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
32 lines
1.2 KiB
Python
32 lines
1.2 KiB
Python
import unittest
|
|
from semantica.normalize.language_detector import LanguageDetector
|
|
|
|
class TestLanguageDetector(unittest.TestCase):
|
|
def setUp(self):
|
|
self.detector = LanguageDetector()
|
|
|
|
def test_detect_language(self):
|
|
# English
|
|
self.assertEqual(self.detector.detect("This is a simple English sentence."), "en")
|
|
# French
|
|
self.assertEqual(self.detector.detect("Ceci est une phrase française simple."), "fr")
|
|
# German
|
|
self.assertEqual(self.detector.detect("Dies ist ein einfacher deutscher Satz."), "de")
|
|
|
|
def test_detect_short_text(self):
|
|
# Should return default for very short text
|
|
self.assertEqual(self.detector.detect("Hi"), "en")
|
|
|
|
def test_detect_with_confidence(self):
|
|
lang, conf = self.detector.detect_with_confidence("This is definitely an English sentence.")
|
|
self.assertEqual(lang, "en")
|
|
self.assertGreater(conf, 0.5)
|
|
|
|
def test_get_language_name(self):
|
|
self.assertEqual(self.detector.get_language_name("en"), "English")
|
|
self.assertEqual(self.detector.get_language_name("fr"), "French")
|
|
self.assertEqual(self.detector.get_language_name("xx"), "XX")
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|