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
61 lines
2.1 KiB
Python
61 lines
2.1 KiB
Python
import os
|
|
import sys
|
|
import uuid
|
|
import pytest
|
|
import pathlib
|
|
from unittest.mock import patch
|
|
|
|
from cognee.modules.chunking.TextChunker import TextChunker
|
|
from cognee.modules.data.processing.document_types.TextDocument import TextDocument
|
|
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 = {
|
|
"code.txt": [
|
|
{"word_count": 252, "len_text": 1376, "cut_type": "paragraph_end"},
|
|
{"word_count": 56, "len_text": 481, "cut_type": "paragraph_end"},
|
|
],
|
|
"Natural_language_processing.txt": [
|
|
{"word_count": 128, "len_text": 984, "cut_type": "paragraph_end"},
|
|
{"word_count": 1, "len_text": 1, "cut_type": "paragraph_end"},
|
|
],
|
|
}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"input_file,chunk_size",
|
|
[("code.txt", 256), ("Natural_language_processing.txt", 128)],
|
|
)
|
|
@patch.object(
|
|
chunk_by_sentence_module, "get_embedding_engine", side_effect=mock_get_embedding_engine
|
|
)
|
|
@pytest.mark.asyncio
|
|
async def test_TextDocument(mock_engine, input_file, chunk_size):
|
|
test_file_path = os.path.join(
|
|
pathlib.Path(__file__).parent.parent.parent, "test_data", input_file
|
|
)
|
|
document = TextDocument(
|
|
id=uuid.uuid4(),
|
|
name=input_file,
|
|
raw_data_location=test_file_path,
|
|
external_metadata="",
|
|
mime_type="",
|
|
)
|
|
|
|
async for ground_truth, paragraph_data in async_gen_zip(
|
|
GROUND_TRUTH[input_file],
|
|
document.read(chunker_cls=TextChunker, max_chunk_size=chunk_size),
|
|
):
|
|
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 = }'
|
|
)
|