mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +03:00
33 lines
1.5 KiB
Python
33 lines
1.5 KiB
Python
|
from ...attrs import LIKE_NUM
|
||
|
|
|
||
|
|
# reference 1: https://en.wikipedia.org/wiki/Tibetan_numerals
|
||
|
|
|
||
|
|
_num_words = [
|
||
|
|
"ཀླད་ཀོར་",
|
||
|
|
"གཅིག་", "གཉིས་", "གསུམ་", "བཞི་", "ལྔ་", "དྲུག་", "བདུན་", "བརྒྱད་", "དགུ་", "བཅུ་",
|
||
|
|
"བཅུ་གཅིག་", "བཅུ་གཉིས་", "བཅུ་གསུམ་", "བཅུ་བཞི་", "བཅུ་ལྔ་", "བཅུ་དྲུག་", "བཅུ་བདུན་", "བཅུ་པརྒྱད", "བཅུ་དགུ་", "ཉི་ཤུ་",
|
||
|
|
"སུམ་ཅུ", "བཞི་བཅུ", "ལྔ་བཅུ", "དྲུག་ཅུ", "བདུན་ཅུ", "བརྒྱད་ཅུ", "དགུ་བཅུ", "བརྒྱ་",
|
||
|
|
"སྟོང་", "ཁྲི་", "ས་ཡ་", " བྱེ་བ་", "དུང་ཕྱུར་", "ཐེར་འབུམ་", "ཐེར་འབུམ་ཆེན་པོ་", "ཁྲག་ཁྲིག་", "ཁྲག་ཁྲིག་ཆེན་པོ་",
|
||
|
|
]
|
||
|
|
|
||
|
|
|
||
|
|
def like_num(text):
|
||
|
|
"""
|
||
|
|
Check if text resembles a number
|
||
|
|
"""
|
||
|
|
if text.startswith(("+", "-", "±", "~")):
|
||
|
|
text = text[1:]
|
||
|
|
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 in _num_words:
|
||
|
|
return True
|
||
|
|
return False
|
||
|
|
|
||
|
|
|
||
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|