mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
2f981d5af1
Remove corpus-specific tag maps from the language data for languages without custom tokenizers. For languages with custom word segmenters that also provide tags (Japanese and Korean), the tag maps for the custom tokenizers are kept as the default. The default tag maps for languages without custom tokenizers are now the default tag map from `lang/tag_map/py`, UPOS -> UPOS.
32 lines
1009 B
Python
32 lines
1009 B
Python
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_SUFFIXES
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
|
|
class PersianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
lex_attr_getters[LANG] = lambda text: "fa"
|
|
tokenizer_exceptions = update_exc(TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
class Persian(Language):
|
|
lang = "fa"
|
|
Defaults = PersianDefaults
|
|
|
|
|
|
__all__ = ["Persian"]
|