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
67 lines
2.7 KiB
Python
67 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.AudioDocument import AudioDocument
|
|
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")
|
|
|
|
|
|
def mock_get_embedding_engine():
|
|
class MockEngine:
|
|
tokenizer = None
|
|
|
|
return MockEngine()
|
|
|
|
|
|
GROUND_TRUTH = [
|
|
{"word_count": 57, "len_text": 353, "cut_type": "sentence_end"},
|
|
{"word_count": 58, "len_text": 358, "cut_type": "sentence_end"},
|
|
{"word_count": 41, "len_text": 219, "cut_type": "sentence_end"},
|
|
]
|
|
|
|
TEST_TEXT = """
|
|
"Mike, we need to talk about the payment processing service."
|
|
"Good timing. The board wants one-click checkout by end of quarter."
|
|
"That's exactly the problem. The service is held together with duct tape. One wrong move and—"
|
|
"Sarah, we've been over this. The market won't wait."
|
|
"And neither will a system collapse! The technical debt is crushing us. Every new feature takes twice as long as it should."
|
|
"Then work twice as hard. Our competitors—"
|
|
"Our competitors will laugh when our whole system goes down during Black Friday! We're talking about financial transactions here, not some blog comments section."
|
|
"Write up your concerns in a doc. Right now, we ship one-click."
|
|
"Then you'll ship it without me. I won't stake my reputation on a house of cards."
|
|
"Are you threatening to quit?"
|
|
"No, I'm threatening to be right. And when it breaks, I want it in writing that you chose this."
|
|
"The feature ships, Sarah. That's final.\""""
|
|
|
|
|
|
@patch.object(
|
|
chunk_by_sentence_module, "get_embedding_engine", side_effect=mock_get_embedding_engine
|
|
)
|
|
@pytest.mark.asyncio
|
|
async def test_AudioDocument(mock_engine):
|
|
document = AudioDocument(
|
|
id=uuid.uuid4(),
|
|
name="audio-dummy-test",
|
|
raw_data_location="",
|
|
external_metadata="",
|
|
mime_type="",
|
|
)
|
|
with patch.object(AudioDocument, "create_transcript", 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 = }'
|
|
)
|