Added Login + Working on pdf creation

requirements.txt

@@ -7,6 +7,7 @@ billiard==4.2.1
 celery==5.5.3
 certifi==2025.8.3
 cffi==2.0.0
+charset-normalizer==3.4.3
 click==8.2.1
 click-didyoumean==0.3.1
 click-plugins==1.1.1.2
@@ -26,10 +27,12 @@ importlib_metadata==8.7.0
 iniconfig==2.1.0
 izulu==0.50.0
 kombu==5.5.4
+lxml==6.0.2
 mongomock==4.3.0
 mongomock-motor==0.0.36
 motor==3.7.1
 packaging==25.0
+pillow==11.3.0
 pipdeptree==2.28.0
 pluggy==1.6.0
 prompt_toolkit==3.0.52
@@ -41,16 +44,19 @@ pydantic_core==2.33.2
 Pygments==2.19.2
 PyJWT==2.10.1
 pymongo==4.15.1
+pypandoc==1.15
 pytest==8.4.2
 pytest-asyncio==1.2.0
 pytest-mock==3.15.1
 python-dateutil==2.9.0.post0
+python-docx==1.2.0
 python-dotenv==1.1.1
 python-magic==0.4.27
 python-multipart==0.0.20
 pytz==2025.2
 PyYAML==6.0.2
 redis==6.4.0
+reportlab==4.4.4
 rsa==4.9.1
 sentinels==1.1.1
 six==1.17.0

src/file-processor/Dockerfile

@@ -7,6 +7,9 @@ WORKDIR /app
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libmagic1 \
     file \
+    pandoc \
+    ghostscript \
+    texlive-xetex \
  && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements and install dependencies

src/file-processor/app/config/settings.py

@@ -34,22 +34,6 @@ def get_redis_url() -> str:
   return os.getenv("REDIS_URL", "redis://localhost:6379/0")
 
 
-# def get_redis_host() -> str:
-#   redis_url = get_redis_url()
-#   if redis_url.startswith("redis://"):
-#     return redis_url.split("redis://")[1].split("/")[0]
-#   else:
-#     return redis_url
-#
-#
-# def get_redis_port() -> int:
-#   redis_url = get_redis_url()
-#   if redis_url.startswith("redis://"):
-#     return int(redis_url.split("redis://")[1].split("/")[0].split(":")[1])
-#   else:
-#     return int(redis_url.split(":")[1])
-
-
 def get_jwt_secret_key() -> str:
   """
   Get JWT secret key from environment variables.
@@ -114,6 +98,11 @@ def get_objects_folder() -> str:
   return os.getenv("OBJECTS_FOLDER", "/objects")
 
 
-def watch_directory() -> str:
+def get_watch_folder() -> str:
   """Directory to monitor for new files"""
   return os.getenv("WATCH_DIRECTORY", "/watched_files")
+
+
+def get_temp_folder() -> str:
+  """Directory to store temporary files"""
+  return os.getenv("TEMP_DIRECTORY", "/temp")

src/file-processor/app/file_watcher.py

@@ -63,17 +63,15 @@ class DocumentFileEventHandler(FileSystemEventHandler):
     
     logger.info(f"Processing new file: {filepath}")
     
-    #    try:
+    try:
-    from tasks.document_processing import process_document
+      from tasks.document_processing import process_document
-    task_result = process_document.delay(filepath)
+      task_result = process_document.delay(filepath)
-    print(task_result)
+      task_id = task_result.task_id
-    print("hello world")
+      logger.info(f"Dispatched Celery task with ID: {task_id}")
-    # task_id = task_result.task_id
-    # logger.info(f"Dispatched Celery task with ID: {task_id}")
     
-    # except Exception as e:
+    except Exception as e:
-    #   logger.error(f"Failed to process file {filepath}: {str(e)}")
+      logger.error(f"Failed to process file {filepath}: {str(e)}")
-    #   # Note: We don't re-raise the exception to keep the watcher running
+      # Note: We don't re-raise the exception to keep the watcher running
 
 
 class FileWatcher:

src/file-processor/app/main.py

@@ -65,12 +65,12 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
     
     # Create and start file watcher
     file_watcher = create_file_watcher(
-      watch_directory=settings.watch_directory(),
+      watch_directory=settings.get_watch_folder(),
       document_service=document_service,
       job_service=job_service
     )
     file_watcher.start()
-    logger.info(f"FileWatcher started for directory: {settings.watch_directory()}")
+    logger.info(f"FileWatcher started for directory: {settings.get_watch_folder()}")
     
     logger.info("Application startup completed successfully")
     
@@ -102,7 +102,7 @@ app = FastAPI(
 # Configure CORS
 app.add_middleware(
   CORSMiddleware,
-  allow_origins=["http://localhost:5173"],  # React frontend
+  allow_origins=["http://localhost:5173", "http://localhost:5174"],  # React frontend
   allow_credentials=True,
   allow_methods=["*"],
   allow_headers=["*"],

src/file-processor/requirements.txt

@@ -5,11 +5,14 @@ email-validator==2.3.0
 fastapi==0.116.1
 httptools==0.6.4
 motor==3.7.1
+pillow==11.3.0
 pydantic==2.11.9
 PyJWT==2.10.1
 pymongo==4.15.0
+pypandoc==1.15
 python-multipart==0.0.20
 redis==6.4.0
+reportlab==4.4.4
 uvicorn==0.35.0
 python-magic==0.4.27
 watchdog==6.0.0

src/frontend/package-lock.json

@@ -12,6 +12,7 @@
         "axios": "^1.12.2",
         "react": "^19.1.1",
         "react-dom": "^19.1.1",
+        "react-icons": "^5.5.0",
         "react-router-dom": "^7.9.3"
       },
       "devDependencies": {
@@ -3377,6 +3378,15 @@
         "react": "^19.1.1"
       }
     },
+    "node_modules/react-icons": {
+      "version": "5.5.0",
+      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.5.0.tgz",
+      "integrity": "sha512-MEFcXdkP3dLo8uumGI5xN3lDFNsRtrjbOEKDLD7yv76v4wpnEq2Lt2qeHaQOr34I/wPN3s3+N08WkQ+CW37Xiw==",
+      "license": "MIT",
+      "peerDependencies": {
+        "react": "*"
+      }
+    },
     "node_modules/react-refresh": {
       "version": "0.17.0",
       "resolved": "https://registry.npmjs.org/react-refresh/-/react-refresh-0.17.0.tgz",

src/frontend/package.json

@@ -14,6 +14,7 @@
     "axios": "^1.12.2",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
+    "react-icons": "^5.5.0",
     "react-router-dom": "^7.9.3"
   },
   "devDependencies": {

src/frontend/src/assets/icons.jsx

@@ -0,0 +1,35 @@
+// src/assets/icons.jsx
+
+export const SunIcon = (
+  <svg
+    xmlns="http://www.w3.org/2000/svg"
+    className="h-6 w-6"
+    fill="none"
+    viewBox="0 0 24 24"
+    stroke="currentColor"
+  >
+    <path
+      strokeLinecap="round"
+      strokeLinejoin="round"
+      strokeWidth="2"
+      d="M12 3v1m0 16v1m8.66-9h-1M4.34 12h-1m15.36 6.36l-.7-.7M6.34 6.34l-.7-.7m12.02 12.02l-.7-.7M6.34 17.66l-.7-.7M16 12a4 4 0 11-8 0 4 4 0 018 0z"
+    />
+  </svg>
+);
+
+export const MoonIcon = (
+  <svg
+    xmlns="http://www.w3.org/2000/svg"
+    className="h-6 w-6"
+    fill="none"
+    viewBox="0 0 24 24"
+    stroke="currentColor"
+  >
+    <path
+      strokeLinecap="round"
+      strokeLinejoin="round"
+      strokeWidth="2"
+      d="M21 12.79A9 9 0 1111.21 3a7 7 0 0010.79 9.79z"
+    />
+  </svg>
+);

src/frontend/src/components/auth/AuthLayout.jsx

@@ -8,13 +8,27 @@ import ThemeSwitcher from "../common/ThemeSwither.jsx";
  * @param {Object} props - Component props
  * @param {React.ReactNode} props.children - Child components to render
  */
+
+const AuthHeader = () => {
+  return (
+    <div className="navbar bg-base-100 shadow-lg">
+      <div className="navbar-start">
+        <h1 className="text-xl font-bold">MyDocManager</h1>
+      </div>
+      <div className="navbar-end">
+        <ThemeSwitcher/>
+      </div>
+    </div>
+  )
+}
+
 function AuthLayout({children}) {
   return (
     <div className="min-h-screen bg-gradient-to-br from-primary/10 via-base-200 to-secondary/10">
+      <AuthHeader/>
       {/* Main container with flex centering */}
       <div className="min-h-screen flex items-center justify-center p-4">
         {/* Content wrapper for responsive spacing */}
-        <ThemeSwitcher />
         <div>
           {children}
         </div>

src/frontend/src/components/auth/LoginForm.jsx

@@ -96,7 +96,6 @@ function LoginForm() {
       <div className="card-body">
         {/* Card Header */}
         <div className="text-center mb-6">
-          <h1 className="text-3xl font-bold text-primary">My Documents DocManager</h1>
           <p className="text-base-content/70 mt-2">Sign in to your account</p>
         </div>
 

src/frontend/src/components/common/Header.jsx

@@ -1,8 +1,10 @@
-import { useAuth } from '../../hooks/useAuth';
+import {useAuth} from '../../hooks/useAuth';
-import { useNavigate } from 'react-router-dom';
+import {useNavigate} from 'react-router-dom';
+import ThemeSwitcher from "./ThemeSwither.jsx";
+import React from "react";
 
 const Header = () => {
-  const { user, logout } = useAuth();
+  const {user, logout} = useAuth();
   const navigate = useNavigate();
 
   const handleLogout = async () => {
@@ -13,35 +15,8 @@ const Header = () => {
   return (
     <div className="navbar bg-base-100 shadow-lg">
       <div className="navbar-start">
-        <div className="dropdown">
+        <h1 className="text-xl font-bold">MyDocManager</h1>
-          <div tabIndex={0} role="button" className="btn btn-ghost lg:hidden">
-            <svg className="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
-              <path strokeLinecap="round" strokeLinejoin="round" strokeWidth="2" d="M4 6h16M4 12h8m-8 6h16" />
-            </svg>
-          </div>
-          <ul tabIndex={0} className="menu menu-sm dropdown-content bg-base-100 rounded-box z-[1] mt-3 w-52 p-2 shadow">
-            <li><a href="/dashboard">Dashboard</a></li>
-            <li><a href="/documents">Documents</a></li>
-            {user?.role === 'admin' && (
-              <li><a href="/users">User Management</a></li>
-            )}
-          </ul>
-        </div>
-        <a className="btn btn-ghost text-xl" href="/dashboard">
-          MyDocManager
-        </a>
       </div>
-
-      <div className="navbar-center hidden lg:flex">
-        <ul className="menu menu-horizontal px-1">
-          <li><a href="/dashboard">Dashboard</a></li>
-          <li><a href="/documents">Documents</a></li>
-          {user?.role === 'admin' && (
-            <li><a href="/users">User Management</a></li>
-          )}
-        </ul>
-      </div>
-
       <div className="navbar-end">
         <div className="dropdown dropdown-end">
           <div tabIndex={0} role="button" className="btn btn-ghost btn-circle avatar">
@@ -59,12 +34,16 @@ const Header = () => {
               </div>
             </li>
             <li><a>Settings</a></li>
-            <li><button onClick={handleLogout}>Logout</button></li>
+            <li><ThemeSwitcher/></li>
+            <li>
+              <button onClick={handleLogout}>Logout</button>
+            </li>
           </ul>
         </div>
+
       </div>
     </div>
   );
 };
 
-export default Header;
+export default Header;

src/frontend/src/components/common/Layout.jsx

@@ -1,13 +1,17 @@
 import Header from './Header';
 import {Outlet} from 'react-router-dom';
+import Menu from "./Menu.jsx";
 
 const Layout = () => {
   return (
     <div className="min-h-screen bg-base-200">
       <Header/>
-      <main className="container mx-auto px-4 py-8">
+      <div className="flex">
-        <Outlet/>
+        <aside className="w-64 min-h-screen bg-base-100 shadow-lg"><Menu/></aside>
-      </main>
+        <main className="flex-1 container mx-auto px-4 py-8">
+          <Outlet/>
+        </main>
+      </div>
     </div>
   );
 };

src/frontend/src/components/common/Menu.jsx

@@ -0,0 +1,16 @@
+import {FaBuffer, FaPlus} from "react-icons/fa6";
+
+const Menu = () => {
+  return (
+    <div className="p-4">
+      <ul className="menu">
+        <li className="menu-title">Exploration</li>
+        <li><a><FaBuffer/>To Review</a></li>
+        <li className="menu-title mt-4">Catégories</li>
+        <li><a><i className="fas fa-plus"></i>Item</a></li>
+      </ul>
+    </div>
+  )
+}
+
+export default Menu;

src/frontend/src/components/common/ThemeSwither.jsx

@@ -1,103 +1,29 @@
-import React from "react";
+import {useEffect, useState} from "react";
+import {MoonIcon, SunIcon} from "../../assets/icons.jsx";
 
-const themes = [
+function ThemeSwitcher() {
-  "light", "dark", "cupcake"
+  // State to store current theme
-];
+  const [theme, setTheme] = useState("light");
+
+  // When theme changes, apply it to <html data-theme="">
+  useEffect(() => {
+    document.querySelector("html").setAttribute("data-theme", theme);
+  }, [theme]);
+
+  // Toggle between light and dark
+  const toggleTheme = () => {
+    setTheme(theme === "light" ? "dark" : "light");
+  };
 
-export default function ThemeSwitcher() {
   return (
-    <div title="Change Theme" className="dropdown dropdown-end block">
+    <button
-      <div
+      onClick={toggleTheme}
-        tabIndex={0}
+      className="btn btn-ghost btn-circle"
-        role="button"
+    >
-        className="btn group btn-sm gap-1.5 px-1.5 btn-ghost"
+      {theme === "light" ? MoonIcon : SunIcon}
-        aria-label="Change Theme"
-      >
-        <div
-          className="bg-base-100 group-hover:border-base-content/20 border-base-content/10 grid shrink-0 grid-cols-2 gap-0.5 rounded-md border p-1 transition-colors">
-          <div className="bg-base-content size-1 rounded-full"></div>
-          <div className="bg-primary size-1 rounded-full"></div>
-          <div className="bg-secondary size-1 rounded-full"></div>
-          <div className="bg-accent size-1 rounded-full"></div>
-        </div>
-        <svg
-          width="12px"
-          height="12px"
-          className="mt-px hidden size-2 fill-current opacity-60 sm:inline-block"
-          xmlns="http://www.w3.org/2000/svg"
-          viewBox="0 0 2048 2048"
-        >
-          <path d="M1799 349l242 241-1017 1017L7 590l242-241 775 775 775-775z"></path>
-        </svg>
-      </div>
 
-      <div
+    </button>
-        tabIndex={0}
-        className="dropdown-content bg-base-200 text-base-content rounded-box top-px h-[30.5rem] max-h-[calc(100vh-8.6rem)] overflow-y-auto border-[length:var(--border)] border-white/5 shadow-2xl outline-[length:var(--border)] outline-black/5 mt-16"
-      >
-        <ul className="menu w-56">
-          <li className="menu-title text-xs">Thème</li>
-          {themes.map((theme) => (
-            <li key={theme}>
-              <button
-                className="gap-3 px-2"
-                data-set-theme={theme}
-                data-act-class="[&_svg]:visible"
-              >
-                <div
-                  data-theme={theme}
-                  className="bg-base-100 grid shrink-0 grid-cols-2 gap-0.5 rounded-md p-1 shadow-sm"
-                >
-                  <div className="bg-base-content size-1 rounded-full"></div>
-                  <div className="bg-primary size-1 rounded-full"></div>
-                  <div className="bg-secondary size-1 rounded-full"></div>
-                  <div className="bg-accent size-1 rounded-full"></div>
-                </div>
-                <div className="w-32 truncate">{theme}</div>
-                <svg
-                  xmlns="http://www.w3.org/2000/svg"
-                  width="16"
-                  height="16"
-                  viewBox="0 0 24 24"
-                  fill="currentColor"
-                  className="invisible h-3 w-3 shrink-0"
-                >
-                  <path d="M20.285 2l-11.285 11.567-5.286-5.011-3.714 3.716 9 8.728 15-15.285z"></path>
-                </svg>
-              </button>
-            </li>
-          ))}
-
-          <li>
-            <a href="/theme-generator/">
-              <svg
-                width="24"
-                height="24"
-                xmlns="http://www.w3.org/2000/svg"
-                className="h-4 w-4 fill-current"
-                viewBox="0 0 512 512"
-              >
-                <path d="M96,208H48a16,16,0,0,1,0-32H96a16,16,0,0,1,0,32Z"></path>
-                <line x1="90.25" y1="90.25" x2="124.19" y2="124.19"></line>
-                <path
-                  d="M124.19,140.19a15.91,15.91,0,0,1-11.31-4.69L78.93,101.56a16,16,0,0,1,22.63-22.63l33.94,33.95a16,16,0,0,1-11.31,27.31Z"></path>
-                <path d="M192,112a16,16,0,0,1-16-16V48a16,16,0,0,1,32,0V96A16,16,0,0,1,192,112Z"></path>
-                <line x1="293.89" y1="90.25" x2="259.95" y2="124.19"></line>
-                <path
-                  d="M260,140.19a16,16,0,0,1-11.31-27.31l33.94-33.95a16,16,0,0,1,22.63,22.63L271.27,135.5A15.94,15.94,0,0,1,260,140.19Z"></path>
-                <line x1="124.19" y1="259.95" x2="90.25" y2="293.89"></line>
-                <path
-                  d="M90.25,309.89a16,16,0,0,1-11.32-27.31l33.95-33.94a16,16,0,0,1,22.62,22.63l-33.94,33.94A16,16,0,0,1,90.25,309.89Z"></path>
-                <path
-                  d="M219,151.83a26,26,0,0,0-36.77,0l-30.43,30.43a26,26,0,0,0,0,36.77L208.76,276a4,4,0,0,0,5.66,0L276,214.42a4,4,0,0,0,0-5.66Z"></path>
-                <path
-                  d="M472.31,405.11,304.24,237a4,4,0,0,0-5.66,0L237,298.58a4,4,0,0,0,0,5.66L405.12,472.31a26,26,0,0,0,36.76,0l30.43-30.43h0A26,26,0,0,0,472.31,405.11Z"></path>
-              </svg>
-              <div className="grow text-sm font-bold">Créer votre thème!</div>
-            </a>
-          </li>
-        </ul>
-      </div>
-    </div>
   );
 }
+
+export default ThemeSwitcher;

src/worker/Dockerfile

@@ -7,6 +7,9 @@ WORKDIR /app
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libmagic1 \
     file \
+    pandoc \
+    ghostscript \
+    texlive-xetex \
  && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements and install dependencies

src/worker/requirements.txt

@@ -5,9 +5,14 @@ email-validator==2.3.0
 fastapi==0.116.1
 httptools==0.6.4
 motor==3.7.1
-pymongo==4.15.0
+pillow==11.3.0
 pydantic==2.11.9
+PyJWT==2.10.1
+pymongo==4.15.0
+pypandoc==1.15
+python-multipart==0.0.20
 redis==6.4.0
+reportlab==4.4.4
 uvicorn==0.35.0
 python-magic==0.4.27
 watchdog==6.0.0

src/worker/tasks/common/converter_utils.py

@@ -0,0 +1,102 @@
+import subprocess
+import uuid
+from pathlib import Path
+
+import magic  # python-magic
+
+from tasks.common.pdf_converter import TextToPdfConverter, ImageToPdfConverter, WordToPdfConverter
+
+
+class UnsupportedFileTypeError(Exception):
+  """Exception raised when a file type is not supported."""
+  pass
+
+
+def generate_uuid_filename() -> str:
+  """Generate a unique filename using UUID4."""
+  return str(uuid.uuid4())
+
+
+def detect_file_type(file_path: str) -> str:
+  """
+  Detect the type of file using python-magic.
+
+  Returns:
+      'text', 'image', 'word'
+
+  Raises:
+      UnsupportedFileTypeError: If file type is not supported.
+  """
+  mime = magic.from_file(file_path, mime=True)
+  if mime.startswith("text/"):
+    return "text"
+  elif mime.startswith("image/"):
+    return "image"
+  elif mime in ("application/vnd.openxmlformats-officedocument.wordprocessingml.document",):
+    return "word"
+  else:
+    raise UnsupportedFileTypeError(f"Unsupported file type: {mime}")
+
+
+def compress_pdf(input_pdf: str, output_pdf: str, quality: str = "ebook") -> None:
+  """
+  Compress a PDF using Ghostscript.
+
+  Args:
+      input_pdf (str): Path to the input PDF.
+      output_pdf (str): Path to save the compressed PDF.
+      quality (str): Ghostscript PDFSETTINGS option: screen, ebook, printer, prepress.
+
+  Raises:
+      FileNotFoundError: If input PDF does not exist.
+      RuntimeError: If Ghostscript returns an error.
+  """
+  input_path = Path(input_pdf)
+  output_path = Path(output_pdf)
+  
+  if not input_path.exists():
+    raise FileNotFoundError(f"Input PDF not found: {input_pdf}")
+  
+  cmd = [
+      "gs",
+      "-sDEVICE=pdfwrite",
+      "-dCompatibilityLevel=1.4",
+      f"-dPDFSETTINGS=/{quality}",
+      "-dNOPAUSE",
+      "-dQUIET",
+      "-dBATCH",
+      f"-sOutputFile={str(output_path)}",
+      str(input_path),
+  ]
+  
+  result = subprocess.run(cmd)
+  if result.returncode != 0:
+    raise RuntimeError(f"Ghostscript failed with return code {result.returncode}")
+
+
+def convert_to_pdf(filepath: str, output_dir: str = ".") -> str:
+  """
+      Convert any supported file to PDF.
+
+      Args:
+          filepath (str): Path to the input file.
+          output_dir (str): Directory to save the output PDF.
+
+      Returns:
+          str: Path to the generated PDF.
+
+      Raises:
+          UnsupportedFileTypeError: If the input file type is not supported.
+      """
+  file_type = detect_file_type(filepath)
+  
+  if file_type == "text":
+    converter = TextToPdfConverter(filepath, output_dir=output_dir)
+  elif file_type == "image":
+    converter = ImageToPdfConverter(filepath, output_dir=output_dir)
+  elif file_type == "word":
+    converter = WordToPdfConverter(filepath, output_dir=output_dir)
+  else:
+    raise ValueError(f"Unsupported file type: {file_type}")
+  
+  return converter.convert()

src/worker/tasks/common/pdf_converter.py

@@ -0,0 +1,83 @@
+from abc import ABC, abstractmethod
+from pathlib import Path
+
+import pypandoc
+from PIL import Image
+from reportlab.lib.pagesizes import A4
+from reportlab.pdfgen import canvas
+
+from tasks.common.converter_utils import generate_uuid_filename
+
+
+class BaseConverter(ABC):
+  """Abstract base class for file converters to PDF."""
+  
+  def __init__(self, input_path: str, output_dir: str = ".") -> None:
+    self.input_path = Path(input_path)
+    self.output_dir = Path(output_dir)
+    self.output_path = self.output_dir / f"{generate_uuid_filename()}.pdf"
+  
+  @abstractmethod
+  def convert(self) -> str:
+    """Convert input file to PDF and return the output path."""
+    pass
+
+
+class TextToPdfConverter(BaseConverter):
+  """Converter for text files to PDF."""
+  
+  def convert(self) -> str:
+    c = canvas.Canvas(str(self.output_path), pagesize=A4)
+    width, height = A4
+    with open(self.input_path, "r", encoding="utf-8") as f:
+      y = height - 50
+      for line in f:
+        c.drawString(50, y, line.strip())
+        y -= 15
+        if y < 50:
+          c.showPage()
+          y = height - 50
+    c.save()
+    return str(self.output_path)
+
+
+class ImageToPdfConverter(BaseConverter):
+  """Converter for image files to PDF."""
+  
+  def convert(self) -> str:
+    image = Image.open(self.input_path)
+    rgb_image = image.convert("RGB")
+    rgb_image.save(self.output_path)
+    return str(self.output_path)
+
+
+class WordToPdfConverter(BaseConverter):
+  """Converter for Word files (.docx) to PDF using pypandoc."""
+  
+  def convert(self) -> str:
+    pypandoc.convert_file(
+      str(self.input_path), "pdf", outputfile=str(self.output_path)
+    )
+    return str(self.output_path)
+
+
+# Placeholders for future extensions
+class HtmlToPdfConverter(BaseConverter):
+  """Placeholder for HTML to PDF converter."""
+  
+  def convert(self) -> str:
+    raise NotImplementedError("HTML to PDF conversion not implemented.")
+
+
+class ExcelToPdfConverter(BaseConverter):
+  """Placeholder for Excel to PDF converter."""
+  
+  def convert(self) -> str:
+    raise NotImplementedError("Excel to PDF conversion not implemented.")
+
+
+class MarkdownToPdfConverter(BaseConverter):
+  """Placeholder for Markdown to PDF converter."""
+  
+  def convert(self) -> str:
+    raise NotImplementedError("Markdown to PDF conversion not implemented.")

src/worker/tasks/document_processing.py

@@ -11,10 +11,20 @@ from typing import Any, Dict
 from app.config import settings
 from app.database.connection import get_database
 from app.services.document_service import DocumentService
+from app.services.job_service import JobService
+from tasks.common.converter_utils import convert_to_pdf
 from tasks.main import celery_app
 
 logger = logging.getLogger(__name__)
 
+
+def get_services():
+  database = get_database()
+  document_service = DocumentService(database=database, objects_folder=settings.get_objects_folder())
+  job_service = JobService(database=database)
+  return document_service, job_service
+
+
 @celery_app.task(bind=True, autoretry_for=(Exception,), retry_kwargs={'max_retries': 3, 'countdown': 60})
 def process_document(self, filepath: str) -> Dict[str, Any]:
   """
@@ -38,10 +48,8 @@ def process_document(self, filepath: str) -> Dict[str, Any]:
   task_id = self.request.id
   logger.info(f"Starting document processing task {task_id} for file: {filepath}")
   
-  database = get_database()
+  # get services
-  document_service = DocumentService(database=database, objects_folder=settings.get_objects_folder())
+  document_service, job_service = get_services()
-  from app.services.job_service import JobService
-  job_service = JobService(database=database)
   
   job = None
   try:
@@ -56,7 +64,10 @@ def process_document(self, filepath: str) -> Dict[str, Any]:
     job_service.mark_job_as_started(job_id=job.id)
     logger.info(f"Job {task_id} marked as PROCESSING")
     
-    # Step 4: Mark job as completed
+    # Step 4: Create the pdf version of the document
+    pdf_file_path = convert_to_pdf(filepath, settings.get_temp_folder())
+    
+    # Step x: Mark job as completed
     job_service.mark_job_as_completed(job_id=job.id)
     logger.info(f"Job {task_id} marked as COMPLETED")
     
@@ -82,4 +93,3 @@ def process_document(self, filepath: str) -> Dict[str, Any]:
     
     # Re-raise the exception to trigger Celery retry mechanism
     raise
-  

src/worker/tasks/main.py

@@ -3,13 +3,19 @@ Celery worker for MyDocManager document processing tasks.
 
 This module contains all Celery tasks for processing documents.
 """
+import logging
 import os
 
 from celery import Celery
 
+from app.config import settings
+
+
 # Environment variables
-REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
+REDIS_URL = settings.get_redis_url()
-MONGODB_URL = os.getenv("MONGODB_URL", "mongodb://localhost:27017")
+MONGODB_URL = settings.get_mongodb_url()
+
+logger = logging.getLogger(__name__)
 
 # Initialize Celery app
 celery_app = Celery(
@@ -28,9 +34,15 @@ celery_app.conf.update(
   timezone="UTC",
   enable_utc=True,
   task_track_started=True,
-  task_time_limit=300,        # 5 minutes
+  task_time_limit=300,  # 5 minutes
-  task_soft_time_limit=240,   # 4 minutes
+  task_soft_time_limit=240,  # 4 minutes
 )
 
 if __name__ == "__main__":
+  # initialize temp folder if needed
+  tmp_folder = settings.get_temp_folder()
+  if not os.path.exists(tmp_folder):
+    logger.info(f"Creating temporary folder: {tmp_folder}")
+    os.makedirs(tmp_folder)
+  
   celery_app.start()

tests/common/test_pdf_converter.py

@@ -0,0 +1,55 @@
+import shutil
+import tempfile
+from pathlib import Path
+
+import pytest
+
+from tasks.common.pdf_converter import TextToPdfConverter, ImageToPdfConverter, WordToPdfConverter
+
+
+@pytest.fixture
+def temp_dir():
+  """Create a temporary directory for output PDFs."""
+  dir_path = tempfile.mkdtemp()
+  yield dir_path
+  shutil.rmtree(dir_path)
+
+
+def test_i_can_convert_text_to_pdf(temp_dir):
+  input_txt = Path(temp_dir) / "test.txt"
+  input_txt.write_text("Hello World!\nThis is a test.")
+  
+  converter = TextToPdfConverter(str(input_txt), output_dir=temp_dir)
+  output_pdf = converter.convert()
+  
+  assert Path(output_pdf).exists()
+  assert output_pdf.endswith(".pdf")
+
+
+def test_i_can_convert_image_to_pdf(temp_dir):
+  from PIL import Image
+  
+  input_img = Path(temp_dir) / "image.png"
+  image = Image.new("RGB", (100, 100), color="red")
+  image.save(input_img)
+  
+  converter = ImageToPdfConverter(str(input_img), output_dir=temp_dir)
+  output_pdf = converter.convert()
+  
+  assert Path(output_pdf).exists()
+  assert output_pdf.endswith(".pdf")
+
+
+def test_i_can_convert_word_to_pdf(temp_dir):
+  import docx
+  
+  input_docx = Path(temp_dir) / "document.docx"
+  doc = docx.Document()
+  doc.add_paragraph("Hello Word!")
+  doc.save(input_docx)
+  
+  converter = WordToPdfConverter(str(input_docx), output_dir=temp_dir)
+  output_pdf = converter.convert()
+  
+  assert Path(output_pdf).exists()
+  assert output_pdf.endswith(".pdf")

tests/common/test_utils.py

@@ -0,0 +1,52 @@
+import shutil
+import tempfile
+from pathlib import Path
+
+import pytest
+
+from tasks.common.converter_utils import detect_file_type, UnsupportedFileTypeError
+
+
+@pytest.fixture
+def temp_dir():
+  """Create a temporary directory for output PDFs."""
+  dir_path = tempfile.mkdtemp()
+  yield dir_path
+  shutil.rmtree(dir_path)
+
+
+def test_i_can_detect_text_file(temp_dir):
+  txt_file = Path(temp_dir) / "sample.txt"
+  txt_file.write_text("Sample text content")
+  detected_type = detect_file_type(str(txt_file))
+  assert detected_type == "text"
+
+
+def test_i_can_detect_image_file(temp_dir):
+  from PIL import Image
+  
+  img_file = Path(temp_dir) / "sample.jpg"
+  image = Image.new("RGB", (50, 50), color="blue")
+  image.save(img_file)
+  
+  detected_type = detect_file_type(str(img_file))
+  assert detected_type == "image"
+
+
+def test_i_can_detect_word_file(temp_dir):
+  import docx
+  
+  docx_file = Path(temp_dir) / "sample.docx"
+  doc = docx.Document()
+  doc.add_paragraph("Sample content")
+  doc.save(docx_file)
+  
+  detected_type = detect_file_type(str(docx_file))
+  assert detected_type == "word"
+
+
+def test_i_cannot_detect_unsupported_file(temp_dir):
+  exe_file = Path(temp_dir) / "sample.exe"
+  exe_file.write_bytes(b'\x4D\x5A\x90\x00\x03\x00\x00\x00')
+  with pytest.raises(UnsupportedFileTypeError):
+    detect_file_type(str(exe_file))