7 @@ export default function Upload({onNavigateToMyPage}) {
         // 파일이 문서일 때 -> 파싱 서버 (8000번) 요청
         console.log("6. 파싱 요청 중..., S3 키:", s3Key);
         const parseResponse = await axios.get(
-          `http://localhost:8000/parse/s3/${encodeURIComponent(s3Key)}`
+          `http://localhost:8000/parse/s3/${encodeURIComponent(s3Key)}?user_email=${userEmail}`
         );
         console.log("7. 파싱 완료!", parseResponse.data);
         
@@ -220,7 +220,7 @@ export default function Upload({onNavigateToMyPage}) {
 
   if (showViewer) {
     // Viewer 컴포넌트에 파싱 데이터와 OCR 데이터를 넘겨준다
-    return <Viewer parsedData={parseResult} ocrData={ocrResult} pdfFileUrl={pdfFileUrl} />;
+    return <Viewer parsedData={parseResult} ocrData={ocrResult} pdfFileUrl={pdfFileUrl} userEmail={userEmail} />;
   }
 
   return (
diff --git a/EasyDOC-frontend/src/pages/Viewer.jsx b/EasyDOC-frontend/src/pages/Viewer.jsx
index 03268bc..b47fd3b 100644
--- a/EasyDOC-frontend/src/pages/Viewer.jsx
+++ b/EasyDOC-frontend/src/pages/Viewer.jsx
@@ -63,7 +63,7 @@ function HighlightedTextView({ text, highlightWord }) {
   );
 }
 
-export default function Viewer({ parsedData, ocrData, pdfFileUrl }) {
+export default function Viewer({ parsedData, ocrData, pdfFileUrl, userEmail }) {
     // 요약 박스 표시 여부 상태 (기본값: true)
     const [showSummary, setShowSummary] = useState(true);
 
@@ -129,7 +129,7 @@ export default function Viewer({ parsedData, ocrData, pdfFileUrl }) {
 
     const fetchDocuments = async () => {
         try {
-            const response = await axios.get('http://localhost:8002/api/documents');
+            const response = await axios.get(`http://localhost:8002/api/documents?user_email=${userEmail}`);
             setRecentDocs(response.data);
         } catch (error) {
             console.error("문서 목록 로딩 실패:", error);
@@ -260,7 +260,7 @@ const handleFileChange = async (e) => {
       // 파일이 이미지일 때 -> OCR 서버 (8001번) 요청
       console.log("6. OCR 서버에 분석 요청...");
       const ocrResponse = await axios.get(
-        `http://localhost:8001/ocr/s3/${encodeURIComponent(s3Key)}`
+        `http://localhost:8001/ocr/s3/${encodeURIComponent(s3Key)}?user_email=${userEmail}`
       );
       console.log("7. OCR 결과 도착!", ocrResponse.data);
       setOcrText(ocrResponse.data.text || ocrResponse.data);
@@ -269,7 +269,7 @@ const handleFileChange = async (e) => {
       // 파일이 문서일 때 -> 파싱 서버 (8000번) 요청
       console.log("6. 파싱 요청 중..., S3 키:", s3Key);
       const parseResponse = await axios.get(
-        `http://localhost:8000/parse/s3/${encodeURIComponent(s3Key)}`
+        `http://localhost:8000/parse/s3/${encodeURIComponent(s3Key)}?user_email=${userEmail}`
       );
       console.log("7. 파싱 완료!", parseResponse.data);
       const extractedText = parseResponse.data.text;
diff --git a/backend-OCR/ocr_server.py b/backend-OCR/ocr_server.py
index 81d74e3..515b887 100644
--- a/backend-OCR/ocr_server.py
+++ b/backend-OCR/ocr_server.py
@@ -52,7 +52,7 @@
 
 # db: Session = Depends(get_db)를 추가하여 API가 호출될 때마다 DB와 통신할 수 있는 세션 할당
 @app.get("/ocr/s3/{filename}")
-def run_ocr(filename: str, db: Session = Depends(get_db)):
+def run_ocr(filename: str, user_email: str = "", db: Session = Depends(get_db)):
     # URL에 포함된 암호화된 파일명(예: %ED%95...)을 정상적인 글자로 변환
     decoded_filename = unquote(filename)
 
@@ -90,7 +90,8 @@ def run_ocr(filename: str, db: Session = Depends(get_db)):
             s3_url = s3_url,
             extracted_text=text_result,
             file_size = file_size_str,
-            page_count = total_pages
+            page_count = total_pages,
+            user_email = user_email
         )
 
         # 4. DB에 추가하고 저장
diff --git a/database_document/__pycache__/database.cpython-310.pyc b/database_document/__pycache__/database.cpython-310.pyc
index ca6b20625aae94cf2792364ce7f6faa9b89a1301..162fac13a06312fe63ee7dce8fe2c3361fd134c7 100644
GIT binary patch
delta 502
zcmXYt&ubGw6vt;~C%c>d(WGXxn^-F%MOlc_Qs_y9mR3cuDOt5;E@90ZYD?<EY<dt6
z3hB`t!W_jvpdcRo3q-HtaSt8^5B?9n-8hf;<@??|-h7z9jqjeH`MyK&{QmOo<Z$k<
zvR`E0d-b+Xz!ojc0P3O*jtIdO5qProfq*Xq)Fs)je2ChR5o+_JD>{<O&XkI-bYK~l
zWf!i@3~^P~r$nqgB+!E3f<PcwriQo%Z3r)jScO_b;^<Gw5nF{nQu>n4ZWLT)*`%nC
zvr#&JndK9~H#gU}geBAbHDn`wY8=z|`ls<Glw4ZCrxX~tGlsw(F7$Q6kDQpQF7Dlr
zL;ab5Z5PgYF4a(;r6=P{qI!6xdin=@?5YU;ZOpu*=e5Z6Xh2n@Kh;jx7gOcv9hAa6
zmXjg8*eYks&tvaQ%BW34rZ%vQuj>cqY(rSPJHuzm-axo$4z`ozus_(Xx{vzF)5;w5
z2Me>m{bWx+w{E6)%Ln*QijXBwweUY>Sym(!gnjQUgY&VxPqClhLRlkC>S5TGGR7O6
QE@I8FjU{T*rr|aI0aI*pSO5S3

delta 917
zcmZuvTT2^36rS1LtZQzjF&9ltjT$d$OYo&otO(v{Dbz?}sVvB{W{xoulen8mFP0SI
zOQAl<zO+;!p-=r4eG&T~=CN<Z_7C{fGpl{;4D-!5hwq#@bI$zm{}~9>0|76=@nQb5
z(mD;Kq#8YaP-{a720OGH>5;vt9xD?)4ns`q&=s;3)`ua+`jbRYK%$%M5vu_4?g%7$
zloE&u{lPNCQK{)E2t$f_neRlR<X{uxRs-%bKMSznF%g;${X*Elx!e)H!R{yv^{AeP
zwxD;Aj=9D#vT>IUBAako1X+efA&miIFoqb1ahFdZ4nYQS_}r&Y0)@#A)u+JA5-b5z
zEO{d9)6m}``pgr;Mp){YuoTR6WIfC7ve9Fr-&2{VNU~`sNI$iId9XZhlpNF!H?k7<
zv3e7!(J-64T&o{~WmOooCQ<bB%t<q|X>OY~<QlK%(!wWw)jPX#&eFd>A76d_n4T$7
zQSRFz;jZ9X#$`tk%H)V_sqbi$9MKLvl@6q2k$fXr%4NH0;q_8(meU<8j9M$~T+7ea
zxp%%=v74p(eq$jj;)tLTV#RU0rdi&%vShp{t`@it$@*fk_%dHuajj4D#SNFN=L<Jv
zZSnc4b4kne$jM1>Rp!Gg_?_?4ro5JoI%D$1=<Ut!^#Wo7G6>VS?3j~R;!22G8K<i3
z&E91BPsY_UG!3@>P$<QxlisUTq8g1!)?++o?>nmJq|G(M*r`;(FnFH@cD;HCTy2;Z
z)SA4{u)(xSyWDGt9tfGuJ(gK31E&UBOJ<E#um|V@udpgMSItHPYK+SU>~K%Rs$dwA
z2>M&YBDI8oq<|3tN(#}r@Qk+}A>qmrHq(8eo8$kU&$apeI%`#7LA2JML&%U2_2blB
h3`&a2HR?r+CIzV?C8$^S;#tg$tjR&D(va*A{sj@+<dOgY

diff --git a/database_document/__pycache__/database.cpython-314.pyc b/database_document/__pycache__/database.cpython-314.pyc
index c95711a228fb52725a30c6a31a05bd4b0898579e..30381e03720e59bba4504328ab3c9ad19a7ae299 100644
GIT binary patch
delta 531
zcmXv~F>ljA6n>Z5iF0<+y0+tlK&VTl5?BI>QWc>NOteD<Cq$>iaubV2N@aAu3{1_y
z(5X_nr3i@u7We}U{DATY5Gs}s8*@S3K!Q6{PI}+Hckg@OeRm)IeY<kKTEQUK_xH!6
zt;0&A@EZ=VKG|ymF}NecC1vgr%xlEtKC!4{0jW?|VwHM%UXwUWeTj27O<t!c09x-M
zB?`bB6bC?TV$%khUzs^Sy+F$W^!^pVn;uAx;{$PNv!^(=8ofw7ANVDrUx9W_EX^D(
zWEx8no|VVRAR6x^DbKWSx6{u`ag;tCCIfLx8=wX8O8a$<>e7Z0z@tC^t&jpSRto0^
zYVuh=!BW{2Z}fGmjaW;z-oa+OE`I2rm+&NwSs3p|qjBbiVag*u8iWz&Y_vV$aT<m!
z5Z{XTW}9-1DOi?~9*DKlUSqoc#r9tmkJ6Xs+ukR;^K654bDB6VeVAA8&Wev?9uBwJ
zsx12Axv_y-;;V5Wu+|Yj%ZsahMbhp>(nWrQ;;}$Mu9RySw|A4_WE`)tyRxBvJbevf
v6E9vq)hzT7owmTVr=^psJ2g+RCo?>!z!CS&2d;%~?DI2_+gVFTPOkeGbsc>8

delta 1306
zcmZ{jPi)&%9LImoAKP&f=TFx-30?EAY3ptZv@4B>Dxi!NbroGO8@Gq$*6wDhq^|8$
z10)im9=d^6CSQWo1BeTp7#B2gK&p@i$A%7)`of=UIWU+6hzrkYlTH)0<llSm_df6Y
z`~IHn&B(W0@C+Md06#aT@2S<>!G!B?*X>a)jKUc}eUpT<1yJU#B$=Eoj~y-_jb^L>
zCWqn~c-`B@!!Y|CfSEusfj;X$rp+WumWz&5ZR98`M*#)^aph-@vF;2dyMie|vHveV
zKLg-{L9Bp_2655TD2kn*7JLFzbR8<CU_R8Pj_TGx&UFe8W<c;ehp#}@Rlx5o_NxI(
zW#BdFmS1qqV`-;M)ullIgusNmyN9i@<>$MWk4LN<>@sHNai(?%Vu<ZQ*~g(C6Y4R!
z6Pa+289I@P^q5*+h@uScqz`3rJcV+d`4Eo%D34=o!fy^E0$=5D@6ZThuwhQ%(1;K(
zx)1G{qsW(m$)m<iz8^4?;6O+sezMDq2~Tifo)Nq`e1j?ck{YPM4_Ko_<K?$J1*Nin
znRnTKdDX;IQIpJTHody8=(;K^)jSseb=ykIk|`}phEmYpETx?@>4T5A53KF<Zy#<P
zeDZ#J)FycARchS&nOGvgdeQYSBhY3{@a2GKEY&^d{R|d(&idN@qxF%8Bl6Z=PdSvr
z>beu0Ps4b};=DEA#+*LYNn4+Lzls*|)F!VgrYJA!(|GZ;^)`8tIBVS_Z`Ei~Tvk^U
zQM4&tF;-XB6`Rx~U8$HhB^rvPFI}@4(do*;4BM+qm8*(Ph&a0>Rb&-+g^wuLRl_uF
zQqnY~BHM0JS+>2Ju3{OtVd|aoSVZr0Y@KpKzY}7#6FD5L4Juo5ej?lR0=}b8M;)^~
zVH3-S^CLf{cRHb`-&mEaE6TI_6`XW7j1|KAiOSY~Vc5;<?-g21y2+&Xm~4yTn+#v4
z+QCqr+4r%VYq#R{nRX=JnED}-sb6eUkrowiQt=j*{GLj->1c~iH0eZR>^_}uv;A9@
z8<lrodf)>l`ey(FvHJOaPpEPJ)1j8<$p>zn_=^M&yYKPs2F7<vdy5kbJEgnQ7w7J*
zeL1yLYECTdj$it2ZI^lFzDM|-1b=XgzsY|vx5o@(Pi%Ngy{R^Wd+c!C-(~`j?wz=@
l()8u5pU7>R4*?Gk2fRezKYz>+aPAUekoYRTAtM)x%zwka872S#

diff --git a/database_document/database.py b/database_document/database.py
index c9f3755..c1fcf97 100644
--- a/database_document/database.py
+++ b/database_document/database.py
@@ -6,7 +6,7 @@
 from pathlib import Path
 from dotenv import load_dotenv
 
-_search = Path(__file__).resolve().parent
+"""_search = Path(__file__).resolve().parent
 _env_files = []
 for _ in range(5):  # 최대 5단계 상위 폴더까지 탐색
     _candidate = _search / ".env"
@@ -18,14 +18,14 @@
     load_dotenv(dotenv_path=_ef, override=True)
 
 if _env_files:
-    print(f"✓ database.py: .env 로드 완료 ({[str(f) for f in _env_files]})")
+    print(f"✓ database.py: .env 로드 완료 ({[str(f) for f in _env_files]})")"""
 
-# 환경변수에서 DB 정보 가져오기
-DB_USER = os.getenv("DB_USER")
-DB_PASSWORD = os.getenv("DB_PASSWORD")
-DB_HOST = os.getenv("DB_HOST")
-DB_PORT = os.getenv("DB_PORT")
-DB_NAME = os.getenv("DB_NAME")
+# DB 정보 가져오기
+DB_USER = "root"
+DB_PASSWORD = "root"
+DB_HOST = "localhost"
+DB_PORT = "3306"
+DB_NAME = "easydoc"
 
 # MySQL 연결 주소 만들기 (pymysql)
 SQLALCHEMY_DATABASE_URL = f"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}?charset=utf8mb4"
@@ -48,6 +48,7 @@ class Document(Base):
     created_at = Column(TIMESTAMP, default=datetime.utcnow)
     page_count = Column(Integer, default=0)
     file_size = Column(String(50))
+    user_email = Column(String(255), index=True)
 
 # DB 연결 세션을 가져오는 함수 (FastAPI에서 사용)
 def get_db():
diff --git a/database_document/document_api.py b/database_document/document_api.py
index ae4ca01..6204995 100644
--- a/database_document/document_api.py
+++ b/database_document/document_api.py
@@ -1,4 +1,4 @@
-from fastapi import FastAPI, HTTPException, Depends
+from fastapi import FastAPI, HTTPException, Depends, Query
 from fastapi.middleware.cors import CORSMiddleware
 from sqlalchemy.orm import Session
 from pydantic import BaseModel
@@ -33,10 +33,11 @@
 class DifficultWordsUpdate(BaseModel):
     difficult_words: list
 
-# 전체 문서 목록 조회
+# 현재 로그인한 특정 유저의 문서 목록만 조회
 @app.get("/api/documents")
-def get_document_list(db: Session = Depends(get_db)):
+def get_document_list(user_email: str = Query(...), db: Session = Depends(get_db)):
     docs = db.query(Document.id, Document.file_name, Document.created_at, Document.page_count, Document.file_size)\
+             .filter(Document.user_email == user_email)\
              .order_by(Document.id.desc())\
              .all()
 
diff --git a/database_document/schema.sql b/database_document/schema.sql
index 765d9dd..e40032e 100644
--- a/database_document/schema.sql
+++ b/database_document/schema.sql
@@ -10,6 +10,7 @@ CREATE TABLE IF NOT EXISTS docsinfos (
     extracted_text LONGTEXT,						-- 추출된 아주 긴 텍스트
     difficult_words JSON,                           -- 어려운 단어 목록 (JSON 형식)        
     created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP	-- 업로드된 시간 (자동 기록)
-    page_count INT DEFAULT 0;                       -- 문서 총 페이지 수
-    file_size VARCHAR(50);                          -- 문서 파일 용량
+    page_count INT DEFAULT 0,                       -- 문서 총 페이지 수
+    file_size VARCHAR(50),                          -- 문서 파일 용량
+    user_email VARCHAR(255);                        -- 사용자 구분용 이메일
 );
\ No newline at end of file

From afde819a513f0852f0a2b2ba80ff459de98ac1e0 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Sat, 28 Mar 2026 15:59:26 +0900
Subject: [PATCH 5/8] =?UTF-8?q?=EC=84=A4=EB=AA=85=20=EC=B6=94=EA=B0=80=20?=
 =?UTF-8?q?=EB=B0=8F=20=EC=A0=95=EB=A6=AC?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- README.md에 최근 문서 목록 서버 설명 추가
- start-all.bat, stop-all.bat에 최근 문서 서버 커맨드 추가
---
 README.md                                     |  23 ++++++++++++++++--
 .../__pycache__/database.cpython-310.pyc      | Bin 1607 -> 1607 bytes
 .../__pycache__/database.cpython-314.pyc      | Bin 2184 -> 2184 bytes
 start-all.bat                                 |  13 +++++++---
 stop-all.bat                                  |  11 ++++++---
 5 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index 34085f1..aa23e74 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,7 @@
 - `EasyDOC-frontend/easydoc-parser/` - FastAPI 파싱 서버 (Python)
 - `EasyDOC-backend/` - Spring Boot 백엔드 (로그인·회원가입·JWT·비밀번호 찾기 등 통합)
 - `backend-OCR/` - FastAPI  OCR 서버 (Python, Google Cloud Vision API)
+- `database_document/` - FastAPI  DB 서버 (Python, 문서 메타데이터 저장 및 사용자별 최근 문서 목록 관리)
 
 ---
 
@@ -72,7 +73,7 @@ pip install -r requirements.txt
 python ocr_server.py
 ```
 
-접속 주소: http://0.0.0.0:8001
+접속 주소: http://localhost:8001
 
 **필요 사항:**
 - 프로젝트 최상위 폴더(`EasyDOC`)에 `.env` 파일 필요 (AWS 키 포함)
@@ -80,6 +81,23 @@ python ocr_server.py
 
 ---
 
+### 5. 최근 문서 목록 서버 실행 (Python)
+
+```bash
+cd database_document
+python -m venv venv
+.\venv\Scripts\activate (맥은 source venv/bin/activate)
+pip install -r requirements.txt
+python document_api.py
+```
+
+접속 주소: http://localhost:8002
+
+**필요 사항:**
+- 폴더 내의 database.py에 #DB 정보 가져오기 아래에 본인 MySQL DB 정보 입력 (로컬 기본값 채워져 있음)
+
+---
+
 ## 환경 변수 설정
 
 프로젝트 최상위 폴더(`EasyDOC`)에 `.env` 파일 생성:
@@ -100,4 +118,5 @@ S3_BUCKET_NAME=your_bucket_name_here
 - PDF, HWP 문서 업로드 및 텍스트 추출
 - S3를 통한 파일 저장
 - 사용자 인증 및 회원가입
-- 문서 파싱/OCR 및 변환
\ No newline at end of file
+- 문서 파싱/OCR 및 변환
+- 로그인 사용자별 맞춤형 최근 업로드 문서 목록 제공 및 마이페이지 통계 가능
\ No newline at end of file
diff --git a/database_document/__pycache__/database.cpython-310.pyc b/database_document/__pycache__/database.cpython-310.pyc
index 162fac13a06312fe63ee7dce8fe2c3361fd134c7..83fa3f54971236eac84dc4ef9a0a1c370522df50 100644
GIT binary patch
delta 19
ZcmX@kbDW1OpO=@50SJ~}-^gXl1^_X21ik<O

delta 19
ZcmX@kbDW1OpO=@50SKOL+sI|h1^_Zv1l|Au

diff --git a/database_document/__pycache__/database.cpython-314.pyc b/database_document/__pycache__/database.cpython-314.pyc
index 30381e03720e59bba4504328ab3c9ad19a7ae299..e2540c2cf6ea7a6be9f915404043268df899379d 100644
GIT binary patch
delta 19
ZcmeAW>=5MA=HumJ0D`60H*(c+001T&1WEt^

delta 19
ZcmeAW>=5MA=HumJ0D@=RHgeT*001Wa1Zn^P

diff --git a/start-all.bat b/start-all.bat
index b5b7d7f..498914d 100644
--- a/start-all.bat
+++ b/start-all.bat
@@ -6,20 +6,24 @@ echo ========================================
 echo.
 
 REM MySQL 서비스 시작 (관리자 권한 필요)
-echo [1/4] MySQL 서비스 시작 중...
+echo [1/5] MySQL 서비스 시작 중...
 powershell -Command "Start-Process powershell -Verb RunAs -ArgumentList '-Command', 'Start-Service MySQL; Write-Host MySQL started; Start-Sleep -Seconds 2'"
 timeout /t 3 /nobreak > nul
 
 REM 파싱 서버 시작 (포트 8000)
-echo [2/4] 파싱 서버 시작 중... (포트 8000)
+echo [2/5] 파싱 서버 시작 중... (포트 8000)
 start "EasyDOC Parser Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd EasyDOC-frontend\easydoc-parser; uvicorn main:app --reload"
 
 REM 백엔드 Spring Boot 시작 (포트 8080)
-echo [3/4] Spring Boot 백엔드 시작 중... (포트 8080)
+echo [3/5] Spring Boot 백엔드 시작 중... (포트 8080)
 start "EasyDOC Backend Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd EasyDOC-backend; .\gradlew.bat bootRun"
 
+REM 최근 문서 DB 서버 시작 (포트 8002)
+echo [4/5] 최근 문서 DB 서버 시작 중... (포트 8002)
+start "EasyDOC Document API Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd database_document; .\venv\Scripts\python document_api.py"
+
 REM 프론트엔드 시작 (포트 5173)
-echo [4/4] 프론트엔드 시작 중... (포트 5173)
+echo [5/5] 프론트엔드 시작 중... (포트 5173)
 start "EasyDOC Frontend Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd EasyDOC-frontend; npm run dev"
 
 echo.
@@ -28,6 +32,7 @@ echo    모든 서버가 시작되었습니다!
 echo ========================================
 echo    - 파싱 서버: http://localhost:8000
 echo    - 백엔드: http://localhost:8080
+echo    - 최근 문서 DB: http://localhost:8002
 echo    - 프론트엔드: http://localhost:5173
 echo ========================================
 echo.
diff --git a/stop-all.bat b/stop-all.bat
index bfd4ab8..1b540ad 100644
--- a/stop-all.bat
+++ b/stop-all.bat
@@ -5,16 +5,19 @@ echo    EasyDOC 전체 서버 종료
 echo ========================================
 echo.
 
-echo [1/4] 프론트엔드 종료 중...
+echo [1/5] 프론트엔드 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Frontend Server*" /F > nul 2>&1
 
-echo [2/4] 백엔드 종료 중...
+echo [2/5] 백엔드 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Backend Server*" /F > nul 2>&1
 
-echo [3/4] 파싱 서버 종료 중...
+echo [3/5] 파싱 서버 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Parser Server*" /F > nul 2>&1
 
-echo [4/4] Java/Node 프로세스 정리 중...
+echo [4/5] 최근 문서 DB 서버 종료 중...
+taskkill /FI "WindowTitle eq EasyDOC Document API Server*" /F > nul 2>&1
+
+echo [5/5] Java/Node 프로세스 정리 중...
 taskkill /IM java.exe /F > nul 2>&1
 taskkill /IM node.exe /F > nul 2>&1
 taskkill /IM python.exe /F > nul 2>&1

From ad49a3b3f7c32919b4798287cfd49d7247c3e9d5 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Sun, 29 Mar 2026 05:07:15 +0900
Subject: [PATCH 6/8] =?UTF-8?q?=EC=9D=B4=EB=AF=B8=EC=A7=80=20=EC=97=85?=
 =?UTF-8?q?=EB=A1=9C=EB=93=9C=20=EC=8B=9C=20=EB=B0=8F=20PDF=20=EB=B3=80?=
 =?UTF-8?q?=ED=99=98=20=EA=B8=B0=EB=8A=A5=20=EA=B5=AC=ED=98=84?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 이미지를 업로드하면 OCR로 텍스트 추출 후 이미지와 텍스트를 이용하여 PDF로 변환하여 원본탭에 표시
- 다운로드 시 PDF로 다운로드 가능

- Viewer 페이지의 최근 문서 목록에서 파일형에 따라 다른 색, 모양의 아이콘이 나오도록 수정
---
 EasyDOC-frontend/easydoc-parser/main.py |  88 ++++++++++++------------
 EasyDOC-frontend/src/pages/Upload.jsx   |   4 ++
 EasyDOC-frontend/src/pages/Viewer.jsx   |  26 ++++++-
 backend-OCR/ocr_logic.py                |  53 ++++++++++++--
 backend-OCR/ocr_server.py               |  47 ++++++++-----
 backend-OCR/requirements.txt            | Bin 256 -> 294 bytes
 6 files changed, 150 insertions(+), 68 deletions(-)

diff --git a/EasyDOC-frontend/easydoc-parser/main.py b/EasyDOC-frontend/easydoc-parser/main.py
index e1dcbfb..6a7b707 100644
--- a/EasyDOC-frontend/easydoc-parser/main.py
+++ b/EasyDOC-frontend/easydoc-parser/main.py
@@ -8,7 +8,7 @@
 import olefile
 import zlib
 import vertexai
-from vertexai.generative_models import GenerativeModel
+from vertexai.generative_models import GenerativeModel, Content, Part
 import io
 import re
 import json
@@ -33,6 +33,19 @@
 if _env_files:
     print(f"✓ .env 로드 완료: {[str(f) for f in _env_files]}")
 
+# GOOGLE_APPLICATION_CREDENTIALS: 상대 경로는 cwd가 아니라 이 파일(easydoc-parser) 기준으로 해석
+_parser_dir = Path(__file__).resolve().parent
+_gac = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
+if _gac:
+    _cred_path = Path(_gac)
+    if not _cred_path.is_absolute():
+        _cred_path = (_parser_dir / _gac).resolve()
+    if _cred_path.is_file():
+        os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = str(_cred_path)
+        print(f"✓ 서비스 계정 키: {_cred_path}")
+    else:
+        print(f"⚠ GOOGLE_APPLICATION_CREDENTIALS 파일 없음: {_cred_path}")
+
 # --- DB 공유를 위한 경로 설정 ---
 current_file_path = Path(__file__).resolve()
 root_dir = current_file_path.parent.parent.parent
@@ -61,16 +74,22 @@
 )
 BUCKET_NAME = os.getenv("S3_BUCKET_NAME")
 
+
+VERTEX_GEMINI_MODEL = os.getenv("GCP_GEMINI_MODEL", "gemini-2.5-flash")
+VERTEX_LOCATION = os.getenv("GCP_VERTEX_LOCATION", "asia-northeast3")
+
 # Vertex AI (Gemini) 설정
 gemini_model = None
 try:
     project_id = os.getenv("GCP_PROJECT_ID")
-    location = os.getenv("GCP_LOCATION", "asia-northeast3")
     
     if project_id:
-        vertexai.init(project=project_id, location=location)
-        gemini_model = GenerativeModel("gemini-1.5-flash")
-        print("✓ Vertex AI Gemini 초기화 성공")
+        vertexai.init(project=project_id, location=VERTEX_LOCATION)
+        gemini_model = GenerativeModel(VERTEX_GEMINI_MODEL)
+        print(
+            f"✓ Vertex AI Gemini 초기화 성공 "
+            f"(model={VERTEX_GEMINI_MODEL}, location={VERTEX_LOCATION})"
+        )
     else:
         print("⚠ GCP_PROJECT_ID가 설정되지 않음 - 사전 기반 설명만 사용")
 except Exception as e:
@@ -287,7 +306,7 @@ async def analyze_with_gemini(data: dict):
     text = data.get("text", "")
     
     if not text:
-        return {"difficult_words": [], "token_usage": {}}
+        return {"difficult_words": []}
     
     if gemini_model is None:
         return {"difficult_words": [], "error": "Gemini API 키가 설정되지 않았습니다."}
@@ -321,7 +340,6 @@ async def analyze_with_gemini(data: dict):
     if cached_word_set:
         cache_exclude_hint = f"\n\n## 이미 설명된 단어 (제외하세요)\n{', '.join(cached_word_set)}"
     
-    total_token_usage = {"prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0}
     new_gemini_words = []
     seen_words = set(cached_word_set)  # 중복 방지
     
@@ -368,16 +386,6 @@ async def analyze_with_gemini(data: dict):
             response = gemini_model.generate_content(prompt)
             response_text = response.text.strip()
             
-            # 토큰 사용량 집계
-            if hasattr(response, 'usage_metadata'):
-                um = response.usage_metadata
-                p_tok = getattr(um, 'prompt_token_count', 0) or 0
-                c_tok = getattr(um, 'candidates_token_count', 0) or 0
-                t_tok = getattr(um, 'total_token_count', 0) or 0
-                total_token_usage["prompt_tokens"] += p_tok
-                total_token_usage["completion_tokens"] += c_tok
-                total_token_usage["total_tokens"] += t_tok
-                print(f"[Gemini 토큰] 청크 {idx + 1}/{len(chunks)}: 입력={p_tok}, 출력={c_tok}, 합계={t_tok}")
             
             # 응답 파싱
             for line in response_text.split("\n"):
@@ -403,7 +411,7 @@ async def analyze_with_gemini(data: dict):
                         seen_words.add(word)
             
         except Exception as e:
-            print(f"[Gemini 청크 {idx + 1} 오류] {e}")
+            print(f"[어려운 단어 분석] 청크 {idx + 1} 처리 오류: {e}")
     
     # 4단계: 새 단어를 CSV 캐시에 저장
     if new_gemini_words:
@@ -413,9 +421,10 @@ async def analyze_with_gemini(data: dict):
     all_words = cached_words + new_gemini_words
     all_words.sort(key=lambda x: x["level"], reverse=True)
     
-    print(f"[Gemini 분석 완료] 캐시={len(cached_words)}개, 신규={len(new_gemini_words)}개, "
-          f"전체={len(all_words)}개, 청크={len(chunks)}개")
-    
+    print(
+        f"[어려운 단어 분석 완료] 캐시 {len(cached_words)}개 · 신규 {len(new_gemini_words)}개 · "
+        f"전체 단어 {len(all_words)}개 · 처리 청크 {len(chunks)}개"
+    )
     return {
         "difficult_words": all_words,
         "total_found": len(all_words),
@@ -492,9 +501,8 @@ async def chat(req: ChatRequest):
         system_prompt += f"\n\n## 현재 사용자가 보고 있는 문서 내용:\n{doc_preview}"
 
     try:
-        # system_instruction이 포함된 모델 인스턴스 생성
-        chat_model = genai.GenerativeModel(
-            'gemini-3-flash-preview',
+        chat_model = GenerativeModel(
+            VERTEX_GEMINI_MODEL,
             system_instruction=system_prompt,
         )
 
@@ -502,26 +510,21 @@ async def chat(req: ChatRequest):
         contents = []
         for msg in req.messages:
             role = "model" if msg.role == "model" else "user"
-            contents.append({"role": role, "parts": [{"text": msg.content}]})
+            contents.append(
+                Content(role=role, parts=[Part.from_text(msg.content)])
+            )
 
         response = chat_model.generate_content(contents)
         reply = response.text.strip()
 
-        # 토큰 사용량 추출
-        token_usage = {"prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0}
-        if hasattr(response, 'usage_metadata'):
-            um = response.usage_metadata
-            token_usage["prompt_tokens"] = getattr(um, 'prompt_token_count', 0) or 0
-            token_usage["completion_tokens"] = getattr(um, 'candidates_token_count', 0) or 0
-            token_usage["total_tokens"] = getattr(um, 'total_token_count', 0) or 0
-
-        print(f"[Chat] persona={req.persona}, msgs={len(req.messages)}, "
-              f"reply_len={len(reply)}, tokens={token_usage['total_tokens']}")
-        return {"reply": reply, "persona": req.persona, "token_usage": token_usage}
+        print(
+            f"[에이전트 채팅] 성격={req.persona}, 대화 {len(req.messages)}턴, 답변 {len(reply)}자"
+        )
+        return {"reply": reply, "persona": req.persona}
 
     except Exception as e:
-        print(f"[Chat 오류] {e}")
-        return {"reply": "응답을 생성하지 못했습니다. 잠시 후 다시 시도해주세요.", "persona": req.persona, "token_usage": None}
+        print(f"[에이전트 채팅 오류] {e}")
+        return {"reply": "응답을 생성하지 못했습니다. 잠시 후 다시 시도해주세요.", "persona": req.persona}
 
 
 # ============================================================
@@ -669,8 +672,7 @@ async def fill_cells(req: FillCellsRequest):
 [/FILL_CELLS]"""
 
     try:
-        fill_model = genai.GenerativeModel('gemini-3-flash-preview')
-        response = fill_model.generate_content(prompt)
+        response = gemini_model.generate_content(prompt)
         reply = response.text.strip()
 
         match = re.search(r'\[FILL_CELLS\](.*?)\[/FILL_CELLS\]', reply, re.DOTALL)
@@ -680,11 +682,11 @@ async def fill_cells(req: FillCellsRequest):
             data["suggestions"] = [
                 s for s in data.get("suggestions", []) if s.get("value")
             ]
-            print(f"[fill-cells] 제안 {len(data['suggestions'])}개")
+            print(f"[표 셀 자동 채우기] 제안 {len(data['suggestions'])}개 반영")
             return data
         else:
-            print(f"[fill-cells] JSON 파싱 실패. 응답: {reply[:200]}")
+            print(f"[표 셀 자동 채우기] JSON 파싱 실패 · 응답 앞부분: {reply[:200]}")
             return {"suggestions": [], "message": "AI 응답 파싱에 실패했습니다."}
     except Exception as e:
-        print(f"[fill-cells 오류] {e}")
+        print(f"[표 셀 자동 채우기 오류] {e}")
         return {"error": str(e), "suggestions": []}
\ No newline at end of file
diff --git a/EasyDOC-frontend/src/pages/Upload.jsx b/EasyDOC-frontend/src/pages/Upload.jsx
index 1bdccd2..0281d6d 100644
--- a/EasyDOC-frontend/src/pages/Upload.jsx
+++ b/EasyDOC-frontend/src/pages/Upload.jsx
@@ -155,6 +155,10 @@ export default function Upload({onNavigateToMyPage, userEmail}) {
         setOcrResult(ocrResponse.data); // 결과 저장
         setParseResult(null);           // 파싱 데이터는 비움
         setParsedText("");
+
+        if (ocrResponse.data.pdf_url) {
+          setPdfFileUrl(ocrResponse.data.pdf_url);
+        }
       } else {
         // 파일이 문서일 때 -> 파싱 서버 (8000번) 요청
         console.log("6. 파싱 요청 중..., S3 키:", s3Key);
diff --git a/EasyDOC-frontend/src/pages/Viewer.jsx b/EasyDOC-frontend/src/pages/Viewer.jsx
index b47fd3b..cfb93a5 100644
--- a/EasyDOC-frontend/src/pages/Viewer.jsx
+++ b/EasyDOC-frontend/src/pages/Viewer.jsx
@@ -1,6 +1,6 @@
 import React, { useState, useRef, useEffect } from "react";
 import axios from "axios"; 
-import { Upload, Clock, FileText, Settings, X, BookOpen, ChevronRight, Lightbulb, Sparkles } from 'lucide-react';
+import { Upload, Clock, FileText, Settings, X, BookOpen, ChevronRight, Lightbulb, Sparkles, Image as ImageIcon } from 'lucide-react';
 import PdfHighlightViewer from "./PdfHighlightViewer";
 import AgentChat from "./AgentChat";
 import "./viewer.css";
@@ -155,7 +155,9 @@ export default function Viewer({ parsedData, ocrData, pdfFileUrl, userEmail }) {
             if (docData.s3_url) {
               setPdfUrl(docData.s3_url);
               const isPdfFile = docData.file_type?.toLowerCase() === 'pdf' ||
-                docData.file_name?.toLowerCase().endsWith('.pdf');
+                docData.file_type?.toLowerCase() === 'pdf' ||
+                docData.file_name?.toLowerCase().endsWith('.pdf') ||
+                docData.s3_url?.toLowerCase().includes('.pdf');
                 setIsPdf(isPdfFile);
             }
         } catch (error) {
@@ -172,6 +174,19 @@ export default function Viewer({ parsedData, ocrData, pdfFileUrl, userEmail }) {
       return dateString.substring(0, 10).replace(/-/g, '.');
     };
 
+    // 파일명에 따라 아이콘과 색상을 다르게 반환
+    const renderFileIcon = (fileName) => {
+      if (!fileName) return <FileText size={18} color="#DC2626" />;
+      const ext = fileName.split(".").pop().toLowerCase();
+      if (["jpg", "jpeg", "png", "gif", "bmp"].includes(ext)) {
+        return <ImageIcon size={18} color="#10B981" />; // 이미지는 초록색 아이콘
+      }
+      if (ext === "hwp") {
+        return <FileText size={18} color="#2563EB" />; // HWP는 파란색 아이콘
+      }
+      return <FileText size={18} color="#DC2626" />; // PDF 등 기본은 빨간색 아이콘
+    };
+
     // props로 받은 데이터를 상태에 반영 (Upload에서 넘어올 때)
     useEffect(() => {
       if (selectedDoc) return;
@@ -265,6 +280,11 @@ const handleFileChange = async (e) => {
       console.log("7. OCR 결과 도착!", ocrResponse.data);
       setOcrText(ocrResponse.data.text || ocrResponse.data);
       setParsedText("");  // 문서 파싱 결과는 비움
+
+      if (ocrResponse.data.pdf_url) {
+        setPdfUrl(ocrResponse.data.pdf_url);
+        setIsPdf(true);
+      }
     } else {
       // 파일이 문서일 때 -> 파싱 서버 (8000번) 요청
       console.log("6. 파싱 요청 중..., S3 키:", s3Key);
@@ -332,7 +352,7 @@ const handleFileChange = async (e) => {
               >
                 <div className="doc-info">
                   <div className="doc-icon-box">
-                    <FileText size={18} />
+                    {renderFileIcon(doc.file_name)}
                   </div>
                   <div className="doc-text">
                     <span className="doc-title">{doc.file_name}</span>
diff --git a/backend-OCR/ocr_logic.py b/backend-OCR/ocr_logic.py
index db7fa63..3127073 100644
--- a/backend-OCR/ocr_logic.py
+++ b/backend-OCR/ocr_logic.py
@@ -1,6 +1,14 @@
 from google.cloud import vision
 import io 
 import os
+from PIL import Image
+from reportlab.pdfgen import canvas
+from reportlab.lib.utils import ImageReader
+from reportlab.pdfbase import pdfmetrics
+from reportlab.pdfbase.ttfonts import TTFont
+
+# 윈도우 기본 폰트 '맑은 고딕' 등록 (프론트엔드에서 텍스트 레이어 인식용)
+pdfmetrics.registerFont(TTFont('Malgun', 'malgun.ttf'))
 
 class EasyDocOCR:
     def __init__(self):
@@ -8,9 +16,10 @@ def __init__(self):
         #주의: 실행 시 환경변수 'GOOGLE_APPLICATION_CREDENTIALS'가 설정되어 있어야 함
         self.client = vision.ImageAnnotatorClient()
 
-    def extract_text(self, image_path: str) -> str:
+    def extract_text_and_make_pdf(self, image_path: str, pdf_output_path: str) -> str:
         """
-        이미지 파일 경로를 받아 텍스트를 추출하여 반환합니다.
+        이미지 파일에서 텍스트를 추출하고, 
+        투명한 텍스트가 입혀진 '드래그 가능한 PDF'를 생성합니다.
         """
         try:
             #1. 이미지 파일을 메모리로 읽어오기
@@ -29,8 +38,44 @@ def extract_text(self, image_path: str) -> str:
             if not texts:
                 return "텍스트를 찾을 수 없습니다."
 
-            #3. 전체 텍스트 반환 (texts[0]에 전체 내용이 들어있음)
-            return texts[0].description
+            full_text = texts[0].description
+            words = texts[1:] 
+
+            #3. PDF 캔버스 생성
+            img = Image.open(image_path)
+            width, height = img.size
+            c = canvas.Canvas(pdf_output_path, pagesize=(width, height))
+
+            #4. 배경으로 원본 이미지 그리기
+            c.drawImage(ImageReader(img), 0, 0, width, height)
+
+            #5. 투명 텍스트 레이어 입히기
+            for word in words:
+                # 단어 좌표 추출
+                vertices = word.bounding_poly.vertices
+                x_min = min(getattr(v, 'x', 0) for v in vertices)
+                y_min = min(getattr(v, 'y', 0) for v in vertices)
+                y_max = max(getattr(v, 'y', 0) for v in vertices)
+
+                word_text = word.description
+                word_height = y_max - y_min
+
+                pdf_y = height - y_max
+                pdf_x = x_min
+
+                font_size = word_height if word_height > 0 else 10
+
+                text_obj = c.beginText()
+                text_obj.setTextRenderMode(3)
+                text_obj.setFont('Malgun', font_size)
+                text_obj.setTextOrigin(pdf_x, pdf_y)
+                text_obj.textOut(word_text)
+
+                c.drawText(text_obj)
+
+            c.save()
+
+            return full_text
 
         except Exception as e:
             print(f"OCR 처리 중 오류 발생: {e}")
diff --git a/backend-OCR/ocr_server.py b/backend-OCR/ocr_server.py
index 515b887..bd8c80e 100644
--- a/backend-OCR/ocr_server.py
+++ b/backend-OCR/ocr_server.py
@@ -7,7 +7,7 @@
 from ocr_logic import EasyDocOCR
 from dotenv import load_dotenv
 from sqlalchemy.orm import Session
-from pathlib import Path  # 추가됨
+from pathlib import Path  
 
 # --- DB 공유를 위한 경로 설정 ---
 current_file_path = Path(__file__).resolve()
@@ -33,7 +33,7 @@
 )
 
 # 설정 및 연결
-os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "google-key.json" # Google Cloud 인증 키 위치 지정   
+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "vision-key.json" # Google Cloud 인증 키 위치 지정   
 ocr_engine = EasyDocOCR()
 
 # .env 파일에서 AWS 설정값 불러오기
@@ -56,8 +56,14 @@ def run_ocr(filename: str, user_email: str = "", db: Session = Depends(get_db)):
     # URL에 포함된 암호화된 파일명(예: %ED%95...)을 정상적인 글자로 변환
     decoded_filename = unquote(filename)
 
+    pure_filename = os.path.basename(decoded_filename)
+
     # 로컬에 다운로드할 임시 경로
-    local_path = f"temp_{decoded_filename}"
+    local_path = f"temp_{pure_filename}"
+
+    filename_without_ext = pure_filename.rsplit('.', 1)[0] if '.' in pure_filename else pure_filename
+    pdf_filename = f"{filename_without_ext}_OCR.pdf"
+    local_pdf_path = f"temp_{pdf_filename}"
 
     try:
         print(f"S3에서 다운로드 시작: {decoded_filename}")
@@ -66,46 +72,49 @@ def run_ocr(filename: str, user_email: str = "", db: Session = Depends(get_db)):
 
         print("OCR 분석 시작...")
         # 다운받은 파일로 OCR 수행
-        text_result = ocr_engine.extract_text(local_path)
+        text_result = ocr_engine.extract_text_and_make_pdf(local_path, local_pdf_path)
         print(f"분석 완료: {text_result[:30]}...")
 
+        print("생성된 PDF를 S3에 업로드 중...")
+        # 생성된 PDF를 S3에 업로드
+        s3_pdf_key = f"ocr_pdfs/{pdf_filename}" 
+        s3_client.upload_file(local_pdf_path, BUCKET_NAME, s3_pdf_key, ExtraArgs={'ContentType': 'application/pdf'})
+        s3_pdf_url = f"https://{BUCKET_NAME}.s3.{AWS_REGION}.amazonaws.com/{s3_pdf_key}"
+
         # ================= DB 저장 로직 =================
-        file_size_bytes = os.path.getsize(local_path)
+        file_size_bytes = os.path.getsize(local_pdf_path)
         size_kb = file_size_bytes / 1024
         file_size_str = f"{size_kb:.1f} KB"
 
         total_pages = 1 
         # OCR은 촬영하거나 기기에 있는 이미지 하나를 업로드 하므로 총 페이지 수를 계산할 필요 없이 1로 고정
 
-        # 1. S3 URL 주소 조립
-        s3_url = f"https://{BUCKET_NAME}.s3.{AWS_REGION}.amazonaws.com/{filename}"
-
-        # 2. 파일명에서 확장자(예: png, jpg) 추출
-        file_extension = decoded_filename.split('.')[-1] if '.' in decoded_filename else "unknown"
-
-        # 3. DB에 넣을 데이터 포장 (INSERT 문과 동일한 역할)
+        file_extension = pure_filename.split('.')[-1].lower() if '.' in pure_filename else "unknown"
+        
+        # DB에 넣을 데이터 포장 (INSERT 문과 동일한 역할)
         new_doc = Document(
-            file_name = decoded_filename,
+            file_name = pure_filename,
             file_type = file_extension,
-            s3_url = s3_url,
+            s3_url = s3_pdf_url,
             extracted_text=text_result,
             file_size = file_size_str,
             page_count = total_pages,
             user_email = user_email
         )
 
-        # 4. DB에 추가하고 저장
+        # DB에 추가하고 저장
         db.add(new_doc)
         db.commit()
         db.refresh(new_doc) #MySQL이 방금 발급해준 고유 ID 번호를 가져온다
 
-        print(f"DB 저장 성공! (문서 번호: {new_doc.id}, 크기: {file_size_str}, 페이지: {total_pages})")
+        print(f"DB 저장 성공! (문서 번호: {new_doc.id}, PDF URL: {s3_pdf_url})")
         # ===================================================
 
-        # 프론트엔드에 추출 텍스트와 함께 부여된 문서 번호 반환
+        # 프론트엔드에 추출 텍스트와 함께 부여된 문서 번호와 새 PDF 주소 반환
         return {
             "id": new_doc.id,
-            "text": text_result
+            "text": text_result,
+            "pdf_url": s3_pdf_url 
         }
 
     except Exception as e:
@@ -116,6 +125,8 @@ def run_ocr(filename: str, user_email: str = "", db: Session = Depends(get_db)):
         # 임시 파일 삭제
         if os.path.exists(local_path):
             os.remove(local_path)
+        if os.path.exists(local_pdf_path):
+            os.remove(local_pdf_path)
 
 if __name__ == "__main__":
     import uvicorn
diff --git a/backend-OCR/requirements.txt b/backend-OCR/requirements.txt
index c00b79edcafe5a18169084aa92603d43ba49f0ca..8aa1c7fdfeb7c26c9faaa1cd3b06641ba4b79361 100644
GIT binary patch
delta 45
ucmZo*TE?`1QH_^@i=l`im7#zkA4r!l<S-;MBr$+Q0~j)ayd0o-IRgO8CkSEy

delta 6
NcmZ3+)WEcW5da4}0n7jZ


From f22af66b58ffbd6df31038f1e120ba7d6b5cd9d2 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Sun, 29 Mar 2026 08:38:42 +0900
Subject: [PATCH 7/8] =?UTF-8?q?=EC=84=9C=EB=B2=84=20=EC=8B=A4=ED=96=89=20?=
 =?UTF-8?q?=EC=8A=A4=ED=81=AC=EB=A6=BD=ED=8A=B8=20=EC=97=85=EB=8D=B0?=
 =?UTF-8?q?=EC=9D=B4=ED=8A=B8=20=EB=B0=8F=20=EC=A0=95=EB=A6=AC?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- start-all.bat, stop-all.bat에 OCR 서버(8001) 구동/종료 커맨드 추가
---
 README.md     |  2 +-
 start-all.bat | 15 ++++++++++-----
 stop-all.bat  | 13 ++++++++-----
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index aa23e74..80397cc 100644
--- a/README.md
+++ b/README.md
@@ -77,7 +77,7 @@ python ocr_server.py
 
 **필요 사항:**
 - 프로젝트 최상위 폴더(`EasyDOC`)에 `.env` 파일 필요 (AWS 키 포함)
-- backend-OCR 폴더 내 `google-key.json` 키 파일 필요
+- backend-OCR 폴더 내 `vision-key.json` 키 파일 필요
 
 ---
 
diff --git a/start-all.bat b/start-all.bat
index 498914d..9dd010e 100644
--- a/start-all.bat
+++ b/start-all.bat
@@ -6,24 +6,28 @@ echo ========================================
 echo.
 
 REM MySQL 서비스 시작 (관리자 권한 필요)
-echo [1/5] MySQL 서비스 시작 중...
+echo [1/6] MySQL 서비스 시작 중...
 powershell -Command "Start-Process powershell -Verb RunAs -ArgumentList '-Command', 'Start-Service MySQL; Write-Host MySQL started; Start-Sleep -Seconds 2'"
 timeout /t 3 /nobreak > nul
 
 REM 파싱 서버 시작 (포트 8000)
-echo [2/5] 파싱 서버 시작 중... (포트 8000)
+echo [2/6] 파싱 서버 시작 중... (포트 8000)
 start "EasyDOC Parser Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd EasyDOC-frontend\easydoc-parser; uvicorn main:app --reload"
 
 REM 백엔드 Spring Boot 시작 (포트 8080)
-echo [3/5] Spring Boot 백엔드 시작 중... (포트 8080)
+echo [3/6] Spring Boot 백엔드 시작 중... (포트 8080)
 start "EasyDOC Backend Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd EasyDOC-backend; .\gradlew.bat bootRun"
 
 REM 최근 문서 DB 서버 시작 (포트 8002)
-echo [4/5] 최근 문서 DB 서버 시작 중... (포트 8002)
+echo [4/6] 최근 문서 DB 서버 시작 중... (포트 8002)
 start "EasyDOC Document API Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd database_document; .\venv\Scripts\python document_api.py"
 
+REM OCR 서버 시작 (포트 8001)
+echo [5/6] OCR 서버 시작 중... (포트 8001)
+start "EasyDOC OCR Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd backend-OCR; .\venv\Scripts\python ocr_server.py"
+
 REM 프론트엔드 시작 (포트 5173)
-echo [5/5] 프론트엔드 시작 중... (포트 5173)
+echo [6/6] 프론트엔드 시작 중... (포트 5173)
 start "EasyDOC Frontend Server" powershell -ExecutionPolicy Bypass -NoExit -Command "cd EasyDOC-frontend; npm run dev"
 
 echo.
@@ -33,6 +37,7 @@ echo ========================================
 echo    - 파싱 서버: http://localhost:8000
 echo    - 백엔드: http://localhost:8080
 echo    - 최근 문서 DB: http://localhost:8002
+echo    - OCR 서버:  http://localhost:8001
 echo    - 프론트엔드: http://localhost:5173
 echo ========================================
 echo.
diff --git a/stop-all.bat b/stop-all.bat
index 1b540ad..3b11d53 100644
--- a/stop-all.bat
+++ b/stop-all.bat
@@ -5,19 +5,22 @@ echo    EasyDOC 전체 서버 종료
 echo ========================================
 echo.
 
-echo [1/5] 프론트엔드 종료 중...
+echo [1/6] 프론트엔드 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Frontend Server*" /F > nul 2>&1
 
-echo [2/5] 백엔드 종료 중...
+echo [2/6] 백엔드 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Backend Server*" /F > nul 2>&1
 
-echo [3/5] 파싱 서버 종료 중...
+echo [3/6] 파싱 서버 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Parser Server*" /F > nul 2>&1
 
-echo [4/5] 최근 문서 DB 서버 종료 중...
+echo [4/6] 최근 문서 DB 서버 종료 중...
 taskkill /FI "WindowTitle eq EasyDOC Document API Server*" /F > nul 2>&1
 
-echo [5/5] Java/Node 프로세스 정리 중...
+echo [5/6] OCR 서버 종료 중...
+taskkill /FI "WindowTitle eq EasyDOC OCR Server*" /F > nul 2>&1
+
+echo [6/6] Java/Node 프로세스 정리 중...
 taskkill /IM java.exe /F > nul 2>&1
 taskkill /IM node.exe /F > nul 2>&1
 taskkill /IM python.exe /F > nul 2>&1

From 6443e3f6a467739799e9312919d529c20ee2b304 Mon Sep 17 00:00:00 2001
From: Sangjoon PARK <sjsj0709@koreatech.ac.kr>
Date: Tue, 31 Mar 2026 16:06:00 +0900
Subject: [PATCH 8/8] =?UTF-8?q?=EB=A7=88=EC=9D=B4=ED=8E=98=EC=9D=B4?=
 =?UTF-8?q?=EC=A7=80=20=EB=8B=A4=EC=9A=B4=EB=A1=9C=EB=93=9C=20=EC=98=A4?=
 =?UTF-8?q?=EB=A5=98=20=EC=88=98=EC=A0=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 EasyDOC-frontend/src/pages/MyPage.jsx | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/EasyDOC-frontend/src/pages/MyPage.jsx b/EasyDOC-frontend/src/pages/MyPage.jsx
index d6866aa..a95d2e8 100644
--- a/EasyDOC-frontend/src/pages/MyPage.jsx
+++ b/EasyDOC-frontend/src/pages/MyPage.jsx
@@ -451,6 +451,15 @@ function HistoryContent({ onDocumentClick, userEmail }) {
         return;
       }
 
+      let finalFileName = fileName;
+
+      // S3 실제 경로는 .pdf가 포함되어 있는데, 원본 파일명이 .pdf로 끝나지 않는 경우 (이미지 파일인 경우)
+      if (s3Url.toLowerCase().includes('.pdf') && !fileName.toLowerCase().endsWith('.pdf')) {
+        // 기존 확장자를 떼어내고 .pdf를 붙여줍니다.
+        const nameWithoutExt = fileName.substring(0, fileName.lastIndexOf('.')) || fileName;
+        finalFileName = `${nameWithoutExt}.pdf`;
+      }
+
       // S3에서 파일을 받아와 내 컴퓨터에 저장
       const fileResponse = await fetch(s3Url);
       const blob = await fileResponse.blob();
@@ -458,7 +467,7 @@ function HistoryContent({ onDocumentClick, userEmail }) {
 
       const link = document.createElement("a");
       link.href = downloadUrl;
-      link.download = fileName;
+      link.download = finalFileName;
       document.body.appendChild(link);
       link.click();