spaCy/spacy/lang/tr/__init__.py
Duygu Altinok 0e55f806dd
Turkish tokenization improvements (#6268)
* added single and paired orth variants

* added token match

* added long text tokenization test

* inverted init

* normalized lemmas to lowercase

* more abbrevs

* tests for ordinals and abbrevs

* separated period abbvrevs to another list

* fiex typo

* added ordinal and abbrev tests

* added number tests for dates

* minor refinement

* added inflected abbrevs regex

* added percentage and inflection

* cosmetics

* added token match

* added url inflection tests

* excluded url tokens from custom pattern

* removed url match import
2020-10-29 09:43:17 +01:00

38 lines
1.1 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from .lex_attrs import LEX_ATTRS
from .morph_rules import MORPH_RULES
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 TurkishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: "tr"
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
token_match = TOKEN_MATCH
syntax_iterators = SYNTAX_ITERATORS
morph_rules = MORPH_RULES
class Turkish(Language):
lang = "tr"
Defaults = TurkishDefaults
__all__ = ["Turkish"]