kodjo/MyDocManager
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implemented default pipeline

Browse Source
This commit is contained in:
Kodjo Sossouvi
2025-09-26 22:08:39 +02:00
parent f1b551d243
commit 4de732b0ae
56 changed files with 4534 additions and 2837 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -1,3 +1,5 @@
volumes
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[codz]

356
Readme.md
View File

@@ -13,7 +13,7 @@ architecture with Redis for task queuing and MongoDB for data persistence.
- **Backend API**: FastAPI (Python 3.12)
- **Task Processing**: Celery with Redis broker
- **Document Processing**: EasyOCR, PyMuPDF, python-docx, pdfplumber
- **Database**: MongoDB
- **Database**: MongoDB (pymongo)
- **Frontend**: React
- **Containerization**: Docker & Docker Compose
- **File Monitoring**: Python watchdog library
@@ -95,25 +95,32 @@ MyDocManager/
│ │ ├── requirements.txt
│ │ ├── app/
│ │ │ ├── main.py
│ │ │ ├── file_watcher.py
│ │ │ ├── celery_app.py
│ │ │ ├── file_watcher.py # FileWatcher class with observer thread
│ │ │ ├── celery_app.py # Celery Configuration
│ │ │ ├── config/
│ │ │ │ ├── __init__.py
│ │ │ │ └── settings.py # JWT, MongoDB config
│ │ │ ├── models/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── user.py # User Pydantic models
│ │ │ │ └── auth.py # Auth Pydantic models
│ │ │ │ ├── auth.py # Auth Pydantic models
│ │ │ │ ├── document.py # Document Pydantic models
│ │ │ │ ├── job.py # Job Processing Pydantic models
│ │ │ │ └── types.py # PyObjectId and other useful types
│ │ │ ├── database/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── connection.py # MongoDB connection
│ │ │ │ ├── connection.py # MongoDB connection (pymongo)
│ │ │ │ └── repositories/
│ │ │ │ ├── __init__.py
│ │ │ │ └── user_repository.py # User CRUD operations
│ │ │ │ ├── user_repository.py # User CRUD operations (synchronous)
│ │ │ │ ├── document_repository.py # Document CRUD operations (synchronous)
│ │ │ │ └── job_repository.py # Job CRUD operations (synchronous)
│ │ │ ├── services/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── auth_service.py # JWT & password logic
│ │ │ │ ├── user_service.py # User business logic
│ │ │ │ ├── auth_service.py # JWT & password logic (synchronous)
│ │ │ │ ├── user_service.py # User business logic (synchronous)
│ │ │ │ ├── document_service.py # Document business logic (synchronous)
│ │ │ │ ├── job_service.py # Job processing logic (synchronous)
│ │ │ │ └── init_service.py # Admin creation at startup
│ │ │ ├── api/
│ │ │ │ ├── __init__.py
@@ -125,7 +132,7 @@ MyDocManager/
│ │ │ └── utils/
│ │ │ ├── __init__.py
│ │ │ ├── security.py # Password utilities
│ │ │ └── exceptions.py # Custom exceptions
│ │ │ └── document_matching.py # Fuzzy matching Algorithms
│ ├── worker/
│ │ ├── Dockerfile
│ │ ├── requirements.txt
@@ -133,7 +140,13 @@ MyDocManager/
│ └── frontend/
│ ├── Dockerfile
│ ├── package.json
│ ├── index.html
│ └── src/
│ ├── assets/
│ ├── App.css
│ ├── App.jsx
│ ├── main.css
│ └── main.jsx
├── tests/
│ ├── file-processor/
│ │ ├── test_auth/
@@ -224,78 +237,76 @@ On first startup, the application automatically creates a default admin user:
#### Files Collection
Stores file metadata and extracted content:
Stores file metadata and extracted content using Pydantic models:
```json
{
"_id": "ObjectId",
"filename": "document.pdf",
"filepath": "/watched_files/document.pdf",
"file_type": "pdf",
"extraction_method": "direct_text", // direct_text, ocr, hybrid
"metadata": {
"page_count": 15, // for PDFs
"word_count": 250, // for text files
"image_dimensions": { // for images
"width": 1920,
"height": 1080
}
},
"detected_at": "2024-01-15T10:29:00Z",
"file_hash": "sha256_hash_value"
}
```
#### Document Contents Collection
```python
class FileDocument(BaseModel):
"""
Model for file documents stored in the 'files' collection.
Stores actual file content and technical metadata:
```json
{
"_id": "ObjectId",
"file_hash": "sha256_hash_value",
"content": "extracted text content...",
"encoding": "utf-8",
"file_size": 2048576,
"mime_type": "application/pdf"
}
Represents a file detected in the watched directory with its
metadata and extracted content.
"""
id: Optional[PyObjectId] = Field(default=None, alias="_id")
filename: str = Field(..., description="Original filename")
filepath: str = Field(..., description="Full path to the file")
file_type: FileType = Field(..., description="Type of the file")
extraction_method: Optional[ExtractionMethod] = Field(default=None, description="Method used to extract content")
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")
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")
@field_validator('filepath')
@classmethod
def validate_filepath(cls, v: str) -> str:
"""Validate filepath format."""
if not v.strip():
raise ValueError("Filepath cannot be empty")
return v.strip()
@field_validator('filename')
@classmethod
def validate_filename(cls, v: str) -> str:
"""Validate filename format."""
if not v.strip():
raise ValueError("Filename cannot be empty")
return v.strip()
```
#### Processing Jobs Collection
Tracks processing status and lifecycle:
```json
{
"_id": "ObjectId",
"file_id": "reference_to_files_collection",
"status": "completed",
// pending, processing, completed, failed
"task_id": "celery_task_uuid",
"created_at": "2024-01-15T10:29:00Z",
"started_at": "2024-01-15T10:29:30Z",
"completed_at": "2024-01-15T10:30:00Z",
"error_message": null
}
```python
class ProcessingJob(BaseModel):
"""
Model for processing jobs stored in the 'processing_jobs' collection.
Tracks the lifecycle and status of document processing tasks.
"""
id: Optional[PyObjectId] = Field(default=None, alias="_id")
file_id: PyObjectId = Field(..., description="Reference to file document")
status: ProcessingStatus = Field(default=ProcessingStatus.PENDING, description="Current processing status")
task_id: Optional[str] = Field(default=None, description="Celery task UUID")
created_at: Optional[datetime] = Field(default=None, description="Timestamp when job was created")
started_at: Optional[datetime] = Field(default=None, description="Timestamp when processing started")
completed_at: Optional[datetime] = Field(default=None, description="Timestamp when processing completed")
error_message: Optional[str] = Field(default=None, description="Error message if processing failed")
@field_validator('error_message')
@classmethod
def validate_error_message(cls, v: Optional[str]) -> Optional[str]:
"""Clean up error message."""
if v is not None:
return v.strip() if v.strip() else None
return v
```
### Data Storage Strategy
- **Choice**: Three separate collections for files, content, and processing status
- **Rationale**: Normalization prevents content duplication when multiple files have identical content
- **Benefits**:
- Content deduplication via SHA256 hash
- Better query performance for metadata vs content searches
- Clear separation of concerns between file metadata, content, and processing lifecycle
- Multiple files can reference the same content (e.g., identical copies in different locations)
### Content Storage Location
- **Choice**: Store extracted content in separate `document_contents` collection
- **Rationale**: Content normalization and deduplication
- **Benefits**:
- Single content storage per unique file hash
- Multiple file entries can reference same content
- Efficient storage for duplicate files
### Supported File Types (Initial Implementation)
- **Text Files** (`.txt`): Direct content reading
@@ -306,7 +317,7 @@ Tracks processing status and lifecycle:
#### Watchdog Implementation
- **Choice**: Dedicated observer thread (Option A)
- **Choice**: Dedicated observer thread
- **Rationale**: Standard approach, clean separation of concerns
- **Implementation**: Watchdog observer runs in separate thread from FastAPI
@@ -327,17 +338,94 @@ Tracks processing status and lifecycle:
#### Content Storage Location
- **Choice**: Store extracted content in `files` collection
- **Rationale**: Content is intrinsic property of the file
- **Benefits**: Single query to get file + content, simpler data model
- **Choice**: Store files in the file system, using the SHA256 hash as filename
- **Rationale**: MongoDB is not meant for large files, better performance. Files remain in the file system for easy
access.
### Implementation Order
#### Repository and Services Implementation
- **Choice**: Synchronous implementation using pymongo
- **Rationale**: Full compatibility with Celery workers and simplified workflow
- **Implementation**: All repositories and services operate synchronously for seamless integration
### Implementation Status
1. ✅ Pydantic models for MongoDB collections
2. ✅ Repository layer for data access (files + processing_jobs)
3. ✅ Celery tasks for document processing
4. ✅ Watchdog file monitoring implementation
5. ✅ FastAPI integration and startup coordination
2. ✅ Repository layer for data access (files + processing_jobs + users + documents) - synchronous
3. ✅ Service layer for business logic (auth, user, document, job) - synchronous
4. ✅ Celery tasks for document processing
5. ✅ Watchdog file monitoring implementation
6. ✅ FastAPI integration and startup coordination
## Job Management Layer
### Repository Pattern Implementation
The job management system follows the repository pattern for clean separation between data access and business logic.
#### JobRepository
Handles direct MongoDB operations for processing jobs using synchronous pymongo:
**CRUD Operations:**
- `create_job()` - Create new processing job with automatic `created_at` timestamp
- `get_job_by_id()` - Retrieve job by ObjectId
- `update_job_status()` - Update job status with automatic timestamp management
- `delete_job()` - Remove job from database
- `get_jobs_by_file_id()` - Get all jobs for specific file
- `get_jobs_by_status()` - Get jobs filtered by processing status
**Automatic Timestamp Management:**
- `created_at`: Set automatically during job creation
- `started_at`: Set automatically when status changes to PROCESSING
- `completed_at`: Set automatically when status changes to COMPLETED or FAILED
#### JobService
Provides synchronous business logic layer with strict status transition validation:
**Status Transition Methods:**
- `mark_job_as_started()` - PENDING → PROCESSING
- `mark_job_as_completed()` - PROCESSING → COMPLETED
- `mark_job_as_failed()` - PROCESSING → FAILED
**Validation Rules:**
- Strict status transitions (invalid transitions raise exceptions)
- Job existence verification before any operation
- Automatic timestamp management through repository layer
#### Custom Exceptions
**InvalidStatusTransitionError**: Raised for invalid status transitions
**JobRepositoryError**: Raised for MongoDB operation failures
#### Valid Status Transitions
```
PENDING → PROCESSING (via mark_job_as_started)
PROCESSING → COMPLETED (via mark_job_as_completed)
PROCESSING → FAILED (via mark_job_as_failed)
```
All other transitions are forbidden and will raise `InvalidStatusTransitionError`.
### File Structure
```
src/file-processor/app/
├── database/repositories/
│ ├── job_repository.py # JobRepository class (synchronous)
│ ├── user_repository.py # UserRepository class (synchronous)
│ ├── document_repository.py # DocumentRepository class (synchronous)
│ └── file_repository.py # FileRepository class (synchronous)
├── services/
│ ├── job_service.py # JobService class (synchronous)
│ ├── auth_service.py # AuthService class (synchronous)
│ ├── user_service.py # UserService class (synchronous)
│ └── document_service.py # DocumentService class (synchronous)
└── exceptions/
└── job_exceptions.py # Custom exceptions
```
### Processing Pipeline Features
@@ -346,87 +434,7 @@ Tracks processing status and lifecycle:
- **Status Tracking**: Real-time processing status via `processing_jobs` collection
- **Extensible Metadata**: Flexible metadata storage per file type
- **Multiple Extraction Methods**: Support for direct text, OCR, and hybrid approaches
## Document Service Architecture
### Service Overview
The document service provides orchestrated access to file documents and their content through a single interface that coordinates between `FileDocument` and `DocumentContent` repositories.
### Service Design
- **Architecture Pattern**: Service orchestration with separate repositories
- **Transaction Support**: MongoDB ACID transactions for data consistency
- **Content Deduplication**: Multiple files can reference the same content via SHA256 hash
- **Error Handling**: MongoDB standard exceptions with transaction rollback
### Document Service (`document_service.py`)
Orchestrates operations between file and content repositories while maintaining data consistency.
#### Core Functionality
##### `create_document(file_path: str, file_bytes: bytes, encoding: str)`
Creates a new document with automatic attribute calculation and content deduplication.
**Automatic Calculations:**
- `file_hash`: SHA256 hash of file bytes
- `file_type`: Detection based on file extension
- `mime_type`: Detection via `python-magic` library
- `file_size`: Length of provided bytes
- `detected_at`: Current timestamp
- `metadata`: Empty dictionary (reserved for future extension)
**Deduplication Logic:**
1. Calculate SHA256 hash of file content
2. Check if `DocumentContent` with this hash already exists
3. If EXISTS: Create only `FileDocument` referencing existing content
4. If NOT EXISTS: Create both `FileDocument` and `DocumentContent` in transaction
**Transaction Flow:**
```
BEGIN TRANSACTION
IF content_exists(file_hash):
CREATE FileDocument with content reference
ELSE:
CREATE DocumentContent
CREATE FileDocument with content reference
COMMIT TRANSACTION
```
#### Available Methods
- `create_document(file_path, file_bytes, encoding)`: Create with deduplication
- `get_document_by_id(document_id)`: Retrieve by document ID
- `get_document_by_hash(file_hash)`: Retrieve by file hash
- `get_document_by_filepath(filepath)`: Retrieve by file path
- `list_documents(skip, limit)`: Paginated document listing
- `count_documents()`: Total document count
- `update_document(document_id, update_data)`: Update document metadata
- `delete_document(document_id)`: Remove document and orphaned content
### Repository Dependencies
The document service coordinates two existing repositories:
#### File Repository (`file_repository.py`)
- `create_document()`, `find_document_by_id()`, `find_document_by_hash()`
- `find_document_by_filepath()`, `find_document_by_name()`
- `list_documents()`, `count_documents()`
- `update_document()`, `delete_document()`
#### Document Content Repository (`document_content_repository.py`)
- `create_document_content()`, `find_document_content_by_id()`
- `find_document_content_by_file_hash()`, `content_exists()`
- `update_document_content()`, `delete_document_content()`
- `list_document_contents()`, `count_document_contents()`
### Dependencies
- `python-magic`: MIME type detection
- `hashlib`: SHA256 hashing (standard library)
- `pymongo`: MongoDB transactions support
- **Synchronous Operations**: All database operations use pymongo for Celery compatibility
## Key Implementation Notes
@@ -449,6 +457,7 @@ The document service coordinates two existing repositories:
- **Package Manager**: pip (standard)
- **External Dependencies**: Listed in each service's requirements.txt
- **Standard Library First**: Prefer standard library when possible
- **Database Driver**: pymongo for synchronous MongoDB operations
### Testing Strategy
@@ -473,6 +482,7 @@ The document service coordinates two existing repositories:
12. **Content in Files Collection**: Extracted content stored with file metadata
13. **Direct Task Dispatch**: File watcher directly creates Celery tasks
14. **SHA256 Duplicate Detection**: Prevents reprocessing identical files
15. **Synchronous Implementation**: All repositories and services use pymongo for Celery compatibility
### Development Process Requirements
@@ -483,21 +493,15 @@ The document service coordinates two existing repositories:
### Next Implementation Steps
1. ✅ Create docker-compose.yml with all services => Done
2. ✅ Define user management and authentication architecture => Done
3. ✅ Implement user models and authentication services =>
1. models/user.py => Done
2. models/auth.py => Done
3. database/repositories/user_repository.py => Done
4. ✅ Add automatic admin user creation if it does not exists => Done
5. **IN PROGRESS**: Implement file processing pipeline =>
1. Create Pydantic models for files and processing_jobs collections
2. Implement repository layer for file and processing job data access
3. Create Celery tasks for document processing (.txt, .pdf, .docx)
4. Implement Watchdog file monitoring with dedicated observer
5. Integrate file watcher with FastAPI startup
6. Create protected API routes for user management
7. Build React monitoring interface with authentication
1. **TODO**: Complete file processing pipeline =>
1. ✅ Create Pydantic models for files and processing_jobs collections
2. ✅ Implement repository layer for file and processing job data access (synchronous)
3. ✅ Implement service layer for business logic (synchronous)
4. ✅ Create Celery tasks for document processing (.txt, .pdf, .docx)
5. ✅ Implement Watchdog file monitoring with dedicated observer
6. ✅ Integrate file watcher with FastAPI startup
2. Create protected API routes for user management
3. Build React monitoring interface with authentication
## Annexes

25
docker-compose.yml
View File

@@ -19,7 +19,7 @@ services:
MONGO_INITDB_ROOT_PASSWORD: password123
MONGO_INITDB_DATABASE: mydocmanager
volumes:
- mongodb-data:/data/db
- ./volumes/db:/data/db
networks:
- mydocmanager-network
@@ -34,10 +34,12 @@ services:
environment:
- REDIS_URL=redis://redis:6379/0
- MONGODB_URL=mongodb://admin:password123@mongodb:27017/mydocmanager?authSource=admin
- PYTHONPATH=/app
- PYTHONPATH=/app:/tasks # Added /tasks to Python path
volumes:
- ./src/file-processor:/app
- ./src/worker/tasks:/app/tasks # <- Added: shared access to worker tasks
- ./volumes/watched_files:/watched_files
- ./volumes/objects:/objects
depends_on:
- redis
- mongodb
@@ -56,14 +58,29 @@ services:
- MONGODB_URL=mongodb://admin:password123@mongodb:27017/mydocmanager?authSource=admin
- PYTHONPATH=/app
volumes:
- ./src/worker/tasks:/app
- ./src/worker:/app
- ./src/file-processor/app:/app/app # <- Added: shared access file-processor app
- ./volumes/watched_files:/watched_files
depends_on:
- redis
- mongodb
networks:
- mydocmanager-network
command: celery -A main worker --loglevel=info
command: celery -A tasks.main worker --loglevel=info
# Frontend - React application with Vite
frontend:
build:
context: ./src/frontend
dockerfile: Dockerfile
container_name: mydocmanager-frontend
ports:
- "5173:5173"
volumes:
- ./src/frontend:/app
- /app/node_modules # Anonymous volume to prevent node_modules override
networks:
- mydocmanager-network
volumes:
mongodb-data:

18
requirements.txt
View File

@@ -1,20 +1,30 @@
amqp==5.3.1
annotated-types==0.7.0
anyio==4.10.0
asgiref==3.9.1
bcrypt==4.3.0
billiard==4.2.1
celery==5.5.3
certifi==2025.8.3
cffi==2.0.0
click==8.2.1
click-didyoumean==0.3.1
click-plugins==1.1.1.2
click-repl==0.3.0
cryptography==46.0.1
dnspython==2.8.0
ecdsa==0.19.1
email-validator==2.3.0
fastapi==0.116.1
h11==0.16.0
hiredis==3.2.1
httpcore==1.0.9
httptools==0.6.4
httpx==0.28.1
idna==3.10
importlib_metadata==8.7.0
iniconfig==2.1.0
izulu==0.50.0
kombu==5.5.4
mongomock==4.3.0
mongomock-motor==0.0.36
@@ -23,9 +33,13 @@ packaging==25.0
pipdeptree==2.28.0
pluggy==1.6.0
prompt_toolkit==3.0.52
pyasn1==0.6.1
pycparser==2.23
pycron==3.2.0
pydantic==2.11.9
pydantic_core==2.33.2
Pygments==2.19.2
PyJWT==2.10.1
pymongo==4.15.1
pytest==8.4.2
pytest-asyncio==1.2.0
@@ -35,6 +49,8 @@ python-dotenv==1.1.1
python-magic==0.4.27
pytz==2025.2
PyYAML==6.0.2
redis==6.4.0
rsa==4.9.1
sentinels==1.1.1
six==1.17.0
sniffio==1.3.1
@@ -45,6 +61,8 @@ tzdata==2025.2
uvicorn==0.35.0
uvloop==0.21.0
vine==5.1.0
watchdog==6.0.0
watchfiles==1.1.0
wcwidth==0.2.13
websockets==15.0.1
zipp==3.23.0

6
src/file-processor/Dockerfile
View File

@@ -3,6 +3,12 @@ FROM python:3.12-slim
# Set working directory
WORKDIR /app
# Install libmagic
RUN apt-get update && apt-get install -y --no-install-recommends \
libmagic1 \
file \
&& rm -rf /var/lib/apt/lists/*
# Copy requirements and install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

0
src/file-processor/app/api/__init__.py Normal file
View File

100
src/file-processor/app/api/dependencies.py Normal file
View File

@@ -0,0 +1,100 @@
import jwt
from fastapi import Depends, HTTPException
from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
from jwt import InvalidTokenError
from starlette import status
from app.config import settings
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.user_service import UserService
security = HTTPBearer()
def get_auth_service() -> AuthService:
"""Dependency to get AuthService instance."""
return AuthService()
def get_user_service() -> UserService:
"""Dependency to get UserService instance."""
database = get_database()
return UserService(database)
def get_current_user(
credentials: HTTPAuthorizationCredentials = Depends(security),
user_service: UserService = Depends(get_user_service)
) -> UserInDB:
"""
Dependency to get current authenticated user from JWT token.
Args:
credentials: HTTP Bearer credentials
user_service: Auth service instance
Returns:
User: Current authenticated user
Raises:
HTTPException: If token is invalid or user not found
"""
try:
payload = jwt.decode(
credentials.credentials,
settings.get_jwt_secret_key(),
algorithms=[settings.get_jwt_algorithm()]
)
username: str = payload.get("sub")
if username is None:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Could not validate credentials",
headers={"WWW-Authenticate": "Bearer"},
)
except InvalidTokenError:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Could not validate credentials",
headers={"WWW-Authenticate": "Bearer"},
)
user = user_service.get_user_by_username(username)
if user is None:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Could not validate credentials",
headers={"WWW-Authenticate": "Bearer"},
)
if not user.is_active:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="Inactive user"
)
return user
def get_admin_user(current_user: UserInDB = Depends(get_current_user)) -> UserInDB:
"""
Dependency to ensure current user has admin role.
Args:
current_user: Current authenticated user
Returns:
User: Current user if admin
Raises:
HTTPException: If user is not admin
"""
if current_user.role != UserRole.ADMIN:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail="Not enough permissions"
)
return current_user

0
src/file-processor/app/api/routes/__init__.py Normal file
View File

80
src/file-processor/app/api/routes/auth.py Normal file
View File

@@ -0,0 +1,80 @@
from fastapi import APIRouter, Depends, HTTPException, status
from fastapi.security import OAuth2PasswordRequestForm
from app.api.dependencies import get_auth_service, get_current_user, get_user_service
from app.models.auth import LoginResponse, UserResponse
from app.models.user import UserInDB
from app.services.auth_service import AuthService
from app.services.user_service import UserService
router = APIRouter(tags=["authentication"])
@router.post("/login", response_model=LoginResponse)
def login(
form_data: OAuth2PasswordRequestForm = Depends(),
auth_service: AuthService = Depends(get_auth_service),
user_service: UserService = Depends(get_user_service)
):
"""
Authenticate user and return JWT token.
Args:
form_data: OAuth2 password form data
auth_service: Auth service instance
user_service: User service instance
Returns:
LoginResponse: JWT token and user info
Raises:
HTTPException: If authentication fails
"""
incorrect_username_or_pwd = HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Incorrect username or password",
headers={"WWW-Authenticate": "Bearer"},
)
user = user_service.get_user_by_username(form_data.username)
if (not user or
not user.is_active or
not auth_service.verify_user_password(form_data.password, user.hashed_password)):
raise incorrect_username_or_pwd
access_token = auth_service.create_access_token(data={"sub": user.username})
return LoginResponse(
access_token=access_token,
user=UserResponse(
_id=user.id,
username=user.username,
email=user.email,
role=user.role,
is_active=user.is_active,
created_at=user.created_at,
updated_at=user.updated_at
)
)
@router.get("/me", response_model=UserResponse)
def get_current_user_profile(current_user: UserInDB = Depends(get_current_user)):
"""
Get current user profile.
Args:
current_user: Current authenticated user
Returns:
UserResponse: Current user profile without sensitive data
"""
return UserResponse(
_id=current_user.id,
username=current_user.username,
email=current_user.email,
role=current_user.role,
is_active=current_user.is_active,
created_at=current_user.created_at,
updated_at=current_user.updated_at
)

172
src/file-processor/app/api/routes/users.py Normal file
View File

@@ -0,0 +1,172 @@
from fastapi import APIRouter, Depends, HTTPException
from starlette import status
from app.api.dependencies import get_admin_user, get_user_service
from app.models.auth import UserResponse, MessageResponse
from app.models.types import PyObjectId
from app.models.user import UserInDB, UserCreate, UserUpdate
from app.services.user_service import UserService
router = APIRouter(tags=["users"])
@router.get("", response_model=list[UserInDB])
def list_users(
admin_user: UserInDB = Depends(get_admin_user),
user_service: UserService = Depends(get_user_service)
):
"""
List all users (admin only).
Args:
admin_user: Current admin user
user_service: User service instance
Returns:
List[UserResponse]: List of all users without sensitive data
"""
return user_service.list_users()
@router.get("/{user_id}", response_model=UserResponse)
def get_user_by_id(
user_id: PyObjectId,
admin_user: UserInDB = Depends(get_admin_user),
user_service: UserService = Depends(get_user_service)
):
"""
Get specific user by ID (admin only).
Args:
user_id: User ID to retrieve
admin_user: Current admin user
user_service: User service instance
Returns:
UserResponse: User information without sensitive data
Raises:
HTTPException: If user not found
"""
user = user_service.get_user_by_id(str(user_id))
if not user:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="User not found"
)
return user
@router.post("", response_model=UserResponse, status_code=status.HTTP_201_CREATED)
def create_user(
user_data: UserCreate,
admin_user: UserInDB = Depends(get_admin_user),
user_service: UserService = Depends(get_user_service)
):
"""
Create new user (admin only).
Args:
user_data: User creation data
admin_user: Current admin user
user_service: User service instance
Returns:
UserResponse: Created user information without sensitive data
Raises:
HTTPException: If user creation fails
"""
try:
user = user_service.create_user(user_data)
return UserResponse(
_id=user.id,
username=user.username,
email=user.email,
role=user.role,
is_active=user.is_active,
created_at=user.created_at,
updated_at=user.updated_at
)
except ValueError as e:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e)
)
@router.put("/{user_id}", response_model=UserResponse)
def update_user(
user_id: PyObjectId,
user_data: UserUpdate,
admin_user: UserInDB = Depends(get_admin_user),
user_service: UserService = Depends(get_user_service)
):
"""
Update existing user (admin only).
Args:
user_id: User ID to update
user_data: User update data
admin_user: Current admin user
user_service: User service instance
Returns:
UserResponse: Updated user information without sensitive data
Raises:
HTTPException: If user not found or update fails
"""
try:
user = user_service.update_user(str(user_id), user_data)
if not user:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="User not found"
)
return UserResponse(
_id=user.id,
username=user.username,
email=user.email,
role=user.role,
is_active=user.is_active,
created_at=user.created_at,
updated_at=user.updated_at
)
except ValueError as e:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e)
)
@router.delete("/{user_id}", response_model=MessageResponse)
def delete_user(
user_id: PyObjectId,
admin_user: UserInDB = Depends(get_admin_user),
user_service: UserService = Depends(get_user_service)
):
"""
Delete user by ID (admin only).
Args:
user_id: User ID to delete
admin_user: Current admin user
user_service: User service instance
Returns:
MessageResponse: Success message
Raises:
HTTPException: If user not found or deletion fails
"""
success = user_service.delete_user(str(user_id))
if not success:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="User not found"
)
return MessageResponse(message="User successfully deleted")

36
src/file-processor/app/config/settings.py
View File

@@ -6,7 +6,6 @@ using simple os.getenv() approach without external validation libraries.
"""
import os
from typing import Optional
def get_mongodb_url() -> str:
@@ -31,6 +30,26 @@ def get_mongodb_database_name() -> str:
return os.getenv("MONGODB_DATABASE", "mydocmanager")
def get_redis_url() -> str:
return os.getenv("REDIS_URL", "redis://localhost:6379/0")
# def get_redis_host() -> str:
# redis_url = get_redis_url()
# if redis_url.startswith("redis://"):
# return redis_url.split("redis://")[1].split("/")[0]
# else:
# return redis_url
#
#
# def get_redis_port() -> int:
# redis_url = get_redis_url()
# if redis_url.startswith("redis://"):
# return int(redis_url.split("redis://")[1].split("/")[0].split(":")[1])
# else:
# return int(redis_url.split(":")[1])
def get_jwt_secret_key() -> str:
"""
Get JWT secret key from environment variables.
@@ -83,3 +102,18 @@ def is_development_environment() -> bool:
bool: True if development environment
"""
return os.getenv("ENVIRONMENT", "development").lower() == "development"
def get_objects_folder() -> str:
"""
Get Vault path from environment variables.
Returns:
str: Vault path
"""
return os.getenv("OBJECTS_FOLDER", "/objects")
def watch_directory() -> str:
"""Directory to monitor for new files"""
return os.getenv("WATCH_DIRECTORY", "/watched_files")

10
src/file-processor/app/database/connection.py
View File

@@ -7,6 +7,7 @@ The application will terminate if MongoDB is not accessible at startup.
import sys
from typing import Optional
from pymongo import MongoClient
from pymongo.database import Database
from pymongo.errors import ConnectionFailure, ServerSelectionTimeoutError
@@ -107,6 +108,15 @@ def get_mongodb_client() -> Optional[MongoClient]:
return _client
def get_extra_args(session):
# Build kwargs only if session is provided
kwargs = {}
if session is not None:
kwargs["session"] = session
return kwargs
def test_database_connection() -> bool:
"""
Test if database connection is working.

214
src/file-processor/app/database/repositories/document_content_repository.py
View File

@@ -1,214 +0,0 @@
from typing import List, Optional
from datetime import datetime
from motor.motor_asyncio import AsyncIOMotorDatabase, AsyncIOMotorCollection
from pymongo.errors import DuplicateKeyError, PyMongoError
from bson import ObjectId
from app.models.document import DocumentContent
class DocumentContentRepository:
"""
Repository class for document content CRUD operations in MongoDB.
This class handles all database operations related to document content,
following the repository pattern with dependency injection and async/await.
"""
def __init__(self, database: AsyncIOMotorDatabase):
"""
Initialize repository with database dependency.
Args:
database (AsyncIOMotorDatabase): MongoDB database instance
"""
self.db = database
self.collection: AsyncIOMotorCollection = database.document_contents
self._ensure_indexes()
async def initialize(self):
"""
Initialize repository by ensuring required indexes exist.
Should be called after repository instantiation to setup database indexes.
"""
await self._ensure_indexes()
async def _ensure_indexes(self):
"""
Ensure required database indexes exist.
Creates unique index on file_hash field to prevent duplicates.
"""
try:
await self.collection.create_index("file_hash", unique=True)
except PyMongoError:
# Index might already exist, ignore error
pass
async def create_document_content(self, document_content: DocumentContent) -> DocumentContent:
"""
Create a new document content in the database.
Args:
document_content (DocumentContent): Document content data
Returns:
DocumentContent: Created document content with database ID
Raises:
DuplicateKeyError: If file_hash already exists
ValueError: If document content creation fails due to validation
"""
document_dict = document_content.model_dump(by_alias=True, exclude_unset=True)
# Remove _id if it's None to let MongoDB generate it
if document_dict.get("_id") is None:
document_dict.pop("_id", None)
try:
result = await self.collection.insert_one(document_dict)
document_dict["_id"] = result.inserted_id
return DocumentContent(**document_dict)
except DuplicateKeyError as e:
raise DuplicateKeyError(f"Document content with file_hash '{document_content.file_hash}' already exists: {e}")
except PyMongoError as e:
raise ValueError(f"Failed to create document content: {e}")
async def find_document_content_by_id(self, document_id: str) -> Optional[DocumentContent]:
"""
Find document content by ID.
Args:
document_id (str): Document content ID to search for
Returns:
DocumentContent or None: Document content if found, None otherwise
"""
try:
if not ObjectId.is_valid(document_id):
return None
document_doc = await self.collection.find_one({"_id": ObjectId(document_id)})
if document_doc:
return DocumentContent(**document_doc)
return None
except PyMongoError:
return None
async def find_document_content_by_file_hash(self, file_hash: str) -> Optional[DocumentContent]:
"""
Find document content by file hash.
Args:
file_hash (str): File hash to search for
Returns:
DocumentContent or None: Document content if found, None otherwise
"""
try:
document_doc = await self.collection.find_one({"file_hash": file_hash})
if document_doc:
return DocumentContent(**document_doc)
return None
except PyMongoError:
return None
async def content_exists(self, file_hash: str) -> bool:
"""
Check if document content exists by file hash.
Args:
file_hash (str): File hash to check
Returns:
bool: True if document content exists, False otherwise
"""
try:
count = await self.collection.count_documents({"file_hash": file_hash})
return count > 0
except PyMongoError:
return False
async def update_document_content(self, document_id: str, update_data: dict) -> Optional[DocumentContent]:
"""
Update document content information.
Args:
document_id (str): Document content ID to update
update_data (dict): Updated document content data
Returns:
DocumentContent or None: Updated document content if found, None otherwise
"""
try:
if not ObjectId.is_valid(document_id):
return None
# Remove None values and _id from update data
clean_update_data = {k: v for k, v in update_data.items() if v is not None and k != "_id"}
if not clean_update_data:
return await self.find_document_content_by_id(document_id)
result = await self.collection.find_one_and_update(
{"_id": ObjectId(document_id)},
{"$set": clean_update_data},
return_document=True
)
if result:
return DocumentContent(**result)
return None
except PyMongoError:
return None
async def delete_document_content(self, document_id: str) -> bool:
"""
Delete document content from database.
Args:
document_id (str): Document content ID to delete
Returns:
bool: True if document content was deleted, False otherwise
"""
try:
if not ObjectId.is_valid(document_id):
return False
result = await self.collection.delete_one({"_id": ObjectId(document_id)})
return result.deleted_count > 0
except PyMongoError:
return False
async def list_document_contents(self, skip: int = 0, limit: int = 100) -> List[DocumentContent]:
"""
List document contents with pagination.
Args:
skip (int): Number of document contents to skip (default: 0)
limit (int): Maximum number of document contents to return (default: 100)
Returns:
List[DocumentContent]: List of document contents
"""
try:
cursor = self.collection.find({}).skip(skip).limit(limit).sort("_id", -1)
document_docs = await cursor.to_list(length=limit)
return [DocumentContent(**document_doc) for document_doc in document_docs]
except PyMongoError:
return []
async def count_document_contents(self) -> int:
"""
Count total number of document contents.
Returns:
int: Total number of document contents in database
"""
try:
return await self.collection.count_documents({})
except PyMongoError:
return 0

72
src/file-processor/app/database/repositories/document_repository.py
View File

@@ -6,9 +6,13 @@ in MongoDB with proper error handling and type safety.
"""
from typing import Optional, List
from bson import ObjectId
from pymongo.collection import Collection
from pymongo.database import Database
from pymongo.errors import DuplicateKeyError, PyMongoError
from motor.motor_asyncio import AsyncIOMotorCollection, AsyncIOMotorDatabase
from app.database.connection import get_extra_args
from app.models.document import FileDocument
from app.utils.document_matching import fuzzy_matching, subsequence_matching
@@ -34,52 +38,49 @@ class FileDocumentRepository:
with proper error handling and data validation.
"""
def __init__(self, database: AsyncIOMotorDatabase):
def __init__(self, database: Database):
"""Initialize file repository with database connection."""
self.db = database
self.collection: AsyncIOMotorCollection = self.db.files
self._ensure_indexes()
self.collection: Collection = self.db.documents
async def initialize(self):
def initialize(self):
"""
Initialize repository by ensuring required indexes exist.
Should be called after repository instantiation to setup database indexes.
"""
await self._ensure_indexes()
self._ensure_indexes()
return self
async def _ensure_indexes(self):
def _ensure_indexes(self):
"""
Ensure required database indexes exist.
Creates unique index on username field to prevent duplicates.
"""
try:
await self.collection.create_index("filepath", unique=True)
except PyMongoError:
# Index might already exist, ignore error
pass
async def create_document(self, file_data: FileDocument) -> FileDocument:
def create_document(self, file_data: FileDocument, session=None) -> FileDocument:
"""
Create a new file document in database.
Args:
file_data (FileDocument): File document data to create
session (AsyncIOMotorClientSession, optional): MongoDB session
Returns:
FileDocument: Created file document with database ID
FileDocument: Created document with database ID
Raises:
ValueError: If file creation fails due to validation
DuplicateKeyError: If file with same hash already exists
DuplicateKeyError: If a document with same hash already exists
"""
try:
file_dict = file_data.model_dump(by_alias=True, exclude_unset=True)
if "_id" in file_dict and file_dict["_id"] is None:
del file_dict["_id"]
result = await self.collection.insert_one(file_dict)
result = self.collection.insert_one(file_dict, **get_extra_args(session))
file_data.id = result.inserted_id
return file_data
@@ -88,7 +89,7 @@ class FileDocumentRepository:
except PyMongoError as e:
raise ValueError(f"Failed to create file document: {e}")
async def find_document_by_id(self, file_id: str) -> Optional[FileDocument]:
def find_document_by_id(self, file_id: str) -> Optional[FileDocument]:
"""
Find file document by ID.
@@ -102,7 +103,7 @@ class FileDocumentRepository:
if not ObjectId.is_valid(file_id):
return None
file_doc = await self.collection.find_one({"_id": ObjectId(file_id)})
file_doc = self.collection.find_one({"_id": ObjectId(file_id)})
if file_doc:
return FileDocument(**file_doc)
return None
@@ -110,7 +111,7 @@ class FileDocumentRepository:
except PyMongoError:
return None
async def find_document_by_hash(self, file_hash: str) -> Optional[FileDocument]:
def find_document_by_hash(self, file_hash: str) -> Optional[FileDocument]:
"""
Find file document by file hash to detect duplicates.
@@ -121,7 +122,7 @@ class FileDocumentRepository:
FileDocument or None: File document if found, None otherwise
"""
try:
file_doc = await self.collection.find_one({"file_hash": file_hash})
file_doc = self.collection.find_one({"file_hash": file_hash})
if file_doc:
return FileDocument(**file_doc)
return None
@@ -129,7 +130,7 @@ class FileDocumentRepository:
except PyMongoError:
return None
async def find_document_by_filepath(self, filepath: str) -> Optional[FileDocument]:
def find_document_by_filepath(self, filepath: str) -> Optional[FileDocument]:
"""
Find file document by exact filepath.
@@ -140,7 +141,7 @@ class FileDocumentRepository:
FileDocument or None: File document if found, None otherwise
"""
try:
file_doc = await self.collection.find_one({"filepath": filepath})
file_doc = self.collection.find_one({"filepath": filepath})
if file_doc:
return FileDocument(**file_doc)
return None
@@ -148,7 +149,7 @@ class FileDocumentRepository:
except PyMongoError:
return None
async def find_document_by_name(self, filename: str, matching_method: MatchMethodBase = None) -> List[FileDocument]:
def find_document_by_name(self, filename: str, matching_method: MatchMethodBase = None) -> List[FileDocument]:
"""
Find file documents by filename using fuzzy matching.
@@ -162,8 +163,7 @@ class FileDocumentRepository:
try:
# Get all files from database
cursor = self.collection.find({})
all_files = await cursor.to_list(length=None)
all_documents = [FileDocument(**file_doc) for file_doc in all_files]
all_documents = [FileDocument(**file_doc) for file_doc in cursor]
if isinstance(matching_method, FuzzyMatching):
return fuzzy_matching(filename, all_documents, matching_method.threshold)
@@ -173,7 +173,7 @@ class FileDocumentRepository:
except PyMongoError:
return []
async def list_documents(self, skip: int = 0, limit: int = 100) -> List[FileDocument]:
def list_documents(self, skip: int = 0, limit: int = 100) -> List[FileDocument]:
"""
List file documents with pagination.
@@ -186,13 +186,12 @@ class FileDocumentRepository:
"""
try:
cursor = self.collection.find({}).skip(skip).limit(limit).sort("detected_at", -1)
file_docs = await cursor.to_list(length=limit)
return [FileDocument(**doc) for doc in file_docs]
return [FileDocument(**doc) for doc in cursor]
except PyMongoError:
return []
async def count_documents(self) -> int:
def count_documents(self) -> int:
"""
Count total number of file documents.
@@ -200,17 +199,18 @@ class FileDocumentRepository:
int: Total number of file documents in collection
"""
try:
return await self.collection.count_documents({})
return self.collection.count_documents({})
except PyMongoError:
return 0
async def update_document(self, file_id: str, update_data: dict) -> Optional[FileDocument]:
def update_document(self, file_id: str, update_data: dict, session=None) -> Optional[FileDocument]:
"""
Update file document with new data.
Args:
file_id (str): File document ID to update
update_data (dict): Fields to update
session (AsyncIOMotorClientSession, optional): MongoDB session
Returns:
FileDocument or None: Updated file document if successful, None otherwise
@@ -223,12 +223,13 @@ class FileDocumentRepository:
clean_update_data = {k: v for k, v in update_data.items() if v is not None}
if not clean_update_data:
return await self.find_document_by_id(file_id)
return self.find_document_by_id(file_id)
result = await self.collection.find_one_and_update(
result = self.collection.find_one_and_update(
{"_id": ObjectId(file_id)},
{"$set": clean_update_data},
return_document=True
return_document=True,
**get_extra_args(session)
)
if result:
@@ -238,12 +239,13 @@ class FileDocumentRepository:
except PyMongoError:
return None
async def delete_document(self, file_id: str) -> bool:
def delete_document(self, file_id: str, session=None) -> bool:
"""
Delete file document from database.
Args:
file_id (str): File document ID to delete
session (AsyncIOMotorClientSession, optional): MongoDB session
Returns:
bool: True if file was deleted, False otherwise
@@ -252,7 +254,7 @@ class FileDocumentRepository:
if not ObjectId.is_valid(file_id):
return False
result = await self.collection.delete_one({"_id": ObjectId(file_id)})
result = self.collection.delete_one({"_id": ObjectId(file_id)}, **get_extra_args(session))
return result.deleted_count > 0
except PyMongoError:

230
src/file-processor/app/database/repositories/job_repository.py Normal file
View File

@@ -0,0 +1,230 @@
"""
Repository for managing processing jobs in MongoDB.
This module provides data access layer for ProcessingJob operations
with automatic timestamp management and error handling.
"""
from datetime import datetime
from typing import List, Optional
from pymongo.collection import Collection
from pymongo.database import Database
from pymongo.errors import PyMongoError
from app.exceptions.job_exceptions import JobRepositoryError
from app.models.job import ProcessingJob, ProcessingStatus
from app.models.types import PyObjectId
class JobRepository:
"""
Repository for processing job data access operations.
Provides CRUD operations for ProcessingJob documents with automatic
timestamp management and proper error handling.
"""
def __init__(self, database: Database):
"""Initialize repository with MongoDB collection reference."""
self.db = database
self.collection: Collection = self.db.processing_jobs
def _ensure_indexes(self):
"""
Ensure required database indexes exist.
Creates unique index on username field to prevent duplicates.
"""
try:
self.collection.create_index("document_id", unique=True)
except PyMongoError:
# Index might already exist, ignore error
pass
def initialize(self):
"""
Initialize repository by ensuring required indexes exist.
Should be called after repository instantiation to setup database indexes.
"""
self._ensure_indexes()
return self
def create_job(self, document_id: PyObjectId, task_id: Optional[str] = None) -> ProcessingJob:
"""
Create a new processing job.
Args:
file_id: Reference to the file document
task_id: Optional Celery task UUID
Returns:
The created ProcessingJob
Raises:
JobRepositoryError: If database operation fails
"""
try:
job_data = {
"document_id": document_id,
"status": ProcessingStatus.PENDING,
"task_id": task_id,
"created_at": datetime.now(),
"started_at": None,
"completed_at": None,
"error_message": None
}
result = self.collection.insert_one(job_data)
job_data["_id"] = result.inserted_id
return ProcessingJob(**job_data)
except PyMongoError as e:
raise JobRepositoryError("create_job", e)
def find_job_by_id(self, job_id: PyObjectId) -> Optional[ProcessingJob]:
"""
Retrieve a job by its ID.
Args:
job_id: The job ObjectId
Returns:
The ProcessingJob document
Raises:
JobNotFoundError: If job doesn't exist
JobRepositoryError: If database operation fails
"""
try:
job_data = self.collection.find_one({"_id": job_id})
if job_data:
return ProcessingJob(**job_data)
return None
except PyMongoError as e:
raise JobRepositoryError("get_job_by_id", e)
def update_job_status(
self,
job_id: PyObjectId,
status: ProcessingStatus,
error_message: Optional[str] = None
) -> Optional[ProcessingJob]:
"""
Update job status with automatic timestamp management.
Args:
job_id: The job ObjectId
status: New processing status
error_message: Optional error message for failed jobs
Returns:
The updated ProcessingJob
Raises:
JobNotFoundError: If job doesn't exist
JobRepositoryError: If database operation fails
"""
try:
# Prepare update data
update_data = {"status": status}
# Set appropriate timestamp based on status
current_time = datetime.now()
if status == ProcessingStatus.PROCESSING:
update_data["started_at"] = current_time
elif status in (ProcessingStatus.COMPLETED, ProcessingStatus.FAILED):
update_data["completed_at"] = current_time
# Add error message if provided
if error_message is not None:
update_data["error_message"] = error_message
result = self.collection.find_one_and_update(
{"_id": job_id},
{"$set": update_data},
return_document=True
)
if result:
return ProcessingJob(**result)
return None
except PyMongoError as e:
raise JobRepositoryError("update_job_status", e)
def delete_job(self, job_id: PyObjectId) -> bool:
"""
Delete a job from the database.
Args:
job_id: The job ObjectId
Returns:
True if job was deleted, False if not found
Raises:
JobRepositoryError: If database operation fails
"""
try:
result = self.collection.delete_one({"_id": job_id})
return result.deleted_count > 0
except PyMongoError as e:
raise JobRepositoryError("delete_job", e)
def find_jobs_by_document_id(self, document_id: PyObjectId) -> List[ProcessingJob]:
"""
Retrieve all jobs for a specific file.
Args:
document_id: The file ObjectId
Returns:
List of ProcessingJob documents
Raises:
JobRepositoryError: If database operation fails
"""
try:
cursor = self.collection.find({"document_id": document_id})
jobs = []
for job_data in cursor:
jobs.append(ProcessingJob(**job_data))
return jobs
except PyMongoError as e:
raise JobRepositoryError("get_jobs_by_file_id", e)
def get_jobs_by_status(self, status: ProcessingStatus) -> List[ProcessingJob]:
"""
Retrieve all jobs with a specific status.
Args:
status: The processing status to filter by
Returns:
List of ProcessingJob documents
Raises:
JobRepositoryError: If database operation fails
"""
try:
cursor = self.collection.find({"status": status})
jobs = []
for job_data in cursor:
jobs.append(ProcessingJob(**job_data))
return jobs
except PyMongoError as e:
raise JobRepositoryError("get_jobs_by_status", e)

58
src/file-processor/app/database/repositories/user_repository.py
View File

@@ -5,10 +5,12 @@ This module implements the repository pattern for user CRUD operations
with dependency injection of the database connection using async/await.
"""
from typing import Optional, List
from datetime import datetime
from typing import Optional, List
from bson import ObjectId
from motor.motor_asyncio import AsyncIOMotorDatabase, AsyncIOMotorCollection
from pymongo.collection import Collection
from pymongo.database import Database
from pymongo.errors import DuplicateKeyError, PyMongoError
from app.models.user import UserCreate, UserInDB, UserUpdate
@@ -23,7 +25,7 @@ class UserRepository:
following the repository pattern with dependency injection and async/await.
"""
def __init__(self, database: AsyncIOMotorDatabase):
def __init__(self, database: Database):
"""
Initialize repository with database dependency.
@@ -31,30 +33,30 @@ class UserRepository:
database (AsyncIOMotorDatabase): MongoDB database instance
"""
self.db = database
self.collection: AsyncIOMotorCollection = database.users
self._ensure_indexes()
self.collection: Collection = database.users
async def initialize(self):
def initialize(self):
"""
Initialize repository by ensuring required indexes exist.
Should be called after repository instantiation to setup database indexes.
"""
await self._ensure_indexes()
self._ensure_indexes()
return self
async def _ensure_indexes(self):
def _ensure_indexes(self):
"""
Ensure required database indexes exist.
Creates unique index on username field to prevent duplicates.
"""
try:
await self.collection.create_index("username", unique=True)
self.collection.create_index("username", unique=True)
except PyMongoError:
# Index might already exist, ignore error
pass
async def create_user(self, user_data: UserCreate) -> UserInDB:
def create_user(self, user_data: UserCreate) -> UserInDB:
"""
Create a new user in the database.
@@ -79,7 +81,7 @@ class UserRepository:
}
try:
result = await self.collection.insert_one(user_dict)
result = self.collection.insert_one(user_dict)
user_dict["_id"] = result.inserted_id
return UserInDB(**user_dict)
except DuplicateKeyError as e:
@@ -87,7 +89,7 @@ class UserRepository:
except PyMongoError as e:
raise ValueError(f"Failed to create user: {e}")
async def find_user_by_username(self, username: str) -> Optional[UserInDB]:
def find_user_by_username(self, username: str) -> Optional[UserInDB]:
"""
Find user by username.
@@ -98,14 +100,14 @@ class UserRepository:
UserInDB or None: User if found, None otherwise
"""
try:
user_doc = await self.collection.find_one({"username": username})
user_doc = self.collection.find_one({"username": username})
if user_doc:
return UserInDB(**user_doc)
return None
except PyMongoError:
return None
async def find_user_by_id(self, user_id: str) -> Optional[UserInDB]:
def find_user_by_id(self, user_id: str) -> Optional[UserInDB]:
"""
Find user by ID.
@@ -119,14 +121,14 @@ class UserRepository:
if not ObjectId.is_valid(user_id):
return None
user_doc = await self.collection.find_one({"_id": ObjectId(user_id)})
user_doc = self.collection.find_one({"_id": ObjectId(user_id)})
if user_doc:
return UserInDB(**user_doc)
return None
except PyMongoError:
return None
async def find_user_by_email(self, email: str) -> Optional[UserInDB]:
def find_user_by_email(self, email: str) -> Optional[UserInDB]:
"""
Find user by email address.
@@ -137,14 +139,14 @@ class UserRepository:
UserInDB or None: User if found, None otherwise
"""
try:
user_doc = await self.collection.find_one({"email": email})
user_doc = self.collection.find_one({"email": email})
if user_doc:
return UserInDB(**user_doc)
return None
except PyMongoError:
return None
async def update_user(self, user_id: str, user_update: UserUpdate) -> Optional[UserInDB]:
def update_user(self, user_id: str, user_update: UserUpdate) -> Optional[UserInDB]:
"""
Update user information.
@@ -177,9 +179,9 @@ class UserRepository:
clean_update_data = {k: v for k, v in update_data.items() if v is not None}
if not clean_update_data:
return await self.find_user_by_id(user_id)
return self.find_user_by_id(user_id)
result = await self.collection.find_one_and_update(
result = self.collection.find_one_and_update(
{"_id": ObjectId(user_id)},
{"$set": clean_update_data},
return_document=True
@@ -192,7 +194,7 @@ class UserRepository:
except PyMongoError:
return None
async def delete_user(self, user_id: str) -> bool:
def delete_user(self, user_id: str) -> bool:
"""
Delete user from database.
@@ -206,12 +208,12 @@ class UserRepository:
if not ObjectId.is_valid(user_id):
return False
result = await self.collection.delete_one({"_id": ObjectId(user_id)})
result = self.collection.delete_one({"_id": ObjectId(user_id)})
return result.deleted_count > 0
except PyMongoError:
return False
async def list_users(self, skip: int = 0, limit: int = 100) -> List[UserInDB]:
def list_users(self, skip: int = 0, limit: int = 100) -> List[UserInDB]:
"""
List users with pagination.
@@ -224,12 +226,12 @@ class UserRepository:
"""
try:
cursor = self.collection.find({}).skip(skip).limit(limit).sort("created_at", -1)
user_docs = await cursor.to_list(length=limit)
user_docs = cursor.to_list(length=limit)
return [UserInDB(**user_doc) for user_doc in user_docs]
except PyMongoError:
return []
async def count_users(self) -> int:
def count_users(self) -> int:
"""
Count total number of users.
@@ -237,11 +239,11 @@ class UserRepository:
int: Total number of users in database
"""
try:
return await self.collection.count_documents({})
return self.collection.count_documents({})
except PyMongoError:
return 0
async def user_exists(self, username: str) -> bool:
def user_exists(self, username: str) -> bool:
"""
Check if user exists by username.
@@ -252,7 +254,7 @@ class UserRepository:
bool: True if user exists, False otherwise
"""
try:
count = await self.collection.count_documents({"username": username})
count = self.collection.count_documents({"username": username})
return count > 0
except PyMongoError:
return False

0
src/file-processor/app/exceptions/__init__.py Normal file
View File

38
src/file-processor/app/exceptions/job_exceptions.py Normal file
View File

@@ -0,0 +1,38 @@
"""
Custom exceptions for job management operations.
This module defines specific exceptions for job processing lifecycle
and repository operations to provide clear error handling.
"""
from app.models.job import ProcessingStatus
class InvalidStatusTransitionError(Exception):
"""
Raised when an invalid status transition is attempted.
This exception indicates that an attempt was made to change a job's
status to an invalid target status given the current status.
"""
def __init__(self, current_status: ProcessingStatus, target_status: ProcessingStatus):
self.current_status = current_status
self.target_status = target_status
super().__init__(
f"Invalid status transition from '{current_status}' to '{target_status}'"
)
class JobRepositoryError(Exception):
"""
Raised when a MongoDB operation fails in the job repository.
This exception wraps database-related errors that occur during
job repository operations.
"""
def __init__(self, operation: str, original_error: Exception):
self.operation = operation
self.original_error = original_error
super().__init__(f"Repository operation '{operation}' failed: {str(original_error)}")

243
src/file-processor/app/file_watcher.py Normal file
View File

@@ -0,0 +1,243 @@
"""
File watcher implementation with Watchdog observer and ProcessingJob management.
This module provides real-time file monitoring for document processing.
When a file is created in the watched directory, it:
1. Creates a document record via DocumentService
2. Dispatches a Celery task for processing
3. Creates a ProcessingJob to track the task lifecycle
"""
import logging
import threading
from pathlib import Path
from typing import Optional
from watchdog.events import FileSystemEventHandler, FileCreatedEvent
from watchdog.observers import Observer
from app.services.document_service import DocumentService
from app.services.job_service import JobService
logger = logging.getLogger(__name__)
class DocumentFileEventHandler(FileSystemEventHandler):
"""
Event handler for document file creation events.
Processes newly created files by creating document records,
dispatching Celery tasks, and managing processing jobs.
"""
SUPPORTED_EXTENSIONS = {'.txt', '.pdf', '.docx'}
def __init__(self, document_service: DocumentService, job_service: JobService):
"""
Initialize the event handler.
Args:
document_service: Service for document management
job_service: Service for processing job management
"""
super().__init__()
self.document_service = document_service
self.job_service = job_service
def on_created(self, event: FileCreatedEvent) -> None:
"""
Handle file creation events.
Args:
event: File system event containing file path information
"""
if event.is_directory:
return
filepath = event.src_path
file_extension = Path(filepath).suffix.lower()
if file_extension not in self.SUPPORTED_EXTENSIONS:
logger.info(f"Ignoring unsupported file type: {filepath}")
return
logger.info(f"Processing new file: {filepath}")
# try:
from tasks.document_processing import process_document
task_result = process_document.delay(filepath)
print(task_result)
print("hello world")
# task_id = task_result.task_id
# logger.info(f"Dispatched Celery task with ID: {task_id}")
# except Exception as e:
# logger.error(f"Failed to process file {filepath}: {str(e)}")
# # Note: We don't re-raise the exception to keep the watcher running
class FileWatcher:
"""
File system watcher for automatic document processing.
Monitors a directory for new files and triggers processing pipeline
using a dedicated observer thread.
"""
def __init__(
self,
watch_directory: str,
document_service: DocumentService,
job_service: JobService,
recursive: bool = True
):
"""
Initialize the file watcher.
Args:
watch_directory: Directory path to monitor
document_service: Service for document management
job_service: Service for processing job management
recursive: Whether to watch subdirectories recursively
"""
self.watch_directory = Path(watch_directory)
self.recursive = recursive
self.observer: Optional[Observer] = None
self._observer_thread: Optional[threading.Thread] = None
self._stop_event = threading.Event()
# Validate watch directory
if not self.watch_directory.exists():
raise ValueError(f"Watch directory does not exist: {watch_directory}")
if not self.watch_directory.is_dir():
raise ValueError(f"Watch path is not a directory: {watch_directory}")
# Create event handler
self.event_handler = DocumentFileEventHandler(
document_service=document_service,
job_service=job_service
)
logger.info(f"FileWatcher initialized for directory: {self.watch_directory}")
def start(self) -> None:
"""
Start the file watcher in a separate thread.
Raises:
RuntimeError: If the watcher is already running
"""
if self.is_running():
raise RuntimeError("FileWatcher is already running")
self.observer = Observer()
self.observer.schedule(
self.event_handler,
str(self.watch_directory),
recursive=self.recursive
)
# Start observer in separate thread
self._observer_thread = threading.Thread(
target=self._run_observer,
name="FileWatcher-Observer"
)
self._stop_event.clear()
self._observer_thread.start()
logger.info("FileWatcher started successfully")
def stop(self, timeout: float = 5.0) -> None:
"""
Stop the file watcher gracefully.
Args:
timeout: Maximum time to wait for graceful shutdown
"""
if not self.is_running():
logger.warning("FileWatcher is not running")
return
logger.info("Stopping FileWatcher...")
# Signal stop and wait for observer thread
self._stop_event.set()
if self.observer:
self.observer.stop()
if self._observer_thread and self._observer_thread.is_alive():
self._observer_thread.join(timeout=timeout)
if self._observer_thread.is_alive():
logger.warning("FileWatcher thread did not stop gracefully within timeout")
else:
logger.info("FileWatcher stopped gracefully")
# Clean up
self.observer = None
self._observer_thread = None
def is_running(self) -> bool:
"""
Check if the file watcher is currently running.
Returns:
True if the watcher is running, False otherwise
"""
return (
self.observer is not None
and self._observer_thread is not None
and self._observer_thread.is_alive()
)
def _run_observer(self) -> None:
"""
Internal method to run the observer in a separate thread.
This method should not be called directly.
"""
if not self.observer:
logger.error("Observer not initialized")
return
try:
self.observer.start()
logger.info("Observer thread started")
# Keep the observer running until stop is requested
while not self._stop_event.is_set():
self._stop_event.wait(timeout=1.0)
logger.info("Observer thread stopping...")
except Exception as e:
logger.error(f"Observer thread error: {str(e)}")
finally:
if self.observer:
self.observer.join()
logger.info("Observer thread stopped")
def create_file_watcher(
watch_directory: str,
document_service: DocumentService,
job_service: JobService
) -> FileWatcher:
"""
Factory function to create a FileWatcher instance.
Args:
watch_directory: Directory path to monitor
document_service: Service for document management
job_service: Service for processing job management
Returns:
Configured FileWatcher instance
"""
return FileWatcher(
watch_directory=watch_directory,
document_service=document_service,
job_service=job_service
)

248
src/file-processor/app/main.py
View File

@@ -1,123 +1,119 @@
"""
FastAPI application for MyDocManager file processor service.
FastAPI application with integrated FileWatcher for document processing.
This service provides API endpoints for health checks and task dispatching.
This module provides the main FastAPI application with:
- JWT authentication
- User management APIs
- Real-time file monitoring via FileWatcher
- Document processing via Celery tasks
"""
import logging
import os
from contextlib import asynccontextmanager
from fastapi import FastAPI, HTTPException, Depends
from pydantic import BaseModel
import redis
from celery import Celery
from typing import AsyncGenerator
from app.database.connection import test_database_connection, get_database
from app.database.repositories.user_repository import UserRepository
from app.models.user import UserCreate
from fastapi import FastAPI
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.config import settings
from app.database.connection import get_database
from app.file_watcher import create_file_watcher, FileWatcher
from app.services.document_service import DocumentService
from app.services.init_service import InitializationService
from app.services.job_service import JobService
from app.services.user_service import UserService
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Global file watcher instance
file_watcher: FileWatcher = None
@asynccontextmanager
async def lifespan(app: FastAPI):
async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
"""
Application lifespan manager for startup and shutdown tasks.
FastAPI lifespan context manager.
Handles initialization tasks that need to run when the application starts,
including admin user creation and other setup procedures.
Handles application startup and shutdown events including:
- Database connection
- Default admin user creation
- FileWatcher startup/shutdown
"""
# Startup tasks
global file_watcher
# Startup
logger.info("Starting MyDocManager application...")
try:
# Initialize database connection
database = get_database()
logger.info("Database connection established")
# Initialize repositories and services
user_repository = UserRepository(database)
user_service = UserService(user_repository)
document_service = DocumentService(database=database, objects_folder=settings.get_objects_folder())
job_service = JobService(database=database)
user_service = UserService(database=database)
logger.info("Service created")
# Create default admin user
init_service = InitializationService(user_service)
init_service.initialize_application()
logger.info("Default admin user initialization completed")
# Run initialization tasks
initialization_result = init_service.initialize_application()
# Create and start file watcher
file_watcher = create_file_watcher(
watch_directory=settings.watch_directory(),
document_service=document_service,
job_service=job_service
)
file_watcher.start()
logger.info(f"FileWatcher started for directory: {settings.watch_directory()}")
if initialization_result["initialization_success"]:
logger.info("Application startup completed successfully")
if initialization_result["admin_user_created"]:
logger.info("Default admin user was created during startup")
else:
logger.error("Application startup completed with errors:")
for error in initialization_result["errors"]:
logger.error(f" - {error}")
yield
except Exception as e:
logger.error(f"Critical error during application startup: {str(e)}")
# You might want to decide if the app should continue or exit here
# For now, we log the error but continue
logger.error(f"Application startup failed: {str(e)}")
raise
yield # Application is running
# Shutdown tasks (if needed)
finally:
# Shutdown
logger.info("Shutting down MyDocManager application...")
if file_watcher and file_watcher.is_running():
file_watcher.stop()
logger.info("FileWatcher stopped")
# Initialize FastAPI app
logger.info("Application shutdown completed")
# Create FastAPI application
app = FastAPI(
title="MyDocManager File Processor",
description="File processing and task dispatch service",
version="1.0.0",
title="MyDocManager",
description="Real-time document processing application with authentication",
version="0.1.0",
lifespan=lifespan
)
# Environment variables
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
MONGODB_URL = os.getenv("MONGODB_URL", "mongodb://localhost:27017")
# Initialize Redis client
try:
redis_client = redis.from_url(REDIS_URL)
except Exception as e:
redis_client = None
print(f"Warning: Could not connect to Redis: {e}")
# Initialize Celery
celery_app = Celery(
"file_processor",
broker=REDIS_URL,
backend=REDIS_URL
# Configure CORS
app.add_middleware(
CORSMiddleware,
allow_origins=["http://localhost:5173"], # React frontend
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# 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(jobs_router, prefix="/jobs", tags=["Processing Jobs"])
# Pydantic models
class TestTaskRequest(BaseModel):
"""Request model for test task."""
message: str
def get_user_service() -> UserService:
"""
Dependency to get user service instance.
This should be properly implemented with database connection management
in your actual application.
"""
database = get_database()
user_repository = UserRepository(database)
return UserService(user_repository)
# Your API routes would use the service like this:
@app.post("/api/users")
async def create_user(
user_data: UserCreate,
user_service: UserService = Depends(get_user_service)
):
return user_service.create_user(user_data)
@app.get("/health")
async def health_check():
@@ -125,79 +121,49 @@ async def health_check():
Health check endpoint.
Returns:
dict: Service health status with dependencies
Dictionary containing application health status
"""
health_status = {
"status": "healthy",
"service": "file-processor",
"dependencies": {
"redis": "unknown",
"mongodb": "unknown"
},
}
# Check Redis connection
if redis_client:
try:
redis_client.ping()
health_status["dependencies"]["redis"] = "connected"
except Exception:
health_status["dependencies"]["redis"] = "disconnected"
health_status["status"] = "degraded"
# check MongoDB connection
if test_database_connection():
health_status["dependencies"]["mongodb"] = "connected"
else:
health_status["dependencies"]["mongodb"] = "disconnected"
return health_status
@app.post("/test-task")
async def dispatch_test_task(request: TestTaskRequest):
"""
Dispatch a test task to Celery worker.
Args:
request: Test task request containing message
Returns:
dict: Task dispatch information
Raises:
HTTPException: If task dispatch fails
"""
try:
# Send task to worker
task = celery_app.send_task(
"main.test_task",
args=[request.message]
)
return {
"status": "dispatched",
"task_id": task.id,
"message": f"Test task dispatched with message: {request.message}"
"status": "healthy",
"service": "MyDocManager",
"version": "1.0.0",
"file_watcher_running": file_watcher.is_running() if file_watcher else False
}
except Exception as e:
raise HTTPException(
status_code=500,
detail=f"Failed to dispatch task: {str(e)}"
)
@app.get("/")
async def root():
"""
Root endpoint.
Root endpoint with basic application information.
Returns:
dict: Basic service information
Dictionary containing welcome message and available endpoints
"""
return {
"service": "MyDocManager File Processor",
"version": "1.0.0",
"status": "running"
"message": "Welcome to MyDocManager",
"description": "Real-time document processing application",
"docs": "/docs",
"health": "/health"
}
@app.get("/watcher/status")
async def watcher_status():
"""
Get file watcher status.
Returns:
Dictionary containing file watcher status information
"""
if not file_watcher:
return {
"status": "not_initialized",
"running": False
}
return {
"status": "initialized",
"running": file_watcher.is_running(),
"watch_directory": str(file_watcher.watch_directory),
"recursive": file_watcher.recursive
}

35
src/file-processor/app/models/auth.py
View File

@@ -3,12 +3,45 @@ Authentication models and enums for user management.
Contains user roles enumeration and authentication-related Pydantic models.
"""
from datetime import datetime
from enum import Enum
from pydantic import BaseModel, Field
from app.models.types import PyObjectId
class UserRole(str, Enum):
"""User roles enumeration with string values."""
USER = "user"
ADMIN = "admin"
class UserResponse(BaseModel):
"""Model for user data in API responses (excludes password_hash)."""
id: PyObjectId = Field(alias="_id")
username: str
email: str
role: UserRole
is_active: bool
created_at: datetime
updated_at: datetime
model_config = {
"populate_by_name": True,
"arbitrary_types_allowed": True,
}
class LoginResponse(BaseModel):
"""Response model for successful login."""
access_token: str
token_type: str = "bearer"
user: UserResponse
class MessageResponse(BaseModel):
"""Generic message response."""
message: str

78
src/file-processor/app/models/document.py
View File

@@ -33,15 +33,6 @@ class ExtractionMethod(str, Enum):
HYBRID = "hybrid"
class ProcessingStatus(str, Enum):
"""Status values for processing jobs."""
PENDING = "pending"
PROCESSING = "processing"
COMPLETED = "completed"
FAILED = "failed"
class FileDocument(BaseModel):
"""
Model for file documents stored in the 'files' collection.
@@ -58,6 +49,9 @@ 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")
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")
@field_validator('filepath')
@classmethod
@@ -74,69 +68,3 @@ class FileDocument(BaseModel):
if not v.strip():
raise ValueError("Filename cannot be empty")
return v.strip()
class Config:
"""Pydantic configuration."""
populate_by_name = True
arbitrary_types_allowed = True
json_encoders = {ObjectId: str}
class DocumentContent(BaseModel):
"""Model for document content."""
id: Optional[PyObjectId] = Field(default=None, alias="_id")
file_hash: Optional[str] = Field(default=None, description="SHA256 hash of file content")
content: str = Field(..., description="File content")
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")
class ProcessingJob(BaseModel):
"""
Model for processing jobs stored in the 'processing_jobs' collection.
Tracks the lifecycle and status of document processing tasks.
"""
id: Optional[PyObjectId] = Field(default=None, alias="_id")
file_id: PyObjectId = Field(..., description="Reference to file document")
status: ProcessingStatus = Field(
default=ProcessingStatus.PENDING,
description="Current processing status"
)
task_id: Optional[str] = Field(
default=None,
description="Celery task UUID"
)
created_at: Optional[datetime] = Field(
default=None,
description="Timestamp when job was created"
)
started_at: Optional[datetime] = Field(
default=None,
description="Timestamp when processing started"
)
completed_at: Optional[datetime] = Field(
default=None,
description="Timestamp when processing completed"
)
error_message: Optional[str] = Field(
default=None,
description="Error message if processing failed"
)
@field_validator('error_message')
@classmethod
def validate_error_message(cls, v: Optional[str]) -> Optional[str]:
"""Clean up error message."""
if v is not None:
return v.strip() if v.strip() else None
return v
class Config:
"""Pydantic configuration."""
populate_by_name = True
arbitrary_types_allowed = True
json_encoders = {ObjectId: str}

42
src/file-processor/app/models/job.py
View File

@@ -0,0 +1,42 @@
from datetime import datetime
from enum import Enum
from typing import Optional
from bson import ObjectId
from pydantic import BaseModel, Field, field_validator
from app.models.types import PyObjectId
class ProcessingStatus(str, Enum):
"""Status values for processing jobs."""
PENDING = "pending"
PROCESSING = "processing"
COMPLETED = "completed"
FAILED = "failed"
class ProcessingJob(BaseModel):
"""
Model for processing jobs stored in the 'processing_jobs' collection.
Tracks the lifecycle and status of document processing tasks.
"""
id: Optional[PyObjectId] = Field(default=None, alias="_id")
document_id: PyObjectId = Field(..., description="Reference to file document")
status: ProcessingStatus = Field(default=ProcessingStatus.PENDING, description="Current processing status")
task_id: Optional[str] = Field(default=None, description="Celery task UUID")
created_at: Optional[datetime] = Field(default=None, description="Timestamp when job was created")
started_at: Optional[datetime] = Field(default=None, description="Timestamp when processing started")
completed_at: Optional[datetime] = Field(default=None, description="Timestamp when processing completed")
error_message: Optional[str] = Field(default=None, description="Error message if processing failed")
@field_validator('error_message')
@classmethod
def validate_error_message(cls, v: Optional[str]) -> Optional[str]:
"""Clean up error message."""
if v is not None:
return v.strip() if v.strip() else None
return v

22
src/file-processor/app/models/user.py
View File

@@ -7,10 +7,10 @@ and API responses with proper validation and type safety.
import re
from datetime import datetime
from typing import Optional, Any
from typing import Optional
from bson import ObjectId
from pydantic import BaseModel, Field, field_validator, EmailStr
from pydantic_core import core_schema
from app.models.auth import UserRole
from app.models.types import PyObjectId
@@ -138,21 +138,3 @@ class UserInDB(BaseModel):
"arbitrary_types_allowed": True,
"json_encoders": {ObjectId: str}
}
class UserResponse(BaseModel):
"""Model for user data in API responses (excludes password_hash)."""
id: PyObjectId = Field(alias="_id")
username: str
email: str
role: UserRole
is_active: bool
created_at: datetime
updated_at: datetime
model_config = {
"populate_by_name": True,
"arbitrary_types_allowed": True,
"json_encoders": {ObjectId: str}
}

26
src/file-processor/app/services/auth_service.py
View File

@@ -4,7 +4,11 @@ Authentication service for password hashing and verification.
This module provides authentication-related functionality including
password hashing, verification, and JWT token management.
"""
from datetime import datetime, timedelta
import jwt
from app.config import settings
from app.utils.security import hash_password, verify_password
@@ -56,3 +60,25 @@ class AuthService:
False
"""
return verify_password(password, hashed_password)
@staticmethod
def create_access_token(data=dict) -> str:
"""
Create a JWT access token.
Args:
data (dict): Payload data to include in the token.
Returns:
str: Encoded JWT token.
"""
# Copy data to avoid modifying the original dict
to_encode = data.copy()
# Add expiration time
expire = datetime.now() + timedelta(hours=settings.get_jwt_expire_hours())
to_encode.update({"exp": expire})
# Encode JWT
encoded_jwt = jwt.encode(to_encode, settings.get_jwt_secret_key(), algorithm=settings.get_jwt_algorithm())
return encoded_jwt

268
src/file-processor/app/services/document_service.py
View File

@@ -6,22 +6,19 @@ while maintaining data consistency through MongoDB transactions.
"""
import hashlib
import magic
import os
from datetime import datetime
from pathlib import Path
from typing import List, Optional, Dict, Any, Tuple
from typing import List, Optional, Dict, Any
from motor.motor_asyncio import AsyncIOMotorClientSession
import magic
from pymongo.errors import PyMongoError
from app.database.connection import get_database
from app.config.settings import get_objects_folder
from app.database.repositories.document_repository import FileDocumentRepository
from app.database.repositories.document_content_repository import DocumentContentRepository
from app.models.document import (
FileDocument,
DocumentContent,
FileType,
ProcessingStatus
)
from app.models.types import PyObjectId
@@ -34,13 +31,25 @@ class DocumentService:
and their content while ensuring data consistency through transactions.
"""
def __init__(self):
"""Initialize the document service with repository dependencies."""
self.db = get_database()
self.file_repository = FileDocumentRepository(self.db)
self.content_repository = DocumentContentRepository(self.db)
def __init__(self, database, objects_folder: str = None):
"""
Initialize the document service with repository dependencies.
def _calculate_file_hash(self, file_bytes: bytes) -> str:
Args:
database: Database instance
objects_folder: folder to store files by their hash
"""
self.db = database
self.document_repository = FileDocumentRepository(self.db)
self.objects_folder = objects_folder or get_objects_folder()
def initialize(self):
self.document_repository.initialize()
return self
@staticmethod
def _calculate_file_hash(file_bytes: bytes) -> str:
"""
Calculate SHA256 hash of file content.
@@ -52,7 +61,8 @@ class DocumentService:
"""
return hashlib.sha256(file_bytes).hexdigest()
def _detect_file_type(self, file_path: str) -> FileType:
@staticmethod
def _detect_file_type(file_path: str) -> FileType:
"""
Detect file type from file extension.
@@ -72,7 +82,8 @@ class DocumentService:
except ValueError:
raise ValueError(f"Unsupported file type: {extension}")
def _detect_mime_type(self, file_bytes: bytes) -> str:
@staticmethod
def _detect_mime_type(file_bytes: bytes) -> str:
"""
Detect MIME type from file content.
@@ -84,10 +95,51 @@ class DocumentService:
"""
return magic.from_buffer(file_bytes, mime=True)
async def create_document(
@staticmethod
def _read_file_bytes(file_path: str | Path) -> bytes:
"""
Read file content as bytes asynchronously.
Args:
file_path (str | Path): Path of the file to read
Returns:
bytes: Content of the file
Raises:
FileNotFoundError: If the file does not exist
OSError: If any I/O error occurs
"""
path = Path(file_path)
if not path.exists():
raise FileNotFoundError(f"File not found: {file_path}")
return path.read_bytes()
def _get_document_path(self, file_hash):
"""
:param file_hash:
:return:
"""
return os.path.join(self.objects_folder, file_hash[:24], file_hash)
def save_content_if_needed(self, file_hash, content: bytes):
target_path = self._get_document_path(file_hash)
if os.path.exists(target_path):
return
if not os.path.exists(os.path.dirname(target_path)):
os.makedirs(os.path.dirname(target_path))
with open(target_path, "wb") as f:
f.write(content)
def create_document(
self,
file_path: str,
file_bytes: bytes,
file_bytes: bytes | None = None,
encoding: str = "utf-8"
) -> FileDocument:
"""
@@ -110,34 +162,16 @@ class DocumentService:
PyMongoError: If database operation fails
"""
# Calculate automatic attributes
file_bytes = file_bytes if file_bytes is not None else self._read_file_bytes(file_path)
file_hash = self._calculate_file_hash(file_bytes)
file_type = self._detect_file_type(file_path)
mime_type = self._detect_mime_type(file_bytes)
file_size = len(file_bytes)
filename = Path(file_path).name
detected_at = datetime.utcnow()
detected_at = datetime.now()
# Start MongoDB transaction
async with await self.db.client.start_session() as session:
async with session.start_transaction():
try:
# Check if content already exists
existing_content = await self.content_repository.find_document_content_by_file_hash(
file_hash, session=session
)
# Create DocumentContent if it doesn't exist
if not existing_content:
content_data = DocumentContent(
file_hash=file_hash,
content="", # Will be populated by processing workers
encoding=encoding,
file_size=file_size,
mime_type=mime_type
)
await self.content_repository.create_document_content(
content_data, session=session
)
self.save_content_if_needed(file_hash, file_bytes)
# Create FileDocument
file_data = FileDocument(
@@ -147,20 +181,21 @@ class DocumentService:
extraction_method=None, # Will be set by processing workers
metadata={}, # Empty for now
detected_at=detected_at,
file_hash=file_hash
file_hash=file_hash,
encoding=encoding,
file_size=file_size,
mime_type=mime_type
)
created_file = await self.file_repository.create_document(
file_data, session=session
)
created_file = self.document_repository.create_document(file_data)
return created_file
except Exception as e:
# Transaction will automatically rollback
# Transaction will automatically rollback if supported
raise PyMongoError(f"Failed to create document: {str(e)}")
async def get_document_by_id(self, document_id: PyObjectId) -> Optional[FileDocument]:
def get_document_by_id(self, document_id: PyObjectId) -> Optional[FileDocument]:
"""
Retrieve a document by its ID.
@@ -170,9 +205,9 @@ class DocumentService:
Returns:
FileDocument if found, None otherwise
"""
return await self.file_repository.find_document_by_id(document_id)
return self.document_repository.find_document_by_id(str(document_id))
async def get_document_by_hash(self, file_hash: str) -> Optional[FileDocument]:
def get_document_by_hash(self, file_hash: str) -> Optional[FileDocument]:
"""
Retrieve a document by its file hash.
@@ -182,9 +217,9 @@ class DocumentService:
Returns:
FileDocument if found, None otherwise
"""
return await self.file_repository.find_document_by_hash(file_hash)
return self.document_repository.find_document_by_hash(file_hash)
async def get_document_by_filepath(self, filepath: str) -> Optional[FileDocument]:
def get_document_by_filepath(self, filepath: str) -> Optional[FileDocument]:
"""
Retrieve a document by its file path.
@@ -194,34 +229,17 @@ class DocumentService:
Returns:
FileDocument if found, None otherwise
"""
return await self.file_repository.find_document_by_filepath(filepath)
return self.document_repository.find_document_by_filepath(filepath)
async def get_document_with_content(
self,
document_id: PyObjectId
) -> Optional[Tuple[FileDocument, DocumentContent]]:
"""
Retrieve a document with its associated content.
Args:
document_id: Document ObjectId
Returns:
Tuple of (FileDocument, DocumentContent) if found, None otherwise
"""
document = await self.get_document_by_id(document_id)
if not document:
def get_document_content_by_hash(self, file_hash):
target_path = self._get_document_path(file_hash)
if not os.path.exists(target_path):
return None
content = await self.content_repository.find_document_content_by_file_hash(
document.file_hash
)
if not content:
return None
with open(target_path, "rb") as f:
return f.read()
return (document, content)
async def list_documents(
def list_documents(
self,
skip: int = 0,
limit: int = 100
@@ -236,18 +254,18 @@ class DocumentService:
Returns:
List of FileDocument instances
"""
return await self.file_repository.list_documents(skip=skip, limit=limit)
return self.document_repository.list_documents(skip=skip, limit=limit)
async def count_documents(self) -> int:
def count_documents(self) -> int:
"""
Get total number of documents.
Returns:
Total document count
"""
return await self.file_repository.count_documents()
return self.document_repository.count_documents()
async def update_document(
def update_document(
self,
document_id: PyObjectId,
update_data: Dict[str, Any]
@@ -262,9 +280,14 @@ class DocumentService:
Returns:
Updated FileDocument if found, None otherwise
"""
return await self.file_repository.update_document(document_id, update_data)
if "file_bytes" in update_data:
file_hash = self._calculate_file_hash(update_data["file_bytes"])
update_data["file_hash"] = file_hash
self.save_content_if_needed(file_hash, update_data["file_bytes"])
async def delete_document(self, document_id: PyObjectId) -> bool:
return self.document_repository.update_document(document_id, update_data)
def delete_document(self, document_id: PyObjectId) -> bool:
"""
Delete a document and its orphaned content.
@@ -281,100 +304,31 @@ class DocumentService:
Raises:
PyMongoError: If database operation fails
"""
# Start MongoDB transaction
async with await self.db.client.start_session() as session:
async with session.start_transaction():
# Start transaction
try:
# Get document to find its hash
document = await self.file_repository.find_document_by_id(
document_id, session=session
)
document = self.document_repository.find_document_by_id(document_id)
if not document:
return False
# Delete the document
deleted = await self.file_repository.delete_document(
document_id, session=session
)
deleted = self.document_repository.delete_document(document_id)
if not deleted:
return False
# Check if content is orphaned
remaining_files = await self.file_repository.find_document_by_hash(
document.file_hash, session=session
)
remaining_files = self.document_repository.find_document_by_hash(document.file_hash)
# If no other files reference this content, delete it
if not remaining_files:
content = await self.content_repository.find_document_content_by_file_hash(
document.file_hash, session=session
)
if content:
await self.content_repository.delete_document_content(
content.id, session=session
)
try:
os.remove(self._get_document_path(document.file_hash))
except Exception:
pass
return True
except Exception as e:
# Transaction will automatically rollback
# Transaction will automatically rollback if supported
raise PyMongoError(f"Failed to delete document: {str(e)}")
async def content_exists(self, file_hash: str) -> bool:
"""
Check if content with given hash exists.
Args:
file_hash: SHA256 hash of file content
Returns:
True if content exists, False otherwise
"""
return await self.content_repository.content_exists(file_hash)
async def get_content_by_hash(self, file_hash: str) -> Optional[DocumentContent]:
"""
Retrieve content by file hash.
Args:
file_hash: SHA256 hash of file content
Returns:
DocumentContent if found, None otherwise
"""
return await self.content_repository.find_document_content_by_file_hash(file_hash)
async def update_document_content(
self,
file_hash: str,
content: str,
encoding: str = "utf-8"
) -> Optional[DocumentContent]:
"""
Update the extracted content for a document.
This method is typically called by processing workers to store
the extracted text content.
Args:
file_hash: SHA256 hash of file content
content: Extracted text content
encoding: Character encoding
Returns:
Updated DocumentContent if found, None otherwise
"""
existing_content = await self.content_repository.find_document_content_by_file_hash(
file_hash
)
if not existing_content:
return None
update_data = {
"content": content,
"encoding": encoding
}
return await self.content_repository.update_document_content(
existing_content.id, update_data
)

22
src/file-processor/app/services/init_service.py
View File

@@ -8,8 +8,8 @@ creating default admin user if none exists.
import logging
from typing import Optional
from app.models.user import UserCreate, UserInDB, UserCreateNoValidation
from app.models.auth import UserRole
from app.models.user import UserInDB, UserCreateNoValidation
from app.services.user_service import UserService
logger = logging.getLogger(__name__)
@@ -32,7 +32,6 @@ class InitializationService:
"""
self.user_service = user_service
def ensure_admin_user_exists(self) -> Optional[UserInDB]:
"""
Ensure default admin user exists in the system.
@@ -131,4 +130,23 @@ class InitializationService:
logger.error(error_msg)
initialization_summary["errors"].append(error_msg)
self.log_initialization_result(initialization_summary)
return initialization_summary
@staticmethod
def log_initialization_result(summary: dict) -> None:
"""
Log the result of the initialization process.
Args:
summary (dict): Summary of initialization tasks performed
"""
if summary["initialization_success"]:
logger.info("Application startup completed successfully")
if summary["admin_user_created"]:
logger.info("Default admin user was created during startup")
else:
logger.error("Application startup completed with errors:")
for error in summary["errors"]:
logger.error(f" - {error}")

182
src/file-processor/app/services/job_service.py Normal file
View File

@@ -0,0 +1,182 @@
"""
Service layer for job processing business logic.
This module provides high-level operations for managing processing jobs
with strict status transition validation and business rules enforcement.
"""
from typing import Optional
from app.database.repositories.job_repository import JobRepository
from app.exceptions.job_exceptions import InvalidStatusTransitionError
from app.models.job import ProcessingJob, ProcessingStatus
from app.models.types import PyObjectId
class JobService:
"""
Service for processing job business logic operations.
Provides high-level job management with strict status transition
validation and business rule enforcement.
"""
def __init__(self, database):
"""
Initialize service with job repository.
Args:
repository: Optional JobRepository instance (creates default if None)
"""
self.db = database
self.repository = JobRepository(database)
def initialize(self):
self.repository.initialize()
return self
def create_job(self, document_id: PyObjectId, task_id: Optional[str] = None) -> ProcessingJob:
"""
Create a new processing job.
Args:
document_id: Reference to the file document
task_id: Optional Celery task UUID
Returns:
The created ProcessingJob
Raises:
JobRepositoryError: If database operation fails
"""
return self.repository.create_job(document_id, task_id)
def get_job_by_id(self, job_id: PyObjectId) -> ProcessingJob:
"""
Retrieve a job by its ID.
Args:
job_id: The job ObjectId
Returns:
The ProcessingJob document
Raises:
JobNotFoundError: If job doesn't exist
JobRepositoryError: If database operation fails
"""
return self.repository.find_job_by_id(job_id)
def mark_job_as_started(self, job_id: PyObjectId) -> ProcessingJob:
"""
Mark a job as started (PENDING → PROCESSING).
Args:
job_id: The job ObjectId
Returns:
The updated ProcessingJob
Raises:
JobNotFoundError: If job doesn't exist
InvalidStatusTransitionError: If job is not in PENDING status
JobRepositoryError: If database operation fails
"""
# Get current job to validate transition
current_job = self.repository.find_job_by_id(job_id)
# Validate status transition
if current_job.status != ProcessingStatus.PENDING:
raise InvalidStatusTransitionError(current_job.status, ProcessingStatus.PROCESSING)
# Update status
return self.repository.update_job_status(job_id, ProcessingStatus.PROCESSING)
def mark_job_as_completed(self, job_id: PyObjectId) -> ProcessingJob:
"""
Mark a job as completed (PROCESSING → COMPLETED).
Args:
job_id: The job ObjectId
Returns:
The updated ProcessingJob
Raises:
JobNotFoundError: If job doesn't exist
InvalidStatusTransitionError: If job is not in PROCESSING status
JobRepositoryError: If database operation fails
"""
# Get current job to validate transition
current_job = self.repository.find_job_by_id(job_id)
# Validate status transition
if current_job.status != ProcessingStatus.PROCESSING:
raise InvalidStatusTransitionError(current_job.status, ProcessingStatus.COMPLETED)
# Update status
return self.repository.update_job_status(job_id, ProcessingStatus.COMPLETED)
def mark_job_as_failed(
self,
job_id: PyObjectId,
error_message: Optional[str] = None
) -> ProcessingJob:
"""
Mark a job as failed (PROCESSING → FAILED).
Args:
job_id: The job ObjectId
error_message: Optional error description
Returns:
The updated ProcessingJob
Raises:
JobNotFoundError: If job doesn't exist
InvalidStatusTransitionError: If job is not in PROCESSING status
JobRepositoryError: If database operation fails
"""
# Get current job to validate transition
current_job = self.repository.find_job_by_id(job_id)
# Validate status transition
if current_job.status != ProcessingStatus.PROCESSING:
raise InvalidStatusTransitionError(current_job.status, ProcessingStatus.FAILED)
# Update status with error message
return self.repository.update_job_status(
job_id,
ProcessingStatus.FAILED,
error_message
)
def delete_job(self, job_id: PyObjectId) -> bool:
"""
Delete a job from the database.
Args:
job_id: The job ObjectId
Returns:
True if job was deleted, False if not found
Raises:
JobRepositoryError: If database operation fails
"""
return self.repository.delete_job(job_id)
def get_jobs_by_status(self, status: ProcessingStatus) -> list[ProcessingJob]:
"""
Retrieve all jobs with a specific status.
Args:
status: The processing status to filter by
Returns:
List of ProcessingJob documents
Raises:
JobRepositoryError: If database operation fails
"""
return self.repository.get_jobs_by_status(status)

13
src/file-processor/app/services/user_service.py
View File

@@ -6,11 +6,11 @@ retrieval, updates, and authentication operations with proper error handling.
"""
from typing import Optional, List
from pymongo.errors import DuplicateKeyError
from app.models.user import UserCreate, UserInDB, UserUpdate, UserResponse, UserCreateNoValidation
from app.models.auth import UserRole
from app.database.repositories.user_repository import UserRepository
from app.models.user import UserCreate, UserInDB, UserUpdate, UserCreateNoValidation
from app.services.auth_service import AuthService
@@ -22,16 +22,21 @@ class UserService:
authentication, and data management with proper validation.
"""
def __init__(self, user_repository: UserRepository):
def __init__(self, database):
"""
Initialize user service with repository dependency.
Args:
user_repository (UserRepository): Repository for user data operations
"""
self.user_repository = user_repository
self.db = database
self.user_repository = UserRepository(self.db)
self.auth_service = AuthService()
def initialize(self):
self.user_repository.initialize()
return self
def create_user(self, user_data: UserCreate | UserCreateNoValidation) -> UserInDB:
"""
Create a new user with business logic validation.

5
src/file-processor/requirements.txt
View File

@@ -1,11 +1,14 @@
asgiref==3.9.1
bcrypt==4.3.0
celery==5.5.3
email-validator==2.3.0
fastapi==0.116.1
httptools==0.6.4
motor==3.7.1
pymongo==4.15.0
pydantic==2.11.9
PyJWT==2.10.1
pymongo==4.15.0
redis==6.4.0
uvicorn==0.35.0
python-magic==0.4.27
watchdog==6.0.0

41
src/frontend/.dockerignore Normal file
View File

@@ -0,0 +1,41 @@
# Dependencies
node_modules
npm-debug.log*
yarn-debug.log*
yarn-error.log*
# Build outputs
dist
build
# Environment files
.env.local
.env.development.local
.env.test.local
.env.production.local
# IDE files
.vscode
.idea
*.swp
*.swo
# OS generated files
.DS_Store
.DS_Store?
._*
.Spotlight-V100
.Trashes
ehthumbs.db
Thumbs.db
# Git
.git
.gitignore
# Docker
Dockerfile
.dockerignore
# Logs
*.log

20
src/frontend/Dockerfile Normal file
View File

@@ -0,0 +1,20 @@
# Use Node.js 20 Alpine for lightweight container
FROM node:20-alpine
# Set working directory
WORKDIR /app
# Copy package.json and package-lock.json (if available)
COPY package*.json ./
# Install dependencies
RUN npm install
# Copy source code
COPY . .
# Expose Vite default port
EXPOSE 5173
# Start development server with host 0.0.0.0 to accept external connections
CMD ["npm", "run", "dev", "--", "--host", "0.0.0.0", "--port", "5173"]

8
src/worker/Dockerfile
View File

@@ -3,12 +3,18 @@ FROM python:3.12-slim
# Set working directory
WORKDIR /app
# Install libmagic
RUN apt-get update && apt-get install -y --no-install-recommends \
libmagic1 \
file \
&& rm -rf /var/lib/apt/lists/*
# Copy requirements and install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# Copy application code
COPY tasks/ .
COPY . .
# Command will be overridden by docker-compose
CMD ["celery", "-A", "main", "worker", "--loglevel=info"]

13
src/worker/requirements.txt
View File

@@ -1,4 +1,13 @@
asgiref==3.9.1
bcrypt==4.3.0
celery==5.5.3
redis==6.4.0
email-validator==2.3.0
fastapi==0.116.1
httptools==0.6.4
motor==3.7.1
pymongo==4.15.0
pydantic==2.11.9
redis==6.4.0
uvicorn==0.35.0
python-magic==0.4.27
watchdog==6.0.0

85
src/worker/tasks/document_processing.py Normal file
View File

@@ -0,0 +1,85 @@
"""
Celery tasks for document processing with ProcessingJob status management.
This module contains Celery tasks that handle document content extraction
and update processing job statuses throughout the task lifecycle.
"""
import logging
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 tasks.main import celery_app
logger = logging.getLogger(__name__)
@celery_app.task(bind=True, autoretry_for=(Exception,), retry_kwargs={'max_retries': 3, 'countdown': 60})
def process_document(self, filepath: str) -> Dict[str, Any]:
"""
Process a document file and extract its content.
This task:
1. Updates the processing job status to PROCESSING
2. Performs document content extraction
3. Updates job status to COMPLETED or FAILED based on result
Args:
self : Celery task instance
filepath: Full path to the document file to process
Returns:
Dictionary containing processing results
Raises:
Exception: Any processing error (will trigger retry)
"""
task_id = self.request.id
logger.info(f"Starting document processing task {task_id} for file: {filepath}")
database = get_database()
document_service = DocumentService(database=database, objects_folder=settings.get_objects_folder())
from app.services.job_service import JobService
job_service = JobService(database=database)
job = None
try:
# Step 1: Insert the document in DB
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")
# Step 4: Mark job as completed
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",
}
except Exception as e:
error_message = f"Document processing failed: {str(e)}"
logger.error(f"Task {task_id} failed: {error_message}")
try:
# Mark job as failed
if job is not None:
job_service.mark_job_as_failed(job_id=job.id, error_message=error_message)
logger.info(f"Job {task_id} marked as FAILED")
else:
logger.error(f"Failed to process {filepath}. error = {str(e)}")
except Exception as job_error:
logger.error(f"Failed to update job status for task {task_id}: {str(job_error)}")
# Re-raise the exception to trigger Celery retry mechanism
raise

91
src/worker/tasks/main.py
View File

@@ -3,9 +3,8 @@ Celery worker for MyDocManager document processing tasks.
This module contains all Celery tasks for processing documents.
"""
import os
import time
from celery import Celery
# Environment variables
@@ -13,14 +12,16 @@ REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
MONGODB_URL = os.getenv("MONGODB_URL", "mongodb://localhost:27017")
# Initialize Celery app
app = Celery(
celery_app = Celery(
"mydocmanager_worker",
broker=REDIS_URL,
backend=REDIS_URL
backend=REDIS_URL,
)
celery_app.autodiscover_tasks(["tasks.document_processing"])
# Celery configuration
app.conf.update(
celery_app.conf.update(
task_serializer="json",
accept_content=["json"],
result_serializer="json",
@@ -31,83 +32,5 @@ app.conf.update(
task_soft_time_limit=240, # 4 minutes
)
@app.task(bind=True)
def test_task(self, message: str):
"""
Test task for validating worker functionality.
Args:
message: Test message to process
Returns:
dict: Task result with processing information
"""
try:
print(f"[WORKER] Starting test task with message: {message}")
# Simulate some work
for i in range(5):
print(f"[WORKER] Processing step {i + 1}/5...")
time.sleep(1)
# Update task progress
self.update_state(
state="PROGRESS",
meta={
"current": i + 1,
"total": 5,
"message": f"Processing step {i + 1}"
}
)
result = {
"status": "completed",
"message": f"Successfully processed: {message}",
"processed_at": time.time(),
"worker_id": self.request.id
}
print(f"[WORKER] Test task completed successfully: {result}")
return result
except Exception as exc:
print(f"[WORKER] Test task failed: {str(exc)}")
raise self.retry(exc=exc, countdown=60, max_retries=3)
@app.task(bind=True)
def process_document_task(self, file_path: str):
"""
Placeholder task for document processing.
Args:
file_path: Path to the document to process
Returns:
dict: Processing result
"""
try:
print(f"[WORKER] Starting document processing for: {file_path}")
# Placeholder for document processing logic
time.sleep(2) # Simulate processing time
result = {
"status": "completed",
"file_path": file_path,
"processed_at": time.time(),
"content": f"Placeholder content for {file_path}",
"worker_id": self.request.id
}
print(f"[WORKER] Document processing completed: {file_path}")
return result
except Exception as exc:
print(f"[WORKER] Document processing failed for {file_path}: {str(exc)}")
raise self.retry(exc=exc, countdown=60, max_retries=3)
if __name__ == "__main__":
app.start()
celery_app.start()

0
tests/api/__init__.py Normal file
View File

149
tests/api/test_auth_routes.py Normal file
View File

@@ -0,0 +1,149 @@
from datetime import datetime
from unittest.mock import MagicMock
import pytest
from fastapi import status, HTTPException
from fastapi.testclient import TestClient
from mongomock.mongo_client import MongoClient
from app.api.dependencies import get_auth_service, get_user_service, get_current_user
from app.main import app # Assuming you have FastAPI app defined in app/main.py
from app.models.auth import UserRole
from app.models.types import PyObjectId
from app.models.user import UserInDB
from app.services.auth_service import AuthService
from app.services.user_service import UserService
@pytest.fixture
def client():
return TestClient(app)
@pytest.fixture
def fake_user():
return UserInDB(
_id=PyObjectId(),
username="testuser",
email="test@example.com",
role=UserRole.USER,
is_active=True,
hashed_password="hashed-secret",
created_at=datetime(2025, 1, 1),
updated_at=datetime(2025, 1, 2),
)
def override_auth_service():
mock = MagicMock(spec=AuthService)
mock.verify_user_password.return_value = True
mock.create_access_token.return_value = "fake-jwt-token"
return mock
def override_user_service(fake_user):
mock = MagicMock(spec=UserService)
mock.get_user_by_username.return_value = fake_user
return mock
def override_get_current_user(fake_user):
def _override():
return fake_user
return _override
def override_get_database():
def _override():
client = MongoClient()
db = client.test_database
return db
return _override
# ---------------------- TESTS FOR /auth/login ----------------------
class TestLogin:
def test_i_can_login_with_valid_credentials(self, client, fake_user):
auth_service = override_auth_service()
user_service = override_user_service(fake_user)
client.app.dependency_overrides[get_auth_service] = lambda: auth_service
client.app.dependency_overrides[get_user_service] = lambda: user_service
response = client.post(
"/auth/login",
data={"username": "testuser", "password": "secret"},
)
assert response.status_code == status.HTTP_200_OK
data = response.json()
assert "access_token" in data
assert data["user"]["username"] == "testuser"
def test_i_cannot_login_with_invalid_username(self, client):
auth_service = override_auth_service()
user_service = MagicMock(spec=UserService)
user_service.get_user_by_username.return_value = None
client.app.dependency_overrides[get_auth_service] = lambda: auth_service
client.app.dependency_overrides[get_user_service] = lambda: user_service
response = client.post(
"/auth/login",
data={"username": "unknown", "password": "secret"},
)
assert response.status_code == status.HTTP_401_UNAUTHORIZED
def test_i_cannot_login_with_inactive_user(self, client, fake_user):
fake_user.is_active = False
auth_service = override_auth_service()
user_service = override_user_service(fake_user)
client.app.dependency_overrides[get_auth_service] = lambda: auth_service
client.app.dependency_overrides[get_user_service] = lambda: user_service
response = client.post(
"/auth/login",
data={"username": "testuser", "password": "secret"},
)
assert response.status_code == status.HTTP_401_UNAUTHORIZED
def test_i_cannot_login_with_wrong_password(self, client, fake_user):
auth_service = override_auth_service()
auth_service.verify_user_password.return_value = False
user_service = override_user_service(fake_user)
client.app.dependency_overrides[get_auth_service] = lambda: auth_service
client.app.dependency_overrides[get_user_service] = lambda: user_service
response = client.post(
"/auth/login",
data={"username": "testuser", "password": "wrong"},
)
assert response.status_code == status.HTTP_401_UNAUTHORIZED
# ---------------------- TESTS FOR /auth/me ----------------------
class TesteMe:
def test_i_can_get_current_user_profile(self, client, fake_user):
client.app.dependency_overrides[get_current_user] = override_get_current_user(fake_user)
response = client.get("/auth/me")
assert response.status_code == status.HTTP_200_OK
data = response.json()
assert data["username"] == fake_user.username
assert data["email"] == fake_user.email
def test_i_cannot_get_profile_without_authentication(self, client, monkeypatch):
def raise_http_exception():
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED)
client.app.dependency_overrides[get_current_user] = raise_http_exception
response = client.get("/auth/me")
assert response.status_code == status.HTTP_401_UNAUTHORIZED

167
tests/api/test_users.py Normal file
View File

@@ -0,0 +1,167 @@
# File: tests/api/test_users.py
from datetime import datetime
from unittest.mock import MagicMock
import pytest
from fastapi import status
from fastapi.testclient import TestClient
from app.api.dependencies import get_admin_user, get_user_service
from app.main import app
from app.models.auth import UserRole
from app.models.types import PyObjectId
from app.models.user import UserInDB, UserCreate
from app.services.user_service import UserService
# -----------------------
# Fixtures
# -----------------------
@pytest.fixture
def fake_user_admin():
return UserInDB(
_id=PyObjectId(),
username="admin",
email="admin@example.com",
role=UserRole.ADMIN,
is_active=True,
hashed_password="hashed-secret",
created_at=datetime(2025, 1, 1),
updated_at=datetime(2025, 1, 2),
)
@pytest.fixture
def fake_user_response():
return UserInDB(
_id=PyObjectId(),
username="other",
email="other@example.com",
role=UserRole.USER,
is_active=True,
hashed_password="hashed-secret-2",
created_at=datetime(2025, 1, 1),
updated_at=datetime(2025, 1, 2),
)
@pytest.fixture
def client(fake_user_admin):
# Fake admin dependency
def get_admin_user_override():
return fake_user_admin
# Fake user service
user_service_mock = MagicMock(spec=UserService)
def get_user_service_override():
return user_service_mock
client = TestClient(app)
client.app.dependency_overrides = {
get_admin_user: get_admin_user_override,
get_user_service: get_user_service_override
}
client.user_service_mock = user_service_mock
return client
# -----------------------
# Tests
# -----------------------
class TestListUsers:
def test_i_can_list_users(self, client, fake_user_admin, fake_user_response):
client.user_service_mock.list_users.return_value = [fake_user_admin, fake_user_response]
response = client.get("/users")
assert response.status_code == status.HTTP_200_OK
data = response.json()
assert len(data) == 2
assert data[0]["username"] == "admin"
def test_i_can_list_users_when_empty(self, client):
client.user_service_mock.list_users.return_value = []
response = client.get("/users")
assert response.status_code == status.HTTP_200_OK
assert response.json() == []
class TestGetUserById:
def test_i_can_get_user_by_id(self, client, fake_user_response):
client.user_service_mock.get_user_by_id.return_value = fake_user_response
response = client.get(f"/users/{fake_user_response.id}")
assert response.status_code == status.HTTP_200_OK
data = response.json()
assert data["username"] == fake_user_response.username
def test_i_cannot_get_user_by_id_not_found(self, client):
client.user_service_mock.get_user_by_id.return_value = None
response = client.get("/users/64f0c9f4b0d1c8b7b8e1f0a2")
assert response.status_code == status.HTTP_404_NOT_FOUND
assert response.json()["detail"] == "User not found"
class TestCreateUser:
def test_i_can_create_user(self, client, fake_user_response):
user_data = UserCreate(username="newuser",
email="new@example.com",
password="#Passw0rd!",
role=UserRole.USER)
client.user_service_mock.create_user.return_value = fake_user_response
response = client.post("/users", json=user_data.model_dump(mode="json"))
assert response.status_code == status.HTTP_201_CREATED
data = response.json()
assert data["username"] == fake_user_response.username
def test_i_cannot_create_user_when_service_raises_value_error(self, client):
user_data = {"username": "baduser", "email": "bad@example.com", "role": "user", "password": "password"}
client.user_service_mock.create_user.side_effect = ValueError("Invalid data")
response = client.post("/users", json=user_data)
assert response.status_code == status.HTTP_422_UNPROCESSABLE_ENTITY
class TestUpdateUser:
def test_i_can_update_user(self, client, fake_user_response):
user_data = {"username": "updateduser", "email": "updated@example.com"}
client.user_service_mock.update_user.return_value = fake_user_response
response = client.put(f"/users/{fake_user_response.id}", json=user_data)
assert response.status_code == status.HTTP_200_OK
data = response.json()
assert data["username"] == fake_user_response.username
def test_i_cannot_update_user_not_found(self, client):
client.user_service_mock.update_user.return_value = None
user_data = {"username": "updateduser"}
response = client.put("/users/64f0c9f4b0d1c8b7b8e1f0a2", json=user_data)
assert response.status_code == status.HTTP_404_NOT_FOUND
assert response.json()["detail"] == "User not found"
def test_i_cannot_update_user_when_service_raises_value_error(self, client):
client.user_service_mock.update_user.side_effect = ValueError("Invalid update")
user_data = {"username": "badupdate"}
response = client.put("/users/64f0c9f4b0d1c8b7b8e1f0a2", json=user_data)
assert response.status_code == status.HTTP_400_BAD_REQUEST
assert response.json()["detail"] == "Invalid update"
class TestDeleteUser:
def test_i_can_delete_user(self, client):
client.user_service_mock.delete_user.return_value = True
response = client.delete("/users/64f0c9f4b0d1c8b7b8e1f0a1")
assert response.status_code == status.HTTP_200_OK
data = response.json()
assert data["message"] == "User successfully deleted"
def test_i_cannot_delete_user_not_found(self, client):
client.user_service_mock.delete_user.return_value = False
response = client.delete("/users/64f0c9f4b0d1c8b7b8e1f0a2")
assert response.status_code == status.HTTP_404_NOT_FOUND
assert response.json()["detail"] == "User not found"

0
tests/database/__init__.py Normal file
View File

0
tests/models/__init__.py Normal file
View File

6
tests/test_user_models.py → tests/models/test_user_models.py
View File

@@ -10,8 +10,8 @@ from pydantic import ValidationError
from datetime import datetime
from bson import ObjectId
from app.models.user import UserCreate, UserUpdate, UserInDB, UserResponse
from app.models.auth import UserRole
from app.models.user import UserCreate, UserUpdate, UserInDB
from app.models.auth import UserRole, UserResponse
class TestUserCreateModel:
@@ -349,7 +349,7 @@ class TestUserResponseModel:
# Convert to response model (excluding password_hash)
user_response = UserResponse(
id=user_in_db.id,
_id=user_in_db.id,
username=user_in_db.username,
email=user_in_db.email,
role=user_in_db.role,

0
tests/repositories/__init__.py Normal file
View File

611
tests/repositories/test_document_repository.py Normal file
View File

@@ -0,0 +1,611 @@
"""
Test suite for FileDocumentRepository with async/support.
This module contains comprehensive tests for all FileDocumentRepository methods
using mongomock-motor for in-memory MongoDB testing.
"""
from datetime import datetime
import pytest
from bson import ObjectId
from mongomock.mongo_client import MongoClient
from pymongo.errors import PyMongoError
from app.database.repositories.document_repository import (
FileDocumentRepository,
MatchMethodBase,
SubsequenceMatching,
FuzzyMatching
)
from app.models.document import FileDocument, FileType, ExtractionMethod
@pytest.fixture
def in_memory_repository():
"""Create an in-memory FileDocumentRepository for testing."""
client = MongoClient()
db = client.test_database
repo = FileDocumentRepository(db)
repo.initialize()
return repo
@pytest.fixture
def sample_file_document():
"""Sample FileDocument data for testing."""
return FileDocument(
filename="sample_document.pdf",
filepath="/home/user/documents/sample_document.pdf",
file_type=FileType.PDF,
extraction_method=ExtractionMethod.OCR,
metadata={"pages": 5, "language": "en", "author": "John Doe"},
detected_at=datetime.now(),
file_hash="a1b2c3d4e5f6789012345678901234567890abcdef1234567890abcdef123456",
encoding="utf-8",
file_size=1024000,
mime_type="application/pdf"
)
@pytest.fixture
def sample_update_data():
"""Sample update data for testing."""
return {
"extraction_method": ExtractionMethod.HYBRID,
"metadata": {"pages": 10, "language": "fr", "updated": True},
"file_size": 2048000
}
@pytest.fixture
def multiple_sample_files():
"""Multiple FileDocument objects for list/search testing."""
base_time = datetime.now()
return [
FileDocument(
filename="first_doc.txt",
filepath="/docs/first_doc.txt",
file_type=FileType.TXT,
extraction_method=ExtractionMethod.DIRECT_TEXT,
metadata={"words": 500},
detected_at=base_time,
file_hash="hash1" + "0" * 58,
encoding="utf-8",
file_size=5000,
mime_type="text/plain"
),
FileDocument(
filename="second_document.pdf",
filepath="/docs/second_document.pdf",
file_type=FileType.PDF,
extraction_method=ExtractionMethod.OCR,
metadata={"pages": 8},
detected_at=base_time,
file_hash="hash2" + "0" * 58,
encoding="utf-8",
file_size=10000,
mime_type="application/pdf"
),
FileDocument(
filename="third_file.docx",
filepath="/docs/third_file.docx",
file_type=FileType.DOCX,
extraction_method=ExtractionMethod.HYBRID,
metadata={"paragraphs": 15},
detected_at=base_time,
file_hash="hash3" + "0" * 58,
encoding="utf-8",
file_size=15000,
mime_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
)
]
class TestFileDocumentRepositoryInitialization:
"""Tests for repository initialization."""
def test_i_can_initialize_repository(self):
"""Test repository initialization."""
# Arrange
client = MongoClient()
db = client.test_database
repo = FileDocumentRepository(db)
repo.initialize()
# Act & Assert (should not raise any exception)
assert repo.db is not None
assert repo.collection is not None
# TODO : check that the indexes are created
class TestFileDocumentRepositoryCreation:
"""Tests for file document creation functionality."""
def test_i_can_create_file_document(self, in_memory_repository, sample_file_document):
"""Test successful file document creation."""
# Act
created_file = in_memory_repository.create_document(sample_file_document)
# Assert
assert created_file is not None
assert created_file.filename == sample_file_document.filename
assert created_file.filepath == sample_file_document.filepath
assert created_file.file_type == sample_file_document.file_type
assert created_file.extraction_method == sample_file_document.extraction_method
assert created_file.metadata == sample_file_document.metadata
assert created_file.file_hash == sample_file_document.file_hash
assert created_file.file_size == sample_file_document.file_size
assert created_file.mime_type == sample_file_document.mime_type
assert created_file.id is not None
assert isinstance(created_file.id, ObjectId)
def test_i_can_create_file_document_without_id(self, in_memory_repository, sample_file_document):
"""Test creating file document with _id set to None (should be removed)."""
# Arrange
sample_file_document.id = None
# Act
created_file = in_memory_repository.create_document(sample_file_document)
# Assert
assert created_file is not None
assert created_file.id is not None
assert isinstance(created_file.id, ObjectId)
def test_i_cannot_create_file_document_with_pymongo_error(self, in_memory_repository,
sample_file_document, mocker):
"""Test handling of PyMongo errors during file document creation."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'insert_one', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(ValueError) as exc_info:
in_memory_repository.create_document(sample_file_document)
assert "Failed to create file document" in str(exc_info.value)
class TestFileDocumentRepositoryFinding:
"""Tests for file document finding functionality."""
def test_i_can_find_document_by_valid_id(self, in_memory_repository, sample_file_document):
"""Test finding file document by valid ObjectId."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
# Act
found_file = in_memory_repository.find_document_by_id(str(created_file.id))
# Assert
assert found_file is not None
assert found_file.id == created_file.id
assert found_file.filename == created_file.filename
assert found_file.filepath == created_file.filepath
def test_i_cannot_find_document_with_invalid_id(self, in_memory_repository):
"""Test that invalid ObjectId returns None."""
# Act
found_file = in_memory_repository.find_document_by_id("invalid_id")
# Assert
assert found_file is None
def test_i_cannot_find_document_by_nonexistent_id(self, in_memory_repository):
"""Test that nonexistent but valid ObjectId returns None."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
found_file = in_memory_repository.find_document_by_id(nonexistent_id)
# Assert
assert found_file is None
def test_i_can_find_document_by_file_hash(self, in_memory_repository, sample_file_document):
"""Test finding file document by file hash."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
# Act
found_file = in_memory_repository.find_document_by_hash(sample_file_document.file_hash)
# Assert
assert found_file is not None
assert found_file.file_hash == created_file.file_hash
assert found_file.id == created_file.id
def test_i_cannot_find_document_with_nonexistent_file_hash(self, in_memory_repository):
"""Test that nonexistent file hash returns None."""
# Act
found_file = in_memory_repository.find_document_by_hash("nonexistent_hash")
# Assert
assert found_file is None
def test_i_can_find_document_by_filepath(self, in_memory_repository, sample_file_document):
"""Test finding file document by filepath."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
# Act
found_file = in_memory_repository.find_document_by_filepath(sample_file_document.filepath)
# Assert
assert found_file is not None
assert found_file.filepath == created_file.filepath
assert found_file.id == created_file.id
def test_i_cannot_find_document_with_nonexistent_filepath(self, in_memory_repository):
"""Test that nonexistent filepath returns None."""
# Act
found_file = in_memory_repository.find_document_by_filepath("/nonexistent/path/file.pdf")
# Assert
assert found_file is None
def test_i_cannot_find_document_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during file document finding."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find_one', side_effect=PyMongoError("Database error"))
# Act
found_file = in_memory_repository.find_document_by_hash("test_hash")
# Assert
assert found_file is None
class TestFileDocumentRepositoryNameMatching:
"""Tests for file document name matching functionality."""
def test_i_can_find_documents_by_name_with_fuzzy_matching(self, in_memory_repository, multiple_sample_files):
"""Test finding file documents by filename using fuzzy matching."""
# Arrange
for file_doc in multiple_sample_files:
in_memory_repository.create_document(file_doc)
# Act
fuzzy_method = FuzzyMatching(threshold=0.5)
found_files = in_memory_repository.find_document_by_name("document", fuzzy_method)
# Assert
assert len(found_files) >= 1
assert all(isinstance(file_doc, FileDocument) for file_doc in found_files)
# Should find files with "document" in the name
found_filenames = [f.filename for f in found_files]
assert any("document" in fname.lower() for fname in found_filenames)
def test_i_can_find_documents_by_name_with_subsequence_matching(self, in_memory_repository,
multiple_sample_files):
"""Test finding file documents by filename using subsequence matching."""
# Arrange
for file_doc in multiple_sample_files:
in_memory_repository.create_document(file_doc)
# Act
subsequence_method = SubsequenceMatching()
found_files = in_memory_repository.find_document_by_name("doc", subsequence_method)
# Assert
assert len(found_files) >= 1
assert all(isinstance(file_doc, FileDocument) for file_doc in found_files)
def test_i_can_find_documents_by_name_with_default_method(self, in_memory_repository, multiple_sample_files):
"""Test finding file documents by filename with default matching method."""
# Arrange
for file_doc in multiple_sample_files:
in_memory_repository.create_document(file_doc)
# Act
found_files = in_memory_repository.find_document_by_name("first")
# Assert
assert len(found_files) >= 0
assert all(isinstance(file_doc, FileDocument) for file_doc in found_files)
def test_i_cannot_find_documents_by_name_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during document name matching."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find', side_effect=PyMongoError("Database error"))
# Act
found_files = in_memory_repository.find_document_by_name("test")
# Assert
assert found_files == []
class TestFileDocumentRepositoryListing:
"""Tests for file document listing functionality."""
def test_i_can_list_documents_with_default_pagination(self, in_memory_repository, multiple_sample_files):
"""Test listing file documents with default pagination."""
# Arrange
for file_doc in multiple_sample_files:
in_memory_repository.create_document(file_doc)
# Act
files = in_memory_repository.list_documents()
# Assert
assert len(files) == len(multiple_sample_files)
assert all(isinstance(file_doc, FileDocument) for file_doc in files)
def test_i_can_list_documents_with_custom_pagination(self, in_memory_repository, multiple_sample_files):
"""Test listing file documents with custom pagination."""
# Arrange
for file_doc in multiple_sample_files:
in_memory_repository.create_document(file_doc)
# Act
files_page1 = in_memory_repository.list_documents(skip=0, limit=2)
files_page2 = in_memory_repository.list_documents(skip=2, limit=2)
# Assert
assert len(files_page1) == 2
assert len(files_page2) == 1 # Only 3 total files
# Ensure no overlap between pages
page1_ids = [file_doc.id for file_doc in files_page1]
page2_ids = [file_doc.id for file_doc in files_page2]
assert len(set(page1_ids).intersection(set(page2_ids))) == 0
def test_i_can_list_documents_sorted_by_detected_at(self, in_memory_repository, sample_file_document):
"""Test that file documents are sorted by detected_at in descending order."""
# Arrange
file1 = sample_file_document.model_copy()
file1.filepath = "/docs/file1.pdf"
file1.filename = "file1.pdf"
file1.file_hash = "hash1" + "0" * 58
file1.detected_at = datetime(2024, 1, 1, 10, 0, 0)
file2 = sample_file_document.model_copy()
file2.filepath = "/docs/file2.pdf"
file2.filename = "file2.pdf"
file2.file_hash = "hash2" + "0" * 58
file2.detected_at = datetime(2024, 1, 2, 10, 0, 0) # Later date
created_file1 = in_memory_repository.create_document(file1)
created_file2 = in_memory_repository.create_document(file2)
# Act
files = in_memory_repository.list_documents()
# Assert
assert len(files) == 2
# Most recent (latest detected_at) should be first
assert files[0].id == created_file2.id
assert files[1].id == created_file1.id
def test_i_can_list_empty_documents(self, in_memory_repository):
"""Test listing file documents from empty collection."""
# Act
files = in_memory_repository.list_documents()
# Assert
assert files == []
def test_i_cannot_list_documents_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during file document listing."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find', side_effect=PyMongoError("Database error"))
# Act
files = in_memory_repository.list_documents()
# Assert
assert files == []
class TestFileDocumentRepositoryUpdate:
"""Tests for file document update functionality."""
def test_i_can_update_document_successfully(self, in_memory_repository, sample_file_document,
sample_update_data):
"""Test successful file document update."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
# Act
updated_file = in_memory_repository.update_document(str(created_file.id), sample_update_data)
# Assert
assert updated_file is not None
assert updated_file.extraction_method == sample_update_data["extraction_method"]
assert updated_file.metadata == sample_update_data["metadata"]
assert updated_file.file_size == sample_update_data["file_size"]
assert updated_file.id == created_file.id
assert updated_file.filename == created_file.filename # Unchanged fields remain
assert updated_file.filepath == created_file.filepath
def test_i_can_update_document_with_partial_data(self, in_memory_repository, sample_file_document):
"""Test updating file document with partial data."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
partial_update = {"file_size": 999999}
# Act
updated_file = in_memory_repository.update_document(str(created_file.id), partial_update)
# Assert
assert updated_file is not None
assert updated_file.file_size == 999999
assert updated_file.filename == created_file.filename # Should remain unchanged
assert updated_file.metadata == created_file.metadata # Should remain unchanged
def test_i_can_update_document_filtering_none_values(self, in_memory_repository, sample_file_document):
"""Test that None values are filtered out from update data."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
update_with_none = {"file_size": 777777, "metadata": None}
# Act
updated_file = in_memory_repository.update_document(str(created_file.id), update_with_none)
# Assert
assert updated_file is not None
assert updated_file.file_size == 777777
assert updated_file.metadata == created_file.metadata # Should remain unchanged (None filtered out)
def test_i_can_update_document_with_empty_data(self, in_memory_repository, sample_file_document):
"""Test updating file document with empty data returns current document."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
empty_update = {}
# Act
result = in_memory_repository.update_document(str(created_file.id), empty_update)
# Assert
assert result is not None
assert result.filename == created_file.filename
assert result.filepath == created_file.filepath
assert result.metadata == created_file.metadata
def test_i_cannot_update_document_with_invalid_id(self, in_memory_repository, sample_update_data):
"""Test that updating with invalid ID returns None."""
# Act
result = in_memory_repository.update_document("invalid_id", sample_update_data)
# Assert
assert result is None
def test_i_cannot_update_nonexistent_document(self, in_memory_repository, sample_update_data):
"""Test that updating nonexistent file document returns None."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
result = in_memory_repository.update_document(nonexistent_id, sample_update_data)
# Assert
assert result is None
def test_i_cannot_update_document_with_pymongo_error(self, in_memory_repository, sample_file_document,
sample_update_data, mocker):
"""Test handling of PyMongo errors during file document update."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
mocker.patch.object(in_memory_repository.collection, 'find_one_and_update',
side_effect=PyMongoError("Database error"))
# Act
result = in_memory_repository.update_document(str(created_file.id), sample_update_data)
# Assert
assert result is None
class TestFileDocumentRepositoryDeletion:
"""Tests for file document deletion functionality."""
def test_i_can_delete_existing_document(self, in_memory_repository, sample_file_document):
"""Test successful file document deletion."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
# Act
deletion_result = in_memory_repository.delete_document(str(created_file.id))
# Assert
assert deletion_result is True
# Verify document is actually deleted
found_file = in_memory_repository.find_document_by_id(str(created_file.id))
assert found_file is None
def test_i_cannot_delete_document_with_invalid_id(self, in_memory_repository):
"""Test that deleting with invalid ID returns False."""
# Act
result = in_memory_repository.delete_document("invalid_id")
# Assert
assert result is False
def test_i_cannot_delete_nonexistent_document(self, in_memory_repository):
"""Test that deleting nonexistent file document returns False."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
result = in_memory_repository.delete_document(nonexistent_id)
# Assert
assert result is False
def test_i_cannot_delete_document_with_pymongo_error(self, in_memory_repository, sample_file_document, mocker):
"""Test handling of PyMongo errors during file document deletion."""
# Arrange
created_file = in_memory_repository.create_document(sample_file_document)
mocker.patch.object(in_memory_repository.collection, 'delete_one', side_effect=PyMongoError("Database error"))
# Act
result = in_memory_repository.delete_document(str(created_file.id))
# Assert
assert result is False
class TestFileDocumentRepositoryUtilities:
"""Tests for utility methods."""
def test_i_can_count_documents(self, in_memory_repository, sample_file_document):
"""Test counting file documents."""
# Arrange
initial_count = in_memory_repository.count_documents()
in_memory_repository.create_document(sample_file_document)
# Act
final_count = in_memory_repository.count_documents()
# Assert
assert final_count == initial_count + 1
def test_i_can_count_zero_documents(self, in_memory_repository):
"""Test counting file documents in empty collection."""
# Act
count = in_memory_repository.count_documents()
# Assert
assert count == 0
def test_i_cannot_count_documents_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during file document counting."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'count_documents', side_effect=PyMongoError("Database error"))
# Act
count = in_memory_repository.count_documents()
# Assert
assert count == 0
class TestMatchingMethods:
"""Tests for matching method classes."""
def test_i_can_create_fuzzy_matching_with_default_threshold(self):
"""Test creating FuzzyMatching with default threshold."""
# Act
fuzzy = FuzzyMatching()
# Assert
assert fuzzy.threshold == 0.6
def test_i_can_create_fuzzy_matching_with_custom_threshold(self):
"""Test creating FuzzyMatching with custom threshold."""
# Act
fuzzy = FuzzyMatching(threshold=0.8)
# Assert
assert fuzzy.threshold == 0.8
def test_i_can_create_subsequence_matching(self):
"""Test creating SubsequenceMatching."""
# Act
subsequence = SubsequenceMatching()
# Assert
assert isinstance(subsequence, MatchMethodBase)
assert isinstance(subsequence, SubsequenceMatching)

496
tests/repositories/test_job_repository.py Normal file
View File

@@ -0,0 +1,496 @@
"""
Test suite for JobRepository with async/support.
This module contains comprehensive tests for all JobRepository methods
using mongomock-motor for in-memory MongoDB testing.
"""
from datetime import datetime
import pytest
from bson import ObjectId
from mongomock.mongo_client import MongoClient
from mongomock_motor import AsyncMongoMockClient
from pymongo.errors import PyMongoError
from app.database.repositories.job_repository import JobRepository
from app.exceptions.job_exceptions import JobRepositoryError
from app.models.job import ProcessingJob, ProcessingStatus
from app.models.types import PyObjectId
@pytest.fixture
def in_memory_repository():
"""Create an in-memory JobRepository for testing."""
client = MongoClient()
db = client.test_database
repo = JobRepository(db)
repo.initialize()
return repo
@pytest.fixture
def sample_document_id():
"""Sample document ObjectId for testing."""
return PyObjectId()
@pytest.fixture
def sample_task_id():
"""Sample Celery task ID for testing."""
return "celery-task-12345-abcde"
@pytest.fixture
def multiple_sample_jobs():
"""Multiple ProcessingJob objects for testing."""
doc_id_1 = ObjectId()
doc_id_2 = ObjectId()
base_time = datetime.utcnow()
return [
ProcessingJob(
document_id=doc_id_1,
status=ProcessingStatus.PENDING,
task_id="task-1",
created_at=base_time,
started_at=None,
completed_at=None,
error_message=None
),
ProcessingJob(
document_id=doc_id_2,
status=ProcessingStatus.PROCESSING,
task_id="task-2",
created_at=base_time,
started_at=base_time,
completed_at=None,
error_message=None
),
ProcessingJob(
document_id=doc_id_1,
status=ProcessingStatus.COMPLETED,
task_id="task-3",
created_at=base_time,
started_at=base_time,
completed_at=base_time,
error_message=None
)
]
class TestJobRepositoryInitialization:
"""Tests for repository initialization."""
def test_i_can_initialize_repository(self):
"""Test repository initialization."""
# Arrange
client = AsyncMongoMockClient()
db = client.test_database
repo = JobRepository(db)
# Act
initialized_repo = repo.initialize()
# Assert
assert initialized_repo is repo
assert repo.db is not None
assert repo.collection is not None
class TestJobRepositoryCreation:
"""Tests for job creation functionality."""
def test_i_can_create_job_with_task_id(self, in_memory_repository, sample_document_id, sample_task_id):
"""Test successful job creation with task ID."""
# Act
created_job = in_memory_repository.create_job(sample_document_id, sample_task_id)
# Assert
assert created_job is not None
assert created_job.document_id == sample_document_id
assert created_job.task_id == sample_task_id
assert created_job.status == ProcessingStatus.PENDING
assert created_job.created_at is not None
assert created_job.started_at is None
assert created_job.completed_at is None
assert created_job.error_message is None
assert created_job.id is not None
assert isinstance(created_job.id, ObjectId)
def test_i_can_create_job_without_task_id(self, in_memory_repository, sample_document_id):
"""Test successful job creation without task ID."""
# Act
created_job = in_memory_repository.create_job(sample_document_id)
# Assert
assert created_job is not None
assert created_job.document_id == sample_document_id
assert created_job.task_id is None
assert created_job.status == ProcessingStatus.PENDING
assert created_job.created_at is not None
assert created_job.started_at is None
assert created_job.completed_at is None
assert created_job.error_message is None
assert created_job.id is not None
assert isinstance(created_job.id, ObjectId)
def test_i_cannot_create_duplicate_job_for_document(self, in_memory_repository, sample_document_id,
sample_task_id):
"""Test that creating job with duplicate document_id raises DuplicateKeyError."""
# Arrange
in_memory_repository.create_job(sample_document_id, sample_task_id)
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.create_job(sample_document_id, "different-task-id")
assert "create_job" in str(exc_info.value)
def test_i_cannot_create_job_with_pymongo_error(self, in_memory_repository, sample_document_id, mocker):
"""Test handling of PyMongo errors during job creation."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'insert_one', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.create_job(sample_document_id)
assert "create_job" in str(exc_info.value)
class TestJobRepositoryFinding:
"""Tests for job finding functionality."""
def test_i_can_find_job_by_valid_id(self, in_memory_repository, sample_document_id, sample_task_id):
"""Test finding job by valid ObjectId."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id, sample_task_id)
# Act
found_job = in_memory_repository.find_job_by_id(created_job.id)
# Assert
assert found_job is not None
assert found_job.id == created_job.id
assert found_job.document_id == created_job.document_id
assert found_job.task_id == created_job.task_id
assert found_job.status == created_job.status
def test_i_cannot_find_job_by_nonexistent_id(self, in_memory_repository):
"""Test that nonexistent ObjectId returns None."""
# Arrange
nonexistent_id = PyObjectId()
# Act
found_job = in_memory_repository.find_job_by_id(nonexistent_id)
# Assert
assert found_job is None
def test_i_cannot_find_job_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during job finding."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find_one', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.find_job_by_id(PyObjectId())
assert "get_job_by_id" in str(exc_info.value)
def test_i_can_find_jobs_by_document_id(self, in_memory_repository, sample_document_id, sample_task_id):
"""Test finding jobs by document ID."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id, sample_task_id)
# Act
found_jobs = in_memory_repository.find_jobs_by_document_id(sample_document_id)
# Assert
assert len(found_jobs) == 1
assert found_jobs[0].id == created_job.id
assert found_jobs[0].document_id == sample_document_id
def test_i_can_find_empty_jobs_list_for_nonexistent_document(self, in_memory_repository):
"""Test that nonexistent document ID returns empty list."""
# Arrange
nonexistent_id = ObjectId()
# Act
found_jobs = in_memory_repository.find_jobs_by_document_id(nonexistent_id)
# Assert
assert found_jobs == []
def test_i_cannot_find_jobs_by_document_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during finding jobs by document ID."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.find_jobs_by_document_id(PyObjectId())
assert "get_jobs_by_file_id" in str(exc_info.value)
@pytest.mark.parametrize("status", [
ProcessingStatus.PENDING,
ProcessingStatus.PROCESSING,
ProcessingStatus.COMPLETED
])
def test_i_can_find_jobs_by_pending_status(self, in_memory_repository, sample_document_id, status):
"""Test finding jobs by PENDING status."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
in_memory_repository.update_job_status(created_job.id, status)
# Act
found_jobs = in_memory_repository.get_jobs_by_status(status)
# Assert
assert len(found_jobs) == 1
assert found_jobs[0].id == created_job.id
assert found_jobs[0].status == status
def test_i_can_find_jobs_by_failed_status(self, in_memory_repository, sample_document_id):
"""Test finding jobs by FAILED status."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
in_memory_repository.update_job_status(created_job.id, ProcessingStatus.FAILED, "Test error")
# Act
found_jobs = in_memory_repository.get_jobs_by_status(ProcessingStatus.FAILED)
# Assert
assert len(found_jobs) == 1
assert found_jobs[0].id == created_job.id
assert found_jobs[0].status == ProcessingStatus.FAILED
assert found_jobs[0].error_message == "Test error"
def test_i_can_find_empty_jobs_list_for_unused_status(self, in_memory_repository):
"""Test that unused status returns empty list."""
# Act
found_jobs = in_memory_repository.get_jobs_by_status(ProcessingStatus.COMPLETED)
# Assert
assert found_jobs == []
def test_i_cannot_find_jobs_by_status_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during finding jobs by status."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.get_jobs_by_status(ProcessingStatus.PENDING)
assert "get_jobs_by_status" in str(exc_info.value)
class TestJobRepositoryStatusUpdate:
"""Tests for job status update functionality."""
def test_i_can_update_job_status_to_processing(self, in_memory_repository, sample_document_id):
"""Test updating job status to PROCESSING with started_at timestamp."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
# Act
updated_job = in_memory_repository.update_job_status(created_job.id, ProcessingStatus.PROCESSING)
# Assert
assert updated_job is not None
assert updated_job.id == created_job.id
assert updated_job.status == ProcessingStatus.PROCESSING
assert updated_job.started_at is not None
assert updated_job.completed_at is None
assert updated_job.error_message is None
def test_i_can_update_job_status_to_completed(self, in_memory_repository, sample_document_id):
"""Test updating job status to COMPLETED with completed_at timestamp."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
in_memory_repository.update_job_status(created_job.id, ProcessingStatus.PROCESSING)
# Act
updated_job = in_memory_repository.update_job_status(created_job.id, ProcessingStatus.COMPLETED)
# Assert
assert updated_job is not None
assert updated_job.id == created_job.id
assert updated_job.status == ProcessingStatus.COMPLETED
assert updated_job.started_at is not None
assert updated_job.completed_at is not None
assert updated_job.error_message is None
def test_i_can_update_job_status_to_failed_with_error(self, in_memory_repository, sample_document_id):
"""Test updating job status to FAILED with error message and completed_at timestamp."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
error_message = "Processing failed due to invalid format"
# Act
updated_job = in_memory_repository.update_job_status(
created_job.id, ProcessingStatus.FAILED, error_message
)
# Assert
assert updated_job is not None
assert updated_job.id == created_job.id
assert updated_job.status == ProcessingStatus.FAILED
assert updated_job.completed_at is not None
assert updated_job.error_message == error_message
def test_i_can_update_job_status_to_failed_without_error(self, in_memory_repository, sample_document_id):
"""Test updating job status to FAILED without error message."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
# Act
updated_job = in_memory_repository.update_job_status(created_job.id, ProcessingStatus.FAILED)
# Assert
assert updated_job is not None
assert updated_job.id == created_job.id
assert updated_job.status == ProcessingStatus.FAILED
assert updated_job.completed_at is not None
assert updated_job.error_message is None
def test_i_cannot_update_nonexistent_job_status(self, in_memory_repository):
"""Test that updating nonexistent job returns None."""
# Arrange
nonexistent_id = ObjectId()
# Act
result = in_memory_repository.update_job_status(nonexistent_id, ProcessingStatus.COMPLETED)
# Assert
assert result is None
def test_i_cannot_update_job_status_with_pymongo_error(self, in_memory_repository, sample_document_id, mocker):
"""Test handling of PyMongo errors during job status update."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
mocker.patch.object(in_memory_repository.collection, 'find_one_and_update',
side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.update_job_status(created_job.id, ProcessingStatus.COMPLETED)
assert "update_job_status" in str(exc_info.value)
class TestJobRepositoryDeletion:
"""Tests for job deletion functionality."""
def test_i_can_delete_existing_job(self, in_memory_repository, sample_document_id):
"""Test successful job deletion."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
# Act
deletion_result = in_memory_repository.delete_job(created_job.id)
# Assert
assert deletion_result is True
# Verify job is actually deleted
found_job = in_memory_repository.find_job_by_id(created_job.id)
assert found_job is None
def test_i_cannot_delete_nonexistent_job(self, in_memory_repository):
"""Test that deleting nonexistent job returns False."""
# Arrange
nonexistent_id = ObjectId()
# Act
result = in_memory_repository.delete_job(nonexistent_id)
# Assert
assert result is False
def test_i_cannot_delete_job_with_pymongo_error(self, in_memory_repository, sample_document_id, mocker):
"""Test handling of PyMongo errors during job deletion."""
# Arrange
created_job = in_memory_repository.create_job(sample_document_id)
mocker.patch.object(in_memory_repository.collection, 'delete_one', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(JobRepositoryError) as exc_info:
in_memory_repository.delete_job(created_job.id)
assert "delete_job" in str(exc_info.value)
class TestJobRepositoryComplexScenarios:
"""Tests for complex job repository scenarios."""
def test_i_can_handle_complete_job_lifecycle(self, in_memory_repository, sample_document_id, sample_task_id):
"""Test complete job lifecycle from creation to completion."""
# Create job
job = in_memory_repository.create_job(sample_document_id, sample_task_id)
assert job.status == ProcessingStatus.PENDING
assert job.started_at is None
assert job.completed_at is None
# Start processing
job = in_memory_repository.update_job_status(job.id, ProcessingStatus.PROCESSING)
assert job.status == ProcessingStatus.PROCESSING
assert job.started_at is not None
assert job.completed_at is None
# Complete job
job = in_memory_repository.update_job_status(job.id, ProcessingStatus.COMPLETED)
assert job.status == ProcessingStatus.COMPLETED
assert job.started_at is not None
assert job.completed_at is not None
assert job.error_message is None
def test_i_can_handle_job_failure_scenario(self, in_memory_repository, sample_document_id, sample_task_id):
"""Test job failure scenario with error message."""
# Create and start job
job = in_memory_repository.create_job(sample_document_id, sample_task_id)
job = in_memory_repository.update_job_status(job.id, ProcessingStatus.PROCESSING)
# Fail job with error
error_msg = "File format not supported"
job = in_memory_repository.update_job_status(job.id, ProcessingStatus.FAILED, error_msg)
# Assert failure state
assert job.status == ProcessingStatus.FAILED
assert job.started_at is not None
assert job.completed_at is not None
assert job.error_message == error_msg
def test_i_can_handle_multiple_documents_with_different_statuses(self, in_memory_repository):
"""Test managing multiple jobs for different documents with various statuses."""
# Create jobs for different documents
doc1 = PyObjectId()
doc2 = PyObjectId()
doc3 = PyObjectId()
job1 = in_memory_repository.create_job(doc1, "task-1")
job2 = in_memory_repository.create_job(doc2, "task-2")
job3 = in_memory_repository.create_job(doc3, "task-3")
# Update to different statuses
in_memory_repository.update_job_status(job1.id, ProcessingStatus.PROCESSING)
in_memory_repository.update_job_status(job2.id, ProcessingStatus.COMPLETED)
in_memory_repository.update_job_status(job3.id, ProcessingStatus.FAILED, "Error occurred")
# Verify status queries
pending_jobs = in_memory_repository.get_jobs_by_status(ProcessingStatus.PENDING)
processing_jobs = in_memory_repository.get_jobs_by_status(ProcessingStatus.PROCESSING)
completed_jobs = in_memory_repository.get_jobs_by_status(ProcessingStatus.COMPLETED)
failed_jobs = in_memory_repository.get_jobs_by_status(ProcessingStatus.FAILED)
assert len(pending_jobs) == 0
assert len(processing_jobs) == 1
assert len(completed_jobs) == 1
assert len(failed_jobs) == 1
assert processing_jobs[0].id == job1.id
assert completed_jobs[0].id == job2.id
assert failed_jobs[0].id == job3.id

134
tests/test_user_repository.py → tests/repositories/test_user_repository.py
View File

@@ -1,29 +1,26 @@
"""
Test suite for UserRepository with async/await support.
Test suite for UserRepository with async/support.
This module contains comprehensive tests for all UserRepository methods
using mongomock-motor for in-memory MongoDB testing.
"""
import pytest
from datetime import datetime
import pytest_asyncio
from bson import ObjectId
from mongomock.mongo_client import MongoClient
from pymongo.errors import DuplicateKeyError
from mongomock_motor import AsyncMongoMockClient
from app.database.repositories.user_repository import UserRepository
from app.models.user import UserCreate, UserUpdate, UserInDB
from app.models.user import UserCreate, UserUpdate
@pytest_asyncio.fixture
async def in_memory_repository():
@pytest.fixture
def in_memory_repository():
"""Create an in-memory UserRepository for testing."""
client = AsyncMongoMockClient()
client = MongoClient()
db = client.test_database
repo = UserRepository(db)
await repo.initialize()
repo.initialize()
return repo
@@ -51,11 +48,10 @@ def sample_user_update():
class TestUserRepositoryCreation:
"""Tests for user creation functionality."""
@pytest.mark.asyncio
async def test_i_can_create_user(self, in_memory_repository, sample_user_create):
def test_i_can_create_user(self, in_memory_repository, sample_user_create):
"""Test successful user creation."""
# Act
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
# Assert
assert created_user is not None
@@ -68,15 +64,14 @@ class TestUserRepositoryCreation:
assert created_user.updated_at is not None
assert created_user.hashed_password != sample_user_create.password # Should be hashed
@pytest.mark.asyncio
async def test_i_cannot_create_user_with_duplicate_username(self, in_memory_repository, sample_user_create):
def test_i_cannot_create_user_with_duplicate_username(self, in_memory_repository, sample_user_create):
"""Test that creating user with duplicate username raises DuplicateKeyError."""
# Arrange
await in_memory_repository.create_user(sample_user_create)
in_memory_repository.create_user(sample_user_create)
# Act & Assert
with pytest.raises(DuplicateKeyError) as exc_info:
await in_memory_repository.create_user(sample_user_create)
in_memory_repository.create_user(sample_user_create)
assert "already exists" in str(exc_info.value)
@@ -84,14 +79,13 @@ class TestUserRepositoryCreation:
class TestUserRepositoryFinding:
"""Tests for user finding functionality."""
@pytest.mark.asyncio
async def test_i_can_find_user_by_id(self, in_memory_repository, sample_user_create):
def test_i_can_find_user_by_id(self, in_memory_repository, sample_user_create):
"""Test finding user by valid ID."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
# Act
found_user = await in_memory_repository.find_user_by_id(str(created_user.id))
found_user = in_memory_repository.find_user_by_id(str(created_user.id))
# Assert
assert found_user is not None
@@ -99,69 +93,63 @@ class TestUserRepositoryFinding:
assert found_user.username == created_user.username
assert found_user.email == created_user.email
@pytest.mark.asyncio
async def test_i_cannot_find_user_by_invalid_id(self, in_memory_repository):
def test_i_cannot_find_user_by_invalid_id(self, in_memory_repository):
"""Test that invalid ObjectId returns None."""
# Act
found_user = await in_memory_repository.find_user_by_id("invalid_id")
found_user = in_memory_repository.find_user_by_id("invalid_id")
# Assert
assert found_user is None
@pytest.mark.asyncio
async def test_i_cannot_find_user_by_nonexistent_id(self, in_memory_repository):
def test_i_cannot_find_user_by_nonexistent_id(self, in_memory_repository):
"""Test that nonexistent but valid ObjectId returns None."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
found_user = await in_memory_repository.find_user_by_id(nonexistent_id)
found_user = in_memory_repository.find_user_by_id(nonexistent_id)
# Assert
assert found_user is None
@pytest.mark.asyncio
async def test_i_can_find_user_by_username(self, in_memory_repository, sample_user_create):
def test_i_can_find_user_by_username(self, in_memory_repository, sample_user_create):
"""Test finding user by username."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
# Act
found_user = await in_memory_repository.find_user_by_username(sample_user_create.username)
found_user = in_memory_repository.find_user_by_username(sample_user_create.username)
# Assert
assert found_user is not None
assert found_user.username == created_user.username
assert found_user.id == created_user.id
@pytest.mark.asyncio
async def test_i_cannot_find_user_by_nonexistent_username(self, in_memory_repository):
def test_i_cannot_find_user_by_nonexistent_username(self, in_memory_repository):
"""Test that nonexistent username returns None."""
# Act
found_user = await in_memory_repository.find_user_by_username("nonexistent")
found_user = in_memory_repository.find_user_by_username("nonexistent")
# Assert
assert found_user is None
@pytest.mark.asyncio
async def test_i_can_find_user_by_email(self, in_memory_repository, sample_user_create):
def test_i_can_find_user_by_email(self, in_memory_repository, sample_user_create):
"""Test finding user by email."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
# Act
found_user = await in_memory_repository.find_user_by_email(str(sample_user_create.email))
found_user = in_memory_repository.find_user_by_email(str(sample_user_create.email))
# Assert
assert found_user is not None
assert found_user.email == created_user.email
assert found_user.id == created_user.id
@pytest.mark.asyncio
async def test_i_cannot_find_user_by_nonexistent_email(self, in_memory_repository):
def test_i_cannot_find_user_by_nonexistent_email(self, in_memory_repository):
"""Test that nonexistent email returns None."""
# Act
found_user = await in_memory_repository.find_user_by_email("nonexistent@example.com")
found_user = in_memory_repository.find_user_by_email("nonexistent@example.com")
# Assert
assert found_user is None
@@ -170,15 +158,14 @@ class TestUserRepositoryFinding:
class TestUserRepositoryUpdate:
"""Tests for user update functionality."""
@pytest.mark.asyncio
async def test_i_can_update_user(self, in_memory_repository, sample_user_create, sample_user_update):
def test_i_can_update_user(self, in_memory_repository, sample_user_create, sample_user_update):
"""Test successful user update."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
original_updated_at = created_user.updated_at
# Act
updated_user = await in_memory_repository.update_user(str(created_user.id), sample_user_update)
updated_user = in_memory_repository.update_user(str(created_user.id), sample_user_update)
# Assert
assert updated_user is not None
@@ -187,24 +174,22 @@ class TestUserRepositoryUpdate:
assert updated_user.role == sample_user_update.role
assert updated_user.id == created_user.id
@pytest.mark.asyncio
async def test_i_cannot_update_user_with_invalid_id(self, in_memory_repository, sample_user_update):
def test_i_cannot_update_user_with_invalid_id(self, in_memory_repository, sample_user_update):
"""Test that updating with invalid ID returns None."""
# Act
result = await in_memory_repository.update_user("invalid_id", sample_user_update)
result = in_memory_repository.update_user("invalid_id", sample_user_update)
# Assert
assert result is None
@pytest.mark.asyncio
async def test_i_can_update_user_with_partial_data(self, in_memory_repository, sample_user_create):
def test_i_can_update_user_with_partial_data(self, in_memory_repository, sample_user_create):
"""Test updating user with partial data."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
partial_update = UserUpdate(username="newusername")
# Act
updated_user = await in_memory_repository.update_user(str(created_user.id), partial_update)
updated_user = in_memory_repository.update_user(str(created_user.id), partial_update)
# Assert
assert updated_user is not None
@@ -212,15 +197,14 @@ class TestUserRepositoryUpdate:
assert updated_user.email == created_user.email # Should remain unchanged
assert updated_user.role == created_user.role # Should remain unchanged
@pytest.mark.asyncio
async def test_i_can_update_user_with_empty_data(self, in_memory_repository, sample_user_create):
def test_i_can_update_user_with_empty_data(self, in_memory_repository, sample_user_create):
"""Test updating user with empty data returns current user."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
empty_update = UserUpdate()
# Act
result = await in_memory_repository.update_user(str(created_user.id), empty_update)
result = in_memory_repository.update_user(str(created_user.id), empty_update)
# Assert
assert result is not None
@@ -231,39 +215,36 @@ class TestUserRepositoryUpdate:
class TestUserRepositoryDeletion:
"""Tests for user deletion functionality."""
@pytest.mark.asyncio
async def test_i_can_delete_user(self, in_memory_repository, sample_user_create):
def test_i_can_delete_user(self, in_memory_repository, sample_user_create):
"""Test successful user deletion."""
# Arrange
created_user = await in_memory_repository.create_user(sample_user_create)
created_user = in_memory_repository.create_user(sample_user_create)
# Act
deletion_result = await in_memory_repository.delete_user(str(created_user.id))
deletion_result = in_memory_repository.delete_user(str(created_user.id))
# Assert
assert deletion_result is True
# Verify user is actually deleted
found_user = await in_memory_repository.find_user_by_id(str(created_user.id))
found_user = in_memory_repository.find_user_by_id(str(created_user.id))
assert found_user is None
@pytest.mark.asyncio
async def test_i_cannot_delete_user_with_invalid_id(self, in_memory_repository):
def test_i_cannot_delete_user_with_invalid_id(self, in_memory_repository):
"""Test that deleting with invalid ID returns False."""
# Act
result = await in_memory_repository.delete_user("invalid_id")
result = in_memory_repository.delete_user("invalid_id")
# Assert
assert result is False
@pytest.mark.asyncio
async def test_i_cannot_delete_nonexistent_user(self, in_memory_repository):
def test_i_cannot_delete_nonexistent_user(self, in_memory_repository):
"""Test that deleting nonexistent user returns False."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
result = await in_memory_repository.delete_user(nonexistent_id)
result = in_memory_repository.delete_user(nonexistent_id)
# Assert
assert result is False
@@ -272,30 +253,27 @@ class TestUserRepositoryDeletion:
class TestUserRepositoryUtilities:
"""Tests for utility methods."""
@pytest.mark.asyncio
async def test_i_can_count_users(self, in_memory_repository, sample_user_create):
def test_i_can_count_users(self, in_memory_repository, sample_user_create):
"""Test counting users."""
# Arrange
initial_count = await in_memory_repository.count_users()
await in_memory_repository.create_user(sample_user_create)
initial_count = in_memory_repository.count_users()
in_memory_repository.create_user(sample_user_create)
# Act
final_count = await in_memory_repository.count_users()
final_count = in_memory_repository.count_users()
# Assert
assert final_count == initial_count + 1
@pytest.mark.asyncio
async def test_i_can_check_user_exists(self, in_memory_repository, sample_user_create):
def test_i_can_check_user_exists(self, in_memory_repository, sample_user_create):
"""Test checking if user exists."""
# Arrange
await in_memory_repository.create_user(sample_user_create)
in_memory_repository.create_user(sample_user_create)
# Act
exists = await in_memory_repository.user_exists(sample_user_create.username)
not_exists = await in_memory_repository.user_exists("nonexistent")
exists = in_memory_repository.user_exists(sample_user_create.username)
not_exists = in_memory_repository.user_exists("nonexistent")
# Assert
assert exists is True
assert not_exists is False

0
tests/services/__init__.py Normal file
View File

570
tests/services/test_document_service.py Normal file
View File

@@ -0,0 +1,570 @@
"""
Unit tests for DocumentService using in-memory MongoDB.
Tests the orchestration logic with real MongoDB operations
using mongomock for better integration testing.
"""
import os
from datetime import datetime
from unittest.mock import patch
import pytest
import pytest_asyncio
from bson import ObjectId
from mongomock.mongo_client import MongoClient
from app.models.document import FileType
from app.services.document_service import DocumentService
@pytest.fixture(autouse=True)
def cleanup_test_folder():
"""Clean up test folder."""
import shutil
shutil.rmtree("test_folder", ignore_errors=True)
@pytest.fixture
def in_memory_database():
"""Create an in-memory database for testing."""
client = MongoClient()
return client.test_database
@pytest_asyncio.fixture
def document_service(in_memory_database):
"""Create DocumentService with in-memory repositories."""
service = DocumentService(in_memory_database, objects_folder="test_folder")
return service
@pytest.fixture
def sample_file_bytes():
"""Sample file content as bytes."""
return b"This is a test PDF content"
@pytest.fixture
def sample_text_bytes():
"""Sample text file content as bytes."""
return b"This is a test text file content"
@pytest.fixture
def sample_file_hash():
"""Expected SHA256 hash for sample file bytes."""
import hashlib
return hashlib.sha256(b"This is a test PDF content").hexdigest()
def validate_file_saved(document_service, file_hash, file_bytes):
# Verify file is saved to disk
target_file_path = os.path.join(document_service.objects_folder, file_hash[:24], file_hash)
assert os.path.exists(target_file_path)
with open(target_file_path, "rb") as f:
content = f.read()
assert content == file_bytes
class TestCreateDocument:
"""Tests for create_document method."""
@patch('app.services.document_service.magic.from_buffer')
@patch('app.services.document_service.datetime')
def test_i_can_create_document_with_new_content(
self,
mock_datetime,
mock_magic,
document_service,
sample_file_bytes
):
"""Test creating document when content doesn't exist yet."""
# Setup mocks
fixed_time = datetime(2025, 1, 1, 10, 30, 0)
mock_datetime.now.return_value = fixed_time
mock_magic.return_value = "application/pdf"
# Execute
result = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Verify document creation
assert result is not None
assert result.filename == "test.pdf"
assert result.filepath == "/test/test.pdf"
assert result.file_type == FileType.PDF
assert result.detected_at == fixed_time
assert result.file_hash == document_service._calculate_file_hash(sample_file_bytes)
# Verify document created in database
doc_in_db = document_service.document_repository.find_document_by_id(result.id)
assert doc_in_db is not None
assert doc_in_db.id == result.id
assert doc_in_db.filename == result.filename
assert doc_in_db.filepath == result.filepath
assert doc_in_db.file_type == result.file_type
assert doc_in_db.detected_at == fixed_time
assert doc_in_db.file_hash == result.file_hash
# Verify file is saved to disk
validate_file_saved(document_service, result.file_hash, sample_file_bytes)
@patch('app.services.document_service.magic.from_buffer')
@patch('app.services.document_service.datetime')
def test_i_can_create_document_with_existing_content(
self,
mock_datetime,
mock_magic,
document_service,
sample_file_bytes
):
"""Test creating document when content already exists (deduplication)."""
# Setup mocks
fixed_time = datetime(2025, 1, 1, 10, 30, 0)
mock_datetime.now.return_value = fixed_time
mock_magic.return_value = "application/pdf"
# Create first document
first_doc = document_service.create_document(
"/test/first.pdf",
sample_file_bytes,
"utf-8"
)
# Create second document with same content
second_doc = document_service.create_document(
"/test/second.pdf",
sample_file_bytes,
"utf-8"
)
# Verify both documents exist but share same hash
assert first_doc.file_hash == second_doc.file_hash
assert first_doc.filename != second_doc.filename
assert first_doc.filepath != second_doc.filepath
def test_i_cannot_create_document_with_unsupported_file_type(
self,
document_service,
sample_file_bytes
):
"""Test that unsupported file types raise ValueError."""
with pytest.raises(ValueError, match="Unsupported file type"):
document_service.create_document(
"/test/test.xyz", # Unsupported extension
sample_file_bytes,
"utf-8"
)
def test_i_cannot_create_document_with_empty_file_path(
self,
document_service,
sample_file_bytes
):
"""Test that empty file path raises ValueError."""
with pytest.raises(ValueError):
document_service.create_document(
"", # Empty path
sample_file_bytes,
"utf-8"
)
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_create_document_with_empty_bytes(
self,
mock_magic,
document_service
):
"""Test behavior with empty file bytes."""
# Setup
mock_magic.return_value = "text/plain"
# Execute with empty bytes
result = document_service.create_document(
"/test/empty.txt",
b"", # Empty bytes
"utf-8"
)
# Verify file is saved to disk
validate_file_saved(document_service, result.file_hash, b"")
class TestGetMethods:
"""Tests for document retrieval methods."""
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_get_document_by_id(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document by ID."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute
result = document_service.get_document_by_id(created_doc.id)
# Verify
assert result is not None
assert result.id == created_doc.id
assert result.filename == created_doc.filename
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_get_document_by_hash(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document by file hash."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute
result = document_service.get_document_by_hash(created_doc.file_hash)
# Verify
assert result is not None
assert result.file_hash == created_doc.file_hash
assert result.filename == created_doc.filename
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_get_document_by_filepath(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document by file path."""
# Setup
mock_magic.return_value = "application/pdf"
test_path = "/test/unique_test.pdf"
# Create a document first
created_doc = document_service.create_document(
test_path,
sample_file_bytes,
"utf-8"
)
# Execute
result = document_service.get_document_by_filepath(test_path)
# Verify
assert result is not None
assert result.filepath == test_path
assert result.id == created_doc.id
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_get_document_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document with associated content."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute
result = document_service.get_document_content_by_hash(created_doc.file_hash)
# Verify
assert result == sample_file_bytes
def test_i_cannot_get_nonexistent_document_by_id(
self,
document_service
):
"""Test that nonexistent document returns None."""
# Execute with random ObjectId
result = document_service.get_document_by_id(ObjectId())
# Verify
assert result is None
def test_i_cannot_get_nonexistent_document_by_hash(
self,
document_service
):
"""Test that nonexistent document hash returns None."""
# Execute
result = document_service.get_document_by_hash("nonexistent_hash")
# Verify
assert result is None
class TestPaginationAndCounting:
"""Tests for document listing and counting."""
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_list_documents_with_pagination(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test document listing with pagination parameters."""
# Setup
mock_magic.return_value = "application/pdf"
# Create multiple documents
for i in range(5):
document_service.create_document(
f"/test/test{i}.pdf",
sample_file_bytes + bytes(str(i), 'utf-8'), # Make each file unique
"utf-8"
)
# Execute with pagination
result = document_service.list_documents(skip=1, limit=2)
# Verify
assert len(result) == 2
# Test counting
total_count = document_service.count_documents()
assert total_count == 5
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_count_documents(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test document counting."""
# Setup
mock_magic.return_value = "text/plain"
# Initially should be 0
initial_count = document_service.count_documents()
assert initial_count == 0
# Create some documents
for i in range(3):
document_service.create_document(
f"/test/test{i}.txt",
sample_file_bytes + bytes(str(i), 'utf-8'),
"utf-8"
)
# Execute
final_count = document_service.count_documents()
# Verify
assert final_count == 3
class TestUpdateAndDelete:
"""Tests for document update and deletion operations."""
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_update_document_metadata(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test updating document metadata."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute update
update_data = {"metadata": {"page_count": 5}}
result = document_service.update_document(created_doc.id, update_data)
# Verify
assert result is not None
assert result.metadata.get("page_count") == 5
assert result.filename == created_doc.filename
assert result.filepath == created_doc.filepath
assert result.file_hash == created_doc.file_hash
assert result.file_type == created_doc.file_type
assert result.metadata == update_data['metadata']
def test_i_can_update_document_content(
self,
document_service,
sample_file_bytes
):
# Create a document first
created_doc = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute update
update_data = {"file_bytes": b"this is an updated file content"}
result = document_service.update_document(created_doc.id, update_data)
assert result.filename == created_doc.filename
assert result.filepath == created_doc.filepath
assert result.file_hash != created_doc.file_hash
assert result.file_type == created_doc.file_type
assert result.metadata == created_doc.metadata
# Verify file is saved to disk
validate_file_saved(document_service, result.file_hash, b"this is an updated file content")
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_delete_document_and_orphaned_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test deleting document with orphaned content cleanup."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document
created_doc = document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Verify content exists
validate_file_saved(document_service, created_doc.file_hash, sample_file_bytes)
# Execute deletion
result = document_service.delete_document(created_doc.id)
# Verify document and content are deleted
assert result is True
deleted_doc = document_service.get_document_by_id(created_doc.id)
assert deleted_doc is None
# validate content is deleted
file_hash = created_doc.file_hash[:24]
target_file_path = os.path.join(document_service.objects_folder, file_hash[:24], file_hash)
assert not os.path.exists(target_file_path)
@patch('app.services.document_service.magic.from_buffer')
def test_i_can_delete_document_without_affecting_shared_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test deleting document without removing shared content."""
# Setup
mock_magic.return_value = "application/pdf"
# Create two documents with same content
doc1 = document_service.create_document(
"/test/test1.pdf",
sample_file_bytes,
"utf-8"
)
doc2 = document_service.create_document(
"/test/test2.pdf",
sample_file_bytes,
"utf-8"
)
# They should share the same hash
assert doc1.file_hash == doc2.file_hash
# Delete first document
result = document_service.delete_document(doc1.id)
assert result is True
# Verify first document is deleted but content still exists
deleted_doc = document_service.get_document_by_id(doc1.id)
assert deleted_doc is None
remaining_doc = document_service.get_document_by_id(doc2.id)
assert remaining_doc is not None
validate_file_saved(document_service, doc2.file_hash, sample_file_bytes)
class TestHashCalculation:
"""Tests for file hash calculation utility."""
def test_i_can_calculate_consistent_file_hash(self, document_service):
"""Test that file hash calculation is consistent."""
test_bytes = b"Test content for hashing"
# Calculate hash multiple times
hash1 = document_service._calculate_file_hash(test_bytes)
hash2 = document_service._calculate_file_hash(test_bytes)
# Should be identical
assert hash1 == hash2
assert len(hash1) == 64 # SHA256 produces 64-character hex string
def test_i_get_different_hashes_for_different_content(self, document_service):
"""Test that different content produces different hashes."""
content1 = b"First content"
content2 = b"Second content"
hash1 = document_service._calculate_file_hash(content1)
hash2 = document_service._calculate_file_hash(content2)
assert hash1 != hash2
class TestFileTypeDetection:
"""Tests for file type detection."""
def test_i_can_detect_pdf_file_type(self, document_service):
"""Test PDF file type detection."""
file_type = document_service._detect_file_type("/path/to/document.pdf")
assert file_type == FileType.PDF
def test_i_can_detect_txt_file_type(self, document_service):
"""Test text file type detection."""
file_type = document_service._detect_file_type("/path/to/document.txt")
assert file_type == FileType.TXT
def test_i_can_detect_docx_file_type(self, document_service):
"""Test DOCX file type detection."""
file_type = document_service._detect_file_type("/path/to/document.docx")
assert file_type == FileType.DOCX
def test_i_cannot_detect_unsupported_file_type(self, document_service):
"""Test unsupported file type raises ValueError."""
with pytest.raises(ValueError, match="Unsupported file type"):
document_service._detect_file_type("/path/to/document.xyz")

518
tests/services/test_job_service.py Normal file
View File

@@ -0,0 +1,518 @@
"""
Unit tests for JobService using in-memory MongoDB.
Tests the business logic operations with real MongoDB operations
using mongomock for better integration testing.
"""
import pytest
from bson import ObjectId
from mongomock.mongo_client import MongoClient
from app.exceptions.job_exceptions import InvalidStatusTransitionError
from app.models.job import ProcessingStatus
from app.models.types import PyObjectId
from app.services.job_service import JobService
@pytest.fixture
def in_memory_database():
"""Create an in-memory database for testing."""
client = MongoClient()
return client.test_database
@pytest.fixture
def job_service(in_memory_database):
"""Create JobService with in-memory repositories."""
service = JobService(in_memory_database).initialize()
return service
@pytest.fixture
def sample_document_id():
"""Sample file ObjectId."""
return PyObjectId()
@pytest.fixture
def sample_task_id():
"""Sample Celery task UUID."""
return "550e8400-e29b-41d4-a716-446655440000"
class TestCreateJob:
"""Tests for create_job method."""
def test_i_can_create_job_with_task_id(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test creating job with task ID."""
# Execute
result = job_service.create_job(sample_document_id, sample_task_id)
# Verify job creation
assert result is not None
assert result.document_id == sample_document_id
assert result.task_id == sample_task_id
assert result.status == ProcessingStatus.PENDING
assert result.created_at is not None
assert result.started_at is None
assert result.error_message is None
# Verify job exists in database
job_in_db = job_service.get_job_by_id(result.id)
assert job_in_db is not None
assert job_in_db.id == result.id
assert job_in_db.document_id == sample_document_id
assert job_in_db.task_id == sample_task_id
assert job_in_db.status == ProcessingStatus.PENDING
def test_i_can_create_job_without_task_id(
self,
job_service,
sample_document_id
):
"""Test creating job without task ID."""
# Execute
result = job_service.create_job(sample_document_id)
# Verify job creation
assert result is not None
assert result.document_id == sample_document_id
assert result.task_id is None
assert result.status == ProcessingStatus.PENDING
assert result.created_at is not None
assert result.started_at is None
assert result.error_message is None
class TestGetJobMethods:
"""Tests for job retrieval methods."""
def test_i_can_get_job_by_id(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test retrieving job by ID."""
# Create a job first
created_job = job_service.create_job(sample_document_id, sample_task_id)
# Execute
result = job_service.get_job_by_id(created_job.id)
# Verify
assert result is not None
assert result.id == created_job.id
assert result.document_id == created_job.document_id
assert result.task_id == created_job.task_id
assert result.status == created_job.status
def test_i_can_get_jobs_by_status(
self,
job_service,
sample_document_id
):
"""Test retrieving jobs by status."""
# Create jobs with different statuses
pending_job = job_service.create_job(sample_document_id, "pending-task")
processing_job = job_service.create_job(ObjectId(), "processing-task")
job_service.mark_job_as_started(processing_job.id)
completed_job = job_service.create_job(ObjectId(), "completed-task")
job_service.mark_job_as_started(completed_job.id)
job_service.mark_job_as_completed(completed_job.id)
# Execute - get pending jobs
pending_results = job_service.get_jobs_by_status(ProcessingStatus.PENDING)
# Verify
assert len(pending_results) == 1
assert pending_results[0].id == pending_job.id
assert pending_results[0].status == ProcessingStatus.PENDING
# Execute - get processing jobs
processing_results = job_service.get_jobs_by_status(ProcessingStatus.PROCESSING)
assert len(processing_results) == 1
assert processing_results[0].status == ProcessingStatus.PROCESSING
# Execute - get completed jobs
completed_results = job_service.get_jobs_by_status(ProcessingStatus.COMPLETED)
assert len(completed_results) == 1
assert completed_results[0].status == ProcessingStatus.COMPLETED
class TestUpdateStatus:
"""Tests for mark_job_as_started method."""
def test_i_can_mark_pending_job_as_started(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test marking pending job as started (PENDING → PROCESSING)."""
# Create a pending job
created_job = job_service.create_job(sample_document_id, sample_task_id)
assert created_job.status == ProcessingStatus.PENDING
# Execute
result = job_service.mark_job_as_started(created_job.id)
# Verify status transition
assert result is not None
assert result.id == created_job.id
assert result.status == ProcessingStatus.PROCESSING
# Verify in database
updated_job = job_service.get_job_by_id(created_job.id)
assert updated_job.status == ProcessingStatus.PROCESSING
def test_i_cannot_mark_processing_job_as_started(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that processing job cannot be marked as started."""
# Create and start a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
job_service.mark_job_as_started(created_job.id)
# Try to start it again
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_started(created_job.id)
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.PROCESSING
assert exc_info.value.target_status == ProcessingStatus.PROCESSING
def test_i_cannot_mark_completed_job_as_started(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that completed job cannot be marked as started."""
# Create, start, and complete a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
job_service.mark_job_as_started(created_job.id)
job_service.mark_job_as_completed(created_job.id)
# Try to start it again
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_started(created_job.id)
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.COMPLETED
assert exc_info.value.target_status == ProcessingStatus.PROCESSING
def test_i_cannot_mark_failed_job_as_started(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that failed job cannot be marked as started."""
# 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)
job_service.mark_job_as_failed(created_job.id, "Test error")
# Try to start it again
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_started(created_job.id)
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.FAILED
assert exc_info.value.target_status == ProcessingStatus.PROCESSING
def test_i_can_mark_processing_job_as_completed(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test marking processing job as completed (PROCESSING → COMPLETED)."""
# Create and start a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
started_job = job_service.mark_job_as_started(created_job.id)
# Execute
result = job_service.mark_job_as_completed(created_job.id)
# Verify status transition
assert result is not None
assert result.id == created_job.id
assert result.status == ProcessingStatus.COMPLETED
# Verify in database
updated_job = job_service.get_job_by_id(created_job.id)
assert updated_job.status == ProcessingStatus.COMPLETED
def test_i_cannot_mark_pending_job_as_completed(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that pending job cannot be marked as completed."""
# Create a pending job
created_job = job_service.create_job(sample_document_id, sample_task_id)
# Try to complete it directly
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_completed(created_job.id)
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.PENDING
assert exc_info.value.target_status == ProcessingStatus.COMPLETED
def test_i_cannot_mark_completed_job_as_completed(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that completed job cannot be marked as completed again."""
# Create, start, and complete a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
job_service.mark_job_as_started(created_job.id)
job_service.mark_job_as_completed(created_job.id)
# Try to complete it again
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_completed(created_job.id)
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.COMPLETED
assert exc_info.value.target_status == ProcessingStatus.COMPLETED
def test_i_cannot_mark_failed_job_as_completed(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that failed job cannot be marked as completed."""
# 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)
job_service.mark_job_as_failed(created_job.id, "Test error")
# Try to complete it
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_completed(created_job.id)
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.FAILED
assert exc_info.value.target_status == ProcessingStatus.COMPLETED
def test_i_can_mark_processing_job_as_failed_with_error_message(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test marking processing job as failed with error message."""
# Create and start a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
started_job = job_service.mark_job_as_started(created_job.id)
error_message = "Processing failed due to invalid file format"
# Execute
result = job_service.mark_job_as_failed(created_job.id, error_message)
# Verify status transition
assert result is not None
assert result.id == created_job.id
assert result.status == ProcessingStatus.FAILED
assert result.error_message == error_message
# Verify in database
updated_job = job_service.get_job_by_id(created_job.id)
assert updated_job.status == ProcessingStatus.FAILED
assert updated_job.error_message == error_message
def test_i_can_mark_processing_job_as_failed_without_error_message(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test marking processing job as failed without error message."""
# Create and start 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.mark_job_as_failed(created_job.id)
# Verify status transition
assert result is not None
assert result.status == ProcessingStatus.FAILED
assert result.error_message is None
def test_i_cannot_mark_pending_job_as_failed(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that pending job cannot be marked as failed."""
# Create a pending job
created_job = job_service.create_job(sample_document_id, sample_task_id)
# Try to fail it directly
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_failed(created_job.id, "Test error")
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.PENDING
assert exc_info.value.target_status == ProcessingStatus.FAILED
def test_i_cannot_mark_completed_job_as_failed(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test that completed job cannot be marked as failed."""
# Create, start, and complete a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
job_service.mark_job_as_started(created_job.id)
job_service.mark_job_as_completed(created_job.id)
# Try to fail it
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_failed(created_job.id, "Test error")
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.COMPLETED
assert exc_info.value.target_status == ProcessingStatus.FAILED
def test_i_cannot_mark_failed_job_as_failed(
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)
job_service.mark_job_as_failed(created_job.id, "First error")
# Try to fail it again
with pytest.raises(InvalidStatusTransitionError) as exc_info:
job_service.mark_job_as_failed(created_job.id, "Second error")
# Verify exception details
assert exc_info.value.current_status == ProcessingStatus.FAILED
assert exc_info.value.target_status == ProcessingStatus.FAILED
class TestDeleteJob:
"""Tests for delete_job method."""
def test_i_can_delete_existing_job(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test deleting an existing job."""
# Create a job
created_job = job_service.create_job(sample_document_id, sample_task_id)
# Verify job exists
job_before_delete = job_service.get_job_by_id(created_job.id)
assert job_before_delete is not None
# Execute deletion
result = job_service.delete_job(created_job.id)
# Verify deletion
assert result is True
# Verify job no longer exists
deleted_job = job_service.get_job_by_id(created_job.id)
assert deleted_job is None
def test_i_cannot_delete_nonexistent_job(
self,
job_service
):
"""Test deleting a nonexistent job returns False."""
# Execute deletion with random ObjectId
result = job_service.delete_job(ObjectId())
# Verify
assert result is False
class TestStatusTransitionValidation:
"""Tests for status transition validation across different scenarios."""
def test_valid_job_lifecycle_flow(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test complete valid job lifecycle: PENDING → PROCESSING → COMPLETED."""
# Create job (PENDING)
job = job_service.create_job(sample_document_id, sample_task_id)
assert job.status == ProcessingStatus.PENDING
# Start job (PENDING → PROCESSING)
started_job = job_service.mark_job_as_started(job.id)
assert started_job.status == ProcessingStatus.PROCESSING
# Complete job (PROCESSING → COMPLETED)
completed_job = job_service.mark_job_as_completed(job.id)
assert completed_job.status == ProcessingStatus.COMPLETED
def test_valid_job_failure_flow(
self,
job_service,
sample_document_id,
sample_task_id
):
"""Test valid job failure: PENDING → PROCESSING → FAILED."""
# Create job (PENDING)
job = job_service.create_job(sample_document_id, sample_task_id)
assert job.status == ProcessingStatus.PENDING
# Start job (PENDING → PROCESSING)
started_job = job_service.mark_job_as_started(job.id)
assert started_job.status == ProcessingStatus.PROCESSING
# Fail job (PROCESSING → FAILED)
failed_job = job_service.mark_job_as_failed(job.id, "Test failure")
assert failed_job.status == ProcessingStatus.FAILED
assert failed_job.error_message == "Test failure"
def test_job_operations_with_empty_database(
self,
job_service
):
"""Test job operations when database is empty."""
# Try to get nonexistent job
result = job_service.get_job_by_id(ObjectId())
assert result is None
# Try to get jobs by status when none exist
pending_jobs = job_service.get_jobs_by_status(ProcessingStatus.PENDING)
assert pending_jobs == []
# Try to delete nonexistent job
delete_result = job_service.delete_job(ObjectId())
assert delete_result is False

187
tests/test_connection.py
View File

@@ -1,187 +0,0 @@
"""
Unit tests for MongoDB database connection module.
Tests the database connection functionality with mocking
to avoid requiring actual MongoDB instance during tests.
"""
import pytest
from unittest.mock import Mock, patch, MagicMock
from pymongo.errors import ConnectionFailure, ServerSelectionTimeoutError
from app.database.connection import (
create_mongodb_client,
get_database,
close_database_connection,
get_mongodb_client,
test_database_connection
)
def test_i_can_get_database_connection():
"""Test successful database connection creation."""
mock_client = Mock()
mock_database = Mock()
# Configure the mock to support dictionary-like access
mock_client.__getitem__ = Mock(return_value=mock_database)
with patch('app.database.connection.MongoClient', return_value=mock_client):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://localhost:27017"):
with patch('app.database.connection.get_mongodb_database_name', return_value="testdb"):
# Reset global variables
import app.database.connection
app.database.connection._client = None
app.database.connection._database = None
result = get_database()
assert result == mock_database
mock_client.admin.command.assert_called_with('ping')
# Verify that __getitem__ was called with the database name
mock_client.__getitem__.assert_called_with("testdb")
def test_i_cannot_connect_to_invalid_mongodb_url():
"""Test fail-fast behavior with invalid MongoDB URL."""
mock_client = Mock()
mock_client.admin.command.side_effect = ConnectionFailure("Connection failed")
with patch('app.database.connection.MongoClient', return_value=mock_client):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://invalid:27017"):
with pytest.raises(SystemExit) as exc_info:
create_mongodb_client()
assert exc_info.value.code == 1
def test_i_cannot_connect_with_server_selection_timeout():
"""Test fail-fast behavior with server selection timeout."""
mock_client = Mock()
mock_client.admin.command.side_effect = ServerSelectionTimeoutError("Timeout")
with patch('app.database.connection.MongoClient', return_value=mock_client):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://timeout:27017"):
with pytest.raises(SystemExit) as exc_info:
create_mongodb_client()
assert exc_info.value.code == 1
def test_i_cannot_connect_with_unexpected_error():
"""Test fail-fast behavior with unexpected connection error."""
with patch('app.database.connection.MongoClient', side_effect=Exception("Unexpected error")):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://error:27017"):
with pytest.raises(SystemExit) as exc_info:
create_mongodb_client()
assert exc_info.value.code == 1
def test_i_can_get_database_singleton():
"""Test that get_database returns the same instance (singleton pattern)."""
mock_client = Mock()
mock_database = Mock()
mock_client.__getitem__ = Mock(return_value=mock_database)
with patch('app.database.connection.MongoClient', return_value=mock_client):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://localhost:27017"):
with patch('app.database.connection.get_mongodb_database_name', return_value="testdb"):
# Reset global variables
import app.database.connection
app.database.connection._client = None
app.database.connection._database = None
# First call
db1 = get_database()
# Second call
db2 = get_database()
assert db1 is db2
# MongoClient should be called only once
assert mock_client.admin.command.call_count == 1
def test_i_can_close_database_connection():
"""Test closing database connection."""
mock_client = Mock()
mock_database = Mock()
mock_client.__getitem__ = Mock(return_value=mock_database)
with patch('app.database.connection.MongoClient', return_value=mock_client):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://localhost:27017"):
with patch('app.database.connection.get_mongodb_database_name', return_value="testdb"):
# Reset global variables
import app.database.connection
app.database.connection._client = None
app.database.connection._database = None
# Create connection
get_database()
# Close connection
close_database_connection()
mock_client.close.assert_called_once()
assert app.database.connection._client is None
assert app.database.connection._database is None
def test_i_can_get_mongodb_client():
"""Test getting raw MongoDB client instance."""
mock_client = Mock()
mock_database = Mock()
mock_client.__getitem__ = Mock(return_value=mock_database)
with patch('app.database.connection.MongoClient', return_value=mock_client):
with patch('app.database.connection.get_mongodb_url', return_value="mongodb://localhost:27017"):
with patch('app.database.connection.get_mongodb_database_name', return_value="testdb"):
# Reset global variables
import app.database.connection
app.database.connection._client = None
app.database.connection._database = None
# Create connection first
get_database()
# Get client
result = get_mongodb_client()
assert result == mock_client
def test_i_can_get_none_mongodb_client_when_not_connected():
"""Test getting MongoDB client returns None when not connected."""
# Reset global variables
import app.database.connection
app.database.connection._client = None
app.database.connection._database = None
result = get_mongodb_client()
assert result is None
def test_i_can_test_database_connection_success():
"""Test database connection health check - success case."""
mock_database = Mock()
mock_database.command.return_value = True
with patch('app.database.connection.get_database', return_value=mock_database):
result = test_database_connection()
assert result is True
mock_database.command.assert_called_with('ping')
def test_i_can_close_connection_when_no_client():
"""Test closing connection when no client exists (should not raise error)."""
# Reset global variables
import app.database.connection
app.database.connection._client = None
app.database.connection._database = None
# Should not raise any exception
close_database_connection()
assert app.database.connection._client is None
assert app.database.connection._database is None

311
tests/test_document_content_repository.py
View File

@@ -1,311 +0,0 @@
"""
Test suite for DocumentContentRepository with async/await support.
This module contains comprehensive tests for all DocumentContentRepository methods
using mongomock-motor for in-memory MongoDB testing.
"""
import pytest
import hashlib
from datetime import datetime
import pytest_asyncio
from bson import ObjectId
from pymongo.errors import DuplicateKeyError
from mongomock_motor import AsyncMongoMockClient
from app.database.repositories.document_content_repository import DocumentContentRepository
from app.models.document import DocumentContent
@pytest_asyncio.fixture
async def in_memory_repository():
"""Create an in-memory DocumentContentRepository for testing."""
client = AsyncMongoMockClient()
db = client.test_database
repo = DocumentContentRepository(db)
await repo.initialize()
return repo
@pytest.fixture
def sample_document_content():
"""Sample DocumentContent data for testing."""
content = "This is sample document content for testing purposes."
file_hash = hashlib.sha256(content.encode()).hexdigest()
return DocumentContent(
file_hash=file_hash,
content=content,
encoding="utf-8",
file_size=len(content.encode()),
mime_type="text/plain"
)
@pytest.fixture
def another_document_content():
"""Another sample DocumentContent data for testing."""
content = "This is another sample document with different content."
file_hash = hashlib.sha256(content.encode()).hexdigest()
return DocumentContent(
file_hash=file_hash,
content=content,
encoding="utf-8",
file_size=len(content.encode()),
mime_type="text/plain"
)
class TestDocumentContentRepositoryCreation:
"""Tests for document content creation functionality."""
@pytest.mark.asyncio
async def test_i_can_create_document_content(self, in_memory_repository, sample_document_content):
"""Test successful document content creation."""
# Act
created_content = await in_memory_repository.create_document_content(sample_document_content)
# Assert
assert created_content is not None
assert created_content.file_hash == sample_document_content.file_hash
assert created_content.content == sample_document_content.content
assert created_content.encoding == sample_document_content.encoding
assert created_content.file_size == sample_document_content.file_size
assert created_content.mime_type == sample_document_content.mime_type
assert created_content.id is not None
@pytest.mark.asyncio
async def test_i_cannot_create_document_content_with_duplicate_file_hash(self, in_memory_repository,
sample_document_content):
"""Test that creating document content with duplicate file_hash raises DuplicateKeyError."""
# Arrange
await in_memory_repository.create_document_content(sample_document_content)
# Act & Assert
with pytest.raises(DuplicateKeyError) as exc_info:
await in_memory_repository.create_document_content(sample_document_content)
assert "already exists" in str(exc_info.value)
class TestDocumentContentRepositoryFinding:
"""Tests for document content finding functionality."""
@pytest.mark.asyncio
async def test_i_can_find_document_content_by_id(self, in_memory_repository, sample_document_content):
"""Test finding document content by valid ID."""
# Arrange
created_content = await in_memory_repository.create_document_content(sample_document_content)
# Act
found_content = await in_memory_repository.find_document_content_by_id(str(created_content.id))
# Assert
assert found_content is not None
assert found_content.id == created_content.id
assert found_content.file_hash == created_content.file_hash
assert found_content.content == created_content.content
@pytest.mark.asyncio
async def test_i_cannot_find_document_content_by_invalid_id(self, in_memory_repository):
"""Test that invalid ObjectId returns None."""
# Act
found_content = await in_memory_repository.find_document_content_by_id("invalid_id")
# Assert
assert found_content is None
@pytest.mark.asyncio
async def test_i_cannot_find_document_content_by_nonexistent_id(self, in_memory_repository):
"""Test that nonexistent but valid ObjectId returns None."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
found_content = await in_memory_repository.find_document_content_by_id(nonexistent_id)
# Assert
assert found_content is None
@pytest.mark.asyncio
async def test_i_can_find_document_content_by_file_hash(self, in_memory_repository, sample_document_content):
"""Test finding document content by file hash."""
# Arrange
created_content = await in_memory_repository.create_document_content(sample_document_content)
# Act
found_content = await in_memory_repository.find_document_content_by_file_hash(sample_document_content.file_hash)
# Assert
assert found_content is not None
assert found_content.file_hash == created_content.file_hash
assert found_content.id == created_content.id
@pytest.mark.asyncio
async def test_i_cannot_find_document_content_by_nonexistent_file_hash(self, in_memory_repository):
"""Test that nonexistent file hash returns None."""
# Act
found_content = await in_memory_repository.find_document_content_by_file_hash("nonexistent_hash")
# Assert
assert found_content is None
class TestDocumentContentRepositoryUpdate:
"""Tests for document content update functionality."""
@pytest.mark.asyncio
async def test_i_can_update_document_content(self, in_memory_repository, sample_document_content):
"""Test successful document content update."""
# Arrange
created_content = await in_memory_repository.create_document_content(sample_document_content)
update_data = {
"content": "Updated content for testing",
"encoding": "utf-16",
"mime_type": "text/html"
}
# Act
updated_content = await in_memory_repository.update_document_content(str(created_content.id), update_data)
# Assert
assert updated_content is not None
assert updated_content.content == update_data["content"]
assert updated_content.encoding == update_data["encoding"]
assert updated_content.mime_type == update_data["mime_type"]
assert updated_content.id == created_content.id
assert updated_content.file_hash == created_content.file_hash # Should remain unchanged
@pytest.mark.asyncio
async def test_i_cannot_update_document_content_with_invalid_id(self, in_memory_repository):
"""Test that updating with invalid ID returns None."""
# Act
result = await in_memory_repository.update_document_content("invalid_id", {"content": "test"})
# Assert
assert result is None
@pytest.mark.asyncio
async def test_i_can_update_document_content_with_partial_data(self, in_memory_repository, sample_document_content):
"""Test updating document content with partial data."""
# Arrange
created_content = await in_memory_repository.create_document_content(sample_document_content)
partial_update = {"encoding": "iso-8859-1"}
# Act
updated_content = await in_memory_repository.update_document_content(str(created_content.id), partial_update)
# Assert
assert updated_content is not None
assert updated_content.encoding == "iso-8859-1"
assert updated_content.content == created_content.content # Should remain unchanged
assert updated_content.mime_type == created_content.mime_type # Should remain unchanged
@pytest.mark.asyncio
async def test_i_can_update_document_content_with_empty_data(self, in_memory_repository, sample_document_content):
"""Test updating document content with empty data returns current content."""
# Arrange
created_content = await in_memory_repository.create_document_content(sample_document_content)
empty_update = {}
# Act
result = await in_memory_repository.update_document_content(str(created_content.id), empty_update)
# Assert
assert result is not None
assert result.content == created_content.content
assert result.encoding == created_content.encoding
assert result.mime_type == created_content.mime_type
class TestDocumentContentRepositoryDeletion:
"""Tests for document content deletion functionality."""
@pytest.mark.asyncio
async def test_i_can_delete_document_content(self, in_memory_repository, sample_document_content):
"""Test successful document content deletion."""
# Arrange
created_content = await in_memory_repository.create_document_content(sample_document_content)
# Act
deletion_result = await in_memory_repository.delete_document_content(str(created_content.id))
# Assert
assert deletion_result is True
# Verify content is actually deleted
found_content = await in_memory_repository.find_document_content_by_id(str(created_content.id))
assert found_content is None
@pytest.mark.asyncio
async def test_i_cannot_delete_document_content_with_invalid_id(self, in_memory_repository):
"""Test that deleting with invalid ID returns False."""
# Act
result = await in_memory_repository.delete_document_content("invalid_id")
# Assert
assert result is False
@pytest.mark.asyncio
async def test_i_cannot_delete_nonexistent_document_content(self, in_memory_repository):
"""Test that deleting nonexistent document content returns False."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
result = await in_memory_repository.delete_document_content(nonexistent_id)
# Assert
assert result is False
class TestDocumentContentRepositoryUtilities:
"""Tests for utility methods."""
@pytest.mark.asyncio
async def test_i_can_check_content_exists(self, in_memory_repository, sample_document_content):
"""Test checking if document content exists by file hash."""
# Arrange
await in_memory_repository.create_document_content(sample_document_content)
# Act
exists = await in_memory_repository.content_exists(sample_document_content.file_hash)
not_exists = await in_memory_repository.content_exists("nonexistent_hash")
# Assert
assert exists is True
assert not_exists is False
@pytest.mark.asyncio
async def test_i_can_list_document_contents(self, in_memory_repository, sample_document_content,
another_document_content):
"""Test listing document contents with pagination."""
# Arrange
await in_memory_repository.create_document_content(sample_document_content)
await in_memory_repository.create_document_content(another_document_content)
# Act
all_contents = await in_memory_repository.list_document_contents()
limited_contents = await in_memory_repository.list_document_contents(skip=0, limit=1)
# Assert
assert len(all_contents) == 2
assert len(limited_contents) == 1
assert all(isinstance(content, DocumentContent) for content in all_contents)
@pytest.mark.asyncio
async def test_i_can_count_document_contents(self, in_memory_repository, sample_document_content,
another_document_content):
"""Test counting document contents."""
# Arrange
initial_count = await in_memory_repository.count_document_contents()
await in_memory_repository.create_document_content(sample_document_content)
await in_memory_repository.create_document_content(another_document_content)
# Act
final_count = await in_memory_repository.count_document_contents()
# Assert
assert final_count == initial_count + 2

566
tests/test_document_repository.py
View File

@@ -1,566 +0,0 @@
"""
Test suite for FileDocumentRepository with async/await support.
This module contains comprehensive tests for all FileDocumentRepository methods
using mongomock-motor for in-memory MongoDB testing.
"""
import pytest
from datetime import datetime
from typing import Dict, Any
import pytest_asyncio
from bson import ObjectId
from pymongo.errors import DuplicateKeyError, PyMongoError
from mongomock_motor import AsyncMongoMockClient
from app.database.repositories.document_repository import FileDocumentRepository
from app.models.document import FileDocument, FileType
@pytest_asyncio.fixture
async def in_memory_repository():
"""Create an in-memory FileDocumentRepository for testing."""
client = AsyncMongoMockClient()
db = client.test_database
repo = FileDocumentRepository(db)
# repo.db = db
# repo.collection = db.files
await repo.initialize()
return repo
@pytest.fixture
def sample_file_document():
"""Sample FileDocument data for testing."""
return FileDocument(
filename="test_document.pdf",
filepath="/path/to/test_document.pdf",
file_hash="a1b2c3d4e5f6789012345678901234567890abcdef1234567890abcdef123456",
file_type=FileType("pdf"),
detected_at=datetime.now(),
)
@pytest.fixture
def sample_update_data():
"""Sample update data for testing."""
return {
"metadata": {"tags": ["updated", "document"]},
"file_type": FileType("txt"),
}
@pytest.fixture
def multiple_sample_documents():
"""Multiple FileDocument objects for list/search testing."""
base_time = datetime.now()
return [
FileDocument(
filename="document1.pdf",
filepath="/path/to/document1.pdf",
file_hash="hash1" + "0" * 58,
file_type=FileType("pdf"),
detected_at=base_time,
),
FileDocument(
filename="similar_document.pdf",
filepath="/path/to/similar_document.pdf",
file_hash="hash2" + "0" * 58,
file_type=FileType("pdf"),
detected_at=base_time,
),
FileDocument(
filename="completely_different.txt",
filepath="/path/to/completely_different.txt",
file_hash="hash3" + "0" * 58,
file_type=FileType("pdf"),
detected_at=base_time,
)
]
class TestFileDocumentRepositoryInitialization:
"""Tests for repository initialization."""
@pytest.mark.asyncio
async def test_i_can_initialize_repository(self):
"""Test repository initialization."""
# Arrange
client = AsyncMongoMockClient()
db = client.test_database
repo = FileDocumentRepository(db)
await repo.initialize()
# Act & Assert (should not raise any exception)
assert repo.db is not None
assert repo.collection is not None
# TODO : check that the indexes are create
class TestFileDocumentRepositoryCreation:
"""Tests for file document creation functionality."""
@pytest.mark.asyncio
async def test_i_can_create_document(self, in_memory_repository, sample_file_document):
"""Test successful file document creation."""
# Act
created_doc = await in_memory_repository.create_document(sample_file_document)
# Assert
assert created_doc is not None
assert created_doc.filename == sample_file_document.filename
assert created_doc.filepath == sample_file_document.filepath
assert created_doc.file_hash == sample_file_document.file_hash
assert created_doc.file_type == sample_file_document.file_type
assert created_doc.id is not None
assert isinstance(created_doc.id, ObjectId)
@pytest.mark.asyncio
async def test_i_can_create_document_without_id(self, in_memory_repository, sample_file_document):
"""Test creating document with _id set to None (should be removed)."""
# Arrange
sample_file_document.id = None
# Act
created_doc = await in_memory_repository.create_document(sample_file_document)
# Assert
assert created_doc is not None
assert created_doc.id is not None
assert isinstance(created_doc.id, ObjectId)
@pytest.mark.asyncio
async def test_i_cannot_create_duplicate_document(self, in_memory_repository, sample_file_document):
"""Test that creating document with duplicate hash raises DuplicateKeyError."""
# Arrange
await in_memory_repository.create_document(sample_file_document)
duplicate_doc = FileDocument(
filename="different_name.pdf",
filepath=sample_file_document.filepath,
file_hash="different_hash" + "0" * 58,
file_type=FileType("pdf"),
detected_at=datetime.now()
)
# Act & Assert
with pytest.raises(DuplicateKeyError) as exc_info:
await in_memory_repository.create_document(duplicate_doc)
assert "already exists" in str(exc_info.value)
@pytest.mark.asyncio
async def test_i_cannot_create_document_with_pymongo_error(self, in_memory_repository, sample_file_document, mocker):
"""Test handling of PyMongo errors during document creation."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'insert_one', side_effect=PyMongoError("Database error"))
# Act & Assert
with pytest.raises(ValueError) as exc_info:
await in_memory_repository.create_document(sample_file_document)
assert "Failed to create file document" in str(exc_info.value)
class TestFileDocumentRepositoryFinding:
"""Tests for file document finding functionality."""
@pytest.mark.asyncio
async def test_i_can_find_document_by_valid_id(self, in_memory_repository, sample_file_document):
"""Test finding document by valid ObjectId."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
# Act
found_doc = await in_memory_repository.find_document_by_id(str(created_doc.id))
# Assert
assert found_doc is not None
assert found_doc.id == created_doc.id
assert found_doc.filename == created_doc.filename
assert found_doc.file_hash == created_doc.file_hash
@pytest.mark.asyncio
async def test_i_cannot_find_document_with_invalid_id(self, in_memory_repository):
"""Test that invalid ObjectId returns None."""
# Act
found_doc = await in_memory_repository.find_document_by_id("invalid_id")
# Assert
assert found_doc is None
@pytest.mark.asyncio
async def test_i_cannot_find_document_by_nonexistent_id(self, in_memory_repository):
"""Test that nonexistent but valid ObjectId returns None."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
found_doc = await in_memory_repository.find_document_by_id(nonexistent_id)
# Assert
assert found_doc is None
@pytest.mark.asyncio
async def test_i_can_find_document_by_hash(self, in_memory_repository, sample_file_document):
"""Test finding document by file hash."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
# Act
found_doc = await in_memory_repository.find_document_by_hash(sample_file_document.file_hash)
# Assert
assert found_doc is not None
assert found_doc.file_hash == created_doc.file_hash
assert found_doc.id == created_doc.id
@pytest.mark.asyncio
async def test_i_cannot_find_document_with_nonexistent_hash(self, in_memory_repository):
"""Test that nonexistent hash returns None."""
# Act
found_doc = await in_memory_repository.find_document_by_hash("nonexistent_hash")
# Assert
assert found_doc is None
@pytest.mark.asyncio
async def test_i_can_find_document_by_filepath(self, in_memory_repository, sample_file_document):
"""Test finding document by exact filepath."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
# Act
found_doc = await in_memory_repository.find_document_by_filepath(sample_file_document.filepath)
# Assert
assert found_doc is not None
assert found_doc.filepath == created_doc.filepath
assert found_doc.id == created_doc.id
@pytest.mark.asyncio
async def test_i_cannot_find_document_with_nonexistent_filepath(self, in_memory_repository):
"""Test that nonexistent filepath returns None."""
# Act
found_doc = await in_memory_repository.find_document_by_filepath("/nonexistent/path.pdf")
# Assert
assert found_doc is None
class TestFileDocumentRepositoryFuzzySearch:
"""Tests for fuzzy search functionality by filename."""
@pytest.mark.asyncio
async def test_i_can_find_documents_by_exact_name(self, in_memory_repository, multiple_sample_documents):
"""Test finding documents with exact filename match."""
# Arrange
for doc in multiple_sample_documents:
await in_memory_repository.create_document(doc)
# Act
found_docs = await in_memory_repository.find_document_by_name("document1.pdf")
# Assert
assert len(found_docs) == 1
assert found_docs[0].filename == "document1.pdf"
@pytest.mark.asyncio
async def test_i_can_find_documents_by_fuzzy_name(self, in_memory_repository, multiple_sample_documents):
"""Test finding documents with fuzzy matching using default threshold."""
# Arrange
for doc in multiple_sample_documents:
await in_memory_repository.create_document(doc)
# Act
found_docs = await in_memory_repository.find_document_by_name("document")
# Assert
assert len(found_docs) >= 2 # Should find document1.pdf and similar_document.pdf
filenames = [doc.filename for doc in found_docs]
assert "document1.pdf" in filenames
assert "similar_document.pdf" in filenames
@pytest.mark.asyncio
async def test_i_cannot_find_documents_by_name_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during name search."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find', side_effect=PyMongoError("Database error"))
# Act
found_docs = await in_memory_repository.find_document_by_name("test")
# Assert
assert found_docs == []
class TestFileDocumentRepositoryListing:
"""Tests for document listing functionality."""
@pytest.mark.asyncio
async def test_i_can_list_documents_with_default_pagination(self, in_memory_repository, multiple_sample_documents):
"""Test listing documents with default pagination."""
# Arrange
for doc in multiple_sample_documents:
await in_memory_repository.create_document(doc)
# Act
docs = await in_memory_repository.list_documents()
# Assert
assert len(docs) == len(multiple_sample_documents)
assert all(isinstance(doc, FileDocument) for doc in docs)
@pytest.mark.asyncio
async def test_i_can_list_documents_with_custom_pagination(self, in_memory_repository, multiple_sample_documents):
"""Test listing documents with custom pagination."""
# Arrange
for doc in multiple_sample_documents:
await in_memory_repository.create_document(doc)
# Act
docs_page1 = await in_memory_repository.list_documents(skip=0, limit=2)
docs_page2 = await in_memory_repository.list_documents(skip=2, limit=2)
# Assert
assert len(docs_page1) == 2
assert len(docs_page2) == 1 # Only 3 total documents
# Ensure no overlap between pages
page1_ids = [doc.id for doc in docs_page1]
page2_ids = [doc.id for doc in docs_page2]
assert len(set(page1_ids).intersection(set(page2_ids))) == 0
@pytest.mark.asyncio
async def test_i_can_list_documents_sorted_by_date(self, in_memory_repository, sample_file_document):
"""Test that documents are sorted by detected_at in descending order."""
# Arrange
from datetime import timedelta
# Create documents with different timestamps
doc1 = sample_file_document.model_copy()
doc1.filename = "oldest.pdf"
doc1.filepath = f"/path/to/{doc1.filename}"
doc1.file_hash = "hash1" + "0" * 58
doc1.detected_at = datetime.now() - timedelta(hours=2)
doc2 = sample_file_document.model_copy()
doc2.filename = "newest.pdf"
doc2.filepath = f"/path/to/{doc2.filename}"
doc2.file_hash = "hash2" + "0" * 58
doc2.detected_at = datetime.now()
await in_memory_repository.create_document(doc1)
await in_memory_repository.create_document(doc2)
# Act
docs = await in_memory_repository.list_documents()
# Assert
assert len(docs) == 2
assert docs[0].filename == "newest.pdf" # Most recent first
assert docs[1].filename == "oldest.pdf"
@pytest.mark.asyncio
async def test_i_can_list_empty_documents(self, in_memory_repository):
"""Test listing documents from empty collection."""
# Act
docs = await in_memory_repository.list_documents()
# Assert
assert docs == []
@pytest.mark.asyncio
async def test_i_cannot_list_documents_with_pymongo_error(self, in_memory_repository, mocker):
"""Test handling of PyMongo errors during document listing."""
# Arrange
mocker.patch.object(in_memory_repository.collection, 'find', side_effect=PyMongoError("Database error"))
# Act
docs = await in_memory_repository.list_documents()
# Assert
assert docs == []
class TestFileDocumentRepositoryUpdate:
"""Tests for document update functionality."""
@pytest.mark.asyncio
async def test_i_can_update_document_successfully(self, in_memory_repository, sample_file_document,
sample_update_data):
"""Test successful document update."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
# Act
updated_doc = await in_memory_repository.update_document(str(created_doc.id), sample_update_data)
# Assert
assert updated_doc is not None
assert updated_doc.file_type == sample_update_data["file_type"]
assert updated_doc.id == created_doc.id
assert updated_doc.filename == created_doc.filename # Unchanged fields remain
@pytest.mark.asyncio
async def test_i_can_update_document_with_partial_data(self, in_memory_repository, sample_file_document):
"""Test updating document with partial data."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
partial_update = {"file_type": FileType("txt")}
# Act
updated_doc = await in_memory_repository.update_document(str(created_doc.id), partial_update)
# Assert
assert updated_doc is not None
assert updated_doc.file_type == FileType("txt")
assert updated_doc.filename == created_doc.filename # Should remain unchanged
assert updated_doc.filepath == created_doc.filepath # Should remain unchanged
@pytest.mark.asyncio
async def test_i_can_update_document_filtering_none_values(self, in_memory_repository, sample_file_document):
"""Test that None values are filtered out from update data."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
update_with_none = {"metadata": {"tags": ["updated", "document"]}, "file_type": None}
# Act
updated_doc = await in_memory_repository.update_document(str(created_doc.id), update_with_none)
# Assert
assert updated_doc is not None
assert updated_doc.metadata == {"tags": ["updated", "document"]}
assert updated_doc.file_type == created_doc.file_type # Should remain unchanged (None filtered out)
@pytest.mark.asyncio
async def test_i_can_update_document_with_empty_data(self, in_memory_repository, sample_file_document):
"""Test updating document with empty data returns current document."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
empty_update = {}
# Act
result = await in_memory_repository.update_document(str(created_doc.id), empty_update)
# Assert
assert result is not None
assert result.filename == created_doc.filename
assert result.file_hash == created_doc.file_hash
assert result.metadata == created_doc.metadata
@pytest.mark.asyncio
async def test_i_cannot_update_document_with_invalid_id(self, in_memory_repository, sample_update_data):
"""Test that updating with invalid ID returns None."""
# Act
result = await in_memory_repository.update_document("invalid_id", sample_update_data)
# Assert
assert result is None
@pytest.mark.asyncio
async def test_i_cannot_update_nonexistent_document(self, in_memory_repository, sample_update_data):
"""Test that updating nonexistent document returns None."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
result = await in_memory_repository.update_document(nonexistent_id, sample_update_data)
# Assert
assert result is None
@pytest.mark.asyncio
async def test_i_cannot_update_document_with_pymongo_error(self, in_memory_repository, sample_file_document,
sample_update_data, mocker):
"""Test handling of PyMongo errors during document update."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
mocker.patch.object(in_memory_repository.collection, 'find_one_and_update',
side_effect=PyMongoError("Database error"))
# Act
result = await in_memory_repository.update_document(str(created_doc.id), sample_update_data)
# Assert
assert result is None
class TestFileDocumentRepositoryDeletion:
"""Tests for document deletion functionality."""
@pytest.mark.asyncio
async def test_i_can_delete_existing_document(self, in_memory_repository, sample_file_document):
"""Test successful document deletion."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
# Act
deletion_result = await in_memory_repository.delete_document(str(created_doc.id))
# Assert
assert deletion_result is True
# Verify document is actually deleted
found_doc = await in_memory_repository.find_document_by_id(str(created_doc.id))
assert found_doc is None
@pytest.mark.asyncio
async def test_i_cannot_delete_document_with_invalid_id(self, in_memory_repository):
"""Test that deleting with invalid ID returns False."""
# Act
result = await in_memory_repository.delete_document("invalid_id")
# Assert
assert result is False
@pytest.mark.asyncio
async def test_i_cannot_delete_nonexistent_document(self, in_memory_repository):
"""Test that deleting nonexistent document returns False."""
# Arrange
nonexistent_id = str(ObjectId())
# Act
result = await in_memory_repository.delete_document(nonexistent_id)
# Assert
assert result is False
@pytest.mark.asyncio
async def test_i_cannot_delete_document_with_pymongo_error(self, in_memory_repository, sample_file_document, mocker):
"""Test handling of PyMongo errors during document deletion."""
# Arrange
created_doc = await in_memory_repository.create_document(sample_file_document)
mocker.patch.object(in_memory_repository.collection, 'delete_one', side_effect=PyMongoError("Database error"))
# Act
result = await in_memory_repository.delete_document(str(created_doc.id))
# Assert
assert result is False
class TestFileDocumentRepositoryUtilities:
"""Tests for utility methods."""
@pytest.mark.asyncio
async def test_i_can_count_documents(self, in_memory_repository, sample_file_document):
"""Test counting documents."""
# Arrange
initial_count = await in_memory_repository.count_documents()
await in_memory_repository.create_document(sample_file_document)
# Act
final_count = await in_memory_repository.count_documents()
# Assert
assert final_count == initial_count + 1
@pytest.mark.asyncio
async def test_i_can_count_zero_documents(self, in_memory_repository):
"""Test counting documents in empty collection."""
# Act
count = await in_memory_repository.count_documents()
# Assert
assert count == 0

697
tests/test_document_service.py
View File

@@ -1,697 +0,0 @@
"""
Unit tests for DocumentService using in-memory MongoDB.
Tests the orchestration logic with real MongoDB operations
using mongomock for better integration testing.
"""
import pytest
import pytest_asyncio
from unittest.mock import Mock, patch
from datetime import datetime
from bson import ObjectId
from pathlib import Path
from mongomock_motor import AsyncMongoMockClient
from app.services.document_service import DocumentService
from app.database.repositories.document_repository import FileDocumentRepository
from app.database.repositories.document_content_repository import DocumentContentRepository
from app.models.document import FileDocument, DocumentContent, FileType, ExtractionMethod
from app.models.types import PyObjectId
@pytest_asyncio.fixture
async def in_memory_file_repository():
"""Create an in-memory FileDocumentRepository for testing."""
client = AsyncMongoMockClient()
db = client.test_database
repo = FileDocumentRepository(db)
await repo.initialize()
return repo
@pytest_asyncio.fixture
async def in_memory_content_repository():
"""Create an in-memory DocumentContentRepository for testing."""
client = AsyncMongoMockClient()
db = client.test_database
repo = DocumentContentRepository(db)
await repo.initialize()
return repo
@pytest_asyncio.fixture
async def in_memory_database():
"""Create an in-memory database for testing."""
client = AsyncMongoMockClient()
return client.test_database
@pytest_asyncio.fixture
async def document_service(in_memory_file_repository, in_memory_content_repository, in_memory_database):
"""Create DocumentService with in-memory repositories."""
with patch('app.services.document_service.get_database', return_value=in_memory_database):
service = DocumentService()
service.file_repository = in_memory_file_repository
service.content_repository = in_memory_content_repository
return service
@pytest.fixture
def sample_file_bytes():
"""Sample file content as bytes."""
return b"This is a test PDF content"
@pytest.fixture
def sample_text_bytes():
"""Sample text file content as bytes."""
return b"This is a test text file content"
@pytest.fixture
def sample_file_hash():
"""Expected SHA256 hash for sample file bytes."""
import hashlib
return hashlib.sha256(b"This is a test PDF content").hexdigest()
@pytest.fixture
def sample_file_document():
"""Sample FileDocument for testing."""
return FileDocument(
id=ObjectId(),
filename="test.pdf",
filepath="/test/test.pdf",
file_type=FileType.PDF,
extraction_method=None,
metadata={},
detected_at=datetime(2024, 1, 15, 10, 30, 0),
file_hash="test_hash"
)
class TestCreateDocument:
"""Tests for create_document method."""
@patch('app.services.document_service.magic.from_buffer')
@patch('app.services.document_service.datetime')
@pytest.mark.asyncio
async def test_i_can_create_document_with_new_content(
self,
mock_datetime,
mock_magic,
document_service,
sample_file_bytes
):
"""Test creating document when content doesn't exist yet."""
# Setup mocks
fixed_time = datetime(2024, 1, 15, 10, 30, 0)
mock_datetime.utcnow.return_value = fixed_time
mock_magic.return_value = "application/pdf"
# Execute
result = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Verify document creation
assert result is not None
assert result.filename == "test.pdf"
assert result.filepath == "/test/test.pdf"
assert result.file_type == FileType.PDF
assert result.detected_at == fixed_time
assert result.file_hash == document_service._calculate_file_hash(sample_file_bytes)
# Verify content was created
content = await document_service.content_repository.find_document_content_by_file_hash(
result.file_hash
)
assert content is not None
assert content.file_hash == result.file_hash
assert content.file_size == len(sample_file_bytes)
assert content.mime_type == "application/pdf"
assert content.encoding == "utf-8"
@patch('app.services.document_service.magic.from_buffer')
@patch('app.services.document_service.datetime')
@pytest.mark.asyncio
async def test_i_can_create_document_with_existing_content(
self,
mock_datetime,
mock_magic,
document_service,
sample_file_bytes
):
"""Test creating document when content already exists (deduplication)."""
# Setup mocks
fixed_time = datetime(2024, 1, 15, 10, 30, 0)
mock_datetime.utcnow.return_value = fixed_time
mock_magic.return_value = "application/pdf"
# Create first document
first_doc = await document_service.create_document(
"/test/first.pdf",
sample_file_bytes,
"utf-8"
)
# Create second document with same content
second_doc = await document_service.create_document(
"/test/second.pdf",
sample_file_bytes,
"utf-8"
)
# Verify both documents exist but share same hash
assert first_doc.file_hash == second_doc.file_hash
assert first_doc.filename != second_doc.filename
assert first_doc.filepath != second_doc.filepath
# Verify only one content document exists
all_content = await document_service.content_repository.list_document_content()
content_for_hash = [c for c in all_content if c.file_hash == first_doc.file_hash]
assert len(content_for_hash) == 1
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_create_document_with_different_encodings(
self,
mock_magic,
document_service,
sample_text_bytes
):
"""Test creating documents with different text encodings."""
# Setup
mock_magic.return_value = "text/plain"
# Test with different encodings
encodings = ["utf-8", "latin-1", "ascii"]
for i, encoding in enumerate(encodings):
result = await document_service.create_document(
f"/test/test{i}.txt",
sample_text_bytes,
encoding
)
# Verify document was created
assert result is not None
assert result.file_type == FileType.TXT
# Verify content has correct encoding
content = await document_service.content_repository.find_document_content_by_file_hash(
result.file_hash
)
assert content.encoding == encoding
@pytest.mark.asyncio
async def test_i_cannot_create_document_with_unsupported_file_type(
self,
document_service,
sample_file_bytes
):
"""Test that unsupported file types raise ValueError."""
with pytest.raises(ValueError, match="Unsupported file type"):
await document_service.create_document(
"/test/test.xyz", # Unsupported extension
sample_file_bytes,
"utf-8"
)
@pytest.mark.asyncio
async def test_i_cannot_create_document_with_empty_file_path(
self,
document_service,
sample_file_bytes
):
"""Test that empty file path raises ValueError."""
with pytest.raises(ValueError):
await document_service.create_document(
"", # Empty path
sample_file_bytes,
"utf-8"
)
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_create_document_with_empty_bytes(
self,
mock_magic,
document_service
):
"""Test behavior with empty file bytes."""
# Setup
mock_magic.return_value = "text/plain"
# Execute with empty bytes
result = await document_service.create_document(
"/test/empty.txt",
b"", # Empty bytes
"utf-8"
)
# Should still work but with zero file size
assert result is not None
content = await document_service.content_repository.find_document_content_by_file_hash(
result.file_hash
)
assert content.file_size == 0
class TestGetMethods:
"""Tests for document retrieval methods."""
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_get_document_by_id(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document by ID."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute
result = await document_service.get_document_by_id(created_doc.id)
# Verify
assert result is not None
assert result.id == created_doc.id
assert result.filename == created_doc.filename
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_get_document_by_hash(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document by file hash."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute
result = await document_service.get_document_by_hash(created_doc.file_hash)
# Verify
assert result is not None
assert result.file_hash == created_doc.file_hash
assert result.filename == created_doc.filename
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_get_document_by_filepath(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document by file path."""
# Setup
mock_magic.return_value = "application/pdf"
test_path = "/test/unique_test.pdf"
# Create a document first
created_doc = await document_service.create_document(
test_path,
sample_file_bytes,
"utf-8"
)
# Execute
result = await document_service.get_document_by_filepath(test_path)
# Verify
assert result is not None
assert result.filepath == test_path
assert result.id == created_doc.id
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_get_document_with_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test retrieving document with associated content."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute
result = await document_service.get_document_with_content(created_doc.id)
# Verify
assert result is not None
document, content = result
assert document.id == created_doc.id
assert content is not None
assert content.file_hash == created_doc.file_hash
@pytest.mark.asyncio
async def test_i_cannot_get_nonexistent_document_by_id(
self,
document_service
):
"""Test that nonexistent document returns None."""
# Execute with random ObjectId
result = await document_service.get_document_by_id(ObjectId())
# Verify
assert result is None
@pytest.mark.asyncio
async def test_i_cannot_get_nonexistent_document_by_hash(
self,
document_service
):
"""Test that nonexistent document hash returns None."""
# Execute
result = await document_service.get_document_by_hash("nonexistent_hash")
# Verify
assert result is None
class TestPaginationAndCounting:
"""Tests for document listing and counting."""
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_list_documents_with_pagination(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test document listing with pagination parameters."""
# Setup
mock_magic.return_value = "application/pdf"
# Create multiple documents
for i in range(5):
await document_service.create_document(
f"/test/test{i}.pdf",
sample_file_bytes + bytes(str(i), 'utf-8'), # Make each file unique
"utf-8"
)
# Execute with pagination
result = await document_service.list_documents(skip=1, limit=2)
# Verify
assert len(result) == 2
# Test counting
total_count = await document_service.count_documents()
assert total_count == 5
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_count_documents(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test document counting."""
# Setup
mock_magic.return_value = "text/plain"
# Initially should be 0
initial_count = await document_service.count_documents()
assert initial_count == 0
# Create some documents
for i in range(3):
await document_service.create_document(
f"/test/test{i}.txt",
sample_file_bytes + bytes(str(i), 'utf-8'),
"utf-8"
)
# Execute
final_count = await document_service.count_documents()
# Verify
assert final_count == 3
class TestUpdateAndDelete:
"""Tests for document update and deletion operations."""
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_update_document_metadata(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test updating document metadata."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Execute update
update_data = {"metadata": {"page_count": 5}}
result = await document_service.update_document(created_doc.id, update_data)
# Verify
assert result is not None
assert result.metadata.get("page_count") == 5
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_delete_document_and_orphaned_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test deleting document with orphaned content cleanup."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Verify content exists
content_before = await document_service.content_repository.find_document_content_by_file_hash(
created_doc.file_hash
)
assert content_before is not None
# Execute deletion
result = await document_service.delete_document(created_doc.id)
# Verify document and content are deleted
assert result is True
deleted_doc = await document_service.get_document_by_id(created_doc.id)
assert deleted_doc is None
content_after = await document_service.content_repository.find_document_content_by_file_hash(
created_doc.file_hash
)
assert content_after is None
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_delete_document_without_affecting_shared_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test deleting document without removing shared content."""
# Setup
mock_magic.return_value = "application/pdf"
# Create two documents with same content
doc1 = await document_service.create_document(
"/test/test1.pdf",
sample_file_bytes,
"utf-8"
)
doc2 = await document_service.create_document(
"/test/test2.pdf",
sample_file_bytes,
"utf-8"
)
# They should share the same hash
assert doc1.file_hash == doc2.file_hash
# Delete first document
result = await document_service.delete_document(doc1.id)
assert result is True
# Verify first document is deleted but content still exists
deleted_doc = await document_service.get_document_by_id(doc1.id)
assert deleted_doc is None
remaining_doc = await document_service.get_document_by_id(doc2.id)
assert remaining_doc is not None
content = await document_service.content_repository.find_document_content_by_file_hash(
doc2.file_hash
)
assert content is not None
class TestUtilityMethods:
"""Tests for utility methods."""
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_check_content_exists(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test checking if content exists by hash."""
# Setup
mock_magic.return_value = "application/pdf"
# Initially content doesn't exist
test_hash = "nonexistent_hash"
exists_before = await document_service.content_exists(test_hash)
assert exists_before is False
# Create a document
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Now content should exist
exists_after = await document_service.content_exists(created_doc.file_hash)
assert exists_after is True
@patch('app.services.document_service.magic.from_buffer')
@pytest.mark.asyncio
async def test_i_can_update_document_content(
self,
mock_magic,
document_service,
sample_file_bytes
):
"""Test updating extracted document content."""
# Setup
mock_magic.return_value = "application/pdf"
# Create a document first
created_doc = await document_service.create_document(
"/test/test.pdf",
sample_file_bytes,
"utf-8"
)
# Update content
new_content = "Updated extracted content"
result = await document_service.update_document_content(
created_doc.file_hash,
new_content
)
# Verify update
assert result is not None
assert result.content == new_content
# Verify persistence
updated_content = await document_service.content_repository.find_document_content_by_file_hash(
created_doc.file_hash
)
assert updated_content.content == new_content
class TestHashCalculation:
"""Tests for file hash calculation utility."""
def test_i_can_calculate_consistent_file_hash(self, document_service):
"""Test that file hash calculation is consistent."""
test_bytes = b"Test content for hashing"
# Calculate hash multiple times
hash1 = document_service._calculate_file_hash(test_bytes)
hash2 = document_service._calculate_file_hash(test_bytes)
# Should be identical
assert hash1 == hash2
assert len(hash1) == 64 # SHA256 produces 64-character hex string
def test_i_get_different_hashes_for_different_content(self, document_service):
"""Test that different content produces different hashes."""
content1 = b"First content"
content2 = b"Second content"
hash1 = document_service._calculate_file_hash(content1)
hash2 = document_service._calculate_file_hash(content2)
assert hash1 != hash2
class TestFileTypeDetection:
"""Tests for file type detection."""
def test_i_can_detect_pdf_file_type(self, document_service):
"""Test PDF file type detection."""
file_type = document_service._detect_file_type("/path/to/document.pdf")
assert file_type == FileType.PDF
def test_i_can_detect_txt_file_type(self, document_service):
"""Test text file type detection."""
file_type = document_service._detect_file_type("/path/to/document.txt")
assert file_type == FileType.TXT
def test_i_can_detect_docx_file_type(self, document_service):
"""Test DOCX file type detection."""
file_type = document_service._detect_file_type("/path/to/document.docx")
assert file_type == FileType.DOCX
def test_i_cannot_detect_unsupported_file_type(self, document_service):
"""Test unsupported file type raises ValueError."""
with pytest.raises(ValueError, match="Unsupported file type"):
document_service._detect_file_type("/path/to/document.xyz")

0
tests/utils/__init__.py Normal file
View File

2
tests/test_utils_document_matching.py → tests/utils/test_document_matching.py
View File

@@ -14,6 +14,8 @@ def get_doc(filename: str = None):
file_hash="a1b2c3d4e5f6789012345678901234567890abcdef1234567890abcdef123456",
file_type=FileType(os.path.splitext(filename)[1].lstrip(".") or "txt"),
detected_at=datetime.now(),
file_size=1024,
mime_type="application/pdf"
)

0
tests/test_security.py → tests/utils/test_security.py
View File