mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
e626a011cc
* Enable lex_attrs on Finnish * Copy the Danish tokenizer rules to Finnish Specifically, don't break hyphenated compound words * Contributor agreement * A new file for Finnish tokenizer rules instead of including the Danish ones
35 lines
1016 B
Python
35 lines
1016 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class FinnishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "fi"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Finnish(Language):
|
|
lang = "fi"
|
|
Defaults = FinnishDefaults
|
|
|
|
|
|
__all__ = ["Finnish"]
|