mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
5ca7dd0f94
* Improve load_language_data helper * WIP: Add Lookups implementation * Start moving lemma data over to JSON * WIP: move data over for more languages * Convert more languages * Fix lemmatizer fixtures in tests * Finish conversion * Auto-format JSON files * Fix test for now * Make sure tables are stored on instance
42 lines
1.3 KiB
Python
42 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 .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
|
|
tag_map = TAG_MAP
|
|
resources = {"lemma_lookup": "lemma_lookup.json"}
|
|
|
|
|
|
class Indonesian(Language):
|
|
lang = "id"
|
|
Defaults = IndonesianDefaults
|
|
|
|
|
|
__all__ = ["Indonesian"]
|