mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-10-30 23:47:31 +03:00 
			
		
		
		
	* This PR adds Gujarati Language class along with - stop words * Add test for gu tokenizer
		
			
				
	
	
		
			19 lines
		
	
	
		
			299 B
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			19 lines
		
	
	
		
			299 B
		
	
	
	
		
			Python
		
	
	
	
	
	
| # coding: utf8
 | |
| from __future__ import unicode_literals
 | |
| 
 | |
| from .stop_words import STOP_WORDS
 | |
| 
 | |
| from ...language import Language
 | |
| 
 | |
| 
 | |
| class GujaratiDefaults(Language.Defaults):
 | |
|     stop_words = STOP_WORDS
 | |
| 
 | |
| 
 | |
| class Gujarati(Language):
 | |
|     lang = "gu"
 | |
|     Defaults = GujaratiDefaults
 | |
| 
 | |
| 
 | |
| __all__ = ["Gujarati"]
 |