564 lines
20 KiB
Python
564 lines
20 KiB
Python
"""
|
|
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()
|
|
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
|
|
repo = FileDocumentRepository()
|
|
await repo.initialize()
|
|
|
|
# Act & Assert (should not raise any exception)
|
|
assert repo.db is not None
|
|
assert repo.collection is not None
|
|
|
|
|
|
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
|