mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 11:59:14 +03:00
e3222fdec9
* add syntax iterators for danish * add test noun chunks for danish syntax iterators * add contributor agreement * update da syntax iterators to remove nested chunks * add tests for da noun chunks * Fix test * add missing import * fix example * Prevent overlapping noun chunks Prevent overlapping noun chunks by tracking the end index of the previous noun chunk span. Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
37 lines
1.0 KiB
Python
37 lines
1.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .morph_rules import MORPH_RULES
|
|
from ..tag_map import TAG_MAP
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class DanishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "da"
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
morph_rules = MORPH_RULES
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
class Danish(Language):
|
|
lang = "da"
|
|
Defaults = DanishDefaults
|
|
|
|
|
|
__all__ = ["Danish"]
|