spaCy/spacy/lang/nb/lemmatizer/_lemma_rules.py
katarkor 5ca853bee0 changed tag_map, morph_rules, lemmatizer for Norwegian (#2565)
* changed tag_map, morph_rules, lemmatizer for Norwegian

* Move unicode declaration up

Hopefully fixes test failure on Python 2

* Update CONTRIBUTOR_AGREEMENT.md

* Move unicode declarations

Hopefully fixes test this time

* Revert "Merge remote-tracking branch 'origin/patch-1'"

This reverts commit f5ccd5dd0d, reversing
changes made to dd07e180ea.

* Update contributor agreement [ci skip]
2018-07-19 19:38:24 +02:00

32 lines
588 B
Python

# 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
["es", "e"], #vaskes -> vaske
["te", "e"], #stekte -> steke
["år", "å"] #får -> få
]
PUNCT_RULES = []