mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
e0cf4796a5
* Add default to util.get_entry_point * Tidy up entry points * Read lookups from entry points * Remove lookup tables and related tests * Add lookups install option * Remove lemmatizer tests * Remove logic to process language data files * Update setup.cfg
36 lines
1.0 KiB
Python
36 lines
1.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
|
|
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
|
|
from .tag_map import TAG_MAP
|
|
|
|
# Lemma data note:
|
|
# Original pairs downloaded from http://www.lexiconista.com/datasets/lemmatization/
|
|
# Replaced characters using cedillas with the correct ones (ș and ț)
|
|
|
|
|
|
class RomanianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "ro"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
tag_map = TAG_MAP
|
|
|
|
|
|
class Romanian(Language):
|
|
lang = "ro"
|
|
Defaults = RomanianDefaults
|
|
|
|
|
|
__all__ = ["Romanian"]
|