spaCy/spacy/lang/fr/lemmatizer/_adp_irreg.py

25 lines
419 B
Python

# coding: utf8
from __future__ import unicode_literals
ADP_IRREG = {
"a": ("à",),
"apr.": ("après",),
"aux": ("à",),
"av.": ("avant",),
"avt": ("avant",),
"cf.": ("cf",),
"conf.": ("cf",),
"confer": ("cf",),
"d'": ("de",),
"des": ("de",),
"du": ("de",),
"jusqu'": ("jusque",),
"pdt": ("pendant",),
"+": ("plus",),
"pr": ("pour",),
"/": ("sur",),
"versus": ("vs",),
"vs.": ("vs",)
}