mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-23 12:29:18 +03:00
2457318b7a
* updating rules and vocabulary for French lemmatization of verbs * updating the file with French auxiliary verb * updating rules and vocabulary for French lemmatization of verbs * adding contributor agreement for amperinet * adding rules for words with inclusive parentheses wrongly tokenized
65 lines
1.1 KiB
Python
65 lines
1.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
ADJECTIVE_RULES = [
|
|
["s", ""],
|
|
["e", ""],
|
|
["es", ""]
|
|
]
|
|
|
|
|
|
NOUN_RULES = [
|
|
["s", ""]
|
|
]
|
|
|
|
|
|
VERB_RULES = [
|
|
["é", "er"],
|
|
["és", "er"],
|
|
["ée", "er"],
|
|
["ées", "er"],
|
|
["é", "er"],
|
|
["es", "er"],
|
|
["ons", "er"],
|
|
["ez", "er"],
|
|
["ent", "er"],
|
|
["ais", "er"],
|
|
["ait", "er"],
|
|
["ions", "er"],
|
|
["iez", "er"],
|
|
["aient", "er"],
|
|
["ai", "er"],
|
|
["as", "er"],
|
|
["a", "er"],
|
|
["âmes", "er"],
|
|
["âtes", "er"],
|
|
["èrent", "er"],
|
|
["erai", "er"],
|
|
["eras", "er"],
|
|
["era", "er"],
|
|
["erons", "er"],
|
|
["erez", "er"],
|
|
["eront", "er"],
|
|
["erais", "er"],
|
|
["erait", "er"],
|
|
["erions", "er"],
|
|
["eriez", "er"],
|
|
["eraient", "er"],
|
|
["asse", "er"],
|
|
["asses", "er"],
|
|
["ât", "er"],
|
|
["assions", "er"],
|
|
["assiez", "er"],
|
|
["assent", "er"],
|
|
["ant", "er"],
|
|
["ante", "er"],
|
|
["ants", "er"],
|
|
["antes", "er"],
|
|
|
|
["u(er", "u"],
|
|
["és(ées", "er"],
|
|
["é()e", "er"],
|
|
["é()", "er"],
|
|
]
|