mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-11-04 01:48:04 +03:00 
			
		
		
		
	* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
		
			
				
	
	
		
			66 lines
		
	
	
		
			1.2 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			66 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}
 |