mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 19:06:33 +03:00
951825532c
* Improved Dutch language resources and Dutch lemmatization * Fix conftest * Update punctuation.py * Auto-format * Format and fix tests * Remove unused test file * Re-add deleted test * removed redundant infix regex pattern for ','; note: brackets + simple hyphen remains * Cleaner lemmatization files
51 lines
1.5 KiB
Python
51 lines
1.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .tag_map import TAG_MAP
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
|
|
from .lemmatizer import LOOKUP, LEMMA_EXC, LEMMA_INDEX, RULES
|
|
from .lemmatizer.lemmatizer import DutchLemmatizer
|
|
|
|
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 DutchDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: 'nl'
|
|
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
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
|
|
@classmethod
|
|
def create_lemmatizer(cls, nlp=None):
|
|
rules = RULES
|
|
lemma_index = LEMMA_INDEX
|
|
lemma_exc = LEMMA_EXC
|
|
lemma_lookup = LOOKUP
|
|
return DutchLemmatizer(index=lemma_index,
|
|
exceptions=lemma_exc,
|
|
lookup=lemma_lookup,
|
|
rules=rules)
|
|
|
|
|
|
class Dutch(Language):
|
|
lang = 'nl'
|
|
Defaults = DutchDefaults
|
|
|
|
|
|
__all__ = ['Dutch']
|