mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-10-30 23:47:31 +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]
		
			
				
	
	
		
			67 lines
		
	
	
		
			1.2 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			67 lines
		
	
	
		
			1.2 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
| from ...attrs import LIKE_NUM
 | |
| 
 | |
| 
 | |
| _num_words = [
 | |
|     "zero",
 | |
|     "jeden",
 | |
|     "dwa",
 | |
|     "trzy",
 | |
|     "cztery",
 | |
|     "pięć",
 | |
|     "sześć",
 | |
|     "siedem",
 | |
|     "osiem",
 | |
|     "dziewięć",
 | |
|     "dziesięć",
 | |
|     "jedenaście",
 | |
|     "dwanaście",
 | |
|     "trzynaście",
 | |
|     "czternaście",
 | |
|     "pietnaście",
 | |
|     "szesnaście",
 | |
|     "siedemnaście",
 | |
|     "osiemnaście",
 | |
|     "dziewiętnaście",
 | |
|     "dwadzieścia",
 | |
|     "trzydzieści",
 | |
|     "czterdzieści",
 | |
|     "pięćdziesiąt",
 | |
|     "szcześćdziesiąt",
 | |
|     "siedemdziesiąt",
 | |
|     "osiemdziesiąt",
 | |
|     "dziewięćdziesiąt",
 | |
|     "sto",
 | |
|     "dwieście",
 | |
|     "trzysta",
 | |
|     "czterysta",
 | |
|     "pięćset",
 | |
|     "sześćset",
 | |
|     "siedemset",
 | |
|     "osiemset",
 | |
|     "dziewięćset",
 | |
|     "tysiąc",
 | |
|     "milion",
 | |
|     "miliard",
 | |
|     "bilion",
 | |
|     "biliard",
 | |
|     "trylion",
 | |
|     "tryliard",
 | |
|     "kwadrylion",
 | |
| ]
 | |
| 
 | |
| 
 | |
| def like_num(text):
 | |
|     text = text.replace(",", "").replace(".", "")
 | |
|     if text.isdigit():
 | |
|         return True
 | |
|     if text.count("/") == 1:
 | |
|         num, denom = text.split("/")
 | |
|         if num.isdigit() and denom.isdigit():
 | |
|             return True
 | |
|     if text.lower() in _num_words:
 | |
|         return True
 | |
|     return False
 | |
| 
 | |
| 
 | |
| LEX_ATTRS = {LIKE_NUM: like_num}
 |