mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
81564cc4e8
* adding e-KTP in tokenizer exceptions list * add exception token * removing lines with containing space as it won't matter since we use .split() method in the end, added new tokens in exception * add tokenizer exceptions list * combining base_norms with norm_exceptions * adding norm_exception * fix double key in lemmatizer * remove unused import on punctuation.py * reformat stop_words to reduce number of lines, improve readibility * updating tokenizer exception * implement is_currency for lang/id * adding orth_first_upper in tokenizer_exceptions * update the norm_exception list * remove bunch of abbreviations * adding contributors file
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
|
from .lemmatizer import LOOKUP
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class IndonesianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: 'id'
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
|
|
BASE_NORMS, NORM_EXCEPTIONS)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
lemma_lookup = LOOKUP
|
|
|
|
|
|
class Indonesian(Language):
|
|
lang = 'id'
|
|
Defaults = IndonesianDefaults
|
|
|
|
|
|
__all__ = ['Indonesian']
|