spaCy/spacy/lang/nb/__init__.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

44 lines
1.4 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .morph_rules import MORPH_RULES
from .lemmatizer import LEMMA_EXC, LEMMA_INDEX, LOOKUP, LEMMA_RULES
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from .tag_map import TAG_MAP
from .morph_rules import MORPH_RULES
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
# Borrowing french syntax parser because both languages use
# universal dependencies for tagging/parsing.
# Read here for more:
# https://github.com/explosion/spaCy/pull/1882#issuecomment-361409573
from .syntax_iterators import SYNTAX_ITERATORS
class NorwegianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'nb'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
morph_rules = MORPH_RULES
tag_map = TAG_MAP
lemma_lookup = LOOKUP
lemma_exc = LEMMA_EXC
lemma_index = LEMMA_INDEX
lemma_rules = LEMMA_RULES
syntax_iterators = SYNTAX_ITERATORS
class Norwegian(Language):
lang = 'nb'
Defaults = NorwegianDefaults
__all__ = ['Norwegian']