Thumbnails generated and displayed in the front end

Makefile

@@ -0,0 +1,32 @@
+.PHONY: init up down restart logs clean
+
+init:
+	@echo "Creating directories and setting permissions..."
+	@mkdir -p ./volumes/watched_files ./volumes/objects
+	@chown -R 1002:1002 ./volumes/watched_files ./volumes/objects
+	@echo "✓ Directories initialized"
+
+up: init
+	@echo "Starting services..."
+	@docker-compose up -d
+	@echo "✓ Services started"
+
+down:
+	@docker-compose down
+
+restart:
+	@docker-compose restart
+
+logs:
+	@docker-compose logs -f
+
+clean: down
+	@echo "Cleaning volumes..."
+	@sudo rm -rf ./volumes
+	@echo "✓ Volumes cleaned"
+
+rebuild: clean init
+	@echo "Rebuilding images..."
+	@docker-compose build --no-cache
+	@docker-compose up -d
+	@echo "✓ Services rebuilt and started"

docker-compose.yml

@@ -40,6 +40,8 @@ services:
       - ./src/worker/tasks:/app/tasks          # <- Added: shared access to worker tasks
       - ./volumes/watched_files:/watched_files
       - ./volumes/objects:/objects
+      - ./volumes/errors:/errors
+      - ./volumes/ignored:/ignored
     depends_on:
       - redis
       - mongodb
@@ -61,6 +63,9 @@ services:
       - ./src/worker:/app
       - ./src/file-processor/app:/app/app     # <- Added: shared access file-processor app
       - ./volumes/watched_files:/watched_files
+      - ./volumes/objects:/objects
+      - ./volumes/errors:/errors
+      - ./volumes/ignored:/ignored
     depends_on:
       - redis
       - mongodb

requirements.txt

@@ -13,6 +13,7 @@ click-didyoumean==0.3.1
 click-plugins==1.1.1.2
 click-repl==0.3.0
 cryptography==46.0.1
+Deprecated==1.2.18
 dnspython==2.8.0
 ecdsa==0.19.1
 email-validator==2.3.0
@@ -32,6 +33,7 @@ mongomock==4.3.0
 mongomock-motor==0.0.36
 motor==3.7.1
 packaging==25.0
+pikepdf==9.11.0
 pillow==11.3.0
 pipdeptree==2.28.0
 pluggy==1.6.0
@@ -44,6 +46,7 @@ pydantic_core==2.33.2
 Pygments==2.19.2
 PyJWT==2.10.1
 pymongo==4.15.1
+PyMuPDF==1.26.4
 pypandoc==1.15
 pytest==8.4.2
 pytest-asyncio==1.2.0
@@ -72,4 +75,5 @@ watchdog==6.0.0
 watchfiles==1.1.0
 wcwidth==0.2.13
 websockets==15.0.1
+wrapt==1.17.3
 zipp==3.23.0

src/file-processor/Dockerfile

@@ -12,10 +12,14 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     texlive-xetex \
  && rm -rf /var/lib/apt/lists/*
 
+
 # Copy requirements and install dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Change the user
+USER 1002:1002
+
 # Copy application code
 COPY . .
 
@@ -24,5 +28,6 @@ ENV PYTHONPATH=/app
 # Expose port
 EXPOSE 8000
 
+
 # Command will be overridden by docker-compose
 CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

src/file-processor/app/api/dependencies.py

@@ -9,6 +9,7 @@ from app.database.connection import get_database
 from app.models.auth import UserRole
 from app.models.user import UserInDB
 from app.services.auth_service import AuthService
+from app.services.document_service import DocumentService
 from app.services.user_service import UserService
 
 security = HTTPBearer()
@@ -25,6 +26,12 @@ def get_user_service() -> UserService:
   return UserService(database)
 
 
+def get_document_service() -> DocumentService:
+  """Dependency to get DocumentService instance."""
+  database = get_database()
+  return DocumentService(database)
+
+
 def get_current_user(
     credentials: HTTPAuthorizationCredentials = Depends(security),
     user_service: UserService = Depends(get_user_service)
@@ -79,7 +86,7 @@ def get_current_user(
   return user
 
 
-def   get_admin_user(current_user: UserInDB = Depends(get_current_user)) -> UserInDB:
+def get_admin_user(current_user: UserInDB = Depends(get_current_user)) -> UserInDB:
   """
   Dependency to ensure current user has admin role.
 

src/file-processor/app/api/routes/document.py

@@ -0,0 +1,241 @@
+"""
+Document API routes.
+
+This module provides REST endpoints for document management operations.
+"""
+
+import logging
+import os
+from typing import List, Optional
+
+import fitz  # PyMuPDF
+from fastapi import APIRouter, Depends, HTTPException, Query, status, Path
+from starlette.responses import Response
+
+from app.api.dependencies import get_document_service, get_current_user
+from app.models.document import DocumentResponse, FileDocument
+from app.services.document_service import DocumentService
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(tags=["Documents"])
+
+
+def _count_pdf_pages(pdf_file_path: str) -> int:
+  """
+  Count the number of pages in a PDF file using PyMuPDF.
+
+  Args:
+      pdf_file_path: Path to the PDF file
+
+  Returns:
+      Number of pages in the PDF, or 0 if file cannot be read
+  """
+  try:
+    with fitz.open(pdf_file_path) as doc:
+      return doc.page_count
+  except Exception as e:
+    logger.warning(f"Could not count pages for PDF {pdf_file_path}: {e}")
+    return 0
+
+
+def _build_object_url(file_hash: Optional[str]) -> Optional[str]:
+  """
+  Build object URL from file hash.
+
+  Args:
+      file_hash: SHA256 hash of the file
+
+  Returns:
+      URL string or None if hash is not provided
+  """
+  if not file_hash:
+    return None
+  return f"/api/objects/{file_hash}"
+
+
+def _extract_metadata_field(metadata: dict, field_name: str) -> List[str]:
+  """
+  Extract a list field from metadata dictionary.
+
+  Args:
+      metadata: Document metadata dictionary
+      field_name: Name of the field to extract
+
+  Returns:
+      List of strings, empty list if field doesn't exist or is not a list
+  """
+  field_value = metadata.get(field_name, [])
+  if isinstance(field_value, list):
+    return [str(item) for item in field_value]
+  return []
+
+
+def _map_file_document_to_response(
+    document: FileDocument,
+    document_service: DocumentService
+) -> DocumentResponse:
+  """
+  Map FileDocument to DocumentResponse format.
+
+  Args:
+      document: FileDocument instance from database
+      document_service: Document service for file operations
+
+  Returns:
+      DocumentResponse instance ready for API response
+  """
+  # Calculate page count for PDF files
+  page_count = 0
+  if document.pdf_file_hash and document_service.exists(document.pdf_file_hash):
+    pdf_path = document_service.get_document_path(document.pdf_file_hash)
+    page_count = _count_pdf_pages(pdf_path)
+  
+  # Build URLs
+  thumbnail_url = _build_object_url(document.thumbnail_file_hash)
+  pdf_url = _build_object_url(document.pdf_file_hash)
+  
+  # Extract tags and categories from metadata
+  tags = _extract_metadata_field(document.metadata, "tags")
+  categories = _extract_metadata_field(document.metadata, "categories")
+  
+  # Format created_at timestamp
+  created_at = document.detected_at.isoformat() if document.detected_at else ""
+  
+  as_dict = {
+      "id": str(document.id),
+      "name": document.filename,
+      "original_file_type": document.file_type.value.upper(),
+      "created_at": created_at,
+      "file_size": document.file_size,
+      "page_count": page_count,
+      "thumbnail_url": thumbnail_url,
+      "pdf_url": pdf_url,
+      "tags": tags,
+      "categories": categories
+  }
+  logger.info(f"Document: {as_dict}")
+  
+  return DocumentResponse(**as_dict)
+
+
+@router.get("/documents", response_model=List[DocumentResponse])
+def list_documents(
+    skip: int = Query(0, ge=0, description="Number of documents to skip"),
+    limit: int = Query(100, ge=1, le=1000, description="Maximum number of documents to return"),
+    UserInDB=Depends(get_current_user),
+    document_service: DocumentService = Depends(get_document_service)
+) -> List[DocumentResponse]:
+  """
+  Retrieve a paginated list of documents.
+
+  Args:
+      skip: Number of documents to skip for pagination
+      limit: Maximum number of documents to return
+      document_service: Document service instance
+
+  Returns:
+      List of documents in API response format
+
+  Raises:
+      HTTPException: If database operation fails
+  """
+  try:
+    # Get documents from service
+    documents = document_service.list_documents(skip=skip, limit=limit)
+    
+    # Map to response format
+    document_responses = [
+        _map_file_document_to_response(doc, document_service)
+        for doc in documents
+    ]
+    
+    return document_responses
+  
+  except Exception as e:
+    logger.error(f"Failed to list documents: {e}")
+    raise HTTPException(
+      status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+      detail="Failed to retrieve documents"
+    )
+
+
+@router.get("/objects/{file_hash}")
+async def get_object_by_hash(
+    file_hash: str = Path(..., description="SHA256 hash of the object to retrieve"),
+    document_service: DocumentService = Depends(get_document_service)
+):
+  """
+  Serve object content by its hash.
+
+  This endpoint serves files (original documents, PDFs, thumbnails) by their
+  SHA256 hash. It supports all file types stored in the objects folder.
+
+  Args:
+      file_hash: SHA256 hash of the object
+      document_service: Document service dependency
+
+  Returns:
+      FileResponse with the requested object content
+
+  Raises:
+      HTTPException: If object not found (404) or server error (500)
+  """
+  try:
+    # Check if object exists
+    if not document_service.exists(file_hash):
+      raise HTTPException(
+        status_code=status.HTTP_404_NOT_FOUND,
+        detail="Object not found"
+      )
+    
+    # Get file path
+    file_path = document_service.get_document_path(file_hash)
+    
+    # Verify file exists on disk
+    if not os.path.exists(file_path):
+      logger.error(f"Object {file_hash} registered but file not found at {file_path}")
+      raise HTTPException(
+        status_code=status.HTTP_404_NOT_FOUND,
+        detail="Object file not found on disk"
+      )
+    
+    # Determine media type based on file content
+    try:
+      file_content = document_service.get_document_content_by_hash(file_hash)
+      if not file_content:
+        raise HTTPException(
+          status_code=status.HTTP_404_NOT_FOUND,
+          detail="Object content not available"
+        )
+      
+      # Detect MIME type
+      import magic
+      mime_type = magic.from_buffer(file_content, mime=True)
+      
+      # Return file content with appropriate headers
+      return Response(
+        content=file_content,
+        media_type=mime_type,
+        headers={
+            "Content-Length": str(len(file_content)),
+            "Cache-Control": "public, max-age=3600"  # Cache for 1 hour
+        }
+      )
+    
+    except Exception as e:
+      logger.error(f"Error reading object content for hash {file_hash}: {str(e)}")
+      raise HTTPException(
+        status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+        detail="Failed to read object content"
+      )
+  
+  except HTTPException:
+    # Re-raise HTTP exceptions as-is
+    raise
+  except Exception as e:
+    logger.error(f"Unexpected error serving object {file_hash}: {str(e)}")
+    raise HTTPException(
+      status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+      detail="Internal server error while serving object"
+    )

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

@@ -105,4 +105,14 @@ def get_watch_folder() -> str:
 
 def get_temp_folder() -> str:
   """Directory to store temporary files"""
-  return os.getenv("TEMP_DIRECTORY", "/temp")
+  return os.getenv("TEMP_DIRECTORY", "/tmp")
+
+
+def get_errors_folder() -> str:
+  """Directory to store temporary files"""
+  return os.getenv("ERRORS_DIRECTORY", "/errors")
+
+
+def get_ignored_folder() -> str:
+  """Directory to store temporary files"""
+  return os.getenv("IGNORED_DIRECTORY", "/ignored")

src/file-processor/app/database/connection.py

@@ -4,7 +4,7 @@ MongoDB database connection management.
 This module handles MongoDB connection with fail-fast approach.
 The application will terminate if MongoDB is not accessible at startup.
 """
-
+import logging
 import sys
 from typing import Optional
 
@@ -13,11 +13,14 @@ from pymongo.database import Database
 from pymongo.errors import ConnectionFailure, ServerSelectionTimeoutError
 
 from app.config.settings import get_mongodb_url, get_mongodb_database_name
+from app.utils.security import safe_connection_string
 
 # Global variables for singleton pattern
 _client: Optional[MongoClient] = None
 _database: Optional[Database] = None
 
+logger = logging.getLogger(__name__)
+
 
 def create_mongodb_client() -> MongoClient:
   """
@@ -43,16 +46,16 @@ def create_mongodb_client() -> MongoClient:
     # Test connection by running admin command
     client.admin.command('ping')
     
-    print(f"Successfully connected to MongoDB at {mongodb_url}")
+    logger.info(f"Successfully connected to MongoDB at {safe_connection_string(mongodb_url)}")
     return client
   
   except (ConnectionFailure, ServerSelectionTimeoutError) as e:
-    print(f"ERROR: Failed to connect to MongoDB at {mongodb_url}")
-    print(f"Connection error: {str(e)}")
-    print("MongoDB is required for this application. Please ensure MongoDB is running and accessible.")
+    logger.error(f"ERROR: Failed to connect to MongoDB at {safe_connection_string(mongodb_url)}")
+    logger.error(f"Connection error: {str(e)}")
+    logger.error("MongoDB is required for this application. Please ensure MongoDB is running and accessible.")
     sys.exit(1)
   except Exception as e:
-    print(f"ERROR: Unexpected error connecting to MongoDB: {str(e)}")
+    logger.error(f"ERROR: Unexpected error connecting to MongoDB: {str(e)}")
     sys.exit(1)
 
 
@@ -74,7 +77,7 @@ def get_database() -> Database:
     
     database_name = get_mongodb_database_name()
     _database = _client[database_name]
-    print(f"Connected to database: {database_name}")
+    logger.info(f"Connected to database: {database_name}")
   
   return _database
 
@@ -92,7 +95,7 @@ def close_database_connection():
     _client.close()
     _client = None
     _database = None
-    print("MongoDB connection closed")
+    logger.info("MongoDB connection closed")
 
 
 def get_mongodb_client() -> Optional[MongoClient]:

src/file-processor/app/database/repositories/document_repository.py

@@ -130,6 +130,47 @@ class FileDocumentRepository:
     except PyMongoError:
       return None
   
+  def find_document_with_pdf_hash(self, file_hash: str) -> Optional[FileDocument]:
+    """
+    Find file document by file hash with a pdf_file_hash set (not None).
+
+    Args:
+        file_hash (str): SHA256 hash of file content
+
+    Returns:
+        FileDocument or None: File document if found, None otherwise
+    """
+    try:
+      file_doc = self.collection.find_one({"file_hash": file_hash,
+                                           "pdf_file_hash": {"$ne": None}})
+      if file_doc:
+        return FileDocument(**file_doc)
+      return None
+    
+    except PyMongoError:
+      return None
+  
+  def find_same_document(self, filename: str, file_hash: str):
+    """
+    Find document with the same file_name and the same file hash
+
+    Args:
+        filename (str):
+        file_hash (str): SHA256 hash of file content
+
+    Returns:
+        FileDocument or None: File document if found, None otherwise
+    """
+    try:
+      file_doc = self.collection.find_one({"file_hash": file_hash,
+                                           "filename": filename})
+      if file_doc:
+        return FileDocument(**file_doc)
+      return None
+    
+    except PyMongoError:
+      return None
+  
   def find_document_by_filepath(self, filepath: str) -> Optional[FileDocument]:
     """
     Find file document by exact filepath.

src/file-processor/app/file_watcher.py

@@ -30,7 +30,7 @@ class DocumentFileEventHandler(FileSystemEventHandler):
   dispatching Celery tasks, and managing processing jobs.
   """
   
-  SUPPORTED_EXTENSIONS = {'.txt', '.pdf', '.docx'}
+  SUPPORTED_EXTENSIONS = {'.txt', '.pdf', '.docx', '.jpg', '.png', '.jpeg'}
   
   def __init__(self, document_service: DocumentService, job_service: JobService):
     """
@@ -59,6 +59,7 @@ class DocumentFileEventHandler(FileSystemEventHandler):
     
     if file_extension not in self.SUPPORTED_EXTENSIONS:
       logger.info(f"Ignoring unsupported file type: {filepath}")
+      self.document_service.move_to_ignored(filepath, "unsupported file type")
       return
     
     logger.info(f"Processing new file: {filepath}")

src/file-processor/app/main.py

@@ -17,6 +17,7 @@ from fastapi.middleware.cors import CORSMiddleware
 
 from app.api.routes.auth import router as auth_router
 from app.api.routes.users import router as users_router
+from app.api.routes.document import router as documents_router
 from app.config import settings
 from app.database.connection import get_database
 from app.file_watcher import create_file_watcher, FileWatcher
@@ -111,7 +112,7 @@ app.add_middleware(
 # Include routers
 app.include_router(auth_router, prefix="/auth", tags=["Authentication"])
 app.include_router(users_router, prefix="/users", tags=["User Management"])
-# app.include_router(documents_router, prefix="/documents", tags=["Documents"])
+app.include_router(documents_router, prefix="/api", tags=["Documents"])
 # app.include_router(jobs_router, prefix="/jobs", tags=["Processing Jobs"])
 
 

src/file-processor/app/models/document.py

@@ -7,10 +7,9 @@ stored in MongoDB collections.
 
 from datetime import datetime
 from enum import Enum
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional
 
-from bson import ObjectId
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, Field, field_validator, ConfigDict
 
 from app.models.types import PyObjectId
 
@@ -49,6 +48,8 @@ class FileDocument(BaseModel):
   metadata: Dict[str, Any] = Field(default_factory=dict, description="File-specific metadata")
   detected_at: Optional[datetime] = Field(default=None, description="Timestamp when file was detected")
   file_hash: Optional[str] = Field(default=None, description="SHA256 hash of file content")
+  pdf_file_hash: Optional[str] = Field(default=None, description="SHA256 hash of the associated pdf file content")
+  thumbnail_file_hash: Optional[str] = Field(default=None, description="SHA256 hash of the thumbnail")
   encoding: str = Field(default="utf-8", description="Character encoding for text files")
   file_size: int = Field(..., ge=0, description="File size in bytes")
   mime_type: str = Field(..., description="MIME type detected")
@@ -68,3 +69,28 @@ class FileDocument(BaseModel):
     if not v.strip():
       raise ValueError("Filename cannot be empty")
     return v.strip()
+
+
+class DocumentResponse(BaseModel):
+  """
+  Response model for document API endpoints.
+  
+  Represents a document in the format expected by the frontend application.
+  Field names are automatically converted from snake_case to camelCase.
+  """
+  
+  model_config = ConfigDict(alias_generator=lambda field_name: ''.join(
+    word.capitalize() if i > 0 else word
+    for i, word in enumerate(field_name.split('_'))
+  ), populate_by_name=True)
+  
+  id: str = Field(..., description="Document unique identifier")
+  name: str = Field(..., description="Document filename")
+  original_file_type: str = Field(..., description="Original file type before conversion")
+  created_at: str = Field(..., description="ISO timestamp when document was created")
+  file_size: int = Field(..., description="File size in bytes")
+  page_count: int = Field(..., description="Number of pages in the document")
+  thumbnail_url: Optional[str] = Field(default=None, description="URL to document thumbnail")
+  pdf_url: Optional[str] = Field(default=None, description="URL to PDF version of document")
+  tags: List[str] = Field(default_factory=list, description="Document tags")
+  categories: List[str] = Field(default_factory=list, description="Document categories")

src/file-processor/app/models/job.py

@@ -14,6 +14,9 @@ class ProcessingStatus(str, Enum):
   PENDING = "pending"
   PROCESSING = "processing"
   COMPLETED = "completed"
+  SAVING_OBJECT = "saving_object"
+  SAVING_PDF = "saving_pdf"
+  CREATING_THUMBNAIL = "creating_thumbnail"
   FAILED = "failed"
 
 

src/file-processor/app/services/document_service.py

@@ -6,7 +6,9 @@ while maintaining data consistency through MongoDB transactions.
 """
 
 import hashlib
+import logging
 import os
+import shutil
 from datetime import datetime
 from pathlib import Path
 from typing import List, Optional, Dict, Any
@@ -14,13 +16,28 @@ from typing import List, Optional, Dict, Any
 import magic
 from pymongo.errors import PyMongoError
 
-from app.config.settings import get_objects_folder
+from app.config.settings import get_objects_folder, get_temp_folder, get_errors_folder, get_ignored_folder
 from app.database.repositories.document_repository import FileDocumentRepository
 from app.models.document import (
   FileDocument,
   FileType,
 )
 from app.models.types import PyObjectId
+from app.utils.pdf_converter import convert_to_pdf
+from app.utils.pdf_thumbmail import PDFThumbnailGenerator
+from app.utils.security import generate_uuid_filename
+
+logger = logging.getLogger(__name__)
+
+
+class DocumentAlreadyExists(Exception):
+  def __init__(self, message):
+    self.message = message
+
+
+class DocumentProcessingError(Exception):
+  def __init__(self, message):
+    self.message = message
 
 
 class DocumentService:
@@ -31,7 +48,11 @@ class DocumentService:
   and their content while ensuring data consistency through transactions.
   """
   
-  def __init__(self, database, objects_folder: str = None):
+  def __init__(self, database,
+               objects_folder: str = None,
+               temp_folder: str = None,
+               errors_folder: str = None,
+               ignored_folder: str = None):
     """
     Initialize the document service with repository dependencies.
     
@@ -43,6 +64,9 @@ class DocumentService:
     self.db = database
     self.document_repository = FileDocumentRepository(self.db)
     self.objects_folder = objects_folder or get_objects_folder()
+    self.temp_folder = temp_folder or get_temp_folder()
+    self.errors_folder = errors_folder or get_errors_folder()
+    self.ignored_folder = ignored_folder or get_ignored_folder()
   
   def initialize(self):
     self.document_repository.initialize()
@@ -117,7 +141,40 @@ class DocumentService:
     
     return path.read_bytes()
   
-  def _get_document_path(self, file_hash):
+  @staticmethod
+  def _get_safe_path(file_path):
+    """
+    If the path already exists, add a suffix to the filename.
+    Increment the suffix until a safe path is found.
+    :param file_path:
+    :return:
+    """
+    path = Path(file_path)
+    
+    # If the path doesn't exist, return it as is
+    if not path.exists():
+      return file_path
+    
+    # Split the filename and extension
+    stem = path.stem
+    suffix = path.suffix
+    directory = path.parent
+    
+    # Try incrementing numbers until a unique path is found
+    counter = 1
+    while True:
+      # Create new filename with counter
+      new_filename = f"{stem}_{counter}{suffix}"
+      new_path = os.path.join(directory, new_filename)
+      
+      # Check if this new path exists
+      if not os.path.exists(new_path):
+        return new_path
+      
+      # Increment counter for next attempt
+      counter += 1
+  
+  def get_document_path(self, file_hash):
     """
 
     :param file_hash:
@@ -125,8 +182,13 @@ class DocumentService:
     """
     return os.path.join(self.objects_folder, file_hash[:24], file_hash)
   
+  def exists(self, file_hash):
+    if file_hash is None:
+      return False
+    return os.path.exists(self.get_document_path(file_hash))
+  
   def save_content_if_needed(self, file_hash, content: bytes):
-    target_path = self._get_document_path(file_hash)
+    target_path = self.get_document_path(file_hash)
     if os.path.exists(target_path):
       return
     
@@ -136,6 +198,19 @@ class DocumentService:
     with open(target_path, "wb") as f:
       f.write(content)
   
+  def move_to_errors(self, document_id, file_path):
+    logger.info(f"Moving file {file_path} to error folder")
+    error_file_name = f"{document_id}_{os.path.basename(file_path)}"
+    error_file_path = self._get_safe_path(os.path.join(self.errors_folder, error_file_name))
+    shutil.move(file_path, error_file_path)
+  
+  def move_to_ignored(self, file_path, reason="Unknown"):
+    logger.info(f"Moving file {file_path} to ignored folder")
+    ignored_file_name = datetime.now().strftime("%Y-%m-%d_%H-%M-%S") + f"_### {reason} ###_" + os.path.basename(
+      file_path)
+    ignored_file_path = self._get_safe_path(os.path.join(self.ignored_folder, ignored_file_name))
+    shutil.move(file_path, ignored_file_path)
+  
   def create_document(
       self,
       file_path: str,
@@ -171,7 +246,16 @@ class DocumentService:
     detected_at = datetime.now()
     
     try:
+      logger.info(f'Creating Document for "{file_path}"')
+      # Skip the document if it already exists
+      same_document = self.document_repository.find_same_document(filename, file_hash)
+      if same_document is not None:
+        logger.info(f"  Document with same hash already exists. Skipping...")
+        self.move_to_ignored(file_path, f"already exists ({same_document.id})")
+        raise DocumentAlreadyExists(f"Document with same hash already exists ({same_document.id})")
+      
       self.save_content_if_needed(file_hash, file_bytes)
+      logger.info(f"  Saved content to {self.get_document_path(file_hash)}")
       
       # Create FileDocument
       file_data = FileDocument(
@@ -187,14 +271,90 @@ class DocumentService:
         mime_type=mime_type
       )
       
-      created_file = self.document_repository.create_document(file_data)
+      created_document = self.document_repository.create_document(file_data)
+      logger.info(f"  Created document with id '{created_document.id}'")
       
-      return created_file
+      return created_document
     
+    except DocumentAlreadyExists as e:
+      raise e
     except Exception as e:
       # Transaction will automatically rollback if supported
       raise PyMongoError(f"Failed to create document: {str(e)}")
   
+  def create_pdf(self, document_id: PyObjectId):
+    """
+    For all files, a controlled pdf version will be created for standard visualization and action
+    :return:
+    """
+    logger.info(f"Creating PDF document for {document_id}")
+    document = self.get_document_by_id(document_id)
+    if document is None:
+      logger.error(f"  Document not found")
+      raise DocumentProcessingError(f"Document {document_id} not found.")
+    
+    # try to find another document that has the same hash
+    document_with_same_hash = self.get_document_with_pdf_hash(document.file_hash)
+    
+    # the pdf will be created only if it does not exist yet
+    if document_with_same_hash and self.exists(document_with_same_hash.pdf_file_hash):
+      logger.info(f'Found document with same hash. Will use pdf "{document_with_same_hash.pdf_file_hash}".')
+      self.update_document(document_id, {"pdf_file_hash": document_with_same_hash.pdf_file_hash})
+      return
+    
+    # get the content of the file
+    logger.info(f"  No document with same hash and valid pdf found. Will create new pdf content.")
+    file_bytes = self.get_document_content_by_hash(document.file_hash)
+    if file_bytes is None:
+      logger.error(f'Content for document "{document_id}" not found. hash = "{document.file_hash}".')
+      raise DocumentProcessingError(f'Content for document "{document_id}" not found. hash = "{document.file_hash}".')
+    
+    # create the pdf file
+    temp_pdf_file = convert_to_pdf(self.get_document_path(document.file_hash), self.temp_folder)
+    pdf_file_hash = self._calculate_file_hash(self._read_file_bytes(temp_pdf_file))
+    self.save_content_if_needed(pdf_file_hash, self._read_file_bytes(temp_pdf_file))
+    os.remove(temp_pdf_file)  # remove the temporary file
+    logger.info(f'  Created new pdf file with hash "{pdf_file_hash}"')
+    
+    # update the document
+    self.update_document(document_id, {"pdf_file_hash": pdf_file_hash})
+  
+  def create_thumbnail(self, document_id: PyObjectId):
+    logger.info(f'Creating thumbnail document for "{document_id}"')
+    document = self.get_document_by_id(document_id)
+    if document is None:
+      logger.error(f"  Document not found !")
+      raise DocumentProcessingError(f"Document {document_id} not found.")
+    
+    # try to find another document that has the same hash
+    document_with_same_hash = self.get_document_with_pdf_hash(document.file_hash)
+    
+    # We will use the thumbnail of the pdf if it exists
+    if document_with_same_hash and self.exists(document_with_same_hash.thumbnail_file_hash):
+      logger.info(f"  Found document with same hash. Will use thumbnail {document_with_same_hash.thumbnail_file_hash}")
+      self.update_document(document_id, {"thumbnail_file_hash": document_with_same_hash.thumbnail_file_hash})
+      return
+    
+    logger.info(f"  No document with same hash and valid thumbnail found. Will create new thumbnail")
+    
+    if not self.exists(document.pdf_file_hash):
+      logger.error(f"  PDF file not found.")
+      raise DocumentProcessingError(f"PDF file for document {document_id} not found")
+    
+    tmp_thumbnail_path = os.path.join(self.temp_folder, f"{generate_uuid_filename()}.png")
+    with PDFThumbnailGenerator(self.get_document_path(document.pdf_file_hash)) as gen:
+      # create the thumbnail
+      gen.create_thumbnail(tmp_thumbnail_path, page_num=0, width=200)
+      thumbnail_file_hash = self._calculate_file_hash(self._read_file_bytes(tmp_thumbnail_path))
+      
+      # save the thumbnail to the objects folder
+      self.save_content_if_needed(thumbnail_file_hash, self._read_file_bytes(tmp_thumbnail_path))
+      os.remove(tmp_thumbnail_path)
+      
+      # update the document
+      self.update_document(document_id, {"thumbnail_file_hash": thumbnail_file_hash})
+      logger.info(f"  Created thumbnail {thumbnail_file_hash}")
+  
   def get_document_by_id(self, document_id: PyObjectId) -> Optional[FileDocument]:
     """
     Retrieve a document by its ID.
@@ -219,6 +379,9 @@ class DocumentService:
     """
     return self.document_repository.find_document_by_hash(file_hash)
   
+  def get_document_with_pdf_hash(self, file_hash) -> Optional[FileDocument]:
+    return self.document_repository.find_document_with_pdf_hash(file_hash)
+  
   def get_document_by_filepath(self, filepath: str) -> Optional[FileDocument]:
     """
     Retrieve a document by its file path.
@@ -232,7 +395,7 @@ class DocumentService:
     return self.document_repository.find_document_by_filepath(filepath)
   
   def get_document_content_by_hash(self, file_hash):
-    target_path = self._get_document_path(file_hash)
+    target_path = self.get_document_path(file_hash)
     if not os.path.exists(target_path):
       return None
     
@@ -323,7 +486,7 @@ class DocumentService:
       # If no other files reference this content, delete it
       if not remaining_files:
         try:
-          os.remove(self._get_document_path(document.file_hash))
+          os.remove(self.get_document_path(document.file_hash))
         except Exception:
           pass
       

src/file-processor/app/services/job_service.py

@@ -111,7 +111,9 @@ class JobService:
     current_job = self.repository.find_job_by_id(job_id)
     
     # Validate status transition
-    if current_job.status != ProcessingStatus.PROCESSING:
+    if current_job.status in (ProcessingStatus.PENDING,
+                              ProcessingStatus.COMPLETED,
+                              ProcessingStatus.FAILED):
       raise InvalidStatusTransitionError(current_job.status, ProcessingStatus.COMPLETED)
     
     # Update status
@@ -141,7 +143,7 @@ class JobService:
     current_job = self.repository.find_job_by_id(job_id)
     
     # Validate status transition
-    if current_job.status != ProcessingStatus.PROCESSING:
+    if current_job.status in (ProcessingStatus.PENDING, ProcessingStatus.COMPLETED, ProcessingStatus.FAILED):
       raise InvalidStatusTransitionError(current_job.status, ProcessingStatus.FAILED)
     
     # Update status with error message
@@ -151,6 +153,11 @@ class JobService:
       error_message
     )
   
+  def update_job_status(self, job_id: PyObjectId,
+                        status: ProcessingStatus,
+                        error_message: str = None) -> ProcessingJob:
+    return self.repository.update_job_status(job_id, status, error_message)
+  
   def delete_job(self, job_id: PyObjectId) -> bool:
     """
     Delete a job from the database.

src/file-processor/app/utils/pdf_annotation.py

@@ -0,0 +1,241 @@
+import fitz  # PyMuPDF
+
+
+class PDFAnnotator:
+  def __init__(self, pdf_path):
+    self.doc = fitz.open(pdf_path)
+  
+  def add_highlight(self, rect, page_num=0, color=(1, 1, 0)):
+    """
+    Add highlight annotation
+
+    Args:
+        rect: (x0, y0, x1, y1) coordinates or fitz.Rect object
+        page_num: Page number (0-indexed), default first page
+        color: RGB tuple (0-1 range), default yellow
+    """
+    page = self.doc[page_num]
+    annot = page.add_highlight_annot(rect)
+    annot.set_colors(stroke=color)
+    annot.update()
+    return annot
+  
+  def add_rectangle(self, rect, page_num=0, color=(1, 0, 0), width=2):
+    """
+    Add rectangle annotation (border only)
+
+    Args:
+        rect: (x0, y0, x1, y1) coordinates or fitz.Rect object
+        page_num: Page number (0-indexed), default first page
+        color: RGB tuple (0-1 range), default red
+        width: Line width in points
+    """
+    page = self.doc[page_num]
+    annot = page.add_rect_annot(rect)
+    annot.set_colors(stroke=color)
+    annot.set_border(width=width)
+    annot.update()
+    return annot
+  
+  def add_text_note(self, point, text, page_num=0, icon="Note"):
+    """
+    Add sticky note annotation
+
+    Args:
+        point: (x, y) position tuple
+        text: Note content string
+        page_num: Page number (0-indexed), default first page
+        icon: "Note", "Comment", "Help", "Insert", "Key", etc.
+    """
+    page = self.doc[page_num]
+    annot = page.add_text_annot(point, text, icon=icon)
+    annot.update()
+    return annot
+  
+  def add_free_text(self, rect, text, page_num=0, fontsize=12,
+                    color=(0, 0, 0)):
+    """
+    Add free text annotation (visible text box)
+
+    Args:
+        rect: (x0, y0, x1, y1) bounding box tuple or fitz.Rect
+        text: Text content string
+        page_num: Page number (0-indexed), default first page
+        fontsize: Font size in points
+        color: Text color RGB tuple (0-1 range)
+    """
+    page = self.doc[page_num]
+    annot = page.add_freetext_annot(
+      rect,
+      text,
+      fontsize=fontsize,
+      text_color=color
+    )
+    annot.update()
+    return annot
+  
+  def add_arrow(self, start_point, end_point, page_num=0,
+                color=(1, 0, 0), width=2):
+    """
+    Add arrow annotation
+
+    Args:
+        start_point: (x, y) tuple for arrow start
+        end_point: (x, y) tuple for arrow end
+        page_num: Page number (0-indexed), default first page
+        color: Arrow color RGB tuple (0-1 range), default red
+        width: Line width in points
+    """
+    page = self.doc[page_num]
+    annot = page.add_line_annot(start_point, end_point)
+    annot.set_colors(stroke=color)
+    annot.set_border(width=width)
+    # Set arrow at end - use integer constant
+    annot.set_line_ends(0, 1)  # 1 = ClosedArrow
+    annot.update()
+    return annot
+  
+  def add_stamp(self, rect, page_num=0, stamp_type=0):
+    """
+    Add stamp annotation
+
+    Args:
+        rect: (x0, y0, x1, y1) bounding box tuple or fitz.Rect
+        page_num: Page number (0-indexed), default first page
+        stamp_type: Integer for stamp type:
+                   0=Approved, 1=AsIs, 2=Confidential,
+                   3=Departmental, 4=Draft, 5=Experimental,
+                   6=Expired, 7=Final, 8=ForComment,
+                   9=ForPublicRelease, 10=NotApproved, etc.
+    """
+    page = self.doc[page_num]
+    annot = page.add_stamp_annot(rect, stamp=stamp_type)
+    annot.update()
+    return annot
+  
+  def add_redaction(self, rect, page_num=0, fill_color=(0, 0, 0)):
+    """
+    Add redaction annotation (marks area for redaction)
+    Note: Use apply_redactions() to permanently remove content
+
+    Args:
+        rect: (x0, y0, x1, y1) area to redact, tuple or fitz.Rect
+        page_num: Page number (0-indexed), default first page
+        fill_color: RGB tuple (0-1 range) for redacted area, default black
+    """
+    page = self.doc[page_num]
+    annot = page.add_redact_annot(rect, fill=fill_color)
+    annot.update()
+    return annot
+  
+  def apply_redactions(self, page_num=0, images=2, graphics=2, text=2):
+    """
+    Apply all redaction annotations on a page (permanent removal)
+
+    Args:
+        page_num: Page number (0-indexed), default first page
+        images: 2=remove, 1=blank, 0=ignore
+        graphics: 2=remove, 1=blank, 0=ignore
+        text: 2=remove, 1=blank, 0=ignore
+
+    Returns:
+        True if redactions were applied, False otherwise
+    """
+    page = self.doc[page_num]
+    # Check if page has redaction annotations
+    has_redactions = any(annot.type[0] == 12 for annot in page.annots())
+    
+    if has_redactions:
+      page.apply_redactions(images=images, graphics=graphics, text=text)
+      return True
+    return False
+  
+  def get_all_annotations(self, page_num=0):
+    """
+    Retrieve all annotations from a page
+
+    Args:
+        page_num: Page number (0-indexed), default first page
+
+    Returns:
+        List of dicts with annotation information
+    """
+    page = self.doc[page_num]
+    annotations = []
+    
+    for annot in page.annots():
+      info = {
+          'type': annot.type[1],  # Annotation type name
+          'rect': annot.rect,
+          'content': annot.info.get('content', ''),
+          'author': annot.info.get('title', ''),
+          'created': annot.info.get('creationDate', ''),
+          'colors': annot.colors
+      }
+      annotations.append(info)
+    
+    return annotations
+  
+  def remove_all_annotations(self, page_num=0):
+    """
+    Remove all annotations from a page
+
+    Args:
+        page_num: Page number (0-indexed), default first page
+    """
+    page = self.doc[page_num]
+    for annot in page.annots():
+      page.delete_annot(annot)
+  
+  def save(self, output_path):
+    """Save the annotated PDF"""
+    self.doc.save(output_path)
+  
+  def close(self):
+    self.doc.close()
+  
+  def __enter__(self):
+    return self
+  
+  def __exit__(self, exc_type, exc_val, exc_tb):
+    self.close()
+
+
+# Example usage
+if __name__ == "__main__":
+  with PDFAnnotator("input.pdf") as annotator:
+    # Add yellow highlight
+    annotator.add_highlight((100, 100, 300, 120), page_num=0,
+                            color=(1, 1, 0))
+    
+    # Add red rectangle border
+    annotator.add_rectangle((100, 150, 300, 250), page_num=0,
+                            color=(1, 0, 0), width=3)
+    
+    # Add sticky note
+    annotator.add_text_note((400, 100), "This is important!",
+                            page_num=0, icon="Comment")
+    
+    # Add visible text box
+    annotator.add_free_text((100, 300, 400, 350), "DRAFT VERSION",
+                            page_num=0, fontsize=20, color=(1, 0, 0))
+    
+    # Add arrow pointing to something
+    annotator.add_arrow((450, 100), (500, 200), page_num=0,
+                        color=(0, 0, 1), width=2)
+    
+    # Add "Approved" stamp
+    annotator.add_stamp((450, 300, 550, 350), page_num=0, stamp_type=0)
+    
+    # Add redaction (black box over sensitive info)
+    annotator.add_redaction((100, 400, 300, 420), page_num=0)
+    annotator.apply_redactions(page_num=0)
+    
+    # List all annotations
+    annots = annotator.get_all_annotations(page_num=0)
+    print(f"Found {len(annots)} annotations:")
+    for a in annots:
+      print(f"  - {a['type']} at {a['rect']}")
+    
+    # Save annotated PDF
+    annotator.save("output_annotated.pdf")

src/file-processor/app/utils/pdf_converter.py

@@ -0,0 +1,210 @@
+import datetime
+import hashlib
+import os
+import uuid
+from abc import ABC
+from pathlib import Path
+from typing import Self
+
+import pikepdf
+import pypandoc
+from PIL import Image
+from reportlab.lib.pagesizes import A4
+from reportlab.pdfgen import canvas
+
+from tasks.common.converter_utils import detect_file_type
+
+
+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"{self.generate_uuid_filename()}.pdf"
+  
+  def convert(self) -> Self:
+    """Convert input file to PDF and return the output path."""
+    pass
+  
+  @staticmethod
+  def generate_uuid_filename() -> str:
+    """Generate a unique filename using UUID4."""
+    return str(uuid.uuid4())
+  
+  def get_deterministic_date(self) -> str:
+    """
+    Generate a deterministic date based on file content.
+    This ensures the same file always produces the same PDF.
+    """
+    # Option 1: Use a fixed date
+    # return "D:20000101000000"
+    
+    # Option 2: Generate date from content hash (recommended)
+    with open(self.input_path, 'rb') as f:
+      content = f.read()
+      content_hash = hashlib.sha256(content).hexdigest()
+    
+    # Use first 14 characters of hash to create a valid date
+    # Format: D:YYYYMMDDHHmmss
+    hash_int = int(content_hash[:14], 16)
+    
+    # Create a date between 2000-2099 to keep it reasonable
+    year = 2000 + (hash_int % 100)
+    month = 1 + (hash_int % 12)
+    day = 1 + (hash_int % 28)  # Stay safe with 28 days
+    hour = hash_int % 24
+    minute = hash_int % 60
+    second = hash_int % 60
+    
+    return f"D:{year:04d}{month:02d}{day:02d}{hour:02d}{minute:02d}{second:02d}"
+  
+  def get_file_creation_date(self):
+    # Get file creation time (or modification time)
+    ts = os.path.getctime(self.input_path)  # getmtime(self.input_path) for last modification
+    dt = datetime.datetime.fromtimestamp(ts)
+    
+    # PDF expects format D:YYYYMMDDHHmmss
+    creation_date = dt.strftime("D:%Y%m%d%H%M%S")
+    return creation_date
+  
+  def clean_pdf(self) -> Self:
+    """Remove all non-deterministic metadata from PDF."""
+    with pikepdf.open(self.output_path, allow_overwriting_input=True) as pdf:
+      # Remove XMP metadata if it exists
+      if hasattr(pdf.Root, 'Metadata'):
+        del pdf.Root.Metadata
+        
+        # Clear all document info by deleting each key
+        for key in list(pdf.docinfo.keys()):
+          del pdf.docinfo[key]
+      
+      # Set deterministic metadata
+      pdf.docinfo["/Producer"] = "MyConverter"
+      pdf.docinfo["/Creator"] = "MyConverter"
+      pdf.docinfo["/CreationDate"] = self.get_deterministic_date()
+      pdf.docinfo["/ModDate"] = self.get_deterministic_date()
+      pdf.docinfo["/Title"] = self.input_path.name
+      
+      # Save with deterministic IDs
+      # compress=True ensures consistent compression
+      # deterministic_id=True (if available) or static_id=True
+      pdf.save(
+        self.output_path,
+        fix_metadata_version=True,
+        compress_streams=True,
+        stream_decode_level=pikepdf.StreamDecodeLevel.generalized,
+        object_stream_mode=pikepdf.ObjectStreamMode.disable,
+        deterministic_id=True  # Use this if pikepdf >= 8.0.0, otherwise use static_id=True
+      )
+    
+    return self
+
+
+class TextToPdfConverter(BaseConverter):
+  """Converter for text files to PDF."""
+  
+  def convert(self) -> Self:
+    c = canvas.Canvas(str(self.output_path), pagesize=A4)
+    
+    # Fix metadata with deterministic values
+    info = c._doc.info
+    info.producer = "MyConverter"
+    info.creationDate = self.get_file_creation_date()
+    info.title = os.path.basename(self.input_path)
+    
+    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 self
+
+
+class PdfToPdfConverter(BaseConverter):
+  """Converter for PDF files to PDF."""
+  
+  def convert(self) -> Self:
+    # copy self.input_path to self.output_path
+    os.system(f"cp {self.input_path} {self.output_path}")
+    return self
+
+
+class ImageToPdfConverter(BaseConverter):
+  """Converter for image files to PDF."""
+  
+  def convert(self) -> Self:
+    image = Image.open(self.input_path)
+    rgb_image = image.convert("RGB")
+    rgb_image.save(self.output_path)
+    return self
+
+
+class WordToPdfConverter(BaseConverter):
+  """Converter for Word files (.docx) to PDF using pypandoc."""
+  
+  def convert(self) -> Self:
+    pypandoc.convert_file(
+      str(self.input_path), "pdf", outputfile=str(self.output_path)
+    )
+    return self
+
+
+# Placeholders for future extensions
+class HtmlToPdfConverter(BaseConverter):
+  """Placeholder for HTML to PDF converter."""
+  
+  def convert(self) -> Self:
+    raise NotImplementedError("HTML to PDF conversion not implemented.")
+
+
+class ExcelToPdfConverter(BaseConverter):
+  """Placeholder for Excel to PDF converter."""
+  
+  def convert(self) -> Self:
+    raise NotImplementedError("Excel to PDF conversion not implemented.")
+
+
+class MarkdownToPdfConverter(BaseConverter):
+  """Placeholder for Markdown to PDF converter."""
+  
+  def convert(self) -> Self:
+    raise NotImplementedError("Markdown to PDF conversion not implemented.")
+
+
+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)
+  elif file_type == "pdf":
+    converter = PdfToPdfConverter(filepath, output_dir=output_dir)
+  else:
+    raise ValueError(f"Unsupported file type: {file_type}")
+  
+  converter.convert()
+  converter.clean_pdf()
+  return str(converter.output_path)

src/file-processor/app/utils/pdf_thumbmail.py

@@ -0,0 +1,167 @@
+from pathlib import Path
+
+import fitz  # PyMuPDF
+
+
+class PDFThumbnailGenerator:
+  def __init__(self, pdf_path):
+    """
+    Initialize PDF thumbnail generator
+
+    Args:
+        pdf_path: Path to the PDF file (string or Path object)
+    """
+    self.pdf_path = pdf_path
+    self.doc = fitz.open(pdf_path)
+  
+  def create_thumbnail(self, output_path, page_num=0, width=200, rotation=0, zoom_factor=1.0):
+    """
+    Create a thumbnail with zoom and rotation
+
+    Args:
+        output_path: Path to save the thumbnail (string or Path)
+        page_num: Page number (0-indexed), default first page
+        width: Desired width in pixels, default 200
+        rotation: Rotation angle in degrees (0, 90, 180, 270), default 0
+        zoom_factor: Additional zoom multiplier (1.0 = normal, 2.0 = 2x), default 1.0
+
+    Returns:
+        Dict with thumbnail info (width, height, rotation, zoom)
+    """
+    page = self.doc[page_num]
+    
+    # Apply rotation to page
+    page.set_rotation(rotation)
+    
+    # Calculate zoom to achieve desired width
+    base_zoom = width / page.rect.width
+    final_zoom = base_zoom * zoom_factor
+    
+    # Create transformation matrix
+    mat = fitz.Matrix(final_zoom, final_zoom)
+    
+    # Render page to pixmap
+    pix = page.get_pixmap(matrix=mat, alpha=False)
+    
+    # Save thumbnail
+    pix.save(output_path)
+    
+    return {
+        'width': pix.width,
+        'height': pix.height,
+        'rotation': rotation,
+        'zoom': zoom_factor
+    }
+  
+  def create_cropped_thumbnail(self, output_path, crop_rect=None, page_num=0, width=200):
+    """
+    Create a thumbnail of a specific region (zoom on area)
+
+    Args:
+        output_path: Path to save the thumbnail (string or Path)
+        crop_rect: Tuple (x0, y0, x1, y1) in PDF coordinates for cropping,
+                  or None for full page, default None
+        page_num: Page number (0-indexed), default first page
+        width: Desired width in pixels, default 200
+
+    Returns:
+        Tuple (width, height) of the generated thumbnail
+    """
+    page = self.doc[page_num]
+    
+    if crop_rect:
+      # Create rectangle for cropping
+      rect = fitz.Rect(crop_rect)
+      zoom = width / rect.width
+    else:
+      rect = page.rect
+      zoom = width / page.rect.width
+    
+    mat = fitz.Matrix(zoom, zoom)
+    
+    # Render only the specified rectangle
+    pix = page.get_pixmap(matrix=mat, clip=rect)
+    pix.save(output_path)
+    
+    return pix.width, pix.height
+  
+  def get_page_info(self, page_num=0):
+    """
+    Get information about a specific page
+
+    Args:
+        page_num: Page number (0-indexed), default first page
+
+    Returns:
+        Dict with page information (width, height, rotation, number, total_pages)
+    """
+    page = self.doc[page_num]
+    return {
+        'width': page.rect.width,
+        'height': page.rect.height,
+        'rotation': page.rotation,
+        'number': page_num + 1,
+        'total_pages': len(self.doc)
+    }
+  
+  def create_multi_resolution_thumbnails(self, output_folder, page_num=0, sizes=(150, 300, 600)):
+    """
+    Create multiple thumbnails at different resolutions
+
+    Args:
+        output_folder: Folder path to save thumbnails (string or Path)
+        page_num: Page number (0-indexed), default first page
+        sizes: List of widths in pixels, default [150, 300, 600]
+
+    Returns:
+        Dict mapping each size to thumbnail info
+    """
+    output_folder = Path(output_folder)
+    output_folder.mkdir(exist_ok=True, parents=True)
+    
+    results = {}
+    for size in sizes:
+      output_path = output_folder / f"thumb_{size}px.png"
+      info = self.create_thumbnail(output_path, page_num=page_num, width=size)
+      results[size] = info
+    
+    return results
+  
+  def close(self):
+    """Close the PDF document and free resources"""
+    self.doc.close()
+  
+  def __enter__(self):
+    return self
+  
+  def __exit__(self, exc_type, exc_val, exc_tb):
+    self.close()
+
+
+# Example usage
+if __name__ == "__main__":
+  # Basic usage with context manager
+  with PDFThumbnailGenerator("example.pdf") as gen:
+    # Standard thumbnail
+    gen.create_thumbnail("thumb_standard.png", page_num=0, width=200)
+    
+    # Rotated thumbnail
+    gen.create_thumbnail("thumb_rotated.png", page_num=0,
+                         width=200, rotation=90)
+    
+    # Zoomed thumbnail (2x zoom)
+    gen.create_thumbnail("thumb_zoomed.png", page_num=0,
+                         width=200, zoom_factor=2.0)
+    
+    # Cropped/zoomed on specific area (x0, y0, x1, y1)
+    gen.create_cropped_thumbnail("thumb_crop.png",
+                                 crop_rect=(100, 100, 400, 400),
+                                 page_num=0, width=300)
+    
+    # Multiple resolutions
+    gen.create_multi_resolution_thumbnails("thumbnails/", page_num=0,
+                                           sizes=[150, 300, 600])
+    
+    # Get page information
+    info = gen.get_page_info(page_num=0)
+    print(f"Page info: {info}")

src/file-processor/app/utils/security.py

@@ -4,9 +4,10 @@ Password security utilities using bcrypt for secure password hashing.
 This module provides secure password hashing and verification functions
 using the bcrypt algorithm with automatic salt generation.
 """
+import re
+import uuid
 
 import bcrypt
-from typing import Union
 
 
 def hash_password(password: str) -> str:
@@ -71,4 +72,33 @@ def verify_password(password: str, hashed_password: str) -> bool:
     # bcrypt raises ValueError for malformed hashes
     raise RuntimeError(f"Invalid hash format: {str(e)}")
   except Exception as e:
-    raise RuntimeError(f"Failed to verify password: {str(e)}")
+    raise RuntimeError(f"Failed to verify password: {str(e)}")
+
+
+def generate_uuid_filename() -> str:
+  """Generate a unique filename using UUID4."""
+  return str(uuid.uuid4())
+
+
+def safe_connection_string(connection_string: str) -> str:
+  """
+  Mask the password in a MongoDB connection string.
+
+  Args:
+      connection_string (str): The complete MongoDB connection string
+
+  Returns:
+      str: The connection string with password replaced by asterisks
+
+  Example:
+      >>> mask_mongodb_password("mongodb://admin:password123@mongodb:27017/mydocmanager?authSource=admin")
+      "mongodb://admin:***@mongodb:27017/mydocmanager?authSource=admin"
+  """
+  # Pattern to detect password in MongoDB URL
+  # Format: mongodb://username:password@host:port/database
+  pattern = r'(mongodb://[^:]+:)([^@]+)(@.*)'
+  
+  # Replace password with asterisks
+  masked_string = re.sub(pattern, r'\1*****\3', connection_string)
+  
+  return masked_string

src/file-processor/requirements.txt

@@ -5,10 +5,12 @@ email-validator==2.3.0
 fastapi==0.116.1
 httptools==0.6.4
 motor==3.7.1
+pikepdf==9.11.0
 pillow==11.3.0
 pydantic==2.11.9
 PyJWT==2.10.1
 pymongo==4.15.0
+PyMuPDF==1.26.4
 pypandoc==1.15
 python-multipart==0.0.20
 redis==6.4.0

src/frontend/README.md

@@ -1,12 +1,93 @@
-# React + Vite
 
-This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
+# MyDocManager Frontend
 
-Currently, two official plugins are available:
+## Overview
+MyDocManager Frontend is a modern web application built with React and Vite that serves as the user interface for the MyDocManager document management system. The application provides a seamless experience for users to manage, process, and organize their documents with an intuitive and responsive interface.
 
-- [@vitejs/plugin-react](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react) uses [Babel](https://babeljs.io/) for Fast Refresh
-- [@vitejs/plugin-react-swc](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react-swc) uses [SWC](https://swc.rs/) for Fast Refresh
+## Project Structure
+frontend/
+├── public/                  # Public assets and static files
+├── src/                     # Source code
+│   ├── assets/             # Icons, images, and other static assets
+│   ├── components/         # Reusable UI components
+│   │   ├── auth/          # Authentication-related components
+│   │   └── common/        # Shared components (Header, Layout, etc.)
+│   ├── contexts/          # React contexts for state management
+│   ├── hooks/             # Custom React hooks
+│   ├── pages/             # Page components representing full views
+│   ├── services/          # API service interfaces
+│   └── utils/             # Utility functions and helpers
+├── Dockerfile             # Container configuration for deployment
+├── package.json           # Dependencies and scripts
+├── tailwind.config.js     # Tailwind CSS configuration
+└── vite.config.js         # Vite bundler configuration
 
-## Expanding the ESLint configuration
 
-If you are developing a production application, we recommend using TypeScript with type-aware lint rules enabled. Check out the [TS template](https://github.com/vitejs/vite/tree/main/packages/create-vite/template-react-ts) for information on how to integrate TypeScript and [`typescript-eslint`](https://typescript-eslint.io) in your project.
+
+## Key Components
+
+### Authentication
+- **AuthContext**: Provides authentication state and methods throughout the application
+- **AuthLayout**: Layout wrapper specifically for authentication screens
+- **LoginForm**: Form component for user authentication
+- **ProtectedRoute**: Route guard that ensures authenticated access to protected pages
+
+### UI Components
+- **Layout**: Main application layout structure with menu and content areas
+- **Header**: Application header with navigation and user controls
+- **Menu**: Side navigation menu with application links
+- **ThemeSwitcher**: Toggle for switching between light and dark themes
+
+### Pages
+- **LoginPage**: User authentication page
+- **DashboardPage**: Main dashboard view for authenticated users
+
+### Services
+- **authService**: Handles API communication for authentication operations
+- **api**: Base API utility for making HTTP requests to the backend
+
+## Getting Started
+
+### Prerequisites
+- Node.js (latest LTS version)
+- npm or yarn package manager
+
+### Installation
+1. Clone the repository
+2. Navigate to the frontend directory
+3. Install dependencies:
+```
+npm install
+```
+
+### Development
+Run the development server:
+```
+npm run dev
+```
+This will start the application in development mode at http://localhost:5173
+
+### Building for Production
+Create a production build:
+```
+npm run build
+```
+
+
+## Technologies
+- React 19.1.1
+- Vite 7.1.2
+- Tailwind CSS 4.1.13
+- DaisyUI 5.1.24
+- React Router 7.9.3
+- Axios for API requests
+
+## Features
+- Responsive design with Tailwind CSS
+- Authentication and authorization
+- Light/dark theme support
+- Document management interface
+- Secure API communication
+
+## Project Integration
+This frontend application works in conjunction with the backend services and workers defined in other parts of the MyDocManager project to provide a complete document management solution.

src/frontend/src/App.jsx

@@ -4,6 +4,7 @@ import ProtectedRoute from './components/common/ProtectedRoute';
 import Layout from './components/common/Layout';
 import LoginPage from './pages/LoginPage';
 import DashboardPage from './pages/DashboardPage';
+import DocumentsPage from './pages/DocumentsPage';
 
 function App() {
   return (
@@ -16,7 +17,8 @@ function App() {
 
             {/* Protected Routes */}
             <Route path="/" element={<ProtectedRoute><Layout /></ProtectedRoute>}>
-              <Route index element={<Navigate to="/dashboard" replace />} />
+              <Route index element={<Navigate to="/documents" replace />} />
+              <Route path="documents" element={<DocumentsPage />} />
               <Route path="dashboard" element={<DashboardPage />} />
               <Route path="documents" element={<div>Documents Page - Coming Soon</div>} />
               <Route path="users" element={<div>User Management - Coming Soon</div>} />

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

@@ -1,11 +1,13 @@
 import {FaBuffer, FaPlus} from "react-icons/fa6";
+import { Link } from "react-router-dom";
 
 const Menu = () => {
   return (
     <div className="p-4">
       <ul className="menu">
         <li className="menu-title">Exploration</li>
-        <li><a><FaBuffer/>To Review</a></li>
+        <li><Link to="/dashboard"><FaBuffer/>Dashboard</Link></li>
+        <li><Link to="/documents"><FaBuffer/>To Review</Link></li>
         <li className="menu-title mt-4">Catégories</li>
         <li><a><i className="fas fa-plus"></i>Item</a></li>
       </ul>

src/frontend/src/components/documents/DeleteConfirmModal.jsx

@@ -0,0 +1,68 @@
+/**
+ * DeleteConfirmModal Component
+ * Modal dialog to confirm document deletion
+ */
+
+import React from 'react';
+
+/**
+ * DeleteConfirmModal component
+ * @param {Object} props
+ * @param {boolean} props.isOpen - Whether the modal is open
+ * @param {Object|null} props.document - Document to delete
+ * @param {function(): void} props.onClose - Callback when modal is closed
+ * @param {function(): void} props.onConfirm - Callback when deletion is confirmed
+ * @param {boolean} props.isDeleting - Whether deletion is in progress
+ * @returns {JSX.Element}
+ */
+const DeleteConfirmModal = ({
+                              isOpen,
+                              document,
+                              onClose,
+                              onConfirm,
+                              isDeleting = false
+                            }) => {
+  if (!isOpen || !document) return null;
+
+  return (
+    <dialog className="modal modal-open">
+      <div className="modal-box">
+        <h3 className="font-bold text-lg">Confirm Deletion</h3>
+        <p className="py-4">
+          Are you sure you want to delete <span className="font-semibold">"{document.name}"</span>?
+        </p>
+        <p className="text-sm text-gray-500">
+          This action cannot be undone.
+        </p>
+        <div className="modal-action">
+          <button
+            className="btn btn-ghost"
+            onClick={onClose}
+            disabled={isDeleting}
+          >
+            Cancel
+          </button>
+          <button
+            className="btn btn-error"
+            onClick={onConfirm}
+            disabled={isDeleting}
+          >
+            {isDeleting ? (
+              <>
+                <span className="loading loading-spinner loading-sm"></span>
+                Deleting...
+              </>
+            ) : (
+              'Delete'
+            )}
+          </button>
+        </div>
+      </div>
+      <form method="dialog" className="modal-backdrop" onClick={onClose}>
+        <button disabled={isDeleting}>close</button>
+      </form>
+    </dialog>
+  );
+};
+
+export default DeleteConfirmModal;

src/frontend/src/components/documents/DocumentCard.jsx

@@ -0,0 +1,193 @@
+/**
+ * DocumentCard Component
+ * Displays a document as a DaisyUI card with thumbnail and metadata
+ * Supports different view modes: small, large, and detail
+ */
+
+import React, { memo } from 'react';
+
+/**
+ * Formats file size to human-readable format
+ * @param {number} bytes - File size in bytes
+ * @returns {string} Formatted file size
+ */
+const formatFileSize = (bytes) => {
+  if (bytes === 0) return '0 Bytes';
+  const k = 1024;
+  const sizes = ['Bytes', 'KB', 'MB', 'GB'];
+  const i = Math.floor(Math.log(bytes) / Math.log(k));
+  return Math.round((bytes / Math.pow(k, i)) * 100) / 100 + ' ' + sizes[i];
+};
+
+/**
+ * Formats date to localized string
+ * @param {string} dateString - ISO date string
+ * @returns {string} Formatted date
+ */
+const formatDate = (dateString) => {
+  return new Date(dateString).toLocaleDateString('en-US', {
+    year: 'numeric',
+    month: 'short',
+    day: 'numeric'
+  });
+};
+
+/**
+ * DocumentCard component
+ * @param {Object} props
+ * @param {Object} props.document - Document object
+ * @param {'small'|'large'|'detail'} props.viewMode - Current view mode
+ * @param {function(): void} props.onEdit - Callback when edit is clicked
+ * @param {function(): void} props.onDelete - Callback when delete is clicked
+ * @returns {JSX.Element}
+ */
+const DocumentCard = memo(({ document, viewMode, onEdit, onDelete }) => {
+  const { name, originalFileType, thumbnailUrl, pageCount, fileSize, createdAt, tags, categories } = document;
+
+  // Determine card classes based on view mode
+  const getCardClasses = () => {
+    const baseClasses = 'card bg-base-100 shadow-xl hover:shadow-2xl transition-shadow group relative';
+
+    switch (viewMode) {
+      case 'small':
+        return `${baseClasses} w-full`;
+      case 'large':
+        return `${baseClasses} w-full`;
+      case 'detail':
+        return `${baseClasses} w-full`;
+      default:
+        return baseClasses;
+    }
+  };
+
+  // Render thumbnail with hover actions
+  const renderThumbnail = () => (
+    <figure className="relative overflow-hidden">
+      <img
+        src={`http://localhost:8000${thumbnailUrl}`}
+        alt={`${thumbnailUrl} thumbnail`}
+        className={`w-full object-cover ${
+          viewMode === 'small' ? 'h-32' : viewMode === 'large' ? 'h-48' : 'h-64'
+        }`}
+        loading="lazy"
+      />
+
+      {/* Hover overlay with actions */}
+      <div className="absolute top-2 right-2 flex gap-2 opacity-0 group-hover:opacity-100 transition-opacity">
+        <button
+          className="btn btn-sm btn-circle btn-primary"
+          onClick={onEdit}
+          aria-label="Edit document"
+          title="Edit"
+        >
+          <svg xmlns="http://www.w3.org/2000/svg" className="h-4 w-4" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+            <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z" />
+          </svg>
+        </button>
+        <button
+          className="btn btn-sm btn-circle btn-error"
+          onClick={onDelete}
+          aria-label="Delete document"
+          title="Delete"
+        >
+          <svg xmlns="http://www.w3.org/2000/svg" className="h-4 w-4" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+            <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 7l-.867 12.142A2 2 0 0116.138 21H7.862a2 2 0 01-1.995-1.858L5 7m5 4v6m4-6v6m1-10V4a1 1 0 00-1-1h-4a1 1 0 00-1 1v3M4 7h16" />
+          </svg>
+        </button>
+      </div>
+
+      {/* File type badge */}
+      <div className="absolute bottom-2 left-2">
+        <span className="badge badge-accent badge-sm">{originalFileType}</span>
+      </div>
+    </figure>
+  );
+
+  // Render card body based on view mode
+  const renderCardBody = () => {
+    if (viewMode === 'small') {
+      return (
+        <div className="card-body p-3">
+          <h3 className="card-title text-sm truncate" title={name}>{name}</h3>
+          <p className="text-xs text-gray-500">{pageCount} page{pageCount > 1 ? 's' : ''}</p>
+        </div>
+      );
+    }
+
+    if (viewMode === 'large') {
+      return (
+        <div className="card-body p-4">
+          <h3 className="card-title text-base truncate" title={name}>{name}</h3>
+          <div className="flex flex-wrap gap-1 mb-2">
+            {tags.slice(0, 3).map(tag => (
+              <span key={tag} className="badge badge-primary badge-xs">{tag}</span>
+            ))}
+            {tags.length > 3 && (
+              <span className="badge badge-ghost badge-xs">+{tags.length - 3}</span>
+            )}
+          </div>
+          <div className="text-sm space-y-1">
+            <p className="text-gray-500">{pageCount} page{pageCount > 1 ? 's' : ''}</p>
+            <p className="text-gray-500">{formatFileSize(fileSize)}</p>
+          </div>
+        </div>
+      );
+    }
+
+    // Detail mode
+    return (
+      <div className="card-body">
+        <h3 className="card-title text-lg" title={name}>{name}</h3>
+
+        {/* Tags */}
+        {tags.length > 0 && (
+          <div className="flex flex-wrap gap-1 mb-2">
+            {tags.map(tag => (
+              <span key={tag} className="badge badge-primary badge-sm">{tag}</span>
+            ))}
+          </div>
+        )}
+
+        {/* Categories */}
+        {categories.length > 0 && (
+          <div className="flex flex-wrap gap-1 mb-3">
+            {categories.map(category => (
+              <span key={category} className="badge badge-secondary badge-sm">{category}</span>
+            ))}
+          </div>
+        )}
+
+        {/* Metadata */}
+        <div className="grid grid-cols-2 gap-2 text-sm">
+          <div>
+            <span className="font-semibold">Pages:</span>
+            <span className="ml-2 text-gray-500">{pageCount}</span>
+          </div>
+          <div>
+            <span className="font-semibold">Size:</span>
+            <span className="ml-2 text-gray-500">{formatFileSize(fileSize)}</span>
+          </div>
+          <div>
+            <span className="font-semibold">Type:</span>
+            <span className="ml-2 text-gray-500">{originalFileType}</span>
+          </div>
+          <div>
+            <span className="font-semibold">Date:</span>
+            <span className="ml-2 text-gray-500">{formatDate(createdAt)}</span>
+          </div>
+        </div>
+      </div>
+    );
+  };
+
+  return (
+    <div className={getCardClasses()}>
+      {renderThumbnail()}
+      {renderCardBody()}
+    </div>
+  );
+});
+
+DocumentCard.displayName = 'DocumentCard';
+
+export default DocumentCard;

src/frontend/src/components/documents/DocumentDetailView.jsx

@@ -0,0 +1,164 @@
+/**
+ * DocumentDetailView Component
+ * Displays a document in detail mode with all pages visible
+ * This is a placeholder that shows multiple page thumbnails
+ * When real PDF backend is ready, this can be replaced with actual PDF rendering
+ */
+
+import React from 'react';
+
+/**
+ * Formats file size to human-readable format
+ * @param {number} bytes - File size in bytes
+ * @returns {string} Formatted file size
+ */
+const formatFileSize = (bytes) => {
+  if (bytes === 0) return '0 Bytes';
+  const k = 1024;
+  const sizes = ['Bytes', 'KB', 'MB', 'GB'];
+  const i = Math.floor(Math.log(bytes) / Math.log(k));
+  return Math.round((bytes / Math.pow(k, i)) * 100) / 100 + ' ' + sizes[i];
+};
+
+/**
+ * Formats date to localized string
+ * @param {string} dateString - ISO date string
+ * @returns {string} Formatted date
+ */
+const formatDate = (dateString) => {
+  return new Date(dateString).toLocaleDateString('en-US', {
+    year: 'numeric',
+    month: 'long',
+    day: 'numeric',
+    hour: '2-digit',
+    minute: '2-digit'
+  });
+};
+
+/**
+ * DocumentDetailView component
+ * @param {Object} props
+ * @param {Object} props.document - Document object
+ * @param {function(): void} props.onEdit - Callback when edit is clicked
+ * @param {function(): void} props.onDelete - Callback when delete is clicked
+ * @returns {JSX.Element}
+ */
+const DocumentDetailView = ({ document, onEdit, onDelete }) => {
+  const {
+    name,
+    originalFileType,
+    thumbnailUrl,
+    pageCount,
+    fileSize,
+    createdAt,
+    tags,
+    categories
+  } = document;
+
+  // Generate placeholder pages (in real implementation, these would be actual PDF pages)
+  const pages = Array.from({ length: pageCount }, (_, i) => ({
+    pageNumber: i + 1,
+    thumbnailUrl: thumbnailUrl.replace('Page+1', `Page+${i + 1}`)
+  }));
+
+  return (
+    <div className="card bg-base-100 shadow-xl">
+      {/* Header with actions */}
+      <div className="card-body">
+        <div className="flex justify-between items-start mb-4">
+          <div className="flex-1">
+            <h2 className="card-title text-2xl mb-2">{name}</h2>
+
+            {/* Tags */}
+            {tags.length > 0 && (
+              <div className="flex flex-wrap gap-2 mb-2">
+                <span className="text-sm font-semibold text-gray-600">Tags:</span>
+                {tags.map(tag => (
+                  <span key={tag} className="badge badge-primary">{tag}</span>
+                ))}
+              </div>
+            )}
+
+            {/* Categories */}
+            {categories.length > 0 && (
+              <div className="flex flex-wrap gap-2 mb-3">
+                <span className="text-sm font-semibold text-gray-600">Categories:</span>
+                {categories.map(category => (
+                  <span key={category} className="badge badge-secondary">{category}</span>
+                ))}
+              </div>
+            )}
+          </div>
+
+          {/* Action buttons */}
+          <div className="flex gap-2">
+            <button
+              className="btn btn-primary btn-sm"
+              onClick={onEdit}
+              aria-label="Edit document"
+            >
+              <svg xmlns="http://www.w3.org/2000/svg" className="h-4 w-4" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+                <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z" />
+              </svg>
+              Edit
+            </button>
+            <button
+              className="btn btn-error btn-sm"
+              onClick={onDelete}
+              aria-label="Delete document"
+            >
+              <svg xmlns="http://www.w3.org/2000/svg" className="h-4 w-4" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+                <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 7l-.867 12.142A2 2 0 0116.138 21H7.862a2 2 0 01-1.995-1.858L5 7m5 4v6m4-6v6m1-10V4a1 1 0 00-1-1h-4a1 1 0 00-1 1v3M4 7h16" />
+              </svg>
+              Delete
+            </button>
+          </div>
+        </div>
+
+        {/* Metadata grid */}
+        <div className="grid grid-cols-2 md:grid-cols-4 gap-4 mb-6 p-4 bg-base-200 rounded-lg">
+          <div>
+            <span className="text-sm font-semibold text-gray-600">Original Type</span>
+            <p className="text-lg">{originalFileType}</p>
+          </div>
+          <div>
+            <span className="text-sm font-semibold text-gray-600">Pages</span>
+            <p className="text-lg">{pageCount}</p>
+          </div>
+          <div>
+            <span className="text-sm font-semibold text-gray-600">File Size</span>
+            <p className="text-lg">{formatFileSize(fileSize)}</p>
+          </div>
+          <div>
+            <span className="text-sm font-semibold text-gray-600">Created</span>
+            <p className="text-lg">{formatDate(createdAt)}</p>
+          </div>
+        </div>
+
+        {/* Pages preview */}
+        <div>
+          <h3 className="text-lg font-semibold mb-4">Document Pages ({pageCount})</h3>
+          <div className="grid grid-cols-2 md:grid-cols-3 lg:grid-cols-4 gap-4">
+            {pages.map((page) => (
+              <div key={page.pageNumber} className="relative group">
+                <div className="aspect-[3/4] bg-base-200 rounded-lg overflow-hidden shadow-md hover:shadow-xl transition-shadow">
+                  <img
+                    src={page.thumbnailUrl}
+                    alt={`Page ${page.pageNumber}`}
+                    className="w-full h-full object-cover"
+                    loading="lazy"
+                  />
+                </div>
+                <div className="text-center mt-2">
+                  <span className="text-sm text-gray-600">Page {page.pageNumber}</span>
+                </div>
+              </div>
+            ))}
+          </div>
+        </div>
+      </div>
+    </div>
+  );
+};
+
+export default DocumentDetailView;

src/frontend/src/components/documents/DocumentGallery.jsx

@@ -0,0 +1,180 @@
+/**
+ * DocumentGallery Component
+ * Main container for displaying documents in different view modes
+ */
+
+import React, { useState } from 'react';
+import DocumentCard from './DocumentCard';
+import DocumentDetailView from './DocumentDetailView';
+import ViewModeSwitcher from './ViewModeSwitcher';
+import EditDocumentModal from './EditDocumentModal';
+import DeleteConfirmModal from './DeleteConfirmModal';
+import { useDocuments } from '../../hooks/useDocuments';
+
+/**
+ * DocumentGallery component
+ * @returns {JSX.Element}
+ */
+const DocumentGallery = () => {
+  const { documents, loading, error, updateDocument, deleteDocument } = useDocuments();
+  const [viewMode, setViewMode] = useState('large');
+  const [editingDocument, setEditingDocument] = useState(null);
+  const [deletingDocument, setDeletingDocument] = useState(null);
+  const [isSaving, setIsSaving] = useState(false);
+  const [isDeleting, setIsDeleting] = useState(false);
+
+  /**
+   * Handles opening the edit modal
+   * @param {Object} document - Document to edit
+   */
+  const handleEditClick = (document) => {
+    setEditingDocument(document);
+  };
+
+  /**
+   * Handles opening the delete confirmation modal
+   * @param {Object} document - Document to delete
+   */
+  const handleDeleteClick = (document) => {
+    setDeletingDocument(document);
+  };
+
+  /**
+   * Handles saving document changes
+   * @param {Object} updates - Updates object with tags and categories
+   */
+  const handleSaveEdit = async (updates) => {
+    if (!editingDocument) return;
+
+    setIsSaving(true);
+    const success = await updateDocument(editingDocument.id, updates);
+    setIsSaving(false);
+
+    if (success) {
+      setEditingDocument(null);
+    }
+  };
+
+  /**
+   * Handles confirming document deletion
+   */
+  const handleConfirmDelete = async () => {
+    if (!deletingDocument) return;
+
+    setIsDeleting(true);
+    const success = await deleteDocument(deletingDocument.id);
+    setIsDeleting(false);
+
+    if (success) {
+      setDeletingDocument(null);
+    }
+  };
+
+  /**
+   * Gets grid classes based on view mode
+   * @returns {string} Tailwind CSS classes
+   */
+  const getGridClasses = () => {
+    switch (viewMode) {
+      case 'small':
+        return 'grid grid-cols-2 sm:grid-cols-3 md:grid-cols-4 lg:grid-cols-5 xl:grid-cols-6 gap-4';
+      case 'large':
+        return 'grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-3 gap-6';
+      case 'detail':
+        return 'flex flex-col gap-6';
+      default:
+        return 'grid grid-cols-1 gap-4';
+    }
+  };
+
+  // Loading state
+  if (loading) {
+    return (
+      <div className="flex justify-center items-center min-h-[400px]">
+        <span className="loading loading-spinner loading-lg"></span>
+      </div>
+    );
+  }
+
+  // Error state
+  if (error) {
+    return (
+      <div className="alert alert-error">
+        <svg xmlns="http://www.w3.org/2000/svg" className="stroke-current shrink-0 h-6 w-6" fill="none" viewBox="0 0 24 24">
+          <path strokeLinecap="round" strokeLinejoin="round" strokeWidth="2" d="M10 14l2-2m0 0l2-2m-2 2l-2-2m2 2l2 2m7-2a9 9 0 11-18 0 9 9 0 0118 0z" />
+        </svg>
+        <span>Error loading documents: {error}</span>
+      </div>
+    );
+  }
+
+  // Empty state
+  if (documents.length === 0) {
+    return (
+      <div className="flex flex-col items-center justify-center min-h-[400px] text-center">
+        <svg xmlns="http://www.w3.org/2000/svg" className="h-24 w-24 text-gray-300 mb-4" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+          <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M9 12h6m-6 4h6m2 5H7a2 2 0 01-2-2V5a2 2 0 012-2h5.586a1 1 0 01.707.293l5.414 5.414a1 1 0 01.293.707V19a2 2 0 01-2 2z" />
+        </svg>
+        <h3 className="text-xl font-semibold mb-2">No documents yet</h3>
+        <p className="text-gray-500">Upload your first document to get started</p>
+      </div>
+    );
+  }
+
+  return (
+    <div>
+      {/* Header with view mode switcher */}
+      <div className="flex justify-between items-center mb-6">
+        <div>
+          <h2 className="text-2xl font-bold">Documents</h2>
+          <p className="text-gray-500">{documents.length} document{documents.length !== 1 ? 's' : ''}</p>
+        </div>
+        <ViewModeSwitcher
+          currentMode={viewMode}
+          onModeChange={setViewMode}
+        />
+      </div>
+
+      {/* Document grid/list */}
+      <div className={getGridClasses()}>
+        {documents.map(document => (
+          viewMode === 'detail' ? (
+            <DocumentDetailView
+              key={document.id}
+              document={document}
+              onEdit={() => handleEditClick(document)}
+              onDelete={() => handleDeleteClick(document)}
+            />
+          ) : (
+            <DocumentCard
+              key={document.id}
+              document={document}
+              viewMode={viewMode}
+              onEdit={() => handleEditClick(document)}
+              onDelete={() => handleDeleteClick(document)}
+            />
+          )
+        ))}
+      </div>
+
+      {/* Modals */}
+      <EditDocumentModal
+        isOpen={!!editingDocument}
+        document={editingDocument}
+        onClose={() => setEditingDocument(null)}
+        onSave={handleSaveEdit}
+        isSaving={isSaving}
+      />
+
+      <DeleteConfirmModal
+        isOpen={!!deletingDocument}
+        document={deletingDocument}
+        onClose={() => setDeletingDocument(null)}
+        onConfirm={handleConfirmDelete}
+        isDeleting={isDeleting}
+      />
+    </div>
+  );
+};
+
+export default DocumentGallery;

src/frontend/src/components/documents/EditDocumentModal.jsx

@@ -0,0 +1,225 @@
+/**
+ * EditDocumentModal Component
+ * Modal dialog for editing document tags and categories
+ */
+
+import React, { useState, useEffect } from 'react';
+import { getAvailableTags, getAvailableCategories } from '../../services/documentService';
+
+/**
+ * EditDocumentModal component
+ * @param {Object} props
+ * @param {boolean} props.isOpen - Whether the modal is open
+ * @param {Object|null} props.document - Document to edit
+ * @param {function(): void} props.onClose - Callback when modal is closed
+ * @param {function(Object): void} props.onSave - Callback when changes are saved
+ * @param {boolean} props.isSaving - Whether save is in progress
+ * @returns {JSX.Element}
+ */
+const EditDocumentModal = ({
+  isOpen,
+  document,
+  onClose,
+  onSave,
+  isSaving = false
+}) => {
+  const [selectedTags, setSelectedTags] = useState([]);
+  const [selectedCategories, setSelectedCategories] = useState([]);
+  const [availableTags, setAvailableTags] = useState([]);
+  const [availableCategories, setAvailableCategories] = useState([]);
+  const [newTag, setNewTag] = useState('');
+  const [newCategory, setNewCategory] = useState('');
+
+  // Load available tags and categories
+  useEffect(() => {
+    const loadOptions = async () => {
+      const [tags, categories] = await Promise.all([
+        getAvailableTags(),
+        getAvailableCategories()
+      ]);
+      setAvailableTags(tags);
+      setAvailableCategories(categories);
+    };
+    loadOptions();
+  }, []);
+
+  // Initialize selected values when document changes
+  useEffect(() => {
+    if (document) {
+      setSelectedTags(document.tags || []);
+      setSelectedCategories(document.categories || []);
+    }
+  }, [document]);
+
+  const handleAddTag = (tag) => {
+    if (tag && !selectedTags.includes(tag)) {
+      setSelectedTags([...selectedTags, tag]);
+    }
+    setNewTag('');
+  };
+
+  const handleRemoveTag = (tag) => {
+    setSelectedTags(selectedTags.filter(t => t !== tag));
+  };
+
+  const handleAddCategory = (category) => {
+    if (category && !selectedCategories.includes(category)) {
+      setSelectedCategories([...selectedCategories, category]);
+    }
+    setNewCategory('');
+  };
+
+  const handleRemoveCategory = (category) => {
+    setSelectedCategories(selectedCategories.filter(c => c !== category));
+  };
+
+  const handleSave = () => {
+    onSave({
+      tags: selectedTags,
+      categories: selectedCategories
+    });
+  };
+
+  if (!isOpen || !document) return null;
+
+  return (
+    <dialog className="modal modal-open">
+      <div className="modal-box max-w-2xl">
+        <h3 className="font-bold text-lg mb-4">Edit Document</h3>
+
+        <div className="mb-4">
+          <p className="text-sm text-gray-500">
+            Document: <span className="font-semibold">{document.name}</span>
+          </p>
+        </div>
+
+        {/* Tags Section */}
+        <div className="mb-6">
+          <label className="label">
+            <span className="label-text font-semibold">Tags</span>
+          </label>
+
+          {/* Selected Tags */}
+          <div className="flex flex-wrap gap-2 mb-3">
+            {selectedTags.map(tag => (
+              <div key={tag} className="badge badge-primary gap-2">
+                {tag}
+                <button
+                  type="button"
+                  className="btn btn-ghost btn-xs"
+                  onClick={() => handleRemoveTag(tag)}
+                  disabled={isSaving}
+                >
+                  ✕
+                </button>
+              </div>
+            ))}
+          </div>
+
+          {/* Add Tag */}
+          <div className="flex gap-2">
+            <select
+              className="select select-bordered flex-1"
+              value={newTag}
+              onChange={(e) => setNewTag(e.target.value)}
+              disabled={isSaving}
+            >
+              <option value="">Select a tag...</option>
+              {availableTags
+                .filter(tag => !selectedTags.includes(tag))
+                .map(tag => (
+                  <option key={tag} value={tag}>{tag}</option>
+                ))
+              }
+            </select>
+            <button
+              className="btn btn-primary"
+              onClick={() => handleAddTag(newTag)}
+              disabled={!newTag || isSaving}
+            >
+              Add
+            </button>
+          </div>
+        </div>
+
+        {/* Categories Section */}
+        <div className="mb-6">
+          <label className="label">
+            <span className="label-text font-semibold">Categories</span>
+          </label>
+
+          {/* Selected Categories */}
+          <div className="flex flex-wrap gap-2 mb-3">
+            {selectedCategories.map(category => (
+              <div key={category} className="badge badge-secondary gap-2">
+                {category}
+                <button
+                  type="button"
+                  className="btn btn-ghost btn-xs"
+                  onClick={() => handleRemoveCategory(category)}
+                  disabled={isSaving}
+                >
+                  ✕
+                </button>
+              </div>
+            ))}
+          </div>
+
+          {/* Add Category */}
+          <div className="flex gap-2">
+            <select
+              className="select select-bordered flex-1"
+              value={newCategory}
+              onChange={(e) => setNewCategory(e.target.value)}
+              disabled={isSaving}
+            >
+              <option value="">Select a category...</option>
+              {availableCategories
+                .filter(cat => !selectedCategories.includes(cat))
+                .map(cat => (
+                  <option key={cat} value={cat}>{cat}</option>
+                ))
+              }
+            </select>
+            <button
+              className="btn btn-secondary"
+              onClick={() => handleAddCategory(newCategory)}
+              disabled={!newCategory || isSaving}
+            >
+              Add
+            </button>
+          </div>
+        </div>
+
+        <div className="modal-action">
+          <button
+            className="btn btn-ghost"
+            onClick={onClose}
+            disabled={isSaving}
+          >
+            Cancel
+          </button>
+          <button
+            className="btn btn-primary"
+            onClick={handleSave}
+            disabled={isSaving}
+          >
+            {isSaving ? (
+              <>
+                <span className="loading loading-spinner loading-sm"></span>
+                Saving...
+              </>
+            ) : (
+              'Save Changes'
+            )}
+          </button>
+        </div>
+      </div>
+      <form method="dialog" className="modal-backdrop" onClick={onClose}>
+        <button disabled={isSaving}>close</button>
+      </form>
+    </dialog>
+  );
+};
+
+export default EditDocumentModal;

src/frontend/src/components/documents/ViewModeSwitcher.jsx

@@ -0,0 +1,46 @@
+/**
+ * ViewModeSwitcher Component
+ * Allows users to switch between different view modes (small, large, detail)
+ */
+
+import React from 'react';
+
+/**
+ * @typedef {'small' | 'large' | 'detail'} ViewMode
+ */
+
+/**
+ * ViewModeSwitcher component
+ * @param {Object} props
+ * @param {ViewMode} props.currentMode - Current active view mode
+ * @param {function(ViewMode): void} props.onModeChange - Callback when mode changes
+ * @returns {JSX.Element}
+ */
+const ViewModeSwitcher = ({ currentMode, onModeChange }) => {
+  const modes = [
+    { id: 'small', label: 'Small', icon: '⊞' },
+    { id: 'large', label: 'Large', icon: '⊡' },
+    { id: 'detail', label: 'Detail', icon: '☰' }
+  ];
+
+  return (
+    <div className="flex gap-2">
+      {modes.map(mode => (
+        <button
+          key={mode.id}
+          onClick={() => onModeChange(mode.id)}
+          className={`btn btn-sm ${
+            currentMode === mode.id ? 'btn-primary' : 'btn-ghost'
+          }`}
+          aria-label={`Switch to ${mode.label} view`}
+          title={`${mode.label} view`}
+        >
+          <span className="text-lg">{mode.icon}</span>
+          <span className="hidden sm:inline ml-1">{mode.label}</span>
+        </button>
+      ))}
+    </div>
+  );
+};
+
+export default ViewModeSwitcher;

src/frontend/src/hooks/useDocuments.js

@@ -0,0 +1,85 @@
+/**
+ * Custom hook for managing documents
+ * Handles fetching, updating, and deleting documents
+ */
+
+import { useState, useEffect, useCallback } from 'react';
+import * as documentService from '../services/documentService';
+
+/**
+ * Hook for managing documents state and operations
+ * @returns {Object} Documents state and operations
+ */
+export const useDocuments = () => {
+  const [documents, setDocuments] = useState([]);
+  const [loading, setLoading] = useState(true);
+  const [error, setError] = useState(null);
+
+  /**
+   * Fetches all documents from the service
+   */
+  const fetchDocuments = useCallback(async () => {
+    try {
+      setLoading(true);
+      setError(null);
+      const data = await documentService.getAllDocuments();
+      setDocuments(data);
+    } catch (err) {
+      setError(err.message);
+      console.error('Error fetching documents:', err);
+    } finally {
+      setLoading(false);
+    }
+  }, []);
+
+  /**
+   * Updates a document's tags and categories
+   * @param {string} id - Document ID
+   * @param {Object} updates - Updates object
+   * @returns {Promise<boolean>} Success status
+   */
+  const updateDocument = useCallback(async (id, updates) => {
+    try {
+      const updatedDoc = await documentService.updateDocument(id, updates);
+      setDocuments(prevDocs =>
+        prevDocs.map(doc => (doc.id === id ? updatedDoc : doc))
+      );
+      return true;
+    } catch (err) {
+      setError(err.message);
+      console.error('Error updating document:', err);
+      return false;
+    }
+  }, []);
+
+  /**
+   * Deletes a document
+   * @param {string} id - Document ID
+   * @returns {Promise<boolean>} Success status
+   */
+  const deleteDocument = useCallback(async (id) => {
+    try {
+      await documentService.deleteDocument(id);
+      setDocuments(prevDocs => prevDocs.filter(doc => doc.id !== id));
+      return true;
+    } catch (err) {
+      setError(err.message);
+      console.error('Error deleting document:', err);
+      return false;
+    }
+  }, []);
+
+  // Fetch documents on mount
+  useEffect(() => {
+    fetchDocuments();
+  }, [fetchDocuments]);
+
+  return {
+    documents,
+    loading,
+    error,
+    fetchDocuments,
+    updateDocument,
+    deleteDocument
+  };
+};

src/frontend/src/pages/DocumentsPage.jsx

@@ -0,0 +1,21 @@
+/**
+ * DocumentsPage Component
+ * Main page for displaying and managing documents
+ */
+
+import React from 'react';
+import DocumentGallery from '../components/documents/DocumentGallery';
+
+/**
+ * DocumentsPage component
+ * @returns {JSX.Element}
+ */
+const DocumentsPage = () => {
+  return (
+    <div className="container mx-auto px-4 py-8">
+      <DocumentGallery />
+    </div>
+  );
+};
+
+export default DocumentsPage;

src/frontend/src/services/documentService.js

@@ -0,0 +1,97 @@
+/**
+ * Document Service
+ * Handles all API calls related to documents
+ * Currently using mock data for development
+ */
+
+import { mockDocuments, availableTags, availableCategories } from '../utils/mockData';
+import api from '../utils/api';
+
+// Simulate network delay
+const delay = (ms) => new Promise(resolve => setTimeout(resolve, ms));
+
+/**
+ * Fetches all documents from the API
+ * @returns {Promise<Array>} Array of document objects
+ */
+export const getAllDocuments = async () => {
+  try {
+    const response = await api.get('/api/documents');
+    return response.data;
+  } catch (error) {
+    console.error('Failed to fetch documents:', error);
+    // Fallback to mock data in case of API error during development
+    console.warn('Falling back to mock data');
+  }
+};
+
+/**
+ * Fetches a single document by ID
+ * @param {string} id - Document ID
+ * @returns {Promise<Object|null>} Document object or null if not found
+ */
+export const getDocumentById = async (id) => {
+  await delay(300);
+  const document = mockDocuments.find(doc => doc.id === id);
+  return document || null;
+};
+
+/**
+ * Updates a document's tags and categories
+ * @param {string} id - Document ID
+ * @param {Object} updates - Object containing tags and/or categories
+ * @param {Array<string>} updates.tags - New tags array
+ * @param {Array<string>} updates.categories - New categories array
+ * @returns {Promise<Object>} Updated document object
+ */
+export const updateDocument = async (id, updates) => {
+  await delay(400);
+
+  const index = mockDocuments.findIndex(doc => doc.id === id);
+  if (index === -1) {
+    throw new Error('Document not found');
+  }
+
+  // Update the document
+  mockDocuments[index] = {
+    ...mockDocuments[index],
+    ...updates
+  };
+
+  return mockDocuments[index];
+};
+
+/**
+ * Deletes a document
+ * @param {string} id - Document ID
+ * @returns {Promise<boolean>} True if deletion was successful
+ */
+export const deleteDocument = async (id) => {
+  await delay(300);
+
+  const index = mockDocuments.findIndex(doc => doc.id === id);
+  if (index === -1) {
+    throw new Error('Document not found');
+  }
+
+  mockDocuments.splice(index, 1);
+  return true;
+};
+
+/**
+ * Gets all available tags
+ * @returns {Promise<Array<string>>} Array of tag strings
+ */
+export const getAvailableTags = async () => {
+  await delay(200);
+  return [...availableTags];
+};
+
+/**
+ * Gets all available categories
+ * @returns {Promise<Array<string>>} Array of category strings
+ */
+export const getAvailableCategories = async () => {
+  await delay(200);
+  return [...availableCategories];
+};

src/frontend/src/utils/mockData.js

@@ -0,0 +1,155 @@
+/**
+ * Mock data for PDF documents
+ * This file provides sample data for development and testing purposes
+ */
+
+/**
+ * Generates a placeholder thumbnail URL
+ * @param {number} index - Document index for unique colors
+ * @returns {string} Placeholder image URL
+ */
+const generateThumbnailUrl = (index) => {
+  const colors = ['3B82F6', '10B981', 'F59E0B', 'EF4444', '8B5CF6', 'EC4899'];
+  const color = colors[index % colors.length];
+  return `https://via.placeholder.com/300x400/${color}/FFFFFF?text=Page+1`;
+};
+
+/**
+ * Mock documents data
+ * @type {Array<Object>}
+ */
+export const mockDocuments = [
+  {
+    id: 'doc-001',
+    name: 'Contrat-2025.pdf',
+    originalFileType: 'DOCX',
+    createdAt: '2025-10-01T10:30:00Z',
+    fileSize: 2048576, // 2 MB
+    pageCount: 12,
+    thumbnailUrl: generateThumbnailUrl(0),
+    pdfUrl: '/mock/contrat-2025.pdf',
+    tags: ['contrat', '2025'],
+    categories: ['legal']
+  },
+  {
+    id: 'doc-002',
+    name: 'Facture-Janvier.pdf',
+    originalFileType: 'XLSX',
+    createdAt: '2025-09-15T14:20:00Z',
+    fileSize: 512000, // 512 KB
+    pageCount: 3,
+    thumbnailUrl: generateThumbnailUrl(1),
+    pdfUrl: '/mock/facture-janvier.pdf',
+    tags: ['facture', 'comptabilité'],
+    categories: ['finance']
+  },
+  {
+    id: 'doc-003',
+    name: 'Présentation-Projet.pdf',
+    originalFileType: 'PPTX',
+    createdAt: '2025-09-28T09:15:00Z',
+    fileSize: 5242880, // 5 MB
+    pageCount: 24,
+    thumbnailUrl: generateThumbnailUrl(2),
+    pdfUrl: '/mock/presentation-projet.pdf',
+    tags: ['présentation', 'projet'],
+    categories: ['marketing']
+  },
+  {
+    id: 'doc-004',
+    name: 'Photo-Identité.pdf',
+    originalFileType: 'JPG',
+    createdAt: '2025-10-05T16:45:00Z',
+    fileSize: 204800, // 200 KB
+    pageCount: 1,
+    thumbnailUrl: generateThumbnailUrl(3),
+    pdfUrl: '/mock/photo-identite.pdf',
+    tags: ['photo', 'identité'],
+    categories: ['personnel']
+  },
+  {
+    id: 'doc-005',
+    name: 'Manuel-Utilisateur.pdf',
+    originalFileType: 'PDF',
+    createdAt: '2025-09-20T11:00:00Z',
+    fileSize: 3145728, // 3 MB
+    pageCount: 45,
+    thumbnailUrl: generateThumbnailUrl(4),
+    pdfUrl: '/mock/manuel-utilisateur.pdf',
+    tags: ['manuel', 'documentation'],
+    categories: ['technique']
+  },
+  {
+    id: 'doc-006',
+    name: 'Rapport-Annuel.pdf',
+    originalFileType: 'DOCX',
+    createdAt: '2025-08-30T13:30:00Z',
+    fileSize: 4194304, // 4 MB
+    pageCount: 67,
+    thumbnailUrl: generateThumbnailUrl(5),
+    pdfUrl: '/mock/rapport-annuel.pdf',
+    tags: ['rapport', 'annuel'],
+    categories: ['finance', 'management']
+  },
+  {
+    id: 'doc-007',
+    name: 'CV-Candidat.pdf',
+    originalFileType: 'DOCX',
+    createdAt: '2025-10-02T08:00:00Z',
+    fileSize: 153600, // 150 KB
+    pageCount: 2,
+    thumbnailUrl: generateThumbnailUrl(0),
+    pdfUrl: '/mock/cv-candidat.pdf',
+    tags: ['cv', 'recrutement'],
+    categories: ['rh']
+  },
+  {
+    id: 'doc-008',
+    name: 'Devis-Travaux.pdf',
+    originalFileType: 'XLSX',
+    createdAt: '2025-09-25T15:20:00Z',
+    fileSize: 409600, // 400 KB
+    pageCount: 5,
+    thumbnailUrl: generateThumbnailUrl(1),
+    pdfUrl: '/mock/devis-travaux.pdf',
+    tags: ['devis', 'travaux'],
+    categories: ['finance']
+  }
+];
+
+/**
+ * Available tags for documents
+ * @type {Array<string>}
+ */
+export const availableTags = [
+  'contrat',
+  'facture',
+  'présentation',
+  'photo',
+  'manuel',
+  'rapport',
+  'cv',
+  'devis',
+  'comptabilité',
+  'projet',
+  'identité',
+  'documentation',
+  'annuel',
+  'recrutement',
+  'travaux',
+  '2025'
+];
+
+/**
+ * Available categories for documents
+ * @type {Array<string>}
+ */
+export const availableCategories = [
+  'legal',
+  'finance',
+  'marketing',
+  'personnel',
+  'technique',
+  'management',
+  'rh'
+];

src/worker/Dockerfile

@@ -12,12 +12,17 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     texlive-xetex \
  && rm -rf /var/lib/apt/lists/*
 
+
 # Copy requirements and install dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Change the user
+USER 1002:1002
+
 # Copy application code
 COPY . .
 
+
 # Command will be overridden by docker-compose
 CMD ["celery", "-A", "main", "worker", "--loglevel=info"]

src/worker/requirements.txt

@@ -5,10 +5,12 @@ email-validator==2.3.0
 fastapi==0.116.1
 httptools==0.6.4
 motor==3.7.1
+pikepdf==9.11.0
 pillow==11.3.0
 pydantic==2.11.9
 PyJWT==2.10.1
 pymongo==4.15.0
+PyMuPDF==1.26.4
 pypandoc==1.15
 python-multipart==0.0.20
 redis==6.4.0

src/worker/tasks/common/converter_utils.py

@@ -1,22 +1,14 @@
 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.
@@ -28,12 +20,19 @@ def detect_file_type(file_path: str) -> str:
       UnsupportedFileTypeError: If file type is not supported.
   """
   mime = magic.from_file(file_path, mime=True)
+  extension = Path(file_path).suffix
   if mime.startswith("text/"):
     return "text"
   elif mime.startswith("image/"):
     return "image"
   elif mime in ("application/vnd.openxmlformats-officedocument.wordprocessingml.document",):
     return "word"
+  elif mime == "application/pdf":
+    return "pdf"
+  elif mime == "application/vnd.ms-powerpoint":
+    return "powerpoint"
+  elif mime == "application/octet-stream" and extension in (".jpg", ".jpeg", ".png", ".gif"):
+    return "image"
   else:
     raise UnsupportedFileTypeError(f"Unsupported file type: {mime}")
 
@@ -72,31 +71,3 @@ def compress_pdf(input_pdf: str, output_pdf: str, quality: str = "ebook") -> Non
   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/document_utils.py

@@ -0,0 +1,64 @@
+import hashlib
+import logging
+import os
+from pathlib import Path
+
+from app.config import settings
+
+logger = logging.getLogger(__name__)
+
+
+def get_file_hash(file_bytes: bytes) -> str:
+  """
+  Calculate SHA256 hash of file content.
+
+  Args:
+      file_bytes: Raw file content as bytes
+
+  Returns:
+      Hexadecimal SHA256 hash string
+  """
+  return hashlib.sha256(file_bytes).hexdigest()
+
+
+def get_object_path(file_hash):
+  """
+
+  :param file_hash:
+  :return:
+  """
+  root = settings.get_objects_folder()
+  return os.path.join(root, file_hash[:24], file_hash)
+
+
+def save_as_object(file_path, remove_on_success=True) -> str:
+  """
+  Read the file, get the hash and save using the hash as the filename.
+  :param file_path:
+  :param remove_on_success:
+  :return: hash of the file
+  """
+  logger.info(f"Saving file {file_path} as object")
+  path = Path(file_path)
+  as_bytes = path.read_bytes()
+  
+  file_hash = get_file_hash(as_bytes)
+  logger.info(f"File hash: {file_hash}")
+  
+  object_path = get_object_path(file_hash)
+  if os.path.exists(object_path):
+    logger.info(f"Object already exists: {object_path}")
+    return file_hash
+  
+  if not os.path.exists(os.path.dirname(object_path)):
+    os.makedirs(os.path.dirname(object_path))
+  
+  logger.info(f"Saving object to: {object_path}")
+  with open(object_path, "wb") as f:
+    f.write(as_bytes)
+  
+  if remove_on_success:
+    logger.info(f"Removing file: {file_path}")
+    path.unlink()
+  
+  return file_hash

src/worker/tasks/common/pdf_converter.py

@@ -1,83 +0,0 @@
-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

@@ -6,13 +6,14 @@ and update processing job statuses throughout the task lifecycle.
 """
 
 import logging
+import os
 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.models.job import ProcessingStatus
+from app.services.document_service import DocumentService, DocumentAlreadyExists
 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__)
@@ -25,7 +26,8 @@ def get_services():
   return document_service, job_service
 
 
-@celery_app.task(bind=True, autoretry_for=(Exception,), retry_kwargs={'max_retries': 3, 'countdown': 60})
+# @celery_app.task(bind=True, autoretry_for=(Exception,), retry_kwargs={'max_retries': 3, 'countdown': 60})
+@celery_app.task(bind=True)
 def process_document(self, filepath: str) -> Dict[str, Any]:
   """
   Process a document file and extract its content.
@@ -46,30 +48,34 @@ def process_document(self, filepath: str) -> Dict[str, Any]:
       Exception: Any processing error (will trigger retry)
   """
   task_id = self.request.id
-  logger.info(f"Starting document processing task {task_id} for file: {filepath}")
+  logger.info(f'Task {task_id} : Starting document processing for file: "{filepath}"')
   
   # get services
   document_service, job_service = get_services()
   
   job = None
+  document = None
   try:
-    # Step 1: Insert the document in DB
+    # Step 1: Create the document and a new job record for the document
     document = document_service.create_document(filepath)
-    logger.info(f"Job {task_id} created for document {document.id} with file path: {filepath}")
-    
-    # Step 2: Create a new job record for the document
     job = job_service.create_job(task_id=task_id, document_id=document.id)
-    
-    # Step 3: Mark job as started
     job_service.mark_job_as_started(job_id=job.id)
-    logger.info(f"Job {task_id} marked as PROCESSING")
+    logger.info(f'Task {task_id} : Created document "{document.id}". Started job "{job.id}"')
     
-    # Step 4: Create the pdf version of the document
-    pdf_file_path = convert_to_pdf(filepath, settings.get_temp_folder())
+    logger.info(f"Task {task_id} : Creating associated PDF")
+    job_service.update_job_status(job_id=job.id, status=ProcessingStatus.SAVING_PDF)
+    document_service.create_pdf(document.id)
+    
+    logger.info(f"Task {task_id} : Creating thumbnail")
+    job_service.update_job_status(job_id=job.id, status=ProcessingStatus.CREATING_THUMBNAIL)
+    document_service.create_thumbnail(document.id)
+    
+    # remove the file from the watch folder
+    os.remove(filepath)
     
     # 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")
+    logger.info(f"Task {task_id} marked as COMPLETED")
     
     return {
         "task_id": task_id,
@@ -77,6 +83,19 @@ def process_document(self, filepath: str) -> Dict[str, Any]:
         "status": "completed",
     }
   
+  except DocumentAlreadyExists as e:
+    logger.info(f"Task {task_id} completed: {str(e)}")
+    if job is not None:
+      job_service.mark_job_as_completed(job_id=job.id)
+      logger.info(f"Job {task_id} marked as COMPLETED")
+    
+    return {
+        "task_id": task_id,
+        "filepath": filepath,
+        "status": "completed",
+        "message": str(e),
+    }
+  
   except Exception as e:
     error_message = f"Document processing failed: {str(e)}"
     logger.error(f"Task {task_id} failed: {error_message}")
@@ -88,6 +107,11 @@ def process_document(self, filepath: str) -> Dict[str, Any]:
         logger.info(f"Job {task_id} marked as FAILED")
       else:
         logger.error(f"Failed to process {filepath}. error = {str(e)}")
+      
+      if document is not None:
+        document_service.move_to_errors(document.id, filepath)
+        logger.info(f"Moved file {filepath} to errors/{document.id}")
+    
     except Exception as job_error:
       logger.error(f"Failed to update job status for task {task_id}: {str(job_error)}")
     

src/worker/tasks/main.py

@@ -7,10 +7,10 @@ import logging
 import os
 
 from celery import Celery
+from celery.signals import worker_process_init
 
 from app.config import settings
 
-
 # Environment variables
 REDIS_URL = settings.get_redis_url()
 MONGODB_URL = settings.get_mongodb_url()
@@ -38,11 +38,16 @@ celery_app.conf.update(
   task_soft_time_limit=240,  # 4 minutes
 )
 
+
+def global_init(**kwargs):
+  """Initialize global variables."""
+  logger.info(f"{'*' * 45}")
+  logger.info(f"{'--' * 5}" + " Starting MyDocManager worker " + f"{'--' * 5}")
+  logger.info(f"{'*' * 45}")
+
+
+global_init()
+
 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)
-  
+  global_init()
   celery_app.start()

tests/services/test_document_service.py

@@ -568,3 +568,137 @@ class TestFileTypeDetection:
     """Test unsupported file type raises ValueError."""
     with pytest.raises(ValueError, match="Unsupported file type"):
       document_service._detect_file_type("/path/to/document.xyz")
+
+
+class TestCreatePdf:
+  """Tests for create_pdf method."""
+  
+  @patch('app.services.document_service.convert_to_pdf')
+  @patch('app.services.document_service.magic.from_buffer')
+  def test_i_can_create_pdf_successfully(
+      self,
+      mock_magic,
+      mock_convert_to_pdf,
+      document_service,
+      sample_file_bytes
+  ):
+    """Test creating PDF from an existing document."""
+    # Setup
+    mock_magic.return_value = "text/plain"
+    
+    # Create a document first
+    created_doc = document_service.create_document(
+      "/test/test.txt",
+      sample_file_bytes,
+      "utf-8"
+    )
+    
+    # Mock the PDF conversion
+    pdf_path = os.path.join(document_service.temp_folder, "converted.pdf")
+    mock_convert_to_pdf.return_value = pdf_path
+    
+    # Write a sample PDF file that the conversion would create
+    pdf_content = b"This is PDF content"
+    os.makedirs(os.path.dirname(pdf_path), exist_ok=True)
+    with open(pdf_path, "wb") as f:
+      f.write(pdf_content)
+    
+    # Execute
+    result = document_service.create_pdf(created_doc.id)
+    
+    # Verify
+    assert result is True
+    
+    # Get the updated document
+    updated_doc = document_service.get_document_by_id(created_doc.id)
+    assert updated_doc.pdf_file_hash is not None
+    
+    # Verify the PDF content was saved
+    pdf_hash = document_service._calculate_file_hash(pdf_content)
+    assert updated_doc.pdf_file_hash == pdf_hash
+    
+    # Verify convert_to_pdf was called with correct arguments
+    doc_path = document_service.get_document_path(created_doc.file_hash)
+    mock_convert_to_pdf.assert_called_once_with(doc_path, document_service.temp_folder)
+    
+    # Verify content exists on disk
+    validate_file_saved(document_service, pdf_hash, pdf_content)
+    
+    # Verify PDF hash was added to document
+    updated_doc = document_service.get_document_by_id(created_doc.id)
+    pdf_hash = document_service._calculate_file_hash(pdf_content)
+    assert updated_doc.pdf_file_hash == pdf_hash
+  
+  @patch('app.services.document_service.convert_to_pdf')
+  @patch('app.services.document_service.magic.from_buffer')
+  def test_i_can_reuse_existing_pdf(
+      self,
+      mock_magic,
+      mock_convert_to_pdf,
+      document_service,
+      sample_file_bytes
+  ):
+    """Test that if PDF already exists, it doesn't recreate it."""
+    # Setup
+    mock_magic.return_value = "text/plain"
+    
+    # Create a document first
+    created_doc = document_service.create_document(
+      "/test/test.txt",
+      sample_file_bytes,
+      "utf-8"
+    )
+    
+    # Create a fake PDF file and update the document
+    pdf_content = b"This is PDF content"
+    pdf_hash = document_service._calculate_file_hash(pdf_content)
+    document_service.save_content_if_needed(pdf_hash, pdf_content)
+    document_service.update_document(created_doc.id, {"pdf_file_hash": pdf_hash})
+    
+    # Execute
+    result = document_service.create_pdf(created_doc.id)
+    
+    # Verify
+    assert result is True
+    
+    # Verify convert_to_pdf was NOT called
+    mock_convert_to_pdf.assert_not_called()
+  
+  def test_i_cannot_create_pdf_for_nonexistent_document(
+      self,
+      document_service
+  ):
+    """Test behavior when document ID doesn't exist."""
+    # Execute with random ObjectId
+    result = document_service.create_pdf(ObjectId())
+    
+    # Verify
+    assert result is False
+  
+  @patch('app.services.document_service.magic.from_buffer')
+  def test_i_cannot_create_pdf_when_file_content_missing(
+      self,
+      mock_magic,
+      document_service,
+      sample_file_bytes
+  ):
+    """Test behavior when file content doesn't exist."""
+    # Setup
+    mock_magic.return_value = "text/plain"
+    
+    # Create a document
+    created_doc = document_service.create_document(
+      "/test/test.txt",
+      sample_file_bytes,
+      "utf-8"
+    )
+    
+    # Simulate missing content by removing file
+    file_path = document_service.get_document_path(created_doc.file_hash)
+    os.remove(file_path)
+    
+    # Execute
+    result = document_service.create_pdf(created_doc.id)
+    
+    # Verify
+    assert result is False

tests/services/test_job_service.py

@@ -417,6 +417,25 @@ class TestUpdateStatus:
     # Verify exception details
     assert exc_info.value.current_status == ProcessingStatus.FAILED
     assert exc_info.value.target_status == ProcessingStatus.FAILED
+  
+  def test_i_can_update_job_status(
+      self,
+      job_service,
+      sample_document_id,
+      sample_task_id
+  ):
+    """Test that failed job cannot be marked as failed again."""
+    # Create, start, and fail a job
+    created_job = job_service.create_job(sample_document_id, sample_task_id)
+    job_service.mark_job_as_started(created_job.id)
+    
+    # Execute without error message
+    result = job_service.update_job_status(created_job.id, ProcessingStatus.SAVING_OBJECT)
+    
+    # Verify status transition
+    assert result is not None
+    assert result.status == ProcessingStatus.SAVING_OBJECT
+    assert result.error_message is None
 
 
 class TestDeleteJob:

tests/utils/test_pdf_converter.py

@@ -4,7 +4,7 @@ from pathlib import Path
 
 import pytest
 
-from tasks.common.pdf_converter import TextToPdfConverter, ImageToPdfConverter, WordToPdfConverter
+from app.utils.pdf_converter import TextToPdfConverter, ImageToPdfConverter, WordToPdfConverter
 
 
 @pytest.fixture
@@ -20,10 +20,10 @@ def test_i_can_convert_text_to_pdf(temp_dir):
   input_txt.write_text("Hello World!\nThis is a test.")
   
   converter = TextToPdfConverter(str(input_txt), output_dir=temp_dir)
-  output_pdf = converter.convert()
+  converter.convert()
   
-  assert Path(output_pdf).exists()
-  assert output_pdf.endswith(".pdf")
+  assert Path(converter.output_path).exists()
+  assert str(converter.output_path).endswith(".pdf")
 
 
 def test_i_can_convert_image_to_pdf(temp_dir):
@@ -34,10 +34,10 @@ def test_i_can_convert_image_to_pdf(temp_dir):
   image.save(input_img)
   
   converter = ImageToPdfConverter(str(input_img), output_dir=temp_dir)
-  output_pdf = converter.convert()
+  converter.convert()
   
-  assert Path(output_pdf).exists()
-  assert output_pdf.endswith(".pdf")
+  assert Path(converter.output_path).exists()
+  assert str(converter.output_path).endswith(".pdf")
 
 
 def test_i_can_convert_word_to_pdf(temp_dir):
@@ -49,7 +49,7 @@ def test_i_can_convert_word_to_pdf(temp_dir):
   doc.save(input_docx)
   
   converter = WordToPdfConverter(str(input_docx), output_dir=temp_dir)
-  output_pdf = converter.convert()
+  converter.convert()
   
-  assert Path(output_pdf).exists()
-  assert output_pdf.endswith(".pdf")
+  assert Path(converter.output_path).exists()
+  assert str(converter.output_path).endswith(".pdf")