mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-11-01 00:17:44 +03:00 
			
		
		
		
	* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
		
			
				
	
	
		
			17 lines
		
	
	
		
			510 B
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			17 lines
		
	
	
		
			510 B
		
	
	
	
		
			Python
		
	
	
	
	
	
| import pytest
 | ||
| 
 | ||
| 
 | ||
| @pytest.mark.parametrize(
 | ||
|     "text,norms,lemmas",
 | ||
|     [
 | ||
|         ("о.г.", ["ове године"], ["ова година"]),
 | ||
|         ("чет.", ["четвртак"], ["четвртак"]),
 | ||
|         ("гђа", ["госпођа"], ["госпођа"]),
 | ||
|         ("ил'", ["или"], ["или"]),
 | ||
|     ],
 | ||
| )
 | ||
| def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms, lemmas):
 | ||
|     tokens = sr_tokenizer(text)
 | ||
|     assert len(tokens) == 1
 | ||
|     assert [token.norm_ for token in tokens] == norms
 |