43 lines
1.1 KiB
Python
43 lines
1.1 KiB
Python
# ruff: noqa: E501
|
|
|
|
import unittest
|
|
|
|
from embedchain.chunkers.text import TextChunker
|
|
|
|
|
|
class TestTextChunker(unittest.TestCase):
|
|
def test_chunks(self):
|
|
"""
|
|
Test the chunks generated by TextChunker.
|
|
# TODO: Not a very precise test.
|
|
"""
|
|
chunker_config = {
|
|
"chunk_size": 10,
|
|
"chunk_overlap": 0,
|
|
"length_function": len,
|
|
}
|
|
chunker = TextChunker(config=chunker_config)
|
|
text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit."
|
|
|
|
result = chunker.create_chunks(MockLoader(), text)
|
|
|
|
documents = result["documents"]
|
|
|
|
self.assertGreaterEqual(len(documents), 5)
|
|
|
|
# Additional test cases can be added to cover different scenarios
|
|
|
|
|
|
class MockLoader:
|
|
def load_data(self, src):
|
|
"""
|
|
Mock loader that returns a list of data dictionaries.
|
|
Adjust this method to return different data for testing.
|
|
"""
|
|
return [
|
|
{
|
|
"content": src,
|
|
"meta_data": {"url": "none"},
|
|
}
|
|
]
|