mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
db55577c45
* 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]
65 lines
1.0 KiB
Python
65 lines
1.0 KiB
Python
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"영",
|
|
"공",
|
|
# Native Korean number system
|
|
"하나",
|
|
"둘",
|
|
"셋",
|
|
"넷",
|
|
"다섯",
|
|
"여섯",
|
|
"일곱",
|
|
"여덟",
|
|
"아홉",
|
|
"열",
|
|
"스물",
|
|
"서른",
|
|
"마흔",
|
|
"쉰",
|
|
"예순",
|
|
"일흔",
|
|
"여든",
|
|
"아흔",
|
|
# Sino-Korean number system
|
|
"일",
|
|
"이",
|
|
"삼",
|
|
"사",
|
|
"오",
|
|
"육",
|
|
"칠",
|
|
"팔",
|
|
"구",
|
|
"십",
|
|
"백",
|
|
"천",
|
|
"만",
|
|
"십만",
|
|
"백만",
|
|
"천만",
|
|
"일억",
|
|
"십억",
|
|
"백억",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
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 any(char.lower() in _num_words for char in text):
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|