mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-23 12:29:18 +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.
87 lines
2.1 KiB
Python
87 lines
2.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
AUXILIARY_VERBS_IRREG = {
|
|
"suis": ("être",),
|
|
"es": ("être",),
|
|
"est": ("être",),
|
|
"sommes": ("être",),
|
|
"êtes": ("être",),
|
|
"sont": ("être",),
|
|
"étais": ("être",),
|
|
"étais": ("être",),
|
|
"était": ("être",),
|
|
"étions": ("être",),
|
|
"étiez": ("être",),
|
|
"étaient": ("être",),
|
|
"fus": ("être",),
|
|
"fut": ("être",),
|
|
"fûmes": ("être",),
|
|
"fûtes": ("être",),
|
|
"furent": ("être",),
|
|
"serai": ("être",),
|
|
"seras": ("être",),
|
|
"sera": ("être",),
|
|
"serons": ("être",),
|
|
"serez": ("être",),
|
|
"seront": ("être",),
|
|
"serais": ("être",),
|
|
"serait": ("être",),
|
|
"serions": ("être",),
|
|
"seriez": ("être",),
|
|
"seraient": ("être",),
|
|
"sois": ("être",),
|
|
"soit": ("être",),
|
|
"soyons": ("être",),
|
|
"soyez": ("être",),
|
|
"soient": ("être",),
|
|
"fusse": ("être",),
|
|
"fusses": ("être",),
|
|
"fût": ("être",),
|
|
"fussions": ("être",),
|
|
"fussiez": ("être",),
|
|
"fussent": ("être",),
|
|
"étant": ("être",),
|
|
"ai": ("avoir",),
|
|
"as": ("avoir",),
|
|
"a": ("avoir",),
|
|
"avons": ("avoir",),
|
|
"avez": ("avoir",),
|
|
"ont": ("avoir",),
|
|
"avais": ("avoir",),
|
|
"avait": ("avoir",),
|
|
"avions": ("avoir",),
|
|
"aviez": ("avoir",),
|
|
"avaient": ("avoir",),
|
|
"eus": ("avoir",),
|
|
"eut": ("avoir",),
|
|
"eûmes": ("avoir",),
|
|
"eûtes": ("avoir",),
|
|
"eurent": ("avoir",),
|
|
"aurai": ("avoir",),
|
|
"auras": ("avoir",),
|
|
"aura": ("avoir",),
|
|
"aurons": ("avoir",),
|
|
"aurez": ("avoir",),
|
|
"auront": ("avoir",),
|
|
"aurais": ("avoir",),
|
|
"aurait": ("avoir",),
|
|
"aurions": ("avoir",),
|
|
"auriez": ("avoir",),
|
|
"auraient": ("avoir",),
|
|
"aie": ("avoir",),
|
|
"aies": ("avoir",),
|
|
"ait": ("avoir",),
|
|
"ayons": ("avoir",),
|
|
"ayez": ("avoir",),
|
|
"aient": ("avoir",),
|
|
"eusse": ("avoir",),
|
|
"eusses": ("avoir",),
|
|
"eût": ("avoir",),
|
|
"eussions": ("avoir",),
|
|
"eussiez": ("avoir",),
|
|
"eussent": ("avoir",),
|
|
"ayant": ("avoir",)
|
|
}
|