wehub-resource-sync
c889a57b6b
Test Suites / Build CI Environment (push) Has been cancelled
Test Suites / Basic Tests (push) Has been cancelled
Test Suites / End-to-End Tests (push) Has been cancelled
Test Suites / CLI Tests (push) Has been cancelled
Test Suites / Slow End-to-End Tests (push) Has been cancelled
Test Suites / Graph Database Tests (push) Has been cancelled
Test Suites / Vector DB Tests (push) Has been cancelled
Test Suites / Temporal Graph Test (push) Has been cancelled
Test Suites / Search Test on Different DBs (push) Has been cancelled
Test Suites / Example Tests (push) Has been cancelled
Test Suites / Notebook Tests (push) Has been cancelled
Test Suites / OS and Python Tests Ubuntu (push) Has been cancelled
Test Suites / OS and Python Tests Extended (push) Has been cancelled
Test Suites / LLM Test Suite (push) Has been cancelled
Test Suites / S3 File Storage Test (push) Has been cancelled
Test Suites / Run Integration Tests (push) Has been cancelled
Test Suites / MCP Tests (push) Has been cancelled
Test Suites / Docker Compose Test (push) Has been cancelled
Test Suites / Docker CI test (push) Has been cancelled
Test Suites / Relational DB Migration Tests (push) Has been cancelled
Test Suites / Distributed Cognee Test (push) Has been cancelled
Test Suites / DB Examples Tests (push) Has been cancelled
Test Suites / Test Completion Status (push) Has been cancelled
Test Suites / Claude Code Review (push) Has been cancelled
Test Suites / basic checks (push) Has been cancelled
build | Build and Push Cognee MCP Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Scorecard supply-chain security / Scorecard analysis (push) Has been cancelled
build | Build and Push Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.11) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.12) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (kuzu, kuzu) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (neo4j, neo4j) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Examples (push) Has been cancelled
Weighted Edges Tests / Code Quality for Weighted Edges (push) Has been cancelled
50 lines
2.7 KiB
Python
50 lines
2.7 KiB
Python
import sys
|
|
import uuid
|
|
import pytest
|
|
from unittest.mock import patch
|
|
|
|
from cognee.modules.chunking.TextChunker import TextChunker
|
|
from cognee.modules.data.processing.document_types.ImageDocument import ImageDocument
|
|
from cognee.tests.integration.documents.AudioDocument_test import mock_get_embedding_engine
|
|
from cognee.tests.integration.documents.async_gen_zip import async_gen_zip
|
|
|
|
chunk_by_sentence_module = sys.modules.get("cognee.tasks.chunks.chunk_by_sentence")
|
|
|
|
|
|
GROUND_TRUTH = [
|
|
{"word_count": 51, "len_text": 298, "cut_type": "sentence_end"},
|
|
{"word_count": 62, "len_text": 369, "cut_type": "sentence_end"},
|
|
{"word_count": 44, "len_text": 294, "cut_type": "sentence_end"},
|
|
]
|
|
|
|
TEST_TEXT = """A dramatic confrontation unfolds as a red fox and river otter engage in an energetic wrestling match at the water's edge. The fox, teeth bared in a playful snarl, has its front paws locked with the otter's flippers as they roll through the shallow stream, sending water spraying in all directions. The otter, displaying its surprising agility on land, counters by twisting its sleek body and attempting to wrap itself around the fox's shoulders, its whiskered face inches from the fox's muzzle.
|
|
The commotion has attracted an audience: a murder of crows has gathered in the low branches, their harsh calls adding to the chaos as they hop excitedly from limb to limb. One particularly bold crow dive-bombs the wrestling pair, causing both animals to momentarily freeze mid-tussle, creating a perfect snapshot of suspended action—the fox's fur dripping wet, the otter's body coiled like a spring, and the crow's wings spread wide against the golden morning light."""
|
|
|
|
|
|
@patch.object(
|
|
chunk_by_sentence_module, "get_embedding_engine", side_effect=mock_get_embedding_engine
|
|
)
|
|
@pytest.mark.asyncio
|
|
async def test_ImageDocument(mock_engine):
|
|
document = ImageDocument(
|
|
id=uuid.uuid4(),
|
|
name="image-dummy-test",
|
|
raw_data_location="",
|
|
external_metadata="",
|
|
mime_type="",
|
|
)
|
|
with patch.object(ImageDocument, "transcribe_image", return_value=TEST_TEXT):
|
|
async for ground_truth, paragraph_data in async_gen_zip(
|
|
GROUND_TRUTH,
|
|
document.read(chunker_cls=TextChunker, max_chunk_size=64),
|
|
):
|
|
assert ground_truth["word_count"] == paragraph_data.chunk_size, (
|
|
f'{ground_truth["word_count"] = } != {paragraph_data.chunk_size = }'
|
|
)
|
|
assert ground_truth["len_text"] == len(paragraph_data.text), (
|
|
f'{ground_truth["len_text"] = } != {len(paragraph_data.text) = }'
|
|
)
|
|
assert ground_truth["cut_type"] == paragraph_data.cut_type, (
|
|
f'{ground_truth["cut_type"] = } != {paragraph_data.cut_type = }'
|
|
)
|