OCR Text Extraction

.env.prod

@@ -2,12 +2,12 @@
 # Connecting to existing 'postgres-db' container in 'arbit-app_arbit-network'
 DB_USER=postgres
 DB_PASSWORD='M@tr!x#149@dm!N'
-DB_NAME=ocr_db
+DB_NAME=ocr
 DB_HOST=postgres-db
 DB_PORT=5432
 
 # Mail Configuration (IMAP)
 MAIL_SERVER=imap.gmail.com
+MAIL_USERNAME=matrixinfotech.it@gmail.com
+MAIL_PASSWORD=qtxsthbxbisgcmqu
 MAIL_PORT=993
-MAIL_USERNAME=your-email@gmail.com
-MAIL_PASSWORD=your-app-password

DEPLOYMENT.md

@@ -9,9 +9,8 @@ This guide describes how to deploy the OCR application on a Linux host (e.g., Ub
 - **Reverse Proxy**: Host Nginx proxies requests to Frontend (Static) and Backend (API).
 
 ## Prerequisites
-- Docker & Docker Compose installed on the host.
-- Nginx installed on the host.
-- Node.js & NPM (for building Angular).
+- **Deployment Host**: Docker & Docker Compose, Nginx.
+- **Build Machine**: Node.js & NPM (to run the package script).
 
 ---
 
@@ -26,9 +25,9 @@ The app connects to your **existing Postgres container** (`postgres-db`) in the
     docker exec -it postgres-db psql -U postgres -c "CREATE DATABASE ocr_db;"
     ```
 
-2.  **Navigate to project root**:
+2.  **Navigate to the packaged directory**:
     ```bash
-    cd /path/to/OCR
+    cd ocr_build
     ```
 
 3.  **Verify Environment**:
@@ -42,7 +41,7 @@ The app connects to your **existing Postgres container** (`postgres-db`) in the
     This will start `ocr_backend` and `ocr_frontend`.
     ```bash
     # Build and start in detached mode
-    docker-compose --env-file .env.prod up -d --build
+    docker-compose up -d --build
     ```
 
 5.  **Verify Status**:
@@ -60,7 +59,7 @@ Since the Frontend is now running in a container on port 8080 (serving `/ocrf/`)
 1.  **Create Config File**:
     Copy the provided config to `/etc/nginx/sites-available/ocr`.
     ```bash
-    sudo cp deployment/nginx.conf /etc/nginx/sites-available/ocr
+    sudo cp nginx_host.conf /etc/nginx/sites-available/ocr
     ```
 
 2.  **Enable Site**:

backend/database.py

@@ -1,5 +1,7 @@
 import os
-from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary
+import urllib.parse
+from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary, Enum as SqlEnum
+from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import sessionmaker, relationship
 from dotenv import load_dotenv
@@ -7,22 +9,11 @@ from dotenv import load_dotenv
 # Load environment variables
 load_dotenv()
 
-DB_USER = os.getenv("DB_USER")
-DB_PASSWORD = os.getenv("DB_PASSWORD")
-DB_HOST = os.getenv("DB_HOST")
-DB_PORT = os.getenv("DB_PORT")
-import urllib.parse
-
-# ... (imports)
-
-# Load environment variables
-load_dotenv()
-
-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_USER = os.getenv("DB_USER", "postgres")
+DB_PASSWORD = os.getenv("DB_PASSWORD", "password")
+DB_HOST = os.getenv("DB_HOST", "localhost")
+DB_PORT = os.getenv("DB_PORT", "5432")
+DB_NAME = os.getenv("DB_NAME", "ocr_db")
 
 encoded_user = urllib.parse.quote_plus(DB_USER)
 encoded_password = urllib.parse.quote_plus(DB_PASSWORD)
@@ -35,6 +26,26 @@ SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
 
 Base = declarative_base()
 
+class Vendor(Base):
+    __tablename__ = "vendors"
+    
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, unique=True, index=True)
+    default_model = Column(String) # 'text' or 'vision'
+    created_at = Column(DateTime)
+
+class Document(Base):
+    __tablename__ = "documents"
+    
+    id = Column(Integer, primary_key=True, index=True)
+    vendor_id = Column(Integer, ForeignKey("vendors.id"), nullable=True)
+    filename = Column(String)
+    upload_date = Column(DateTime)
+    status = Column(String) # 'pending', 'verified'
+    processed_data = Column(JSONB) # Store the verified extraction results
+    
+    vendor = relationship("Vendor")
+
 class Email(Base):
     __tablename__ = "emails"
 
@@ -54,7 +65,7 @@ class Attachment(Base):
     email_id = Column(Integer, ForeignKey("emails.id"))
     filename = Column(String)
     content_type = Column(String)
-    file_content = Column(LargeBinary) # Storing content directly in DB as requested
+    file_content = Column(LargeBinary)
     
     email = relationship("Email", back_populates="attachments")
 

backend/main.py

@@ -85,6 +85,12 @@ class LoginResponse(BaseModel):
     token: str
     message: str
 
+@app.post("/api/login", response_model=LoginResponse)
+def login(request: LoginRequest):
+    if request.username == "admin" and request.password == "admin":
+        return LoginResponse(token="fake-super-secret-token", message="Success")
+    raise HTTPException(status_code=401, detail="Invalid username or password")
+
 class NERResponse(BaseModel):
     text: str
 

docker-compose.yaml

@@ -31,7 +31,7 @@ services:
     container_name: ocr_frontend
     restart: always
     ports:
-      - "8080:80"
+      - "8075:80"
     networks:
       - arbit-network
 

frontend/package.json

@@ -3,7 +3,7 @@
   "version": "0.0.0",
   "scripts": {
     "ng": "ng",
-    "start": "ng serve",
+    "start": "ng serve --proxy-config proxy.conf.json",
     "build": "ng build",
     "watch": "ng build --watch --configuration development",
     "test": "ng test"

frontend/proxy.conf.json

@@ -0,0 +1,10 @@
+{
+  "/ocrb": {
+    "target": "http://localhost:8000",
+    "secure": false,
+    "changeOrigin": true,
+    "pathRewrite": {
+      "^/ocrb": ""
+    }
+  }
+}

frontend/src/app/login/login.component.ts

@@ -26,16 +26,16 @@ import { ToastModule } from 'primeng/toast';
   template: `
     <div class="login-container">
       <p-card header="OCR Admin Login" [style]="{width: '360px'}" styleClass="p-card-shadow">
-        <div class="field">
+        <div class="field mt-4">
             <span class="p-float-label">
                 <input id="username" type="text" pInputText [(ngModel)]="username" class="w-full"> 
-                <label htmlFor="username">Username</label>
+                <label for="username">Username</label>
             </span>
         </div>
         <div class="field mt-4">
             <span class="p-float-label">
                 <input id="password" type="password" pInputText [(ngModel)]="password" class="w-full">
-                <label htmlFor="password">Password</label>
+                <label for="password">Password</label>
             </span>
         </div>
         <div class="mt-4">
@@ -55,6 +55,7 @@ import { ToastModule } from 'primeng/toast';
     }
     .w-full { width: 100%; }
     .mt-4 { margin-top: 1.5rem; }
+    /* PrimeNG handles the rest */
   `]
 })
 export class LoginComponent {

ocr_build/.env

@@ -0,0 +1,13 @@
+# Database Configuration
+# Connecting to existing 'postgres-db' container in 'arbit-app_arbit-network'
+DB_USER=postgres
+DB_PASSWORD='M@tr!x#149@dm!N'
+DB_NAME=ocr
+DB_HOST=postgres-db
+DB_PORT=5432
+
+# Mail Configuration (IMAP)
+MAIL_SERVER=imap.gmail.com
+MAIL_USERNAME=matrixinfotech.it@gmail.com
+MAIL_PASSWORD=qtxsthbxbisgcmqu
+MAIL_PORT=993

ocr_build/DEPLOYMENT.md

@@ -0,0 +1,95 @@
+# OCR Application Deployment Guide
+
+This guide describes how to deploy the OCR application on a Linux host (e.g., Ubuntu/Debian).
+
+## Architecture
+- **Backend**: Containerized (FastAPI, Python 3.9).
+- **Database**: Containerized (PostgreSQL 15).
+- **Frontend**: Static files (Angular) served by Host Nginx.
+- **Reverse Proxy**: Host Nginx proxies requests to Frontend (Static) and Backend (API).
+
+## Prerequisites
+- **Deployment Host**: Docker & Docker Compose, Nginx.
+- **Build Machine**: Node.js & NPM (to run the package script).
+
+---
+
+## 1. Full Stack Deployment (Docker)
+
+The app connects to your **existing Postgres container** (`postgres-db`) in the `arbit-app_arbit-network`.
+
+1.  **Create the Database**:
+    Since we are using an existing postgres instance, we must manually create the `ocr_db`.
+    ```bash
+    # Run this on your host to create the DB inside the existing container
+    docker exec -it postgres-db psql -U postgres -c "CREATE DATABASE ocr_db;"
+    ```
+
+2.  **Navigate to the packaged directory**:
+    ```bash
+    cd ocr_build
+    ```
+
+3.  **Verify Environment**:
+    Ensure `.env.prod` exists and points to `DB_HOST=postgres-db`.
+    **Also configure your Email credentials** in `.env.prod` if you want the Mailbox feature to work (Gmail requires an App Password).
+    ```bash
+    cat .env.prod
+    ```
+
+4.  **Start App Containers**:
+    This will start `ocr_backend` and `ocr_frontend`.
+    ```bash
+    # Build and start in detached mode
+    docker-compose up -d --build
+    ```
+
+5.  **Verify Status**:
+    ```bash
+    docker-compose ps
+    ```
+    You should see `ocr_backend` and `ocr_frontend` running.
+
+---
+
+## 2. Nginx Configuration (Host Reverse Proxy)
+
+Since the Frontend is now running in a container on port 8080 (serving `/ocrf/`), we configure the Host Nginx to proxy traffic to it.
+
+1.  **Create Config File**:
+    Copy the provided config to `/etc/nginx/sites-available/ocr`.
+    ```bash
+    sudo cp nginx_host.conf /etc/nginx/sites-available/ocr
+    ```
+
+2.  **Enable Site**:
+    ```bash
+    sudo ln -s /etc/nginx/sites-available/ocr /etc/nginx/sites-enabled/
+    ```
+
+3.  **Test & Reload**:
+    ```bash
+    sudo nginx -t
+    sudo systemctl reload nginx
+    ```
+
+---
+
+## 3. Verification
+
+- **Url**: `http://app.technobeesolutions.in/ocrf/` (Proxies to Frontend Container)
+- **API**: `http://app.technobeesolutions.in/ocrb/` (Proxies to Backend Container)
+
+---
+
+## 4. Troubleshooting
+
+- **Logs**:
+    ```bash
+    docker-compose logs -f backend
+    ```
+- **Database**:
+    Connect via the existing container:
+    ```bash
+    docker exec -it postgres-db psql -U postgres -d ocr_db
+    ```

ocr_build/backend/.env

@@ -0,0 +1,11 @@
+DB_USER=postgres
+DB_PASSWORD=M@tr!x#149@dm!N
+DB_HOST=192.168.0.111
+DB_PORT=7925
+DB_NAME=ocr
+
+# Mail Configuration (Gmail)
+MAIL_SERVER=imap.gmail.com
+MAIL_USERNAME=matrixinfotech.it@gmail.com
+MAIL_PASSWORD=qtxsthbxbisgcmqu
+MAIL_PORT=993

ocr_build/backend/Dockerfile

@@ -0,0 +1,30 @@
+# Use official lightweight Python image
+FROM python:3.9-slim
+
+# Install system dependencies
+# tesseract-ocr: for pytesseract
+# poppler-utils: for pdf2image
+# libtesseract-dev: development headers
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr \
+    poppler-utils \
+    libtesseract-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose port (default for Uvicorn)
+EXPOSE 8000
+
+# Run the application
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

ocr_build/backend/create_tables.py

@@ -0,0 +1,12 @@
+from database import engine, Base
+
+def create_tables():
+    print("Creating tables in database...")
+    try:
+        Base.metadata.create_all(bind=engine)
+        print("Tables created successfully!")
+    except Exception as e:
+        print(f"Error creating tables: {e}")
+
+if __name__ == "__main__":
+    create_tables()

ocr_build/backend/database.py

@@ -0,0 +1,77 @@
+import os
+import urllib.parse
+from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary, Enum as SqlEnum
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import sessionmaker, relationship
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+DB_USER = os.getenv("DB_USER", "postgres")
+DB_PASSWORD = os.getenv("DB_PASSWORD", "password")
+DB_HOST = os.getenv("DB_HOST", "localhost")
+DB_PORT = os.getenv("DB_PORT", "5432")
+DB_NAME = os.getenv("DB_NAME", "ocr_db")
+
+encoded_user = urllib.parse.quote_plus(DB_USER)
+encoded_password = urllib.parse.quote_plus(DB_PASSWORD)
+
+# SQLAlchemy Database URL
+DATABASE_URL = f"postgresql://{encoded_user}:{encoded_password}@{DB_HOST}:{DB_PORT}/{DB_NAME}"
+
+engine = create_engine(DATABASE_URL)
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+Base = declarative_base()
+
+class Vendor(Base):
+    __tablename__ = "vendors"
+    
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, unique=True, index=True)
+    default_model = Column(String) # 'text' or 'vision'
+    created_at = Column(DateTime)
+
+class Document(Base):
+    __tablename__ = "documents"
+    
+    id = Column(Integer, primary_key=True, index=True)
+    vendor_id = Column(Integer, ForeignKey("vendors.id"), nullable=True)
+    filename = Column(String)
+    upload_date = Column(DateTime)
+    status = Column(String) # 'pending', 'verified'
+    processed_data = Column(JSONB) # Store the verified extraction results
+    
+    vendor = relationship("Vendor")
+
+class Email(Base):
+    __tablename__ = "emails"
+
+    id = Column(Integer, primary_key=True, index=True)
+    subject = Column(String, index=True)
+    sender = Column(String, index=True)
+    body = Column(Text)
+    received_date = Column(DateTime)
+    is_read = Column(Boolean, default=False)
+
+    attachments = relationship("Attachment", back_populates="email")
+
+class Attachment(Base):
+    __tablename__ = "attachments"
+
+    id = Column(Integer, primary_key=True, index=True)
+    email_id = Column(Integer, ForeignKey("emails.id"))
+    filename = Column(String)
+    content_type = Column(String)
+    file_content = Column(LargeBinary)
+    
+    email = relationship("Email", back_populates="attachments")
+
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()

ocr_build/backend/generate_tests.py

@@ -0,0 +1,20 @@
+from reportlab.pdfgen import canvas
+from PIL import Image, ImageDraw
+
+def create_pdf(filename, text):
+    c = canvas.Canvas(filename)
+    c.drawString(100, 750, text)
+    c.save()
+    print(f"Created {filename}")
+
+def create_image(filename, text):
+    img = Image.new('RGB', (400, 100), color = (255, 255, 255))
+    d = ImageDraw.Draw(img)
+    # Default font is usually tiny, but readable by tesseract
+    d.text((10,10), text, fill=(0,0,0))
+    img.save(filename)
+    print(f"Created {filename}")
+
+if __name__ == "__main__":
+    create_pdf("test_ocr.pdf", "Hello World PDF OCR")
+    create_image("test_ocr.png", "Hello World Image OCR")

ocr_build/backend/mail_service.py

@@ -0,0 +1,95 @@
+import os
+import datetime
+import mimetypes
+import time
+from imap_tools import MailBox, AND
+from sqlalchemy.orm import Session
+from database import SessionLocal, Email, Attachment
+from dotenv import load_dotenv
+
+load_dotenv()
+
+MAIL_SERVER = os.getenv("MAIL_SERVER")
+MAIL_USERNAME = os.getenv("MAIL_USERNAME")
+MAIL_PASSWORD = os.getenv("MAIL_PASSWORD")
+MAIL_PORT = int(os.getenv("MAIL_PORT", 993))
+
+def fetch_and_store_emails():
+    """
+    Connects to Gmail, fetches UNREAD emails, stores them in DB, and marks as READ.
+    """
+    print(f"[{datetime.datetime.now()}] Checking for new emails...")
+    
+    if not MAIL_USERNAME or not MAIL_PASSWORD or MAIL_USERNAME == "your-email@gmail.com":
+        print("Skipping Email Sync: Credentials not configured.")
+        return {"status": "skipped", "message": "Credentials not configured"}
+
+    db: Session = SessionLocal()
+    count = 0
+    
+    try:
+        # Connect to Inbox
+        # imap-tools MailBox defaults to SSL (port 993) if not specified, but we make it explicit here.
+        with MailBox(MAIL_SERVER, port=MAIL_PORT).login(MAIL_USERNAME, MAIL_PASSWORD, initial_folder='INBOX') as mailbox:
+            # Fetch UNREAD emails
+            for msg in mailbox.fetch(AND(seen=False)):
+                print(f"Processing Email: {msg.subject}")
+                
+                # Check if already exists (optional, but good practice if marking read fails)
+                # For now using simplistic approach: if we fetch it, we save it.
+                
+                new_email = Email(
+                    subject=msg.subject,
+                    sender=msg.from_,
+                    body=msg.text or msg.html,
+                    received_date=msg.date,
+                    is_read=False # Consumed by app, but 'seen' on server
+                )
+                db.add(new_email)
+                db.commit() # Commit to get ID
+                db.refresh(new_email)
+                
+                
+                # Process Attachments
+                for i, att in enumerate(msg.attachments):
+                    filename = att.filename
+                    if not filename:
+                        # Fallback for missing filename
+                        ext = mimetypes.guess_extension(att.content_type) or ".bin"
+                        timestamp = int(time.time())
+                        filename = f"attachment_{timestamp}_{i}{ext}"
+                    
+                    print(f"  - Attachment: {filename}")
+                    new_attachment = Attachment(
+                        email_id=new_email.id,
+                        filename=filename,
+                        content_type=att.content_type,
+                        file_content=att.payload # raw bytes
+                    )
+                    db.add(new_attachment)
+                
+                db.commit()
+                
+                # Mark as Read on Server (Auto-done by fetch unless bulk=True or mark_seen=False)
+                # imap-tools fetches are auto-seen by default.
+                count += 1
+                
+        print(f"Sync Complete. {count} new emails.")
+        return {"status": "success", "count": count}
+
+    except Exception as e:
+        error_msg = str(e)
+        print(f"Error fetching emails: {error_msg}")
+        
+        if "AUTHENTICATIONFAILED" in error_msg or "Invalid credentials" in error_msg:
+             return {
+                 "status": "error", 
+                 "message": f"Authentication Failed: {error_msg}. \n[HINT]: If using Gmail, you MUST use an 'App Password', not your login password. Also ensure IMAP is enabled in Gmail Settings."
+             }
+             
+        return {"status": "error", "message": error_msg}
+    finally:
+        db.close()
+
+if __name__ == "__main__":
+    fetch_and_store_emails()

ocr_build/backend/main.py

@@ -0,0 +1,263 @@
+import io
+import datetime
+from typing import Optional, List
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI, File, UploadFile, HTTPException, Depends
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from pypdf import PdfReader
+import pytesseract
+from PIL import Image
+from pdf2image import convert_from_bytes
+import pdfplumber
+from sqlalchemy.orm import Session
+
+
+
+# 2. OCR Module
+def extract_text_from_pdf(file_bytes: bytes) -> str:
+    # Try pdfplumber first for layout preservation
+    try:
+        with pdfplumber.open(io.BytesIO(file_bytes)) as pdf:
+            text = ""
+            for page in pdf.pages:
+                page_text = page.extract_text(layout=True)
+                if page_text:
+                    text += page_text + "\n"
+            if text.strip():
+                return text.strip()
+    except Exception as e:
+        print(f"pdfplumber error: {e}")
+
+    # Fallback to pypdf
+    try:
+        reader = PdfReader(io.BytesIO(file_bytes))
+        text = ""
+        for page in reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
+        return text.strip()
+    except Exception as e:
+        print(f"Error reading PDF: {e}")
+        return ""
+
+# Internal modules
+from database import get_db, Email
+from scheduler import start_scheduler, stop_scheduler
+from mail_service import fetch_and_store_emails
+
+# Lifespan for Scheduler
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # Startup
+    start_scheduler()
+    yield
+    # Shutdown
+    stop_scheduler()
+
+app = FastAPI(lifespan=lifespan)
+
+# CORS configuration
+origins = [
+    "http://localhost",
+    "http://localhost:3000",
+    "http://localhost:5173", # Vite default
+    "http://localhost:4200", # Angular default
+    "http://127.0.0.1:4200",
+]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Models
+class LoginRequest(BaseModel):
+    username: str
+    password: str
+
+class LoginResponse(BaseModel):
+    token: str
+    message: str
+
+@app.post("/api/login", response_model=LoginResponse)
+def login(request: LoginRequest):
+    if request.username == "admin" and request.password == "admin":
+        return LoginResponse(token="fake-super-secret-token", message="Success")
+    raise HTTPException(status_code=401, detail="Invalid username or password")
+
+class NERResponse(BaseModel):
+    text: str
+
+
+
+def extract_text_from_image(file_bytes: bytes) -> str:
+    try:
+        image = Image.open(io.BytesIO(file_bytes))
+        text = pytesseract.image_to_string(image)
+        return text.strip()
+    except Exception as e:
+        print(f"Error reading Image: {e}")
+        return ""
+
+@app.post("/api/ocr/extract", response_model=NERResponse)
+async def extract_text(file: UploadFile = File(...)):
+    content = await file.read()
+    filename = file.filename.lower()
+    
+    extracted_text = ""
+    
+    if filename.endswith(".pdf"):
+        # Try text extraction first
+        extracted_text = extract_text_from_pdf(content)
+        
+        # If text is empty, it might be a scanned PDF. 
+        if not extracted_text.strip():
+             try:
+                 images = convert_from_bytes(content)
+                 for i, image in enumerate(images):
+                     page_text = pytesseract.image_to_string(image)
+                     extracted_text += f"\n--- Page {i+1} ---\n{page_text}"
+             except Exception as e:
+                 extracted_text = f"Error processing Scanned PDF: {str(e)}\n\n(Hint: Ensure 'poppler' is installed on your system. Run 'brew install poppler')"
+
+    elif filename.endswith((".png", ".jpg", ".jpeg", ".tiff", ".bmp")):
+        extracted_text = extract_text_from_image(content)
+    else:
+        raise HTTPException(status_code=400, detail="Unsupported file type")
+    
+    return NERResponse(text=extracted_text)
+
+import zipfile
+import mimetypes
+from fastapi.responses import StreamingResponse
+
+class EmailDTO(BaseModel):
+    id: int
+    subject: Optional[str]
+    sender: Optional[str]
+    received_date: Optional[datetime.datetime]
+    is_read: bool
+    has_attachments: bool = False
+
+class AttachmentDTO(BaseModel):
+    id: int
+    filename: str
+    content_type: str
+
+class EmailListResponse(BaseModel):
+    items: List[EmailDTO]
+    total: int
+
+class EmailDetailDTO(EmailDTO):
+    body: Optional[str]
+    attachments: List[AttachmentDTO]
+
+@app.get("/api/emails", response_model=EmailListResponse)
+def get_emails(skip: int = 0, limit: int = 50, db: Session = Depends(get_db)):
+    total = db.query(Email).count()
+    emails = db.query(Email).order_by(Email.received_date.desc()).offset(skip).limit(limit).all()
+    
+    items = [
+        EmailDTO(
+            id=e.id, 
+            subject=e.subject, 
+            sender=e.sender, 
+            received_date=e.received_date, 
+            is_read=e.is_read,
+            has_attachments=bool(e.attachments) # Check if list is not empty
+        ) for e in emails
+    ]
+    return EmailListResponse(items=items, total=total)
+
+# ...
+
+@app.get("/api/emails/{email_id}", response_model=EmailDetailDTO)
+def get_email_details(email_id: int, db: Session = Depends(get_db)):
+    email = db.query(Email).filter(Email.id == email_id).first()
+    if not email:
+        raise HTTPException(status_code=404, detail="Email not found")
+    
+    # Mark as read if opened
+    if not email.is_read:
+        email.is_read = True
+        db.commit()
+    
+    # Safely handle missing content_type and filename
+    attachments = []
+    for a in email.attachments:
+        fname = a.filename
+        if not fname or fname == "unknown":
+            ext = mimetypes.guess_extension(a.content_type or "") or ".bin"
+            fname = f"attachment_{a.id}{ext}"
+            
+        attachments.append(
+            AttachmentDTO(
+                id=a.id, 
+                filename=fname, 
+                content_type=a.content_type or "application/octet-stream"
+            )
+        )
+        
+    return EmailDetailDTO(
+        id=email.id,
+        subject=email.subject,
+        sender=email.sender,
+        received_date=email.received_date,
+        is_read=email.is_read,
+        has_attachments=bool(email.attachments),
+        body=email.body,
+        attachments=attachments
+    )
+
+@app.get("/api/emails/{email_id}/download-all")
+def download_all_attachments(email_id: int, db: Session = Depends(get_db)):
+    email = db.query(Email).filter(Email.id == email_id).first()
+    if not email:
+        raise HTTPException(status_code=404, detail="Email not found")
+        
+    if not email.attachments:
+         raise HTTPException(status_code=400, detail="No attachments found")
+
+    # Create a zip file in memory
+    zip_buffer = io.BytesIO()
+    with zipfile.ZipFile(zip_buffer, "w", zipfile.ZIP_DEFLATED) as zip_file:
+        for att in email.attachments:
+            # Use filename from DB, ensure unique names if duplicates exist (simple append here)
+            zip_file.writestr(att.filename, att.file_content)
+    
+    zip_buffer.seek(0)
+    
+    return StreamingResponse(
+        zip_buffer,
+        media_type="application/zip",
+        headers={"Content-Disposition": f"attachment; filename=email-{email_id}-attachments.zip"}
+    )
+
+@app.get("/api/attachments/{attachment_id}")
+def download_attachment(attachment_id: int, view: bool = False, db: Session = Depends(get_db)):
+    attachment = db.query(DBAttachment).filter(DBAttachment.id == attachment_id).first()
+    if not attachment:
+        raise HTTPException(status_code=404, detail="Attachment not found")
+    
+    disposition = "inline" if view else "attachment"
+    
+    return StreamingResponse(
+        io.BytesIO(attachment.file_content), 
+        media_type=attachment.content_type,
+        headers={"Content-Disposition": f"{disposition}; filename={attachment.filename}"}
+    )
+
+@app.post("/api/emails/sync")
+def sync_emails():
+    result = fetch_and_store_emails()
+    return result
+
+@app.get("/")
+def read_root():
+    return {"message": "OCR Backend API is running"}

ocr_build/backend/requirements.txt

@@ -0,0 +1,13 @@
+fastapi
+uvicorn
+python-multipart
+pypdf
+pytesseract
+Pillow
+sqlalchemy
+psycopg2-binary
+imap-tools
+apscheduler
+python-dotenv
+pdfplumber
+pdf2image

ocr_build/backend/scheduler.py

@@ -0,0 +1,14 @@
+from apscheduler.schedulers.background import BackgroundScheduler
+from mail_service import fetch_and_store_emails
+
+scheduler = BackgroundScheduler()
+
+def start_scheduler():
+    # Add job to run every 10 seconds
+    scheduler.add_job(fetch_and_store_emails, 'interval', seconds=10, id='mail_sync_job', replace_existing=True)
+    scheduler.start()
+    print("Mail Scheduler Started (Interval: 10s)")
+
+def stop_scheduler():
+    scheduler.shutdown()
+    print("Mail Scheduler Stopped")

ocr_build/backend/test.txt

@@ -0,0 +1 @@
+This is a test PDF content

ocr_build/backend/test_ocr.pdf

@@ -0,0 +1,68 @@
+%PDF-1.3
+%<25><><EFBFBD><EFBFBD> ReportLab Generated PDF document (opensource)
+1 0 obj
+<<
+/F1 2 0 R
+>>
+endobj
+2 0 obj
+<<
+/BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font
+>>
+endobj
+3 0 obj
+<<
+/Contents 7 0 R /MediaBox [ 0 0 595.2756 841.8898 ] /Parent 6 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+4 0 obj
+<<
+/PageMode /UseNone /Pages 6 0 R /Type /Catalog
+>>
+endobj
+5 0 obj
+<<
+/Author (anonymous) /CreationDate (D:20260121205329+05'00') /Creator (anonymous) /Keywords () /ModDate (D:20260121205329+05'00') /Producer (ReportLab PDF Library - \(opensource\)) 
+  /Subject (unspecified) /Title (untitled) /Trapped /False
+>>
+endobj
+6 0 obj
+<<
+/Count 1 /Kids [ 3 0 R ] /Type /Pages
+>>
+endobj
+7 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 115
+>>
+stream
+GapQh0E=F,0U\H3T\pNYT^QKk?tc>IP,;W#U1^23ihPEM_?CW4KISi90MjG^2,FS#<RC5+c,n(/#gY0H8Pob4EDu@N%an;^a\iDl!bkQj!W^(m'ef~>endstream
+endobj
+xref
+0 8
+0000000000 65535 f 
+0000000061 00000 n 
+0000000092 00000 n 
+0000000199 00000 n 
+0000000402 00000 n 
+0000000470 00000 n 
+0000000731 00000 n 
+0000000790 00000 n 
+trailer
+<<
+/ID 
+[<6da718d498e92fec48910ff2674542d2><6da718d498e92fec48910ff2674542d2>]
+% ReportLab generated PDF document -- digest (opensource)
+
+/Info 5 0 R
+/Root 4 0 R
+/Size 8
+>>
+startxref
+995
+%%EOF

ocr_build/docker-compose.yaml

@@ -0,0 +1,41 @@
+services:
+  # Backend API
+  backend:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: ocr_backend
+    restart: always
+    environment:
+      DB_USER: ${DB_USER}
+      DB_PASSWORD: ${DB_PASSWORD}
+      DB_HOST: ${DB_HOST} 
+      DB_PORT: ${DB_PORT}
+      DB_NAME: ${DB_NAME}
+      
+      # Mail Config
+      MAIL_SERVER: ${MAIL_SERVER}
+      MAIL_PORT: ${MAIL_PORT}
+      MAIL_USERNAME: ${MAIL_USERNAME}
+      MAIL_PASSWORD: ${MAIL_PASSWORD}
+    ports:
+      - "8000:8000"
+    networks:
+      - arbit-network
+
+  # Frontend Angular App
+  frontend:
+    build:
+      context: ./frontend
+      dockerfile: Dockerfile
+    container_name: ocr_frontend
+    restart: always
+    ports:
+      - "8075:80"
+    networks:
+      - arbit-network
+
+networks:
+  arbit-network:
+    external: true
+    name: arbit-app_arbit-network

ocr_build/frontend/Dockerfile

@@ -0,0 +1,18 @@
+FROM nginx:alpine
+
+# Remove default nginx static assets
+RUN rm -rf /usr/share/nginx/html/*
+
+# Create target directory
+RUN mkdir -p /usr/share/nginx/html/ocrf
+
+# Copy Pre-built assets (from local dist)
+COPY dist /usr/share/nginx/html/ocrf
+
+# Copy custom nginx config
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+
+# Expose port 80
+EXPOSE 80
+
+CMD ["nginx", "-g", "daemon off;"]

ocr_build/frontend/dist/index.html

@@ -0,0 +1,18 @@
+<!doctype html>
+<html lang="en" data-beasties-container>
+<head>
+  <meta charset="utf-8">
+  <title>Frontend</title>
+  <base href="/ocrf/">
+  <meta name="viewport" content="width=device-width, initial-scale=1">
+  <link rel="icon" type="image/x-icon" href="favicon.ico">
+  <!-- PrimeNG Theme -->
+  <link id="theme-css" rel="stylesheet" type="text/css" href="https://unpkg.com/primeng@17.18.0/resources/themes/lara-light-blue/theme.css">
+  <link rel="stylesheet" type="text/css" href="https://unpkg.com/primeng@17.18.0/resources/primeng.min.css">
+  <!-- PrimeFlex -->
+  <link rel="stylesheet" href="https://unpkg.com/primeflex@3.3.1/primeflex.css">
+<style>@-webkit-keyframes fa-spin{0%{-webkit-transform:rotate(0deg);transform:rotate(0)}to{-webkit-transform:rotate(359deg);transform:rotate(359deg)}}html,body{margin:0;font-family:var(--font-family);background-color:var(--surface-ground);height:100%}</style><link rel="stylesheet" href="styles-4O3ZUZOP.css" media="print" onload="this.media='all'"><noscript><link rel="stylesheet" href="styles-4O3ZUZOP.css"></noscript></head>
+<body>
+  <app-root></app-root>
+<link rel="modulepreload" href="chunk-IMH4GOJN.js"><script src="polyfills-6ISPNSXF.js" type="module"></script><script src="main-ZCNRUEIP.js" type="module"></script></body>
+</html>

ocr_build/frontend/nginx.conf

@@ -0,0 +1,16 @@
+server {
+    listen 80;
+    server_name localhost;
+    root /usr/share/nginx/html/ocrf;
+    index index.html;
+
+    location / {
+        try_files $uri $uri/ /index.html;
+    }
+
+    # Optional: Cache static assets
+    location ~* \.(js|css|png|jpg|jpeg|gif|ico)$ {
+        expires 1y;
+        add_header Cache-Control "public, no-transform";
+    }
+}

ocr_build/nginx_host.conf

@@ -0,0 +1,22 @@
+server {
+    listen 80;
+    server_name app.technobeesolutions.in;
+
+    # Proxy Angular Frontend Container
+    location /ocrf/ {
+        proxy_pass http://localhost:8080/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+
+    # Proxy API requests to the Docker Backend
+    location /ocrb/ {
+        proxy_pass http://localhost:8000/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+}

package_release.sh

@@ -0,0 +1,65 @@
+#!/bin/bash
+
+# Exit on error
+set -e
+
+ECHO "📦 Starting Release Package Process..."
+
+# 1. Clean previous build
+rm -rf ocr_build
+mkdir -p ocr_build
+
+# 2. Build Frontend Locally
+echo "🏗️  Building Angular Frontend (Base Href: /ocrf/)..."
+cd frontend
+npm install --legacy-peer-deps
+npm run build -- --configuration production --base-href /ocrf/
+cd ..
+
+# 3. Prepare Frontend Artifacts
+echo "📂 Preparing Frontend Packaging..."
+mkdir -p ocr_build/frontend
+# Copy the compiled 'browser' folder to ocr_build/frontend/dist
+cp -r frontend/dist/frontend/browser ocr_build/frontend/dist
+# Copy the internal nginx config
+cp frontend/nginx.conf ocr_build/frontend/
+
+# Create a lightweight Production Dockerfile for Frontend
+# This replaces the multi-stage build with a single stage serving pre-built files
+cat <<EOF > ocr_build/frontend/Dockerfile
+FROM nginx:alpine
+
+# Remove default nginx static assets
+RUN rm -rf /usr/share/nginx/html/*
+
+# Create target directory
+RUN mkdir -p /usr/share/nginx/html/ocrf
+
+# Copy Pre-built assets (from local dist)
+COPY dist /usr/share/nginx/html/ocrf
+
+# Copy custom nginx config
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+
+# Expose port 80
+EXPOSE 80
+
+CMD ["nginx", "-g", "daemon off;"]
+EOF
+
+# 4. Prepare Backend Artifacts
+echo "🐍 Preparing Backend Packaging..."
+mkdir -p ocr_build/backend
+# Copy Backend Source (Excluding venv and pycache)
+rsync -av --progress backend/ ocr_build/backend/ --exclude venv --exclude __pycache__ --exclude .pytest_cache --exclude uploads
+
+# 5. Copy Root Configurations
+echo "⚙️  Copying Configuration files..."
+cp docker-compose.yaml ocr_build/
+cp .env.prod ocr_build/.env
+cp deployment/nginx.conf ocr_build/nginx_host.conf
+cp DEPLOYMENT.md ocr_build/
+
+echo "✅ Release Package Created: ./ocr_build"
+echo "   Transfer the 'ocr_build' folder to your Linux server and run:"
+echo "   cd ocr_build && docker-compose --env-file .env.prod up -d --build"