spaCy/spacy/lang/nb/lemmatizer/_lemma_rules.py

# coding: utf8
from __future__ import unicode_literals


ADJECTIVE_RULES = [
    ["e", ""],  # pene -> pen
    ["ere", ""],  # penere -> pen
    ["est", ""],  # penest -> pen
    ["este", ""],  # peneste -> pen
]


NOUN_RULES = [
    ["en", "e"],  # hansken -> hanske
    ["a", "e"],  # veska -> veske
    ["et", ""],  # dyret -> dyr
    ["er", "e"],  # hasker -> hanske
    ["ene", "e"],  # veskene -> veske
]


VERB_RULES = [
    ["er", "e"],  # vasker -> vaske
    ["et", "e"],  # vasket -> vaske
    ["a", "e"],  # vaska -> vaske
    ["es", "e"],  # vaskes -> vaske
    ["te", "e"],  # stekte -> steke
    ["år", "å"],  # får -> få
]


PUNCT_RULES = []