explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-05 13:43:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

enable syntax iterator and lemma lookup

Browse Source
This commit is contained in:
Jim Geovedi 2017-07-27 10:51:15 +07:00
parent 24a8c8bf28
commit bbc75da38d
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/lang/id/__init__.py
View File

@ -5,10 +5,13 @@ from .stop_words import STOP_WORDS
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .norm_exceptions import NORM_EXCEPTIONS from .norm_exceptions import NORM_EXCEPTIONS
from .lemmatizer import LOOKUP
from .lex_attrs import LEX_ATTRS from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from ..tokenizer_exceptions import BASE_EXCEPTIONS from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language from ...language import Language
from ...lemmatizerlookup import Lemmatizer
from ...attrs import LANG from ...attrs import LANG
from ...util import update_exc from ...util import update_exc
@ -25,6 +28,11 @@ class IndonesianDefaults(Language.Defaults):
prefixes = tuple(TOKENIZER_PREFIXES) prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES) suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(TOKENIZER_INFIXES) infixes = tuple(TOKENIZER_INFIXES)
syntax_iterators = dict(SYNTAX_ITERATORS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class Indonesian(Language): class Indonesian(Language):