You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
from . . . symbols import ORTH
from . . . util import update_exc
from . . tokenizer_exceptions import BASE_EXCEPTIONS
_exc = { }
for raw in [
" a-e " ,
" a-o " ,
" a-i " ,
" a-a " ,
" co-a " ,
" co-e " ,
" co-i " ,
" co-o " ,
" da-a " ,
" da-e " ,
" da-i " ,
" da-o " ,
" pe-a " ,
" pe-e " ,
" pe-i " ,
" pe-o " ,
] :
for orth in [ raw , raw . capitalize ( ) ] :
_exc [ orth ] = [ { ORTH : orth } ]
# Prefix + prepositions with à (e.g. "sott'a-o")
for prep in [
" a-a " ,
" a-e " ,
" a-o " ,
" a-i " ,
] :
for prefix in [
" sott ' " ,
" sott’ " ,
" contr ' " ,
" contr’ " ,
" ch ' " ,
" ch’ " ,
" s ' " ,
" s’ " ,
] :
for prefix_orth in [ prefix , prefix . capitalize ( ) ] :
_exc [ prefix_orth + prep ] = [ { ORTH : prefix_orth } , { ORTH : prep } ]
TOKENIZER_EXCEPTIONS = update_exc ( BASE_EXCEPTIONS , _exc )
