mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-08-29 04:26:20 +00:00
KaifAhmad1
58707ff721
- Robust ID extraction in CentralityCalculator, CommunityDetector, and ConnectivityAnalyzer - Support for direct Entity objects and dictionaries as node identifiers - Improved Entity hashability in utils/types.py - Added integration test to verify fix and prevent regression
54 lines
2.2 KiB
Python
54 lines
2.2 KiB
Python
import unittest
|
|
from unittest.mock import MagicMock, patch
|
|
from semantica.split.splitter import TextSplitter
|
|
from semantica.split.semantic_chunker import SemanticChunker, Chunk
|
|
|
|
class TestSplitter(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
self.mock_logger = MagicMock()
|
|
self.logger_patcher = patch('semantica.split.splitter.get_logger', return_value=self.mock_logger)
|
|
self.logger_patcher_sc = patch('semantica.split.semantic_chunker.get_logger', return_value=self.mock_logger)
|
|
self.tracker_patcher = patch('semantica.split.semantic_chunker.get_progress_tracker', return_value=MagicMock())
|
|
|
|
self.logger_patcher.start()
|
|
self.logger_patcher_sc.start()
|
|
self.tracker_patcher.start()
|
|
|
|
def tearDown(self):
|
|
self.logger_patcher.stop()
|
|
self.logger_patcher_sc.stop()
|
|
self.tracker_patcher.stop()
|
|
|
|
def test_text_splitter_initialization(self):
|
|
splitter = TextSplitter(method="recursive", chunk_size=500, chunk_overlap=50)
|
|
self.assertEqual(splitter.chunk_size, 500)
|
|
self.assertEqual(splitter.chunk_overlap, 50)
|
|
self.assertEqual(splitter.methods, ["recursive"])
|
|
|
|
def test_text_splitter_list_methods(self):
|
|
splitter = TextSplitter(method=["recursive", "token"])
|
|
self.assertEqual(splitter.methods, ["recursive", "token"])
|
|
|
|
@patch('semantica.split.semantic_chunker.spacy')
|
|
def test_semantic_chunker_initialization(self, mock_spacy):
|
|
# Mock spacy.load to return a mock nlp object
|
|
mock_nlp = MagicMock()
|
|
mock_spacy.load.return_value = mock_nlp
|
|
|
|
# We need to ensure SPACY_AVAILABLE is True for this test context if possible,
|
|
# but it is imported at module level.
|
|
# If spacy is not installed, it sets SPACY_AVAILABLE = False.
|
|
# We might need to patch the module attribute or just test fallback if spacy missing.
|
|
|
|
chunker = SemanticChunker(chunk_size=100)
|
|
self.assertEqual(chunker.chunk_size, 100)
|
|
|
|
def test_chunk_dataclass(self):
|
|
chunk = Chunk(text="test", start_index=0, end_index=4, metadata={"key": "value"})
|
|
self.assertEqual(chunk.text, "test")
|
|
self.assertEqual(chunk.metadata["key"], "value")
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|