trustgraph/tests/unit/test_chunking/conftest.py

153 lines
4.3 KiB
Python
Raw Normal View History

Release/v1.2 (#457) * Bump setup.py versions for 1.1 * PoC MCP server (#419) * Very initial MCP server PoC for TrustGraph * Put service on port 8000 * Add MCP container and packages to buildout * Update docs for API/CLI changes in 1.0 (#421) * Update some API basics for the 0.23/1.0 API change * Add MCP container push (#425) * Add command args to the MCP server (#426) * Host and port parameters * Added websocket arg * More docs * MCP client support (#427) - MCP client service - Tool request/response schema - API gateway support for mcp-tool - Message translation for tool request & response - Make mcp-tool using configuration service for information about where the MCP services are. * Feature/react call mcp (#428) Key Features - MCP Tool Integration: Added core MCP tool support with ToolClientSpec and ToolClient classes - API Enhancement: New mcp_tool method for flow-specific tool invocation - CLI Tooling: New tg-invoke-mcp-tool command for testing MCP integration - React Agent Enhancement: Fixed and improved multi-tool invocation capabilities - Tool Management: Enhanced CLI for tool configuration and management Changes - Added MCP tool invocation to API with flow-specific integration - Implemented ToolClientSpec and ToolClient for tool call handling - Updated agent-manager-react to invoke MCP tools with configurable types - Enhanced CLI with new commands and improved help text - Added comprehensive documentation for new CLI commands - Improved tool configuration management Testing - Added tg-invoke-mcp-tool CLI command for isolated MCP integration testing - Enhanced agent capability to invoke multiple tools simultaneously * Test suite executed from CI pipeline (#433) * Test strategy & test cases * Unit tests * Integration tests * Extending test coverage (#434) * Contract tests * Testing embeedings * Agent unit tests * Knowledge pipeline tests * Turn on contract tests * Increase storage test coverage (#435) * Fixing storage and adding tests * PR pipeline only runs quick tests * Empty configuration is returned as empty list, previously was not in response (#436) * Update config util to take files as well as command-line text (#437) * Updated CLI invocation and config model for tools and mcp (#438) * Updated CLI invocation and config model for tools and mcp * CLI anomalies * Tweaked the MCP tool implementation for new model * Update agent implementation to match the new model * Fix agent tools, now all tested * Fixed integration tests * Fix MCP delete tool params * Update Python deps to 1.2 * Update to enable knowledge extraction using the agent framework (#439) * Implement KG extraction agent (kg-extract-agent) * Using ReAct framework (agent-manager-react) * ReAct manager had an issue when emitting JSON, which conflicts which ReAct manager's own JSON messages, so refactored ReAct manager to use traditional ReAct messages, non-JSON structure. * Minor refactor to take the prompt template client out of prompt-template so it can be more readily used by other modules. kg-extract-agent uses this framework. * Migrate from setup.py to pyproject.toml (#440) * Converted setup.py to pyproject.toml * Modern package infrastructure as recommended by py docs * Install missing build deps (#441) * Install missing build deps (#442) * Implement logging strategy (#444) * Logging strategy and convert all prints() to logging invocations * Fix/startup failure (#445) * Fix loggin startup problems * Fix logging startup problems (#446) * Fix logging startup problems (#447) * Fixed Mistral OCR to use current API (#448) * Fixed Mistral OCR to use current API * Added PDF decoder tests * Fix Mistral OCR ident to be standard pdf-decoder (#450) * Fix Mistral OCR ident to be standard pdf-decoder * Correct test * Schema structure refactor (#451) * Write schema refactor spec * Implemented schema refactor spec * Structure data mvp (#452) * Structured data tech spec * Architecture principles * New schemas * Updated schemas and specs * Object extractor * Add .coveragerc * New tests * Cassandra object storage * Trying to object extraction working, issues exist * Validate librarian collection (#453) * Fix token chunker, broken API invocation (#454) * Fix token chunker, broken API invocation (#455) * Knowledge load utility CLI (#456) * Knowledge loader * More tests
2025-08-18 20:56:09 +01:00
import pytest
from unittest.mock import AsyncMock, Mock, patch
from trustgraph.schema import TextDocument, Metadata
from trustgraph.chunking.recursive.chunker import Processor as RecursiveChunker
from trustgraph.chunking.token.chunker import Processor as TokenChunker
from prometheus_client import REGISTRY
@pytest.fixture
def mock_flow():
"""Mock flow function that returns a mock output producer."""
output_mock = AsyncMock()
flow_mock = Mock(return_value=output_mock)
return flow_mock, output_mock
@pytest.fixture
def mock_consumer():
"""Mock consumer with test attributes."""
consumer = Mock()
consumer.id = "test-consumer"
consumer.flow = "test-flow"
return consumer
@pytest.fixture
def sample_text_document():
"""Sample document with moderate length text."""
metadata = Metadata(
id="test-doc-1",
metadata=[],
user="test-user",
collection="test-collection"
)
text = "The quick brown fox jumps over the lazy dog. " * 20
return TextDocument(
metadata=metadata,
text=text.encode("utf-8")
)
@pytest.fixture
def long_text_document():
"""Long document for testing multiple chunks."""
metadata = Metadata(
id="test-doc-long",
metadata=[],
user="test-user",
collection="test-collection"
)
# Create a long text that will definitely be chunked
text = " ".join([f"Sentence number {i}. This is part of a long document." for i in range(200)])
return TextDocument(
metadata=metadata,
text=text.encode("utf-8")
)
@pytest.fixture
def unicode_text_document():
"""Document with various unicode characters."""
metadata = Metadata(
id="test-doc-unicode",
metadata=[],
user="test-user",
collection="test-collection"
)
text = """
English: Hello World!
Chinese: 你好世界
Japanese: こんにちは世界
Korean: 안녕하세요 세계
Arabic: مرحبا بالعالم
Russian: Привет мир
Emoji: 🌍 🌎 🌏 😀 🎉
Math: π
Symbols: © ® £ ¥
"""
return TextDocument(
metadata=metadata,
text=text.encode("utf-8")
)
@pytest.fixture
def empty_text_document():
"""Empty document for edge case testing."""
metadata = Metadata(
id="test-doc-empty",
metadata=[],
user="test-user",
collection="test-collection"
)
return TextDocument(
metadata=metadata,
text=b""
)
@pytest.fixture
def mock_message(sample_text_document):
"""Mock message containing a document."""
msg = Mock()
msg.value.return_value = sample_text_document
return msg
@pytest.fixture(autouse=True)
def clear_metrics():
"""Clear metrics before each test to avoid duplicates."""
# Clear the chunk_metric class attribute if it exists
if hasattr(RecursiveChunker, 'chunk_metric'):
# Unregister from Prometheus registry first
try:
REGISTRY.unregister(RecursiveChunker.chunk_metric)
except KeyError:
pass # Already unregistered
delattr(RecursiveChunker, 'chunk_metric')
if hasattr(TokenChunker, 'chunk_metric'):
try:
REGISTRY.unregister(TokenChunker.chunk_metric)
except KeyError:
pass # Already unregistered
delattr(TokenChunker, 'chunk_metric')
yield
# Clean up after test as well
if hasattr(RecursiveChunker, 'chunk_metric'):
try:
REGISTRY.unregister(RecursiveChunker.chunk_metric)
except KeyError:
pass
delattr(RecursiveChunker, 'chunk_metric')
if hasattr(TokenChunker, 'chunk_metric'):
try:
REGISTRY.unregister(TokenChunker.chunk_metric)
except KeyError:
pass
delattr(TokenChunker, 'chunk_metric')
@pytest.fixture
def mock_async_processor_init():
"""Mock AsyncProcessor.__init__ to avoid taskgroup requirement."""
def init_mock(self, **kwargs):
# Set attributes that AsyncProcessor would normally set
self.config_handlers = []
self.specifications = []
self.flows = {}
self.id = kwargs.get('id', 'test-processor')
# Don't call the real __init__
with patch('trustgraph.base.async_processor.AsyncProcessor.__init__', init_mock):
yield