mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
36514b5762
<!--- Provide a general summary of your changes in the title. --> ## Description <!--- Use this section to describe your changes. If your changes required testing, include information about the testing environment and the tests you ran. If your test fixes a bug reported in an issue, don't forget to include the issue number. If your PR is still a work in progress, that's totally fine – just include a note to let us know. --> Add a rule-based French Lemmatizer following the english one and the excellent PR for [greek language optimizations](https://github.com/explosion/spaCy/pull/2558) to adapt the Lemmatizer class. ### Types of change <!-- What type of change does your PR cover? Is it a bug fix, an enhancement or new feature, or a change to the documentation? --> - Lemma dictionary used can be found [here](http://infolingu.univ-mlv.fr/DonneesLinguistiques/Dictionnaires/telechargement.html), I used the XML version. - Add several files containing exhaustive list of words for each part of speech - Add some lemma rules - Add POS that are not checked in the standard Lemmatizer, i.e PRON, DET, ADV and AUX - Modify the Lemmatizer class to check in lookup table as a last resort if POS not mentionned - Modify the lemmatize function to check in lookup table as a last resort - Init files are updated so the model can support all the functionalities mentioned above - Add words to tokenizer_exceptions_list.py in respect to regex used in tokenizer_exceptions.py ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [X] I have submitted the spaCy Contributor Agreement. - [X] I ran the tests, and all new and existing tests passed. - [X] My changes don't require a change to the documentation, or if they do, I've added all required information.
50 lines
1.6 KiB
Python
50 lines
1.6 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
|
|
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from .tag_map import TAG_MAP
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .lemmatizer import LEMMA_RULES, LEMMA_INDEX, LEMMA_EXC, LOOKUP
|
|
from .lemmatizer.lemmatizer import FrenchLemmatizer
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
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 FrenchDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: 'fr'
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
token_match = TOKEN_MATCH
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
@classmethod
|
|
def create_lemmatizer(cls, nlp=None):
|
|
lemma_rules = LEMMA_RULES
|
|
lemma_index = LEMMA_INDEX
|
|
lemma_exc = LEMMA_EXC
|
|
lemma_lookup = LOOKUP
|
|
return FrenchLemmatizer(index=lemma_index, exceptions=lemma_exc,
|
|
rules=lemma_rules, lookup=lemma_lookup)
|
|
|
|
|
|
class French(Language):
|
|
lang = 'fr'
|
|
Defaults = FrenchDefaults
|
|
|
|
|
|
__all__ = ['French']
|