spaCy/spacy/lang/id/__init__.py
jeannefukumaru 6cdb7b2e04 added tag_map for indonesian (#3515)
* added tag_map for indonesian

* changed tag map from .py to .txt to see if tests pass

* added symbols import

* added utf8 encoding flag

* added missing SCONJ symbol

* Auto-format

* Remove unused imports

* Make tag map available in Indonesian defaults
2019-04-01 12:27:48 +02:00

43 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 .tag_map import TAG_MAP
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
tag_map = TAG_MAP
class Indonesian(Language):
lang = "id"
Defaults = IndonesianDefaults
__all__ = ["Indonesian"]