mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 08:26:21 +02:00
The metadata field (list of triples) in the pipeline Metadata class was redundant. Document metadata triples already flow directly from librarian to triple-store via emit_document_provenance() - they don't need to pass through the extraction pipeline. Additionally, chunker and PDF decoder were overwriting metadata to [] anyway, so any metadata passed through the pipeline was being discarded. Changes: - Remove metadata field from Metadata dataclass (schema/core/metadata.py) - Update all Metadata instantiations to remove metadata=[] parameter - Remove metadata handling from translators (document_loading, knowledge) - Remove metadata consumption from extractors (ontology, agent) - Update gateway serializers and import handlers - Update all unit, integration, and contract tests
149 lines
No EOL
4.2 KiB
Python
149 lines
No EOL
4.2 KiB
Python
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",
|
|
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",
|
|
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",
|
|
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",
|
|
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 |