Reorganise Italian language data

This commit is contained in:
ines 2017-05-08 15:50:17 +02:00
parent 1bbfa14436
commit 51a389d3bb
2 changed files with 14 additions and 12 deletions

View File

@ -1,12 +1,15 @@
# coding: utf8 # coding: utf8
from __future__ import unicode_literals, print_function from __future__ import unicode_literals
from .stop_words import STOP_WORDS
from .lemmatizer import LOOKUP
from ..language_data import BASE_EXCEPTIONS
from ..language import Language from ..language import Language
from ..attrs import LANG
from .language_data import *
from ..lemmatizerlookup import Lemmatizer from ..lemmatizerlookup import Lemmatizer
from .lemmatization import LOOK_UP from ..attrs import LANG
from ..util import update_exc
class Italian(Language): class Italian(Language):
lang = 'it' lang = 'it'
@ -15,13 +18,12 @@ class Italian(Language):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters) lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'it' lex_attr_getters[LANG] = lambda text: 'it'
tokenizer_exceptions = TOKENIZER_EXCEPTIONS tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = STOP_WORDS stop_words = set(STOP_WORDS)
@classmethod @classmethod
def create_lemmatizer(cls, nlp=None): def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOK_UP) return Lemmatizer(LOOKUP)
__all__ = ['Italian']
EXPORT = Italian

View File

@ -1,7 +1,7 @@
# coding: utf8 # coding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
LOOK_UP = { LOOKUP = {
"'ndranghete": "'ndrangheta", "'ndranghete": "'ndrangheta",
"'ndrine": "'ndrina", "'ndrine": "'ndrina",
"a-storica": "a-storico", "a-storica": "a-storico",
@ -333684,4 +333684,4 @@ LOOK_UP = {
"èlites": "èlite", "èlites": "èlite",
"ère": "èra", "ère": "èra",
"élites": "élite" "élites": "élite"
} }