explosion--spacy
wehub-resource-sync
f877c37fc6
tests / Test (windows-latest, 3.13) (push) Has been cancelled
tests / Test (windows-latest, 3.14) (push) Has been cancelled
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.10) (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.13) (push) Has been cancelled
tests / Test (macos-latest, 3.14) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.10) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.11) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.14) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
universe validation / Validate (push) Has been cancelled
77 行
1.1 KiB
Python
77 行
1.1 KiB
Python
from ...attrs import LIKE_NUM
|
|
|
|
# Source http://mylanguages.org/basque_numbers.php
|
|
|
|
|
|
_num_words = """
|
|
bat
|
|
bi
|
|
hiru
|
|
lau
|
|
bost
|
|
sei
|
|
zazpi
|
|
zortzi
|
|
bederatzi
|
|
hamar
|
|
hamaika
|
|
hamabi
|
|
hamahiru
|
|
hamalau
|
|
hamabost
|
|
hamasei
|
|
hamazazpi
|
|
Hemezortzi
|
|
hemeretzi
|
|
hogei
|
|
ehun
|
|
mila
|
|
milioi
|
|
""".split()
|
|
|
|
# source https://www.google.com/intl/ur/inputtools/try/
|
|
|
|
_ordinal_words = """
|
|
lehen
|
|
bigarren
|
|
hirugarren
|
|
laugarren
|
|
bosgarren
|
|
seigarren
|
|
zazpigarren
|
|
zortzigarren
|
|
bederatzigarren
|
|
hamargarren
|
|
hamaikagarren
|
|
hamabigarren
|
|
hamahirugarren
|
|
hamalaugarren
|
|
hamabosgarren
|
|
hamaseigarren
|
|
hamazazpigarren
|
|
hamazortzigarren
|
|
hemeretzigarren
|
|
hogeigarren
|
|
behin
|
|
""".split()
|
|
|
|
|
|
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 text in _num_words:
|
|
return True
|
|
if text in _ordinal_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|